Article(id=1215700812555272850, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700809971581533, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202312189, 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=1767775260342, onlineDateStr=2026-01-07, pubDate=1716566400000, pubDateStr=2024-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1767775260342, onlineIssueDateStr=2026-01-07, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1767775260342, creator=13701087609, updateTime=1767775260342, 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=122, endPage=131, ext={EN=ArticleExt(id=1215700812760793753, articleId=1215700812555272850, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model, columnId=1211002409397129992, journalTitle=Thermal Power Generation, columnName=Power generation technology forum, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problem of low accuracy of wind power prediction caused by wind speed uncertainty and volatility, this paper proposes a VMD-ISSA-GRU combination model based on variational mode decomposition (VMD), improved sparrow search algorithm (ISSA) and gated recurrent neural network (GRU). Firstly, the center frequency method is used to determine the number of modal components after VMD decomposition, which can effectively avoid over-decomposition or insufficient decomposition. Then, chaotic mapping, nonlinear decreasing weights and a mutation strategy are introduced to improve the sparrow search algorithm to optimize the gated recurrent neural network, and then an ISSA-GRU prediction model is established for each decomposed subsequence. Finally, the predicted value of each subseries is superimposed and the final predicted value is obtained. The experimental results show that, the mean absolute error, mean absolute percentage error and root mean square error of the VMD-ISSA-GRU model are 1.211 8, 1.890 0 and 1.591 6 MW, respectively. Compared with the conventional GRU, long short-term memory (LSTM) neural network, Bi-directional LSTM (BiLSTM) neural network model and other combination models, the prediction accuracy has been significantly improved, which can solve the problem of low prediction accuracy of wind power.

, 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=Hui WANG, Zhichao ZOU, Xin LI, Zuohui WU, Kerui ZHOU), CN=ArticleExt(id=1215700815147352875, articleId=1215700812555272850, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于VMD-ISSA-GRU组合模型的短期风电功率预测, columnId=1211002409581679375, journalTitle=热力发电, columnName=发电技术论坛, runingTitle=null, highlight=null, articleAbstract=

为解决风速不确定性和波动性造成风电功率预测精度不高的问题,提出一种基于变分模态分解(VMD)、改进麻雀搜索算法(ISSA)和门控循环神经网络(GRU)的VMD-ISSA-GRU组合模型。首先,利用中心频率法确定采用VMD分解后的模态分量个数,这样有效避免了过分解或者分解不充分。其次引入混沌映射、非线性递减权重以及一个突变策略来改进麻雀搜索算法,用于优化门控循环神经网络,然后对分解得到的各个子序列建立ISSA-GRU预测模型,最后叠加每个子序列的预测值得到最终的预测值。将该模型用于实际风电功率预测,实验结果表明:VMD-ISSA-GRU组合模型的平均绝对误差、平均绝对百分比误差、均方根误差分别为1.211 8 MW、1.890 0及1.591 6 MW;相较于传统的GRU、长短时记忆(LSTM)神经网络、BiLSTM(Bi-directional LSTM)神经网络模型以及其他组合模型在预测精度上都有明显的提升,能很好地解决风电功率预测精度不高的问题

, correspAuthors=null, authorNote=null, correspAuthorsNote=
邹智超(2000),男,硕士研究生,主要研究方向为基于深度学习的目标检测、预测,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=/agvh4roXp8kYxdxgpmziw==, magXml=L12aVNStrv8ErF7Hh2ZGKg==, pdfUrl=null, pdf=8scRlKxWKS5m7LD1mfARcg==, pdfFileSize=1713318, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=3P2pWR7SOjYJ4cY9dkBiDQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PsTQZMlHS7+9fNzRyPFk/Q==, mapNumber=null, authorCompany=null, fund=null, authors=

王辉(1969),男,教授,硕士,主要研究方向为新能源微电网运行优化与控制,

, authorsList=王辉, 邹智超, 李欣, 吴作辉, 周珂锐)}, authors=[Author(id=1215700815575171918, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wanghui@ctgu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700815663252308, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700815575171918, language=EN, stringName=Hui WANG, firstName=Hui, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700815742944088, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700815575171918, language=CN, stringName=王辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.三峡大学电气与新能源学院,湖北 宜昌 443002, bio={"content":"

