Article(id=1327011621316178824, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330577, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1689523200000, receivedDateStr=2023-07-17, revisedDate=1710345600000, revisedDateStr=2024-03-14, acceptedDate=1716480000000, acceptedDateStr=2024-05-24, onlineDate=1794313825205, onlineDateStr=2026-11-10, pubDate=1735660800000, pubDateStr=2025-01-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794313825205, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794313825205, creator=13701087609, updateTime=1794313825205, updator=13701087609, issue=Issue{id=1327011511924535414, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='1', pageStart='1', pageEnd='283', issueExtLink='null', onlineDate='null', pubDate='1735660800000', pubDateStr='2025-01-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794313799123, creator='13701087609', updateTime=1794376660021, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275170160554491, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275170160554492, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=207, endPage=231, ext={EN=ArticleExt(id=1327011621546865545, articleId=1327011621316178824, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of Machine Learning-Based KPI Anomaly Detection on Internet-Based Services, columnId=1325493671541474142, journalTitle=Journal of Computer Research and Development, columnName=Network and Information Security, runingTitle=null, highlight=null, articleAbstract=
Key performance indicator (KPI) anomaly detection is a fundamental technology for artificial intelligence for IT operations (AIOps) of Internet-based services. To improve the efficiency and accuracy of KPI anomaly detection, machine learning-based KPI anomaly detection has become a hotspot in both academia and industry recently. Through synthetically analyzing prior arts in this field, we first provide a technical framework of KPI anomaly detection for Internet-based services. Then, from the perspective of mining KPI’s dependency patterns in different domains (including time domain, metric domain and entity domain), we explore the motivation for model selection of KPI anomaly detection on three KPI types (including univariate KPI, multivariate KPIs and matrix-variate KPIs). Furthermore, guided by the detection performance objectives, we elaborate on KPI anomaly detection techniques from two perspectives: accuracy-centric anomaly detection techniques which focus on how to improve the accuracy of KPI anomaly detection models and multi-objective balancing-centric anomaly detection techniques which focus on how to balance theoretical performance with actual application objectives. Finally, we sort out five challenges on machine learning-based KPI anomaly detection, including KPI monitoring and KPI pre-processing, generality of the model, interpretability of the model, alarm management of anomalies, and limitations of KPI anomaly detection; and we also point out the corresponding potential research directions.
, authors=Shuyi Shang
1, 2, Hongjia Li
1, *, Chen Song
1, Zhitong Lu
1, Liming Wang
1, Zhen Xu
1, authorsList=Shuyi Shang, Hongjia Li, Chen Song, Zhitong Lu, Liming Wang, Zhen Xu, authorCompany=null, correspAuthors=Hongjia Li, authorNote=
born in 1996. PhD candidate. Her main research interests include time series data mining, machine learning, and AIOps
born in 1981. PhD, associate professor. His main research interests include cyberspace security, 5G/6G network, and edge intelligence computing
born in 1984. PhD, senior engineer. Her main research interest includes cyber security
born in 1993. Master, engineer. Her main research interests include image adversarial learning and information security
born in 1978. PhD, professorate senior engineer. Member of CCF. His main research interests include cloud security,date security, and wireless security
born in 1976. PhD, professorate senior engineer. Member of CCF. His main research interests include trusted computing, cyber security, and system security
, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327011625279796131, articleId=1327011621316178824, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=互联网服务场景下基于机器学习的KPI异常检测综述, columnId=1325493672690713440, journalTitle=计算机研究与发展, columnName=网络与信息安全, runingTitle=null, highlight=null, articleAbstract=
关键性能指标(key performance indicator,KPI)异常检测技术是互联网服务智能运维的基础支撑技术. 为了提升KPI异常检测的效率与准确性,基于机器学习的KPI异常检测技术成为近年来学术界与工业界的研究热点. 在综合分析相关研究的基础上,给出了面向互联网服务的KPI异常检测技术框架. 然后,分别针对单变量KPI、多变量KPI和矩阵变量KPI,从挖掘KPI在不同维度域(时间域、度量域、实体域)的依赖模式的角度出发,探讨了用于KPI异常检测的机器学习模型的选择动机. 进一步地,以检测性能目标为导向,详细介绍了以准确性目标为核心的KPI异常检测技术(关注如何提升KPI异常检测模型的准确性)和以多目标平衡为核心的KPI异常检测技术(关注如何平衡理论性能与实际应用目标间的关系). 最后,梳理了基于机器学习的KPI异常检测技术在KPI监控及预处理、模型通用性、模型可解释性、异常告警管理以及KPI异常检测任务自身局限性5个方面的挑战,同时指出了与之对应的潜在研究方向.
, authors=尚书一
1, 2, 李宏佳
1, *, 宋晨
1, 卢至彤
1, 王利明
1, 徐震
1, authorsList=尚书一, 李宏佳, 宋晨, 卢至彤, 王利明, 徐震, authorCompany=null, correspAuthors=李宏佳, authorNote=
 |
1996年生. 博士研究生. 主要研究方向为时序数据挖掘、机器学习、智能运维 |
 |
1981年生. 博士,副研究员. 主要研究方向为网络空间安全、5G/6G网络、边缘智能计算 |
 |
1984年生. 博士,高级工程师. 主要研究方向为网络安全 |
 |
1993年生. 硕士,工程师. 主要研究方向为图像对抗学习、信息安全 |
 |
1978年生. 博士,正高级工程师. CCF会员. 主要研究方向为云安全、数据安全、无线安全 |
 |
1976年生. 博士,正高级工程师. CCF会员. 主要研究方向为可信计算、网络安全、系统安全 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=7Ef7d4Imhv/dtmV1hlrBbQ==, magXml=wvoPa6YvoyVLPeZAltczfA==, pdfUrl=null, pdf=soRfHyE52ffDLxMyRJ1HsQ==, pdfFileSize=2571494, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=DhqYqjM7RaukRifX5r7Obw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ZeXw0zNhC1jfN6+UiCKv+A==, mapNumber=null, fund=null)}, authors=[Author(id=1327012284720853943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=shangshuyi@iie.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012284863460282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012284720853943, language=EN, stringName=Shuyi Shang, firstName=Shuyi, middleName=null, lastName=Shang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093
2School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1996. PhD candidate. Her main research interests include time series data mining, machine learning, and AIOps
"}, bioImg=null, bioContent=
born in 1996. PhD candidate. Her main research interests include time series data mining, machine learning, and AIOps
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012284943152059, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012284720853943, language=CN, stringName=尚书一, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1中国科学院信息工程研究所 北京 100093
2中国科学院大学网络空间安全学院 北京 100049, bio={"img":"QVtdmZtAvoVVPKoXwpvnpw==","content":"
1996年生. 博士研究生. 主要研究方向为时序数据挖掘、机器学习、智能运维
"}, bioImg=QVtdmZtAvoVVPKoXwpvnpw==, bioContent=
1996年生. 博士研究生. 主要研究方向为时序数据挖掘、机器学习、智能运维
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)]), AuthorCompany(id=1327012284465001395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=2, ext=[AuthorCompanyExt(id=1327012284544693172, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284465001395, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327012284599219125, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284465001395, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学网络空间安全学院 北京 100049)])]), Author(id=1327012285035426749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lihongjia@iie.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327012285165450177, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285035426749, language=EN, stringName=Hongjia Li, firstName=Hongjia, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, bio={"content":"
born in 1981. PhD, associate professor. His main research interests include cyberspace security, 5G/6G network, and edge intelligence computing
"}, bioImg=null, bioContent=
born in 1981. PhD, associate professor. His main research interests include cyberspace security, 5G/6G network, and edge intelligence computing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012285316445122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285035426749, language=CN, stringName=李宏佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1中国科学院信息工程研究所 北京 100093, bio={"img":"5z0Nkspyjm1BzKEnUDlrKQ==","content":"
1981年生. 博士,副研究员. 主要研究方向为网络空间安全、5G/6G网络、边缘智能计算
"}, bioImg=5z0Nkspyjm1BzKEnUDlrKQ==, bioContent=
1981年生. 博士,副研究员. 主要研究方向为网络空间安全、5G/6G网络、边缘智能计算
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)])]), Author(id=1327012285438079940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012285521966022, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285438079940, language=EN, stringName=Chen Song, firstName=Chen, middleName=null, lastName=Song, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, bio={"content":"
born in 1984. PhD, senior engineer. Her main research interest includes cyber security
"}, bioImg=null, bioContent=
born in 1984. PhD, senior engineer. Her main research interest includes cyber security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012285589074887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285438079940, language=CN, stringName=宋晨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1中国科学院信息工程研究所 北京 100093, bio={"img":"p5ffRAylBJgZ/1HQgSLfRg==","content":"
1984年生. 博士,高级工程师. 主要研究方向为网络安全
"}, bioImg=p5ffRAylBJgZ/1HQgSLfRg==, bioContent=
