Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers
Energy aggregation service providers in the electricity market are highly dependent on the load-forecasting accuracy to maximize their market interests. However，the required forecasting data are typically scattered among different energy suppliers，and owing to data security and privacy concerns，thes...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Electric Power Construction
2025-01-01
|
| Series: | Dianli jianshe |
| Subjects: | |
| Online Access: | https://www.cepc.com.cn/fileup/1000-7229/PDF/1735120370258-1686418971.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861297124474880 |
|---|---|
| author | HUANG Yichuan, SONG Yuhui, JING Zhaoxia |
| author_facet | HUANG Yichuan, SONG Yuhui, JING Zhaoxia |
| author_sort | HUANG Yichuan, SONG Yuhui, JING Zhaoxia |
| collection | DOAJ |
| description | Energy aggregation service providers in the electricity market are highly dependent on the load-forecasting accuracy to maximize their market interests. However，the required forecasting data are typically scattered among different energy suppliers，and owing to data security and privacy concerns，these suppliers are often unwilling to share their data. Inaccurate load forecasting reduces the operational efficiency of energy aggregation service providers and limits the in-depth understanding of supplier operating models. To address this issue，this study proposes a load-forecasting model based on federated learning，which achieves an effective improvement in load-forecasting accuracy while ensuring data security and privacy. First，an artificial neural network with multidimensional environmental feature selection is established according to the task requirements. Subsequently，a weighted-average strategy was used to jointly train the artificial neural network，bridging the gap between individual energy entities and environmental features. Finally，the model features trained separately are sent to the server of the energy-aggregation service provider for the fitting process. The results of a case analysis using actual data from a large energy aggregation service provider in a southern city in China demonstrate that the proposed model significantly improves operational efficiency and forecasting accuracy. |
| format | Article |
| id | doaj-art-e8260ffaa95a4bdca2cb48fa6dbbf7ce |
| institution | Kabale University |
| issn | 1000-7229 |
| language | zho |
| publishDate | 2025-01-01 |
| publisher | Editorial Department of Electric Power Construction |
| record_format | Article |
| series | Dianli jianshe |
| spelling | doaj-art-e8260ffaa95a4bdca2cb48fa6dbbf7ce2025-02-10T02:35:53ZzhoEditorial Department of Electric Power ConstructionDianli jianshe1000-72292025-01-01461374710.12204/j.issn.1000-7229.2025.01.004Federated Learning-Based Load Forecasting for Energy Aggregation Service ProvidersHUANG Yichuan, SONG Yuhui, JING Zhaoxia0School of Electric Power Engineering，South China University of Technology，Guangzhou 510641，ChinaEnergy aggregation service providers in the electricity market are highly dependent on the load-forecasting accuracy to maximize their market interests. However，the required forecasting data are typically scattered among different energy suppliers，and owing to data security and privacy concerns，these suppliers are often unwilling to share their data. Inaccurate load forecasting reduces the operational efficiency of energy aggregation service providers and limits the in-depth understanding of supplier operating models. To address this issue，this study proposes a load-forecasting model based on federated learning，which achieves an effective improvement in load-forecasting accuracy while ensuring data security and privacy. First，an artificial neural network with multidimensional environmental feature selection is established according to the task requirements. Subsequently，a weighted-average strategy was used to jointly train the artificial neural network，bridging the gap between individual energy entities and environmental features. Finally，the model features trained separately are sent to the server of the energy-aggregation service provider for the fitting process. The results of a case analysis using actual data from a large energy aggregation service provider in a southern city in China demonstrate that the proposed model significantly improves operational efficiency and forecasting accuracy.https://www.cepc.com.cn/fileup/1000-7229/PDF/1735120370258-1686418971.pdfenergy aggregation service provider|load forecasting|federated learning|data privacy|neural network |
| spellingShingle | HUANG Yichuan, SONG Yuhui, JING Zhaoxia Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers Dianli jianshe energy aggregation service provider|load forecasting|federated learning|data privacy|neural network |
| title | Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers |
| title_full | Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers |
| title_fullStr | Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers |
| title_full_unstemmed | Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers |
| title_short | Federated Learning-Based Load Forecasting for Energy Aggregation Service Providers |
| title_sort | federated learning based load forecasting for energy aggregation service providers |
| topic | energy aggregation service provider|load forecasting|federated learning|data privacy|neural network |
| url | https://www.cepc.com.cn/fileup/1000-7229/PDF/1735120370258-1686418971.pdf |
| work_keys_str_mv | AT huangyichuansongyuhuijingzhaoxia federatedlearningbasedloadforecastingforenergyaggregationserviceproviders |