王辉(1969),男,教授,硕士,主要研究方向为新能源微电网运行优化与控制,

"}, bioImg=null, bioContent=

王辉(1969),男,教授,硕士,主要研究方向为新能源微电网运行优化与控制,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700815399011135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=1., ext=[AuthorCompanyExt(id=1215700815403205440, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1215700815407399745, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.三峡大学电气与新能源学院,湖北 宜昌 443002)])]), Author(id=1215700815810052958, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1161754021@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700815881356132, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700815810052958, language=EN, stringName=Zhichao ZOU, firstName=Zhichao, middleName=null, lastName=ZOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700815994602345, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700815810052958, language=CN, stringName=邹智超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.三峡大学电气与新能源学院,湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700815399011135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=1., ext=[AuthorCompanyExt(id=1215700815403205440, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1215700815407399745, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.三峡大学电气与新能源学院,湖北 宜昌 443002)])]), Author(id=1215700816091071346, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, 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=1215700816212706169, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816091071346, language=EN, stringName=Xin LI, firstName=Xin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700816279815038, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816091071346, language=CN, stringName=李欣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700815487091526, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=2., ext=[AuthorCompanyExt(id=1215700815495480135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China), AuthorCompanyExt(id=1215700815503868744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002)])]), Author(id=1215700816372089734, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, 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=1215700816493724557, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816372089734, language=EN, stringName=Zuohui WU, firstName=Zuohui, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700816594387856, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816372089734, language=CN, stringName=吴作辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700815487091526, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=2., ext=[AuthorCompanyExt(id=1215700815495480135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China), AuthorCompanyExt(id=1215700815503868744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002)])]), Author(id=1215700816732799897, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700816846046112, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816732799897, language=EN, stringName=Kerui ZHOU, firstName=Kerui, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700816913154981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, authorId=1215700816732799897, language=CN, stringName=周珂锐, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700815487091526, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=2., ext=[AuthorCompanyExt(id=1215700815495480135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China), AuthorCompanyExt(id=1215700815503868744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002)])])], keywords=[Keyword(id=1215700817034789804, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, orderNo=1, keyword=wind power prediction), Keyword(id=1215700817139647408, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, orderNo=2, keyword=variational mode decomposition), Keyword(id=1215700817240310709, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, orderNo=3, keyword=improved sparrow search algorithm), Keyword(id=1215700817357751228, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, orderNo=4, keyword=gated recurrent neural network), Keyword(id=1215700817450025921, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, orderNo=5, keyword=hyperparameter), Keyword(id=1215700817592632268, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, orderNo=1, keyword=风电功率预测), Keyword(id=1215700817701684176, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, orderNo=2, keyword=变分模态分解), Keyword(id=1215700817840096220, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, orderNo=3, keyword=改进麻雀搜索算法), Keyword(id=1215700817982702560, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, orderNo=4, keyword=门控循环神经网络), Keyword(id=1215700818095948774, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, orderNo=5, keyword=超参数)], refs=[Reference(id=1215700822789374119, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=CAO B, CHANG L C, journalName=Development of short-term wind power forecasting methods, refType=null, unstructuredReference=CAO B, CHANG L C. Development of short-term wind power forecasting methods[M]. 2022 IEEE 7th Southern Power Electronics Conference (SPEC). IEEE, 2022: 1-5., articleTitle=null, refAbstract=null), Reference(id=1215700822881648812, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=147703, pageEnd=147710, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=SUN Y, LI Z Y, YU X N, journalName=IEEE Access, refType=null, unstructuredReference=SUN Y, LI Z Y, YU X N, et al. Research on ultra-short-term wind power prediction considering source relevance[J]. IEEE Access, 2020, 8: 147703-147710., articleTitle=Research on ultra-short-term wind power prediction considering source relevance, refAbstract=null), Reference(id=1215700822982312112, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2018, volume=33, issue=3, pageStart=3276, pageEnd=3284, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=YAN J, ZHANG H, LIU Y Q, journalName=IEEE Transactions on Power Systems, refType=null, unstructuredReference=YAN J, ZHANG H, LIU Y Q, et al. Forecasting the high-penetration of wind power on multiple scales using multi-to-multi mapping[J]. IEEE Transactions on Power Systems, 2018, 33(3): 3276-3284., articleTitle=Forecasting the high-penetration of wind power on multiple scales using multi-to-multi mapping, refAbstract=null), Reference(id=1215700823091364025, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=12, pageStart=213, pageEnd=236, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=唐新姿, 顾能伟, 黄轩晴, journalName=机械工程学报, refType=null, unstructuredReference=唐新姿, 顾能伟, 黄轩晴, 等. 风电功率短期预测技术研究进展[J]. 机械工程学报, 2022, 58(12): 213-236., articleTitle=风电功率短期预测技术研究进展, refAbstract=null), Reference(id=1215700823196221629, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=12, pageStart=213, pageEnd=236, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=TANG Xinzi, GU Nengwei, HUANG Xuanqing, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=TANG Xinzi, GU Nengwei, HUANG Xuanqing, et al. Progress on short term wind power forecasting technology[J]. Journal of Mechanical Engineering, 2022, 58(12): 213-236., articleTitle=Progress on short term wind power forecasting technology, refAbstract=null), Reference(id=1215700823284302021, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=4, pageStart=1047, pageEnd=1060, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=钱政, 裴岩, 曹利宵, journalName=高电压技术, refType=null, unstructuredReference=钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060., articleTitle=风电功率预测方法综述, refAbstract=null), Reference(id=1215700823410131145, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=4, pageStart=1047, pageEnd=1060, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=QIAN Zheng, PEI Yan, CAO Lixiao, journalName=High Voltage Engineering, refType=null, unstructuredReference=QIAN Zheng, PEI Yan, CAO Lixiao, et al. Review of wind power forecasting method[J]. High Voltage Engineering, 2016, 42(4): 1047-1060., articleTitle=Review of wind power forecasting method, refAbstract=null), Reference(id=1215700823519183052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=24, pageStart=178, pageEnd=187, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=韩自奋, 景乾明, 张彦凯, journalName=电力系统保护与控制, refType=null, unstructuredReference=韩自奋, 景乾明, 张彦凯, 等. 风电预测方法与新趋势综述[J]. 电力系统保护与控制, 2019, 47(24): 178-187., articleTitle=风电预测方法与新趋势综述, refAbstract=null), Reference(id=1215700824790057170, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=24, pageStart=178, pageEnd=187, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=HAN Zifen, JING Qianming, ZHANG Yankai, journalName=Power System Protection and Control, refType=null, unstructuredReference=HAN Zifen, JING Qianming, ZHANG Yankai, et al. Review of wind power forecasting methods and new trends[J]. Power System Protection and Control, 2019, 47(24): 178-187., articleTitle=Review of wind power forecasting methods and new trends, refAbstract=null), Reference(id=1215700824890720474, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=10, pageStart=145, pageEnd=148, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=张怡, 杨宇晴, journalName=计算机仿真, refType=null, unstructuredReference=张怡, 杨宇晴. 基于AM-LSTM的风电场内多点位风电功率预测[J]. 计算机仿真, 2021, 38(10): 145-148., articleTitle=基于AM-LSTM的风电场内多点位风电功率预测, refAbstract=null), Reference(id=1215700824982995167, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=10, pageStart=145, pageEnd=148, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=ZHANG Yi, YANG Yuqing, journalName=Computer Simulation, refType=null, unstructuredReference=ZHANG Yi, YANG Yuqing. Multi-point wind power prediction in wind farms based on AM-LSTM[J]. Computer Simulation, 2021, 38(10): 145-148., articleTitle=Multi-point wind power prediction in wind farms based on AM-LSTM, refAbstract=null), Reference(id=1215700825100435683, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=40, issue=6, pageStart=22, pageEnd=25, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=李森文, 张伟, 李纯宇, journalName=机械与电子, refType=null, unstructuredReference=李森文, 张伟, 李纯宇, 等. 基于SSA-LSTM的海上风电功率预测[J]. 机械与电子, 2022, 40(6): 22-25., articleTitle=基于SSA-LSTM的海上风电功率预测, refAbstract=null), Reference(id=1215700825180127465, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=40, issue=6, pageStart=22, pageEnd=25, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=LI Senwen, ZHANG Wei, LI Chunyu, journalName=Machinery & Electronics, refType=null, unstructuredReference=LI Senwen, ZHANG Wei, LI Chunyu, et al. Power prediction of offshore wind farm based on SSA-LSTM[J]. Machinery & Electronics, 2022, 40(6): 22-25., articleTitle=Power prediction of offshore wind farm based on SSA-LSTM, refAbstract=null), Reference(id=1215700825310150894, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=14, pageStart=5629, pageEnd=5635, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=王愈轩, 梁沁雯, 章思远, journalName=科学技术与工程, refType=null, unstructuredReference=王愈轩, 梁沁雯, 章思远, 等. 基于LSTM-XGboost组合的超短期风电功率预测方法[J]. 科学技术与工程, 2022, 22(14): 5629-5635., articleTitle=基于LSTM-XGboost组合的超短期风电功率预测方法, refAbstract=null), Reference(id=1215700825410814192, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=14, pageStart=5629, pageEnd=5635, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=WANG Yuxuan, LIANG Qinwen, ZHANG Siyuan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=WANG Yuxuan, LIANG Qinwen, ZHANG Siyuan, et al. An ultra⁃short⁃term wind power prediction method based on LSTM⁃XGboost combination[J]. Science Technology and Engineering, 2022, 22(14): 5629-5635., articleTitle=An ultra⁃short⁃term wind power prediction method based on LSTM⁃XGboost combination, refAbstract=null), Reference(id=1215700825503088885, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=58, pageEnd=63, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=王斌, 魏成伟, 谢丽蓉, journalName=太阳能学报, refType=null, unstructuredReference=王斌, 魏成伟, 谢丽蓉, 等. 基于风速误差校正和ALO-LSSVM的风电功率预测[J]. 太阳能学报, 2022, 43(1): 58-63., articleTitle=基于风速误差校正和ALO-LSSVM的风电功率预测, refAbstract=null), Reference(id=1215700825607946489, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=58, pageEnd=63, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=WANG Bin, WEI Chengwei, XIE Lirong, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=WANG Bin, WEI Chengwei, XIE Lirong, et al. Wind power forecasting based on wind speed errorcorretion and ALO-LSSVM[J]. Acta Energiae Solaris Sinica, 2022, 43(1): 58-63., articleTitle=Wind power forecasting based on wind speed errorcorretion and ALO-LSSVM, refAbstract=null), Reference(id=1215700825746358527, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=张涛, 朱瑞金, 扎西顿珠, journalName=热力发电, refType=null, unstructuredReference=张涛, 朱瑞金, 扎西顿珠. 基于改进骨干差分进化算法优化LSSVM的短期光伏发电功率预测[J]. 热力发电, 2021, 50(5): 102-107., articleTitle=基于改进骨干差分进化算法优化LSSVM的短期光伏发电功率预测, refAbstract=null), Reference(id=1215700825838633219, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=ZHANG Tao, ZHU Ruijin, ZHAXI Dunzhu, journalName=Thermal Power Generation, refType=null, unstructuredReference=ZHANG Tao, ZHU Ruijin, ZHAXI Dunzhu, et al. Short-term photovoltaic power prediction based on IBBDE-LSSVM[J]. Thermal Power Generation, 2021, 50(5): 102-107., articleTitle=Short-term photovoltaic power prediction based on IBBDE-LSSVM, refAbstract=null), Reference(id=1215700825960268039, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=292, pageEnd=300, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=李宏扬, 高丙朋, journalName=太阳能学报, refType=null, unstructuredReference=李宏扬, 高丙朋. 基于改进VMD和SNS-Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报, 2023, 44(8): 292-300., articleTitle=基于改进VMD和SNS-Attention-GRU的短期光伏发电功率预测, refAbstract=null), Reference(id=1215700826098680076, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=8, pageStart=292, pageEnd=300, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=LI Hongyang, GAO Bingpeng, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=LI Hongyang, GAO Bingpeng. Short-term PV power forecasting based on improved VMD and SNS-Attention-GRU[J]. Acta Energiae Solaris Sinica, 2023, 44(8): 292-300., articleTitle=Short-term PV power forecasting based on improved VMD and SNS-Attention-GRU, refAbstract=null), Reference(id=1215700826224509201, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=DAN F C, HORA C, BENDEA G, journalName=null, refType=null, unstructuredReference=DAN F C, HORA C, BENDEA G. Short-term forecasting of wind power generation[C]. 2021 10th International Conference on Energy and Environment (CIEM). 2021: 1-5., articleTitle=Short-term forecasting of wind power generation, refAbstract=null), Reference(id=1215700826329366805, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=5, pageStart=82, pageEnd=87, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=张振中, 郭傅傲, 刘大明, journalName=计算机应用与软件, refType=null, unstructuredReference=张振中, 郭傅傲, 刘大明, 等. 基于最大互信息系数和小波分解的多模型集成短期负荷预测[J]. 