Article(id=1236321539621180356, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236321537146540956, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202412272, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1735228800000, receivedDateStr=2024-12-27, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1772691624788, onlineDateStr=2026-03-05, pubDate=1761321600000, pubDateStr=2025-10-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1772691624788, onlineIssueDateStr=2026-03-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1772691624788, creator=13701087609, updateTime=1772691624788, updator=13701087609, issue=Issue{id=1236321537146540956, tenantId=1146029695717560320, journalId=1210938733613449225, year='2025', volume='54', issue='10', pageStart='1', pageEnd='174', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1772691624199, creator=13701087609, updateTime=1772691865526, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1236322549404070348, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236321537146540956, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1236322549408264653, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236321537146540956, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=82, endPage=92, ext={EN=ArticleExt(id=1236321539939947470, articleId=1236321539621180356, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Ultra-short-term wind power prediction based on modal decomposition and combined neural network, columnId=1211002405299294959, journalTitle=Thermal Power Generation, columnName=Thermal energy science research, runingTitle=null, highlight=null, articleAbstract=

Due to the significant volatility and randomness of wind power data, low prediction accuracy is often observed with a single model in wind power prediction. To overcome this, an ultra-short-term wind power prediction method is introduced, based on modal decomposition and a combined neural network model. Firstly, the wind power data are processed based on the improved fully integrated empirical modal decomposition and sample entropy, which decomposes the unsteady series into smoother sub-sequences and reconstructs the high-frequency oscillatory component and low-frequency smooth component synchronously. Secondly, a hybrid prediction model for wind power based on an adaptive sparse self-attention mechanism is constructed. For the high-frequency oscillatory component with high complexity, the adaptive sparse Transformer model is used to fully explore the fluctuation information. For the low-frequency stationary components, the sequence features are fully extracted by the bidirectional gated recurrent unit model. Finally, the final prediction outcomes are derived by overlaying the forecast results of each component. Test was performed with actual data from a wind farm in Shandong, and the results show that, compared with other commonly used models, the proposed model’s root mean square error and average absolute error has decreased by 2.644 MW and 2.42 MW, and the coefficient of determination has a notable 18.2% increase, implying it has a good prediction performance.

, 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=Zhengzhong GAO, Yi KUANG, Jinglong ZHANG), CN=ArticleExt(id=1236321543983255595, articleId=1236321539621180356, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于模态分解与组合神经网络的超短期风电功率预测, columnId=1211002405437706993, journalTitle=热力发电, columnName=热能科学研究, runingTitle=null, highlight=null, articleAbstract=

针对风电功率数据存在的显著波动性和随机性导致风电功率预测中单一模型预测精确度欠佳的问题,提出了一种基于模态分解和组合神经网络模型的超短期风电功率预测方法。首先,基于改进完全集成经验模态分解和样本熵对风电数据进行处理,由不平稳序列分解为较为平稳子序列,同步重构出高频振荡分量和低频平稳分量。然后,构建基于自适应稀疏自注意力机制的风电混合预测模型,对于复杂度较高的高频振荡分量,采用自适应稀疏Transformer模型充分发掘关键波动特征;对于低频平稳分量,采用双向门控循环单元模型充分提取序列特征。最后,将各分量预测结果叠加得到最终预测结果。基于山东某风电场的实际数据进行测试,结果表明:相较于其他常用模型,所提模型均方根误差和平均绝对误差分别减小2.644 MW和2.420 MW,同时决定系数提高18.2%,具有良好的预测性能。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zJesbduksHRHIR1Txy8jiA==, magXml=cl5nXlGUcDraEiplmxZZbQ==, pdfUrl=null, pdf=jMQWEKHr1VKdygrht71ZYw==, pdfFileSize=1736785, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Ypjamif6gwZCXLxk7aRREg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=yrC5TUhj7tsIXlJqnplsDA==, mapNumber=null, authorCompany=null, fund=null, authors=

高正中(1971),男,博士,教授,主要研究方向为新能源功率预测、智能电网技术,

, authorsList=高正中, 况逸, 张经龙)}, authors=[Author(id=1236321544482377796, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zzgao@sdust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1236321544570458185, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321544482377796, language=EN, stringName=Zhengzhong GAO, firstName=Zhengzhong, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236321546055241809, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321544482377796, language=CN, stringName=高正中, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山东科技大学电气与自动化工程学院,山东 青岛 266590, bio={"content":"