1984年生. 博士,高级工程师. 主要研究方向为网络安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)])]), Author(id=1327012285664572361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012285744264141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285664572361, language=EN, stringName=Zhitong Lu, firstName=Zhitong, middleName=null, lastName=Lu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, bio={"content":"
born in 1993. Master, engineer. Her main research interests include image adversarial learning and information security
"}, bioImg=null, bioContent=
born in 1993. Master, engineer. Her main research interests include image adversarial learning and information security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012287413597134, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012285664572361, language=CN, stringName=卢至彤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1中国科学院信息工程研究所 北京 100093, bio={"img":"Q/WRGfxNfOrZA2qvuCMyfQ==","content":"
1993年生. 硕士,工程师. 主要研究方向为图像对抗学习、信息安全
"}, bioImg=Q/WRGfxNfOrZA2qvuCMyfQ==, bioContent=
1993年生. 硕士,工程师. 主要研究方向为图像对抗学习、信息安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)])]), Author(id=1327012287526843344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012287610729426, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012287526843344, language=EN, stringName=Liming Wang, firstName=Liming, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, bio={"content":"
born in 1978. PhD, professorate senior engineer. Member of CCF. His main research interests include cloud security,date security, and wireless security
"}, bioImg=null, bioContent=
born in 1978. PhD, professorate senior engineer. Member of CCF. His main research interests include cloud security,date security, and wireless security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012287694615507, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012287526843344, language=CN, stringName=王利明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1中国科学院信息工程研究所 北京 100093, bio={"img":"nSMYQGw+CerQFfNpbnRQzw==","content":"
1978年生. 博士,正高级工程师. CCF会员. 主要研究方向为云安全、数据安全、无线安全
"}, bioImg=nSMYQGw+CerQFfNpbnRQzw==, bioContent=
1978年生. 博士,正高级工程师. CCF会员. 主要研究方向为云安全、数据安全、无线安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)])]), Author(id=1327012287770112981, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327012287837221847, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012287770112981, language=EN, stringName=Zhen Xu, firstName=Zhen, middleName=null, lastName=Xu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, bio={"content":"
born in 1976. PhD, professorate senior engineer. Member of CCF. His main research interests include trusted computing, cyber security, and system security
"}, bioImg=null, bioContent=
born in 1976. PhD, professorate senior engineer. Member of CCF. His main research interests include trusted computing, cyber security, and system security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327012287895942104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, authorId=1327012287770112981, language=CN, stringName=徐震, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1中国科学院信息工程研究所 北京 100093, bio={"img":"K5nthlboeZaNp+CxshF4uw==","content":"
1976年生. 博士,正高级工程师. CCF会员. 主要研究方向为可信计算、网络安全、系统安全
"}, bioImg=K5nthlboeZaNp+CxshF4uw==, bioContent=
1976年生. 博士,正高级工程师. CCF会员. 主要研究方向为可信计算、网络安全、系统安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)])])], keywords=[Keyword(id=1327012288101463001, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, orderNo=1, keyword=Internet-based services), Keyword(id=1327012288260846554, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, orderNo=2, keyword=anomaly detection), Keyword(id=1327012288378287067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, orderNo=3, keyword=key performance indicator (KPI)), Keyword(id=1327012288491533276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, orderNo=4, keyword=machine learning), Keyword(id=1327012288621556702, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, orderNo=5, keyword=artificial intelligence for IT operations (AIOps)), Keyword(id=1327012288722219999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, orderNo=1, keyword=互联网服务), Keyword(id=1327012288869020640, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, orderNo=2, keyword=异常检测), Keyword(id=1327012289040987105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, orderNo=3, keyword=关键性能指标), Keyword(id=1327012289120678882, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, orderNo=4, keyword=机器学习), Keyword(id=1327012289196176355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, orderNo=5, keyword=智能运维)], refs=[Reference(id=1327012294199980037, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Yanbo, Zhao Zhuofeng. Aggregating, operating, sharing and utilizing Internet-based services with the VINCA approach[C]//Proc of the 12th Asia-Pacific Web Conf. Piscataway, NJ: IEEE, 2010: 398−398, articleTitle=null, refAbstract=null), Reference(id=1327012294275477510, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Ono E, Ikkatai Y. Internet-based services to obtain information on science and technology according to the degree of interest[C]//Proc of the 9th Int Congress on Advanced Applied Informatics (IIAI-AAI). Piscataway, NJ: IEEE, 2020: 328−331, articleTitle=null, refAbstract=null), Reference(id=1327012294350974983, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=吴建平,林嵩,徐恪,等. 可演进的新一代互联网体系结构研究进展[J]. 计算机学报,2012,35(6):1094−1108, articleTitle=null, refAbstract=null), Reference(id=1327012294460026889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Jianping, Lin Song, Xu Ke, et al. Advances in evolvable new generation Internet architecture[J]. Chinese Journal of Computers, 2012, 35(6): 1094−1108 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012294531330058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=徐恪,朱敏,林闯. 互联网体系结构评估模型、机制及方法研究综述[J]. 计算机学报,2012,35(10):1985−2006, articleTitle=null, refAbstract=null), Reference(id=1327012294631993355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Ke, Zhu Min, Lin Chuang. Internet architecture evaluation models, mechanisms and methods[J]. Chinese Journal of Computers, 2012, 35(10): 1985−2006 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012294724268044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Gartner. The cost of downtime[EB/OL]. (2014-07-16)[2023-03-30]. https://www.loadbalancer.org/blog/how-to-calculate-the-cost-of-downtime-to-your-organization, articleTitle=null, refAbstract=null), Reference(id=1327012296313909261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Dapeng, Zhao Youjian, Xu Haowen, et al. Opprentice: Towards practical and automatic anomaly detection through machine learning[C]//Proc of the 2015 ACM/SIGCOMM Conf on Internet Measurement Conf. New York: ACM, 2015: 211−224, articleTitle=null, refAbstract=null), Reference(id=1327012296410378254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Mekuria R, McGrath M J, Riccobene V, et al. Automated profiling of virtualized media processing functions using telemetry and machine learning[C]//Proc of the 9th ACM Multimedia Systems Conf. New York: ACM, 2018: 150−161, articleTitle=null, refAbstract=null), Reference(id=1327012296477487119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=裴丹,张圣林,裴昶华. 基于机器学习的智能运维[J]. 中国计算机学会通讯,2017,13(12):67−73, articleTitle=null, refAbstract=null), Reference(id=1327012296548790288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Pei Dan, Zhang Shenglin, Pei Changhua. AIOps based on machine learning[J]. Communications of the CCF, 2017, 13(12): 67−73 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012296620093457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Gartner. AIOps (Artificial Intelligence for IT Operations)[EB/OL]. [2024-12-13]. https://www.gartner.com/en/information-technology/glossary/aiops-artificial-intelligence-operations, articleTitle=null, refAbstract=null), Reference(id=1327012296695590930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Ho T K. Random decision forests[C]//Proc of the 3rd Int Conf on Document Analysis and Recognition. Piscataway, NJ: IEEE, 1995: 278−282, articleTitle=null, refAbstract=null), Reference(id=1327012296766894099, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Breiman L. Bagging predictors[J]. Machine Learning, 1996, 24(2): 123−140, articleTitle=null, refAbstract=null), Reference(id=1327012296838197268, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proc of the 2nd Int Conf on Knowledge Discovery and Data Mining. Palo Alto, CA: AAAI, 1996: 226−231, articleTitle=null, refAbstract=null), Reference(id=1327012296917889045, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Kriegel H P, Kröger P, Sander J, et al. Density‐based clustering[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2011, 1(3): 231−240, articleTitle=null, refAbstract=null), Reference(id=1327012296980803606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278−2324, articleTitle=null, refAbstract=null), Reference(id=1327012297056301079, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Elman J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179−211, articleTitle=null, refAbstract=null), Reference(id=1327012297144381464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Le Q V, Jaitly N, Hinton G E. A simple way to initialize recurrent networks of rectified linear units[J]. arXiv preprint, arXiv:1504.00941, 2015, articleTitle=null, refAbstract=null), Reference(id=1327012297207296025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780, articleTitle=null, refAbstract=null), Reference(id=1327012297266016282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Chung