计算机应用与软件, 2021, 38(5): 82-87., articleTitle=基于最大互信息系数和小波分解的多模型集成短期负荷预测, refAbstract=null), Reference(id=1215700826417447193, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=5, pageStart=82, pageEnd=87, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=ZHANG Zhenzhong, GUO Fuao, LIU Daming, journalName=Computer Applications and Software, refType=null, unstructuredReference=ZHANG Zhenzhong, GUO Fuao, LIU Daming, et al. Multi-model intergrated short-term load prediction based on maximum mutual information coefficientand wavelet decomposition[J]. Computer Applications and Software, 2021, 38(5): 82-87., articleTitle=Multi-model intergrated short-term load prediction based on maximum mutual information coefficientand wavelet decomposition, refAbstract=null), Reference(id=1215700826513916187, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=余周, 姜涛, 范鹏辉, journalName=长江科学院院报, refType=null, unstructuredReference=余周, 姜涛, 范鹏辉, 等. 基于EMD-DELM-LSTM组合模型的湖泊水位多时间尺度预测[J/OL]. 长江科学院院报:1-9 [2024-03-01]. http://kns.cnki.net/kcms/detail/42.1171.TV.20230413.1830.002.html., articleTitle=基于EMD-DELM-LSTM组合模型的湖泊水位多时间尺度预测, refAbstract=null), Reference(id=1215700826673299744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=YU Zhou, JIANG Tao, FAN Penghui, journalName=Journal of Changjiang River Scientific Research Institute, refType=null, unstructuredReference=YU Zhou, JIANG Tao, FAN Penghui, et al. Multi-time scale prediction for lake level based on EMD-DELM-LSTM combined model[J/OL]. Journal of Changjiang River Scientific Research Institute: 1-9 [2024-03-01]. http://kns.cnki.net/kcms/detail/42.1171.TV.20230413.1830.002.html., articleTitle=Multi-time scale prediction for lake level based on EMD-DELM-LSTM combined model, refAbstract=null), Reference(id=1215700826778157349, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=92, pageEnd=98, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=侯金霄, 黄林显, 胡晓农, journalName=水资源与水工程学报, refType=null, unstructuredReference=侯金霄, 黄林显, 胡晓农, 等. 基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用[J]. 水资源与水工程学报, 2023, 34(4): 92-98., articleTitle=基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用, refAbstract=null), Reference(id=1215700826899792173, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=92, pageEnd=98, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=HOU Jinxiao, HUANG Linxian, HU Xiaonong, journalName=Journal of Water Resources and Water Engineering, refType=null, unstructuredReference=HOU Jinxiao, HUANG Linxian, HU Xiaonong, et al. Application of EMD-LSTM coupled model to karst groundwater level prediction in Baotu Spring[J]. Journal of Water Resources and Water Engineering, 2023, 34(4): 92-98., articleTitle=Application of EMD-LSTM coupled model to karst groundwater level prediction in Baotu Spring, refAbstract=null), Reference(id=1215700827013038385, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=张雲钦, 程起泽, 蒋文杰, journalName=太阳能学报, refType=null, unstructuredReference=张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69., articleTitle=基于EMD-PCA-LSTM的光伏功率预测模型, refAbstract=null), Reference(id=1215700827088535861, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=ZHANG Yunqin, CHENG Qize, JIANG Wenjie, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=ZHANG Yunqin, CHENG Qize, JIANG Wenjie, et al. Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta Energiae Solaris Sinica, 2021, 42(9): 62-69., articleTitle=Photovoltaic power prediction model based on EMD-PCA-LSTM, refAbstract=null), Reference(id=1215700827176616254, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=18, issue=10, pageStart=7019, pageEnd=7029, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=TATINATI S, WANG Y, KHONG A W H, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=TATINATI S, WANG Y, KHONG A W H. Hybrid method based on random convolution nodes for short-term wind speed forecasting[J]. IEEE Transactions on Industrial Informatics, 2022, 18(10): 7019-7029., articleTitle=Hybrid method based on random convolution nodes for short-term wind speed forecasting, refAbstract=null), Reference(id=1215700827277279552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=10, issue=21, pageStart=18754, pageEnd=18765, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=WANG Z, WANG L, REVANESH M, journalName=IEEE Internet of Things Journal, refType=null, unstructuredReference=WANG Z, WANG L, REVANESH M, et al. Short-term wind speed and power forecasting for smart city power grid with a hybrid machine learning framework[J]. IEEE Internet of Things Journal, 2023, 10(21): 18754-18765., articleTitle=Short-term wind speed and power forecasting for smart city power grid with a hybrid machine learning framework, refAbstract=null), Reference(id=1215700827369554244, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=3, pageStart=204, pageEnd=211, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=王维高, 魏云冰, 滕旭东, journalName=太阳能学报, refType=null, unstructuredReference=王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211., articleTitle=基于VMD-SSA-LSSVM的短期风电预测, refAbstract=null), Reference(id=1215700827482800458, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=3, pageStart=204, pageEnd=211, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=WANG Weigao, WEI Yunbing, TENG Xudong, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=WANG Weigao, WEI Yunbing, TENG Xudong. Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta Energiae Solaris Sinica, 2023, 44(3): 204-211., articleTitle=Short-term wind power forecasting based on VMD-SSA-LSSVM, refAbstract=null), Reference(id=1215700827562492239, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2014, volume=62, issue=3, pageStart=531, pageEnd=544, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=DRAGOMIRETSKIY K, ZOSSO D, journalName=IEEE Transactions on Signal Processing, refType=null, unstructuredReference=DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544., articleTitle=Variational mode decomposition, refAbstract=null), Reference(id=1215700827650572628, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[22], rfOrder=35, authorNames=薛建凯, journalName=上海: 东华大学, refType=null, unstructuredReference=薛建凯. 一种新型的群智能优化技术的研究与应用 [J]. 上海: 东华大学, 2020: 1-10., articleTitle=一种新型的群智能优化技术的研究与应用, refAbstract=null), Reference(id=1215700827730264408, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=XUE Jiankai, journalName=Shanghai: Dong Hua University, refType=null, unstructuredReference=XUE Jiankai. Research and application of a novel swarm intelligence optimization technique: sparrow search algorithm[J]. Shanghai: Dong Hua University, 2020: 1-10., articleTitle=Research and application of a novel swarm intelligence optimization technique: sparrow search algorithm, refAbstract=null), Reference(id=1215700827868676446, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=537, pageEnd=543, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=SONG W, LIU S, WANG X C, journalName=null, refType=null, unstructuredReference=SONG W, LIU S, WANG X C, et al. An improved sparrow search algorithm[C]. 2020 IEEE Intl Conf on Parallel & Distributed Processing with Applica & Communications, Social Computing & Networking (ISPA/BDCloud/Social Com/SustainCom). 2020: 537-543., articleTitle=An improved sparrow search algorithm, refAbstract=null), Reference(id=1215700827952562532, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=159218, pageEnd=159261, url=null, language=null, rfNumber=[24], rfOrder=38, authorNames=MA B, LU P M, ZHANG L F, journalName=IEEE Access, refType=null, unstructuredReference=MA B, LU P M, ZHANG L F, et al. Enhanced sparrow search algorithm with mutation strategy for global optimization[J]. IEEE Access, 2021, 9: 159218-159261., articleTitle=Enhanced sparrow search algorithm with mutation strategy for global optimization, refAbstract=null), Reference(id=1215700829353460073, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=462, pageEnd=476, url=null, language=null, rfNumber=[25], rfOrder=39, authorNames=GU Y, WANG F D, LI M K, journalName=null, refType=null, unstructuredReference=GU Y, WANG F D, LI M K, et al. A digital load forecasting method based on digital twin and improved GRU[C]. 2022 Asian Conference on Frontiers of Power and Energy (ACFPE). 2022: 462-476., articleTitle=A digital load forecasting method based on digital twin and improved GRU, refAbstract=null), Reference(id=1215700829466706286, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=1724, pageEnd=1734, url=null, language=null, rfNumber=[26], rfOrder=40, authorNames=CHO K, VAN M B, GULCEHRE C, journalName=null, refType=null, unstructuredReference=CHO K, VAN M B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014: 1724-1734., articleTitle=Learning phrase representations using RNN encoder-decoder for statistical machine translation, refAbstract=null), Reference(id=1215700829575758191, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=967, pageEnd=972, url=null, language=null, rfNumber=[27], rfOrder=41, authorNames=GAO L, ZHAO L J, KONG F, journalName=null, refType=null, unstructuredReference=GAO L, ZHAO L J, KONG F, et al. Research method of ultra-short-term wind power prediction based on PSO-GRU prediction[C]. 2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC). 2022: 967-972., articleTitle=Research method of ultra-short-term wind power prediction based on PSO-GRU prediction, refAbstract=null), Reference(id=1215700829697393011, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=264, pageEnd=279, url=null, language=null, rfNumber=[28], rfOrder=42, authorNames=ZHANG H R, ZHANG Y Y, XU Z W, journalName=Thermal load forecasting of an ultra-short-term integrated energy system based on VMD-CNN-LSTM, refType=null, unstructuredReference=ZHANG H R, ZHANG Y Y, XU Z W. Thermal load forecasting of an ultra-short-term integrated energy system based on VMD-CNN-LSTM[M]. 2022 International Conference on Big Data, Information and Computer Network (BDICN). 2022: 264-279., articleTitle=null, refAbstract=null)], funds=[Fund(id=1215700822567075998, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, awardId=52107107, language=EN, fundingSource=National Natural Science Foundation of China(52107107), fundOrder=null, country=null), Fund(id=1215700822671933601, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, awardId=52107107, language=CN, fundingSource=国家自然科学基金项目(52107107), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1215700815399011135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=1., ext=[AuthorCompanyExt(id=1215700815403205440, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1215700815407399745, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815399011135, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.三峡大学电气与新能源学院,湖北 宜昌 443002)]), AuthorCompany(id=1215700815487091526, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, xref=2., ext=[AuthorCompanyExt(id=1215700815495480135, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China), AuthorCompanyExt(id=1215700815503868744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, companyId=1215700815487091526, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002)])], figs=[ArticleFig(id=1215700818217583598, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.1, caption=Flowchart of the ISSA, figureFileSmall=x2rJlMiziLTfpPTDKMdB1A==, figureFileBig=3P2pWR7SOjYJ4cY9dkBiDQ==, tableContent=null), ArticleFig(id=1215700818335024115, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图1, caption=改进麻雀搜索算法流程, figureFileSmall=x2rJlMiziLTfpPTDKMdB1A==, figureFileBig=3P2pWR7SOjYJ4cY9dkBiDQ==, tableContent=null), ArticleFig(id=1215700818540545024, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.2, caption=Structure of the GRU unit, figureFileSmall=Km8ZYHaIyB6Ti51UKX13Lg==, figureFileBig=8W1pNTAmdQWSpRPg+iDE7g==, tableContent=null), ArticleFig(id=1215700818616041477, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图2, caption=GRU单元结构, figureFileSmall=Km8ZYHaIyB6Ti51UKX13Lg==, figureFileBig=8W1pNTAmdQWSpRPg+iDE7g==, tableContent=null), ArticleFig(id=1215700818704121866, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.3, caption=Flowchart of the ISSA-GRU, figureFileSmall=W2CS+NjFBhE7JIYzoaixHg==, figureFileBig=BBGB4yB/8lf1Hou5BQoWmw==, tableContent=null), ArticleFig(id=1215700818788007953, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图3, caption=ISSA-GRU流程, figureFileSmall=W2CS+NjFBhE7JIYzoaixHg==, figureFileBig=BBGB4yB/8lf1Hou5BQoWmw==, tableContent=null), ArticleFig(id=1215700818897059863, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.4, caption=Flowchart of the VMD-ISSA-GRU, figureFileSmall=QZSFxs+sUpE5yEQt8zw/jw==, figureFileBig=eKedzmrvpN/lwx7e9/zvmg==, tableContent=null), ArticleFig(id=1215700818985140256, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图4, caption=VMD-ISSA-GRU流程, figureFileSmall=QZSFxs+sUpE5yEQt8zw/jw==, figureFileBig=eKedzmrvpN/lwx7e9/zvmg==, tableContent=null), ArticleFig(id=1215700819064832040, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.5, caption=The original wind power curve, figureFileSmall=Ui6pDLMka3oqZB49625Gbg==, figureFileBig=NlWUq5j8+rFNu+QgnFB+sQ==, tableContent=null), ArticleFig(id=1215700820327317550, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图5, caption=原始风电功率曲线, figureFileSmall=Ui6pDLMka3oqZB49625Gbg==, figureFileBig=NlWUq5j8+rFNu+QgnFB+sQ==, tableContent=null), ArticleFig(id=1215700820465729591, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.6, caption=Decomposition of raw data using VMD, figureFileSmall=QeKgd5fGV2y9QS78tgjwiw==, figureFileBig=xXk+tIcJBhSndVRioVgDdA==, tableContent=null), ArticleFig(id=1215700820553809981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图6, caption=VMD分解原始数据, figureFileSmall=QeKgd5fGV2y9QS78tgjwiw==, figureFileBig=xXk+tIcJBhSndVRioVgDdA==, tableContent=null), ArticleFig(id=1215700820629307458, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.7, caption=Change of prediction errors of the GRU model with time step, figureFileSmall=SoIWLWc6cp0qP7hve344wg==, figureFileBig=OmGSf1VmvB3xHtVm0p0RSA==, tableContent=null), ArticleFig(id=1215700820734165060, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图7, caption=GRU模型预测误差随时间步长的变化, figureFileSmall=SoIWLWc6cp0qP7hve344wg==, figureFileBig=OmGSf1VmvB3xHtVm0p0RSA==, tableContent=null), ArticleFig(id=1215700820813856841, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.8, caption=The single time series input step size and the output result, figureFileSmall=bV8UIpe1Mr5JkWrkceNGfw==, figureFileBig=pC9tDS5Hi5jpvEABJDKxfg==, tableContent=null), ArticleFig(id=1215700820922908753, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图8, caption=单时间序列输入步长与输出结果, figureFileSmall=bV8UIpe1Mr5JkWrkceNGfw==, figureFileBig=pC9tDS5Hi5jpvEABJDKxfg==, tableContent=null), ArticleFig(id=1215700821065515094, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.9, caption=Prediction results of various optimal models and GRU model, figureFileSmall=TeYS+Mf/REKWRYEeeIQ5ng==, figureFileBig=S2Vc186l3mvRKEe7osEByw==, tableContent=null), ArticleFig(id=1215700821174567004, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图9, caption=各个最优模型与GRU模型预测结果, figureFileSmall=TeYS+Mf/REKWRYEeeIQ5ng==, figureFileBig=S2Vc186l3mvRKEe7osEByw==, tableContent=null), ArticleFig(id=1215700821275230305, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Fig.10, caption=Prediction results of each model on the AM dataset, figureFileSmall=UfefrlG7t/QUV7oe9fvirA==, figureFileBig=ovix4bFdk6j7k/77VQ1cyQ==, tableContent=null), ArticleFig(id=1215700821392670824, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=图10, caption=AM数据集上各模型的预测结果, figureFileSmall=UfefrlG7t/QUV7oe9fvirA==, figureFileBig=ovix4bFdk6j7k/77VQ1cyQ==, tableContent=null), ArticleFig(id=1215700821476556909, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Tab.1, caption=