高正中(1971),男,博士,教授,主要研究方向为新能源功率预测、智能电网技术,

"}, bioImg=null, bioContent=

高正中(1971),男,博士,教授,主要研究方向为新能源功率预测、智能电网技术,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236321544239108148, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, xref=1., ext=[AuthorCompanyExt(id=1236321544247496757, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1236321544260079670, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山东科技大学电气与自动化工程学院,山东 青岛 266590)])]), Author(id=1236321546160099417, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, orderNo=1, 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=1236321546277539934, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321546160099417, language=EN, stringName=Yi KUANG, firstName=Yi, middleName=null, lastName=KUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236321546424340579, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321546160099417, language=CN, stringName=况逸, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.山东科技大学电气与自动化工程学院,山东 青岛 266590, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236321544239108148, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, xref=1., ext=[AuthorCompanyExt(id=1236321544247496757, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1236321544260079670, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山东科技大学电气与自动化工程学院,山东 青岛 266590)])]), Author(id=1236321546684387436, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, 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=1236321546797633648, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321546684387436, language=EN, stringName=Jinglong ZHANG, firstName=Jinglong, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Yiqiao Coal Mine of Jining Energy Group, Jining 272500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236321546919268469, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, authorId=1236321546684387436, language=CN, stringName=张经龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.济宁能源集团义桥煤矿,山东 济宁 272500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236321544352354364, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, xref=2., ext=[AuthorCompanyExt(id=1236321544360742973, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544352354364, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Yiqiao Coal Mine of Jining Energy Group, Jining 272500, China), AuthorCompanyExt(id=1236321544369131582, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544352354364, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.济宁能源集团义桥煤矿,山东 济宁 272500)])])], keywords=[Keyword(id=1236321547141566591, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, orderNo=1, keyword=modal decomposition), Keyword(id=1236321547259007109, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, orderNo=2, keyword=wind power prediction), Keyword(id=1236321547405807758, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, orderNo=3, keyword=sample entropy), Keyword(id=1236321547489693845, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, orderNo=4, keyword=adaptive sparse self-attention mechanism), Keyword(id=1236321547586162842, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, orderNo=1, keyword=模态分解), Keyword(id=1236321547695214751, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, orderNo=2, keyword=风电功率预测), Keyword(id=1236321547787489444, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, orderNo=3, keyword=样本熵), Keyword(id=1236321547858792616, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, orderNo=4, keyword=自适应稀疏自注意力机制)], refs=[Reference(id=1236321555693752831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=331, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=LI Z, WU L, XU Y, journalName=Applied Energy, refType=null, unstructuredReference=LI Z, WU L, XU Y, et al. Distributed trilayer risk-averse stochastic game approach for energy trading among multi-energy microgrids[J]. Applied Energy, 2023, 331: 120282., articleTitle=Distributed trilayer risk-averse stochastic game approach for energy trading among multi-energy microgrids, refAbstract=null), Reference(id=1236321555819581956, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=8, pageStart=3027, pageEnd=3048, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=朱琼锋, 李家腾, 乔骥, journalName=中国电机工程学报, refType=null, unstructuredReference=朱琼锋, 李家腾, 乔骥, 等. 人工智能技术在新能源功率预测的应用及展望[J]. 中国电机工程学报, 2023, 43(8): 3027-3048., articleTitle=人工智能技术在新能源功率预测的应用及展望, refAbstract=null), Reference(id=1236321555937022479, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=8, pageStart=3027, pageEnd=3047, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=ZHU Qiongfeng, LI Jiateng, QIAO Ji, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=ZHU Qiongfeng, LI Jiateng, QIAO Ji, et al. Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE, 2023, 43(8): 3027-3047., articleTitle=Application and prospect of artificial intelligence technology in renewable energy forecasting, refAbstract=null), Reference(id=1236321556041880085, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=4, pageStart=1129, pageEnd=1143, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=孙荣富, 张涛, 和青, journalName=高电压技术, refType=null, unstructuredReference=孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143., articleTitle=风电功率预测关键技术及应用综述, refAbstract=null), Reference(id=1236321556159320606, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=4, pageStart=1129, pageEnd=1143, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=SUN Rongfu, ZHANG Tao, HE Qing, journalName=High Voltage Engineering, refType=null, unstructuredReference=SUN Rongfu, ZHANG Tao, HE Qing, et al. Review on key technologies and applications in wind power forecasting[J]. High Voltage Engineering, 2021, 47(4): 1129-1143., articleTitle=Review on key technologies and applications in wind power forecasting, refAbstract=null), Reference(id=1236321556251595303, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2018, volume=13, issue=5, pageStart=1874, pageEnd=1885, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=PARK S W, SON S Y, KIM C, journalName=Journal of Electrical Engineering and Technology, refType=null, unstructuredReference=PARK S W, SON S Y, KIM C, et al. An improved photovoltaic system output prediction model under limited weather information[J]. Journal of Electrical Engineering and Technology, 2018, 13(5): 1874-1885., articleTitle=An improved photovoltaic system output prediction model under limited weather information, refAbstract=null), Reference(id=1236321556352258602, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=302, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=SI Z, YANG M, YU Y, journalName=Applied Energy, refType=null, unstructuredReference=SI Z, YANG M, YU Y, et al. Photovoltaic power forecast based on satellite images considering effects of solar position[J]. Applied Energy, 2021, 302: 117514., articleTitle=Photovoltaic power forecast based on satellite images considering effects of solar position, refAbstract=null), Reference(id=1236321556469699122, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=11, pageStart=224, pageEnd=234, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=赵泽妮, 云斯宁, 贾凌云, journalName=太阳能学报, refType=null, unstructuredReference=赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234., articleTitle=基于统计模型的短期风能预测方法研究进展, refAbstract=null), Reference(id=1236321556570362427, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=11, pageStart=224, pageEnd=234, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=ZHAO Zeni, YUN Sining, JIA Lingyun, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=ZHAO Zeni, YUN Sining, JIA Lingyun, et al. Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta Energiae Solaris Sinica, 2022, 43(11): 224-234., articleTitle=Recent progress in short-term forecasting of wind energy based on statistical models, refAbstract=null), Reference(id=1236321556662637119, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=2, pageStart=437, pageEnd=445, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=李国庆, 刘钊, 金国彬, journalName=电网技术, refType=null, unstructuredReference=李国庆, 刘钊, 金国彬, 等. 基于随机分布式嵌入框架及BP神经网络的超短期电力负荷预测[J]. 电网技术, 2020, 44(2): 437-445., articleTitle=基于随机分布式嵌入框架及BP神经网络的超短期电力负荷预测, refAbstract=null), Reference(id=1236321556771689031, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=2, pageStart=437, pageEnd=445, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=LI Guoqing, LIU Zhao, JIN Guobin, journalName=Power System Technology, refType=null, unstructuredReference=LI Guoqing, LIU Zhao, JIN Guobin, et al. Ultra short-term power load forecasting based on randomly distributive embedded framework and BP neural network[J]. Power System Technology, 2020, 44(2): 437-445., articleTitle=Ultra short-term power load forecasting based on randomly distributive embedded framework and BP neural network, refAbstract=null), Reference(id=1236321556851380809, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=33, issue=11, pageStart=2606, pageEnd=2614, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=刘兴, 王艳, 纪志成, journalName=系统仿真学报, refType=null, unstructuredReference=刘兴, 王艳, 纪志成. 基于随机森林的风电功率短期预测方法[J]. 系统仿真学报, 2021, 33(11): 2606-2614., articleTitle=基于随机森林的风电功率短期预测方法, refAbstract=null), Reference(id=1236321556947849807, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=33, issue=11, pageStart=2606, pageEnd=2614, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=LIU Xing, WANG Yan, JI Zhicheng, journalName=Journal of System Simulation, refType=null, unstructuredReference=LIU Xing, WANG Yan, JI Zhicheng. Short-term wind power prediction method based on random forest[J]. Journal of System Simulation, 2021, 33(11): 2606-2614., articleTitle=Short-term wind power prediction method based on random forest, refAbstract=null), Reference(id=1236321557056901714, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=426, pageEnd=432, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=叶家豪, 魏霞, 黄德启, journalName=太阳能学报, refType=null, unstructuredReference=叶家豪, 魏霞, 黄德启, 等. 基于灰色关联分析的BSO-ELM-AdaBoost风电功率短期预测[J]. 太阳能学报, 2022, 43(3): 426-432., articleTitle=基于灰色关联分析的BSO-ELM-AdaBoost风电功率短期预测, refAbstract=null), Reference(id=1236321557149176407, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=426, pageEnd=432, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=YE Jiahao, WEI Xia, HUANG Deqi, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=YE Jiahao, WEI Xia, HUANG Deqi, et al. Short-term forecast of wind power based on BSO-ELM-AdaBoost with grey correlation analysis[J]. Acta Energiae Solaris Sinica, 2022, 43(3): 426-432., articleTitle=Short-term forecast of wind power based on BSO-ELM-AdaBoost with grey correlation analysis, refAbstract=null), Reference(id=1236321557266616924, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=22, pageEnd=30, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=张磊, 李海涛, 熊致知, journalName=电力建设, refType=null, unstructuredReference=张磊, 李海涛, 熊致知, 等. 基于可解释性XGBoost的电力系统惯量短期预测方法[J]. 电力建设, 2023, 44(8): 22-30., articleTitle=基于可解释性XGBoost的电力系统惯量短期预测方法, refAbstract=null), Reference(id=1236321557379863136, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=22, pageEnd=30, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=ZHANG Lei, LI Haitao, XIONG Zhizhi, journalName=Electric Power Construction, refType=null, unstructuredReference=ZHANG Lei, LI Haitao, XIONG Zhizhi, et al. Short-term prediction method based on interpretable XGBoost for power system inertia[J]. Electric Power Construction, 2023, 44(8): 22-30., articleTitle=Short-term prediction method based on interpretable XGBoost for power system inertia, refAbstract=null), Reference(id=1236321557493109352, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=9, pageStart=3615, pageEnd=3623, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=杨维熙, 刘勇, 舒勤, journalName=电网技术, refType=null, unstructuredReference=杨维熙, 刘勇, 舒勤. 基于补充集合经验模态分解的短期负荷预测模型[J]. 电网技术, 2022, 46(9): 3615-3623., articleTitle=基于补充集合经验模态分解的短期负荷预测模型, refAbstract=null), Reference(id=1236321557581189741, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=9, pageStart=3615, pageEnd=3623, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=YANG Weixi, LIU Yong, SHU Qin, journalName=Power System Technology, refType=null, unstructuredReference=YANG Weixi, LIU Yong, SHU Qin. A short-term load forecasting model based on CEEMD[J]. Power System Technology, 2022, 46(9): 3615-3623., articleTitle=A short-term load forecasting model based on CEEMD, refAbstract=null), Reference(id=1236321557669270129, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=8, pageStart=162, pageEnd=171, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=杨锡运, 马文兵, 彭琰, journalName=热力发电, refType=null, unstructuredReference=杨锡运, 马文兵, 彭琰, 等. 基于组合神经网络的分布式光伏超短期功率预测方法[J]. 热力发电, 2023, 52(8): 162-171., articleTitle=基于组合神经网络的分布式光伏超短期功率预测方法, refAbstract=null), Reference(id=1236321557778322040, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=8, pageStart=162, pageEnd=171, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=YANG Xiyun, MA Wenbing, PENG Yan, journalName=Thermal Power Generation, refType=null, unstructuredReference=YANG Xiyun, MA Wenbing, PENG Yan, et al. Distributed photovoltaic ultra-short-term power prediction method based on combined neural network[J]. Thermal Power Generation, 2023, 52(8): 162-171., articleTitle=Distributed photovoltaic ultra-short-term power prediction method based on combined neural network, refAbstract=null), Reference(id=1236321557874791038, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=7, pageStart=438, pageEnd=444, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=陈庆明, 廖鸿飞, 孙颖楷, journalName=太阳能学报, refType=null, unstructuredReference=陈庆明, 廖鸿飞, 孙颖楷, 等. 基于GWO-GRU的光伏发电功率预测[J]. 太阳能学报, 2024, 45(7): 438-444., articleTitle=基于GWO-GRU的光伏发电功率预测, refAbstract=null), Reference(id=1236321557979648643, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=7, pageStart=438, pageEnd=444, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=CHEN Qingming, LIAO Hongfei, SUN Yingkai, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=CHEN Qingming, LIAO Hongfei, SUN Yingkai, et al. Photovoltaic power prediction model based on GWO-GRU[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 438-444., articleTitle=Photovoltaic power prediction model based on GWO-GRU, refAbstract=null), Reference(id=1236321558071923334, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2025, volume=54, issue=7, pageStart=33, pageEnd=42, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=王勇权, 高明明, 王唯铧, journalName=热力发电, refType=null, unstructuredReference=王勇权, 高明明, 王唯铧, 等. 基于CNN-GRU-MHA的CFB机组污染物排放动态预测[J]. 热力发电, 2025, 54(7): 33-42., articleTitle=基于CNN-GRU-MHA的CFB机组污染物排放动态预测, refAbstract=null), Reference(id=1236321559435072141, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2025, volume=54, issue=7, pageStart=33, pageEnd=42, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=WANG Yongquan, GAO Mingming, WANG Weihua, journalName=Thermal Power Generation, refType=null, unstructuredReference=WANG Yongquan, GAO Mingming, WANG Weihua, et al. Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA[J]. Thermal Power Generation, 2025, 54(7): 33-42., articleTitle=Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA, refAbstract=null), Reference(id=1236321559598650002, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=288, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=WANG S, SHI J, YANG W, journalName=Energy, refType=null, unstructuredReference=WANG S, SHI J, YANG W, et al. High and low frequency wind power prediction based on Transformer and BiGRU-Attention[J]. Energy, 2024, 288: 129753., articleTitle=High and low frequency wind power prediction based on Transformer and BiGRU-Attention, refAbstract=null), Reference(id=1236321559720284825, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2025, volume=45, issue=12, pageStart=4693, pageEnd=4707, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=钟吴君, 李培强, 涂春鸣, journalName=中国电机工程学报, refType=null, unstructuredReference=钟吴君, 李培强, 涂春鸣. 