Privacy-preserving federated learning for residential short-term load forecasting. (15th November 2022)

• Record Type: Journal Article
• Authors: Fernández, Joaquín Delgado; Menci, Sergio Potenciano; Lee, Chul Min; Rieger, Alexander; Fridgen, Gilbert
• Is Part Of: Applied energy. Volume 326(2022)
• Publication Date: 2022-11-15
• Subjects: Deep neural networks -- Differential privacy -- Federated learning -- Secure aggregation -- Privacy-preserving federated learning -- Short-term load forecasting; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2022.119915
• Languages: English
• ISSNs: 0306-2619

Abstract

Abstract: 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. Highlights: The accuracy of federated learning varies with the number of households considered. Simple socio-economic clustering improves the accuracy of federated learning. The addition of privacy-preserving techniques leads to negligible drops in accuracy. Adaptive clipping outperforms fixed clipping for differential privacy. Secure aggregation has certain advantages over differential privacy.