Center frequency of different K values

, figureFileSmall=null, figureFileBig=null, tableContent=
KIMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8
20.000 30.015 0
30.000 20.011 10.034 8
40.000 10.009 40.021 60.047 6
50.000 10.009 20.020 50.042 00.163 3
60.000 10.008 90.019 30.033 90.060 70.233 1
70.000 10.008 80.019 10.033 30.056 10.160 90.302 0
80.000 10.008 70.018 80.032 10.049 90.091 70.169 00.307 6
), ArticleFig(id=1215700821648523381, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=表1, caption=

不同K值下中心频率

, figureFileSmall=null, figureFileBig=null, tableContent=
KIMF1IMF2IMF3IMF4IMF5IMF6IMF7IMF8
20.000 30.015 0
30.000 20.011 10.034 8
40.000 10.009 40.021 60.047 6
50.000 10.009 20.020 50.042 00.163 3
60.000 10.008 90.019 30.033 90.060 70.233 1
70.000 10.008 80.019 10.033 30.056 10.160 90.302 0
80.000 10.008 70.018 80.032 10.049 90.091 70.169 00.307 6
), ArticleFig(id=1215700821770158198, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Tab.2, caption=

Error comparison before and after VMD decomposition

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δMAE/MWδMAPE/%δRMSE/MW
GRU3.031 34.660 13.743 8
VMD-GRU2.976 94.362 03.590 9
LSTM3.335 85.191 44.060 1
VMD-LSTM3.151 84.619 53.812 0
BiLSTM3.052 54.672 23.800 5
VMD-BiLSTM2.580 03.765 63.096 0
), ArticleFig(id=1215700821900181629, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=表2, caption=

VMD分解前后误差比较

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δMAE/MWδMAPE/%δRMSE/MW
GRU3.031 34.660 13.743 8
VMD-GRU2.976 94.362 03.590 9
LSTM3.335 85.191 44.060 1
VMD-LSTM3.151 84.619 53.812 0
BiLSTM3.052 54.672 23.800 5
VMD-BiLSTM2.580 03.765 63.096 0
), ArticleFig(id=1215700822021816455, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Tab.3, caption=

Error indicators for each combined model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型GRULSTMBiLSTM
δMAEδMAPE/%δRMSEδMAEδMAPE/%δRMSEδMAEδMAPE/%δRMSE
单一3.031 34.660 13.743 83.335 85.191 44.060 13.052 54.672 23.800 5
VMD2.976 94.362 03.590 93.151 84.619 53.812 02.580 03.765 63.096 0
VMD-GWO1.473 92.140 01.907 82.697 83.860 03.362 01.978 22.880 02.471 2
VMD-PSO1.353 92.020 01.766 81.801 92.570 02.298 21.556 92.280 01.998 7
VMD-AVOA1.563 92.430 01.957 51.768 62.550 02.263 51.584 52.440 02.008 5
VMD-ISSA1.211 81.890 01.591 61.985 32.780 02.526 81.355 81.950 01.797 6
), ArticleFig(id=1215700822143451275, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=表3, caption=

各组合模型误差指标

, figureFileSmall=null, figureFileBig=null, tableContent=
模型GRULSTMBiLSTM
δMAEδMAPE/%δRMSEδMAEδMAPE/%δRMSEδMAEδMAPE/%δRMSE
单一3.031 34.660 13.743 83.335 85.191 44.060 13.052 54.672 23.800 5
VMD2.976 94.362 03.590 93.151 84.619 53.812 02.580 03.765 63.096 0
VMD-GWO1.473 92.140 01.907 82.697 83.860 03.362 01.978 22.880 02.471 2
VMD-PSO1.353 92.020 01.766 81.801 92.570 02.298 21.556 92.280 01.998 7
VMD-AVOA1.563 92.430 01.957 51.768 62.550 02.263 51.584 52.440 02.008 5
VMD-ISSA1.211 81.890 01.591 61.985 32.780 02.526 81.355 81.950 01.797 6
), ArticleFig(id=1215700822294446224, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=EN, label=Tab.4, caption=