Junyoung, Gulcehre C, Cho K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv preprint, arXiv:1412.3555, 2014, articleTitle=null, refAbstract=null), Reference(id=1327012297345708059, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533−536, articleTitle=null, refAbstract=null), Reference(id=1327012297437982748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Kingma D P, Welling M. Auto-encoding variational bayes[J]. arXiv preprint, arXiv:1312.6114, 2014, articleTitle=null, refAbstract=null), Reference(id=1327012297580589085, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. arXiv preprint, arXiv:1406.2661, 2014, articleTitle=null, refAbstract=null), Reference(id=1327012297647697950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Mnih V, Heess N, Graves A. Recurrent models of visual attention[C]//Proc of the 28th Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2014: 2204−2212, articleTitle=null, refAbstract=null), Reference(id=1327012297710612511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint, arXiv:1409.0473, 2015, articleTitle=null, refAbstract=null), Reference(id=1327012297777721376, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Parikh A P, Täckström O, Das D, et al. A decomposable attention model for natural language inference[C]//Proc of the 2016 Conf on Empirical Methods in Natural Language. Stroudsburg, PA: ACL, 2016: 2249−2255, articleTitle=null, refAbstract=null), Reference(id=1327012297857413153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Jianpeng, Dong Li, Lapata M. Long short-term memory-networks for machine reading[C]//Proc of the 2016 Conf on Empirical Methods in Natural Language. Stroudsburg, PA: ACL, 2016: 551−561, articleTitle=null, refAbstract=null), Reference(id=1327012297920327714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Zhouhan, Feng Minwei, Santos C N, et al. A structured self-attentive sentence embedding[C/OL]//Proc of the 5th Int Conf on Learning Representations (Poster). New York: OpenReview. net, 2017[2024-01-24]. https://openreview.net/forum?id=BJC_jUqxe, articleTitle=null, refAbstract=null), Reference(id=1327012297983242275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 5998−6008, articleTitle=null, refAbstract=null), Reference(id=1327012298054545444, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Haoyi, Zhang Shanghang, Peng Jieqi, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]//Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 11106−11115, articleTitle=null, refAbstract=null), Reference(id=1327012298113265701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Veličković P, Cucurull G, Casanova A, et al. Graph attention networks[J]. arXiv preprint, arXiv:1710.10903, 2017, articleTitle=null, refAbstract=null), Reference(id=1327012298180374566, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Qian Ji, Zeng Guangfu, Cai Zhiping, et al. A survey on anomaly detection techniques in large-scale KPI data[C]//Proc of the 9th Int Conf on Computer Engineering and Networks. Berlin: Springer, 2021: 767−776, articleTitle=null, refAbstract=null), Reference(id=1327012298239094823, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=He Shiming, Yang Bo, Qiao Qi. Overview of key performance indicator anomaly detection[C/OL]//Proc of the 2021 IEEE Region 10 Symp (TENSYMP). Piscataway, NJ: IEEE, 2021[2024-03-09]. https://ieeexplore.ieee.org/abstract/document/9550989, articleTitle=null, refAbstract=null), Reference(id=1327012298310397992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=王速,卢华,汪硕,等. 智能运维中 KPI 异常检测的研究进展[J]. 电信科学,2021,37(5):42−51, articleTitle=null, refAbstract=null), Reference(id=1327012298390089769, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Su, Lu Hua, Wang Shuo, et al. Research progress of KPI anomaly detection in intelligent operation and maintenance[J]. Telecommunications Science, 2021, 37(5): 42−51 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012298473975850, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen E Y, Tsay R S, Chen Rong. Constrained factor models for high-dimensional matrix-variate time series[J]. arXiv preprint, arXiv:1710.06075, 2017, articleTitle=null, refAbstract=null), Reference(id=1327012298532696107, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Husheng. A survey of research on anomaly detection for time series[C]//Proc of the 13th Int Computer Conf on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). Piscataway, NJ: IEEE, 2016: 426−431, articleTitle=null, refAbstract=null), Reference(id=1327012298595610668, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Nengwen, Zhu Jing, Liu Rong, et al. Label-less: A semi-automatic labelling tool for KPI anomalies[C]//Proc of the 38th IEEE Conf on Computer Communications (INFOCOM). Piscataway, NJ: IEEE, 2019: 1882−1890, articleTitle=null, refAbstract=null), Reference(id=1327012298671108141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Laptev N, Amizadeh S, Flint I. Generic and scalable framework for automated time-series anomaly detection[C]//Proc of the 21st ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2015: 1939−1947, articleTitle=null, refAbstract=null), Reference(id=1327012298754994222, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Hansheng, Xu Bixiong, Wang Yujing, et al. Time-series anomaly detection service at Microsoft[C]//Proc of the 25th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2019: 3009−3017, articleTitle=null, refAbstract=null), Reference(id=1327012298826297391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Ming, Su Ya, Zhang Shenglin, et al. CTF: Anomaly detection in high-dimensional time series with coarse-to-fine model transfer[C/OL]//Proc of the 40th IEEE Conf on Computer Communications (INFOCOM). Piscataway, NJ: IEEE, 2021[2024-03-09]. https://ieeexplore.ieee.org/document/9488755, articleTitle=null, refAbstract=null), Reference(id=1327012298910183472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Gama J, Zliobaite I, Bifet I, et al. A survey on concept drift adaptation[J]. Computing Surveys, 2014, 46(4): 1−37, articleTitle=null, refAbstract=null), Reference(id=1327012298968903729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhihan, Zhao Youjian, Han Jiaqi, et al. Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding[C]//Proc of the 27th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2021: 3220−3230, articleTitle=null, refAbstract=null), Reference(id=1327012299036012595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Ya, Zhao Youjian, Niu Chenhao, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]//Proc of the 25th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2019: 2828−2837, articleTitle=null, refAbstract=null), Reference(id=1327012299111510068, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=2018AIOps. The AIOps dataset [EB/OL]. [2023-03-30]. https://github.com/NetManAIOps/KPI-Anomaly-Detection?tab=readme-ov-file, articleTitle=null, refAbstract=null), Reference(id=1327012299224756277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Lavin A, Ahmad S. Evaluating real-time anomaly detection algorithms – The Numenta anomaly benchmark[C]//Proc of the 14th IEEE Int Conf on Machine Learning and Applications (ICMLA). Piscataway, NJ: IEEE, 2015: 38−44, articleTitle=null, refAbstract=null), Reference(id=1327012300462075960, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Chandola V, Banerjee A, Kumar V. Anomaly detection: A survey[J]. ACM Computing Surveys, 2009, 41(3): 1−58, articleTitle=null, refAbstract=null), Reference(id=1327012300529184826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xu, Qiu Qiu, Li Changshan, et al. GraphAD: A graph neural network for entity-wise multivariate time-series anomaly detection[C]//Proc of the 45th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2022: 2297−2302, articleTitle=null, refAbstract=null), Reference(id=1327012300587905083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xuanhao, Deng Liwei, Huang Feiteng, et al. DAEMON: Unsupervised anomaly detection and interpretation for multivariate time series[C]//Proc of the 37th IEEE Int Conf on Data Engineering. Piscataway, NJ: IEEE, 2021: 2225−2230, articleTitle=null, refAbstract=null), Reference(id=1327012300671791164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Wujie, Lu Haochuan, Zhou Yangfan, et al. iFeedback: Exploiting user feedback for real-time issue detection in large-scale online service systems[C]//Proc of the 34th IEEE∕ACM Int Conf on Automated Software Engineering (ASE). Piscataway, NJ: IEEE, 2019: 352−363, articleTitle=null, refAbstract=null), Reference(id=1327012300734705725, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Shuo, Chen Xiaofei, Chen Jiayuan, et al. Anomaly detection of periodic multivariate time series under high acquisition frequency scene in IoT[C]//Proc of the 20th Int Conf on Data Mining Workshops. Piscataway, NJ: IEEE, 2020: 543−552, articleTitle=null, refAbstract=null), Reference(id=1327012300797620286, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Ibidunmoye O, Rezaie A R, Elmroth E. Adaptive anomaly detection in performance metric streams[J]. IEEE Transactions on Network and Service Management, 2017, 15(1): 217−231, articleTitle=null, refAbstract=null), Reference(id=1327012300873117759, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Hundman K, Constantinou V, Laporte