基于尾流关联的动态超图风电功率超短期预测方法[J]. 中国电机工程学报, 2025, 45(12): 4693-4707., articleTitle=基于尾流关联的动态超图风电功率超短期预测方法, refAbstract=null), Reference(id=1236321559833531037, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2025, volume=45, issue=12, pageStart=4693, pageEnd=4707, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=ZHONG Wujun, LI Peiqiang, TU Chunming, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=ZHONG Wujun, LI Peiqiang, TU Chunming. Dynamic hypergraph wind power ultra short term prediction method based on wake correlation[J]. Proceedings of the CSEE, 2025, 45(12): 4693-4707., articleTitle=Dynamic hypergraph wind power ultra short term prediction method based on wake correlation, refAbstract=null), Reference(id=1236321559980331685, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2021, volume=224, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=LI Q, ZHANG X, MA T, journalName=Energy, refType=null, unstructuredReference=LI Q, ZHANG X, MA T, et al. A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine[J]. Energy, 2021, 224: 120094., articleTitle=A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine, refAbstract=null), Reference(id=1236321560106160812, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=84, pageEnd=93, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=王绍敏, 王守相, 赵倩宇, journalName=电力建设, refType=null, unstructuredReference=王绍敏, 王守相, 赵倩宇, 等. 基于频域分解和精度加权集成的分布式风电功率预测方法[J]. 电力建设, 2023, 44(5): 84-93., articleTitle=基于频域分解和精度加权集成的分布式风电功率预测方法, refAbstract=null), Reference(id=1236321560248767155, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=84, pageEnd=93, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=WANG Shaomin, WANG Shouxiang, ZHAO Qianyu, journalName=Electric Power Construction, refType=null, unstructuredReference=WANG Shaomin, WANG Shouxiang, ZHAO Qianyu, et al. Distributed wind power forecasting method based on frequency domain decomposition and precision-weighted ensemble[J]. Electric Power Construction, 2023, 44(5): 84-93., articleTitle=Distributed wind power forecasting method based on frequency domain decomposition and precision-weighted ensemble, refAbstract=null), Reference(id=1236321560332653240, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=59, issue=1, pageStart=192, pageEnd=206, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=WU Y K, HUANG C L, WU S H, journalName=IEEE Transactions on Industry Applications, refType=null, unstructuredReference=WU Y K, HUANG C L, WU S H, et al. Deterministic and probabilistic wind power forecasts by considering various atmospheric models and feature engineering approaches[J]. IEEE Transactions on Industry Applications, 2022, 59(1): 192-206., articleTitle=Deterministic and probabilistic wind power forecasts by considering various atmospheric models and feature engineering approaches, refAbstract=null), Reference(id=1236321560458482365, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=12, pageStart=21, pageEnd=28, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=苏子越, 柴琳, 谢亮, journalName=热力发电, refType=null, unstructuredReference=苏子越, 柴琳, 谢亮, 等. 基于变分模态分解的综合能源系统短期电负荷预测[J]. 热力发电, 2024, 53(12): 21-28., articleTitle=基于变分模态分解的综合能源系统短期电负荷预测, refAbstract=null), Reference(id=1236321560622060226, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=12, pageStart=21, pageEnd=28, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=SU Ziyue, CHAI Lin, XIE Liang, journalName=Thermal Power Generation, refType=null, unstructuredReference=SU Ziyue, CHAI Lin, XIE Liang, et al. Short-term electrical load forecasting for integrated energy system based on variational mode decomposition[J]. Thermal Power Generation, 2024, 53(12): 21-28., articleTitle=Short-term electrical load forecasting for integrated energy system based on variational mode decomposition, refAbstract=null), Reference(id=1236321560773055176, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=216, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=ZHANG J, LIU Z, CHEN T, journalName=Electric Power Systems Research, refType=null, unstructuredReference=ZHANG J, LIU Z, CHEN T. Interval prediction of ultra-short-term photovoltaic power based on a hybrid model[J]. Electric Power Systems Research, 2023, 216: 109035., articleTitle=Interval prediction of ultra-short-term photovoltaic power based on a hybrid model, refAbstract=null), Reference(id=1236321560903078603, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2022, volume=206, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=35, authorNames=LIANG Y, LIN Y, LU Q, journalName=Expert Systems with Applications, refType=null, unstructuredReference=LIANG Y, LIN Y, LU Q. Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM[J]. Expert Systems with Applications, 2022, 206: 117847., articleTitle=Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM, refAbstract=null), Reference(id=1236321561146348242, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=25, pageStart=33, pageEnd=40, url=null, language=null, rfNumber=[23], rfOrder=36, authorNames=张学清, 梁军, 张熙, journalName=中国电机工程学报, refType=null, unstructuredReference=张学清, 梁军, 张熙, 等. 基于样本熵和极端学习机的超短期风电功率组合预测模型[J]. 中国电机工程学报, 2013, 33(25): 33-40., articleTitle=基于样本熵和极端学习机的超短期风电功率组合预测模型, refAbstract=null), Reference(id=1236321561259594456, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=25, pageStart=33, pageEnd=40, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=ZHANG Xueqing, LIANG Jun, ZHANG Xi, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=ZHANG Xueqing, LIANG Jun, ZHANG Xi, et al. Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J]. Proceedings of the CSEE, 2013, 33(25): 33-40., articleTitle=Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine, refAbstract=null), Reference(id=1236321561368646365, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=2952, pageEnd=2963, url=null, language=null, rfNumber=[24], rfOrder=38, authorNames=ZHOU S, CHEN D, PAN J, journalName=null, refType=null, unstructuredReference=ZHOU S, CHEN D, PAN J, et al. Adapt or perish: adaptive sparse transformer with attentive feature refinement for image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 2952-2963., articleTitle=Adapt or perish: adaptive sparse transformer with attentive feature refinement for image restoration, refAbstract=null), Reference(id=1236321561452532448, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=9, pageStart=3850, pageEnd=3859, url=null, language=null, rfNumber=[25], rfOrder=39, authorNames=吉兴全, 赵国航, 叶平峰, journalName=高电压技术, refType=null, unstructuredReference=吉兴全, 赵国航, 叶平峰, 等. 基于QMD-HBiGRU的短期光伏功率预测方法[J]. 高电压技术, 2024, 50(9): 3850-3859., articleTitle=基于QMD-HBiGRU的短期光伏功率预测方法, refAbstract=null), Reference(id=1236321561616110308, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=9, pageStart=3850, pageEnd=3859, url=null, language=null, rfNumber=[25], rfOrder=40, authorNames=JI Xingquan, ZHAO Guohang, YE Pingfeng, journalName=High Voltage Engineering, refType=null, unstructuredReference=JI Xingquan, ZHAO Guohang, YE Pingfeng, et al. Short-term PV forecasting method based on QMD-HBiGRU model[J]. High Voltage Engineering, 2024, 50(9): 3850-3859., articleTitle=Short-term PV forecasting method based on QMD-HBiGRU model, refAbstract=null), Reference(id=1236321561737745125, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=5, pageStart=122, pageEnd=131, url=null, language=null, rfNumber=[26], rfOrder=41, authorNames=王辉, 邹智超, 李欣, journalName=热力发电, refType=null, unstructuredReference=王辉, 邹智超, 李欣, 等. 基于VMD-ISSA-GRU组合模型的短期风电功率预测[J]. 热力发电, 2024, 53(5): 122-131., articleTitle=基于VMD-ISSA-GRU组合模型的短期风电功率预测, refAbstract=null), Reference(id=1236321561850991336, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=5, pageStart=122, pageEnd=131, url=null, language=null, rfNumber=[26], rfOrder=42, authorNames=WANG Hui, ZOU Zhichao, LI Xin, journalName=Thermal Power Generation, refType=null, unstructuredReference=WANG Hui, ZOU Zhichao, LI Xin, et al. Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model[J]. Thermal Power Generation, 2024, 53(5): 122-131., articleTitle=Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model, refAbstract=null), Reference(id=1236321561960043243, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=47, issue=8, pageStart=156, pageEnd=168, url=null, language=null, rfNumber=[27], rfOrder=43, authorNames=李青, 张新燕, 摆志俊, journalName=电力系统自动化, refType=null, unstructuredReference=李青, 张新燕, 摆志俊, 等. 基于MQ-WaveNet的风电集群发电功率多步概率预测[J]. 电力系统自动化, 2023, 47(8): 156-168., articleTitle=基于MQ-WaveNet的风电集群发电功率多步概率预测, refAbstract=null), Reference(id=1236321562052317936, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, doi=null, pmid=null, pmcid=null, year=2023, volume=47, issue=8, pageStart=156, pageEnd=168, url=null, language=null, rfNumber=[27], rfOrder=44, authorNames=LI Qing, ZHANG Xinyan, BAI Zhijun, journalName=Automation of Electric Power Systems, refType=null, unstructuredReference=LI Qing, ZHANG Xinyan, BAI Zhijun, et al. Multi-step probability prediction of power generation for wind power clusters based on Multi-horizon quantile-WaveNet[J]. Automation of Electric Power Systems, 2023, 47(8): 156-168., articleTitle=Multi-step probability prediction of power generation for wind power clusters based on Multi-horizon quantile-WaveNet, refAbstract=null)], funds=[Fund(id=1236321555408540137, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, awardId=62273215, language=EN, fundingSource=National Natural Science Foundation of China(62273215), fundOrder=null, country=null), Fund(id=1236321555509203442, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, awardId=62273215, language=CN, fundingSource=国家自然科学基金项目(62273215), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1236321544239108148, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, xref=1., ext=[AuthorCompanyExt(id=1236321544247496757, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1236321544260079670, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544239108148, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山东科技大学电气与自动化工程学院,山东 青岛 266590)]), AuthorCompany(id=1236321544352354364, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, xref=2., ext=[AuthorCompanyExt(id=1236321544360742973, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544352354364, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Yiqiao Coal Mine of Jining Energy Group, Jining 272500, China), AuthorCompanyExt(id=1236321544369131582, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, companyId=1236321544352354364, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.济宁能源集团义桥煤矿,山东 济宁 272500)])], figs=[ArticleFig(id=1236321548076896429, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.1, caption=Structural diagram of the AST, figureFileSmall=yzlJQ/taqJrNVRZodowWOg==, figureFileBig=Ypjamif6gwZCXLxk7aRREg==, tableContent=null), ArticleFig(id=1236321548152393907, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图1, caption=AST结构示意, figureFileSmall=yzlJQ/taqJrNVRZodowWOg==, figureFileBig=Ypjamif6gwZCXLxk7aRREg==, tableContent=null), ArticleFig(id=1236321548383080644, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.2, caption=Schematic diagram of the ASSA, figureFileSmall=UjhalizHCI6zQnls0KgeGA==, figureFileBig=TRWsX8ZPJdA07B+pMxDv8Q==, tableContent=null), ArticleFig(id=1236321548487938251, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图2, caption=ASSA示意, figureFileSmall=UjhalizHCI6zQnls0KgeGA==, figureFileBig=TRWsX8ZPJdA07B+pMxDv8Q==, tableContent=null), ArticleFig(id=1236321548622155986, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.3, caption=Structural diagram of the ASBiGRU, figureFileSmall=etFXlxP355jA+2+BptOuSw==, figureFileBig=tFsj/CUOxTmA5zvFX8391Q==, tableContent=null), ArticleFig(id=1236321548752179417, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图3, caption=ASBiGRU结构示意, figureFileSmall=etFXlxP355jA+2+BptOuSw==, figureFileBig=tFsj/CUOxTmA5zvFX8391Q==, tableContent=null), ArticleFig(id=1236321548844454111, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.4, caption=Structural diagram of the GRU, figureFileSmall=9xaTGmqdJ10E+tQHD63mdg==, figureFileBig=MNxnuPHD/9krm5yb3xsSiw==, tableContent=null), ArticleFig(id=1236321548966088932, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图4, caption=GRU结构示意, figureFileSmall=9xaTGmqdJ10E+tQHD63mdg==, figureFileBig=MNxnuPHD/9krm5yb3xsSiw==, tableContent=null), ArticleFig(id=1236321549138055403, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.5, caption=Flowchart of wind power prediction based on ICEEMDAN-SE-AST-ASBiGRU, figureFileSmall=xpmS+8Vxw82xwr6MZbLEAA==, figureFileBig=AIWhxtH2OLYLY9L1r2lD5g==, tableContent=null), ArticleFig(id=1236321550572507386, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图5, caption=基于ICEEMDAN-SE-AST-ASBiGRU的风电功率预测流程, figureFileSmall=xpmS+8Vxw82xwr6MZbLEAA==, figureFileBig=AIWhxtH2OLYLY9L1r2lD5g==, tableContent=null), ArticleFig(id=1236321550706725123, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.6, caption=Sample entropy of IMF component of each sample, figureFileSmall=bMvr0HVCf0xCLW/d820lCw==, figureFileBig=a14qGZjVsDbs+ZQlHU73pw==, tableContent=null), ArticleFig(id=1236321550849331468, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图6, caption=各样本IMF分量样本熵, figureFileSmall=bMvr0HVCf0xCLW/d820lCw==, figureFileBig=a14qGZjVsDbs+ZQlHU73pw==, tableContent=null), ArticleFig(id=1236321550996132120, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.7, caption=Data reconstruction result, figureFileSmall=6ruZlKr1Yj3ef4pQNIiDMQ==, figureFileBig=G78osa1JnHXqqfT7lvybYQ==, tableContent=null), ArticleFig(id=1236321551151321379, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图7, caption=数据重构结果, figureFileSmall=6ruZlKr1Yj3ef4pQNIiDMQ==, figureFileBig=G78osa1JnHXqqfT7lvybYQ==, tableContent=null), ArticleFig(id=1236321551285539113, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.8, caption=Prediction results of high-frequency oscillation component, figureFileSmall=/t7uiwU1vxTCu3/+b7zChw==, figureFileBig=BW9CfZw5td1vR14o1jcaKQ==, tableContent=null), ArticleFig(id=1236321551440728372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图8, caption=高频振荡分量预测结果, figureFileSmall=/t7uiwU1vxTCu3/+b7zChw==, figureFileBig=BW9CfZw5td1vR14o1jcaKQ==, tableContent=null), ArticleFig(id=1236321551541391678, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.9, caption=Prediction results of low-frequency stationary component, figureFileSmall=spxfe4tQBzLjoU22/ADFIw==, figureFileBig=vBxxlvyA8W6+GydgVVXf2g==, tableContent=null), ArticleFig(id=1236321551633666373, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图9, caption=低频平稳分量预测结果, figureFileSmall=spxfe4tQBzLjoU22/ADFIw==, figureFileBig=vBxxlvyA8W6+GydgVVXf2g==, tableContent=null), ArticleFig(id=1236321551746912588, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.10, caption=Wind power prediction results of each decomposition model, figureFileSmall=HpN0imbPnot0Cq5unUzKKA==, figureFileBig=STBUiPf82Yowl5P+83Qnjw==, tableContent=null), ArticleFig(id=1236321551872741721, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图10, caption=各分解模型风电功率预测结果, figureFileSmall=HpN0imbPnot0Cq5unUzKKA==, figureFileBig=STBUiPf82Yowl5P+83Qnjw==, tableContent=null), ArticleFig(id=1236321551985987941, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Fig.11, caption=Wind power prediction results of each forecasting model, figureFileSmall=g9/Yu6fpNoAiw3yu8fWk7w==, figureFileBig=rAnQ46a83By35IL0AIfkMw==, tableContent=null), ArticleFig(id=1236321552107622767, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=图11, caption=各预测模型风电功率预测结果, figureFileSmall=g9/Yu6fpNoAiw3yu8fWk7w==, figureFileBig=rAnQ46a83By35IL0AIfkMw==, tableContent=null), ArticleFig(id=1236321552363475318, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.1, caption=

