Article(id=1215700815067665279, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700809971581533, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202312188, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1701705600000, receivedDateStr=2023-12-05, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1767775260940, onlineDateStr=2026-01-07, pubDate=1716566400000, pubDateStr=2024-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1767775260940, onlineIssueDateStr=2026-01-07, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1767775260940, creator=13701087609, updateTime=1767775260940, updator=13701087609, issue=Issue{id=1215700809971581533, tenantId=1146029695717560320, journalId=1210938733613449225, year='2024', volume='53', issue='5', pageStart='1', pageEnd='148', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1767775259725, creator=13701087609, updateTime=1767775403954, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1215701414953796264, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700809971581533, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1215701414953796265, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700809971581533, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=132, endPage=140, ext={EN=ArticleExt(id=1215700815365460874, articleId=1215700815067665279, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Prediction of solar irradiation based on interpretable deep learning, columnId=1211002409397129992, journalTitle=Thermal Power Generation, columnName=Power generation technology forum, runingTitle=null, highlight=null, articleAbstract=

Accurately predicting solar irradiation (SI) is crucial for power scheduling and photovoltaic site selection. With the development of high-performance computing and large-capacity storage devices, data-driven deep learning models have gained widespread attentions in the SI prediction domain. However, the lack of physical interpretability due to the “black-box” nature of deep learning models restricts their credibility in specific scenarios. To enhance the interpretability of the model on the premise of maintaining prediction accuracy and keeping the model structure unchanged, and without increasing computational complexity, a model based on long short-term memory (LSTM) neural network is constructed, demonstrating an 8.07% performance improvement over the conventional neural networks and showing superior outlier handling capabilities. By employing layer-wise relevance propagation (LRP) algorithm, factors influencing the model output are scored from both temporal and spatial dimensions, enhancing the model’s interpretability. The research results indicate that the model possesses good interpretability under the premise of ensuring performance, with historical solar irradiation, time-related features (such as hour, day, week, month), solar altitude information (such as sunrise and sunset times), cloud cover, radiation time, temperature, and dew point temperature being the main factors influencing SI prediction.

, correspAuthors=null, 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=Ang LI, Leijin ZHOU, Qunmin YAN, Haiyu HE), CN=ArticleExt(id=1215700818410524716, articleId=1215700815067665279, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于可解释性深度学习的太阳辐射强度预测, columnId=1211002409581679375, journalTitle=热力发电, columnName=发电技术论坛, runingTitle=null, highlight=null, articleAbstract=

准确预测太阳辐射强度(SI)对电力调度和光伏选址至关重要。随着高性能计算机和大容量存储设备的发展,基于数据驱动的深度学习模型在SI预测领域获得广泛关注,然而,深度学习模型的“黑箱”特性在物理解释性上的缺失,限制了其在特定场合的应用可信度。为了在保持预测精度和模型结构不变、不增加计算复杂度的前提下,提升模型的可解释性,构建了一个基于长短时记忆(LSTM)神经网络的模型。其性能比传统神经网络提高了8.07%,并展示出更优的离群点处理能力。通过采用分层相关传播(LRP)算法,从时间和空间2个维度对影响模型输出的因素进行了评分,增强了模型的可解释性。研究结果表明:该模型在确保性能的前提下,具备良好的可解释性,其中历史辐射强度、时间相关特征(如时日周月)、太阳高度角信息(如日出和日落时刻)、云层覆盖度、辐射时长、温度和露点温度等因素是影响太阳辐射强度预测的主要因素。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
周雷金(1999),男,硕士研究生,主要研究方向为深度学习在新能源发电中的应用,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=qq4fdm46LtDgvLSJLb6VSw==, magXml=F8bGFtKmN9zj8CDQO65m1g==, pdfUrl=null, pdf=s+9BVQ8ILVlPJBX1/KcLtA==, pdfFileSize=1771097, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Xa6UASV0tSBE89onIsLx4Q==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=7kIuLwmeqzx6PdCszo3MDA==, mapNumber=null, authorCompany=null, fund=null, authors=

李昂(1971),男,硕士,教授,主要研究方向为电能质量分析及光伏发电技术,

, authorsList=李昂, 周雷金, 闫群民, 贺海育)}, authors=[Author(id=1215700818750263364, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=la1011@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700818972561483, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700818750263364, language=EN, stringName=Ang LI, firstName=Ang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700819081613392, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700818750263364, language=CN, stringName=李昂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=陕西理工大学电气工程学院,陕西 汉中 723000, bio={"content":"