C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]//Proc of the 24th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2018: 387−395, articleTitle=null, refAbstract=null), Reference(id=1327012300936032320, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Goh J, Adepu S, Junejo K N, et al. A dataset to support research in the design of secure water treatment systems[C]//Proc of the 11th Int Conf on Critical Information Infrastructures Security. Berlin: Springer, 2016: 88−99, articleTitle=null, refAbstract=null), Reference(id=1327012300994752577, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmed C M, Palleti V R, Mathur A P. WADI: A water distribution testbed for research in the design of secure cyber physical systems[C]//Proc of the 3rd Int Workshop on Cyber-physical Systems for Smart Water Networks. New York: ACM, 2017: 25−28, articleTitle=null, refAbstract=null), Reference(id=1327012301070250051, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Dau H A, Bagnall A, Kamgar K, et al. The UCR time series archive[J]. IEEE/CAA Journal of Automatica Sinica, 2019, 6(6): 1293−1305, articleTitle=null, refAbstract=null), Reference(id=1327012301162524741, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Stehman S V. Selecting and interpreting measures of thematic classification accuracy[J]. Remote Sensing of Environment, 1997, 62(1): 77−89, articleTitle=null, refAbstract=null), Reference(id=1327012301246410822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Faraggi D, Reiser B. Estimation of the area under the ROC curve[J]. Statistics in Medicine, 2002, 21(20): 3093−3106, articleTitle=null, refAbstract=null), Reference(id=1327012301351268423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Haowen, Chen Wenxiao, Zhao Nengwen, et al. Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications[C]//Proc of the 27th Web Conf. New York: ACM, 2018: 187−196, articleTitle=null, refAbstract=null), Reference(id=1327012301405794376, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=纪守领,杜天宇,邓水光,等. 深度学习模型鲁棒性研究综述[J]. 计算机学报,2022,45(1):190−206, articleTitle=null, refAbstract=null), Reference(id=1327012301472903241, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Shouling, Du Tianyu, Deng Shuiguang, et al. Robustness certification research on deep learning models: A survey[J]. Chinese Journal of Computers, 2022, 45((1): ): 190−206 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012301540012106, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Liang, Lin Tao, Liu Chang, et al. SDFVAE: Static and dynamic factorized VAE for anomaly detection of multivariate CDN KPIs[C]//Proc of the 30th Web Conf. New York: ACM, 2021: 3076−3086, articleTitle=null, refAbstract=null), Reference(id=1327012301695201355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Zolfaghari B, Srivastava G, Roy S, et al. Content delivery networks: State of the art, trends, and future roadmap[J]. ACM Computing Surveys, 2020, 53(2): 1−34, articleTitle=null, refAbstract=null), Reference(id=1327012301787476044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghaznavi M, Jalalpour E, Salahuddin M A, et al. Content delivery network security: A survey[J]. IEEE Communications Surveys & Tutorials, 2021, 23(4): 2166−2190, articleTitle=null, refAbstract=null), Reference(id=1327012301846196301, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=吴吉义,李文娟,黄剑平,等. 移动互联网研究综述[J]. 中国科学:信息科学,2015,45(1):45−69, articleTitle=null, refAbstract=null), Reference(id=1327012301921693774, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Jiyi, Li Wenjuan, Huang Jianping, et al. Key techniques for mobile Internet: A survey[J]. SCIENTIA SINICA Informationis, 2015, 45(1): 45−69 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012301997191247, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Hsieh M Y. SoLoMo technology: Exploring the most critical determinants of SoLoMo technology in the contemporary mobile communication technology era[J]. Journal of Ambient Intelligence and Humanized Computing, 2018, 9(2): 307−318, articleTitle=null, refAbstract=null), Reference(id=1327012302064300112, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=李晖,李凤华,曹进,等. 移动互联服务与隐私保护的研究进展[J]. 通信学报,2014,35(11):1−11, articleTitle=null, refAbstract=null), Reference(id=1327012302143991889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Hui, Li Fenghua, Cao Jin, et al. Survey on security and privacy preserving for mobile Internet service[J]. Journal on Communications, 2014, 35(11): 1−11 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012302215295058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=王久超,赵卓峰. 基于实体-数据的物联网服务建模[J]. 计算机系统应用,2023,32(6):70−79, articleTitle=null, refAbstract=null), Reference(id=1327012302274015315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jiuchao, Zhao Zhuofeng. Entity-data-based modeling for Internet of things services[J]. Computer System & Applications, 2023, 32(6): 70−79 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012302345318484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=孙海丽,龙翔,韩兰胜,等. 工业物联网异常检测技术综述[J]. 通信学报,2022,43(3):196−210, articleTitle=null, refAbstract=null), Reference(id=1327012302412427349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Haili, Long Xiang, Han Lansheng, et al. Overview of anomaly detection techniques for industrial Internet of things[J]. Journal on Communications, 2022, 43(3): 196−210 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327012302475341910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Shenglin, Zhao Chenyu, Sui Yicheng, et al. Robust KPI anomaly detection for large-scale software services with partial labels[C]//Proc of the 32nd IEEE Int Symp on Software Reliability Engineering (ISSRE). Piscataway, NJ: IEEE, 2021: 103−114, articleTitle=null, refAbstract=null), Reference(id=1327012302542450775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xu, Lin Qingwei, Xu Yong, et al. Cross-dataset time series anomaly detection for cloud systems[C]//Proc of the 2019 USENIX Annual Technical Conf. Berkeley, CA: USENIX Association, 2019: 1063−1076, articleTitle=null, refAbstract=null), Reference(id=1327012302601171032, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jingyu, Jing Yuhan, Qi Qi, et al. ALSR: An adaptive label screening and relearning approach for interval-oriented anomaly detection[J]. Expert Systems with Applications, 2019, 136: 94−104, articleTitle=null, refAbstract=null), Reference(id=1327012302664085593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yao, Wang Zhaowei, Xie Zejun, et al. Practical and white-box anomaly detection through unsupervised and active learning[C/OL]//Proc of the 29th Int Conf on Computer Communications and Networks (ICCCN). Piscataway, NJ: IEEE, 2020[2024-03-09]. https://ieeexplore.ieee.org/document/9209704, articleTitle=null, refAbstract=null), Reference(id=1327012302722805850, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Moysen J, Ahmed F, García-Lozano M, et al. Big data-driven automated anomaly detection and performance forecasting in mobile networks[C/OL]//Proc of the 2020 IEEE Global Communications Conf Workshops. Piscataway, NJ: IEEE, 2020[2024-03-09]. https://ieeexplore.ieee.org/document/9367579, articleTitle=null, refAbstract=null), Reference(id=1327012302781526107, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Bu Jiahao, Liu Ying, Zhang Shenglin, et al. Rapid deployment of anomaly detection models for large number of emerging KPI streams[C/OL]//Proc of the 37th IEEE Int Performance, Computing, and Communications Conf. Piscataway, NJ: IEEE, 2018[2024-03-09]. https://ieeexplore.ieee.org/document/8711315, articleTitle=null, refAbstract=null), Reference(id=1327012302848634972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Jun, Lee P P C, Li Qi, et al. CellPAD: Detecting performance anomalies in cellular networks via regression analysis[C/OL]//Proc of the 17th IFIP Networking Conf. Piscataway, NJ: IEEE, 2018[2024-03-09]. https://ieeexplore.ieee.org/document/8697027, articleTitle=null, refAbstract=null), Reference(id=1327012302915743837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Guang, Cai Zhiping, Wang Siqi, et al. Unsupervised online anomaly detection with parameter adaptation for KPI abrupt changes[J]. IEEE Transactions on Network and Service Management, 2019, 17(3): 1294−1308, articleTitle=null, refAbstract=null), Reference(id=1327012303016407134, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Haiwen, Yu Guang, Liu Fang, et al. Unsupervised anomaly detection via DBSCAN for KPIs jitters in network managements[J]. Computers, Materials & Continua, 2020, 62(2): 917−927, articleTitle=null, refAbstract=null), Reference(id=1327012303100293215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zhichao, Singh S, Pereira A. Large scale time series analysis for infrastructure reliability[C]//Proc of the 7th IEEE Int Conf on Big Data. Piscataway, NJ: IEEE, 2019: 6240−6242, articleTitle=null, refAbstract=null), Reference(id=1327012303159013472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Teh H Y, Kevin I, Wang K, et al. Expect the unexpected: Unsupervised feature selection for automated sensor anomaly detection[J]. IEEE Sensors Journal, 2021, 21(16): 18033−18046, articleTitle=null, refAbstract=null), Reference(id=1327012303259676769, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Nengwen, Zhu Jing, Wang Yao, et al. Automatic and generic periodicity adaptation for KPI