Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging
Accurate load forecasting plays a crucial role in the optimal scheduling of electric vehicles’ (EVs) coordinated charging. Although many load forecasting methods have emerged in recent years, these methods face two significant challenges: effectively capturing the impact of special events on load an...
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/S0142061524005726 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595381267988480 |
|---|---|
| author | Shuhua Gao Yuanbin Liu Jing Wang Zhengfang Wang Xu Wenjun Renfeng Yue Ruipeng Cui Yong Liu Xuezhong Fan |
| author_facet | Shuhua Gao Yuanbin Liu Jing Wang Zhengfang Wang Xu Wenjun Renfeng Yue Ruipeng Cui Yong Liu Xuezhong Fan |
| author_sort | Shuhua Gao |
| collection | DOAJ |
| description | Accurate load forecasting plays a crucial role in the optimal scheduling of electric vehicles’ (EVs) coordinated charging. Although many load forecasting methods have emerged in recent years, these methods face two significant challenges: effectively capturing the impact of special events on load and requiring a substantial amount of historical data for model training. To better apply day-ahead load forecasting (DALF) to the optimal scheduling of EVs’ coordinated charging, we propose a Transformer-based network architecture combining transfer learning and multi-attention fusion. The core idea of this algorithm comprehensively considers the dependencies between special events, seasonality, and load through multi-attention fusion. Simultaneously, by introducing time series decomposition block (TSDBlock), the load data is decomposed into seasonal and trend components to effectively extract crucial information, enhancing the performance of load forecasting models. To address data scarcity issues, we introduce transfer learning, selecting the best-performing model on the target task as the source model to avoid negative transfer effects. Ultimately, the experimental results show that our proposed method achieves the best forecasting performance in the datasets in five different regions. Especially in the non-working days, its performance is outstanding. |
| format | Article |
| id | doaj-art-290ee7d60ef145dbaf5fad953db8bd8c |
| 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-290ee7d60ef145dbaf5fad953db8bd8c2025-01-19T06:23:49ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-03-01164110349Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated chargingShuhua Gao0Yuanbin Liu1Jing Wang2Zhengfang Wang3Xu Wenjun4Renfeng Yue5Ruipeng Cui6Yong Liu7Xuezhong Fan8School of Control Science and Engineering, Shandong University, Jinan, 250100, Shandong, ChinaResearch Institute of Multiple Agents and Embodied Intelligence, Peng Cheng Laboratory, Shenzhen, 518055, Guangdong, China; School of Control Science and Engineering, Shandong University, Jinan, 250100, Shandong, ChinaSchool of Control Science and Engineering, Shandong University, Jinan, 250100, Shandong, China; Corresponding authors.School of Control Science and Engineering, Shandong University, Jinan, 250100, Shandong, China; Corresponding authors.Research Institute of Multiple Agents and Embodied Intelligence, Peng Cheng Laboratory, Shenzhen, 518055, Guangdong, ChinaJinan Licheng District Power Supply Company, State Grid Shandong Electric Power Company, Jinan, 250100, Shandong, ChinaSchool of Control Science and Engineering, Shandong University, Jinan, 250100, Shandong, ChinaJinan Gaoxin Branch, Shandong Aipu Electric Equipment Co. LTD, Jinan, 250061, Shandong, ChinaJinan Gaoxin Branch, Shandong Aipu Electric Equipment Co. LTD, Jinan, 250061, Shandong, ChinaAccurate load forecasting plays a crucial role in the optimal scheduling of electric vehicles’ (EVs) coordinated charging. Although many load forecasting methods have emerged in recent years, these methods face two significant challenges: effectively capturing the impact of special events on load and requiring a substantial amount of historical data for model training. To better apply day-ahead load forecasting (DALF) to the optimal scheduling of EVs’ coordinated charging, we propose a Transformer-based network architecture combining transfer learning and multi-attention fusion. The core idea of this algorithm comprehensively considers the dependencies between special events, seasonality, and load through multi-attention fusion. Simultaneously, by introducing time series decomposition block (TSDBlock), the load data is decomposed into seasonal and trend components to effectively extract crucial information, enhancing the performance of load forecasting models. To address data scarcity issues, we introduce transfer learning, selecting the best-performing model on the target task as the source model to avoid negative transfer effects. Ultimately, the experimental results show that our proposed method achieves the best forecasting performance in the datasets in five different regions. Especially in the non-working days, its performance is outstanding.http://www.sciencedirect.com/science/article/pii/S0142061524005726Day-ahead load forecastingTransformerMulti-attention fusionTime series decompositionTransfer learningCoordinated charging |
| spellingShingle | Shuhua Gao Yuanbin Liu Jing Wang Zhengfang Wang Xu Wenjun Renfeng Yue Ruipeng Cui Yong Liu Xuezhong Fan Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging International Journal of Electrical Power & Energy Systems Day-ahead load forecasting Transformer Multi-attention fusion Time series decomposition Transfer learning Coordinated charging |
| title | Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging |
| title_full | Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging |
| title_fullStr | Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging |
| title_full_unstemmed | Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging |
| title_short | Short-term residential load forecasting via transfer learning and multi-attention fusion for EVs’ coordinated charging |
| title_sort | short term residential load forecasting via transfer learning and multi attention fusion for evs coordinated charging |
| topic | Day-ahead load forecasting Transformer Multi-attention fusion Time series decomposition Transfer learning Coordinated charging |
| url | http://www.sciencedirect.com/science/article/pii/S0142061524005726 |
| work_keys_str_mv | AT shuhuagao shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT yuanbinliu shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT jingwang shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT zhengfangwang shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT xuwenjun shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT renfengyue shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT ruipengcui shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT yongliu shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging AT xuezhongfan shorttermresidentialloadforecastingviatransferlearningandmultiattentionfusionforevscoordinatedcharging |