Article(id=1149768953108545742, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404295, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1717862400000, receivedDateStr=2024-06-09, revisedDate=1731772800000, revisedDateStr=2024-11-17, acceptedDate=null, acceptedDateStr=null, onlineDate=1752055880095, onlineDateStr=2025-07-09, pubDate=1748361600000, pubDateStr=2025-05-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752055880095, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752055880095, creator=13701087609, updateTime=1752055880095, updator=13701087609, issue=Issue{id=1149768937925165147, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='15', pageStart='6155', pageEnd='6586', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752055876475, creator=13701087609, updateTime=1768456822194, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559490207699090, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559490211893395, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=6410, endPage=6418, ext={EN=ArticleExt(id=1149768954656243935, articleId=1149768953108545742, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Material Demand Forecasting for Distribution Networks Based on Improved Particle Swarm Algorithm and Extreme Learning Machine Modeling, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problem of difficulty in constructing forecasting models caused by the characteristics of power grid materials, such as many varieties, diverse specifications, huge quantities, wide range of uses, and great influence by policies and investments. Firstly, the factors affecting the quantity of material demand for infrastructure, business expansion, and emergency repair projects were screened by the Delphi method and gray correlation analysis (GRA). Secondly, an improved particle swarm algorithm that introduced adaptive inertia factor and learning factor was utilized to adjust the optimal parameter combinations of the extreme learning machine, and train the material demand prediction models for various distribution network projects. Finally, the results of the GRA-IPSO-ELM (grey relational analysis, improved particle swarm optimization, and extreme learning machines) model were compared with the results of four common forecasting models by taking the demand of 10 kV power cables of a power grid for 2020—2022 infrastructure projects as an example. The results show that the prediction accuracy of the GRA-IPSO-ELM model is improved by 10.38%, 5.37% and 3.83% compared with the ELM model, the support vector machine model and the PSO-ELM model, which shows that the model proposed in this paper realizes accurate and efficient prediction of the quantity of material demand in the distribution network.

, correspAuthors=Zhong-hua ZHAO, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Yong-li WANG, Zhong-hua ZHAO, Yi-nuo ZHANG, Tian-yi FENG, Yi-ran LIU), CN=ArticleExt(id=1149768978026905932, articleId=1149768953108545742, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进粒子群算法和极限学习机模型的配电网物资需求预测, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

为解决电网物资品种繁多、规格多样、数量巨大、用途广泛、受政策和投资影响大等特点所导致的预测模型构建困难的问题。首先,通过德尔菲法和灰色关联分析法(gray correlation analysis,GRA)筛选影响基建、业扩及抢修项目物资需求数量的因素。其次,利用引入自适应惯性因子和学习因子的改进粒子群算法调整极限学习机的最佳参数组合,训练各类配网项目物资需求预测模型。最后,以南方电网深圳市某供电局2020—2022年基建项目10 kV电力电缆需求情况为例,将GRA-IPSO-ELM(grey relational analysis,improved particle swarm optimization,and extreme learning machines)德尔菲法和灰色关联分析法模型与常见的4种预测模型的结果进行对比。结果表明,相较于ELM模型、支持向量机模型以及PSO-ELM模型,GRA-IPSO-ELM模型预测准确率得到10.38%、5.37%、3.83%的提升,可见,所提出的模型实现了对配网物资需求数量准确且高效的预测。

, correspAuthors=赵中华, authorNote=null, correspAuthorsNote=
* 赵中华(1999—),男,汉族,河北保定人,硕士研究生。研究方向:电力物资需求预测。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=+P5wA6TOA+74Bo/s6lRAvQ==, magXml=bS29RzUNOxOAsXsJGmddog==, pdfUrl=null, pdf=Mnqm9RFXYpatQkQNkXOowg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=l6ycbf8YDDnBhmnwswpWYw==, mapNumber=null, authorCompany=null, fund=null, authors=

王永利(1980—),男,汉族,河北石家庄人,博士,教授。研究方向:电力经济管理。E-mail:

, authorsList=王永利, 赵中华, 张一诺, 冯天义, 刘怡然)}, authors=[Author(id=1172924059546435955, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wyl_2001_ren@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172924059609350517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924059546435955, language=EN, stringName=Yong-li WANG, firstName=Yong-li, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Economics and Management College, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924059689042294, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924059546435955, language=CN, stringName=王永利, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华北电力大学经济与管理学院, 北京 102206, bio={"content":"

王永利(1980—),男,汉族,河北石家庄人,博士,教授。研究方向:电力经济管理。E-mail:

