PV and Load Forecasting for Photovoltaic Communities Based on a Hybrid Model of LSTM and Transformer

This paper investigates the PV and load forecasting problem for PV communities. A construction of a PV and load forecasting model based on a hybrid model of LSTM and Transformer is proposed. The multi-attention mechanism of Transformer is added to the traditional neural network LSTM model. This hybr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Conference on Industrial Technology (Online) s. 1 - 6
Hlavní autoři: Cen, Jinglong, Zhang, Xing, Wang, Qingyi, Xiao, Zhongyuan, Xu, Chang, Li, Xiang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 26.03.2025
Témata:
ISSN:2643-2978
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper investigates the PV and load forecasting problem for PV communities. A construction of a PV and load forecasting model based on a hybrid model of LSTM and Transformer is proposed. The multi-attention mechanism of Transformer is added to the traditional neural network LSTM model. This hybrid model optimizes the original data according to the PV and load time series characteristics. The weighted mean square error method is used to design the loss function. In order to prevent model overfitting and improve stability, Adam optimizer and regularization coefficient is introduced. In order to verify the superiority of the model, machine learning and traditional neural network method comparison experiments are carried out in this paper. The experimental results show that the model designed in this paper has the smallest error between the predicted value and the true value. It shows that the model with the introduction of Transformer's multi-attention mechanism in LSTM model can improve the prediction accuracy.
AbstractList This paper investigates the PV and load forecasting problem for PV communities. A construction of a PV and load forecasting model based on a hybrid model of LSTM and Transformer is proposed. The multi-attention mechanism of Transformer is added to the traditional neural network LSTM model. This hybrid model optimizes the original data according to the PV and load time series characteristics. The weighted mean square error method is used to design the loss function. In order to prevent model overfitting and improve stability, Adam optimizer and regularization coefficient is introduced. In order to verify the superiority of the model, machine learning and traditional neural network method comparison experiments are carried out in this paper. The experimental results show that the model designed in this paper has the smallest error between the predicted value and the true value. It shows that the model with the introduction of Transformer's multi-attention mechanism in LSTM model can improve the prediction accuracy.
Author Xu, Chang
Li, Xiang
Xiao, Zhongyuan
Zhang, Xing
Wang, Qingyi
Cen, Jinglong
Author_xml – sequence: 1
  givenname: Jinglong
  surname: Cen
  fullname: Cen, Jinglong
  email: 1350085142@cug.edu.cn
  organization: School of Automation, China University of Geosciences,Wuhan,China
– sequence: 2
  givenname: Xing
  surname: Zhang
  fullname: Zhang, Xing
  email: xingzhang2917@163.com
  organization: Wuhan Second Ship Design & Res Inst,Wuhan,China
– sequence: 3
  givenname: Qingyi
  surname: Wang
  fullname: Wang, Qingyi
  email: wangqingyi@cug.edu.cn
  organization: School of Automation, China University of Geosciences,Wuhan,China
– sequence: 4
  givenname: Zhongyuan
  surname: Xiao
  fullname: Xiao, Zhongyuan
  email: 1228078176@qq.com
  organization: School of Automation, China University of Geosciences,Wuhan,China
– sequence: 5
  givenname: Chang
  surname: Xu
  fullname: Xu, Chang