Errors of each model on the AM dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δMAE/MWδMAPE/%δRMSE/MW
GRU2.403 35.828 03.040 7
VMD-GRU1.799 34.020 72.391 3
ISSA-GRU1.793 84.575 02.427 9
VMD-AVOA-LSTM1.280 13.237 51.520 5
VMD-ISSA-BiLSTM0.895 12.378 01.072 7
VMD-ISSA-GRU0.765 12.014 80.946 3
), ArticleFig(id=1215700822437052569, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700812555272850, language=CN, label=表4, caption=

各模型在AM数据集上的误差

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δMAE/MWδMAPE/%δRMSE/MW
GRU2.403 35.828 03.040 7
VMD-GRU1.799 34.020 72.391 3
ISSA-GRU1.793 84.575 02.427 9
VMD-AVOA-LSTM1.280 13.237 51.520 5
VMD-ISSA-BiLSTM0.895 12.378 01.072 7
VMD-ISSA-GRU0.765 12.014 80.946 3
)], 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.202312189, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202312189, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202312189, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202312189, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于VMD-ISSA-GRU组合模型的短期风电功率预测
收藏切换
PDF下载
王辉 1 , 邹智超 1 , 李欣 2 , 吴作辉 2 , 周珂锐 2
热力发电 | 发电技术论坛 2024,53(5): 122-131
收起
收藏切换
热力发电 | 发电技术论坛 2024, 53(5): 122-131
基于VMD-ISSA-GRU组合模型的短期风电功率预测
全屏
王辉1 , 邹智超1 , 李欣2, 吴作辉2, 周珂锐2
作者信息
  • 1.三峡大学电气与新能源学院,湖北 宜昌 443002
  • 2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002
  • 王辉(1969),男,教授,硕士,主要研究方向为新能源微电网运行优化与控制,

通讯作者:

邹智超(2000),男,硕士研究生,主要研究方向为基于深度学习的目标检测、预测,
Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model
Hui WANG1 , Zhichao ZOU1 , Xin LI2, Zuohui WU2, Kerui ZHOU2
Affiliations
  • 1.School of Electrical Engineering and New Energy, Three Gorges University, Yichang 443002, China
  • 2.Hubei Engineering Research Center of Smart Energy Technology (Three Gorges University), Yichang 443002, China
出版时间: 2024-05-25 doi: 10.19666/j.rlfd.202312189
文章导航
收藏切换

为解决风速不确定性和波动性造成风电功率预测精度不高的问题,提出一种基于变分模态分解(VMD)、改进麻雀搜索算法(ISSA)和门控循环神经网络(GRU)的VMD-ISSA-GRU组合模型。首先,利用中心频率法确定采用VMD分解后的模态分量个数,这样有效避免了过分解或者分解不充分。其次引入混沌映射、非线性递减权重以及一个突变策略来改进麻雀搜索算法,用于优化门控循环神经网络,然后对分解得到的各个子序列建立ISSA-GRU预测模型,最后叠加每个子序列的预测值得到最终的预测值。将该模型用于实际风电功率预测,实验结果表明:VMD-ISSA-GRU组合模型的平均绝对误差、平均绝对百分比误差、均方根误差分别为1.211 8 MW、1.890 0及1.591 6 MW;相较于传统的GRU、长短时记忆(LSTM)神经网络、BiLSTM(Bi-directional LSTM)神经网络模型以及其他组合模型在预测精度上都有明显的提升,能很好地解决风电功率预测精度不高的问题

风电功率预测  /  变分模态分解  /  改进麻雀搜索算法  /  门控循环神经网络  /  超参数

In order to solve the problem of low accuracy of wind power prediction caused by wind speed uncertainty and volatility, this paper proposes a VMD-ISSA-GRU combination model based on variational mode decomposition (VMD), improved sparrow search algorithm (ISSA) and gated recurrent neural network (GRU). Firstly, the center frequency method is used to determine the number of modal components after VMD decomposition, which can effectively avoid over-decomposition or insufficient decomposition. Then, chaotic mapping, nonlinear decreasing weights and a mutation strategy are introduced to improve the sparrow search algorithm to optimize the gated recurrent neural network, and then an ISSA-GRU prediction model is established for each decomposed subsequence. Finally, the predicted value of each subseries is superimposed and the final predicted value is obtained. The experimental results show that, the mean absolute error, mean absolute percentage error and root mean square error of the VMD-ISSA-GRU model are 1.211 8, 1.890 0 and 1.591 6 MW, respectively. Compared with the conventional GRU, long short-term memory (LSTM) neural network, Bi-directional LSTM (BiLSTM) neural network model and other combination models, the prediction accuracy has been significantly improved, which can solve the problem of low prediction accuracy of wind power.