"}, bioImg=null, bioContent=

王永利(1980—),男,汉族,河北石家庄人,博士,教授。研究方向:电力经济管理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])]), Author(id=1172924059743568248, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zzhlbj@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1172924059877785978, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924059743568248, language=EN, stringName=Zhong-hua ZHAO, firstName=Zhong-hua, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=Economics and Management College, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924059936506235, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924059743568248, language=CN, stringName=赵中华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=华北电力大学经济与管理学院, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])]), Author(id=1172924060024586621, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, 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=1172924060095889791, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060024586621, language=EN, stringName=Yi-nuo ZHANG, firstName=Yi-nuo, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Economics and Management College, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924060167192960, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060024586621, language=CN, stringName=张一诺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华北电力大学经济与管理学院, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])]), Author(id=1172924060251079042, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, 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=1172924060397879684, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060251079042, language=EN, stringName=Tian-yi FENG, firstName=Tian-yi, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Economics and Management College, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924060464988549, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060251079042, language=CN, stringName=冯天义, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华北电力大学经济与管理学院, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])]), Author(id=1172924060527903111, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, 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=1172924060599206281, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060527903111, language=EN, stringName=Yi-ran LIU, firstName=Yi-ran, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Economics and Management College, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924060674703754, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, authorId=1172924060527903111, language=CN, stringName=刘怡然, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华北电力大学经济与管理学院, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])])], keywords=[Keyword(id=1172924060796338571, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, orderNo=1, keyword=material demand forecasting), Keyword(id=1172924060892807564, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, orderNo=2, keyword=distribution networks), Keyword(id=1172924060951527821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, orderNo=3, keyword=extreme learning machines), Keyword(id=1172924061031219598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, orderNo=4, keyword=improved particle swarm optimisation algorithm), Keyword(id=1172924061106717071, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, orderNo=1, keyword=物资需求预测), Keyword(id=1172924061236740496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, orderNo=2, keyword=配电网), Keyword(id=1172924061291266449, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, orderNo=3, keyword=极限学习机), Keyword(id=1172924061383541138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, orderNo=4, keyword=改进粒子群优化算法)], refs=[Reference(id=1172924063581356460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=32, pageStart=3420, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=张瑞宏, journalName=建筑工程技术与设计, refType=null, unstructuredReference=张瑞宏. 电力物资采购合同管理流程探讨[J]. 建筑工程技术与设计, 2018(32): 3420., articleTitle=电力物资采购合同管理流程探讨, refAbstract=null), Reference(id=1172924063652659629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=32, pageStart=3420, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhang Ruihong, journalName=Construction Engineering Technology and Design, refType=null, unstructuredReference=Zhang Ruihong. Discussion on power material procurement contract management process[J]. Construction Engineering Technology and Design, 2018(32): 3420., articleTitle=Discussion on power material procurement contract management process, refAbstract=null), Reference(id=1172924063707185582, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=唐铭浩, journalName=工业园区110 kV智能变电站的设计与应用, refType=null, unstructuredReference=唐铭浩. 工业园区110 kV智能变电站的设计与应用[D]. 长沙: 湖南大学, 2018., articleTitle=null, refAbstract=null), Reference(id=1172924063782683056, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Tang Minghao, journalName=Design and application of 110 kV intelligent substation in industrial park, refType=null, unstructuredReference=Tang Minghao. Design and application of 110 kV intelligent substation in industrial park[D]. Changsha: Hunan University, 2018., articleTitle=null, refAbstract=null), Reference(id=1172924063837209008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=27, issue=2, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=何培颖, 唐昭媛, 傅晓菲, journalName=山东电力高等专科学校学报, refType=null, unstructuredReference=何培颖, 唐昭媛, 傅晓菲, 等. 基于机器学习的电力物资需求预测[J]. 山东电力高等专科学校学报, 2024, 27(2): 43-47., articleTitle=基于机器学习的电力物资需求预测, refAbstract=null), Reference(id=1172924063900123569, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=27, issue=2, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=He Peiying, Tang Zhaoyuan, Fu Xiaofei, journalName=Journal of Shandong Electric Power Higher Specialized School, refType=null, unstructuredReference=He Peiying, Tang Zhaoyuan, Fu Xiaofei, et al. Demand forecasting of electric power materials based on machine learning[J]. Journal of Shandong Electric Power Higher Specialized School, 2024, 27(2): 43-47., articleTitle=Demand forecasting of electric power materials based on machine learning, refAbstract=null), Reference(id=1172924063946260914, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=3, pageStart=71, pageEnd=76, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=李明, 郑逸林, 高瞻, journalName=物流技术, refType=null, unstructuredReference=李明, 郑逸林, 高瞻, 等. 基于影响因素多维融合与贝叶斯概率更新的电力物资需求预测[J]. 物流技术, 2021, 40(3): 71-76., articleTitle=基于影响因素多维融合与贝叶斯概率更新的电力物资需求预测, refAbstract=null), Reference(id=1172924064013369779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=3, pageStart=71, pageEnd=76, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Li Ming, Zheng Yilin, Gao Zhan, journalName=Logistics Technology, refType=null, unstructuredReference=Li Ming, Zheng Yilin, Gao Zhan, et al. Electricity material demand forecasting based on multidimensional fusion of influencing factors and Bayesian probability updating[J]. Logistics Technology, 2021, 40(3): 71-76., articleTitle=Electricity material demand forecasting based on multidimensional fusion of influencing factors and Bayesian probability updating, refAbstract=null), Reference(id=1172924064067895732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2017, volume=26, issue=10, pageStart=196, pageEnd=200, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=赵一鹏, 丁云峰, 姚恺丰, journalName=计算机系统应用, refType=null, unstructuredReference=赵一鹏, 丁云峰, 姚恺丰. BP神经网络误差修正的电力物资时间序列预测[J]. 计算机系统应用, 2017, 26(10): 196-200., articleTitle=BP神经网络误差修正的电力物资时间序列预测, refAbstract=null), Reference(id=1172924064122421685, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2017, volume=26, issue=10, pageStart=196, pageEnd=200, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Zhao Yipeng, Ding Yunfeng, Yao Kaifeng, journalName=Computer System Applications, refType=null, unstructuredReference=Zhao Yipeng, Ding Yunfeng, Yao Kaifeng. BP neural network error correction for time series forecasting of power supplies[J]. Computer System Applications, 2017, 26(10): 196-200., articleTitle=BP neural network error correction for time series forecasting of power supplies, refAbstract=null), Reference(id=1172924064210502070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2004, volume=null, issue=null, pageStart=239695, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Elragal H, journalName=Proceedings of the Twenty-First National, refType=null, unstructuredReference=Elragal H. Improving neural networks prediction using fuzzy-genetic model[C]// Proceedings of the Twenty-First National. Cairo: IEEE, 2004: 239695., articleTitle=Improving neural networks prediction using fuzzy-genetic model, refAbstract=null), Reference(id=1172924064298582455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=33, pageStart=163, pageEnd=164, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=牛凯, 洪芳华, 费冬, journalName=科学技术创新, refType=null, unstructuredReference=牛凯, 洪芳华, 费冬, 等. 基于Prophet算法的电力物资需求预测方法研究[J]. 科学技术创新, 2020(33): 163-164., articleTitle=基于Prophet算法的电力物资需求预测方法研究, refAbstract=null), Reference(id=1172924064353108408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=33, pageStart=163, pageEnd=164, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Niu Kai, Hong Fanghua, Fei Dong, journalName=Science and Technology Innovation, refType=null, unstructuredReference=Niu Kai, Hong Fanghua, Fei Dong, et al. Research on demand forecasting method of electric power materials based on Prophet algorithm[J]. Science and Technology Innovation, 2020(33): 163-164., articleTitle=Research on demand forecasting method of electric power materials based on Prophet algorithm, refAbstract=null), Reference(id=1172924064424411577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2014, volume=67, issue=null, pageStart=200, pageEnd=212, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Bennett J C, Stewart A R, Lu W J, journalName=Energy, refType=null, unstructuredReference=Bennett J C, Stewart A R, Lu W J. Forecasting low voltage distribution network demand profiles using a pattern recognition based expert system[J]. Energy, 2014, 67: 200-212., articleTitle=Forecasting low voltage distribution network demand profiles using a pattern recognition based expert system, refAbstract=null), Reference(id=1172924064487326138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=10, pageStart=37, pageEnd=42, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=杨楚明, 刘远鹤, 雷璟, journalName=浙江电力, refType=null, unstructuredReference=杨楚明, 刘远鹤, 雷璟, 等. 