Correlation coefficients between wind power and meteorological variable linear

, figureFileSmall=null, figureFileBig=null, tableContent=
气象因素相关系数
10 m高风速0.738
30 m高风速0.658
50 m高风速0.874
中心高风速0.901
10 m高风向0.207
30 m高风向0.635
50 m高风向0.546
中心高风向0.786
10 m高气压0.613
10 m高湿度0.091
10 m高温度0.135
), ArticleFig(id=1236321552506081665, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表1, caption=

风电功率与气象变量线性相关系数

, figureFileSmall=null, figureFileBig=null, tableContent=
气象因素相关系数
10 m高风速0.738
30 m高风速0.658
50 m高风速0.874
中心高风速0.901
10 m高风向0.207
30 m高风向0.635
50 m高风向0.546
中心高风向0.786
10 m高气压0.613
10 m高湿度0.091
10 m高温度0.135
), ArticleFig(id=1236321552619327879, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.2, caption=

The IMF component reconstruction results

, figureFileSmall=null, figureFileBig=null, tableContent=
分量名称原分量序号
高频振荡分量1、2、3、4、5、6
低频平稳分量7、8、9、10、11、12、13
), ArticleFig(id=1236321552690631054, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表2, caption=

IMF分量重构结果

, figureFileSmall=null, figureFileBig=null, tableContent=
分量名称原分量序号
高频振荡分量1、2、3、4、5、6
低频平稳分量7、8、9、10、11、12、13
), ArticleFig(id=1236321552854208919, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.3, caption=

Comparison of high-frequency oscillation component models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWR2训练时间/s
FEDformer3.512 30.853 2504
ASBiGRU3.256 10.872 4316
Informer2.731 40.914 1392
TFT2.027 10.926 3464
AST1.689 70.964 3348
), ArticleFig(id=1236321552980038052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表3, caption=

高频振荡分量模型对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWR2训练时间/s
FEDformer3.512 30.853 2504
ASBiGRU3.256 10.872 4316
Informer2.731 40.914 1392
TFT2.027 10.926 3464
AST1.689 70.964 3348
), ArticleFig(id=1236321553214919087, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.4, caption=