  email: 2380411738@qq.com
  organization: School of Automation, China University of Geosciences,Wuhan,China
– sequence: 6
  givenname: Xiang
  surname: Li
  fullname: Li, Xiang
  email: lx_utop@cug.edu.cn
  organization: School of Automation, China University of Geosciences,Wuhan,China
BookMark eNo10N9KwzAYBfAoCs65NxDMC3Sm-ZpkudTi3KDDgcXbkTRfNLImklZhb-_wz9WBc_HjcC7JWUwRCbkp2bwsmb5d1-tWggQ154yL-bGSArg4ITOt9AKgFLzUgp2SCZcVFFyrxQWZDcM7Yww4g6qSE-K2L9RER5tkHF2mjJ0ZxhBfqU-Zbt_SmL7SfjSho3Xq-88YxoADvTcDOpoiNXR1sDk4ukkO9zR52jy3mx-xzSYOR6XHfEXOvdkPOPvLKWmXD229Kpqnx3V91xRBw1hUvEN0bsFUxf1xudCguLBcOGUdl1h10nlr0RuLUnknvAXHkYEoAUvsYEquf9mAiLuPHHqTD7v_X-AbpllaGg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICIT63637.2025.10965325
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798331521950
EISSN 2643-2978
EndPage 6
ExternalDocumentID 10965325
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-42ceedd80742f195593725b25d7bd26e4c6dfbbefabe67fd5fb3d2e03513e1ec3
IEDL.DBID RIE
IngestDate Wed Apr 30 05:50:36 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-42ceedd80742f195593725b25d7bd26e4c6dfbbefabe67fd5fb3d2e03513e1ec3
PageCount 6
ParticipantIDs ieee_primary_10965325
PublicationCentury 2000
PublicationDate 2025-March-26
PublicationDateYYYYMMDD 2025-03-26
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-March-26
  day: 26
PublicationDecade 2020
PublicationTitle IEEE International Conference on Industrial Technology (Online)
PublicationTitleAbbrev ICIT
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003203446
Score 1.9033605
Snippet This paper investigates the PV and load forecasting problem for PV communities. A construction of a PV and load forecasting model based on a hybrid model of...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Attention mechanisms
Correlation
Data models
Load forecasting
Load modeling
Long short term memory
multiple attention mechanisms
Neural networks
prediction
Predictive models
time Series
Time series analysis
Transformers
Title PV and Load Forecasting for Photovoltaic Communities Based on a Hybrid Model of LSTM and Transformer
URI https://ieeexplore.ieee.org/document/10965325
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62eNCLr4pvcvC6tU02SfdqsbRQy4JL6a3kMcGC7Eq7Ffz3ZrbbqgcP3kJIQkiYfJlkvm8IuVc6-FUBKSMV8Cg4KNJEWggb2WBXiRYdYysi7XSsJpPebJakNVm94sIAQBV8Bm0sVn_5rrBrfCoLFp5IwZlokIZSakPW2j2ocIbqdbKO4QpNH0b9USa55Cq4gUy0t71_5VGpYGRw9M8JHJPWNyGPpjuoOSF7kJ-Swx9agmfEpVOqc0fHhXYUE25avcKQZhpupTR9LcoiHESlXlhac0JQSZU-BhBztMippsNPJG9RTI72RgtPxy_ZczVitr3bwrJFssFT1h9GdQqFaJHwMooZTsyh4A3zXRSb44oJw4RTxjEJsZXOGwNeG5DKO-ENdwzwd5FDFyw_J828yOGCUB3gLlisj4W3MQhtuOeyw5MAgkmPeX5JWrhe8_eNSMZ8u1RXf9RfkwPcFQznYvKGNMvlGm7Jvv0oF6vlXbW1X6Lmo_I
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBfXiq-LbOXjd2iabbPdqsbS4LQWX0lvJEwuyK-1W8N-b2W6rHjx4CyEJIWHyZZL5viHkPpLer_JIGUQej7yDIlQgOdeB9nYVS95UuiTSjpNoOGxPJvGoIquXXBhrbRl8ZhtYLP_yTa6X-FTmLTwWnFG-TXZ4GNLWiq61eVJhFPXrRBXF5Rs_9Dv9VDDBIu8IUt5Y9_-VSaUEku7hP6dwROrflDwYbcDmmGzZ7IQc_FATPCVmNAaZGUhyaQBTbmq5wKBm8PdSGL3mRe6PokLONFSsENRShUcPYwbyDCT0PpG-BZge7Q1yB8lLOihHTNe3Wzuvk7T7lHZ6QZVEIZjFrAhCihMzKHlDXQvl5lhEuaLcRMpQYUMtjFPKOqmsiJzhTjFDLf4vMtuymp2RWpZn9pyA9IDnbdaF3OnQcqmYY6LJYg-DcZs6dkHquF7T95VMxnS9VJd_1N-RvV46SKZJf_h8RfZxhzC4i4prUivmS3tDdvVHMVvMb8tt_gJYDKc5
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Industrial+Technology+%28Online%29&rft.atitle=PV+and+Load+Forecasting+for+Photovoltaic+Communities+Based+on+a+Hybrid+Model+of+LSTM+and+Transformer&rft.au=Cen%2C+Jinglong&rft.au=Zhang%2C+Xing&rft.au=Wang%2C+Qingyi&rft.au=Xiao%2C+Zhongyuan&rft.date=2025-03-26&rft.pub=IEEE&rft.eissn=2643-2978&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FICIT63637.2025.10965325&rft.externalDocID=10965325