Leveraging Graph Neural Networks to Forecast Electricity Consumption
Published in ECML PKDD 2024, Machine Learning for Sustainable Power Systems (ML4SPS) Workshop, 2024
Accurate electricity demand forecasting is essential for several reasons, especially as the integration of renewable energy sources and the transition to a decentralized network paradigm introduce greater complexity and uncertainty. The proposed methodology leverages graph-based representations to effectively capture the spatial distribution and relational intricacies inherent in this decentralized network structure. This research work offers a novel approach that extends beyond the conventional Generalized Additive Model framework by considering models like Graph Convolutional Networks or Graph SAGE. These graph-based models enable the incorporation of various levels of interconnectedness and information sharing among nodes, where each node corresponds to the combined load of a subset of consumers (e.g. the regions of a country). More specifically, we introduce a range of methods for inferring graphs tailored to consumption forecasting, along with a framework for evaluating the developed models in terms of both performance and explainability. We conduct experiments on electricity load forecasting, in both a synthetic and a real framework considering the French mainland regions, and the performance and merits of our approach are discussed.
Recommended citation: Campagne, E., Amara-Ouali, Y., Goude, Y., Kalogeratos, A. (2024). "Leveraging Graph Neural Networks to Forecast Electricity Consumption." In Proceedings of the Machine Learning for Sustainable Power Systems workshop at ECML PKDD 2024, Vilnius, Lithuania. https://arxiv.org/pdf/2408.17366