Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning
The integration of photovoltaic (PV) power into electrical grids introduces significant uncertainty due to the inherent volatility and intermittency of solar energy, underscoring the need for precise short and medium-term PV power forecasting. Despite the superior performance of Transformer-based ti...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142061524006124 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595405353779200 |
|---|---|
| author | Liang Yuan Xiangting Wang Yao Sun Xubin Liu Zhao Yang Dong |
| author_facet | Liang Yuan Xiangting Wang Yao Sun Xubin Liu Zhao Yang Dong |
| author_sort | Liang Yuan |
| collection | DOAJ |
| description | The integration of photovoltaic (PV) power into electrical grids introduces significant uncertainty due to the inherent volatility and intermittency of solar energy, underscoring the need for precise short and medium-term PV power forecasting. Despite the superior performance of Transformer-based time series methods, their application to PV power prediction remains suboptimal. In response to this deficiency, this paper proposes a novel attention mechanism that aggregates fluctuations across multiple time scales. This mechanism enhances the segmentation and extraction of nonlinear correlations between PV power outputs and meteorological factors, assigning variable weights to patterns of change across different time scales. Furthermore, a novel approach for selecting similar days is also developed based on contrastive learning, which enables self-supervised identification of similarities among PV power samples and enhances the model’s attention to local dynamic variations. Comparative analysis with eight state-of-the-art benchmark methods shows that the proposed MFA-attention model achieves lower prediction errors and improved effectiveness.© 2017 Elsevier Inc. All rights reserved. |
| format | Article |
| id | doaj-art-7d95c470b31a4c6fb4d976cb2049c936 |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-7d95c470b31a4c6fb4d976cb2049c9362025-01-19T06:23:53ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-03-01164110389Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learningLiang Yuan0Xiangting Wang1Yao Sun2Xubin Liu3Zhao Yang Dong4School of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, China; Corresponding author.Department of Electrical Engineering, City University of Hong Kong, Hong KongThe integration of photovoltaic (PV) power into electrical grids introduces significant uncertainty due to the inherent volatility and intermittency of solar energy, underscoring the need for precise short and medium-term PV power forecasting. Despite the superior performance of Transformer-based time series methods, their application to PV power prediction remains suboptimal. In response to this deficiency, this paper proposes a novel attention mechanism that aggregates fluctuations across multiple time scales. This mechanism enhances the segmentation and extraction of nonlinear correlations between PV power outputs and meteorological factors, assigning variable weights to patterns of change across different time scales. Furthermore, a novel approach for selecting similar days is also developed based on contrastive learning, which enables self-supervised identification of similarities among PV power samples and enhances the model’s attention to local dynamic variations. Comparative analysis with eight state-of-the-art benchmark methods shows that the proposed MFA-attention model achieves lower prediction errors and improved effectiveness.© 2017 Elsevier Inc. All rights reserved.http://www.sciencedirect.com/science/article/pii/S0142061524006124Photovoltaic power forecastingSelf-attention mechanismSimilar day selectionContrastive learningTransformer |
| spellingShingle | Liang Yuan Xiangting Wang Yao Sun Xubin Liu Zhao Yang Dong Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning International Journal of Electrical Power & Energy Systems Photovoltaic power forecasting Self-attention mechanism Similar day selection Contrastive learning Transformer |
| title | Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning |
| title_full | Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning |
| title_fullStr | Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning |
| title_full_unstemmed | Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning |
| title_short | Multistep photovoltaic power forecasting based on multi-timescale fluctuation aggregation attention mechanism and contrastive learning |
| title_sort | multistep photovoltaic power forecasting based on multi timescale fluctuation aggregation attention mechanism and contrastive learning |
| topic | Photovoltaic power forecasting Self-attention mechanism Similar day selection Contrastive learning Transformer |
| url | http://www.sciencedirect.com/science/article/pii/S0142061524006124 |
| work_keys_str_mv | AT liangyuan multistepphotovoltaicpowerforecastingbasedonmultitimescalefluctuationaggregationattentionmechanismandcontrastivelearning AT xiangtingwang multistepphotovoltaicpowerforecastingbasedonmultitimescalefluctuationaggregationattentionmechanismandcontrastivelearning AT yaosun multistepphotovoltaicpowerforecastingbasedonmultitimescalefluctuationaggregationattentionmechanismandcontrastivelearning AT xubinliu multistepphotovoltaicpowerforecastingbasedonmultitimescalefluctuationaggregationattentionmechanismandcontrastivelearning AT zhaoyangdong multistepphotovoltaicpowerforecastingbasedonmultitimescalefluctuationaggregationattentionmechanismandcontrastivelearning |