Probabilistic Solar Irradiation Forecasting Based on Variational Bayesian Inference With Secure Federated Learning

Abstract

The irradiation forecasting technology is important for the effective utilization of solar power. Existing irradiation forecasting methods have achieved excellent performance with a massive amount of data in a centralized way. However, concerns about privacy protection and data security, which may arise in the process of data collection and transmission from distributed points to the centralized server, pose challenges to current forecasting methods. In this article, a novel federated probabilistic forecasting scheme of solar irradiation is proposed based on deep learning, variational Bayesian inference, and federated learning (FL). In this scheme, the training data are stored and computed in local Internet of Things devices, only forecasting models are shared. Two real-world datasets from SolarGIS and National Solar Radiation Database, and one benchmark dataset of Folsom are used to verify the feasibility and performance of the federated-based scheme. Comprehensive case studies are conducted to analyze the performance of the proposed scheme in multihorizon. And the effects of using meteorological features and variational Bayesian inference are evaluated. Compared with other state-of-the-art probabilistic centralized models, when data can be shared, the proposed scheme achieves competitive forecasting performance on the basis of data privacy protection. When data sharing is unavailable, due to the cooperative nature inherent (model-sharing) of FL, the performance advantage of the proposed scheme is more obvious.