Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production

Abstract

In recent years, there has been a growing demand for renewable energy sources, which are inherently associated with a decentralized distribution and dependent on weather conditions. Their management and associated forecasting of produced energy are tasks of increasing complexity. Spatio-Temporal Graph Neural Networks have been applied in this context with excellent results, taking advantage of the correct integration of both topological data, defined by the distribution of the plants in the territory, and temporal data of the time series. A drawback of graph neural networks is the recurrent mechanism adopted to process the temporal part, which increases greatly the computational load of these models. Moreover, these models are formulated for real and sensitive contexts where, in addition to being accurate, the predictions must also be understandable by the human operator. For these reasons, in this paper we propose a novel explainable energy forecasting framework based on Spatio-Temporal Graph Neural Networks: the forecasting model generates predictions by processing temporal and spatial information using a spectral graph convolution and a 1D convolutional neural network respectively, then we apply a state-of-the-art explainer to them in order to produce explanations about the generation process. Our proposed method obtains predictions having better performance than previous approaches, both in terms of computational efficiency and prediction accuracy, with the possibility of interpreting them in order to understand the generation process. The novel approach based on fusion of forecasting and explainability in a single framework enables the creation of powerful and reliable systems suitable for real-world issues and challenges.