Personalized Federated Learning for Heterogeneous Residential Load Forecasting
Accurate load forecasting is critical for electricity production, transmission, and maintenance. Deep learning (DL) model has replaced other classical models as the most popular prediction models. However, the deep prediction model requires users to provide a large amount of private electricity cons...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2023-12-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2022.9020043 |
| _version_ | 1797384841840295936 |
|---|---|
| author | Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui |
| author_facet | Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui |
| author_sort | Xiaodong Qu |
| collection | DOAJ |
| description | Accurate load forecasting is critical for electricity production, transmission, and maintenance. Deep learning (DL) model has replaced other classical models as the most popular prediction models. However, the deep prediction model requires users to provide a large amount of private electricity consumption data, which has potential privacy risks. Edge nodes can federally train a global model through aggregation using federated learning (FL). As a novel distributed machine learning (ML) technique, it only exchanges model parameters without sharing raw data. However, existing forecasting methods based on FL still face challenges from data heterogeneity and privacy disclosure. Accordingly, we propose a user-level load forecasting system based on personalized federated learning (PFL) to address these issues. The obtained personalized model outperforms the global model on local data. Further, we introduce a novel differential privacy (DP) algorithm in the proposed system to provide an additional privacy guarantee. Based on the principle of generative adversarial network (GAN), the algorithm achieves the balance between privacy and prediction accuracy throughout the game. We perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios. |
| first_indexed | 2024-03-08T21:45:28Z |
| format | Article |
| id | doaj.art-e96d12cc43804385bff4752aa540d08a |
| institution | Directory Open Access Journal |
| issn | 2096-0654 |
| language | English |
| last_indexed | 2024-03-08T21:45:28Z |
| publishDate | 2023-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj.art-e96d12cc43804385bff4752aa540d08a2023-12-20T09:32:32ZengTsinghua University PressBig Data Mining and Analytics2096-06542023-12-016442143210.26599/BDMA.2022.9020043Personalized Federated Learning for Heterogeneous Residential Load ForecastingXiaodong Qu0Chengcheng Guan1Gang Xie2Zhiyi Tian3Keshav Sood4Chaoli Sun5Lei Cui6Shanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaShanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaShanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaFaculty of Engineering and Information Technology, University of Technology Sydney, Ultimo 2007, AustraliaCentre for Cyber Security Research and Innovation, Deakin University, Melbourne 3125, AustraliaSchool of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaShanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaAccurate load forecasting is critical for electricity production, transmission, and maintenance. Deep learning (DL) model has replaced other classical models as the most popular prediction models. However, the deep prediction model requires users to provide a large amount of private electricity consumption data, which has potential privacy risks. Edge nodes can federally train a global model through aggregation using federated learning (FL). As a novel distributed machine learning (ML) technique, it only exchanges model parameters without sharing raw data. However, existing forecasting methods based on FL still face challenges from data heterogeneity and privacy disclosure. Accordingly, we propose a user-level load forecasting system based on personalized federated learning (PFL) to address these issues. The obtained personalized model outperforms the global model on local data. Further, we introduce a novel differential privacy (DP) algorithm in the proposed system to provide an additional privacy guarantee. Based on the principle of generative adversarial network (GAN), the algorithm achieves the balance between privacy and prediction accuracy throughout the game. We perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.https://www.sciopen.com/article/10.26599/BDMA.2022.9020043load forecastingpersonalized federated learningdifferential privacy |
| spellingShingle | Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui Personalized Federated Learning for Heterogeneous Residential Load Forecasting Big Data Mining and Analytics load forecasting personalized federated learning differential privacy |
| title | Personalized Federated Learning for Heterogeneous Residential Load Forecasting |
| title_full | Personalized Federated Learning for Heterogeneous Residential Load Forecasting |
| title_fullStr | Personalized Federated Learning for Heterogeneous Residential Load Forecasting |
| title_full_unstemmed | Personalized Federated Learning for Heterogeneous Residential Load Forecasting |
| title_short | Personalized Federated Learning for Heterogeneous Residential Load Forecasting |
| title_sort | personalized federated learning for heterogeneous residential load forecasting |
| topic | load forecasting personalized federated learning differential privacy |
| url | https://www.sciopen.com/article/10.26599/BDMA.2022.9020043 |
| work_keys_str_mv | AT xiaodongqu personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT chengchengguan personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT gangxie personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT zhiyitian personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT keshavsood personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT chaolisun personalizedfederatedlearningforheterogeneousresidentialloadforecasting AT leicui personalizedfederatedlearningforheterogeneousresidentialloadforecasting |