李昂(1971),男,硕士,教授,主要研究方向为电能质量分析及光伏发电技术,

"}, bioImg=null, bioContent=

李昂(1971),男,硕士,教授,主要研究方向为电能质量分析及光伏发电技术,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700818653794362, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, xref=null, ext=[AuthorCompanyExt(id=1215700818662182971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China), AuthorCompanyExt(id=1215700818670571580, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=陕西理工大学电气工程学院,陕西 汉中 723000)])]), Author(id=1215700820331515993, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Zhou99723000@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700820558008424, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700820331515993, language=EN, stringName=Leijin ZHOU, firstName=Leijin, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700820637700205, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700820331515993, language=CN, stringName=周雷金, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=陕西理工大学电气工程学院,陕西 汉中 723000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700818653794362, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, xref=null, ext=[AuthorCompanyExt(id=1215700818662182971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China), AuthorCompanyExt(id=1215700818670571580, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=陕西理工大学电气工程学院,陕西 汉中 723000)])]), Author(id=1215700820771917938, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, 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=1215700820922912892, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700820771917938, language=EN, stringName=Qunmin YAN, firstName=Qunmin, middleName=null, lastName=YAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700821036159107, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700820771917938, language=CN, stringName=闫群民, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=陕西理工大学电气工程学院,陕西 汉中 723000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700818653794362, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, xref=null, ext=[AuthorCompanyExt(id=1215700818662182971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China), AuthorCompanyExt(id=1215700818670571580, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=陕西理工大学电气工程学院,陕西 汉中 723000)])]), Author(id=1215700821166182538, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, 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=1215700821359120535, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700821166182538, language=EN, stringName=Haiyu HE, firstName=Haiyu, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700821480755357, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, authorId=1215700821166182538, language=CN, stringName=贺海育, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=陕西理工大学电气工程学院,陕西 汉中 723000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700818653794362, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, xref=null, ext=[AuthorCompanyExt(id=1215700818662182971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China), AuthorCompanyExt(id=1215700818670571580, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=陕西理工大学电气工程学院,陕西 汉中 723000)])])], keywords=[Keyword(id=1215700821682081961, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, orderNo=1, keyword=solar irradiation prediction), Keyword(id=1215700821782745264, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1215700821904380086, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, orderNo=3, keyword=interpretability), Keyword(id=1215700822030209214, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, orderNo=4, keyword=LRP algorithm), Keyword(id=1215700822147649735, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, orderNo=5, keyword=LSTM), Keyword(id=1215700822290256075, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, orderNo=1, keyword=太阳辐射强度预测), Keyword(id=1215700822390919374, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1215700822474805462, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, orderNo=3, keyword=可解释性), Keyword(id=1215700822562885854, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, orderNo=4, keyword=LRP算法), Keyword(id=1215700822655160548, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, orderNo=5, keyword=LSTM)], refs=[Reference(id=1215700827898040776, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=305, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ACIKGOZ H, journalName=Applied Energy, refType=null, unstructuredReference=ACIKGOZ H. A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting[J]. Applied Energy, 2022, 305: 117912., articleTitle=A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting, refAbstract=null), Reference(id=1215700827973538252, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=167, issue=null, pageStart=333, pageEnd=342, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=NARVAEZ G, GIRALDO L F, BRESSAN M, journalName=Renewable Energy, refType=null, unstructuredReference=NARVAEZ G, GIRALDO L F, BRESSAN M, et al. Machine learning for site-adaptation and solar radiation forecasting[J]. Renewable Energy, 2021, 167: 333-342., articleTitle=Machine learning for site-adaptation and solar radiation forecasting, refAbstract=null), Reference(id=1215700828078395859, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=162, issue=null, pageStart=249, pageEnd=256, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=ESPINOSA A R, BRESSAN M, GIRALDO L F, journalName=Renewable Energy, refType=null, unstructuredReference=ESPINOSA A R, BRESSAN M, GIRALDO L F. Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks[J]. Renewable Energy, 2020, 162: 249-256., articleTitle=Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks, refAbstract=null), Reference(id=1215700829382824407, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=162, issue=null, pageStart=1665, pageEnd=1683, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=GAO B, HUANG X, SHI J, journalName=Renewable Energy, refType=null, unstructuredReference=GAO B, HUANG X, SHI J, et al. Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks[J]. Renewable Energy, 2020, 162: 1665-1683., articleTitle=Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks, refAbstract=null), Reference(id=1215700829600928222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=235, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=ZHOU Y, LIU Y, WANG D, journalName=Energy Conversion and Management, refType=null, unstructuredReference=ZHOU Y, LIU Y, WANG D, et al. A review on global solar radiation prediction with machine learning models in a comprehensive perspective[J]. Energy Conversion and Management, 2021, 235: 113960., articleTitle=A review on global solar radiation prediction with machine learning models in a comprehensive perspective, refAbstract=null), Reference(id=1215700829705785825, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2011, volume=8, issue=8, pageStart=795, pageEnd=819, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=KHATIB T, MOHAMED A, MAHMOUD M, journalName=International Journal of Green Energy, refType=null, unstructuredReference=KHATIB T, MOHAMED A, MAHMOUD M, et al. Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia[J]. International Journal of Green Energy, 2011, 8(8): 795-819., articleTitle=Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia, refAbstract=null), Reference(id=1215700829819032038, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=8, pageStart=10052, pageEnd=10073, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=BAMISILE O, OLUWASANMI A, EJIYI C, journalName=International Journal of Energy Research, refType=null, unstructuredReference=BAMISILE O, OLUWASANMI A, EJIYI C, et al. Comparison of machine learning and deep learning algorithms for hourly global/diffuse solar radiation predictions[J]. International Journal of Energy Research, 2022, 46(8): 10052-10073., articleTitle=Comparison of machine learning and deep learning algorithms for hourly global/diffuse solar radiation predictions, refAbstract=null), Reference(id=1215700829898723816, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2010, volume=84, issue=8, pageStart=1468, pageEnd=1480, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=BEHRANG M A, ASSAREH E, GHANBARZADEH A, journalName=Solar Energy, refType=null, unstructuredReference=BEHRANG M A, ASSAREH E, GHANBARZADEH A, et al. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data[J]. Solar Energy, 2010, 84(8): 1468-1480., articleTitle=The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data, refAbstract=null), Reference(id=1215700830011970026, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2006, volume=31, issue=15, pageStart=3435, pageEnd=3445, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=CAO J C, CAO S H, journalName=Energy, refType=null, unstructuredReference=CAO J C, CAO S H. Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis[J]. Energy, 2006, 31(15): 3435-3445., articleTitle=Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis, refAbstract=null), Reference(id=1215700830100050414, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2015, volume=122, issue=null, pageStart=1398, pageEnd=1408, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=AHMAD A, ANDERSON T N, LIE T T, journalName=Solar Energy, refType=null, unstructuredReference=AHMAD A, ANDERSON T N, LIE T T. Hourly global solar irradiation forecasting for New Zealand[J]. Solar Energy, 2015, 122: 1398-1408., articleTitle=Hourly global solar irradiation forecasting for New Zealand, refAbstract=null), Reference(id=1215700830221685230, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2016, volume=90, issue=null, pageStart=481, pageEnd=492, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=SHARMA V, YANG D, WALSH W, journalName=Renewable Energy, refType=null, unstructuredReference=SHARMA V, YANG D, WALSH W, et al. Short term solar irradiance forecasting using a mixed wavelet neural network[J]. Renewable Energy, 2016, 90: 481-492., articleTitle=Short term solar irradiance forecasting using a mixed wavelet neural network, refAbstract=null), Reference(id=1215700830322348531, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=156, issue=null, pageStart=279, pageEnd=289, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=PANG Z, NIU F, O’NEILL Z, journalName=Renewable Energy, refType=null, unstructuredReference=PANG Z, NIU F, O’NEILL Z. Solar radiation prediction using recurrent neural network and artificial neural network: a case study with comparisons[J]. Renewable Energy, 2020, 156: 279-289., articleTitle=Solar radiation prediction using recurrent neural network and artificial neural network: a case study with comparisons, refAbstract=null), Reference(id=1215700830402040310, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=917, pageEnd=920, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=ASLAM M, SEUNG K H, LEE S