Strumenti digitali per lo sviluppo delle CER in contesti urbani

Digital tools for the development of CERs in urban contexts. The growing urgency to reduce greenhouse gas emissions and promote the transition to a sustainable energy system requires the development of innovative tools for the efficient management of renewable resources. In this context, renewable energy communities represent a strategic solution to promote self-production, self-consumption and energy sharing on a local scale. This paper proposes a methodological approach based on AI - Artificial Intelligence and ML - Machine Learning techniques for the automated design of energy systems dedicated to REC. The concept of an open tool is introduced, i.e. a platform designed to process data relating to buildings, consumption and territorial characteristics, in order to optimize the sizing of photovoltaic systems, storage systems and the estimation of CO2 emission reductions. Although the latter is presented as a conceptual model, the work describes and validates the main predictive algorithms that form its core, highlighting the high performance of LSTM - Long Short-Term Memory networks compared to other machine learning models. The results confirm the potential of the proposed approach in supporting urban energy planning and lay the foundations for the future development of an operational platform for the transition to smart and sustainable energy communities.