Ultra-Short-Term Distributed Photovoltaic Power Probabilistic Forecasting Method Based on Federated Learning and Joint Probability Distribution Modeling

• Published in: Energies (Basel) 2025-01, Vol.18 (1), p.197
• Main Authors: Wang, Yubo, Huo, Chao, Xu, Fei, Zheng, Libin, Hao, Ling
• Format: Article
• Language: English
• Subjects: Accuracy; Alternative energy sources; Data integrity; distributed photovoltaic; federated learning; Fossil fuels; joint probability distribution; Machine learning; Mining; Neural networks; Nonparametric statistics; Power plants; Privacy; spatiotemporal correlation; Statistical methods; ultra-short-term power forecasting; Weather forecasting
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en18010197

The accurate probabilistic forecasting of ultra-short-term power generation from distributed photovoltaic (DPV) systems is of great significance for optimizing electricity markets and managing energy on the user side. Existing methods regarding cluster information sharing tend to easily trigger issues of data privacy leakage during information sharing, or they suffer from insufficient information sharing while protecting data privacy, leading to suboptimal forecasting performance. To address these issues, this paper proposes a privacy-preserving deep federated learning method for the probabilistic forecasting of ultra-short-term power generation from DPV systems. Firstly, a collaborative feature federated learning framework is established. For the central server, information sharing among clients is realized through the interaction of global models and features while avoiding the direct interaction of raw data to ensure the security of client data privacy. For local clients, a Transformer autoencoder is used as the forecasting model to extract local temporal features, which are combined with global features to form spatiotemporal correlation features, thereby deeply exploring the spatiotemporal correlations between different power stations and improving the accuracy of forecasting. Subsequently, a joint probability distribution model of forecasting values and errors is constructed, and the distribution patterns of errors are finely studied based on the dependencies between data to enhance the accuracy of probabilistic forecasting. Finally, the effectiveness of the proposed method was validated through real datasets.