J, journalName=null, refType=null, unstructuredReference=ASLAM M, SEUNG K H, LEE S J, et al. Long-term solar radiation forecasting using a deep learning approach-GRUs[C]//2019 IEEE 8th International Conference on Advanced Power System Automation and Protection (APAP). IEEE, 2019: 917-920., articleTitle=Long-term solar radiation forecasting using a deep learning approach-GRUs, refAbstract=null), Reference(id=1215700830494315003, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2018, volume=162, issue=null, pageStart=232, pageEnd=247, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=SRIVASTAVA S, LESSMANN S, journalName=Solar Energy, refType=null, unstructuredReference=SRIVASTAVA S, LESSMANN S. A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data[J]. Solar Energy, 2018, 162: 232-247., articleTitle=A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data, refAbstract=null), Reference(id=1215700830574006783, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=OBIORA C N, ALI A, HASAN A N, journalName=null, refType=null, unstructuredReference=OBIORA C N, ALI A, HASAN A N. Forecasting hourly solar irradiance using long short-term memory (LSTM) network[C]//2020 11th International Renewable Energy Congress (IREC). IEEE, 2020: 1-6., articleTitle=Forecasting hourly solar irradiance using long short-term memory (LSTM) network, refAbstract=null), Reference(id=1215700830683058690, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=295, issue=1, pageStart=292, pageEnd=305, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=GUNNARSSON B R, VANDEN BROUCKE S, BAESENS B, journalName=European Journal of Operational Research, refType=null, unstructuredReference=GUNNARSSON B R, VANDEN BROUCKE S, BAESENS B, et al. Deep learning for credit scoring: do or don’t?[J]. European Journal of Operational Research, 2021, 295(1): 292-305., articleTitle=Deep learning for credit scoring: do or don’t?, refAbstract=null), Reference(id=1215700830792110599, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=91, issue=4, pageStart=2330, pageEnd=2342, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=MIGNAN A, BROCCARDO M, journalName=Seismological Research Letters, refType=null, unstructuredReference=MIGNAN A, BROCCARDO M. Neural network applications in earthquake prediction (1994—2019): Meta-analytic and statistical insights on their limitations[J]. Seismological Research Letters, 2020, 91(4): 2330-2342., articleTitle=Neural network applications in earthquake prediction (1994—2019): Meta-analytic and statistical insights on their limitations, refAbstract=null), Reference(id=1215700830884385289, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=113, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=SHAMSHIRBAND S, FATHI M, DEHZANGI A, journalName=Journal of Biomedical Informatics, refType=null, unstructuredReference=SHAMSHIRBAND S, FATHI M, DEHZANGI A, et al. A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues[J]. Journal of Biomedical Informatics, 2021, 113: 103627., articleTitle=A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues, refAbstract=null), Reference(id=1215700830968271373, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=DAS A, RAD P, journalName=arXiv:2006.11371, refType=null, unstructuredReference=DAS A, RAD P. Opportunities and challenges in explainable artificial intelligence (XAI): a survey[J/OL]. arXiv:2006.11371, 2020: 1-22. https://doi.org/10.48550/arXiv.2006.11371, articleTitle=Opportunities and challenges in explainable artificial intelligence (XAI): a survey, refAbstract=null), Reference(id=1215700831102489104, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=299, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=LI A, XIAO F, ZHANG C, journalName=Applied Energy, refType=null, unstructuredReference=LI A, XIAO F, ZHANG C, et al. Attention-based interpretable neural network for building cooling load prediction[J]. Applied Energy, 2021, 299: 117238., articleTitle=Attention-based interpretable neural network for building cooling load prediction, refAbstract=null), Reference(id=1215700831253484055, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=15, issue=14, pageStart=5232, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=LÓPEZ SANTOS M, GARCÍA-SANTIAGO X, ECHEVARRÍA CAMARERO F, journalName=Energies, refType=null, unstructuredReference=LÓPEZ SANTOS M, GARCÍA-SANTIAGO X, ECHEVARRÍA CAMARERO F, et al. Application of temporal fusion transformer for day-ahead PV power forecasting[J]. Energies, 2022, 15(14): 5232., articleTitle=Application of temporal fusion transformer for day-ahead PV power forecasting, refAbstract=null), Reference(id=1215700831354147355, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=321, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=GAO Y, MIYATA S, AKASHI Y, journalName=Applied Energy, refType=null, unstructuredReference=GAO Y, MIYATA S, AKASHI Y. Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention[J]. Applied Energy, 2022, 321: 119288., articleTitle=Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention, refAbstract=null), Reference(id=1215700831421256224, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2023, volume=297, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=GAO Y, MIYATA S, MATSUNAMI Y, journalName=Energy and Buildings, refType=null, unstructuredReference=GAO Y, MIYATA S, MATSUNAMI Y, et al. Spatio-temporal interpretable neural network for solar irradiation prediction using transformer[J]. Energy and Buildings, 2023, 297: 113461., articleTitle=Spatio-temporal interpretable neural network for solar irradiation prediction using transformer, refAbstract=null), Reference(id=1215700831513530915, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2015, volume=10, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=BACH S, BINDER A, MONTAVON G, journalName=PloS One, refType=null, unstructuredReference=BACH S, BINDER A, MONTAVON G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation[J]. PloS One, 2015, 10(7): e0130140., articleTitle=On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation, refAbstract=null), Reference(id=1215700831593222692, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=152, pageEnd=162, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=YANG Y, TRESP V, WUNDERLE M, journalName=null, refType=null, unstructuredReference=YANG Y, TRESP V, WUNDERLE M, et al. Explaining therapy predictions with layer-wise relevance propagation in neural networks[C]//2018 IEEE International Conference on Healthcare Informatics (ICHI). IEEE, 2018: 152-162., articleTitle=Explaining therapy predictions with layer-wise relevance propagation in neural networks, refAbstract=null), Reference(id=1215700831719051815, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2019, volume=20, issue=6, pageStart=3172, pageEnd=3181, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=GREZMAK J, ZHANG J, WANG P, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=GREZMAK J, ZHANG J, WANG P, et al. Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis[J]. IEEE Sensors Journal, 2019, 20(6): 3172-3181., articleTitle=Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis, refAbstract=null), Reference(id=1215700831807132202, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=276, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=KIM D, HO C H, PARK I, journalName=Atmospheric Environment, refType=null, unstructuredReference=KIM D, HO C H, PARK I, et al. Untangling the contribution of input parameters to an artificial intelligence PM2.5 forecast model using the layer-wise relevance propagation method[J]. Atmospheric Environment, 2022, 276: 119034., articleTitle=Untangling the contribution of input parameters to an artificial intelligence PM2.5 forecast model using the layer-wise relevance propagation method, refAbstract=null), Reference(id=1215700831899406894, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=7, pageStart=1789, pageEnd=1799, url=null, language=null, rfNumber=[28], rfOrder=27, authorNames=王琛, 王颖, 郑涛, journalName=电工技术学报, refType=null, unstructuredReference=王琛, 王颖, 郑涛, 等. 基于ResNet-LSTM网络和注意力机制的综合能源系统多元负荷预测[J]. 电工技术学报, 2022, 37(7): 1789-1799., articleTitle=基于ResNet-LSTM网络和注意力机制的综合能源系统多元负荷预测, refAbstract=null), Reference(id=1215700832004264499, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=7, pageStart=1789, pageEnd=1799, url=null, language=null, rfNumber=[28], rfOrder=28, authorNames=WANG Chen, WANG Ying, ZHENG Tao, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=WANG Chen, WANG Ying, ZHENG Tao, et al. Multi-energy load forecasting in integrated energy system based on resNet-LSTM network and attention mechanism[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1789-1799., articleTitle=Multi-energy load forecasting in integrated energy system based on resNet-LSTM network and attention mechanism, refAbstract=null), Reference(id=1215700832092344888, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[29], rfOrder=29, authorNames=CHO K, VAN MERRIËNBOER B, GULCEHRE C, journalName=arXiv preprint arXiv:1406.1078, refType=null, unstructuredReference=CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [J/OL]. arXiv preprint arXiv:1406.1078, 2014: 1-10., articleTitle=Learning phrase representations using RNN encoder-decoder for statistical machine translation, refAbstract=null), Reference(id=1215700832163648060, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=404, pageEnd=411, url=null, language=null, rfNumber=[30], rfOrder=30, authorNames=殷孝雎, 都治良, 卲国策, journalName=太阳能学报, refType=null, unstructuredReference=殷孝雎, 都治良, 卲国策, 等. 基于GWO-SVR的风电机组柔性塔架振动建模与仿真分析[J]. 太阳能学报, 2023, 44(8): 404-411., articleTitle=基于GWO-SVR的风电机组柔性塔架振动建模与仿真分析, refAbstract=null), Reference(id=1215700832230756928, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=404, pageEnd=411, url=null, language=null, rfNumber=[30], rfOrder=31, authorNames=YIN Xiaoju, DU Zhiliang, SHAO Guoce, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=YIN Xiaoju, DU Zhiliang, SHAO Guoce, et al. Vibration modeling and simulation analysis of flexible tower of wind turbines based on GWO-SVR[J]. Acta Energiae Solaris Sinica, 2023, 44(8): 404-411., articleTitle=Vibration modeling and simulation analysis of flexible tower of wind turbines based on GWO-SVR, refAbstract=null), Reference(id=1215700832310448709, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=1, pageStart=76, pageEnd=84, url=null, language=null, rfNumber=[31], rfOrder=32, authorNames=雷江龙, 余娟, 向明旭, journalName=电力系统自动化, refType=null, unstructuredReference=雷江龙, 余娟, 向明旭, 等. 基于深度神经网络的数据驱动潮流计算异常误差改进策略[J]. 