Comparison of low-frequency stationary component models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWR2训练时间/s
AST2.724 20.894 1324
BiGRU2.163 10.913 2211
ASBiGRU1.465 70.976 2146
), ArticleFig(id=1236321553332359609, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表4, caption=

低频平稳分量模型对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWR2训练时间/s
AST2.724 20.894 1324
BiGRU2.163 10.913 2211
ASBiGRU1.465 70.976 2146
), ArticleFig(id=1236321553449800132, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.5, caption=

The prediction accuracy of each decomposition model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWδMAE/MWR2
H14.372 52.973 20.743 7
H23.863 22.671 40.794 5
H33.636 12.482 10.814 2
H43.385 42.357 20.843 6
H52.657 31.836 70.904 1
H62.174 61.324 30.913 6
), ArticleFig(id=1236321553600795083, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表5, caption=

各分解模型预测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWδMAE/MWR2
H14.372 52.973 20.743 7
H23.863 22.671 40.794 5
H33.636 12.482 10.814 2
H43.385 42.357 20.843 6
H52.657 31.836 70.904 1
H62.174 61.324 30.913 6
), ArticleFig(id=1236321555127521753, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=EN, label=Tab.6, caption=

Comparative analysis of forecasting accuracy among diverse predictive models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWδMAE/MWR2
M14.3283.730.818 9
M23.2242.750.864 2
M32.7942.310.891 2
M42.3741.780.925 6
M51.6841.310.967 9
), ArticleFig(id=1236321555228185055, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236321539621180356, language=CN, label=表6, caption=

各预测模型预测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/MWδMAE/MWR2
M14.3283.730.818 9
M23.2242.750.864 2
M32.7942.310.891 2
M42.3741.780.925 6
M51.6841.310.967 9
)], 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.202412272, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202412272, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202412272, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202412272, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于模态分解与组合神经网络的超短期风电功率预测
收藏切换
PDF下载
高正中 1 , 况逸 1 , 张经龙 2
热力发电 | 热能科学研究 2025,54(10): 82-92
收起
收藏切换
热力发电 | 热能科学研究 2025, 54(10): 82-92
基于模态分解与组合神经网络的超短期风电功率预测
全屏
高正中1 , 况逸1, 张经龙2
作者信息
  • 1.山东科技大学电气与自动化工程学院,山东 青岛 266590
  • 2.济宁能源集团义桥煤矿,山东 济宁 272500
  • 高正中(1971),男,博士,教授,主要研究方向为新能源功率预测、智能电网技术,

Ultra-short-term wind power prediction based on modal decomposition and combined neural network
Zhengzhong GAO1 , Yi KUANG1, Jinglong ZHANG2
Affiliations
  • 1.College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
  • 2.Yiqiao Coal Mine of Jining Energy Group, Jining 272500, China
出版时间: 2025-10-25 doi: 10.19666/j.rlfd.202412272
文章导航
收藏切换

针对风电功率数据存在的显著波动性和随机性导致风电功率预测中单一模型预测精确度欠佳的问题,提出了一种基于模态分解和组合神经网络模型的超短期风电功率预测方法。首先,基于改进完全集成经验模态分解和样本熵对风电数据进行处理,由不平稳序列分解为较为平稳子序列,同步重构出高频振荡分量和低频平稳分量。然后,构建基于自适应稀疏自注意力机制的风电混合预测模型,对于复杂度较高的高频振荡分量,采用自适应稀疏Transformer模型充分发掘关键波动特征;对于低频平稳分量,采用双向门控循环单元模型充分提取序列特征。最后,将各分量预测结果叠加得到最终预测结果。基于山东某风电场的实际数据进行测试,结果表明:相较于其他常用模型,所提模型均方根误差和平均绝对误差分别减小2.644 MW和2.420 MW,同时决定系数提高18.2%,具有良好的预测性能。

模态分解  /  风电功率预测  /  样本熵  /  自适应稀疏自注意力机制

Due to the significant volatility and randomness of wind power data, low prediction accuracy is often observed with a single model in wind power prediction. To overcome this, an ultra-short-term wind power prediction method is introduced, based on modal decomposition and a combined neural network model. Firstly, the wind power data are processed based on the improved fully integrated empirical modal decomposition and sample entropy, which decomposes the unsteady series into smoother sub-sequences and reconstructs the high-frequency oscillatory component and low-frequency smooth component synchronously. Secondly, a hybrid prediction model for wind power based on an adaptive sparse self-attention mechanism is constructed. For the high-frequency oscillatory component with high complexity, the adaptive sparse Transformer model is used to fully explore the fluctuation information. For the low-frequency stationary components, the sequence features are fully extracted by the bidirectional gated recurrent unit model. Finally, the final prediction outcomes are derived by overlaying the forecast results of each component. Test was performed with actual data from a wind farm in Shandong, and the results show that, compared with other commonly used models, the proposed model’s root mean square error and average absolute error has decreased by 2.644 MW and 2.42 MW, and the coefficient of determination has a notable 18.2% increase, implying it has a good prediction performance.