基于模糊逻辑的220 kV主变压器的主材用量估算[J]. 浙江电力, 2017, 36(10): 37-42., articleTitle=基于模糊逻辑的220 kV主变压器的主材用量估算, refAbstract=null), Reference(id=1172924064550240699, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=10, pageStart=37, pageEnd=42, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Yang Chuming, Liu Yuanhe, Lei Jing, journalName=Zhejiang Electric Power, refType=null, unstructuredReference=Yang Chuming, Liu Yuanhe, Lei Jing, et al. Estimation of main material usage of 220 kV main transformer based on fuzzy logic[J]. Zhejiang Electric Power, 2017, 36(10): 37-42., articleTitle=Estimation of main material usage of 220 kV main transformer based on fuzzy logic, refAbstract=null), Reference(id=1172924064676069820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=10, pageStart=206, pageEnd=207, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=宋斌, 宋秉虎, 沈男, journalName=时代经贸, refType=null, unstructuredReference=宋斌, 宋秉虎, 沈男, 等. 基于BP神经网络的电网建设项目物资需求预测[J]. 时代经贸, 2013(10): 206-207., articleTitle=基于BP神经网络的电网建设项目物资需求预测, refAbstract=null), Reference(id=1172924064734790077, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=10, pageStart=206, pageEnd=207, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Song Bin, Song Binghu, Shen Nan, journalName=Times Economy and Trade, refType=null, unstructuredReference=Song Bin, Song Binghu, Shen Nan, et al. Grid construction project material demand prediction based on BP neural network[J]. Times Economy and Trade, 2013(10): 206-207., articleTitle=Grid construction project material demand prediction based on BP neural network, refAbstract=null), Reference(id=1172924064822870462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=杨晶晶, 李隽, 齐志刚, journalName=2012年中国电机工程学会年会论文集, refType=null, unstructuredReference=杨晶晶, 李隽, 齐志刚, 等. 基于极限学习机的电力配网物资需求预测[C]// 2012年中国电机工程学会年会论文集. 北京: 中国电机工程学会, 2012: 1-8., articleTitle=基于极限学习机的电力配网物资需求预测, refAbstract=null), Reference(id=1172924064885785023, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Yang Jingjing, Li Jun, Qi Zhigang, journalName=2012 Proceedings of the Annual Conference of the Chinese Society of Electrical Engineering, refType=null, unstructuredReference=Yang Jingjing, Li Jun, Qi Zhigang, et al. Demand forecasting of power distribution network materials based on extreme learning machine[C]// 2012 Proceedings of the Annual Conference of the Chinese Society of Electrical Engineering. Beijing: Chinese Society for Electrical Engineering, 2012: 1-8., articleTitle=Demand forecasting of power distribution network materials based on extreme learning machine, refAbstract=null), Reference(id=1172924064944505280, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=21, pageStart=8987, pageEnd=8995, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=杨华强, 熊坚, 张鹏, journalName=科学技术与工程, refType=null, unstructuredReference=杨华强, 熊坚, 张鹏, 等. 基于改进Croston方法的多需求模式零备件预测[J]. 科学技术与工程, 2024, 24(21): 8987-8995., articleTitle=基于改进Croston方法的多需求模式零备件预测, refAbstract=null), Reference(id=1172924065082917313, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=21, pageStart=8987, pageEnd=8995, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Yang Huaqiang, Xiong Jian, Zhang Peng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Yang Huaqiang, Xiong Jian, Zhang Peng, et al. Multi-demand model spare parts forecasting based on improved Croston method[J]. Science Technology and Engineering, 2024, 24(21): 8987-8995., articleTitle=Multi-demand model spare parts forecasting based on improved Croston method, refAbstract=null), Reference(id=1172924065175192003, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=李晓娟, 张芳媛, 喻玲, journalName=科学技术与工程, refType=null, unstructuredReference=李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288., articleTitle=基于主成分分析-BP神经网络的风电备件需求预测, refAbstract=null), Reference(id=1172924065221329348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Li Xiaojuan, Zhang Fangyuan, Yu Ling, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on principal component analysis-BP neural network[J]. Science Technology and Engineering, 2024, 24(1): 281-288., articleTitle=Wind power spare parts demand forecasting based on principal component analysis-BP neural network, refAbstract=null), Reference(id=1172924065326186950, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2022, volume=54, issue=2, pageStart=17, pageEnd=24, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=韩宏泉, 吴珊, 侯本伟, journalName=哈尔滨工业大学学报, refType=null, unstructuredReference=韩宏泉, 吴珊, 侯本伟. 采用核极限学习机的短期需水量预测模型[J]. 哈尔滨工业大学学报, 2022, 54(2): 17-24., articleTitle=采用核极限学习机的短期需水量预测模型, refAbstract=null), Reference(id=1172924065372324295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2022, volume=54, issue=2, pageStart=17, pageEnd=24, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=Han Hongquan, Wu Shan, Hou Benwei, journalName=Journal of Harbin Institute of Technology, refType=null, unstructuredReference=Han Hongquan, Wu Shan, Hou Benwei. Short-term water demand prediction model using nuclear limit learning machine[J]. Journal of Harbin Institute of Technology, 2022, 54(2): 17-24., articleTitle=Short-term water demand prediction model using nuclear limit learning machine, refAbstract=null), Reference(id=1172924065460404680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=20, pageStart=185, pageEnd=188, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=徐英, 李满君, 段振兴, journalName=电子设计工程, refType=null, unstructuredReference=徐英, 李满君, 段振兴, 等. 基于灰色关联分析的短期电力负荷预测系统[J]. 电子设计工程, 2022, 30(20): 185-188, 193., articleTitle=基于灰色关联分析的短期电力负荷预测系统, refAbstract=null), Reference(id=1172924065544290761, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, doi=null, pmid=null, pmcid=null, year=2022, volume=30, issue=20, pageStart=185, pageEnd=188, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=Xu Ying, Li Manjun, Duan Zhenxing, journalName=Electronic Design Engineering, refType=null, unstructuredReference=Xu Ying, Li Manjun, Duan Zhenxing, et al. Short-term power load forecasting system based on gray correlation analysis[J]. Electronic Design Engineering, 2022, 30(20): 185-188, 193., articleTitle=Short-term power load forecasting system based on gray correlation analysis, refAbstract=null)], funds=[Fund(id=1172924063363252651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, awardId=72371101, language=CN, fundingSource=国家自然科学基金(72371101), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1172924059475132783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, xref=null, ext=[AuthorCompanyExt(id=1172924059483521392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Economics and Management College, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1172924059487715697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, companyId=1172924059475132783, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华北电力大学经济与管理学院, 北京 102206)])], figs=[ArticleFig(id=1172924061555507603, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.1, caption=Factors influencing the demand for distribution network materials, figureFileSmall=9NbOkvhEaGnhqZw6vPAtXQ==, figureFileBig=eTNaaEYdDdsWLTRH+378KA==, tableContent=null), ArticleFig(id=1172924061635199380, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图1, caption=配网物资需求影响因素, figureFileSmall=9NbOkvhEaGnhqZw6vPAtXQ==, figureFileBig=eTNaaEYdDdsWLTRH+378KA==, tableContent=null), ArticleFig(id=1172924061727474069, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.2, caption=Key influences on the quantity of 10 kV material required for each type of project, figureFileSmall=zQ+8q/EeyYhYI2fzBX1lZA==, figureFileBig=2Uv7RqhOKzn2pi50VR9SVw==, tableContent=null), ArticleFig(id=1172924061786194326, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图2, caption=各类型项目10 kV物资需求数量关键影响因素, figureFileSmall=zQ+8q/EeyYhYI2fzBX1lZA==, figureFileBig=2Uv7RqhOKzn2pi50VR9SVw==, tableContent=null), ArticleFig(id=1172924061853303191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.3, caption=Flowchart of GRA-IPSO-ELM algorithm, figureFileSmall=rlATP88sLfBUmpXl6KfhjQ==, figureFileBig=fwDbeXYpMpwN1bWf5r3lgA==, tableContent=null), ArticleFig(id=1172924061916217752, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图3, caption=GRA-IPSO-ELM算法流程图, figureFileSmall=rlATP88sLfBUmpXl6KfhjQ==, figureFileBig=fwDbeXYpMpwN1bWf5r3lgA==, tableContent=null), ArticleFig(id=1172924061966549401, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.4, caption=IPSO-ELM model prediction results, figureFileSmall=1Xm8luYl3Q5Xij74jsltQA==, figureFileBig=nPXtbCE/lfTKP6ltuRzGOA==, tableContent=null), ArticleFig(id=1172924062029463962, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图4, caption=IPSO-ELM模型预测结果, figureFileSmall=1Xm8luYl3Q5Xij74jsltQA==, figureFileBig=nPXtbCE/lfTKP6ltuRzGOA==, tableContent=null), ArticleFig(id=1172924062100767131, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.5, caption=Multi-model prediction results, figureFileSmall=p71YcEDZYP+MOqA/bu+uXg==, figureFileBig=B6xCBnqNcCOHcnMXXskgZA==, tableContent=null), ArticleFig(id=1172924062159487388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图5, caption=多模型预测结果, figureFileSmall=p71YcEDZYP+MOqA/bu+uXg==, figureFileBig=B6xCBnqNcCOHcnMXXskgZA==, tableContent=null), ArticleFig(id=1172924062218207645, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.6, caption=Comparison of decision coefficients of multiple models, figureFileSmall=zUIW9aPVC/bgH7eVkiOfyw==, figureFileBig=6qIs3Jgw9QsJJ1ygeppvdA==, tableContent=null), ArticleFig(id=1172924062281122206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图6, caption=多种模型决定系数对比, figureFileSmall=zUIW9aPVC/bgH7eVkiOfyw==, figureFileBig=6qIs3Jgw9QsJJ1ygeppvdA==, tableContent=null), ArticleFig(id=1172924062377591199, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Fig.7, caption=Comparison of training time for multiple models, figureFileSmall=1XFaN92zmuuEg5gfW3G3RQ==, figureFileBig=bnYzA7HfykVKu1wUIIcU3g==, tableContent=null), ArticleFig(id=1172924062444700064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=图7, caption=多种模型训练时间对比, figureFileSmall=1XFaN92zmuuEg5gfW3G3RQ==, figureFileBig=bnYzA7HfykVKu1wUIIcU3g==, tableContent=null), ArticleFig(id=1172924062503420321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Table 1, caption=