电力系统自动化, 2022, 46(1): 76-84., articleTitle=基于深度神经网络的数据驱动潮流计算异常误差改进策略, refAbstract=null), Reference(id=1215700832411112006, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=1, pageStart=76, pageEnd=84, url=null, language=null, rfNumber=[31], rfOrder=33, authorNames=LEI Jianglong, YU Juan, XIANG Mingxu, journalName=Automation of Electric Power Systems, refType=null, unstructuredReference=LEI Jianglong, YU Juan, XIANG Mingxu, et al. Improvement strategy for abnormal error of data-driven power flow calculation based on deep neural network[J]. Automation of Electric Power Systems, 2022, 46(1): 76-84., articleTitle=Improvement strategy for abnormal error of data-driven power flow calculation based on deep neural network, refAbstract=null), Reference(id=1215700832503386700, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=7, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=34, authorNames=CHICCO D, WARRENS M J, JURMAN G, journalName=Peer J Computer Science, refType=null, unstructuredReference=CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peer J Computer Science, 2021, 7: e623., articleTitle=The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation, refAbstract=null), Reference(id=1215700833782649424, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2023, volume=126, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[33], rfOrder=35, authorNames=GAO Y, LI P, YANG H, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=GAO Y, LI P, YANG H, et al. A solar radiation intelligent forecasting framework based on feature selection and multivariable fuzzy time series[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106986., articleTitle=A solar radiation intelligent forecasting framework based on feature selection and multivariable fuzzy time series, refAbstract=null), Reference(id=1215700833887507028, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2021, volume=176, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[34], rfOrder=36, authorNames=CHAKCHAK J, CETIN N S, journalName=Measurement, refType=null, unstructuredReference=CHAKCHAK J, CETIN N S. Investigating the impact of weather parameters selection on the prediction of solar radiation under different genera of cloud cover: a case-study in a subtropical location[J]. Measurement, 2021, 176: 109159., articleTitle=Investigating the impact of weather parameters selection on the prediction of solar radiation under different genera of cloud cover: a case-study in a subtropical location, refAbstract=null), Reference(id=1215700833975587416, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=1984, volume=31, issue=2, pageStart=159, pageEnd=166, url=null, language=null, rfNumber=[35], rfOrder=37, authorNames=BRISTOW K L, CAMPBELL G S, journalName=Agricultural and Forest Meteorology, refType=null, unstructuredReference=BRISTOW K L, CAMPBELL G S. On the relationship between incoming solar radiation and daily maximum and minimum temperature[J]. Agricultural and Forest Meteorology, 1984, 31(2): 159-166., articleTitle=On the relationship between incoming solar radiation and daily maximum and minimum temperature, refAbstract=null), Reference(id=1215700834063667803, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2019, volume=2019, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[36], rfOrder=38, authorNames=SHRESTHA A K, THAPA A, GAUTAM H, journalName=International Journal of Photoenergy, refType=null, unstructuredReference=SHRESTHA A K, THAPA A, GAUTAM H. Solar radiation, air temperature, relative humidity, and dew point study: Damak, Jhapa, Nepal[J]. International Journal of Photoenergy, 2019, 2019: 1-7., articleTitle=Solar radiation, air temperature, relative humidity, and dew point study: Damak, Jhapa, Nepal, refAbstract=null), Reference(id=1215700834139165282, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, doi=null, pmid=null, pmcid=null, year=2012, volume=25, issue=4, pageStart=1330, pageEnd=1339, url=null, language=null, rfNumber=[37], rfOrder=39, authorNames=MEDVIGY D, BEAULIEU C, journalName=Journal of Climate, refType=null, unstructuredReference=MEDVIGY D, BEAULIEU C. Trends in daily solar radiation and precipitation coefficients of variation since 1984[J]. Journal of Climate, 2012, 25(4): 1330-1339., articleTitle=Trends in daily solar radiation and precipitation coefficients of variation since 1984, refAbstract=null)], funds=[Fund(id=1215700827449250225, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, awardId=20JS018, language=EN, fundingSource=Key Scientific Research Project of Education Department of Shaanxi Provincial(20JS018), fundOrder=null, country=null), Fund(id=1215700827558302135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, awardId=20JS018, language=CN, fundingSource=陕西省教育厅重点科学研究计划项目(20JS018), fundOrder=null, country=null), Fund(id=1215700827654771134, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, awardId=5JK1125, language=EN, fundingSource=Special Scientific Research Project of Shaanxi Provincial Department of Education(5JK1125), fundOrder=null, country=null), Fund(id=1215700827734462914, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, awardId=5JK1125, language=CN, fundingSource=陕西省教育厅专项科研计划(5JK1125), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1215700818653794362, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, xref=null, ext=[AuthorCompanyExt(id=1215700818662182971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China), AuthorCompanyExt(id=1215700818670571580, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, companyId=1215700818653794362, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=陕西理工大学电气工程学院,陕西 汉中 723000)])], figs=[ArticleFig(id=1215700822877458676, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.1, caption=Basic unit of the LSTM neutral network, figureFileSmall=N0HDgf//7p8rluOBGZZEGg==, figureFileBig=Xa6UASV0tSBE89onIsLx4Q==, tableContent=null), ArticleFig(id=1215700822965539067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图1, caption=LSTM神经网络基本单元, figureFileSmall=N0HDgf//7p8rluOBGZZEGg==, figureFileBig=Xa6UASV0tSBE89onIsLx4Q==, tableContent=null), ArticleFig(id=1215700823175254280, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.2, caption=Structure of the conventional Encoder-Decoder model, figureFileSmall=FjeIl/Vq3fb6OCq+5/7U0Q==, figureFileBig=H1D0TXFHnahP407G6KrbZw==, tableContent=null), ArticleFig(id=1215700823292694802, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图2, caption=传统Encoder-Decoder模型结构, figureFileSmall=FjeIl/Vq3fb6OCq+5/7U0Q==, figureFileBig=H1D0TXFHnahP407G6KrbZw==, tableContent=null), ArticleFig(id=1215700823384969497, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.3, caption=Structure of the Encoder-Decoder model adopted in this paper, figureFileSmall=uaIaWpepCcj+DxapWeRO1A==, figureFileBig=CFEUZ00EuAJzgenHDUFPAw==, tableContent=null), ArticleFig(id=1215700823510798626, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图3, caption=本文采取的Encoder-Decoder结构, figureFileSmall=uaIaWpepCcj+DxapWeRO1A==, figureFileBig=CFEUZ00EuAJzgenHDUFPAw==, tableContent=null), ArticleFig(id=1215700824811032870, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.4, caption=Propagation process of the LRP algorithm, figureFileSmall=CPtLIlxRcetaca/3RGQKRA==, figureFileBig=dwOUEwAc+ufjqJAbObqz+Q==, tableContent=null), ArticleFig(id=1215700824903307565, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图4, caption=LRP算法传播过程, figureFileSmall=CPtLIlxRcetaca/3RGQKRA==, figureFileBig=dwOUEwAc+ufjqJAbObqz+Q==, tableContent=null), ArticleFig(id=1215700824991387955, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.5, caption=Sliding window, figureFileSmall=NYiYTWUkSrjFcCmgoBcupw==, figureFileBig=z/vzyaaNQg7iMfiEoB5USQ==, tableContent=null), ArticleFig(id=1215700825113022778, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图5, caption=滑动窗口, figureFileSmall=NYiYTWUkSrjFcCmgoBcupw==, figureFileBig=z/vzyaaNQg7iMfiEoB5USQ==, tableContent=null), ArticleFig(id=1215700825255629122, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.6, caption=The 168-hour SI forecast between July 2 and July 8, figureFileSmall=Wqkbknc/Q9ZgZQnVNt15gg==, figureFileBig=S1YiFPo4c6F/tIx4xsOj/w==, tableContent=null), ArticleFig(id=1215700825347903816, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图6, caption=7月2日—7月8日共168 h SI预测, figureFileSmall=Wqkbknc/Q9ZgZQnVNt15gg==, figureFileBig=S1YiFPo4c6F/tIx4xsOj/w==, tableContent=null), ArticleFig(id=1215700825469538637, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.7, caption=The 168-hour SI forecast between December 1 and December 7, figureFileSmall=s31XiSvRFHh16TDwcN8gdg==, figureFileBig=lWjyr0BzkmZtZdxOEBv6/A==, tableContent=null), ArticleFig(id=1215700825545036115, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图7, caption=12月1日—12月7日共168 h SI预测, figureFileSmall=s31XiSvRFHh16TDwcN8gdg==, figureFileBig=lWjyr0BzkmZtZdxOEBv6/A==, tableContent=null), ArticleFig(id=1215700825637310806, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.8, caption=Absolute error of the models, figureFileSmall=nNWoAVc9NWybVvB4cbvwJg==, figureFileBig=EdpAgUcMxYyNbNwBVu05Xw==, tableContent=null), ArticleFig(id=1215700825775722846, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图8, caption=模型的绝对误差, figureFileSmall=nNWoAVc9NWybVvB4cbvwJg==, figureFileBig=EdpAgUcMxYyNbNwBVu05Xw==, tableContent=null), ArticleFig(id=1215700825901551976, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.9, caption=Attribution analysis of features of test sets, figureFileSmall=p5+nD5GrGoxx8+++LU0Drw==, figureFileBig=CTr26odv/aYFhStJbE0ZkA==, tableContent=null), ArticleFig(id=1215700825998020969, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图9, caption=测试集特征归因分析, figureFileSmall=p5+nD5GrGoxx8+++LU0Drw==, figureFileBig=CTr26odv/aYFhStJbE0ZkA==, tableContent=null), ArticleFig(id=1215700826157404525, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.10, caption=Attribution analysis of time steps of test sets, figureFileSmall=eGj4oNDNfIXS0IOBxep+Ow==, figureFileBig=VRUUyD9t8C258fl0Epaydg==, tableContent=null), ArticleFig(id=1215700826270650739, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图10, caption=测试集时间步归因分析, figureFileSmall=eGj4oNDNfIXS0IOBxep+Ow==, figureFileBig=VRUUyD9t8C258fl0Epaydg==, tableContent=null), ArticleFig(id=1215700826400674169, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.11, caption=Attribution analysis of the characteristics on August 7, figureFileSmall=sFTM6BcM0SKuxoXqKJOZqg==, figureFileBig=M2Ler4o4F396mcKJbgE62g==, tableContent=null), ArticleFig(id=1215700826526503297, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图11, caption=8月7日特征归因分析, figureFileSmall=sFTM6BcM0SKuxoXqKJOZqg==, figureFileBig=M2Ler4o4F396mcKJbgE62g==, tableContent=null), ArticleFig(id=1215700826664915336, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Fig.12, caption=Attribution analysis of the characteristics on December 9, figureFileSmall=PvBbG3OL9haF+Q5tm0CFog==, figureFileBig=69lgjD08ULL2qXRTeJdWiQ==, tableContent=null), ArticleFig(id=1215700826769772940, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=图12, caption=12月9日特征归因分析, figureFileSmall=PvBbG3OL9haF+Q5tm0CFog==, figureFileBig=69lgjD08ULL2qXRTeJdWiQ==, tableContent=null), ArticleFig(id=1215700826870436243, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Tab.1, caption=