anomaly detection[J]. IEEE Transactions on Network and Service Management, 2019, 16(3): 1170−1183, articleTitle=null, refAbstract=null), Reference(id=1327012303318397026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Na, Han Biao, Cai Yang, et al. SeqAD: An unsupervised and sequential autoencoder ensembles based anomaly detection framework for KPI[C/OL]//Proc of the 29th IEEE∕ACM Int Symp on Quality of Service (IWQoS). Piscataway, NJ: IEEE, 2021[2024-03-09]. https://ieeexplore.ieee.org/document/9521258, articleTitle=null, refAbstract=null), Reference(id=1327012303385505891, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Na, Han Biao, Li Ruidong, et al. A multivariate KPIs anomaly detection framework with dynamic balancing loss training[J]. IEEE Transactions on Network and Service Management, 2023, 20(2): 1418−1429, articleTitle=null, refAbstract=null), Reference(id=1327012303452614756, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Lingxue, Laptev N. Deep and confident prediction for time series at uber[C]//Proc of the 17th Int Conf on Data Mining Workshops. Piscataway, NJ: IEEE, 2017: 103−110, articleTitle=null, refAbstract=null), Reference(id=1327012303532306533, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee Mingchang, Lin Jiachun, Gan E G. ReRe: A lightweight real-time ready-to-go anomaly detection approach for time series[C]//Proc of the 44th IEEE Annual Computers, Software, and Applications Conf (COMPSAC). Piscataway, NJ: IEEE, 2020: 322−327, articleTitle=null, refAbstract=null), Reference(id=1327012303595221094, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Yueyue, Ma Jianghong, Ye Yunming. KfreqGAN: Unsupervised detection of sequence anomaly with adversarial learning and frequency domain information[J]. Knowledge-Based Systems, 2022, 236: 107757, articleTitle=null, refAbstract=null), Reference(id=1327012303687495783, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Shang Zijing, Zhang Yingjun, Zhang Xiuguo, et al. Time series anomaly detection for KPIs based on correlation analysis and HMM[J]. Applied Sciences, 2021, 11(23): 11353, articleTitle=null, refAbstract=null), Reference(id=1327012303767187560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmad S, Lavin A, Purdy S, et al. Unsupervised real-time anomaly detection for streaming data[J]. Neurocomputing, 2017, 262: 134−147, articleTitle=null, refAbstract=null), Reference(id=1327012303838490729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Lea C, Vidal R, Reiter A, et al. Temporal convolutional networks: A unified approach to action segmentation[C]//Proc of the 14th European Conf on Computer Vision Workshops. Berlin: Springer, 2016: 47−54, articleTitle=null, refAbstract=null), Reference(id=1327012303918182506, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhihan, Zhao Youjian, Liu Rong, et al. Robust and rapid clustering of KPIs for large-scale anomaly detection[C/OL]//Proc of the 26th IEEE∕ACM Int Symp on Quality of Service (IWQoS). Piscataway, NJ: IEEE, 2018[2024-03-09]. https://ieeexplore.ieee.org/document/8624168, articleTitle=null, refAbstract=null), Reference(id=1327012305583321195, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Shenglin, Zhong Zhenyu, Li Dongwen, et al. Efficient KPI anomaly detection through transfer learning for large-scale web services[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(8): 2440−2455, articleTitle=null, refAbstract=null), Reference(id=1327012305654624364, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Huo Wunjun, Wang Wei, Li Wen. AnomalyDetect: An online distance-based anomaly detection algorithm[C]//Proc of the 16th IEEE Int Conf on Web Services. Piscataway, NJ: IEEE, 2019: 63−79, articleTitle=null, refAbstract=null), Reference(id=1327012305763676270, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Audibert J, Michiardi P, Guyard F, et al. USAD: Unsupervised anomaly detection on multivariate time series[C]//Proc of the 25th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2020: 3395−3404, articleTitle=null, refAbstract=null), Reference(id=1327012305839173743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Abdulaal A, Lancewicki T. Real-time synchronization in neural networks for multivariate time series anomaly detection[C]//Proc of 2021 the IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2021: 3570−3574, articleTitle=null, refAbstract=null), Reference(id=1327012305931448432, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Jensen L, Fosa J, Teitelbaum B, et al. How dense autoencoders can still achieve the state-of-the-art in time-series anomaly detection[C]//Proc of the 20th IEEE Int Conf on Machine Learning and Applications (ICMLA). Piscataway, NJ: IEEE, 2021: 1272−1277, articleTitle=null, refAbstract=null), Reference(id=1327012306011140209, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zeyan, Chen Wenxiao, Pei Dan. Robust and unsupervised KPI anomaly detection based on conditional variational autoencoder[C/OL]//Proc of the 37th IEEE Int Performance, Computing, and Communications Conf. Piscataway, NJ: IEEE, 2018[2024-03-09]. https://ieeexplore.ieee.org/document/8710885, articleTitle=null, refAbstract=null), Reference(id=1327012306090831986, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Jiemin, Guan Donghai, Deng Yuwen, et al. Model-agnostic causal principle for unbiased KPI anomaly detection[C/OL]//Proc of the 2022 Int Joint Conf on Neural Networks (IJCNN). Piscataway, NJ: IEEE, 2022[2024-03-09]. https://ieeexplore.ieee.org/document/9892664, articleTitle=null, refAbstract=null), Reference(id=1327012306178912371, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Wenlu, Chen Pengfei, Xu Yibin, et al. Active-MTSAD: Multivariate time series anomaly detection with active learning[C]//Proc of the 52nd Annual IEEE/IFIP Int Conf on Dependable Systems and Networks (DSN). Piscataway, NJ: IEEE, 2022: 263−274, articleTitle=null, refAbstract=null), Reference(id=1327012306262798452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Bo, Xu Qian, Yao Zhenjie, et al. VAE-TCN hybrid model for KPI anomaly detection[C/OL]//Proc of the 23rd Asia-Pacific Network Operations and Management Symp (APNOMS). Piscataway, NJ: IEEE, 2022[2024-03-09]. https://ieeexplore.ieee.org/document/9919985, articleTitle=null, refAbstract=null), Reference(id=1327012306338295925, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Ningjiang, Tu Huan, Duan Xiaoyan, et al. Semisupervised anomaly detection of multivariate time series based on a variational autoencoder[J]. Applied Intelligence, 2023, 53(5): 6074−6098, articleTitle=null, refAbstract=null), Reference(id=1327012306413793398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Tuli S, Casale G, Jennings N R. TranAD: Deep transformer networks for anomaly detection in multivariate time series data[J]. Proceedings of the VLDB Endowment, 2022, 15(6): 1201−1214, articleTitle=null, refAbstract=null), Reference(id=1327012306480902263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Jiehui, Wu Haixu, Wang Jianmin, et al. Anomaly transformer: Time series anomaly detection with association discrepancy[C/OL]//Proc of the 10th Int Conf on Learning Representations. New York: OpenReview. net, 2022[2024-01-24]. https://openreview.net/forum?id=LzQQ89U1qm_, articleTitle=null, refAbstract=null), Reference(id=1327012306594148473, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhong Jie, Zuo Enguang, Chen Chen, et al. A masked attention network with query sparsity measurement for time series anomaly detection[C]//Proc of the 30th IEEE Int Conf on Multimedia and Expo (ICME). Piscataway, NJ: IEEE, 2023: 2741−2746, articleTitle=null, refAbstract=null), Reference(id=1327012306669645946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Qin Shuxin, Zhu Jing, Wang Dan, et al. Decomposed transformer with frequency attention for multivariate time series anomaly detection[C]//Proc of the 10th IEEE Int Conf on Big Data. Piscataway, NJ: IEEE, 2022: 1090−1098, articleTitle=null, refAbstract=null), Reference(id=1327012306732560507, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yu, Wang Tianbo. Applying value-based deep reinforcement learning on KPI time series anomaly detection[C]//Proc of the 15th IEEE Int Conf on Cloud Computing (CLOUD). Piscataway, NJ: IEEE, 2022: 197−202, articleTitle=null, refAbstract=null), Reference(id=1327012306866778236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Shu Yanjun, Gao Tianrun, Zhang Zhan, et al. A general KPI anomaly detection using attention models[C]//Proc of the 19th IEEE Int Conf on Services Computing (SCC). Piscataway, NJ: IEEE, 2022: 114−119, articleTitle=null, refAbstract=null), Reference(id=1327012306996801661, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Doshi K, Abudalou S, Yilmaz Y. Reward once, penalize once: Rectifying time series anomaly detection[C/OL]//Proc of the 2022 Int Joint Conf on Neural Networks (IJCNN). Piscataway, NJ: IEEE, 2022[2024-03-09]. https://ieeexplore.ieee.org/document/9891913, articleTitle=null, refAbstract=null), Reference(id=1327012307076493438, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Geiger A, Liu Dongyu, Alnegheimish S, et al. TadGAN: Time series anomaly detection using generative adversarial networks[C]//Proc of the 8th IEEE Int Conf on Big Data. Piscataway, NJ: IEEE, 2020: 33−43, articleTitle=null, refAbstract=null), Reference(id=1327012307177156735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Jiachen, Li