Internal and external influences and how they are quantified

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 量化方式
内部影响
因素
项目数量 每月项目数量
历史用量 各月(1—12月)领用总数量
年度投资 年度投资(元)
外部影响
因素
负荷增长 选取每月最高负荷反映每个月的用电负荷情况
经济发展 固定资产投资额变化幅度(导入该地区统计局固定资产投资额变化
天气环境
(降雨)
每月降雨量
天气环境
(台风)
每月平均风速
天气环境
(雷击)
每月雷电天气频率
), ArticleFig(id=1172924062557946274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=表1, caption=

内外部影响因素及其量化方式

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 量化方式
内部影响
因素
项目数量 每月项目数量
历史用量 各月(1—12月)领用总数量
年度投资 年度投资(元)
外部影响
因素
负荷增长 选取每月最高负荷反映每个月的用电负荷情况
经济发展 固定资产投资额变化幅度(导入该地区统计局固定资产投资额变化
天气环境
(降雨)
每月降雨量
天气环境
(台风)
每月平均风速
天气环境
(雷击)
每月雷电天气频率
), ArticleFig(id=1172924062666998179, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Table 2, caption=

Correlation between the quantity of materials required for infrastructure projects and the factors affecting them

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
年度投资 0.904 1 20.7
项目数量 0.898 2 20.6
负荷增长 0.872 3 19.9
经济发展 0.870 4 19.9
历史用量 0.822 5 18.9
天气环境(降雨) 0.643 6
天气环境(台风) 0.601 7
天气环境(雷击) 0.592 8
), ArticleFig(id=1172924062725718436, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=表2, caption=

基建项目物资需求数量与各影响因素的关联度

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
年度投资 0.904 1 20.7
项目数量 0.898 2 20.6
负荷增长 0.872 3 19.9
经济发展 0.870 4 19.9
历史用量 0.822 5 18.9
天气环境(降雨) 0.643 6
天气环境(台风) 0.601 7
天气环境(雷击) 0.592 8
), ArticleFig(id=1172924062792827301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Table 3, caption=

Correlation between the quantity of material requirements for the business expansion project and the factors affecting them

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
负荷增长 0.921 1 26.3
经济发展 0.886 2 25.3
历史用量 0.870 3 24.9
项目数量 0.821 4 23.5
年度投资 0.602 5
天气环境(降雨) 0.532 6
天气环境(台风) 0.521 7
天气环境(雷击) 0.497 8
), ArticleFig(id=1172924062855741862, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=表3, caption=

业扩项目物资需求数量与各影响因素的关联度

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
负荷增长 0.921 1 26.3
经济发展 0.886 2 25.3
历史用量 0.870 3 24.9
项目数量 0.821 4 23.5
年度投资 0.602 5
天气环境(降雨) 0.532 6
天气环境(台风) 0.521 7
天气环境(雷击) 0.497 8
), ArticleFig(id=1172924062922850727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Table 4, caption=

Correlation between the quantity of materials required for emergency repair projects and the factors affecting them

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
天气环境(降雨) 0.901 1 26.1
天气环境(台风) 0.892 2 25.8
天气环境(雷击) 0.867 3 25.0
负荷增长 0.801 4 23.1
经济发展 0.552 5
项目数量 0.534 6
历史用量 0.501 7
年度投资 0.490 8
), ArticleFig(id=1172924063023514024, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=表4, caption=

抢修项目物资需求数量与各影响因素的关联度

, figureFileSmall=null, figureFileBig=null, tableContent=
影响因素 关联度 排名 权重/%
天气环境(降雨) 0.901 1 26.1
天气环境(台风) 0.892 2 25.8
天气环境(雷击) 0.867 3 25.0
负荷增长 0.801 4 23.1
经济发展 0.552 5
项目数量 0.534 6
历史用量 0.501 7
年度投资 0.490 8
), ArticleFig(id=1172924063078039977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=EN, label=Table 5, caption=

Comparison of true and predicted values for multiple model test sets

, figureFileSmall=null, figureFileBig=null, tableContent=
样本编号 真实值 ELM预测 支持向量机预测 PSO-ELM预测 IPSO-ELM预测
预测值 相对
误差/%
预测值 相对误差/% 预测值 相对
误差/%
预测值 相对
误差/%
27 202.415 9 225.892 0 11.6 235.516 0 16.35 174.977 9 13.56 191.7815 5.25
28 73.225 1 69.011 0 5.75 86.420 4 18.02 83.623 5 14.20 63.834 1 12.82
29 50.117 5 35.151 0 29.86 50.213 5 0.19 55.191 2 10.12 42.412 4 15.37
30 22.108 5 27.617 0 24.92 25.446 6 15.10 23.602 4 6.76 20.540 2 7.09
31 39.038 0 34.130 2 12.57 45.221 1 15.84 44.038 0 12.81 42.851 0 9.77
32 55.724 1 44.880 0 19.46 45.783 0 17.84 62.647 0 12.42 51.526 7 7.53
33 87.374 0 108.137 0 23.76 69.469 0 20.49 68.158 0 21.99 80.535 0 7.83
34 124.143 6 156.770 1 26.28 119.602 0 3.66 108.744 4 12.40 112.679 7 9.23
35 180.538 0 214.230 0 18.66 207.502 0 14.94 151.032 0 16.34 165.967 0 8.07
36 95.634 0 77.670 0 18.78 113.909 2 19.11 90.366 8 5.51 100.303 8 4.88
平均相对误差 19.71 14.15 12.61 8.79
), ArticleFig(id=1172924063157731754, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768953108545742, language=CN, label=表5, caption=

多种模型测试集真实值与预测值对比

, figureFileSmall=null, figureFileBig=null, tableContent=
样本编号 真实值 ELM预测 支持向量机预测 PSO-ELM预测 IPSO-ELM预测
预测值 相对
误差/%
预测值 相对误差/% 预测值 相对
误差/%
预测值 相对
误差/%
27 202.415 9 225.892 0 11.6 235.516 0 16.35 174.977 9 13.56 191.7815 5.25
28 73.225 1 69.011 0 5.75 86.420 4 18.02 83.623 5 14.20 63.834 1 12.82
29 50.117 5 35.151 0 29.86 50.213 5 0.19 55.191 2 10.12 42.412 4 15.37
30 22.108 5 27.617 0 24.92 25.446 6 15.10 23.602 4 6.76 20.540 2 7.09
31 39.038 0 34.130 2 12.57 45.221 1 15.84 44.038 0 12.81 42.851 0 9.77
32 55.724 1 44.880 0 19.46 45.783 0 17.84 62.647 0 12.42 51.526 7 7.53
33 87.374 0 108.137 0 23.76 69.469 0 20.49 68.158 0 21.99 80.535 0 7.83
34 124.143 6 156.770 1 26.28 119.602 0 3.66 108.744 4 12.40 112.679 7 9.23
35 180.538 0 214.230 0 18.66 207.502 0 14.94 151.032 0 16.34 165.967 0 8.07
36 95.634 0 77.670 0 18.78 113.909 2 19.11 90.366 8 5.51 100.303 8 4.88
平均相对误差 19.71 14.15 12.61 8.79
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404295, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404295, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404295, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404295, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进粒子群算法和极限学习机模型的配电网物资需求预测
收藏切换
PDF下载
王永利 , 赵中华 * , 张一诺 , 冯天义 , 刘怡然
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(15): 6410-6418
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(15): 6410-6418
基于改进粒子群算法和极限学习机模型的配电网物资需求预测
全屏
王永利 , 赵中华* , 张一诺, 冯天义, 刘怡然
作者信息
  • 华北电力大学经济与管理学院, 北京 102206
  • 王永利(1980—),男,汉族,河北石家庄人,博士,教授。研究方向:电力经济管理。E-mail:

通讯作者:

* 赵中华(1999—),男,汉族,河北保定人,硕士研究生。研究方向:电力物资需求预测。E-mail:
Material Demand Forecasting for Distribution Networks Based on Improved Particle Swarm Algorithm and Extreme Learning Machine Modeling
Yong-li WANG , Zhong-hua ZHAO* , Yi-nuo ZHANG, Tian-yi FENG, Yi-ran LIU
Affiliations
  • Economics and Management College, North China Electric Power University, Beijing 102206, China
出版时间: 2025-05-28 doi: 10.12404/j.issn.1671-1815.2404295
文章导航
收藏切换