Parameters of model 1

, figureFileSmall=null, figureFileBig=null, tableContent=
输入维度输出维度隐藏层细胞数激活函数Dropout
Linear 1388776776relu0.3
Linear 1776776776relu0.3
Linear 17761776
), ArticleFig(id=1215700826941739415, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=表1, caption=

模型1参数

, figureFileSmall=null, figureFileBig=null, tableContent=
输入维度输出维度隐藏层细胞数激活函数Dropout
Linear 1388776776relu0.3
Linear 1776776776relu0.3
Linear 17761776
), ArticleFig(id=1215700827042402716, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Tab.2, caption=

Parameters of model 2

, figureFileSmall=null, figureFileBig=null, tableContent=
输入维度输出维度隐藏层细胞数LSTM网络深度激活函数Dropout
Encoder24×1624×12812820.3
Decoder1×41×12812820.3
Linear1×1281128relu0.3
), ArticleFig(id=1215700827113705889, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=表2, caption=

模型2参数

, figureFileSmall=null, figureFileBig=null, tableContent=
输入维度输出维度隐藏层细胞数LSTM网络深度激活函数Dropout
Encoder24×1624×12812820.3
Decoder1×41×12812820.3
Linear1×1281128relu0.3
), ArticleFig(id=1215700827197591975, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=EN, label=Tab.3, caption=

Comparison of R2 between the models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型1模型2
7月0.7460.811
8月0.8370.933
9月0.8400.916
10月0.8850.944
11月0.9080.954
12月0.9200.958
7月2日—7月8日0.7510.837
12月1日—12月7日0.9250.976
测试集0.8550.924
), ArticleFig(id=1215700827298255273, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700815067665279, language=CN, label=表3, caption=

