期刊
APPLIED ENERGY
卷 326, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.apenergy.2022.119915
关键词
Deep neural networks; Differential privacy; Federated learning; Secure aggregation; Privacy-preserving federated learning; Short-term load forecasting
资金
- European Union (EU) [814654]
- Kopernikus-project Syn-Ergie of the German Federal Ministry of Education and Research (BMBF)
- PayPal
- Luxembourg National Research Fund FNR [P17/IS/13342933]
- Luxembourg National Research Fund (FNR) -FiReSpARX Project [14783405]
- H2020 Societal Challenges Programme [814654] Funding Source: H2020 Societal Challenges Programme
This paper investigates the challenges of using smart meter data for load forecasting and proposes a solution using a combination of federated learning and privacy preserving techniques. The results show that this combination can achieve high forecasting accuracy and near-complete privacy protection.
With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these forecasts as they provide detailed load data. However, using smart meter data for load forecasting is challenging due to data privacy requirements. This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation. For our analysis, we employ a large set of residential load data and simulate how different federated learning models and privacy preserving techniques affect performance and privacy. Our simulations reveal that combining federated learning and privacy preserving techniques can secure both high forecasting accuracy and near-complete privacy. Specifically, we find that such combinations enable a high level of information sharing while ensuring privacy of both the processed load data and forecasting models. Moreover, we identify and discuss challenges of applying federated learning, differential privacy and secure aggregation for residential short-term load forecasting.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据