为解决电网物资品种繁多、规格多样、数量巨大、用途广泛、受政策和投资影响大等特点所导致的预测模型构建困难的问题。首先,通过德尔菲法和灰色关联分析法(gray correlation analysis,GRA)筛选影响基建、业扩及抢修项目物资需求数量的因素。其次,利用引入自适应惯性因子和学习因子的改进粒子群算法调整极限学习机的最佳参数组合,训练各类配网项目物资需求预测模型。最后,以南方电网深圳市某供电局2020—2022年基建项目10 kV电力电缆需求情况为例,将GRA-IPSO-ELM(grey relational analysis,improved particle swarm optimization,and extreme learning machines)德尔菲法和灰色关联分析法模型与常见的4种预测模型的结果进行对比。结果表明,相较于ELM模型、支持向量机模型以及PSO-ELM模型,GRA-IPSO-ELM模型预测准确率得到10.38%、5.37%、3.83%的提升,可见,所提出的模型实现了对配网物资需求数量准确且高效的预测。

物资需求预测  /  配电网  /  极限学习机  /  改进粒子群优化算法

In order to solve the problem of difficulty in constructing forecasting models caused by the characteristics of power grid materials, such as many varieties, diverse specifications, huge quantities, wide range of uses, and great influence by policies and investments. Firstly, the factors affecting the quantity of material demand for infrastructure, business expansion, and emergency repair projects were screened by the Delphi method and gray correlation analysis (GRA). Secondly, an improved particle swarm algorithm that introduced adaptive inertia factor and learning factor was utilized to adjust the optimal parameter combinations of the extreme learning machine, and train the material demand prediction models for various distribution network projects. Finally, the results of the GRA-IPSO-ELM (grey relational analysis, improved particle swarm optimization, and extreme learning machines) model were compared with the results of four common forecasting models by taking the demand of 10 kV power cables of a power grid for 2020—2022 infrastructure projects as an example. The results show that the prediction accuracy of the GRA-IPSO-ELM model is improved by 10.38%, 5.37% and 3.83% compared with the ELM model, the support vector machine model and the PSO-ELM model, which shows that the model proposed in this paper realizes accurate and efficient prediction of the quantity of material demand in the distribution network.