模型R2对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型1模型2
7月0.7460.811
8月0.8370.933
9月0.8400.916
10月0.8850.944
11月0.9080.954
12月0.9200.958
7月2日—7月8日0.7510.837
12月1日—12月7日0.9250.976
测试集0.8550.924
)], attaches=null, journal=Journal(id=1210938006006558725, delFlag=0, nameCn=热力发电, nameEn=Thermal Power Generation, nameHistory1=null, nameHistory2=null, issn=1002-3364, eissn=null, cn=61-1111/TM, 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=YWgAUXbKXZzTw3c+kJbAIA==, journalPrice=null, startedYear=null, abbrevIsoEn=Thermal Power Generation, journalRemark=null, publicationField=null, createdTime=1766639718774, updatedTime=1766640759031, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=T, firstLetterEn=T, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=YWgAUXbKXZzTw3c+kJbAIA==, picEn=jfJjUlYAGfUZwuOMQZ6AHQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1210942369256575009, language=CN, name=热力发电, 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=1766640759052, updatedTime=1766640759052, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1210942369315295266, language=EN, name=Thermal Power Generation, 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=1766640759066, updatedTime=1766640759066, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1210938733613449225, websiteList=[Website(id=1210941118787744741, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, 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/rlfd/CN, language=CN, createTime=1766640460918, createBy=18614031015, updateTime=1766640511525, updateBy=18614031015, name=热力发电-中文, tplId=1146099689490845704, title=热力发电, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944690380214659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=articleTextType, value=kx, createTime=1766641312451, updateTime=1766641312451, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690359243136, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=banner, value=null, createTime=1766641312446, updateTime=1766641312446, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690401186182, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=grayFlag, value=0, createTime=1766641312456, updateTime=1766641312456, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690346660223, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641312443, updateTime=1766641312443, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690409574792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=minRunFlag, value=0, createTime=1766641312458, updateTime=1766641312458, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690371826050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic, createTime=1766641312449, updateTime=1766641312449, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690405380487, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=silenceFlag, value=0, createTime=1766641312457, updateTime=1766641312457, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690367631745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1766641312448, updateTime=1766641312448, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690388603268, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeColor, value=null, createTime=1766641312453, updateTime=1766641312453, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690392797573, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeStyle, value=null, createTime=1766641312454, updateTime=1766641312454, creator=18614031015, updator=18614031015)]), Website(id=1210941118926156777, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, 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/rlfd/EN, language=EN, createTime=1766640460950, createBy=18614031015, updateTime=1766640598724, updateBy=18614031015, name=热力发电-英文, tplId=1146101810881728533, title=Thermal Power Generation, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944709317489283, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=articleTextType, value=kx, createTime=1766641316966, updateTime=1766641316966, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709296517760, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=banner, value=null, createTime=1766641316961, updateTime=1766641316961, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709334266502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=grayFlag, value=0, createTime=1766641316970, updateTime=1766641316970, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709288129151, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641316959, updateTime=1766641316959, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709346849416, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=minRunFlag, value=0, createTime=1766641316973, updateTime=1766641316973, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709309100674, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/EN/file/pic, createTime=1766641316964, updateTime=1766641316964, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709338460807, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=silenceFlag, value=0, createTime=1766641316971, updateTime=1766641316971, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709300712065, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1766641316962, updateTime=1766641316962, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709321683588, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeColor, value=null, createTime=1766641316967, updateTime=1766641316967, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709330072197, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeStyle, value=null, createTime=1766641316969, updateTime=1766641316969, creator=18614031015, updator=18614031015)])], journalTitle=热力发电, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Thermal Power Generation, journalPhotoCn=YWgAUXbKXZzTw3c+kJbAIA==, journalPhotoEn=jfJjUlYAGfUZwuOMQZ6AHQ==, journalFirstLetter=T, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202312188, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202312188, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202312188, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202312188, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于可解释性深度学习的太阳辐射强度预测
收藏切换
PDF下载
李昂 , 周雷金 , 闫群民 , 贺海育
热力发电 | 发电技术论坛 2024,53(5): 132-140
收起
收藏切换
热力发电 | 发电技术论坛 2024, 53(5): 132-140
基于可解释性深度学习的太阳辐射强度预测
全屏
李昂 , 周雷金 , 闫群民, 贺海育
作者信息
  • 陕西理工大学电气工程学院,陕西 汉中 723000
  • 李昂(1971),男,硕士,教授,主要研究方向为电能质量分析及光伏发电技术,

通讯作者:

周雷金(1999),男,硕士研究生,主要研究方向为深度学习在新能源发电中的应用,
Prediction of solar irradiation based on interpretable deep learning
Ang LI , Leijin ZHOU , Qunmin YAN, Haiyu HE
Affiliations
  • College of Electrical Engineering, Shaanxi University of Technology, Hanzhong 723000, China
出版时间: 2024-05-25 doi: 10.19666/j.rlfd.202312188
文章导航
收藏切换

准确预测太阳辐射强度(SI)对电力调度和光伏选址至关重要。随着高性能计算机和大容量存储设备的发展,基于数据驱动的深度学习模型在SI预测领域获得广泛关注,然而,深度学习模型的“黑箱”特性在物理解释性上的缺失,限制了其在特定场合的应用可信度。为了在保持预测精度和模型结构不变、不增加计算复杂度的前提下,提升模型的可解释性,构建了一个基于长短时记忆(LSTM)神经网络的模型。其性能比传统神经网络提高了8.07%,并展示出更优的离群点处理能力。通过采用分层相关传播(LRP)算法,从时间和空间2个维度对影响模型输出的因素进行了评分,增强了模型的可解释性。研究结果表明:该模型在确保性能的前提下,具备良好的可解释性,其中历史辐射强度、时间相关特征(如时日周月)、太阳高度角信息(如日出和日落时刻)、云层覆盖度、辐射时长、温度和露点温度等因素是影响太阳辐射强度预测的主要因素。

太阳辐射强度预测  /  深度学习  /  可解释性  /  LRP算法  /  LSTM

Accurately predicting solar irradiation (SI) is crucial for power scheduling and photovoltaic site selection. With the development of high-performance computing and large-capacity storage devices, data-driven deep learning models have gained widespread attentions in the SI prediction domain. However, the lack of physical interpretability due to the “black-box” nature of deep learning models restricts their credibility in specific scenarios. To enhance the interpretability of the model on the premise of maintaining prediction accuracy and keeping the model structure unchanged, and without increasing computational complexity, a model based on long short-term memory (LSTM) neural network is constructed, demonstrating an 8.07% performance improvement over the conventional neural networks and showing superior outlier handling capabilities. By employing layer-wise relevance propagation (LRP) algorithm, factors influencing the model output are scored from both temporal and spatial dimensions, enhancing the model’s interpretability. The research results indicate that the model possesses good interpretability under the premise of ensuring performance, with historical solar irradiation, time-related features (such as hour, day, week, month), solar altitude information (such as sunrise and sunset times), cloud cover, radiation time, temperature, and dew point temperature being the main factors influencing SI prediction.