modal decomposition  /  wind power prediction  /  sample entropy  /  adaptive sparse self-attention mechanism
高正中, 况逸, 张经龙. 基于模态分解与组合神经网络的超短期风电功率预测. 热力发电, 2025 , 54 (10) : 82 -92 . DOI: 10.19666/j.rlfd.202412272
Zhengzhong GAO, Yi KUANG, Jinglong ZHANG. Ultra-short-term wind power prediction based on modal decomposition and combined neural network[J]. Thermal Power Generation, 2025 , 54 (10) : 82 -92 . DOI: 10.19666/j.rlfd.202412272
为了实现“双碳”战略目标,深化电力系统改革,加快构建能源供给新体系,发展以风电为代表的可再生能源,已经成为我国能源转型的核心[1-2]。但风电在配网侧的大规模接入,导致电力系统的不确定性提高。提高风电功率的短期预测精度有助于降低风电对电网的不确定性扰动,有效提升新能源的消纳水平,助力国家能源转型[3]。因此,如何有效识别和提取风电机组数据的深层关键特征,提升风电功率预测的准确性是当前亟待解决的关键问题。
短期风电功率预测主要分为物理方法[4]和统计方法[5]。物理建模方法基于风场环境构建力学模型,需要精准的气象和风机数据,建模复杂且计算量大,在实际应用中效率不足。统计方法基于历史数据和统计模型,常见的统计方法包括机器学习算法[6]。如支持向量机[7]、随机森林[8]和极限学习机[9]等。此类方法不受地理环境的限制,具有一定前景。但风电功率与相关因素的复杂关系难以把握,现有方法不能满足工程实际的需要。
近年来,随着人工智能迅猛发展,风电功率预测也迎来新的突破,如采用分布式梯度增强库(XGBoost)、广义回归神经网络(GRNN)、长短时记忆(LSTM)神经网络等深度学习方法[10-12]凭借对非线性函数高效的拟合性能,在风电功率预测方面得到了广泛的应用。文献[13]提出了门控循环单元(gated recurrent unit,GRU)神经网络模型是基于循环神经网络(RNN)的改进模型,对光伏功率数据可进行动态挖掘,能在一定程度上缓解梯度爆炸和梯度消失问题。文献[14]提出一种基于卷积神经网络(CNN)的改进GRU模型,可有效提高模型的特征提取能力,但受限于单向递归结构,无法考虑耦合双向时序信息,在处理长时序列时易出现关键信息遗失的问题。文献[15]引入基于多头注意力机制的Transformer架构,利用编码-解码流程有效捕捉数据间的依赖关系,提升了风电功率预测精度。文献[16]将图卷积神经网络与LSTM神经网络相结合,实现了动态特征的高效提取。但上述方法仅从原始需求方面出发进行建模,未深入考虑风电功率数据是典型的强波动信号,易受干扰变量影响的特点,直接建立单一预测模型误差较大。
为进一步解决上述问题,研究人员提出基于组合模型的风电功率预测方法,通过发挥不同模型的优势,挖掘数据集的特征信息,提高预测精度[17]。组合预测方法结合深度学习与信号分解的优势区间,引入预处理环节实现对序列的降维,提高预测精度[18]。文献[19]提出的经验模态分解(empirical mode decomposition,EMD)方法,能有效避免不平稳数据对预测结果的影响,但处理过程易出现模态混淆问题。文献[20]提出变分模态分解(variational mode decomposition,VMD)方法,将原始信号分解为非递归模态分量,来解决EMD模态混淆的问题,但在序列重构阶段,会引入部分误差,影响预测精度。相对而言,自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)算法[21]能够高效处理非线性信号。但在分解过程中易出现噪声引入过量问题,对预测精度产生不利影响。可见,现有组合方法均未很好地考虑分解残留高频噪声对预测精度的影响,在处理序列耦合关系的过程中呈现削弱趋势,无法高效统合特征数据。
综上,为挖掘风电机组数据的深层耦合特征,提高预测精度。本文提出了一种基于模态分解和组合神经网络模型的超短期风电功率预测方法,主要贡献如下:
1)提出基于改进完全自适应噪声集合经验模态分解(improved complete ensemble empirical mode decomposition with adaptive noise,ICEEMDAN)和样本熵(sample entropy,SE)的数据预处理方法,通过ICEEMDAN算法在实现风电功率数据降维的同时保留各子序列间的耦合特征,增强模型数据泛化能力;结合SE实现序列同频重构,在保证预测精度的同时,实现预测流程的架构优化。
2)提出基于自适应稀疏Transformer(adaptive sparse transformer,AST)和ASBiGRU(adaptive sparse bi-directional gated recurrent unit)的混合功率预测模型,引入自适应稀疏自注意力机制,以表征风电机组数据多变量间的强耦合性关系,增强模型鲁棒性。发挥Transformer的架构优势应对高频振荡分量,通过ASBiGRU模型处理低频平稳分量的长期依赖关系。集成多模型优势区间,在实现预测精度提升的同时,优化预测效率。
风电功率数据属于强波动、不确定性数据。为降低风电功率数据随机性和波动性对预测精度的影响,本文提出的ICEEMDAN-SE方法将原始功率序列分解为若干组不同频率的本征模态分量(intrinsic mode function,IMF),进而实现对原始序列中非线性特征的捕捉。在此基础上,基于SE算法计算各分量复杂程度,并重构聚合相似分量,通过低维映射减轻模型运算负担,在兼顾效率提升的同时改善了预测精度。
ICEEMDAN在分解过程采用添加自适应噪声的方法,根据每次分解的信号动态特征自适应地调整噪声方差。避免出现高斯噪声过度引入的问题[22]。分解主要步骤如下。
1)自适应噪声处理 对原始信号添加高斯白噪声v(i),得到含可控噪声信号s(i)为:
s1(i)=s+β0E1v(i)
式中:s为原始信号;Ek(·)为经过EMD分解所产生的第k阶模态分量;β0为第1个分解信号的噪声标准差;ω1(i)为第i次添加的高斯白噪声。
2)一阶残差分量获取 当k=1时,计算第1阶残差分量r1,计算公式为:
r1=M(x(i))
式中:M(·)为计算信号局部平均值的算子;〈·〉表示取平均值。
3)一阶模态分量获取 将原始信号s减去第1阶残差分量r1得到第1阶模态分量IMF为:
IMF1=sr1
4)k阶残差噪声获取 当k≥2时,计算第k阶残差分量rk为:
rk=M[rk1+βk1Ek(v(i))]
式中:k=2,3,…, NN为固有模态函数的分量总数;rk-1为第k–1阶残差分量;βk-1k–1次噪声幅度系数。
5)k阶模态分量获取 模态分量IMFk为:
IMFk=rk1rk
SE是基于近似熵技术上的改进方法,数据的依赖性小,对时间序列的估计更加精确,具有更好的一致性和准确性。
传统预测方法在数据分解后单独为各模态分别建立预测模型,这种方法易出现计算复杂度骤升及误差累积的问题。通过计算SE值,将风电功率IMF分量复杂度进行量化,重构出高频振荡分量和低频平稳分量2种不同动态特性的时间序列,可有效降低预测模型的复杂程度,避免出现误差累积效应[23]。SE计算过程如下。
1)给定时间序列x={x(1),…,x(N)},按顺序组成多个m维向量:
X(i)={x(i),x(i+1),...,x(i+m1)}
式中:i=1,2,…,N-m+1;m为向量维数。
2)计算X(i)和X(j)对应元素最大差值d[X(i), X(j)]的表达式为:
d[X(i),X(j)]=max|x(i+k)x(j+k)|
式中:k∈[0,m-1]。
3)对于X(i),统计X(i)和X(j)之间小于相似容限rj的数目,同时计算与距离个数N-m的比值Bim(r)
Bim(r)=1NmBi
式中:1≤iN-m
4)对所有Bim(r)取平均值。
Bm(r)=1Nm+1i=1Nm+1Bim(r)
5)将维数增加至m+1,重复式(6)—式(8),得到Bim+1(r)
Bm+1(r)=1Nmi=1NmBim+1(r)
6)计算序列样本熵的理论值。
SampEn(m,r,N)=[lnBm+1(r)Bm(r)]
7)计算IMF分量SE阈值S^
S^=1Pp=1PS¯p
式中:P为IMF的总数。
本文针对高频振荡分量中的非线性特征及高频噪声,采用AST模型进行预测,模型结构如图1所示。AST通过自适应稀疏自注意力(adaptive sparse self-attention,ASSA)和特征细化前馈网络(feature refinement feed-forward network,FRFN)减少无关数据的干扰和特征冗余,在保留数据特征的基础上,实现对冗余计算任务的剔除,在模型结构上保证了预测效率[24]
首先,通过位置编码实现时序信息嵌入隐藏信息矩阵,确保可有效捕捉序列间的依赖关系;随后,利用ASSA机制对振荡分量与其相关信息之间的高维特征进行提取,动态调整注意力权重;接着,借助FRFN中的部分卷积及深度可分离卷积对ASSA的输出特征进行筛选,旨在减少冗余数据并增强模型的非线性拟合能力;最后,通过输出层的线性变换和Sigmoid激活函数完成预测任务。
本文所提ASSA注意力机制在自注意力的基础上引入稀疏性,结构如图2所示。ASSA注意力机制通过计算向量间的相关性得分,为时序向量分配不同的注意力权重,以表征向量间的依赖关系,从而有效处理不同数据之间的相关性。每个输入元素只与部分其他元素计算注意力权重,能够更好地控制输入标记的稀疏度,从而提高模型的泛化能力和准确性。
注意力机制由查询向量集(Q)、键向量集(K)和值向量集(V)组成,主要用于计算并获取值的加权总和。计算公式为:
A=f(QKT/d+B)V
式中:A为传统注意力机制;d为输入维数;B为相对位置偏置;f(·)为评估函数。
ASSA注意力机制主要包含稀疏分支(spares self-attention,SSA)和密集分支(dense self-attention,DSA)2个分支,其函数表达式为:
A=(w1SSA+w2DSA)V
式中w1w2分别为SSA和DSA对应的归一化权重值,可描述为:
wn=eani=1Neai,n={1,2}
式中{a1,a2}为可学习参数。
SSA可对输入数据进行过滤,避免不相关的数据影响特征聚合,可描述为:
SSA=ReLU2(QKT/d+B)
式中:ReLU表示激活函数。在本文所提模型中,ReLU类激活函数可实现注意力机制的稀疏性,增强特征聚合。
DSA能够确保网络中有足够的信息流动,以学习出具有区分度的特征表示,可描述为:
DSA=SoftMax(QKT/d+B)
式中:SoftMax表示激活函数。本文所提模型中,SoftMax类激活函数可实现数据关键信息的保留。
通过ASSA模块对输入数据进行处理后,所得到的特征数据仍存在一定的信息冗余问题。为此,通过对前馈网络引入部分卷积构建特征细化前馈网络,选取具有代表性的特征进行增强表示,同时消除特征冗余问题。FRFN可表示为:
{X^=GELU(W1PConv(X^))[X^1,X^2]=X^Xr^=X1^F(DWConv(R(X2^)))X^out=GELU(W2X^r)
式中:X^为输入数据;X^为输出数据;W1W2为线性投影;[·]表示channel-wise卷积;R(·)和F(·)分别表示特征重塑和扁平化;PCconv(·)和DWconv(·)分别表示部分卷积和深度可分离卷积;·表示矩阵乘法。
为增强对低频平稳分量的特征感知能力,将ASSA机制与双向门控循环单元(bi-directional gated recurrent unit,BiGRU)相融合,利用ASSA机制的稀疏注意力动态筛选关键时序特征,并结合BiGRU的双向机制捕捉特征间的长期依赖关系,构建ASBiGRU模型,其结构如图3所示。
图3可见,BiGRU由正、反向GRU构成,可保证信息在神经网络中的双向传播,有利于挖掘耦合时间步间的深层信息[25],可表示为:
ht=Concat(htf,htb)
式中:htt时刻合并的结果;Concat为拼接操作;htfhtb分别表示前向和后向的隐藏层状态。
GRU主要由更新门和重置门组成[26],结构如图4所示。
计算公式为:
rt=σ(Wr[ht1,xt]+br)
zt=σ(Wz[ht1,xt]+bz)
h˜t=tanh(Wh[rtht1,xt]+bh)
ht=(1zt)ht1+zth˜t
