A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster

Abstract Short-term day-ahead photovoltaic power prediction is of great significance for power system dispatch plan formulation. In this work, to improve the accuracy of photovoltaic power prediction, a TCN-Wpsformer (temporal convolutional network-window probability sparse Transformer) day-ahead ph...

Full description

Saved in:
Bibliographic Details
Main Authors: Tong Yang, Minan Tang, Hanting Li, Hongjie Wang, Chuntao Rao
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-95843-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258831623323648
author Tong Yang
Minan Tang
Hanting Li
Hongjie Wang
Chuntao Rao
author_facet Tong Yang
Minan Tang
Hanting Li
Hongjie Wang
Chuntao Rao
author_sort Tong Yang
collection DOAJ
description Abstract Short-term day-ahead photovoltaic power prediction is of great significance for power system dispatch plan formulation. In this work, to improve the accuracy of photovoltaic power prediction, a TCN-Wpsformer (temporal convolutional network-window probability sparse Transformer) day-ahead photovoltaic power prediction model based on combining data restoration and FCM (fuzzy C means) cluster is proposed. The time code of the dataset obtained after data restoration and FCM clustering was spliced with the location code. A temporal convolutional neural network is introduced to extract temporal segment features and incorporate a self-attention mechanism. The short-term photovoltaic power prediction is outputted by the window probability sparse Transformer model in multiple steps. Compared with the original Transformer model, the window probability sparse Transformer model uses the window probability sparse self-attention mechanism. It captures the long-term dependencies while filtering out the time segment features with relatively high importance for computation, which improves the prediction accuracy and reduces the computational cost. The computing time is reduced to 68.83% and R squared is improved by 5.3% compared to Transformer. The comparison is made through 11 models, and the R squared of this model is above 99% while different data volume and different power station data. It proves that the model stability and cross scene generalisation ability is well. Meanwhile, it can also provide more accurate confidence intervals on the basis of point prediction, which has certain application value.
format Article
id doaj-art-702c8eeafac14bfda8496ca69b94cc1b
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-702c8eeafac14bfda8496ca69b94cc1b2025-08-20T01:56:01ZengNature PortfolioScientific Reports2045-23222025-04-0115112210.1038/s41598-025-95843-9A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM clusterTong Yang0Minan Tang1Hanting Li2Hongjie Wang3Chuntao Rao4School of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversitySchool of Automation and Electrical Engineering, Lanzhou Jiaotong UniversityAbstract Short-term day-ahead photovoltaic power prediction is of great significance for power system dispatch plan formulation. In this work, to improve the accuracy of photovoltaic power prediction, a TCN-Wpsformer (temporal convolutional network-window probability sparse Transformer) day-ahead photovoltaic power prediction model based on combining data restoration and FCM (fuzzy C means) cluster is proposed. The time code of the dataset obtained after data restoration and FCM clustering was spliced with the location code. A temporal convolutional neural network is introduced to extract temporal segment features and incorporate a self-attention mechanism. The short-term photovoltaic power prediction is outputted by the window probability sparse Transformer model in multiple steps. Compared with the original Transformer model, the window probability sparse Transformer model uses the window probability sparse self-attention mechanism. It captures the long-term dependencies while filtering out the time segment features with relatively high importance for computation, which improves the prediction accuracy and reduces the computational cost. The computing time is reduced to 68.83% and R squared is improved by 5.3% compared to Transformer. The comparison is made through 11 models, and the R squared of this model is above 99% while different data volume and different power station data. It proves that the model stability and cross scene generalisation ability is well. Meanwhile, it can also provide more accurate confidence intervals on the basis of point prediction, which has certain application value.https://doi.org/10.1038/s41598-025-95843-9Photovoltaic power predictionData restorationFCM similar day clusterTemporal convolutional neural networkTCN-Wpsformer modelInterval forecast
spellingShingle Tong Yang
Minan Tang
Hanting Li
Hongjie Wang
Chuntao Rao
A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
Scientific Reports
Photovoltaic power prediction
Data restoration
FCM similar day cluster
Temporal convolutional neural network
TCN-Wpsformer model
Interval forecast
title A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
title_full A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
title_fullStr A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
title_full_unstemmed A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
title_short A novel PV power prediction method with TCN-Wpsformer model considering data repair and FCM cluster
title_sort novel pv power prediction method with tcn wpsformer model considering data repair and fcm cluster
topic Photovoltaic power prediction
Data restoration
FCM similar day cluster
Temporal convolutional neural network
TCN-Wpsformer model
Interval forecast
url https://doi.org/10.1038/s41598-025-95843-9
work_keys_str_mv AT tongyang anovelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT minantang anovelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT hantingli anovelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT hongjiewang anovelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT chuntaorao anovelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT tongyang novelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT minantang novelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT hantingli novelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT hongjiewang novelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster
AT chuntaorao novelpvpowerpredictionmethodwithtcnwpsformermodelconsideringdatarepairandfcmcluster