solar irradiation prediction  /  deep learning  /  interpretability  /  LRP algorithm  /  LSTM
李昂, 周雷金, 闫群民, 贺海育. 基于可解释性深度学习的太阳辐射强度预测. 热力发电, 2024 , 53 (5) : 132 -140 . DOI: 10.19666/j.rlfd.202312188
Ang LI, Leijin ZHOU, Qunmin YAN, Haiyu HE. Prediction of solar irradiation based on interpretable deep learning[J]. Thermal Power Generation, 2024 , 53 (5) : 132 -140 . DOI: 10.19666/j.rlfd.202312188
随着“双碳”目标的提出,可再生能源在国家电网中的应用和渗透持续增长。其中,太阳能作为一种可靠、清洁且前景广阔的可再生能源,受到了广大研究者和产业界的高度关注[1]。根据国家能源局发布的《2022年光伏发电建设运行情况》报告,2022年,我国新增的光伏发电并网容量达到了87.408 GW,再次验证了太阳能在我国可再生能源布局中的重要地位。
对于光伏发电系统,太阳辐射强度(solar irradiation,SI)是影响其发电效率的主要因素[2]。SI的不确定性使得光伏输出电压具有波动性和间歇性[3],因此为保证电网运行的稳定性与电力调度的可靠性,准确的SI预测至关重要[4]
随着高性能计算机的快速发展以及大容量储存设备的普及,研究人员发现传统经验模型不能满足高精度的要求[5],因此由数据驱动的预测模型在SI预测中脱颖而出。在实际研究中,以人工智能为基础的SI预测模型通常采用温度、辐射时长等多元气象参数作为输入因子[6]。然而,传统机器学习方法在处理高维数据时需要复杂的特征工程[7]。基于此,本文选择采用深度学习方法进行SI预测。
深度学习用于SI预测中,最初一般以人工神经网络(artificial neural network,ANN)为主。文献[8]中Behrang等人以ANN作为预测模型,以气温、相对湿度、日照时长、风速值等气象变量作为输入,研究了ANN在SI预测中的潜力。文献[9]中Cao等人以逐日历史SI数据作为输入,利用小波变换法将SI样本数据分解为不同时频域的分量,并将上述分量作为循环反投影网络(recurrent back-projection network,RBPN)的输入建立了SI预测模型,结果表明采用小波变换法的模型具有更高的精度。文献[10]中Ahmad等人利用含外源输入的非线性自回归神经网络,以9种气象数据方式作为输入,输出了日前1 h的SI。文献[11]中Sharma等人将Morlet小波变换与Mexican hat小波变换相结合,将这种混合小波变换作为前馈ANN隐藏层的激活函数,分别以1 h与0.25 h将2种尺度的历史SI作为输入建立了SI预测模型。
随着计算能力的更加强大,循环神经网络(recurrent neural network,RNN)及其变体神经网络开始被人们大规模研究,由于其本身串行计算的特点,相对于前述ANN等神经网络能够更好地表征时序特性,因此被广泛用于SI预测中。文献[12]中Pang等人通过RNN与ANN对SI进行预测,并对比2种模型在不同采样频率以及是否加入滑动窗口情况下的准确性以及效率;结果表明RNN比ANN在SI预测中具有更好的效果,且加入滑动窗口算法与提高采样频率都能提高预测精度,但是在计算时间方面,RNN要明显高于ANN。文献[13]中Aslam等人通过门控循环单元(gated recurrent units,GRUs)对SI进行长期预测,即预测未来一年中逐时SI。文献[14]中Srivastava等人以多元气象数据以及地理数据作为输入,将长短时记忆(long short-term memory,LSTM)神经网络用于SI预测,结果表明相较于数值天气预报模型LSTM预测模型具有更高的精度,说明LSTM神经网络在SI预测方面具有巨大的潜力。文献[15]中Obiora等人通过LSTM神经网络,以10年的历史气象数据作为输入对SI进行了单步逐时预测,通过与SVR预测模型进行对比,结果表明LSTM模型具有更小的均方根误差。以上文献充分说明RNN及其变体神经网络在SI预测中的强大能力。
然而,上述文献仅侧重于精度方面,而未考虑深度学习模型常被视为“黑箱”模型,其内部计算过程缺乏明确的可解释性。随着深度学习技术快速发展,其在众多领域如信用评分[16]、地震预报[17]和医疗保健[18]等方面都得到了广泛应用,从伦理、法律和道德的角度出发,深度学习的可解释性在决定其在实际场景中的应用潜力时具有至关重要的作用[19]
在可解释性方面,在工程领域中,文献[20]中Li等人将attention机制引入RNN中,通过对注意力向量的进一步分析,可以更好地理解建筑热力学中的时间信息。文献[21]中López等人利用TFT(temporal fusion transformer)对光伏功率进行预测,TFT中含有时间自注意解码器,可以识别全局重要特征、时间模式以及重要事件,不仅提高了模型的准确性,也提高了模型的可解释性。文献[22]中Gao等人通过引入attention机制与图卷积神经网络(graph convolutional network,GCN)提高了模型的可解释性。文献[23]中Gao等人采用time2vec对输入进行时间维度编码,采用标准嵌入对输入进行空间维度编码,使得输入同时具有了时间与空间特性,利用类Transformer结构获取不同步长的各种特征的权重,同时从时间、空间两方面来对模型进行可解释性分析。
但是以上文献所采用方法在提高可解释性的同时,改变了网络的结构且增加了计算的复杂性。而分层相关传播(layer-wise relevance propagation,LRP)算法[24]则可解决上述问题。文献[25]中Yang等人将LRP运用于临床领域,文献[26]中Grezmak等人将LRP运用于机器故障诊断,文献[27]中Kim等人将LRP运用于PM2.5的预测中。
在SI预测方面,仅有极少数文献对模型的可解释性进行了分析,且并未有文献将模型与LRP相结合。因此,本文提出一种将LRP与LSTM神经网络相结合的SI预测算法,能在保持预测精度和模型结构不变、不增加计算复杂度前提下,增强了基于LSTM神经网络的SI预测模型的可解释性。
为保证充分挖掘SI预测中的时序特征,本文采用LSTM神经网络作为模型构建的基本单元。LSTM神经网络是一种改进的RNN,解决了普通RNN易出现梯度消失的问题。相较于经典的前馈神经网络,LSTM神经网络具有反馈连接,能够有效处理与预测时间序列数据,并且也具有处理单个数据点的能力[28],因此被广泛运用于自然语言处理与时间序列预测。图1为LSTM神经网络基本单元。
图1所示,LSTM神经网络输入包括前一时间步输出Ht-1、前一时间步Cell输出Ct-1与当前时间步输入Xt,输出包括当前时间步输出Ht与当前时间步Cell输出Ct。LSTM神经网络单元分为遗忘门(forget gate)、输入门(input gate)、输出门(output gate)3个部分。
遗忘门以XtHt-1作为输入,通过sigmoid函数来产生1个0~1的概率值,作为Ct-1在本次时间步的权重Ft,计算公式为:
Ft=σ(XtWxf+Ht1Whf+bf)
式中:WxfWhfbf分别为XtHt-1的权重和偏置。
输入门的输入分为两部分:一部分由XtHt-1分别通过tanh函数产生一个[–1,1]之间的值,这个值就作为本次时间步的候选Cell信息C˜t;另一部分由XtHt-1通过sigmoid函数产生C˜t的权重It,计算公式为:
It=σ(XtWxi+Ht1Whi+bi)
C˜t=tanh(XtWxc+Ht1Whc+bc)
式中:WxiWhi分别为XtHt-1的权重;bi为偏置,式(3)同理。因此由式(1)—式(3)可得当前时间步Cell输出Ct,计算公式为:
Ct=FtCt1+ItC˜t
输出门逻辑同输入门,由tanh函数产生输出的候选信息,由sigmoid函数产生输出候选信息的权重Ot,并由两者共同产生输出权重Ht,计算公式为:
Ot=σ(XtWxo+Ht1Who+bo)
Ht=Ottanh(Ct)
式中:WxoWho分别为XtHt-1的权重;bo为偏置。
Encoder-Decode模型,也称编码-解码模型。最早在机器翻译领域提出[29],被广泛运用于sequence-to-sequence类问题。图2为传统Encoder-Decoder模型结构。
图2可见,该模型存在编码与解码2个过程。前者将输入序列Xi编码为定长向量C,从时间和空间2个维度上提取特征,并认为编码器中最后一个时间步所输出向量C包含编码器所有输入的信息,从而使输入数据降维。后者则采用C对编码器进行初始化,解码器每次只输出1个向量,且解码器每个时间步的输出与隐藏状态都作为下一时间步的输入,从而保证了输出的连续性。传统用于机器翻译的Encoder-Decoder模型,由于语句中的信息在最初已经全部包含,不需要在解码器中再进行额外的信息输入。但是对于SI预测来说,输入序列为时间序列,若采用上述结构则可能会忽略一些静态特征,如:本日为1年中第几天,为1周中第几天等。因此,在编码器中应该考虑将一些静态特征作为额外输入。本文以LSTM神经网络作为编码器与解码器,所采用结构如图3所示。
为了清晰地阐述后续的可解释性内容,提出以下2个关键问题:1)为什么需要对深度学习模型进行可解释性分析;2)如何对深度学习模型进行可解释性分析。这2个问题将为后续的讨论提供方向和框架。
对于第1个问题,本文基于可信度、透明度以及公平性3点来进行阐述。首先,对于1个模型,只有用户明白该模型做出决策的机理,以及算法做出决策符合人们的常识,这样才能增强模型的可信度,模型的可信度对于模型是否能够大规模应用在实际场合至关重要。其次,对于1个模型而言,若能够理解模型内部决策过程,则可以认为模型是透明的。而透明的模型有益于人们评估预测质量以及针对不合理的输出结果进行改进。最后,模型在进行决策时,不会偏袒任何输入变量,做出的决策公平公正即模型的公平性。模型在决策时,有时会因为数据集的质量不佳而产生偏差,而对深度学习进行可解释性分析则可改善这一点提高公平性。
对于第2个问题可解释性的分析,本文主要从时间与空间2个方面进行考虑。即在SI预测中考虑不同时间步对于输出的影响以及同一时间步不同输入对于输出的影响。
LRP通过利用已设计好的局部传播规则,使预测值在网络中进行反向传播。
这种传播规则类似电路中的基尔霍夫定理,在传播过程中要遵守守恒规则,即网络中每个神经元接收到的信息必须等量的重新分配到下一层的神经元中,传播过程如图4所示。图4中:Ri为第i个神经元,R10为网络输出,规定Rij为神经元j流向神经元i的信息。以R10流向R7的信息R7←10为例,此时R7←10满足式(7):
R710=R47+R57+R67
假设RmRn为相邻2层神经元,RmRn输入,传播规则公式为:
Rm=nzmnmzmnRn
式中:zmn模拟了神经元m对神经元n的贡献;分母则是用来保证守恒性质的。若将此规则扩展至全局,则可得到输入对于输出的影响程度。
本文气象数据集来自日本气象厅官方网站[22],为2019年1月1日至2020年12月31日期间实测的东京逐时气象特征数据,其中包括15个特征,分别为4个与时间相关的特征即时、日、周、月,以及11个气象特征即本站气压(hPa)、海平面气压(hPa)、降雨量(mm)、温度(℃)、露点温度(℃)、水蒸气压(hPa)、湿度、风速(m/s)、每小时辐射时长(h)、云层覆盖等级(等级为10的人为观测标定量)、通过经纬度。结合太阳高度角和方位角所计算出的信息(日出和日落时刻),SI样本值数据来源于靠近气象测量点附近实测每平米所接收的太阳辐射强度(W/m2)。
本文数据集将2019年1月1日至2019年12月31日设置为训练集,2020年1月1日至2020年6月30日设置为验证集,2020年7月1日至2020年12月31日设置为测试集。
本文将滑动窗口设置为24,即以历史24 h的数据对未来1 h进行预测(图5)。
深度学习虽然减少特征工程的复杂度,但是并不代表不需要进行特征处理。输入特征的量级等方面的差异会影响各特征在训练过程中所占权重,因此仍需对特征进行归一化处理。本文将输入划分2种,分别为上述15种特征值与历史辐射强度。
15种特征值采用Z-score的方式进行归一化,Z-score为一种常见的标准化归一方式[30-31],可以将不同量级的数据转化为统一量度。计算公式为:
z=xμσ
式中:x为输入特征的个体数据;μ为输入特征的均值;σ为输入特征的标准差。
历史辐射强度为输出变量,为保证在数据还原时不引入测试集信息,因此采取log归一化的方式对其进行归一化。计算公式为:
z=logay
式中:y为输出变量的个体数据;a为底数。
均方误差值δMSE是时间序列预测中常见评估指标,因此本文将δMSE作为损失函数,计算公式为:
δMSE=1ni=1n(y^iyi)2
式中:y^i为预测值;yi为训练集中实际输出值。
采用决定系数(R-squared Coefficient,R2)作为模型的评估指标[32],用于验证集选择最佳模型以及在测试集中对模型精度进行评估。R2作为一种衡量线性回归程度的无量纲指标,取值范围为0~1,越接近1代表模型拟合能力越强。其计算公式为:
{R2=1δSSEδSSTδSSE=i=1n(y^iyi)2δSST=i=1n(y¯iyi)2
式中:δSSE为残差平方和;δSST为总体离差平方和;y^i为预测值;yi为测试集与验证集中实际输出值;y¯i为测试集或验证集实际输出值的均值。
为验证上述方法的有效性与准确性,将以传统深度神经网络与本文算法进行对照实验。编程环境为Python 3.10.9,框架为Pytorch 1.12,硬件配置GPU型号为NVIDIA GeForce RTX 3070 Ti Laptop。
模型1(M1)为传统深度神经网络,为保证实验输入的公平性,将历史24 h的15种特征值和SI以及未来1 h的时间信息作为输入,参数设置见表1。模型2(M2)为本文所用算法,Encoder为按时序输入的历史24 h的15种特征值与SI,并且将Encoder输出对Decoder进行初始化。Decoder中输入未来1 h的时间信息,参数设置见表2
为保证实验公平,设置实验迭代次数为100次,批大小为32,优化器为Adam优化器。并且为保证实验的可复现性,将本实验所有随机种子设置为1 000。
为验证上述方法的有效性与准确性,从实验精度与可解释性进行分析。
表3为2种模型R2对比。由表3可见,本文算法的R2在整体上都优于传统的深度神经网络,且性能提高了8.07%。
由于本文算法7月R2表现相对较差,12月R2表现相对较好。分别任选此2月中任意1周,7月2日至7月8日和12月1日至12月7日间2个模型预测结果进行对比,结果如图6图7所示。
通过图6图7可以看出,模型2的预测值相较于模型1的预测值有着更高的精度,拟合程度更好,但是仍存在一定误差。这是因为在夏日期间,SI的绝对数值较大,且存在暴雨、台风等气候影响,导致数值出现剧烈的变化,而数值越大其本身可能产生的误差也会随之越大。因此在7月时模型表现相对较差,R2相对较低。
对每步预测进行离群值分析,图8为模型的绝对误差。由图8a)可见,由于SI具有很强的周期性,因此大量数据为0,所以2个模型的绝对误差平均值基本为0。但可以明显看出模型2的箱型比模型1更小,且模型2上边缘低于模型1上边缘,说明模型2整体上具有更好的分布。但2个模型仍存在着异常值。为更好地进行观察,取最大的前10%绝对误差进行分析。如图8b)所示,此时模型2的箱型明显低于模型1,误差平均值优于模型1,箱型比模型1更小,且上边缘低于模型1上边缘。说明在离群值分析中模型2明显优于模型1。
由4.1节分析可知,模型2性能明显优于模型1。因此,本文对模型2进行可解释性分析,从时间空间2个方面进行考虑,即考虑同一时间步中各个输入特征对于SI预测结果的影响,以及不同时间步对于SI预测结果的影响。图9为测试集特征归因分析,图10为测试集时间步归因分析。选取2个极端辐射强度,以8月7日00:00、11:00与12月9日00:00、12:00为例进行特征归因分析,结果如图11图12所示。由图9可见,从空间方面进行考虑,历史辐射强度量为影响SI的最主要变量,时间相关特征(时日周月)、太阳高度角相关信息(日出和日落时刻)、云层覆盖等级、辐射时长、温度与露点温度也对SI有着明显影响。
SI受历史辐射的影响,这符合人们的常规认知。本文对于SI的预测,是以小时为时间尺度,代表了一个累积的能量,而不是瞬态强度,因此太阳辐射强度的预测是与辐射时长强相关的。由于地球在一年中不同时间处于轨道的不同位置,某个固定地方的一年中SI也是不同的,因此SI与时间息息相关[33]。文献[34]中以云量与辐射时长等气象指数作为分类系统,研究证明不同云层覆盖等级能够影响太阳的辐射强度。有学者研究证明SI与日极端温度即最高温度与最低温度之差,存在着某种有用的关系[35]。露点温度一般受温度与相对湿度的影响,但是在很大程度上露点温度取决于温度,而不是相对湿度,因此本实验中湿度的影响很小[36]。同时,本实验中的水蒸气压与降雨量的影响因素很小,但是文献[37]研究证明降雨量与云量、SI都有着密切关系,文献[22]中以图神经网络作为研究方法,水蒸气压与降雨量都为SI的一阶邻点。因此推测模型对水蒸气压与降雨量的误判是本文模型出现误差的原因之一。
图10可见,从时间方面考虑,以未来1 h为起点,从距离最近的第24 h到距离最远的第1 h呈现递减趋势,符合人们的常规认知。但是第23 h的影响因素呈现一个急剧下降的趋势,这可能也是本文模型出现误差的原因之一。
图11可见,8月7日2个时间点最大影响因素仍为历史辐射量,与前述分析相同。11:00 SI与历史辐射量呈现正相关,这是因为在当日白天辐射量具有较大数值,进行归一化后都为正值,并且根据图10分析SI受到距离最近的几个时间步影响最大,而此时几个辐射量都为较大正值,因此在11:00呈现正相关,同理在00:00呈现负相关。由于辐射时长在11:00的近几个时间步都为1 h,因此辐射时间的影响程度增大。在00:00,目前所处时数的影响因素激增,这是因为夜间时辐射强度为0,不随时间中其他3个因素(日、周、月)而发生改变。
