Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity
This work solves the challenge of unobservable PV generation for energy management and grid operations, but it is incremental as it builds on existing federated learning methods with personalization.
The paper tackles the problem of estimating behind-the-meter photovoltaic generation from net load, known as PV disaggregation, by proposing a privacy-preserving personalized federated learning framework that addresses statistical heterogeneity, resulting in improved accuracy and robustness compared to benchmarks.
The rapid expansion of distributed photovoltaic (PV) installations worldwide, many being behind-the-meter systems, has significantly challenged energy management and grid operations, as unobservable PV generation further complicates the supply-demand balance. Therefore, estimating this generation from net load, known as PV disaggregation, is critical. Given privacy concerns and the need for large training datasets, federated learning becomes a promising approach, but statistical heterogeneity, arising from geographical and behavioral variations among prosumers, poses new challenges to PV disaggregation. To overcome these challenges, a privacy-preserving distributed PV disaggregation framework is proposed using Personalized Federated Learning (PFL). The proposed method employs a two-level framework that combines local and global modeling. At the local level, a transformer-based PV disaggregation model is designed to generate solar irradiance embeddings for representing local PV conditions. A novel adaptive local aggregation mechanism is adopted to mitigate the impact of statistical heterogeneity on the local model, extracting a portion of global information that benefits the local model. At the global level, a central server aggregates information uploaded from multiple data centers, preserving privacy while enabling cross-center knowledge sharing. Experiments on real-world data demonstrate the effectiveness of this proposed framework, showing improved accuracy and robustness compared to benchmark methods.