A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy
Accurate load forecasting serves as the core foundation for grid planning and operations. Traditional load forecasting methods often rely solely on historical load data from a single region for training, making the models region-specific and leading to significant accuracy degradation when applied t...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10857325/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206996102545408 |
|---|---|
| author | Jinsong Deng Shaotang Cai Weinong Wu Rong Jiang Hongyu Deng Jinhua Ma Yonghang Luo |
| author_facet | Jinsong Deng Shaotang Cai Weinong Wu Rong Jiang Hongyu Deng Jinhua Ma Yonghang Luo |
| author_sort | Jinsong Deng |
| collection | DOAJ |
| description | Accurate load forecasting serves as the core foundation for grid planning and operations. Traditional load forecasting methods often rely solely on historical load data from a single region for training, making the models region-specific and leading to significant accuracy degradation when applied to other regions. This limits the generalization ability of these models to cross-regional load forecasting tasks. To address this issue, this study proposed a collaborative training strategy based on pseudo-distributed federated learning. Inspired by the pseudo-distributed concept, this strategy builds multiple sub-models by serially training load datasets from different regions on the same server. After a certain number of local epochs for each sub-model, parameter aggregation was performed. The aggregated parameters are then updated into each sub-model, and this process is repeated during each global epoch until the model converges, ultimately forming a global model capable of forecasting loads across multiple regions. Experiments demonstrated that this strategy exhibited exceptional generalization ability across various deep learning models, federated learning methods, and datasets. |
| format | Article |
| id | doaj-art-01ef972b9527472a8effc6a6cadffc1e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-01ef972b9527472a8effc6a6cadffc1e2025-02-07T00:01:18ZengIEEEIEEE Access2169-35362025-01-0113224462245810.1109/ACCESS.2025.353609710857325A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning StrategyJinsong Deng0Shaotang Cai1Weinong Wu2Rong Jiang3Hongyu Deng4Jinhua Ma5Yonghang Luo6https://orcid.org/0009-0003-0245-2959Qijiang Power Supply Branch, State Grid Chongqing Electric Power Company, Qijiang, Chongqing, ChinaInformation and Communication Branch, State Grid Chongqing Electric Power Company, Yubei, Chongqing, ChinaInformation and Communication Branch, State Grid Chongqing Electric Power Company, Yubei, Chongqing, ChinaInformation and Communication Branch, State Grid Chongqing Electric Power Company, Yubei, Chongqing, ChinaInformation and Communication Branch, State Grid Chongqing Electric Power Company, Yubei, Chongqing, ChinaInformation and Communication Branch, State Grid Chongqing Electric Power Company, Yubei, Chongqing, ChinaCollege of Computer and Information Science, Chongqing Normal University, Shapingba, Chongqing, ChinaAccurate load forecasting serves as the core foundation for grid planning and operations. Traditional load forecasting methods often rely solely on historical load data from a single region for training, making the models region-specific and leading to significant accuracy degradation when applied to other regions. This limits the generalization ability of these models to cross-regional load forecasting tasks. To address this issue, this study proposed a collaborative training strategy based on pseudo-distributed federated learning. Inspired by the pseudo-distributed concept, this strategy builds multiple sub-models by serially training load datasets from different regions on the same server. After a certain number of local epochs for each sub-model, parameter aggregation was performed. The aggregated parameters are then updated into each sub-model, and this process is repeated during each global epoch until the model converges, ultimately forming a global model capable of forecasting loads across multiple regions. Experiments demonstrated that this strategy exhibited exceptional generalization ability across various deep learning models, federated learning methods, and datasets.https://ieeexplore.ieee.org/document/10857325/Load forecastingfederated learningpseudo-distributed |
| spellingShingle | Jinsong Deng Shaotang Cai Weinong Wu Rong Jiang Hongyu Deng Jinhua Ma Yonghang Luo A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy IEEE Access Load forecasting federated learning pseudo-distributed |
| title | A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy |
| title_full | A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy |
| title_fullStr | A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy |
| title_full_unstemmed | A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy |
| title_short | A Cross-Regional Load Forecasting Method Based on a Pseudo-Distributed Federated Learning Strategy |
| title_sort | cross regional load forecasting method based on a pseudo distributed federated learning strategy |
| topic | Load forecasting federated learning pseudo-distributed |
| url | https://ieeexplore.ieee.org/document/10857325/ |
| work_keys_str_mv | AT jinsongdeng acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT shaotangcai acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT weinongwu acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT rongjiang acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT hongyudeng acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT jinhuama acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT yonghangluo acrossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT jinsongdeng crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT shaotangcai crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT weinongwu crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT rongjiang crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT hongyudeng crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT jinhuama crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy AT yonghangluo crossregionalloadforecastingmethodbasedonapseudodistributedfederatedlearningstrategy |