BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer
This study addresses the challenges in short-term electrical bus load forecasting. We propose a novel BLformer framework based on an enhanced Patch-TSTransformer. The framework quantifies the importance of temporal features across three load types and filters key input dimensions to reduce redundant...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2025.1622991/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850233911264673792 |
|---|---|
| author | Hui Liu Qian Chen Di Zhang Haiyun Wang Xinchen Zhao Zaichi Zhang Lei Fu Wei Wang Sizhuang Chen |
| author_facet | Hui Liu Qian Chen Di Zhang Haiyun Wang Xinchen Zhao Zaichi Zhang Lei Fu Wei Wang Sizhuang Chen |
| author_sort | Hui Liu |
| collection | DOAJ |
| description | This study addresses the challenges in short-term electrical bus load forecasting. We propose a novel BLformer framework based on an enhanced Patch-TSTransformer. The framework quantifies the importance of temporal features across three load types and filters key input dimensions to reduce redundant information interference. A sparse attention mechanism is designed to dynamically allocate computational resources, balancing efficiency and robustness. Innovatively, we integrate DCNN into the Patch-TST module, combining the advantages of local feature extraction and global temporal modeling to enhance the learning capability of time-frequency coupling characteristics. Furthermore, a coupled prediction strategy is developed to explore high-accuracy bus load forecasting models that incorporate multiple heterogeneous loads. Experiments demonstrate that BLformer significantly outperforms baseline models in terms of RMSE and MAPE metrics. Notably, the indirect prediction strategy substantially reduces errors compared to direct prediction, validating its effective learning ability for multi-load characteristics. |
| format | Article |
| id | doaj-art-5115602dda3d43dbba576462cfe6723d |
| institution | OA Journals |
| issn | 2296-598X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj-art-5115602dda3d43dbba576462cfe6723d2025-08-20T02:02:47ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2025-06-011310.3389/fenrg.2025.16229911622991BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformerHui Liu0Qian Chen1Di Zhang2Haiyun Wang3Xinchen Zhao4Zaichi Zhang5Lei Fu6Wei Wang7Sizhuang Chen8State Grid Beijing Electric Power Company, Beijing, ChinaState Grid Beijing Electric Power Research Institute, Beijing, ChinaState Grid Beijing Electric Power Company, Beijing, ChinaState Grid Beijing Electric Power Research Institute, Beijing, ChinaState Grid Beijing Electric Power Company, Beijing, ChinaState Grid Beijing Electric Power Research Institute, Beijing, ChinaState Grid Beijing Electric Power Company, Beijing, ChinaState Grid Beijing Electric Power Research Institute, Beijing, ChinaBeijing Tsingsoft Technology Co., Ltd., Beijing, ChinaThis study addresses the challenges in short-term electrical bus load forecasting. We propose a novel BLformer framework based on an enhanced Patch-TSTransformer. The framework quantifies the importance of temporal features across three load types and filters key input dimensions to reduce redundant information interference. A sparse attention mechanism is designed to dynamically allocate computational resources, balancing efficiency and robustness. Innovatively, we integrate DCNN into the Patch-TST module, combining the advantages of local feature extraction and global temporal modeling to enhance the learning capability of time-frequency coupling characteristics. Furthermore, a coupled prediction strategy is developed to explore high-accuracy bus load forecasting models that incorporate multiple heterogeneous loads. Experiments demonstrate that BLformer significantly outperforms baseline models in terms of RMSE and MAPE metrics. Notably, the indirect prediction strategy substantially reduces errors compared to direct prediction, validating its effective learning ability for multi-load characteristics.https://www.frontiersin.org/articles/10.3389/fenrg.2025.1622991/fullelectrical bus load forecastingPatch-Tstransformersparse attentionDCNN fusionmulti-source load coupling |
| spellingShingle | Hui Liu Qian Chen Di Zhang Haiyun Wang Xinchen Zhao Zaichi Zhang Lei Fu Wei Wang Sizhuang Chen BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer Frontiers in Energy Research electrical bus load forecasting Patch-Tstransformer sparse attention DCNN fusion multi-source load coupling |
| title | BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer |
| title_full | BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer |
| title_fullStr | BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer |
| title_full_unstemmed | BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer |
| title_short | BLformer: a short-term electrical bus load forecasting method based on enhanced Patch-TSTransformer |
| title_sort | blformer a short term electrical bus load forecasting method based on enhanced patch tstransformer |
| topic | electrical bus load forecasting Patch-Tstransformer sparse attention DCNN fusion multi-source load coupling |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2025.1622991/full |
| work_keys_str_mv | AT huiliu blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT qianchen blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT dizhang blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT haiyunwang blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT xinchenzhao blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT zaichizhang blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT leifu blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT weiwang blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer AT sizhuangchen blformerashorttermelectricalbusloadforecastingmethodbasedonenhancedpatchtstransformer |