material demand forecasting  /  distribution networks  /  extreme learning machines  /  improved particle swarm optimisation algorithm
王永利, 赵中华, 张一诺, 冯天义, 刘怡然. 基于改进粒子群算法和极限学习机模型的配电网物资需求预测. 科学技术与工程, 2025 , 25 (15) : 6410 -6418 . DOI: 10.12404/j.issn.1671-1815.2404295
Yong-li WANG, Zhong-hua ZHAO, Yi-nuo ZHANG, Tian-yi FENG, Yi-ran LIU. Material Demand Forecasting for Distribution Networks Based on Improved Particle Swarm Algorithm and Extreme Learning Machine Modeling[J]. Science Technology and Engineering, 2025 , 25 (15) : 6410 -6418 . DOI: 10.12404/j.issn.1671-1815.2404295
纵观供应链各环节,需求管理是供应链的源头,是引领入网设备质量提升及择优确定供应商的基础。但由于配网物资属于专业设备,种类规格较复杂、需求数量波动较大、规律性不明显[1]等问题,对其需求数量的预测结果往往不佳,缺少以品类为导向的需求预测方法。配网物资是保证电网系统安全高效运行的基础保障,承担着电能传输和信号传递的重要工作[2],其年需求量逐步增加,对需求预测准确率提出了较高的要求。为准确地预测配网物资需求,在保障配电网物资供应可靠性的前提下节约投资成本,指导电网企业进行投资计划的制定,亟需相关领域的研究对配电网物资需求预测工作提供新思路,做出科学指导。
目前,在电力物资需求预测影响因素选取方面,何培颖等[3]综合考虑数据的易取性、可量化性,选取供货时长、项目类别、项目投资、项目建设进度、历史月份退库金额、历史月份出库金额、在途物资、库存物资、重大节日、天气状况作为预测预测模型入参。李明等[4]将电力物资需求影响因素划分为内部因素和外部因素两类,在内部因素中选取物资重要性、物资价格、物资质量、物资采购周期、物资生产周期、招投标时长、需求迫切程度等因素,在外部因素中选取计划变更、地域经济水平、地域用电规模、设备故障率、季节因素、自然灾害环保要求等。赵一鹏等[5]认为电力物资月需求量的历史统计数据是所有影响因素互相作用的结果,其中隐含包括了这些影响因素对电力物资需求影响的规律。所以,将所有外部因素对电力物资需求的影响规律作为一个复杂的、综合的规律进行表达,而不需要人为分析影响物资需求的外部因素。可见,针对电力物资需求影响因素的研究已有学者进行了多角度的尝试和探索,但是现有研究可能没有充分考虑不同类型项目(如基建项目、业扩项目、抢修项目)对物资需求的特殊影响,而这些类型项目的需求模式可能存在显著差异。
在电力物资需求预测模型方面,Elragal[6]针对阶段性电网物资供应问题进行深入研究,提出了基于模糊遗传算法的神经网络预测模型。牛凯等[7]分析各类型电网物资历史数量的变化规律,并基于Prophet算法进行电力物资预测。在配网物资需求预测方面,李明等[4]利用影响因素多维融合和贝叶斯概率更新两个工具提出新的需求预测方法,并以10 kV配网项目物资需求为例对预测模型进行验证。Bennett等[8]开发了一种由相关聚类、离散分类神经网络和后处理程序3个模块组成的新型混合专家系统,用于预测低压(低压)变压器的需求曲线。杨楚明等[9]重点研究220 kV油浸式变压器的需求特性,并结合重心法得到该类型变压器的预测值。宋斌等[10]结合电网项目的需求物资特征,采用BP(back propagation)神经网络预测方法进行预测。
杨晶晶等[11]利用基于极限学习机(extreme learning machines,ELM)模型的多任务学习方法去解决配网建设项目物资需求预测问题。杨华强等[12]针对具备间歇性与随机性特征的维修备件需求预测问题,提出了基于改进Croston方法的备件需求预测模型,解决了备件需求波动性强、间断性大的难题。李晓娟等[13]针对受多因素影响的复杂备件,先利用主成分分析(principal component analysis,PCA)将影响风电备件的要素进行筛选,再利用BP神经网络算法,得到最为精确的预测结果。现有研究取得了一些研究成果,但是一些模型可能过于依赖特定数据集或特定条件下的历史数据,限制了模型向其他类型项目和物资的泛化能力和适应性。
在总结现有研究成果的基础上,针对现有研究的不足,应用德尔菲法和灰色关联分析法(grey relational analysis,GRA),分项目类型(基建项目、业扩项目、抢修项目)筛选影响其物资需求情况的影响因子;选用泛化能力更强的极限学习机(extreme learning machines,ELM)模型,并利用改进粒子群算法(improved particle swarm optimization,PSO)对ELM参数进行优化,最终构建GRA-IPSO-ELM配网物资需求预测模型,开展基建项目、业扩项目、抢修项目物资需求预测工作。
配网物资的需求在不同的时间段内差距较大,为了极大地减少需求变化带来的损失,关键在于从引发需求不确定性的根本原因或起点开始,去探寻导致物资需求出现变化的根本因素,即需求变动的影响因素。先通过实地调研和考察初步筛选出配电网物资需求影响因素,接着通过灰色关联分析法确定不同影响因素与不同类型项目物资需求情况间的关联度,最终筛选出显著影响不同类型项目物资需求情况的影响因素,并确定各因素在输入预测模型时的权重。
应用德尔菲法进行配网物资需求预测影响因素初步识别,根据物资需求的类型向电网相应部门的专家分发问卷,收集了各种影响因子的评分,进而确定了导致配网物资需求波动的关键因素,影响因素如图1所示。
(1)年度投资。电网项目投资计划是基础设施项目和技术改造项目需求的主要驱动力,而这些投资计划是按年度周期进行的。如果投资计划额较大,涉及新建或扩建大型电力设施,那么对配网物资的需求将会大幅增加。
(2)项目数量。项目数量增加意味着需要更多的配网物资来满足这些新增的需求,包括电线、电缆、变压器、断路器、开关设备等各种类型的物资。
(3)负荷增长。负荷增长对配电网需求的影响主要涉及电网的负载能力、电缆温升和功率损耗。随着负荷的增加,可能需要电网升级改造以满足新的负荷需求,确保电力系统的稳定运行。本文中选取每月最高负荷反映每个月的用电量情况。
(4)经济发展。经济发展情况对配网物资需求的影响主要体现在固定资产投资额变化幅度,对于基建项目和业扩项目,可通过固定资产投资额变化幅度确定客户需求的变化趋势,从而预测配网物资的需求变化走势。
(5)历史用量。正如文献[5]中所述,电力物资历史需求量的历史统计数据是所有影响因素互相作用的结果,本文中选用该电网公司配网物资历史每月领用总数量反映历史用量变化情况,旨在将月度需求量作为所提出其他影响因素的补充,以期更全面的反应配电网物资需求影响因素。
(6)天气环境。降雨、台风和雷击等气象因素都会破坏配网设施,从而引发电力故障以及停电现象,配网设备检修以及更换要求大大增加,从而确保电力设施能够正常工作。本文中选取每月平均降雨量、每月平均风速、每月雷电天气频率分别反映天气情况。
基于对该电网公司实际业务的深入调查和分析,将上述的影响因子划分为内部和外部因素。内部因素包括与电网内部指标相关的各种因素,外部因素涵盖了规划、经济和环境等多个方面,具体的分类和量化结果如表1所示。
灰色关联分析法通过对各个变量数据序列的相似性进行分析,来评估变量参数间的实际关联能力,并据此进行关联度的排序[14],其主要原理为因变量和自变量的相关程度取决于两者的相似程度。计算步骤如下。
(1)建立原始数据矩阵。
X= X 0 ( 1 ) X 1 ( 1 ) X n ( 1 ) X 0 ( 2 ) X 1 ( 2 ) X n ( 2 ) X 0 ( m ) X 1 ( m ) X n ( m )
式(1)中:X为数据集合;i=0,1,2,…,n;j=1,2,…,m;X0为参考序列;Xi为比较序列。
(2)标准化处理。对数据矩阵进行标准化操作,确保每个变量的数值处于[0,1]的范围之内。公式为
X'i(j)= X i ( j ) - X i ( j ) ¯ σ
σ= j = 1 m [ X i ( j ) - X i ( j ) ¯ ] 2 m
式中:X'i(j)为标准化值; X i ( j ) ¯为平均值;σ为标准差;m为样本数据个数。
(3)计算灰色关联系数ζi(j),公式为
$\begin{aligned} \zeta_{i}(j)= & {\left[\min _{i} \min _{j}\left|X_{0}(j)-X_{i}(j)\right|+\rho \max _{i}\right.} \\ & \left.\max _{i}\left|X_{0}(j)-X_{i}(j)\right|\right] / \\ & {\left[\left|X_{0}(j)-X_{i}(j)\right|+\rho \max _{i}\right.} \\ & \left.\max _{j}\left|X_{0}(j)-X_{i}(j)\right|\right] \end{aligned} $
式(4)中:X0(j)为参考序列;Xi(j)为比较序列;ρ为分辨系数。
(4)计算灰色关联度γi(j),公式为
γi(j)= j = 1 m ζ i ( j ) m
(5)排序。根据最后关联度结果对各类型影响因素进行排序,数值越高,说明该影响因素与需求变化的相关性越强。
配网物资需求受年度投资、项目数量、负荷增长、经济发展、历史用量和天气环境等因素的影响,不同影响因素对基建项目、业扩项目及抢修项目物资需求情况的影响程度不同,灰色关联度可反映不同影响因素与不同类型项目物资需求情况之间关联强度。因此,采用灰色关联系数确定不同影响因素与不同类型项目物资需求情况间的关联度,确定在不同类型项目中对配网物资需求情况影响较大的因素,为分类预测工作奠定基础。结果如表2~表4所示。
表2~表4可知,不同类型项目物资需求情况与各影响因素之间的相关性存在一定差异,本文中选取年度投资、项目数量、负荷增长、经济发展、历史用量作为基建项目物资需求预测影响因素的入参,选取负荷增长、经济发展、历史用量、项目数量作为业扩项目物资需求预测影响因素的入参,选取降雨、台风、雷击、负荷增长作为抢修项目物资需求预测影响因素的入参,并依据关联度系数确定各因素在输入预测模型时的权重值,具体结果如图2所示。