wind power prediction  /  variational mode decomposition  /  improved sparrow search algorithm  /  gated recurrent neural network  /  hyperparameter
王辉, 邹智超, 李欣, 吴作辉, 周珂锐. 基于VMD-ISSA-GRU组合模型的短期风电功率预测. 热力发电, 2024 , 53 (5) : 122 -131 . DOI: 10.19666/j.rlfd.202312189
Hui WANG, Zhichao ZOU, Xin LI, Zuohui WU, Kerui ZHOU. Short-term wind power prediction based on VMD-ISSA-GRU comprehensive model[J]. Thermal Power Generation, 2024 , 53 (5) : 122 -131 . DOI: 10.19666/j.rlfd.202312189
随着全球对环境保护意识的提高,风电作为一种清洁能源得到广泛的应用[1]。然而,由于风资源的不稳定性,风力发电量也有一定的不确定性,这也给风电并网以及电力调度与消纳带来挑战[2]。在这种情况下,风电功率预测技术可以帮助平衡系统电力供应和负荷需求之间的关系,从而保障系统安全稳定运行。因此,风电功率的准确预测具有重要实用价值[3]
当今,由于不同的数据来源,风电功率的预测方法可分为物理学方法和统计学习方法2种[4]。统计学习方法就是利用某个风电场的历史风电功率数据及其周边风电场数据构建一个统计学习模型。另外,在短期风电功率预测中,数据挖掘技术逐渐用于提高预测的精度[5]。不过,每个模型都各有优劣,需要合理地组合各个模型,充分发挥各个模型的优势,因此如何组合各个模型以达到更高的预测精度也成为当今的研究热点之一[6]。文献[7-8]分别引入注意力机制(attention mechanism,AM)和麻雀搜索算法(sparrow search algorithm,SSA)对长短时记忆(long short-term memory,LSTM)神经网络模型进行优化,结果表明引入AM和SSA确实可以提高模型性能以及预测精度,但是也可能会出现梯度消失或梯度爆炸等问题,且传统的优化算法可能存在种群初始化质量不高、位置更新不佳等问题,因此需要使用一些数据处理方法或其他特殊的LSTM神经网络结构模型,并使用一些策略来改进优化。文献[9]利用误差倒数法对LSTM神经网络和XGboost(extreme gradient boosting)的预测数据进行加权构建组合预测模型,该组合模型在预测精度上确实有提升,但是并没有很好地解决模型参数设置的问题。文献[10]建立了基于风速误差校正和ALO(ant lion optimizer)-LSSVM(least squares support vector machines)组合模型,很好地预测了风电场多点位的风电功率。文献[11]利用基于广义反向初始化种群和自适应调整交叉概率的骨干差分进化算法去优化LSSVM,也能提高模型的预测精度。上述2篇文献都利用了优化算法,很好地解决了最小二乘支持向量机(LSSVM)在参数选择上存在困难的问题。基于此,本文通过混沌映射初始化种群,并引入非线性递减权重和一个突变策略来更好地更新种群中各角色的位置来改进传统SSA,使改进麻雀搜索算法(ISSA)能更好解决门控循环神经网络(GRU)参数选择困难的问题,同时GRU也能有效避免出现梯度爆炸或梯度消失等问题[12]
同时,风速具有不确定性和波动性,直接对原始数据进行训练和预测会存在难以获取数据特征、预测精度不高等问题[13]。因此,很多用于预测的组合模型都会使用一些数据分解技术来处理原始数据,如小波分解[14]、变分模态分解以及经验模态分解(empirical mode decomposition,EMD)等技术。文献[15-17]在组合模型中引入EMD,有效降低了数据的波动性以及不平稳性,提高了预测精度,文献[18]提出一种EMD-KM-SXL以及一种基于风速预测和风电功率曲线(WPC)建模的两阶段短期风电功率模型,能很好结合环境因素预测最终的风电功率,但EMD往往存在计算复杂等问题,且常常会受到模态混叠的限制。文献[19]提出EVMD-fRCN(elastic VMD-forecasting random convolution nodes)模型,通过EVMD算法将时间序列分解成多个独立的分量,并用fRCN对于每个独立的分量进行预测,最后进行叠加。基于上述文献,本文引入VMD来解决模态混叠以及计算复杂的问题,同时VMD也能很好地处理非平稳信号和噪声,这也有利于提高预测精度[20]
综上,本文首先利用VMD将原始数据分解为多个子序列,同时使用混沌映射、非线性递减权重以及一个突变策略来改进传统SSA,并用ISSA来优化GRU的各个参数,得到VMD-ISSA-GRU组合模型,最后将VMD分解得到的各个子序列预测值进行叠加,以此获得最终的预测结果。由实验结果可知,本文所提出的VMD-ISSA-GRU组合模型在风电功率预测精度方面相较于单一模型以及其他组合模型都有明显提升。
VMD是由Dragomiretskiy等人于2014年提出的一种信号分解方法[21]。它可以将一个复杂的信号分解成多个具有不同中心频率和有限带宽的本征模态函数(intrinsic mode functions,IMF)。VMD基于变分贝叶斯理论构造一个变分问题,并且利用交替方向乘子法(alternating direction method of multipliers,ADMM)来求解。VMD的优势在于能指定模态数,避免了模态混叠和端点效应,同时保证分解结果在频域上的稀疏性。VMD的主要参数有K值,惩罚系数α和收敛容差tol,它们对分解结果有重要的影响。首先构造变分问题,步骤如下:
1)构造变分问题
经过VMD分解得到K个子序列,这K个子序列都是具有中心频率和有限带宽的分量,同时,要求分解得到的各个模态的带宽之和最小,其约束条件表达式为:
min{uk},{ωk}{kt[(δ(t)+jπt)uk(t)]ejωkt22}
s.t.k=1Kuk=f(t)
式中:{μk}为K个模态分量;{wk}为中心频率;∂t为梯度运算;δ(t)为狄拉克函数;*为卷积运算;f(t)为原始信号。
2)约束问题转为非约束问题求解
求解式(1),可以使上述约束变分问题转换为非约束问题,更方便求解,其表达式为:
L({uk},{wk},λ)=αkαi[(δ(t)+jπi)uk(t)]ejwkt22+f(t)kuk(t)22+λ(t),f(t)kuk(t)
式中:α为二次惩罚参数;λ为拉格朗日乘法算子。
3)求解中心频率以及各个模态分量
使用ADMM结合Parseval/Plancherel、傅里叶等距变换,可以得到分解后各个子序列的中心频率和模态分量,同时寻找Lagrange函数的鞍点,交替巡游迭代后的ukwkλ的表达式为:
u^kn+1(ω)=f^(ω)ikˉu^i(ω)+λ^(ω)/21+2α(ωωk)2
ωkn+1=0w|u^kn+1(ω)|2dω0|u^kn+1(ω)|2dω
λ^n+1(ω)=λ^n(ω)+γ(f(ω)ku^kn+1(ω))
式中:γ为噪声容忍度;u^kn+1(ω)u^i(ω)f^(ω)以及λ^(ω)分别为ukn+1(t)ui(t)、f(t)和λ(t)的傅里叶变换。
2020年,薛建凯等提出了一种新型智能优化算法——麻雀搜索算法[22],该算法根据麻雀的觅食以及反捕食行为提出,具有优化效率高以及收敛速度快的特点,但也存在初始化种群质量不高、位置更新不佳等问题。因此本文通过使用混沌映射来初始化种群[23],并使用非线性递减权重以及一个突变策略改进原有算法对传统麻雀算法中的发现者以及加入者位置更新,使其能达到更优的效果,ISSA流程如图1所示。
其优化步骤如下:
1)基于混沌映射的种群初始化
首先,生成虚拟麻雀种群来模拟麻雀进行食物搜索,利用混沌映射产生的种群具有随机性、遍历性以及规律性,能提高种群质量,其表达式为:
xk+1{xk/φ0xkφ (1xk)/(1φ)φxk1
式中:xk为第k只麻雀在空间中的位置;φ为一个随机数,且φ∈(0,1)。
2)定义麻雀的适应度值
在ISSA中,发现者的适应度高时,更容易获取食物,并可以为加入者提供觅食方向,所有麻雀的适应度值可以表示为:
FX=[f([x1,1x1,2...x1,d])f([x2,1x2,2...x2,d])f([xn,1xn,2...xn,d])]
式中:f为适应度值。
3)基于非线性递减权重更新发现者位置
传统的SSA在选代过程中执行全局探索来更新发现者的位置,但位置更新的权重相对较大,并且其位置更新的变化较小,有很大概率会找不到全局的最优解。因此,引入一个非线性递减权重用于周围不存在捕食者时更新发现者的位置,以提高优化迭代过程中发现者的搜索能力,更好找到全局最优解。发现者位置更新变化的计算公式为:
Xi,jt+1={ω*Xi,jtexp(iα itermax)  R2STXi,jt+QL  R2ST
ω=(itermaxt+1itermax)t
式中:t为当前迭代次数;Xi,jt为迭代t时第j维的第i个麻雀;ω为线性递减权重;itermax为常数,表示最大迭代次数;α为(0,1]之间的随机数;Q为一个服从正态分布的随机数;L为1×d的单位列向量。
4)加入者的位置更新
传统的SSA会根据当前位置与当前全局最差位置的差值更新当前位置。虽然这种方式可以防止饥饿的加入者去不好的地方觅食,但不能保证更新的位置有丰富的食物。本文ISSA中,引入一个额外的方程,采用突变策略更新加入者的位置[24],计算公式为:
xi,jt+1=xi,jt+λ*(xi,jbestxi,jt)
式中:xi,jbest为全局最佳位置;λ为一个随机数,且λ∈[0,1]。式可以引导饥饿的加入者向全局最佳位置移动。基于当前全局最坏位置的位置更新方程不被替换,而是与式相结合能更好避免陷入局部最优。
另外,当加入者能量储备充足时,它们跟随发现者觅食,一旦观察到发现者找到好的食物,它们就会争夺食物,但SSA的局部搜索能力不强,易丢失最优解。混沌扰动具有更好的深度搜索能力,能避免搜索陷入局部最优。因此,SSA结合混沌扰动可以提高加入者对最佳觅食区域的探索能力。
XT={2xt0xt0.52(1xt)0.5xt1
Xjchaos=pxj+XT*(xjbestpxj)
Xjchaos_New=ηpxj+(1η)Xjchaos
改进后加入者位置更新计算公式为:
xi,jt+1={min(Qexp(xwrosttxi,jti2),xi,jt+λ(xi,jbestxi,jt))i>n2min(xpt+1+|xi,jn+1xpt+1|*A+*L,ηpxj+(1η)Xjchaos)
利用混沌扰动增强局部搜索的步骤如下:
步骤1 通过式(12)产生一个混沌变量XT,其中XT为一个均匀分布在区间[0,1]随机数。
步骤2 根据式(13),XT被用来产生一个混沌扰动变量Xjchaos,其中pxj为当前执行的混沌搜索操作的第j维值;xjbest为全局最优位置的第j维值。
步骤3 式(14)给出了混沌扰动的运行过程,其中xjchaos_new为在一个混沌扰动后的新结果第j维度值;η为一个均匀分布在区间[0,1]的随机数。
步骤4 最后,根据式(15)更新加入者位置。
5)更新侦察者的位置
在仿真中,假设其中15%左右的麻雀能够意识到危险,将这些麻雀作为侦察者。侦察者的初始位置是随机产生的,其表达式为:
Xi,j(t+1)={Xbest (t)+β|Xi,j(t)Xbest (t)|,fi>fgXi,j(t)+K(|Xi,j(t)Xworst (t)|(fifw)+ε),fi=fg
式中:Xbest(t)为当前的最优位置;β为控制步长的参数;K∈[-1,1]为一个随机数;fi为麻雀的适应度值;fgfw分别为当前全局最佳和最差的适应度值;ε为一个很小的数值。
GRU是一种循环神经网络(recurrent neural network,RNN)的变体,由Cho等人于2014年提出,它可以处理序列数据,如文本、语音和时间序列等[25-26],其单元结构如图2所示。GRU可以有选择地存储较为重要的信息,并遗忘不重要的信息,同时它也能很好地解决LSTM神经网络等传统循环网络存在的梯度爆炸及长期记忆的问题,其运算效率也较高[23]。GRU的运算表达式为:
{zt=σ(Wzxt+Uzht1+bz)rt=σ(Wrxt+Urht1+br)h˜t=tanh(Whxt+Uh(rtht1)+bh)ht=(1zt)ht1+zth˜t
式中:为矩阵中的各个元素相乘;WzWrWhUzUrUh分别为权重系数;bzbrbh分别为输入参数的偏置;ztrt分别为更新门和重置门t时刻的输出;xtt时刻输入;ht-1t-1时刻的输出;htt时刻的输出;h˜t为待更新参数;σ为sigmoid函数。
