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 (i.e. consumption) 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 forecasting, in both a synthetic and a real framework considering the French mainland regions, and the performance and merits of our approach are discussed.

It is well know that Artificial Intelligence (AI) identifies in a broad sense the ability of a machine to learn from experience, to simulate the human intelligence, to adapt to new scenarios, and to get engaged in human-like activities. AI identifies an interdisciplinary area which includes computer science, robotics, engineering, mathematics. Over the years, it has made a rapid progress: it will contribute to the society transformation through the adoption of innovating technologies and creative intelligence and the large-scale implementation of AI in technologies such as IoT, smart speakers, chat-bots, cybersecurity, 3D printing, drones, face emotions analysis, sentiment analysis, natural language processing, and their applications to human resources, marketing, finance, and many others. With the term Machine learning (ML), instead, we identify a branch of AI in which algorithms are used to learn from data to make future decisions or predictions. ML algorithms are trained on past data in order to make future predictions or to support the decision making process. Deep Learning (DL), instead, is a subset of ML and it includes a large family of ML methods and architectures based on Artificial Neural Networks (ANNs). It includes Deep Neural Networks, Deep Belief Networks, Deep Reinforcement Learning, Recurrent Neural Networks and Convolutional Neural Networks, to mention a few of them. DL algorithms have been used in several applications including computer vision, speech recognition, natural language processing, bioinformatics, medical image analysis, and in most of these areas they have demonstrated to perform better than humans. In the recent years DL has disrupted every application domain and it provides a robust, generalized, and scalable approach to work with different data types, including time-series data [1-4].