Méthodes avancées pour améliorer l'interprétabilité des outils d'IA avec application au secteur de l'énergie

Decision-making in energy systems traditionally relies on complex models integrating multiple uncertainties. The growing share of Renewable Energy Sources (RES) adds complexity due to weather dependence. While Artificial Intelligence (AI) tools improve forecasting, optimization, and decision-making, their lack of interpretability hinders adoption. This research enhances AI interpretability in energy applications by distinguishing between explainability methods and inherently interpretable models. It develops a symbolic AI approach for renewable energy bidding, applies rule-based models for grid adequacy forecasting, and utilizes Information Flow Fuzzy Cognitive Maps (IF-FCMs) to predict grid overloads. Additionally, it assesses AI regulations in the U.S., China, and Europe. The findings aim to improve trust, transparency, and regulatory compliance in energy AI applications.