图2可知,h˜t是由ht-1xt共同决定的,重置门rt决定了xtht-1相结合的比重,并存储短期记忆中的信息;同时ht中包含了ht-1h˜t,并由更新门zt来设置权重,zt能存储长期记忆中的信息。此时,长期记忆和短期记忆组合起来,一起组成了GRU单元t时刻的输出ht,然后将其输入下一个GRU单元中。
GRU中各个参数的设置非常重要,参数设置会影响模型的结构和性能,不同的参数组合可能会导致不同的预测结果。同时,参数设置需要平衡模型的复杂度和泛化能力,过大或过小的参数可能会导致过拟合或欠拟合的问题,影响模型在未知数据上的预测效果。因此本文引入ISSA来对GRU中的参数进行优化,利用ISSA模拟麻雀的觅食和返捕食行为,来寻找最优的参数组合,以提高GRU预测的有效性和准确性,ISSA-GRU流程如图3所示。
相较于LSTM模型,GRU模型参数量少,训练速度快,但也可能导致表达能力不足,无法捕捉复杂的序列特征,同时GRU模型也存在梯度爆炸的风险[27]。因此本文在GRU模型中引入VMD,可以有效地降低信号的复杂度和噪声干扰,提高信号的平稳性和可分辨性,同时也可以有效减少GRU模型的输入维度和参数数量,提高GRU模型的训练速度和准确性。图4为VMD-ISSA-GRU流程。
结合VMD、ISSA算法以及GRU模型,本文搭建VMD-ISSA-GRU组合模型,其运行步骤如下:
1)通过VMD将原始风电功率数据X(t)分解,得到n个子序列,其表达式为:
X(t)=i=1nIMFi(t)+Re(t)
2)将分解得到的各个分量输入搭建的ISSA-GRU模型中,并运用改进麻雀搜索算法对GRU中各个参数(隐藏层层数、隐藏层节点数以及丢失率)进行寻优,然后用训练结束后的模型进行功率预测。
3)各个序列经过训练后的模型会预测出其对应的功率值,将这n个数值进行相加,便能得到最终的预测结果。
4)误差分析。
本文采用Kaggle上德国TenneT TSO能源公司的风力发电数据,选取2020年8.1—8.10的风力发电数据,采样间隔为15 min,每天采样96个点,10天总计960个采样点,本文采用均值插补法对其中的缺失值、异常值进行处理,以便更好地用于模型的训练以及预测,提高预测精度,其风电功率曲线如图5所示。
为了更好地适应于模型的训练,将原始数据按照8:1:1划分为训练集、验证集以及测试集。本文采用的评价指标有平均绝对误差(mean absolute error,δMAE)、平均绝对百分比误差(mean absolute percentage error,δMAPE)、均方根误差(root mean square error,δRMSE),其表达式为:
δMAE=1ni=1ny^iyi
δMAPE=100%ni=1ny^iyiyi
δRMSE=1ni=1n(yiy^i)2
式中:yi为真实值;y^i为预测值。
VMD能将风电功率分解为多个窄带信号,每个信号有单一频率和模式,这样能降低数据的复杂度和不稳定性,突出信号的时频特征。但是,K值的选择至关重要,K值过小,会导致信号的重要信息被过滤或混合;K值过大,会导致信号的过分解或模态重复[28]。因此本文通过对中心频率的观察来确定K值,当分解得到的最后一层分量的中心频率达到稳定时,可获得最佳K值。其他参数:惩罚系数α取1 000,收敛容差tol取5×10-6,拉格朗日乘子更新率tau取0.01。在MATLAB上进行实验,实验结果如图6表1所示。由表1可见,在分解次数为7和8时,它们最后一个模态中心频率相差不大,趋于稳定,且倒数第2个模态的中心频率也近似,因此,当K=7时,VMD分解效果达到最佳。
使用不同的时间步长可能会出现不同的结果,因此本小节使用GRU作为基础模型来确定输入的时间步长,步长范围设定为[1,10],对于不同的时间步长分别进行仿真,其结果如图7所示。从图7可以看出,当步长设置为4时,所对应的平均绝对误差、均方根误差为最小,此时预测精度最高,因此后续的实验仿真输入时间步长统一设置为4。单时间序列输入步长与输出结果如图8所示。
图8P为风电功率,Pt表示t时刻的风电功率,若要预测t时刻的风电功率,则要输入t–4、t–3、t–2、t–1时刻的风电功率数据,即进行单点预测,输入历史前4个点的数据,得到第5个点的预测值。
为验证VMD的有效性,首先将原始数据通过VMD进行分解,再将分解后的各个子序列分别输入GRU、LSTM、BiLSTM模型中,得到各个误差,并与不采用VMD直接利用这2个模型进行预测的预测误差进行对比,结果见表2
表2可知,在使用VMD对原始风电功率序列进行分解后,模型的预测精度都有一定的提高,其中,VMD-GRU模型相较于GRU模型,平均绝对误差、平均绝对百分比误差、均方根误差分别降低了1.79%、6.40%、4.08%,VMD-LSTM模型相较于LSTM模型,平均绝对误差、平均绝对百分比误差、均方根误差分别降低了1.65%、11.02%、6.11%。VMD-BiLSTM模型相较于BiLSTM模型,平均绝对误差、平均绝对百分比误差、均方根误差分别降低了15.48%、19.40%、18.54%。实验结果表明VMD能降低原始数据的噪声以及复杂程度,将分解后的数据输入模型中能提高模型的预测精度。
采用一些神经网络以及优化算法进行对比,为了更方便实验的对比,将模型和算法的各个参数统一设置,其中神经元个数设置为16,epochs为200,初始学习率为0.001,Batchsize为75,优化算法种群个数为4,进化次数为15。同时设置优化算法优化的超参数范围,其中隐藏层层数优化范围为[1,3],神经元个数范围为[2,50],丢失率范围为(0,0.005)。
为了更好地验证本文提出组合模型的预测能力,针对不同模型以及算法建立了不同的组合模型,分别进行实验,参数按照上节所示设置,时间步长统一设置成4,可以得到如图9所示的各个基础模型对应最优组合模型的结果比较,各组合模型误差指标见表3
表3的数据可知,相较于单一模型或者未使用优化算法进行参数寻优的模型,使用VMD技术且加入优化算法进行参数寻优的组合模型预测精度更高,预测结果与原始数据的拟合程度更好。结合表3中的数据可知,VMD-ISSA-GRU组合模型相较于GRU以及VMD-GRU模型,其平均绝对误差分别降低了60.02%与59.69%;平均绝对百分比误差分别降低了59.44%与56.67%;均方根误差分别降低了57.49%与55.68%;使用其他优化算法同样也对模型的精度有一定的提升,如VMD-PSO-GRU模型相较于GRU以及VMD-GRU模型,其平均绝对误差分别降低了55.34%与54.52%;其平均绝对百分比误差分别降低了56.65%与53.69%;其均方根误差分别降低了52.81%与50.80%。同样的,以LSTM、BiLSTM为基础模型的其他组合模型相较于单一模型在预测误差上也都有不同程度的降低,可见在加入变分模态分解对原始数据进行处理以及使用优化算法对基础模型的超参数进行寻优后,能更好提高模型的性能,并提高预测精度。将GRU、LSTM、BiLSTM中最优的组合模型进行比较,本文使用混沌映射、非线性递减权重以及一个突变策略来改进的麻雀搜索算法相较于其他优化算法具有更高的预测精度,其中VMD-ISSA-GRU组合模型相较于VMD-AVOA-LSTM以及VMD-ISSA-BiLSTM组合模型,其平均绝对误差分别降低了31.48%与10.62%;其平均绝对百分比误差分别降低了25.88%与3.08%;其均方根误差分别降低了29.68%与11.50%。
为了验证本文提出模型的普适性,选取Kaggle上另外一家德国能源公司Amprion风力发电数据进行模型性能的验证,后面将这个数据集分别简称为AM数据集,同样每15 min采样一次,10天共计960个采样点,将数据集按照8:1:1进行划分为训练集、验证集以及测试集,对模型进行训练并验证其性能,模型参数等保持不变,训练结果如图10以及表4所示。由表4可知,本文提出的VMD-ISSA-GRU模型相较于GRU、VMD-GRU以及ISSA-GRU模型,其平均绝对误差分别降低了68.16%、57.48%以及57.35%;其平均绝对百分比误差分别降低了65.43%、49.89%以及55.96%;其均方根误差分别降低了68.88%、60.43%以及61.02%。可见,VMD-ISSA-GRU模型相较于传统GRU模型或仅使用VMD或者ISSA中一种方法的模型具有更高的精度。同样的,相较于VMD-ISSA-BiLSTM组合模型,其平均绝对误差、平均绝对百分比误差、均方根误差分别降低了14.52%、15.27%以及11.78%。因此,本文提出的VMD-ISSA-GRU组合模型具有一定的普适性,且相较于其他模型具有更高的预测精度。
本文针对风电功率波动和不平稳的特性以及提高风电功率预测精度的问题上,提出了一种通过中心频率法确定VMD分解次数,并且通过VMD将复杂的风电功率数据分解成多个子序列,分别结合ISSA优化的GRU对各个子序列进行训练预测,最后将预测结果叠加得到最终预测结果,主要结论如下。
1)本文通过中心频率法确定VMD分解次数能够更好地分解风电功率数据,有效避免了分解不充分以及过分解的问题,更加有利于后续模型的训练与预测,能够有效提高模型预测精度。
2)通过引入混沌映射来初始化麻雀搜索算法的种群位置,使用非线性递减权重以及突变策略来更新发现者和加入者的位置,能更好地解决传统SSA种群初始化混乱、加入者发现者位置更新不到位的问题,并利用ISSA对GRU进行参数寻优,以便更好地设置模型的超参数。
3)本文提出的VMD-ISSA-GRU组合模型通过使用VMD以及ISSA解决了风电功率数据复杂、波动大以及GRU参数设置困难的问题,在AM数据集上,其平均绝对误差、平均绝对百分比误差、均方根误差相较于GRU分别降低了68.16%、65.43%、68.88%,且相较于其他组合模型,误差更小,具有更高的预测精度。
虽然本文模型在超短期风电功率预测精度上相较于其他模型有一定的提升,但是风电功率受风速、温度、气压等因素的影响,本文在预测过程中未考虑,因此后续会将这些因素作为特征输入模型中,以便进一步提高预测精度。
  • 国家自然科学基金项目(52107107)
参考文献 引证文献
排序方式:
[1]
CAO B, CHANG L C. Development of short-term wind power forecasting methods[M]. 2022 IEEE 7th Southern Power Electronics Conference (SPEC). IEEE, 2022: 1-5.
[2]
SUN Y, LI Z Y, YU X N, et al. Research on ultra-short-term wind power prediction considering source relevance[J]. IEEE Access, 2020, 8: 147703-147710.
[3]
YAN J, ZHANG H, LIU Y Q, et al. Forecasting the high-penetration of wind power on multiple scales using multi-to-multi mapping[J]. IEEE Transactions on Power Systems, 2018, 33(3): 3276-3284.
[4]
唐新姿, 顾能伟, 黄轩晴, 等. 风电功率短期预测技术研究进展[J]. 机械工程学报, 2022, 58(12): 213-236.
TANG Xinzi, GU Nengwei, HUANG Xuanqing, et al. Progress on short term wind power forecasting technology[J]. Journal of Mechanical Engineering, 2022, 58(12): 213-236.
[5]
钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060.
QIAN Zheng, PEI Yan, CAO Lixiao, et al. Review of wind power forecasting method[J]. High Voltage Engineering, 2016, 42(4): 1047-1060.
[6]
韩自奋, 景乾明, 张彦凯, 等. 风电预测方法与新趋势综述[J]. 电力系统保护与控制, 2019, 47(24): 178-187.