电力物资因其专业性强、品种繁多、规格复杂、数量差异大以及需求规律性不明显等特点,导致预测模型的选择面临较大困难。ELM模型学习速度快、泛化能力强,且由于参数数量少,简化了模型训练过程。它对输入数据的噪声和异常值具有很好的鲁棒性,且不依赖于数据的统计分布,灵活性高、适应性强,易于实现和维护,且可扩展性好,能够应对不同项目类型和物资种类。但仍然需要确定隐藏层节点的数量和权重等关键参数,改进后的IPSO算法避免了算法陷入局部最优解,可有效帮助ELM模型确定隐藏层节点的数量和权重等关键参数的最优组合,达到节省人工调参时间、提高模型泛化能力、减小预测误差的目的。
ELM模型相较于神经网络的训练方式,有能力随机生成输入与隐藏层之间的权重系数以及隐藏层神经元的阈值,无需对训练成果做出任何修改,仅需设置合适的隐藏层神经元数量,就能达到最佳的训练效果[15]
在ELM模型中,任意给定U个不同月份物资需求数据及对应影响因素入参(xφ,yφ),xφ为第φ个样本的影响因素入参,则xφ= [ x φ 1 , x φ 2 , , x φ u ] TRu,Ru为影响因素入参数据组;yφ为对应于xφ的物资需求数据输出,则yφ=[yφ1, yφ2, …, yφm]TRm,Rm为输出数据组,φ=1,2,…,Uωρ= [ ω ρ 1 , ω ρ 2 , , ω ρ u ] T为输入和隐含层之间权重,Bλ=[Bλ1,Bλ2,…,BλL]T为隐含层和输出层之间权重,bδ=[b1,b2,…,bL]T为隐含层第δ个神经元的阈值,g(ω,x,b)为激活函数,最终输出结果为
F(x)= φ = 1 U[Bλg(ωρxφ+bδ)]
H作为隐含层输出矩阵,Y作为期望输出矩阵,简化可得
HB=Y,Y=[y1,y2,…,yU]
H= g ( ω 1 x 1 + b 1 ) , g ( ω 2 x 1 + b 2 ) , , g ( ω L x 1 + b L ) g ( ω 1 x 2 + b 1 ) , g ( ω 2 x 2 + b 2 ) , , g ( ω L x 2 + b L ) g ( ω 1 x U + b 1 ) , g ( ω 2 x U + b 2 ) , , g ( ω L x U + b L )
H的逆为H+,则B的取值可以表示为
B=H+Y
PSO首先随机设定粒子的速度和位置,其次通过持续的迭代来解决预设的目标函。在D维搜索区域中,s个粒子位置Xs和最佳位置PsXs= [ X s 1 , X s 2 , , X s D ] T,Ps= [ P s 1 , P s 2 , , P s D ] T,粒子s的速度Vs= [ V s 1 , V s 2 , , V s D ] T。则可由式(10)、式(11)计算粒子自身的速度和位置。
V s d τ + 1=w V s d τ+c1σ1( P s d τ- X s d τ)+c2σ2( P g d τ- X s d τ)
X s d τ + 1= X s d τ+ V s d τ + 1
式中: V s d τ为粒子的速度; X s d τ为粒子的位置; P s d τ为局部最优解; P g d τ为全局最优解;c1c2为学习因子;σ1σ2为随机取值;τ为当前迭代次数;w为惯性因子;d不为0。
可知,粒子速度设定的大小影响了算法的收敛速度。当粒子速度过快时,算法的收敛速度也会加快,但这可能会超出最优解的范围;当粒子速度太慢时,算法的收敛速度也会减缓,容易陷入局部最优解,同时粒子的速度与惯性因子和学习因子有着密切的关联。因此,本研究对wc1c2进行调整,在避免陷入局部最优解的情况下进行寻优。
上一代粒子速度能够对下一代速度产生的影响程度由惯性因子表示。惯性因子的取值大小影响模型的全局搜索能力以及局部搜索能力。已有的粒子群算法为惯性权重设定一个固定值,本文中引入自适应惯性权重,其表达式为
w=wmin- 1 2(wmax-wmin) 1 + c o s ( τ - 1 ) π τ m a x - 1
式(12)中:wmaxwmin作为惯性因子的最大值和最小值,参数设置为0.1~1;迭代次数的最大设为τmax
由式(12)可知:当粒子的适应度超过了群体的平均适应度,通常为这个粒子分配更大的惯性权重,从而增强其独立搜索的意识;当一个粒子的适应能力低于整个群体的平均适应度时,应将该粒子设置更低的惯性权重,以增强群体的搜索意识。在算法的初步迭代阶段,为粒子分配了较高的惯性权重,保证全局搜寻能力,在迭代后期,群体的平均适应度逐渐降低,粒子的惯性权重大幅减少,算法的局部搜索能力得到提升,优化了算法的效率。
个体学习因子c1和社会学习因子c2分别反映个体学习信息和群体学习信息在寻优过程中对寻优方式的影响。当c1的值较大时,各粒子倾向于在自身周边搜索,个体独立搜索的意识较强;当c2的值较大时,容易出现粒子聚集,落入局部最优解。因此,在设置算法参数时使c1的取值较大、c2的取值较小,让c1的值在迭代时逐渐递减、c2的值逐渐递增,从而使得算法向全局最优点收敛。c1c2取值变化为
c1=c1, ini+(c1, fin-c1, ini) τ η τ m a x
c2=c2, ini+(c2, fin-c2, ini) τ η τ m a x
式中:c1, ini c1, fin c2, ini c2, fin 分别为c1c2的初始值、迭代终止值,c1, ini c1, fin c2, ini c2, fin 的取值范围通常设置为0~4;η为缩放系数,取值设置在1~2。
GRA-IPSO-ELM预测模型的主要思想:首先基于GRA对3类项目的影响因素进行初步筛选,确定预测模型的入参,利用经过调整的IPSO卓越的全局搜索功能,对ELM模型进行了深度优化,从而确定了ELM网络的最优初始权重和隐藏层的偏置值,最后成功构建了ELM极限学习机模型。以下是具体的执行步骤。
(1)基于德尔菲法初步识别配电网物资需求影响因素,基于GRA进行基建项目、业扩项目和抢修项目配电网物资需求量与影响因素关联度分析,筛选各类型项目关键影响因素,确定预测模型入参。
(2)根据输入指标和输出指标的具体数量设定ELM模型各层级神经元数,隐藏层神经元数设定依据由式(15)确定,该隐藏层神经元数目为7。
L= n + m+∂
式(15)中:∂为常量,取值范围为0<∂<10。
(3)设置IPSO算法中的参数,包括种群规模、迭代次数、惯性权重、学习因子、粒子特征等。
(4)输出粒子适应度大小并对其更新最大值,迭代到第τ代时的适应度值计算式为
R2=1- i ( y i - y i ) 2 i ( y i - y - ) 2
式(16)中: y i为预测结果;yi为真实数据。根据最新适应度与个体最优位置pbest 的适应度值中较大的结果,更新pbest 。根据当前粒子最小适应度值和群体最优位置gbest 的适应度值中较大的结果,更新gbest
(5)根据式(12)~式(14)的规则,对粒子的速度和位置进行了相应的调整。在完成更新之后,需要判断粒子的速度和位置是否超出了最大边界值或最小边界值,如果粒子的移动速度和位置都超出边界值,那么就将其设定为边界值。
(6)需要评估迭代的次数以及误差的准确性是否达到了预期标准。如果满足条件,就停止迭代,如果不满足,则转向步骤(3)。
(7)将步骤(5)记录的最优解用ELM极限学习机模型进行学习训练,并将其用于配网物资需求预测。
GRA-IPSO-ELM预测模型的算法流程图如图3所示。
中以南方电网深圳市供电局2020—2022年36个月度基建项目10 kV电力电缆需求情况为数据基础设计算例,仿真分析在SPSS及Matlab软件环境下实现。
在Matlab环境下,将样本集中前26个样本以及后10个样本作为训练样本和测试样本。设置ELM模型输入层、隐含层以及输出层神经元数目分别为5、7、1,激活函数设为S形。设置IPSO算法种群规模大小N=100,个体学习因子的初值c1, ini =2.5和终值c1, fin =0.5,社会学习因子初值c2, ini =0.5和终值c2, fin =2.5,缩放系数η=0.5,惯性权重最大值wmax=1和最小值wmin=0.2,粒子的位置范围为[-1,1],速度范围为[-0.5,0.5],迭代次数最大T=200。
IPSO-ELM模型预测结果如图4所示,训练集数据与测试集数据的预测曲线与实际曲线的趋势均相符并且拟合程度较好,同时其误差也相对较小。
为了证明IPSO-ELM模型在10 kV电力电缆预测中的优越性,将IPSO-ELM算法、PSO-ELM算法、未经PSO模型优化的ELM以及支持向量机算法进行了详细的比较实验。PSO-ELM模型的参数配置如下:学习因子c1=c2=2,权重w=1,其余参数设置与IPSO-ELM神经网络模型的一致。ELM模型以及支持向量机模型参数则采用系统默认的参数。
图5所示为训练集、测试集4种模型10 kV电力电缆需求量预测结果和真实值之间的拟合曲线。表5反映4种预测模型真实值与预测值之间的相对误差并进行对比。
观察图5(b)的拟合曲线,ELM模型预测值的偏差较大,支持向量机预测结果与真实值之间的变化趋势一致,但仍然具有较大的偏差。PSO-ELM模型的预测结果准确率相对于ELM模型得到提升,但仍有个别值偏差较大。IPSO-ELM模型预测曲线拟合程度高,预测结果较为可靠。
表5显示了4种预测模型输出测试集结果和真实值之间的误差大小,ELM模型测试集误差处于25%左右,个别取值误差接近30%,预测效果较差。支持向量机模型测试结果大多小于20%,但仍有个别值误差较大。PSO-ELM模型测试集相对误差在5%~22%波动,预测稳定性较差。IPSO-ELM模型测试集误差大多数情况下都低于16%,且平均相对误差较小,因此,本文中引入的IPSO-ELM模型显著地增强了预测的准确性和结果的信赖度。
在本案例中,预测模型效率主要采用决定系数R2和训练时间进行评估。决定系数R2的取值范围是[0,1],数值越靠近1,预测拟合效果越佳;从图6可以看出,IPSO-ELM模型相比其他3种算法整个集合的决定系数都非常接近1,显示出该模型预测结果的高拟合效果。
图7为4种模型训练时间对比,ELM模型相较于支持向量机预测模型具有快速训练及预测的优点。未经优化的ELM训练时间则为16 s,相比之下,IPSO-ELM模型训练结果为10 s,这主要源于传统ELM训练中输入权重和阈值是随机产生的,需要多次参数调整以提高预测精度和确定系数。
由上述模型对比实验可以看出,通过GRA筛选出关键影响因素,能够避免影响因素之间的冗余性、相关性,这为模型提供了坚实的数据支撑。ELM模型避免了传统机器学习模型(如支持向量机)可能由于样本数量太少或数据量过大而导致训练时间过长的问题,在此基础上通过IPSO算法优化神经网络的初始输入权重和阈值,避免了算法寻优的盲目性,提升了预测精度,从而使预测模型得到较为良好预测结果。
电力物资的专业性强、品种多、规格杂、数量差异大、数量规律性不显著,故电力物资需求具有高复杂性和高不确定性的特点,由此导致现阶段电力物资需求预测工作预测主体不清晰,预测规则不明确,依赖于手工录入重复数据,工作量大且效率低下,亟需开发一种能覆盖大部分项目类型和物资种类的智能化、高精准物资需求预测模型。因此,本文开展配电网物资需求预测工作,并得到如下结论。