Yongling, He Haibo, et al. One-step predictive encoder-gaussian segment model for time series anomaly detection[C/OL]//Proc of the 2020 Int Joint Conf on Neural Networks (IJCNN). Piscataway, NJ: IEEE, 2020[2024-03-09]. https://ieeexplore.ieee.org/document/9207569, articleTitle=null, refAbstract=null), Reference(id=1327012307252654208, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Wenxiao, Xu Haowen, Li Zwyan, et al. Unsupervised anomaly detection for intricate KPIs via adversarial training of VAE[C]//Proc of the 38th IEEE Conf on Computer Communications (INFOCOM). Piscataway, NJ: IEEE, 2019: 1891−1899, articleTitle=null, refAbstract=null), Reference(id=1327012307386871937, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Yun, Zhang Xiuguo, Shang Zijing, et al. A novel hybrid method for KPI anomaly detection based on VAE and SVDD[J/OL]. Symmetry, 2021, 13(11): 2104, articleTitle=null, refAbstract=null), Reference(id=1327012307483340930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=He Zilong, Chen Pengfei, Huang Tao. Share or not share? Towards the practicability of deep models for unsupervised anomaly detection in modern online systems[C]//Proc of the 33rd IEEE Int Symp on Software Reliability Engineering (ISSRE). Piscataway, NJ: IEEE, 2022: 25−35, articleTitle=null, refAbstract=null), Reference(id=1327012307571421315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(5/6): 602−610, articleTitle=null, refAbstract=null), Reference(id=1327012307672084612, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Liang, Chen Wenchao, Liu Yanwei, et al. Switching Gaussian mixture variational RNN for anomaly detection of diverse CDN websites[C]//Proc of the 41st IEEE Conf on Computer Communications (INFOCOM). Piscataway, NJ: IEEE, 2022: 300−309, articleTitle=null, refAbstract=null), Reference(id=1327012307739193477, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Qi Qi, Shen Runye, Wang Jingyu, et al. Spatial-temporal learning-based artificial intelligence for IT operations in the edge network[J]. IEEE Network, 2021, 35(1): 197−203, articleTitle=null, refAbstract=null), Reference(id=1327012307823079558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Scheinert D, Acker A. TELESTO: A graph neural network model for anomaly classification in cloud services[C]//Proc of the 2020 Int Conf on Service-Oriented Computing Workshops. Berlin: Springer, 2020: 214−227, articleTitle=null, refAbstract=null), Reference(id=1327012307898577031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Suozhao, Wu Wenjun, Pu Yanjun. Multi-indicators prediction in microservice using Granger causality test and Attention LSTM[C]//Proc of the 2020 IEEE World Congress on Services (SERVICES). Piscataway, NJ: IEEE, 2020: 77−82, articleTitle=null, refAbstract=null), Reference(id=1327012307974074504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Minghua, Zhang Shenglin, Pei Dan, et al. Robust and rapid adaption for concept drift in software system anomaly detection[C]//Proc of the 29th IEEE Int Symp on Software Reliability Engineering (ISSRE). Piscataway, NJ: IEEE, 2018: 13−24, articleTitle=null, refAbstract=null), Reference(id=1327012308049571977, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jingwen, Liu Jingxin, Pu Juntao, et al. An anomaly prediction framework for financial IT systems using hybrid machine learning methods[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(11): 15277−15286, articleTitle=null, refAbstract=null), Reference(id=1327012308120875146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Shupeng, Fung C, Huang Shaohan, et al. PSOM: Periodic self-organizing maps for unsupervised anomaly detection in periodic time series[C/OL]//Proc of the 25th IEEE∕ACM Int Symp on Quality of Service (IWQoS). Piscataway, NJ: IEEE, 2017[2024-03-09]. https://ieeexplore.ieee.org/document/7969174, articleTitle=null, refAbstract=null), Reference(id=1327012308284453003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Le K H, Papotti P. User-driven error detection for time series with events[C]//Proc of the 36th IEEE Int Conf on Data Engineering. Piscataway, NJ: IEEE, 2020: 745−757, articleTitle=null, refAbstract=null), Reference(id=1327012308368339084, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Loog M. Contrastive pessimistic likelihood estimation for semi-supervised classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(3): 462−475, articleTitle=null, refAbstract=null), Reference(id=1327012308439642253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Sohn K, Lee H, Yan Xinchen. Learning structured output representation using deep conditional generative models[C]//Proc of the 29th Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2015: 3483−3491, articleTitle=null, refAbstract=null), Reference(id=1327012308515139726, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xuanhao, Deng Liwei, Zhao Yan, et al. Adversarial autoencoder for unsupervised time series anomaly detection and interpretation[C]//Proc of the 16th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2023: 267−275, articleTitle=null, refAbstract=null), Reference(id=1327012310192861327, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[C]//Proc of the 34th Int Conf on Machine Learning. New York: ACM, 2017: 214−223, articleTitle=null, refAbstract=null), Reference(id=1327012310280941712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GANs[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 5767−5777, articleTitle=null, refAbstract=null), Reference(id=1327012310343856273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Haiqi, Rho S, Liu Shaohui, et al. Learning spatial graph structure for multivariate KPI anomaly detection in large-scale cyber-physical systems[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1−16, articleTitle=null, refAbstract=null), Reference(id=1327012310419353746, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Siffer A, Fouque P A, Termier A, et al. Anomaly detection in streams with extreme value theory[C]//Proc of the 23rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2017: 1067−1075, articleTitle=null, refAbstract=null), Reference(id=1327012310515822739, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=García S, Luengo J, Herrera F. Data Preprocessing in Data Mining[M]. Cham, Switzerland: Springer International Publishing, 2015, articleTitle=null, refAbstract=null), Reference(id=1327012310746509460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=成科扬,王宁,师文喜,等. 深度学习可解释性研究进展[J]. 计算机研究与发展,2020,57(6):1208−1217, articleTitle=null, refAbstract=null), Reference(id=1327012310863949973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Keyang, Wang Ning, Shi Wenxi, et al. Research advances in the interpretability of deep learning[J]. Journal of Computer Research and Development, 2020, 57(6): 1208−1217 (in Chinese), articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327012284242703280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=1, ext=[AuthorCompanyExt(id=1327012284267869105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093), AuthorCompanyExt(id=1327012284276257714, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284242703280, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国科学院信息工程研究所 北京 100093)]), AuthorCompany(id=1327012284465001395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, xref=2, ext=[AuthorCompanyExt(id=1327012284544693172, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284465001395, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327012284599219125, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, companyId=1327012284465001395, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学网络空间安全学院 北京 100049)])], figs=[ArticleFig(id=1327012289468806116, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 1, caption=
Types of KPI curve, figureFileSmall=4vqA0BenZSNzPbVFZTlZ/Q==, figureFileBig=DhqYqjM7RaukRifX5r7Obw==, tableContent=null), ArticleFig(id=1327012289540109285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图1, caption=
KPI曲线类型, figureFileSmall=4vqA0BenZSNzPbVFZTlZ/Q==, figureFileBig=DhqYqjM7RaukRifX5r7Obw==, tableContent=null), ArticleFig(id=1327012289640772582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 2, caption=
An example of concept drift, figureFileSmall=tq7IQPWj1ptpeAXrGGOaBA==, figureFileBig=JmgkMmwMUlp37E+v0mShgQ==, tableContent=null), ArticleFig(id=1327012289728852967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图2, caption=
概念漂移示例, figureFileSmall=tq7IQPWj1ptpeAXrGGOaBA==, figureFileBig=JmgkMmwMUlp37E+v0mShgQ==, tableContent=null), ArticleFig(id=1327012289892430824, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 3, caption=
Two basic types of KPI anomalies, figureFileSmall=+zdiBRfLjg5nhK9JGXUobA==, figureFileBig=Zu5Jm5pGT+Q6xgixZd+yiQ==, tableContent=null), ArticleFig(id=1327012289955345385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图3, caption=
KPI的2种基本异常类型, figureFileSmall=+zdiBRfLjg5nhK9JGXUobA==, figureFileBig=Zu5Jm5pGT+Q6xgixZd+yiQ==, tableContent=null), ArticleFig(id=1327012290009871338, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 4, caption=
Technical framework of KPI anomaly detection, figureFileSmall=lrmsQGesXaknscKprTPPnA==, figureFileBig=EszaffxI8uSMmLy7wihKqA==, tableContent=null), ArticleFig(id=1327012290085368811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图4, caption=