图12可见,12月7日2个时间点历史辐射量仍保持较大影响比例。12月7日00:00与8月7日00:00基本为相同趋势,原因同前所述。在12:00,由于当日整体SI很小,且云层覆盖较高,历史辐射量、日照时长等归一化后为负值,因此呈现负相关。
本文构建了基于LSTM神经网络为核心的模型,对太阳辐射强度进行了预测,并采用LRP算法从时间与空间2个方面对于模型进行了可解释性分析,并得到以下结论。
1)相较于传统的深度神经网络模型,本文所用模型结构性能提高了8.07%,且具有更优的离群点处理能力。
2)本文提出的基于LRP算法来提高SI预测模型可解释性的方法,具有简洁的网络结构以及更少的计算量。
3)本文模型具良好的可解释性,通过可解释性分析可知历史辐射强度为影响因素最大的因子,时间相关特征(时日周月)、太阳高度角相关信息(日出和日落时刻)、云层覆盖等级、辐射时长、温度与露点温度也具有一定影响。
4)模型对于水蒸气压、降雨量以及某些时间步的误判,可能是造成模型出现误差的原因。
  • 陕西省教育厅重点科学研究计划项目(20JS018)
  • 陕西省教育厅专项科研计划(5JK1125)
参考文献 引证文献
排序方式:
[1]
ACIKGOZ H. A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting[J]. Applied Energy, 2022, 305: 117912.
[2]
NARVAEZ G, GIRALDO L F, BRESSAN M, et al. Machine learning for site-adaptation and solar radiation forecasting[J]. Renewable Energy, 2021, 167: 333-342.
[3]
ESPINOSA A R, BRESSAN M, GIRALDO L F. Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks[J]. Renewable Energy, 2020, 162: 249-256.
[4]
GAO B, HUANG X, SHI J, et al. Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks[J]. Renewable Energy, 2020, 162: 1665-1683.
[5]
ZHOU Y, LIU Y, WANG D, et al. A review on global solar radiation prediction with machine learning models in a comprehensive perspective[J]. Energy Conversion and Management, 2021, 235: 113960.
[6]
KHATIB T, MOHAMED A, MAHMOUD M, et al. Modeling of daily solar energy on a horizontal surface for five main sites in Malaysia[J]. International Journal of Green Energy, 2011, 8(8): 795-819.
[7]
BAMISILE O, OLUWASANMI A, EJIYI C, et al. Comparison of machine learning and deep learning algorithms for hourly global/diffuse solar radiation predictions[J]. International Journal of Energy Research, 2022, 46(8): 10052-10073.
[8]
BEHRANG M A, ASSAREH E, GHANBARZADEH A, et al. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data[J]. Solar Energy, 2010, 84(8): 1468-1480.
[9]
CAO J C, CAO S H. Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis[J]. Energy, 2006, 31(15): 3435-3445.
[10]
AHMAD A, ANDERSON T N, LIE T T. Hourly global solar irradiation forecasting for New Zealand[J]. Solar Energy, 2015, 122: 1398-1408.
[11]
SHARMA V, YANG D, WALSH W, et al. Short term solar irradiance forecasting using a mixed wavelet neural network[J]. Renewable Energy, 2016, 90: 481-492.
[12]
PANG Z, NIU F, O’NEILL Z. Solar radiation prediction using recurrent neural network and artificial neural network: a case study with comparisons[J]. Renewable Energy, 2020, 156: 279-289.
[13]
ASLAM M, SEUNG K H, LEE S J, et al. Long-term solar radiation forecasting using a deep learning approach-GRUs[C]//2019 IEEE 8th International Conference on Advanced Power System Automation and Protection (APAP). IEEE, 2019: 917-920.
[14]
SRIVASTAVA S, LESSMANN S. A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data[J]. Solar Energy, 2018, 162: 232-247.
[15]
OBIORA C N, ALI A, HASAN A N. Forecasting hourly solar irradiance using long short-term memory (LSTM) network[C]//2020 11th International Renewable Energy Congress (IREC). IEEE, 2020: 1-6.
[16]
GUNNARSSON B R, VANDEN BROUCKE S, BAESENS B, et al. Deep learning for credit scoring: do or don’t?[J]. European Journal of Operational Research, 2021, 295(1): 292-305.
[17]
MIGNAN A, BROCCARDO M. Neural network applications in earthquake prediction (1994—2019): Meta-analytic and statistical insights on their limitations[J]. Seismological Research Letters, 2020, 91(4): 2330-2342.
[18]
SHAMSHIRBAND S, FATHI M, DEHZANGI A, et al. A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues[J]. Journal of Biomedical Informatics, 2021, 113: 103627.
[19]
DAS A, RAD P. Opportunities and challenges in explainable artificial intelligence (XAI): a survey[J/OL]. arXiv:2006.11371, 2020: 1-22. https://doi.org/10.48550/arXiv.2006.11371
[20]
LI A, XIAO F, ZHANG C, et al. Attention-based interpretable neural network for building cooling load prediction[J]. Applied Energy, 2021, 299: 117238.
[21]
LÓPEZ SANTOS M, GARCÍA-SANTIAGO X, ECHEVARRÍA CAMARERO F, et al. Application of temporal fusion transformer for day-ahead PV power forecasting[J]. Energies, 2022, 15(14): 5232.
[22]
GAO Y, MIYATA S, AKASHI Y. Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention[J]. Applied Energy, 2022, 321: 119288.
[23]
GAO Y, MIYATA S, MATSUNAMI Y, et al. Spatio-temporal interpretable neural network for solar irradiation prediction using transformer[J]. Energy and Buildings, 2023, 297: 113461.
[24]
BACH S, BINDER A, MONTAVON G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation[J]. PloS One, 2015, 10(7): e0130140.
[25]
YANG Y, TRESP V, WUNDERLE M, et al. Explaining therapy predictions with layer-wise relevance propagation in neural networks[C]//2018 IEEE International Conference on Healthcare Informatics (ICHI). IEEE, 2018: 152-162.
[26]
GREZMAK J, ZHANG J, WANG P, et al. Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis[J]. IEEE Sensors Journal, 2019, 20(6): 3172-3181.
[27]
KIM D, HO C H, PARK I, et al. Untangling the contribution of input parameters to an artificial intelligence PM2.5 forecast model using the layer-wise relevance propagation method[J]. Atmospheric Environment, 2022, 276: 119034.
[28]
王琛, 王颖, 郑涛, 等. 基于ResNet-LSTM网络和注意力机制的综合能源系统多元负荷预测[J]. 电工技术学报, 2022, 37(7): 1789-1799.
WANG Chen, WANG Ying, ZHENG Tao, et al. Multi-energy load forecasting in integrated energy system based on resNet-LSTM network and attention mechanism[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1789-1799.
[29]
CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [J/OL]. arXiv preprint arXiv:1406.1078, 2014: 1-10.
[30]
殷孝雎, 都治良, 卲国策, 等. 基于GWO-SVR的风电机组柔性塔架振动建模与仿真分析[J]. 太阳能学报, 2023, 44(8): 404-411.
YIN Xiaoju, DU Zhiliang, SHAO Guoce, et al. Vibration modeling and simulation analysis of flexible tower of wind turbines based on GWO-SVR[J]. Acta Energiae Solaris Sinica, 2023, 44(8): 404-411.
[31]
雷江龙, 余娟, 向明旭, 等. 基于深度神经网络的数据驱动潮流计算异常误差改进策略[J]. 电力系统自动化, 2022, 46(1): 76-84.
LEI Jianglong, YU Juan, XIANG Mingxu, et al. Improvement strategy for abnormal error of data-driven power flow calculation based on deep neural network[J]. Automation of Electric Power Systems, 2022, 46(1): 76-84.
[32]
CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peer J Computer Science, 2021, 7: e623.
[33]
GAO Y, LI P, YANG H, et al. A solar radiation intelligent forecasting framework based on feature selection and multivariable fuzzy time series[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106986.
[34]
CHAKCHAK J, CETIN N S. Investigating the impact of weather parameters selection on the prediction of solar radiation under different genera of cloud cover: a case-study in a subtropical location[J]. Measurement, 2021, 176: 109159.
[35]
BRISTOW K L, CAMPBELL G S. On the relationship between incoming solar radiation and daily maximum and minimum temperature[J]. Agricultural and Forest Meteorology, 1984, 31(2): 159-166.
[36]
SHRESTHA A K, THAPA A, GAUTAM H. Solar radiation, air temperature, relative humidity, and dew point study: Damak, Jhapa, Nepal[J]. International Journal of Photoenergy, 2019, 2019: 1-7.
[37]
MEDVIGY D, BEAULIEU C. Trends in daily solar radiation and precipitation coefficients of variation since 1984[J]. Journal of Climate, 2012, 25(4): 1330-1339.
2024年第53卷第5期
PDF下载
95
43
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202312188
  • 接收时间:2023-12-05
  • 首发时间:2026-01-07
  • 出版时间:2024-05-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-12-05
基金
Key Scientific Research Project of Education Department of Shaanxi Provincial(20JS018)
陕西省教育厅重点科学研究计划项目(20JS018)
Special Scientific Research Project of Shaanxi Provincial Department of Education(5JK1125)
陕西省教育厅专项科研计划(5JK1125)
作者信息
    陕西理工大学电气工程学院,陕西 汉中 723000

通讯作者:

周雷金(1999),男,硕士研究生,主要研究方向为深度学习在新能源发电中的应用,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202312188
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