HAN Zifen, JING Qianming, ZHANG Yankai, et al. Review of wind power forecasting methods and new trends[J]. Power System Protection and Control, 2019, 47(24): 178-187.
[7]
张怡, 杨宇晴. 基于AM-LSTM的风电场内多点位风电功率预测[J]. 计算机仿真, 2021, 38(10): 145-148.
ZHANG Yi, YANG Yuqing. Multi-point wind power prediction in wind farms based on AM-LSTM[J]. Computer Simulation, 2021, 38(10): 145-148.
[8]
李森文, 张伟, 李纯宇, 等. 基于SSA-LSTM的海上风电功率预测[J]. 机械与电子, 2022, 40(6): 22-25.
LI Senwen, ZHANG Wei, LI Chunyu, et al. Power prediction of offshore wind farm based on SSA-LSTM[J]. Machinery & Electronics, 2022, 40(6): 22-25.
[9]
王愈轩, 梁沁雯, 章思远, 等. 基于LSTM-XGboost组合的超短期风电功率预测方法[J]. 科学技术与工程, 2022, 22(14): 5629-5635.
WANG Yuxuan, LIANG Qinwen, ZHANG Siyuan, et al. An ultra⁃short⁃term wind power prediction method based on LSTM⁃XGboost combination[J]. Science Technology and Engineering, 2022, 22(14): 5629-5635.
[10]
王斌, 魏成伟, 谢丽蓉, 等. 基于风速误差校正和ALO-LSSVM的风电功率预测[J]. 太阳能学报, 2022, 43(1): 58-63.
WANG Bin, WEI Chengwei, XIE Lirong, et al. Wind power forecasting based on wind speed errorcorretion and ALO-LSSVM[J]. Acta Energiae Solaris Sinica, 2022, 43(1): 58-63.
[11]
张涛, 朱瑞金, 扎西顿珠. 基于改进骨干差分进化算法优化LSSVM的短期光伏发电功率预测[J]. 热力发电, 2021, 50(5): 102-107.
ZHANG Tao, ZHU Ruijin, ZHAXI Dunzhu, et al. Short-term photovoltaic power prediction based on IBBDE-LSSVM[J]. Thermal Power Generation, 2021, 50(5): 102-107.
[12]
李宏扬, 高丙朋. 基于改进VMD和SNS-Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报, 2023, 44(8): 292-300.
LI Hongyang, GAO Bingpeng. Short-term PV power forecasting based on improved VMD and SNS-Attention-GRU[J]. Acta Energiae Solaris Sinica, 2023, 44(8): 292-300.
[13]
DAN F C, HORA C, BENDEA G. Short-term forecasting of wind power generation[C]. 2021 10th International Conference on Energy and Environment (CIEM). 2021: 1-5.
[14]
张振中, 郭傅傲, 刘大明, 等. 基于最大互信息系数和小波分解的多模型集成短期负荷预测[J]. 计算机应用与软件, 2021, 38(5): 82-87.
ZHANG Zhenzhong, GUO Fuao, LIU Daming, et al. Multi-model intergrated short-term load prediction based on maximum mutual information coefficientand wavelet decomposition[J]. Computer Applications and Software, 2021, 38(5): 82-87.
[15]
余周, 姜涛, 范鹏辉, 等. 基于EMD-DELM-LSTM组合模型的湖泊水位多时间尺度预测[J/OL]. 长江科学院院报:1-9 [2024-03-01]. http://kns.cnki.net/kcms/detail/42.1171.TV.20230413.1830.002.html.
YU Zhou, JIANG Tao, FAN Penghui, et al. Multi-time scale prediction for lake level based on EMD-DELM-LSTM combined model[J/OL]. Journal of Changjiang River Scientific Research Institute: 1-9 [2024-03-01]. http://kns.cnki.net/kcms/detail/42.1171.TV.20230413.1830.002.html.
[16]
侯金霄, 黄林显, 胡晓农, 等. 基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用[J]. 水资源与水工程学报, 2023, 34(4): 92-98.
HOU Jinxiao, HUANG Linxian, HU Xiaonong, et al. Application of EMD-LSTM coupled model to karst groundwater level prediction in Baotu Spring[J]. Journal of Water Resources and Water Engineering, 2023, 34(4): 92-98.
[17]
张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG Yunqin, CHENG Qize, JIANG Wenjie, et al. Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta Energiae Solaris Sinica, 2021, 42(9): 62-69.
[18]
TATINATI S, WANG Y, KHONG A W H. Hybrid method based on random convolution nodes for short-term wind speed forecasting[J]. IEEE Transactions on Industrial Informatics, 2022, 18(10): 7019-7029.
[19]
WANG Z, WANG L, REVANESH M, et al. Short-term wind speed and power forecasting for smart city power grid with a hybrid machine learning framework[J]. IEEE Internet of Things Journal, 2023, 10(21): 18754-18765.
[20]
王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.
WANG Weigao, WEI Yunbing, TENG Xudong. Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta Energiae Solaris Sinica, 2023, 44(3): 204-211.
[21]
DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[22]
薛建凯. 一种新型的群智能优化技术的研究与应用 [J]. 上海: 东华大学, 2020: 1-10.
XUE Jiankai. Research and application of a novel swarm intelligence optimization technique: sparrow search algorithm[J]. Shanghai: Dong Hua University, 2020: 1-10.
[23]
SONG W, LIU S, WANG X C, et al. An improved sparrow search algorithm[C]. 2020 IEEE Intl Conf on Parallel & Distributed Processing with Applica & Communications, Social Computing & Networking (ISPA/BDCloud/Social Com/SustainCom). 2020: 537-543.
[24]
MA B, LU P M, ZHANG L F, et al. Enhanced sparrow search algorithm with mutation strategy for global optimization[J]. IEEE Access, 2021, 9: 159218-159261.
[25]
GU Y, WANG F D, LI M K, et al. A digital load forecasting method based on digital twin and improved GRU[C]. 2022 Asian Conference on Frontiers of Power and Energy (ACFPE). 2022: 462-476.
[26]
CHO K, VAN M B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014: 1724-1734.
[27]
GAO L, ZHAO L J, KONG F, et al. Research method of ultra-short-term wind power prediction based on PSO-GRU prediction[C]. 2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC). 2022: 967-972.
[28]
ZHANG H R, ZHANG Y Y, XU Z W. Thermal load forecasting of an ultra-short-term integrated energy system based on VMD-CNN-LSTM[M]. 2022 International Conference on Big Data, Information and Computer Network (BDICN). 2022: 264-279.
2024年第53卷第5期
PDF下载
92
40
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202312189
  • 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
National Natural Science Foundation of China(52107107)
国家自然科学基金项目(52107107)
作者信息
    1.三峡大学电气与新能源学院,湖北 宜昌 443002
    2.智慧能源技术湖北省工程研究中心(三峡大学),湖北 宜昌 443002

通讯作者:

邹智超(2000),男,硕士研究生,主要研究方向为基于深度学习的目标检测、预测,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202312189
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