KPI异常检测技术框架, figureFileSmall=lrmsQGesXaknscKprTPPnA==, figureFileBig=EszaffxI8uSMmLy7wihKqA==, tableContent=null), ArticleFig(id=1327012290198615020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 5, caption=
Venn graph of the KPI anomaly detection techniques, figureFileSmall=k2hbgsPNsQjd+e0ez4i66w==, figureFileBig=3BlnjKVLr0H/o2X9VTMu1Q==, tableContent=null), ArticleFig(id=1327012291867948013, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图5, caption=
KPI异常检测技术韦恩图, figureFileSmall=k2hbgsPNsQjd+e0ez4i66w==, figureFileBig=3BlnjKVLr0H/o2X9VTMu1Q==, tableContent=null), ArticleFig(id=1327012291960222702, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Figure 6, caption=
Classification framework of KPI anomaly detection techniques, figureFileSmall=j9eHS+2CobiteLz61VavYg==, figureFileBig=2DHM3UCzV7hFC1M5idjHfw==, tableContent=null), ArticleFig(id=1327012292031525871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=图6, caption=
KPI异常检测技术分类框架, figureFileSmall=j9eHS+2CobiteLz61VavYg==, figureFileBig=2DHM3UCzV7hFC1M5idjHfw==, tableContent=null), ArticleFig(id=1327012292107023344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 1, caption=
Summary of KPI Data Types, figureFileSmall=null, figureFileBig=null, tableContent=
| KPI类型 | 释义 | 举例或表示 |
|---|
变量或维度域 数目不同 | 单变量KPI | 每个时间点由单一元素表示的KPI (该元素一般代表度量域中的单个度量值) | $ {\boldsymbol{X}}=({x}_{1},\;{x}_{2},\;…,\;{x}_{n}),\;\forall {X}^{(t)}={x}_{t}\in \mathbb{R} $ |
| 多变量KPI | 每个时间点由含M个元素的向量表示的KPI (该向量一般代表度量域中的多个度量值) | $ {\cal{\boldsymbol{X}}}=({\boldsymbol X}_{1},\;{\boldsymbol X}_{2},\;…,\;{\boldsymbol X}_{M}),\;\forall {\cal{\boldsymbol{X}}}^{(t)}={{\boldsymbol{X}}}_{1:M}^{(t)}\in {\mathbb{R}}^{M},\;M\ge 1\in {\mathbb{N}}_{+} $ |
| 矩阵变量KPI | 每个时间点由M×E的2维矩阵表示的KPI (矩阵的行向量和列向量分别代表度量域和实体域) | $ \bar{\cal{\boldsymbol{X}}}=({\cal{\boldsymbol X}}_{1},\;{\cal{\boldsymbol X}}_{2},\;…,\;{\cal{\boldsymbol X}}_{E}),\;\forall {\bar{\cal{\boldsymbol{X}}}}^{(t)}={\cal{\boldsymbol{X}}}_{1:E}^{(t)}\in {\mathbb{R}}^{M\times E},E\ge 1\in \mathbb{N}_{+} $ |
| 形态特点不同 | 周期性KPI | 呈现固定变化规律的KPI | 见图1(a) |
| 非周期性KPI | 无固定变化规律的KPI | 见图1(b)(c) |
| 噪声分布不同 | 平滑KPI | 具有对角多元高斯噪声的KPI | |
| 复杂KPI | 非高斯噪声分布的KPI | |
| 监控来源不同 | 服务KPI | 反映服务质量的业务级KPI | 页面浏览量、在线用户数及响应时间等 |
| 机器KPI | 反映机器状态的实体级KPI | CPU利用率、内存利用率及吞吐量等 |
), ArticleFig(id=1327012292186715121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表1, caption=
KPI数据类型总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| KPI类型 | 释义 | 举例或表示 |
|---|
变量或维度域 数目不同 | 单变量KPI | 每个时间点由单一元素表示的KPI (该元素一般代表度量域中的单个度量值) | $ {\boldsymbol{X}}=({x}_{1},\;{x}_{2},\;…,\;{x}_{n}),\;\forall {X}^{(t)}={x}_{t}\in \mathbb{R} $ |
| 多变量KPI | 每个时间点由含M个元素的向量表示的KPI (该向量一般代表度量域中的多个度量值) | $ {\cal{\boldsymbol{X}}}=({\boldsymbol X}_{1},\;{\boldsymbol X}_{2},\;…,\;{\boldsymbol X}_{M}),\;\forall {\cal{\boldsymbol{X}}}^{(t)}={{\boldsymbol{X}}}_{1:M}^{(t)}\in {\mathbb{R}}^{M},\;M\ge 1\in {\mathbb{N}}_{+} $ |
| 矩阵变量KPI | 每个时间点由M×E的2维矩阵表示的KPI (矩阵的行向量和列向量分别代表度量域和实体域) | $ \bar{\cal{\boldsymbol{X}}}=({\cal{\boldsymbol X}}_{1},\;{\cal{\boldsymbol X}}_{2},\;…,\;{\cal{\boldsymbol X}}_{E}),\;\forall {\bar{\cal{\boldsymbol{X}}}}^{(t)}={\cal{\boldsymbol{X}}}_{1:E}^{(t)}\in {\mathbb{R}}^{M\times E},E\ge 1\in \mathbb{N}_{+} $ |
| 形态特点不同 | 周期性KPI | 呈现固定变化规律的KPI | 见图1(a) |
| 非周期性KPI | 无固定变化规律的KPI | 见图1(b)(c) |
| 噪声分布不同 | 平滑KPI | 具有对角多元高斯噪声的KPI | |
| 复杂KPI | 非高斯噪声分布的KPI | |
| 监控来源不同 | 服务KPI | 反映服务质量的业务级KPI | 页面浏览量、在线用户数及响应时间等 |
| 机器KPI | 反映机器状态的实体级KPI | CPU利用率、内存利用率及吞吐量等 |
), ArticleFig(id=1327012292270601202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 2, caption=
Datasets for KPI Anomaly Detection on Internet-Based Services, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | KPI变量数目 (度量域×实体域) | KPI数据点总数 | 异常点占比/% |
|---|
| Yahoo[36] | 367×1 | 572 966 | 0.68 |
| ASD[40] | 19×12 | 154 171 | 4.16 |
| SMD[41] | 38×28 | 1 416 825 | 4.16 |
| KPI[42] | 58×1 | 5 922 913 | 2.26 |
| NAB-Twitter[43] | 9×1 | 142 765 | 0.15 |
), ArticleFig(id=1327012292350292979, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表2, caption=
互联网服务KPI异常检测数据集
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | KPI变量数目 (度量域×实体域) | KPI数据点总数 | 异常点占比/% |
|---|
| Yahoo[36] | 367×1 | 572 966 | 0.68 |
| ASD[40] | 19×12 | 154 171 | 4.16 |
| SMD[41] | 38×28 | 1 416 825 | 4.16 |
| KPI[42] | 58×1 | 5 922 913 | 2.26 |
| NAB-Twitter[43] | 9×1 | 142 765 | 0.15 |
), ArticleFig(id=1327012292446761972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 3, caption=
Interpretability Metrics of KPI Anomaly Detection, figureFileSmall=null, figureFileBig=null, tableContent=
| 典型工作 | 可解释性指标 | 释义 |
|---|
| OmniAnomaly[41] | $ HitRate@P\% = \dfrac{{Hit@\left\lfloor {P\% \times \left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|} \right\rfloor }}{{\left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|}} $ | $ {\boldsymbol{GT}}_{{t}} $表示真实异常度量的排序数组,P=100或150,$ Hit@\left\lfloor {P\% \times \left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|} \right\rfloor $表示模型在$ \lfloor P\% \times $$ | {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} | \rfloor $下的异常度量命中数量 |
| DAEMON[46] | $ RDCG@P\% = \displaystyle\sum\limits_{i=1}^{\left| {{{\boldsymbol{G}}_{{x_t}}}} \right|} {\dfrac{{{v_i}}}{{{\text{lb}}\left( {{d_i} + 2} \right)}}} $ | 在HitRate@P%基础上考虑不同异常度量的重要性,其中,vi表示第i个度量是否命中(vi = 1或vi = 0),di表示真实异常度量排序集合中i的位置索引与模型检测到的异常度量排序集合中i的位置索引间的距离 |
| InterFusion[40] | $ IPS = \displaystyle\sum\limits_{a = 1}^A {\dfrac{{{w_a}\left| {{{\boldsymbol{G}}_{{\phi _a}}} \cap {{\boldsymbol{I}}_{{\phi _a}}}} \right|}}{{\left| {{{\boldsymbol{G}}_{{\phi _a}}}} \right|}}} ,{w_a} = \dfrac{{{N_{{\phi _a}}}}}{{\displaystyle\sum\limits_{a = 1}^A {{N_{{\phi _a}}}} }} $ | 在HitRate@P%基础上考虑异常段级的可解释性,其中,$ {N_{{\phi _a}}} $表示异常段$ {\phi _a} $的长度,$ {w_a} $用于衡量该异常段在所有异常段中的重要性 |
), ArticleFig(id=1327012292551619573, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表3, caption=
KPI异常检测中的可解释性指标
, figureFileSmall=null, figureFileBig=null, tableContent=
| 典型工作 | 可解释性指标 | 释义 |
|---|
| OmniAnomaly[41] | $ HitRate@P\% = \dfrac{{Hit@\left\lfloor {P\% \times \left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|} \right\rfloor }}{{\left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|}} $ | $ {\boldsymbol{GT}}_{{t}} $表示真实异常度量的排序数组,P=100或150,$ Hit@\left\lfloor {P\% \times \left| {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} \right|} \right\rfloor $表示模型在$ \lfloor P\% \times $$ | {{\boldsymbol{G}}{{\boldsymbol{T}}_t}} | \rfloor $下的异常度量命中数量 |
| DAEMON[46] | $ RDCG@P\% = \displaystyle\sum\limits_{i=1}^{\left| {{{\boldsymbol{G}}_{{x_t}}}} \right|} {\dfrac{{{v_i}}}{{{\text{lb}}\left( {{d_i} + 2} \right)}}} $ | 在HitRate@P%基础上考虑不同异常度量的重要性,其中,vi表示第i个度量是否命中(vi = 1或vi = 0),di表示真实异常度量排序集合中i的位置索引与模型检测到的异常度量排序集合中i的位置索引间的距离 |
| InterFusion[40] | $ IPS = \displaystyle\sum\limits_{a = 1}^A {\dfrac{{{w_a}\left| {{{\boldsymbol{G}}_{{\phi _a}}} \cap {{\boldsymbol{I}}_{{\phi _a}}}} \right|}}{{\left| {{{\boldsymbol{G}}_{{\phi _a}}}} \right|}}} ,{w_a} = \dfrac{{{N_{{\phi _a}}}}}{{\displaystyle\sum\limits_{a = 1}^A {{N_{{\phi _a}}}} }} $ | 在HitRate@P%基础上考虑异常段级的可解释性,其中,$ {N_{{\phi _a}}} $表示异常段$ {\phi _a} $的长度,$ {w_a} $用于衡量该异常段在所有异常段中的重要性 |
), ArticleFig(id=1327012292627117046, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 4, caption=
KPI Monitoring System, figureFileSmall=null, figureFileBig=null, tableContent=
| 监控层次 | 监控范围 | 相关KPI |
|---|
| 基础资源 | 主要对服务中的硬件设备、虚拟机或容器集群等资源进行监控 | CPU利用率、网络接口流量、丢包数、吞吐量等 |
| 应用性能 | 主要对服务中的可用性状态、应用处理能力、业务运营状态等应用性能进行监控 | 页面浏览量、服务响应时间、交易量、在线用户数等 |
| 用户体验 | 主要对用户真实访问体验及反馈意见进行监控 | 首屏时间、下载速度、用户反馈文本中某些关键词组合出现的频率[47]等 |
), ArticleFig(id=1327012292698420215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表4, caption=
KPI监控体系
, figureFileSmall=null, figureFileBig=null, tableContent=
| 监控层次 | 监控范围 | 相关KPI |
|---|
| 基础资源 | 主要对服务中的硬件设备、虚拟机或容器集群等资源进行监控 | CPU利用率、网络接口流量、丢包数、吞吐量等 |
| 应用性能 | 主要对服务中的可用性状态、应用处理能力、业务运营状态等应用性能进行监控 | 页面浏览量、服务响应时间、交易量、在线用户数等 |
| 用户体验 | 主要对用户真实访问体验及反馈意见进行监控 | 首屏时间、下载速度、用户反馈文本中某些关键词组合出现的频率[47]等 |
), ArticleFig(id=1327012292782306296, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 5, caption=
Comparison of Mining Ability for KPI’s Dependency Patterns, figureFileSmall=null, figureFileBig=null, tableContent=
| 机器学习模型 | 时序依赖性 | 度量依赖性 | 实体依赖性 |
|---|
| 注:颜色越深表示该模型相应的挖掘能力越强. |
传统机器学习模型 (人工提取统计特征) | | | |
传统机器学习模型 (人工提取预测误差特征) | | | |
传统机器学习模型 (人工提取时序特征) | | | |
传统机器学习模型 (人工提取相关性特征) | | | |
| 时间序列聚类 | | | |
| RNN | | | |
| LSTM | | | |
| GRU | | | |
| 1维CNN | | | |
| TCN | | | |
| Transformer | | | |
| 非序列-重构神经网络 | | | |
| 序列-重构神经网络 | | | |
| 图神经网络 | | | |
), ArticleFig(id=1327012292882969593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表5, caption=
KPI依赖模式挖掘能力对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 机器学习模型 | 时序依赖性 | 度量依赖性 | 实体依赖性 |
|---|
| 注:颜色越深表示该模型相应的挖掘能力越强. |
传统机器学习模型 (人工提取统计特征) | | | |
传统机器学习模型 (人工提取预测误差特征) | | | |
传统机器学习模型 (人工提取时序特征) | | | |
传统机器学习模型 (人工提取相关性特征) | | | |
| 时间序列聚类 | | | |
| RNN | | | |
| LSTM | | | |
| GRU | | | |
| 1维CNN | | | |
| TCN | | | |
| Transformer | | | |
| 非序列-重构神经网络 | | | |
| 序列-重构神经网络 | | | |
| 图神经网络 | | | |
), ArticleFig(id=1327012293143016442, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 6, caption=
Motivation for Model Selection of KPI Anomaly Detection, figureFileSmall=null, figureFileBig=null, tableContent=
| KPI场景 | 机器学习模型 | 模型选择动机 (主要动机是挖掘KPI依赖模式的能力) | 代表性工作 |
|---|
| 单变量KPI | 传统机器学习模型(人工提取统计特征) | 挖掘短期时序依赖 | 文献[67–70,73–74] |
| 传统机器学习模型(人工提取预测误差特征) | 挖掘趋势及偏离预测的异常模式 | 文献[6,35,47,66–68,71] |
| 传统机器学习模型(人工特征提取时序特征) | 挖掘长期时序依赖及剧烈变化的异常模式 | 文献[66–67,69–70,75] |
