A federated LSTM network for load forecasting using multi-source data with homomorphic encryption
Short-term load forecasting is of great significance to the operation of power systems. Various uncertain factors, such as meteorological social data, have already been combined with historical power data to create more accurate load forecasting models. In traditional systems, data from various indu...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2025-03-01
|
| Series: | AIMS Energy |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/energy.2025011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849730182019022848 |
|---|---|
| author | Mengdi Wang Rui Xin Mingrui Xia Zhifeng Zuo Yinyin Ge Pengfei Zhang Hongxing Ye |
| author_facet | Mengdi Wang Rui Xin Mingrui Xia Zhifeng Zuo Yinyin Ge Pengfei Zhang Hongxing Ye |
| author_sort | Mengdi Wang |
| collection | DOAJ |
| description | Short-term load forecasting is of great significance to the operation of power systems. Various uncertain factors, such as meteorological social data, have already been combined with historical power data to create more accurate load forecasting models. In traditional systems, data from various industries and regions are centralized for knowledge extraction. However, concerns regarding data security and privacy often prevent industries from sharing their data, limiting both the quantity and diversity of data available for forecasting models. These challenges drive the adoption of federated learning (FL) to address issues related to data silos and privacy. In this paper, a novel framework for short-term load forecasting was proposed using historical data from industries such as power, meteorology, and finance. Long short-term memory (LSTM) networks were utilized for forecasting, and federated learning (FL) was implemented to protect data privacy. FL allows clients in multiple regions to collaboratively train a shared model without exposing their data. To further enhance security, the homomorphic encryption (HE) using Paillier algorithm was introduced during the federated process. Experimental results demonstrate that the federated model, which extracts knowledge from different regions, outperforms locally trained models. Furthermore, longer HE keys have little effect on predictive performance but significantly slow down encryption and decryption, thereby increasing training time. |
| format | Article |
| id | doaj-art-77266cfd2ca84882935299b898f76314 |
| institution | DOAJ |
| issn | 2333-8334 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Energy |
| spelling | doaj-art-77266cfd2ca84882935299b898f763142025-08-20T03:08:57ZengAIMS PressAIMS Energy2333-83342025-03-0113226528910.3934/energy.2025011A federated LSTM network for load forecasting using multi-source data with homomorphic encryptionMengdi Wang0Rui Xin1Mingrui Xia2Zhifeng Zuo3Yinyin Ge4Pengfei Zhang5Hongxing Ye6State Grid Hebei Electric Power Co., Ltd. Information and Communication Branch, Zhongtong City Square, Qiaoxi District, Shijiazhuang City, Hebei Province, ChinaState Grid Hebei Electric Power Co., Ltd. Information and Communication Branch, Zhongtong City Square, Qiaoxi District, Shijiazhuang City, Hebei Province, ChinaXi'an Jiaotong University, No. 28, Xianning West Road Xi'an, Shaanxi Province, ChinaXi'an Jiaotong University, No. 28, Xianning West Road Xi'an, Shaanxi Province, ChinaXi'an Jiaotong University, No. 28, Xianning West Road Xi'an, Shaanxi Province, ChinaState Grid Hebei Electric Power Co., Ltd. Information and Communication Branch, Zhongtong City Square, Qiaoxi District, Shijiazhuang City, Hebei Province, ChinaXi'an Jiaotong University, No. 28, Xianning West Road Xi'an, Shaanxi Province, ChinaShort-term load forecasting is of great significance to the operation of power systems. Various uncertain factors, such as meteorological social data, have already been combined with historical power data to create more accurate load forecasting models. In traditional systems, data from various industries and regions are centralized for knowledge extraction. However, concerns regarding data security and privacy often prevent industries from sharing their data, limiting both the quantity and diversity of data available for forecasting models. These challenges drive the adoption of federated learning (FL) to address issues related to data silos and privacy. In this paper, a novel framework for short-term load forecasting was proposed using historical data from industries such as power, meteorology, and finance. Long short-term memory (LSTM) networks were utilized for forecasting, and federated learning (FL) was implemented to protect data privacy. FL allows clients in multiple regions to collaboratively train a shared model without exposing their data. To further enhance security, the homomorphic encryption (HE) using Paillier algorithm was introduced during the federated process. Experimental results demonstrate that the federated model, which extracts knowledge from different regions, outperforms locally trained models. Furthermore, longer HE keys have little effect on predictive performance but significantly slow down encryption and decryption, thereby increasing training time.https://www.aimspress.com/article/doi/10.3934/energy.2025011short-term load forecastingfederated learninglong short-term memoryhomomorphic encryptionsmart grid |
| spellingShingle | Mengdi Wang Rui Xin Mingrui Xia Zhifeng Zuo Yinyin Ge Pengfei Zhang Hongxing Ye A federated LSTM network for load forecasting using multi-source data with homomorphic encryption AIMS Energy short-term load forecasting federated learning long short-term memory homomorphic encryption smart grid |
| title | A federated LSTM network for load forecasting using multi-source data with homomorphic encryption |
| title_full | A federated LSTM network for load forecasting using multi-source data with homomorphic encryption |
| title_fullStr | A federated LSTM network for load forecasting using multi-source data with homomorphic encryption |
| title_full_unstemmed | A federated LSTM network for load forecasting using multi-source data with homomorphic encryption |
| title_short | A federated LSTM network for load forecasting using multi-source data with homomorphic encryption |
| title_sort | federated lstm network for load forecasting using multi source data with homomorphic encryption |
| topic | short-term load forecasting federated learning long short-term memory homomorphic encryption smart grid |
| url | https://www.aimspress.com/article/doi/10.3934/energy.2025011 |
| work_keys_str_mv | AT mengdiwang afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT ruixin afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT mingruixia afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT zhifengzuo afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT yinyinge afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT pengfeizhang afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT hongxingye afederatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT mengdiwang federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT ruixin federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT mingruixia federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT zhifengzuo federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT yinyinge federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT pengfeizhang federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption AT hongxingye federatedlstmnetworkforloadforecastingusingmultisourcedatawithhomomorphicencryption |