PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment
The randomness, volatility, and intermittence of solar power generation make it difficult to achieve the desired accuracy of PV output-power prediction. Therefore, the time learning weight (TLW) proposed in this paper is used to improve the time correlation of the LSTM network. The Fusion Activation...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8808846/ |
| _version_ | 1818412528459317248 |
|---|---|
| author | Minkang Chai Fei Xia Shuotao Hao Daogang Peng Chenggang Cui Wei Liu |
| author_facet | Minkang Chai Fei Xia Shuotao Hao Daogang Peng Chenggang Cui Wei Liu |
| author_sort | Minkang Chai |
| collection | DOAJ |
| description | The randomness, volatility, and intermittence of solar power generation make it difficult to achieve the desired accuracy of PV output-power prediction. Therefore, the time learning weight (TLW) proposed in this paper is used to improve the time correlation of the LSTM network. The Fusion Activation Function (FAF) is used to resolve gradient disappearance. Learning Factor Adaptation (LFA) and Momentum Resistance Weight Estimation (MRWE) are used to accelerate weight convergence and improve global search capabilities. Finally, this paper synthesizes the improvement and proposes the AHPA-LSTM model to stabilize the convergence domain. Using actual data verification, the δMAPE indicator of the improved model is only 2.85% on a sunny day, 5.92% on a cloudy day, 7.71% on a rainy day, and only 5.8% on average. Therefore, the AHPA-LSTM model under full climate and climatic conditions has a good predictive effect which is generally applicable to the prediction of ultra-short-term PV power generation. |
| first_indexed | 2024-12-14T10:48:45Z |
| format | Article |
| id | doaj.art-4d238bcfbbd04b7cb1bd3de6b6c2305e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:48:45Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4d238bcfbbd04b7cb1bd3de6b6c2305e2022-12-21T23:05:20ZengIEEEIEEE Access2169-35362019-01-01711547311548610.1109/ACCESS.2019.29365978808846PV Power Prediction Based on LSTM With Adaptive Hyperparameter AdjustmentMinkang Chai0https://orcid.org/0000-0002-8206-6999Fei Xia1https://orcid.org/0000-0003-0793-3113Shuotao Hao2Daogang Peng3Chenggang Cui4Wei Liu5College of Automation Engineering, Shanghai University of Electric Power, Shanghai, ChinaCollege of Automation Engineering, Shanghai University of Electric Power, Shanghai, ChinaFangshan Power Supply Company, Beijing Power Company, State Grid, Beijing, ChinaCollege of Automation Engineering, Shanghai University of Electric Power, Shanghai, ChinaCollege of Automation Engineering, Shanghai University of Electric Power, Shanghai, ChinaHaining Chinaust Plastics Piping System Company Ltd., Haining, ChinaThe randomness, volatility, and intermittence of solar power generation make it difficult to achieve the desired accuracy of PV output-power prediction. Therefore, the time learning weight (TLW) proposed in this paper is used to improve the time correlation of the LSTM network. The Fusion Activation Function (FAF) is used to resolve gradient disappearance. Learning Factor Adaptation (LFA) and Momentum Resistance Weight Estimation (MRWE) are used to accelerate weight convergence and improve global search capabilities. Finally, this paper synthesizes the improvement and proposes the AHPA-LSTM model to stabilize the convergence domain. Using actual data verification, the δMAPE indicator of the improved model is only 2.85% on a sunny day, 5.92% on a cloudy day, 7.71% on a rainy day, and only 5.8% on average. Therefore, the AHPA-LSTM model under full climate and climatic conditions has a good predictive effect which is generally applicable to the prediction of ultra-short-term PV power generation.https://ieeexplore.ieee.org/document/8808846/Photovoltaic output powerultra-short-term predictionlong short term memory (LSTM)time weight decouplingadaptive hyperparameter adjustment |
| spellingShingle | Minkang Chai Fei Xia Shuotao Hao Daogang Peng Chenggang Cui Wei Liu PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment IEEE Access Photovoltaic output power ultra-short-term prediction long short term memory (LSTM) time weight decoupling adaptive hyperparameter adjustment |
| title | PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment |
| title_full | PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment |
| title_fullStr | PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment |
| title_full_unstemmed | PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment |
| title_short | PV Power Prediction Based on LSTM With Adaptive Hyperparameter Adjustment |
| title_sort | pv power prediction based on lstm with adaptive hyperparameter adjustment |
| topic | Photovoltaic output power ultra-short-term prediction long short term memory (LSTM) time weight decoupling adaptive hyperparameter adjustment |
| url | https://ieeexplore.ieee.org/document/8808846/ |
| work_keys_str_mv | AT minkangchai pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment AT feixia pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment AT shuotaohao pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment AT daogangpeng pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment AT chenggangcui pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment AT weiliu pvpowerpredictionbasedonlstmwithadaptivehyperparameteradjustment |