式中:rtzt分别为重置门和更新门;xtt时刻的输入数据;WrWzWh为权重矩阵;brbzbh为偏置向量;s表示Sigmoid激活函数;tanh(·)表示tanh激活函数;h˜t为通过重置门后的候选状态;ht为通过更新门控制的隐藏状态;ht–1为前一时刻隐藏神经元的输出;表示哈达马积。
为提高风电功率预测精度,本文将ICEEMDAN、SE、AST、ASBiGRU模型相结合,构建组合预测模型。该组合模型整体架构如图5所示,核心步骤简述如下。
1)原始功率数据处理 收集风电功率历史数据。利用ICEEMDAN将预处理的风电功率数据分解为多个IMF分量和残差分量。基于分量的SE值,以原始数据样本熵阈值为基准,对分解后的序列进行重构,重构为高频振荡分量和低频平稳分量。
2)数据预处理 利用最大互信息系数(maximal information coefficient,MIC)确定模型气象因素输入特征,与各分量进行归一化处理,并将数据集按8:1:1的比例划分为训练集、验证集和测试集。
3)构建混合预测模型 将重构后的功率分量与气象数据同时输入模型中。对于高频振荡分量采用AST模型进行预测;对于低频平稳分量先采用ASSA机制对数据进行特征挖掘,之后通过BiGRU模型获得更准确低频分量的预测结果。
4)误差分析 对各分量结果进行反归一化处理,采用线性合并得到风电功率预测值,借助误差评估指标与对比模型进行综合对比分析。
本文以山东某风电场2021年1月1日至5月1日的风电功率数据为例进行仿真。采样频率为15 min,选取前80%的数据用于训练模型,剩余数据按1:1比例用于验证与测试模型。采用Python深度学习框架构建风电功率短期预测模型。实验室计算机系统为Win11,CPU为intel i9-13900H,GPU为Nvidia RTX4060。
实验中模型参数选取:训练次数为200次,学习率为0.001,batch_size为64,采用adam优化器,并使用均方根误差作为损失函数。
风电功率与多种因素相关,如果盲目选取输入数据,该数据与输出目标之间的相关性指数过低,会导致模型计算量增加,降低训练效率和预测精度。
为此,采用最大互信息系数法来分析各气象变量与风电功率之间的相关性,系数越大相关性越高,计算公式为:
MIC(X,Y)=maxa×b<BMI(X,Y)log2min(a,b)
式中:ab分别为散点图网格划分时横、纵坐标轴单元格的数量;B为网格数上限;MI(X,Y)为互信息值,其计算公式为:
MI(X,Y)=XYP(X,Y)lgP(X,Y)P(X)P(Y)
式中:P(X,Y)为X、Y的联合密度分布函数;P(X)与P(Y)分别为X、Y边缘密度分布函数[27]
风电功率与气象变量线性相关系数见表1。本文选取最大信息系数(MIC)较大的8组气象变量作为关键影响因素,分别与高频振荡分量输入AST模型,与低频平稳分量输入ASBiGRU模型。
误差评价指标采用均方根误差(root mean square error,δRMSE)、平均绝对误差(mean absolute error,δMAE)和决定系数(coefficient of determination,R2)等指标评价模型性能。各评价指标表达式为:
δRMSE=1Ni=1N(yiy^i)2
δMAE=1Ni=1Nyiy^i
R2=1i=1N(yiy^i)2i=1N(yiy¯)2
式中:yiy^i分别为i时刻功率的真实值和预测值;y¯为功率平均值;N为预测时间点数。
本文通过改进完全集成经验模态分解结合样本熵的方法,降低风电功率的随机性和波动性。采用ICEEMDAN方法对风电功率数据进行分解处理,得到IMF分量。根据SE算法,计算各分量的熵值,计算结果如图6所示。
对信号分解后的各模态分量进行重构,样本熵值与模态复杂度及非线性强度呈正相关关系,样本熵值越大,对预测精度的影响越大。
原始数据样本熵阈值为0.412,由图6可见,前6个IMF分量的SE值高于样本熵阈值,含有较多的非线性数据,可划分为高频振荡分量。后7个IMF分量SE低于样本熵阈值,故将后7个分量叠加作为低频分量。叠加结果见表2,重构结果如图7所示。
为验证本文基于各分量数据特性所提的预测模型的有效性,分别对高频振荡分量预测模型AST与低频平稳分量预测模型ASBiGRU构建对比实验,以评估其预测性能及适用性。
为验证本文所提AST模型在处理高频振荡分量中非线性特征及高频噪声的优越性,选择在时间序列预测中广泛认可的基线模型——Informer、FEDformer及TFT与本文所提出的AST和ASBiGRU模型进行对比,预测效果如图8所示,并借助相关评价指标进行分析,结果见表3
为验证本文所提ASBiGRU模型在处理低频平稳分量中数据长期依赖关系及平稳特征的优越性,分别构建BiGRU、AST和ASBiGRU模型,预测结果如图9所示,并借助相关评价指标进行分析,结果见表4
图9表4可知,当功率数据呈现较强时间依赖性及平稳性时,相较于BiGRU模型,AST模型在处理低频平稳分量时,模型复杂度较高,且对数据的长期依赖关系不敏感,预测效果欠佳;实验结果表明,ASBiGRU模型在BiGRU模型的基础上引入ASSA机制,能够进一步提取低频平稳分量的关键特征,具有良好的预测性能。
为全面验证所提模型的有效性,分别针对数据分解方法与混合预测模型进行独立检验。一方面,通过对比实验以验证ICEEMDAN-SE数据处理模型的性能;另一方面,设置对比算例以验证AST-ASBiGRU混合预测模型的预测性能。
为了验证本文所提数据处理方法的优越性,分别构建EMD(H1)、EMD-SE(H2)、VMD(H3)、VMD-SE(H4)和CEEMDAN-SE(H5)及本文所提的ICEEMDAN-SE(H6)对风电数据进行处理,并通过BiGRU模型对各模型数据进行预测,预测效果及其评价结果如图10表5所示。
图10可见,对于相同的预测模型,应用不同数据分解算法后的预测功率曲线有较大差异,其中,经过数据重构的数据分解算法较常规算法预测效果有一定改善。与EMD、CEEMDAN和VMD算法相比,本文所提ICEEMDAN算法在功率波动突变点处的预测能力与实际值偏差较小。
表5可知,经过数据重构后的EMD和VMD算法较原始算法均方根误差分别下降0.509 3、0.250 7 MW,平均绝对误差分别下降0.301 8、 0.124 9 MW,决定系数分别提升0.050 8、0.029 4。相较于EMD和VMD,CEEMDAN算法可有效降低模态函数数量对模型精度的影响,相较于EMD-SE算法,其均方根误差下降1.205 9 MW,平均绝对误差下降0.834 7 MW,决定系数提升0.109 6,预测精度提升较大。但在处理强波动的风电功率序列数据时,经CEEMDAN-SE分解重构后序列仍存在部分高频噪声无法消除的问题,对预测精度影响较大。而本文提出的ICEEMDAN-SE的分解重构模型,通过自适应噪声机制对上述模型缺陷进行改善,精度得到明显提高,其均方根误差为2.174 6 MW,平均绝对误差为1.324 3 MW,决定系数为0.913 6,相较于EMD和VMD模型精度提高1.5~2.0倍,相较于CEEMDAN模型,均方根误差下降0.482 7 MW,平均绝对误差下降0.512 4 MW。综上,ICEEMDAN-SE数据分解重构模型有效降低了子序列重构误差,并提高了时间序列相关性和耦合性,有效提升了功率预测精度。
为验证本文所提预测模型在提升短期风电功率预测精度的有效性,分别构建主流预测模型LSTM(M1)、BiGRU(M2)、Informer(M3)、ICEEM DAN-SE-Informer(M4)以及本文所提ICEEMDAN-SE-AST-ASBiGRU(M5)进行对比验证,预测结果如图11所示,并通过相关评价指标进行分析,结果见表6
图11可见,由于风电出力具有不确定性,相较于组合模型,单一预测模型难以捕捉非线性动态特征,M1、M2、M3模型在波形突变点处表现较差。M4通过数据处理算法,预测精度有所提升,但在功率波动剧烈处存在较大误差。相较而言,本文通过Transformer与BiGRU模型引入ASSA机制,结合数据处理算法,预测效果得到一定提升,与实际功率曲线拟合程度较好。
表6可以看出,M1模型均方根误差为4.328 MW,平均绝对误差为3.73 MW,决定系数为0.818 9,预测准确度最低。M2在M1的基础上简化模型结构,并引入双向机制,提高对多维时间数据的表征能力,预测效果相对M1,均方根误差降低1.104 MW,平均绝对误差降低0.98 MW,决定系数提升为0.864 2;M3通过注意力机制实现对非线性特征的高效提取,相较于M2,均方根误差降低0.430 MW,平均绝对误差降低0.44 MW,决定系数提升为0.891 2,虽然单一预测模型通过结构优化可在一定程度上提高预测精度,但仍难以满足工程实际的需要。结合ICEEMDAN-SE数据处理算法的M4模型,在一定程度上减弱了数据的波动性和随机性,提升了预测的准确度。M4模型均方根误差值相对于M3下降0.420 MW,平均绝对误差下降0.53 MW,决定系数提高3.9%,但仍存在对数据的长期依赖关系敏感度较低的问题。本文所提ICEEMDAN-SE-AST-ASBiGRU模型,在M4模型的基础上,引入ASSA机制提升模型的特征表征能力,并融合ASBiGRU模型,集成多模型优势区间,降低非线性数据和高频噪声对风电预测精度的影响,同时深度挖掘数据的长期变化趋势及周期性特征,均方根误差下降2.644 MW,平均绝对误差下降2.42 MW,决定系数提高18.2%。实验结果表明,相较主流预测模型,本文所提模型在预测精度及效率方面具有一定的优势。
本文提出了基于ICEEMDAN-SE-AST-ASBiGRU模型的短期风电功率预测方法,通过算例分析,得到如下结论。
1)本文所提ICEEMDAN-SE组合方法实现了风电功率数据的分解与重构,降低了时间序列的复杂度,降低了数据波动性和随机性对预测精度的影响。相较于传统分解方法,其均方根误差和平均绝对误差均降低,决定系数提高。
2)所构建的AST-ASBiGRU组合预测模型能充分发挥AST对中高频分量的处理能力与BiGRU模型低频分量拟合优势,结合ASSA注意力机制的特征提取能力可对风电数据特征进行全面挖掘,提高短期风电功率预测精度,具有良好的工程实际应用能力。
本文对于风电功率的区间预测探索不足,对量化由风电不确定性所引发的结果偏差考虑不足。因此,未来研究中将进一步考虑点预测与区间预测的融合形式,探索不同时间窗口对预测结果的影响。
  • 国家自然科学基金项目(62273215)
参考文献 引证文献
排序方式:
[1]
LI Z, WU L, XU Y, et al. Distributed trilayer risk-averse stochastic game approach for energy trading among multi-energy microgrids[J]. Applied Energy, 2023, 331: 120282.
[2]
朱琼锋, 李家腾, 乔骥, 等. 人工智能技术在新能源功率预测的应用及展望[J]. 中国电机工程学报, 2023, 43(8): 3027-3048.
ZHU Qiongfeng, LI Jiateng, QIAO Ji, et al. Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE, 2023, 43(8): 3027-3047.
[3]
孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143.
SUN Rongfu, ZHANG Tao, HE Qing, et al. Review on key technologies and applications in wind power forecasting[J]. High Voltage Engineering, 2021, 47(4): 1129-1143.
[4]
PARK S W, SON S Y, KIM C, et al. An improved photovoltaic system output prediction model under limited weather information[J]. Journal of Electrical Engineering and Technology, 2018, 13(5): 1874-1885.
[5]
SI Z, YANG M, YU Y, et al. Photovoltaic power forecast based on satellite images considering effects of solar position[J]. Applied Energy, 2021, 302: 117514.
[6]
赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Zeni, YUN Sining, JIA Lingyun, et al. Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta Energiae Solaris Sinica, 2022, 43(11): 224-234.
[7]
李国庆, 刘钊, 金国彬, 等. 基于随机分布式嵌入框架及BP神经网络的超短期电力负荷预测[J]. 电网技术, 2020, 44(2): 437-445.
LI Guoqing, LIU Zhao, JIN Guobin, et al. Ultra short-term power load forecasting based on randomly distributive embedded framework and BP neural network[J]. Power System Technology, 2020, 44(2): 437-445.
[8]
刘兴, 王艳, 纪志成. 基于随机森林的风电功率短期预测方法[J]. 系统仿真学报, 2021, 33(11): 2606-2614.
LIU Xing, WANG Yan, JI Zhicheng. Short-term wind power prediction method based on random forest[J]. Journal of System Simulation, 2021, 33(11): 2606-2614.
[9]
叶家豪, 魏霞, 黄德启, 等. 基于灰色关联分析的BSO-ELM-AdaBoost风电功率短期预测[J]. 太阳能学报, 2022, 43(3): 426-432.
YE Jiahao, WEI Xia, HUANG Deqi, et al. Short-term forecast of wind power based on BSO-ELM-AdaBoost with grey correlation analysis[J]. Acta Energiae Solaris Sinica, 2022, 43(3): 426-432.
[10]
张磊, 李海涛, 熊致知, 等. 基于可解释性XGBoost的电力系统惯量短期预测方法[J]. 电力建设, 2023, 44(8): 22-30.
ZHANG Lei, LI Haitao, XIONG Zhizhi, et al. Short-term prediction method based on interpretable XGBoost for power system inertia[J]. Electric Power Construction, 2023, 44(8): 22-30.
[11]
杨维熙, 刘勇, 舒勤. 基于补充集合经验模态分解的短期负荷预测模型[J]. 电网技术, 2022, 46(9): 3615-3623.
YANG Weixi, LIU Yong, SHU Qin. A short-term load forecasting model based on CEEMD[J]. Power System Technology, 2022, 46(9): 3615-3623.
[12]
杨锡运, 马文兵, 彭琰, 等. 基于组合神经网络的分布式光伏超短期功率预测方法[J]. 热力发电, 2023, 52(8): 162-171.
YANG Xiyun, MA Wenbing, PENG Yan, et al. Distributed photovoltaic ultra-short-term power prediction method based on combined neural network[J]. Thermal Power Generation, 2023, 52(8): 162-171.
[13]
陈庆明, 廖鸿飞, 孙颖楷, 等. 基于GWO-GRU的光伏发电功率预测[J]. 太阳能学报, 2024, 45(7): 438-444.
CHEN Qingming, LIAO Hongfei, SUN Yingkai, et al. Photovoltaic power prediction model based on GWO-GRU[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 438-444.
[14]
王勇权, 高明明, 王唯铧, 等. 基于CNN-GRU-MHA的CFB机组污染物排放动态预测[J]. 热力发电, 2025, 54(7): 33-42.
WANG Yongquan, GAO Mingming, WANG Weihua, et al. Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA[J]. Thermal Power Generation, 2025, 54(7): 33-42.
[15]
WANG S, SHI J, YANG W, et al. High and low frequency wind power prediction based on Transformer and BiGRU-Attention[J]. Energy, 2024, 288: 129753.
[16]
钟吴君, 李培强, 涂春鸣. 基于尾流关联的动态超图风电功率超短期预测方法[J]. 中国电机工程学报, 2025, 45(12): 4693-4707.
ZHONG Wujun, LI Peiqiang, TU Chunming. Dynamic hypergraph wind power ultra short term prediction method based on wake correlation[J]. Proceedings of the CSEE, 2025, 45(12): 4693-4707.
[17]
LI Q, ZHANG X, MA T, et al. A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine[J]. Energy, 2021, 224: 120094.
[18]
王绍敏, 王守相, 赵倩宇, 等. 基于频域分解和精度加权集成的分布式风电功率预测方法[J]. 电力建设, 2023, 44(5): 84-93.
WANG Shaomin, WANG Shouxiang, ZHAO Qianyu, et al. Distributed wind power forecasting method based on frequency domain decomposition and precision-weighted ensemble[J]. Electric Power Construction, 2023, 44(5): 84-93.
[19]
WU Y K, HUANG C L, WU S H, et al. Deterministic and probabilistic wind power forecasts by considering various atmospheric models and feature engineering approaches[J]. IEEE Transactions on Industry Applications, 2022, 59(1): 192-206.
[20]
苏子越, 柴琳, 谢亮, 等. 基于变分模态分解的综合能源系统短期电负荷预测[J]. 热力发电, 2024, 53(12): 21-28.
SU Ziyue, CHAI Lin, XIE Liang, et al. Short-term electrical load forecasting for integrated energy system based on variational mode decomposition[J]. Thermal Power Generation, 2024, 53(12): 21-28.
[21]
ZHANG J, LIU Z, CHEN T. Interval prediction of ultra-short-term photovoltaic power based on a hybrid model[J]. Electric Power Systems Research, 2023, 216: 109035.
[22]
LIANG Y, LIN Y, LU Q. Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM[J]. Expert Systems with Applications, 2022, 206: 117847.
[23]
张学清, 梁军, 张熙, 等. 基于样本熵和极端学习机的超短期风电功率组合预测模型[J]. 中国电机工程学报, 2013, 33(25): 33-40.
ZHANG Xueqing, LIANG Jun, ZHANG Xi, et al. Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J]. Proceedings of the CSEE, 2013, 33(25): 33-40.
[24]
ZHOU S, CHEN D, PAN J, et al. Adapt or perish: adaptive sparse transformer with attentive feature refinement for image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 2952-2963.
[25]
吉兴全, 赵国航, 叶平峰, 等. 基于QMD-HBiGRU的短期光伏功率预测方法[J]. 高电压技术, 2024, 50(9): 3850-3859.
JI Xingquan, ZHAO Guohang, YE Pingfeng, et al. Short-term PV forecasting method based on QMD-HBiGRU model[J]. High Voltage Engineering, 2024, 50(9): 3850-3859.
[26]
王辉, 邹智超, 李欣, 等. 基于VMD-ISSA-GRU组合模型的短期风电功率预测[J]. 热力发电, 2024, 53(5): 122-131.
WANG Hui, ZOU Zhichao, LI Xin, et al. Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model[J]. Thermal Power Generation, 2024, 53(5): 122-131.
[27]
李青, 张新燕, 摆志俊, 等. 基于MQ-WaveNet的风电集群发电功率多步概率预测[J]. 电力系统自动化, 2023, 47(8): 156-168.
LI Qing, ZHANG Xinyan, BAI Zhijun, et al. Multi-step probability prediction of power generation for wind power clusters based on Multi-horizon quantile-WaveNet[J]. Automation of Electric Power Systems, 2023, 47(8): 156-168.
2025年第54卷第10期
PDF下载
89
39
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202412272
  • 接收时间:2024-12-27
  • 首发时间:2026-03-05
  • 出版时间:2025-10-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-12-27
基金
National Natural Science Foundation of China(62273215)
国家自然科学基金项目(62273215)
作者信息
    1.山东科技大学电气与自动化工程学院,山东 青岛 266590
    2.济宁能源集团义桥煤矿,山东 济宁 272500
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202412272
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