Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion
ABSTRACT The accurate prediction of the output power of each power plant is crucial for effective resource deployment. This paper proposes a convolutional neural network‐long short‐term memory (CNN‐LSTM) network integration model based on spatio‐temporal feature fusion. Firstly, the temporal correla...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.13088 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576597069135872 |
|---|---|
| author | Junwei Ma Meiru Huo Jinfeng Han Yunfeng Liu Shunfa Lu Xiaokun Yu |
| author_facet | Junwei Ma Meiru Huo Jinfeng Han Yunfeng Liu Shunfa Lu Xiaokun Yu |
| author_sort | Junwei Ma |
| collection | DOAJ |
| description | ABSTRACT The accurate prediction of the output power of each power plant is crucial for effective resource deployment. This paper proposes a convolutional neural network‐long short‐term memory (CNN‐LSTM) network integration model based on spatio‐temporal feature fusion. Firstly, the temporal correlation of the PV features of the target power plant and the spatial correlation between the PV power of the target power plant and the PV power of the neighboring power plants are computed. The features are then fused according to the strength of the correlation, which allows the features to be combined with spatial and temporal attributes, which promotes faster and more effective training of the model. Subsequently, an integrated network architecture comprising three individual models, CNN, LSTM, and CNN‐LSTM, is designed. The SENet attention mechanism is utilized to add non‐linear integration weights to the outputs of the individual models. Due to the variability of different neural networks, the prediction results of the integrated model are often higher than the best‐performing individual model. Additionally, we designed different case studies to compare model performance under sunny, rainy, and cloudy conditions. Extensive simulation experiments demonstrate the effectiveness of our proposed integrated approach. When the prediction interval is set to 5 min, the RMSE loss of the integrated model on the test set is reduced by 13.5%, 6.9%, and 5.1% compared to the CNN, LSTM, and CNN‐LSTM models included in the ensemble, respectively. |
| format | Article |
| id | doaj-art-1006be11d53e497bb9e5922d449c9b36 |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-1006be11d53e497bb9e5922d449c9b362025-01-31T00:22:49ZengWileyEngineering Reports2577-81962025-01-0171n/an/a10.1002/eng2.13088Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature FusionJunwei Ma0Meiru Huo1Jinfeng Han2Yunfeng Liu3Shunfa Lu4Xiaokun Yu5Information and Communication Branch State Grid Shanxi Electric Power Company Taiyuan ChinaInformation and Communication Branch State Grid Shanxi Electric Power Company Taiyuan ChinaInformation and Communication Branch State Grid Shanxi Electric Power Company Taiyuan ChinaInformation and Communication Branch State Grid Shanxi Electric Power Company Taiyuan ChinaState Grid Block Chain Technology (Beijing) Co. Ltd Beijing ChinaState Grid Block Chain Technology (Beijing) Co. Ltd Beijing ChinaABSTRACT The accurate prediction of the output power of each power plant is crucial for effective resource deployment. This paper proposes a convolutional neural network‐long short‐term memory (CNN‐LSTM) network integration model based on spatio‐temporal feature fusion. Firstly, the temporal correlation of the PV features of the target power plant and the spatial correlation between the PV power of the target power plant and the PV power of the neighboring power plants are computed. The features are then fused according to the strength of the correlation, which allows the features to be combined with spatial and temporal attributes, which promotes faster and more effective training of the model. Subsequently, an integrated network architecture comprising three individual models, CNN, LSTM, and CNN‐LSTM, is designed. The SENet attention mechanism is utilized to add non‐linear integration weights to the outputs of the individual models. Due to the variability of different neural networks, the prediction results of the integrated model are often higher than the best‐performing individual model. Additionally, we designed different case studies to compare model performance under sunny, rainy, and cloudy conditions. Extensive simulation experiments demonstrate the effectiveness of our proposed integrated approach. When the prediction interval is set to 5 min, the RMSE loss of the integrated model on the test set is reduced by 13.5%, 6.9%, and 5.1% compared to the CNN, LSTM, and CNN‐LSTM models included in the ensemble, respectively.https://doi.org/10.1002/eng2.13088convolutional neural networkfeature correlationlong short‐term memory networkphotovoltaic power prediction |
| spellingShingle | Junwei Ma Meiru Huo Jinfeng Han Yunfeng Liu Shunfa Lu Xiaokun Yu Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion Engineering Reports convolutional neural network feature correlation long short‐term memory network photovoltaic power prediction |
| title | Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion |
| title_full | Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion |
| title_fullStr | Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion |
| title_full_unstemmed | Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion |
| title_short | Integrated CNN‐LSTM for Photovoltaic Power Prediction based on Spatio‐Temporal Feature Fusion |
| title_sort | integrated cnn lstm for photovoltaic power prediction based on spatio temporal feature fusion |
| topic | convolutional neural network feature correlation long short‐term memory network photovoltaic power prediction |
| url | https://doi.org/10.1002/eng2.13088 |
| work_keys_str_mv | AT junweima integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion AT meiruhuo integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion AT jinfenghan integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion AT yunfengliu integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion AT shunfalu integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion AT xiaokunyu integratedcnnlstmforphotovoltaicpowerpredictionbasedonspatiotemporalfeaturefusion |