(1)提出了一种基于德尔菲法和GRA法的电力物资需求影响因素筛选方法。首先,充分考虑多方面、多角度的配电网物资需求影响因素,通过德尔菲法,广泛收集电网各部门专家意见,初步识别影响配电网物资需求的内外部因素。随后,应用GRA法对这些因素进行深入分析,量化它们与物资需求变化之间的关联度,并通过排序筛选出最具影响的因素,提高需求预测模型的精确度。
(2)构建了一种GRA-IPSO-ELM配电网物资需求预测模型。在PSO算法基础上引入自适应惯性因子和学习因子提高全局寻优能力,并通过IPSO算法对ELM网络进行调整优化,构造GRA-IPSO-ELM配电网物资需求预测模型。构建算例,将IPSO-ELM模型与其他3种预测模型对。结果表明:相较于ELM模型、支持向量机模型与PSO-ELM模型,IPSO-ELM模型在预测准确率上提升10.38%、5.37%、3.83%,能够迅速且高效地预测配网物资的数量。
本文所提方法实现了对配电网物资需求数量进行快速高效的预测,有助于电力部门在保障工程进度的前提下提高资金的利用率、节约成本。此外,主要凭借德尔菲法和GRA法进行影响因素筛选,未来可通过增加影响因素、进一步分析影响因素特征及其与预测目标的相互作用机理,优化预测模型输入参数,提高配电网预测模型应用的高效性和可靠性。
  • 国家自然科学基金(72371101)
参考文献 引证文献
排序方式:
[1]
张瑞宏. 电力物资采购合同管理流程探讨[J]. 建筑工程技术与设计, 2018(32): 3420.
Zhang Ruihong. Discussion on power material procurement contract management process[J]. Construction Engineering Technology and Design, 2018(32): 3420.
[2]
唐铭浩. 工业园区110 kV智能变电站的设计与应用[D]. 长沙: 湖南大学, 2018.
Tang Minghao. Design and application of 110 kV intelligent substation in industrial park[D]. Changsha: Hunan University, 2018.
[3]
何培颖, 唐昭媛, 傅晓菲, 等. 基于机器学习的电力物资需求预测[J]. 山东电力高等专科学校学报, 2024, 27(2): 43-47.
He Peiying, Tang Zhaoyuan, Fu Xiaofei, et al. Demand forecasting of electric power materials based on machine learning[J]. Journal of Shandong Electric Power Higher Specialized School, 2024, 27(2): 43-47.
[4]
李明, 郑逸林, 高瞻, 等. 基于影响因素多维融合与贝叶斯概率更新的电力物资需求预测[J]. 物流技术, 2021, 40(3): 71-76.
Li Ming, Zheng Yilin, Gao Zhan, et al. Electricity material demand forecasting based on multidimensional fusion of influencing factors and Bayesian probability updating[J]. Logistics Technology, 2021, 40(3): 71-76.
[5]
赵一鹏, 丁云峰, 姚恺丰. BP神经网络误差修正的电力物资时间序列预测[J]. 计算机系统应用, 2017, 26(10): 196-200.
Zhao Yipeng, Ding Yunfeng, Yao Kaifeng. BP neural network error correction for time series forecasting of power supplies[J]. Computer System Applications, 2017, 26(10): 196-200.
[6]
Elragal H. Improving neural networks prediction using fuzzy-genetic model[C]// Proceedings of the Twenty-First National. Cairo: IEEE, 2004: 239695.
[7]
牛凯, 洪芳华, 费冬, 等. 基于Prophet算法的电力物资需求预测方法研究[J]. 科学技术创新, 2020(33): 163-164.
Niu Kai, Hong Fanghua, Fei Dong, et al. Research on demand forecasting method of electric power materials based on Prophet algorithm[J]. Science and Technology Innovation, 2020(33): 163-164.
[8]
Bennett J C, Stewart A R, Lu W J. Forecasting low voltage distribution network demand profiles using a pattern recognition based expert system[J]. Energy, 2014, 67: 200-212.
[9]
杨楚明, 刘远鹤, 雷璟, 等. 基于模糊逻辑的220 kV主变压器的主材用量估算[J]. 浙江电力, 2017, 36(10): 37-42.
Yang Chuming, Liu Yuanhe, Lei Jing, et al. Estimation of main material usage of 220 kV main transformer based on fuzzy logic[J]. Zhejiang Electric Power, 2017, 36(10): 37-42.
[10]
宋斌, 宋秉虎, 沈男, 等. 基于BP神经网络的电网建设项目物资需求预测[J]. 时代经贸, 2013(10): 206-207.
Song Bin, Song Binghu, Shen Nan, et al. Grid construction project material demand prediction based on BP neural network[J]. Times Economy and Trade, 2013(10): 206-207.
[11]
杨晶晶, 李隽, 齐志刚, 等. 基于极限学习机的电力配网物资需求预测[C]// 2012年中国电机工程学会年会论文集. 北京: 中国电机工程学会, 2012: 1-8.
Yang Jingjing, Li Jun, Qi Zhigang, et al. Demand forecasting of power distribution network materials based on extreme learning machine[C]// 2012 Proceedings of the Annual Conference of the Chinese Society of Electrical Engineering. Beijing: Chinese Society for Electrical Engineering, 2012: 1-8.
[12]
杨华强, 熊坚, 张鹏, 等. 基于改进Croston方法的多需求模式零备件预测[J]. 科学技术与工程, 2024, 24(21): 8987-8995.
Yang Huaqiang, Xiong Jian, Zhang Peng, et al. Multi-demand model spare parts forecasting based on improved Croston method[J]. Science Technology and Engineering, 2024, 24(21): 8987-8995.
[13]
李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288.
Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on principal component analysis-BP neural network[J]. Science Technology and Engineering, 2024, 24(1): 281-288.
[14]
韩宏泉, 吴珊, 侯本伟. 采用核极限学习机的短期需水量预测模型[J]. 哈尔滨工业大学学报, 2022, 54(2): 17-24.
Han Hongquan, Wu Shan, Hou Benwei. Short-term water demand prediction model using nuclear limit learning machine[J]. Journal of Harbin Institute of Technology, 2022, 54(2): 17-24.
[15]
徐英, 李满君, 段振兴, 等. 基于灰色关联分析的短期电力负荷预测系统[J]. 电子设计工程, 2022, 30(20): 185-188, 193.
Xu Ying, Li Manjun, Duan Zhenxing, et al. Short-term power load forecasting system based on gray correlation analysis[J]. Electronic Design Engineering, 2022, 30(20): 185-188, 193.
2025年第25卷第15期
PDF下载
369
153
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404295
  • 接收时间:2024-06-09
  • 首发时间:2025-07-09
  • 出版时间:2025-05-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-09
  • 修回日期:2024-11-17
基金
国家自然科学基金(72371101)
作者信息
    华北电力大学经济与管理学院, 北京 102206

通讯作者:

* 赵中华(1999—),男,汉族,河北保定人,硕士研究生。研究方向:电力物资需求预测。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404295
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