| 传统机器学习模型(人工特征提取小波特征) | 挖掘频域模式有利于检测波动性KPI异常 | 文献[68] |
| 时间序列聚类(DBSCAN)+传统机器学习模型 | 挖掘周期性模式的相似性 | 文献[66,69–71,77,86–88] |
| 序列神经网络(RNN) | 挖掘短期时序依赖 | |
| 序列神经网络(LSTM) | 挖掘长期时序依赖 | 文献[78–81] |
| 序列神经网络(GRU) | 挖掘长期时序依赖 | |
| 序列神经网络(1维CNN) | 挖掘长期时序依赖,缓解梯度消失,训练快 | 文献[37,82–83] |
| 序列神经网络(TCN) | 挖掘长期时序依赖,扩大卷积核的感受野 | 文献[83] |
| 多变量KPI | 传统机器学习模型(人工提取相关性特征) | 挖掘度量依赖 | 文献[72] |
| 重构神经网络(AE) | 挖掘度量依赖 | 文献[89–91] |
| 重构神经网络(VAE) | 挖掘度量依赖且缓解过拟合问题 | 文献[56,87,92–94] |
| 序列-重构神经网络 | 挖掘时序、度量依赖的混合模式 | 文献[38,40–41,48,58,95,104–107,110] |
| Transformer及其变体 | 挖掘时序、度量依赖的混合模式,训练快 | 文献[96–103,108] |
| 聚类+重构神经网络 | 挖掘不同实体中时序、度量依赖的混合模式 | 文献[38] |
| 切换高斯模型+重构神经网络 | 挖掘不同实体中时序、度量依赖的混合模式 | 文献[110] |
| 矩阵变量KPI | 图卷积网络 | 挖掘时序、实体(空间)依赖的混合模式 | 文献[111–112] |
| 图注意力网络 | 挖掘时序、实体依赖的混合模式 | 文献[45] |
), ArticleFig(id=1327012293235291131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表6, caption=
KPI异常检测的模型选择动机
, figureFileSmall=null, figureFileBig=null, tableContent=
| KPI场景 | 机器学习模型 | 模型选择动机 (主要动机是挖掘KPI依赖模式的能力) | 代表性工作 |
|---|
| 单变量KPI | 传统机器学习模型(人工提取统计特征) | 挖掘短期时序依赖 | 文献[67–70,73–74] |
| 传统机器学习模型(人工提取预测误差特征) | 挖掘趋势及偏离预测的异常模式 | 文献[6,35,47,66–68,71] |
| 传统机器学习模型(人工特征提取时序特征) | 挖掘长期时序依赖及剧烈变化的异常模式 | 文献[66–67,69–70,75] |
| 传统机器学习模型(人工特征提取小波特征) | 挖掘频域模式有利于检测波动性KPI异常 | 文献[68] |
| 时间序列聚类(DBSCAN)+传统机器学习模型 | 挖掘周期性模式的相似性 | 文献[66,69–71,77,86–88] |
| 序列神经网络(RNN) | 挖掘短期时序依赖 | |
| 序列神经网络(LSTM) | 挖掘长期时序依赖 | 文献[78–81] |
| 序列神经网络(GRU) | 挖掘长期时序依赖 | |
| 序列神经网络(1维CNN) | 挖掘长期时序依赖,缓解梯度消失,训练快 | 文献[37,82–83] |
| 序列神经网络(TCN) | 挖掘长期时序依赖,扩大卷积核的感受野 | 文献[83] |
| 多变量KPI | 传统机器学习模型(人工提取相关性特征) | 挖掘度量依赖 | 文献[72] |
| 重构神经网络(AE) | 挖掘度量依赖 | 文献[89–91] |
| 重构神经网络(VAE) | 挖掘度量依赖且缓解过拟合问题 | 文献[56,87,92–94] |
| 序列-重构神经网络 | 挖掘时序、度量依赖的混合模式 | 文献[38,40–41,48,58,95,104–107,110] |
| Transformer及其变体 | 挖掘时序、度量依赖的混合模式,训练快 | 文献[96–103,108] |
| 聚类+重构神经网络 | 挖掘不同实体中时序、度量依赖的混合模式 | 文献[38] |
| 切换高斯模型+重构神经网络 | 挖掘不同实体中时序、度量依赖的混合模式 | 文献[110] |
| 矩阵变量KPI | 图卷积网络 | 挖掘时序、实体(空间)依赖的混合模式 | 文献[111–112] |
| 图注意力网络 | 挖掘时序、实体依赖的混合模式 | 文献[45] |
), ArticleFig(id=1327012293340148732, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 7, caption=
Accuracy-Centric KPI Anomaly Detection Techniques, figureFileSmall=null, figureFileBig=null, tableContent=
代表性 工作 | 主要模型 | 准确性提升方式 |
|---|
| 检测技术准确性提升方式可概括为4种:①人工提取高质量特征;②完善模型结构;③优化目标函数或改进训练方式;④调整异常计算方法或阈值选择机制. |
| 文献[6] | 随机森林分类 | 利用随机森林分类进行二次学习,设计动态阈值②④ |
| 文献[68] | 随机森林分类 | 利用随机森林分类进行二次学习② |
| 文献[115] | 随机森林回归 | 集成学习② |
| 文献[69] | 孤立森林 | 改进孤立森林中的切割算法③ |
| 文献[66] | 混合模型(聚类+随机森林) | 利用主动学习修正错误结果②③④ |
| 文献[67] | 混合模型(聚类+随机森林) | 提取多角度特征①② |
| 文献[71] | 混合模型(聚类+随机森林) | 引入半监督学习框架CPLE②③ |
| 文献[117] | 混合模型(聚类+随机森林) | 无监督聚类直接推导随机森林的决策规则,利用主动学习修正错误结果②③ |
| 文献[113] | 预测神经网络 | 采用基于多头注意力机制的LSTM③ |
| 文献[78] | 重构神经网络 | 集成学习② |
| 文献[56] | 重构神经网络 | 通过修正异常数据权重去除异常偏差③ |
| 文献[92] | 重构神经网络 | 引入额外的时间信息输入至VAE (CVAE)② |
| 文献[79] | 重构神经网络 | 集成学习,采用动态平衡损失函数②③④ |
| 文献[93] | 重构神经网络 | 通过切断异常标签到输入的因果路径去除异常偏差③ |
| 文献[38] | 混合模型(重构神经网络+聚类) | 利用聚类实现检测模型由粗到精地微调②④ |
| 文献[46] | 对抗式重构 神经网络 | 采用双层GAN+VAE,对目标函数进行显式地对抗正则化处理②③ |
| 文献[106] | 对抗式重构 神经网络 | 采用WGAN+VAE,利用梯度惩罚以及贝叶斯正则项修改目标函数②③ |
| 文献[89] | 对抗式重构 神经网络 | 采用基于对抗式训练思想的双层解码器AE②③④ |
| 文献[97] | 对抗式重构 神经网络 | 采用基于对抗式训练思想的双层解码器AE,引入Transformer层②③④ |
| 文献[104] | 对抗式重构 神经网络 | 采用双层GAN+AE②③④ |
| 文献[123] | 图注意力+重构神经网络 | 采用图结构挖掘深层次度量依赖② |
| 文献[98] | 基于关联差异的重构神经网络 | 采用基于关联差异思想的Transformer变体③④ |
| 文献[96] | 半监督重构 神经网络 | 伪标签学习③ |
| 文献[94] | 半监督重构 神经网络 | 利用主动学习修正错误结果及目标函数②③ |
), ArticleFig(id=1327012293474366461, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表7, caption=
以准确性目标为核心的KPI异常检测技术
, figureFileSmall=null, figureFileBig=null, tableContent=
代表性 工作 | 主要模型 | 准确性提升方式 |
|---|
| 检测技术准确性提升方式可概括为4种:①人工提取高质量特征;②完善模型结构;③优化目标函数或改进训练方式;④调整异常计算方法或阈值选择机制. |
| 文献[6] | 随机森林分类 | 利用随机森林分类进行二次学习,设计动态阈值②④ |
| 文献[68] | 随机森林分类 | 利用随机森林分类进行二次学习② |
| 文献[115] | 随机森林回归 | 集成学习② |
| 文献[69] | 孤立森林 | 改进孤立森林中的切割算法③ |
| 文献[66] | 混合模型(聚类+随机森林) | 利用主动学习修正错误结果②③④ |
| 文献[67] | 混合模型(聚类+随机森林) | 提取多角度特征①② |
| 文献[71] | 混合模型(聚类+随机森林) | 引入半监督学习框架CPLE②③ |
| 文献[117] | 混合模型(聚类+随机森林) | 无监督聚类直接推导随机森林的决策规则,利用主动学习修正错误结果②③ |
| 文献[113] | 预测神经网络 | 采用基于多头注意力机制的LSTM③ |
| 文献[78] | 重构神经网络 | 集成学习② |
| 文献[56] | 重构神经网络 | 通过修正异常数据权重去除异常偏差③ |
| 文献[92] | 重构神经网络 | 引入额外的时间信息输入至VAE (CVAE)② |
| 文献[79] | 重构神经网络 | 集成学习,采用动态平衡损失函数②③④ |
| 文献[93] | 重构神经网络 | 通过切断异常标签到输入的因果路径去除异常偏差③ |
| 文献[38] | 混合模型(重构神经网络+聚类) | 利用聚类实现检测模型由粗到精地微调②④ |
| 文献[46] | 对抗式重构 神经网络 | 采用双层GAN+VAE,对目标函数进行显式地对抗正则化处理②③ |
| 文献[106] | 对抗式重构 神经网络 | 采用WGAN+VAE,利用梯度惩罚以及贝叶斯正则项修改目标函数②③ |
| 文献[89] | 对抗式重构 神经网络 | 采用基于对抗式训练思想的双层解码器AE②③④ |
| 文献[97] | 对抗式重构 神经网络 | 采用基于对抗式训练思想的双层解码器AE,引入Transformer层②③④ |
| 文献[104] | 对抗式重构 神经网络 | 采用双层GAN+AE②③④ |
| 文献[123] | 图注意力+重构神经网络 | 采用图结构挖掘深层次度量依赖② |
| 文献[98] | 基于关联差异的重构神经网络 | 采用基于关联差异思想的Transformer变体③④ |
| 文献[96] | 半监督重构 神经网络 | 伪标签学习③ |
| 文献[94] | 半监督重构 神经网络 | 利用主动学习修正错误结果及目标函数②③ |
), ArticleFig(id=1327012293591806975, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 8, caption=
Common Imputation Methods for Missing Values, figureFileSmall=null, figureFileBig=null, tableContent=
| 代表性工作 | 缺失值填补方法 |
|---|
| 文献[38] | 采用前一个观测值填补缺失位置 |
| 文献[40,56,106] | 采用MCMC(Markov chain Monte Carlo)插补法填补缺失位置 |
| 文献[35,77–79,86–87] | 采用线性插值法根据邻居点填补缺失位置 |
| 文献[73] | 采用缺失点所在滑动窗口的平均值填补缺失位置 |
), ArticleFig(id=1327012293667304448, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表8, caption=
常用缺失值填补方法
, figureFileSmall=null, figureFileBig=null, tableContent=
| 代表性工作 | 缺失值填补方法 |
|---|
| 文献[38] | 采用前一个观测值填补缺失位置 |
| 文献[40,56,106] | 采用MCMC(Markov chain Monte Carlo)插补法填补缺失位置 |
| 文献[35,77–79,86–87] | 采用线性插值法根据邻居点填补缺失位置 |
| 文献[73] | 采用缺失点所在滑动窗口的平均值填补缺失位置 |
), ArticleFig(id=1327012293755383808, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 9, caption=
Contribution Computing Methods of KPI Anomaly Interpretation, figureFileSmall=null, figureFileBig=null, tableContent=
| 代表性工作 | 贡献计算 |
|---|
| InterFusion[40] | 重构概率分量$ S_t^i = \dfrac{1}{L}\displaystyle\sum\limits_{l = 1}^L {\left[ {\log {p_\theta }\left( {x_t^i|{\boldsymbol{z}}_1^{\left( l \right)},{\boldsymbol{z}}_2^{\left( l \right)}} \right)} \right]} $ |
| OmniAnomaly[41] | 重构概率分量$ S_t^i = \log {p_\theta }\left( {x_t^i|{{\boldsymbol{z}}_{t - T:t}}} \right) $ |
| DAEMON[46] | 重构误差分量$ S_t^i = {\left\| {x_t^i - x_t^{i'}} \right\|_1} $ |
), ArticleFig(id=1327012293839269890, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表9, caption=
KPI异常可解释性的贡献计算方法
, figureFileSmall=null, figureFileBig=null, tableContent=
| 代表性工作 | 贡献计算 |
|---|
| InterFusion[40] | 重构概率分量$ S_t^i = \dfrac{1}{L}\displaystyle\sum\limits_{l = 1}^L {\left[ {\log {p_\theta }\left( {x_t^i|{\boldsymbol{z}}_1^{\left( l \right)},{\boldsymbol{z}}_2^{\left( l \right)}} \right)} \right]} $ |
| OmniAnomaly[41] | 重构概率分量$ S_t^i = \log {p_\theta }\left( {x_t^i|{{\boldsymbol{z}}_{t - T:t}}} \right) $ |
| DAEMON[46] | 重构误差分量$ S_t^i = {\left\| {x_t^i - x_t^{i'}} \right\|_1} $ |
), ArticleFig(id=1327012293944127491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=EN, label=Table 10, caption=
Multi-Objective Balancing-Centric KPI Anomaly Detection Techniques, figureFileSmall=null, figureFileBig=null, tableContent=
代表性 工作 | 主要应用目标 | 性能优化方式 |
|---|
| 检测技术性能优化方式可细分为7种:①数据清洗;②快速适应“概念漂移”;③提高检测效率;④降低漏报率;⑤减小告警频率;⑥“白盒”检测模型;⑦事后解释方法. |
| 文献[37] | 鲁棒性 | SR模型清洗异常① |
| 文献[72] | 鲁棒性 | 去除KPI中的趋势成分② |
| 文献[91] | 鲁棒性 | 在滑动窗口中采用一小段检测延迟② |
| 文献[117] | 鲁棒性 | 采用逆最近邻区分预期“概念漂移”与异常② |
| 文献[114] | 鲁棒性 | 采用双重差分模型判断“概念漂移”正确分类② |
| 文献[30] | 鲁棒性、 实时性 | 缺失值填补,并行计算,连续检测到5个异常点触发告警①③⑤ |
| 文献[56] | 鲁棒性、 实时性 | 缺失值填补,提出一种可接受延迟内的性能计算调整方法降低漏报率①④ |
| 文献[73] | 鲁棒性、 实时性 | 缺失值填补,提取差异特征代替基于原始特征的 学习,调整子采样技术以降低时间复杂度,仅提 取一阶、二阶差分特征以减少不必要的时间和内 存消耗①②③ |
| 文献[103] | 实时性 | 提出一种同时衡量检测延迟和精确率的新指标③ |
| 文献[49] | 实时性 | 采用基于KD-Trees的核密度估计降低时间复杂度③ |
| 文献[82] | 实时性 | 调整KPI窗口大小(控制样本长度)以降低时间复杂度③ |
| 文献[111] | 实时性 | 并行编码,利用 Chebyshev多项式降低时间复 杂度③ |
| 文献[76] | 实时性 | 将异常检测任务部署在边缘设备以减少通信量③ |
| 文献[80] | 实时性 | 利用贝叶斯网络捕获预测的不确定性估计以减少 误报⑤ |
| 文献[40] | 鲁棒性、 可解释性 | 缺失值填补,采用基于特征重要性的局部解释 方法①⑦ |
| 文献[46] | 鲁棒性、 可解释性 | SR模型清洗异常,采用基于特征重要性的局部解释方法①⑦ |
| 文献[41] | 可解释性 | 采用基于特征重要性的局部解释方法⑦ |
| 文献[69] | 可解释性 | 采用基于孤立森林的“白盒”模型(实现内在可解释 性)⑥ |
), ArticleFig(id=1327012294023819268, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011621316178824, language=CN, label=表10, caption=
以多目标平衡为核心的KPI异常检测技术
, figureFileSmall=null, figureFileBig=null, tableContent=
代表性 工作 | 主要应用目标 | 性能优化方式 |
|---|
| 检测技术性能优化方式可细分为7种:①数据清洗;②快速适应“概念漂移”;③提高检测效率;④降低漏报率;⑤减小告警频率;⑥“白盒”检测模型;⑦事后解释方法. |
| 文献[37] | 鲁棒性 | SR模型清洗异常① |
| 文献[72] | 鲁棒性 | 去除KPI中的趋势成分② |
| 文献[91] | 鲁棒性 | 在滑动窗口中采用一小段检测延迟② |
| 文献[117] | 鲁棒性 | 采用逆最近邻区分预期“概念漂移”与异常② |
| 文献[114] | 鲁棒性 | 采用双重差分模型判断“概念漂移”正确分类② |
| 文献[30] | 鲁棒性、 实时性 | 缺失值填补,并行计算,连续检测到5个异常点触发告警①③⑤ |
| 文献[56] | 鲁棒性、 实时性 | 缺失值填补,提出一种可接受延迟内的性能计算调整方法降低漏报率①④ |
| 文献[73] | 鲁棒性、 实时性 | 缺失值填补,提取差异特征代替基于原始特征的 学习,调整子采样技术以降低时间复杂度,仅提 取一阶、二阶差分特征以减少不必要的时间和内 存消耗①②③ |
| 文献[103] | 实时性 | 提出一种同时衡量检测延迟和精确率的新指标③ |
| 文献[49] | 实时性 | 采用基于KD-Trees的核密度估计降低时间复杂度③ |
| 文献[82] | 实时性 | 调整KPI窗口大小(控制样本长度)以降低时间复杂度③ |
| 文献[111] | 实时性 | 并行编码,利用 Chebyshev多项式降低时间复 杂度③ |
| 文献[76] | 实时性 | 将异常检测任务部署在边缘设备以减少通信量③ |
| 文献[80] | 实时性 | 利用贝叶斯网络捕获预测的不确定性估计以减少 误报⑤ |
| 文献[40] | 鲁棒性、 可解释性 | 缺失值填补,采用基于特征重要性的局部解释 方法①⑦ |
| 文献[46] | 鲁棒性、 可解释性 | SR模型清洗异常,采用基于特征重要性的局部解释方法①⑦ |
| 文献[41] | 可解释性 | 采用基于特征重要性的局部解释方法⑦ |
| 文献[69] | 可解释性 | 采用基于孤立森林的“白盒”模型(实现内在可解释 性)⑥ |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202330577, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330577, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330577, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330577, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1735660800000, fullTextJson=null, articleText=null, reference=null)