Privacy-preserving federated learning for residential short-term load forecasting

TLDR

Accurate residential load forecasts are essential due to intermittent generation and dynamic demand, and smart meters provide detailed data, but privacy concerns hinder their use. The study aims to determine whether federated learning combined with differential privacy and secure aggregation can satisfy privacy requirements while enabling accurate load forecasting. The authors simulate various federated learning models on a large residential load dataset, applying differential privacy and secure aggregation to assess their impact on forecasting performance and privacy. Simulations show that federated learning with privacy‑preserving techniques achieves high forecasting accuracy while providing near‑complete privacy, enabling substantial information sharing without compromising data or model confidentiality.

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.