Hierarchical GA–LP Framework with Explainable AI and Clustering for Generating and Interpreting Diverse Feasible Solutions in Net-Zero Energy Systems: An Illustrative Case Study

The transition to net-zero energy systems involves substantial uncertainty in exogenous conditions such as policy, fuel prices, and technology deployment. Conventional energy system optimization models, formulated as forward problems, excel at identifying a single least-cost solution but provide limited insight into the diverse configurations feasible within an acceptable cost range. This study proposes a hierarchical inverse-analysis framework integrating a genetic algorithm (GA) and linear programming (LP). The upper-level GA explores a broad space of exogenous conditions, including policy conditions, fuel prices, end-use electrification rates, and CO2 capture rates, while the lower-level LP rigorously optimizes operations for each candidate. The framework applies explainable AI (SHAP) to identify dominant cost-determining factors and their interactions, and employs k-means clustering to compress the high-dimensional feasible solution space into representative scenarios. As an illustrative demonstration, the framework is applied to a hypothetical 2050 net-zero case for the Kanto region. The results confirm diverse solution generation, identification of dominant factors, and extraction of five representative scenarios, enabling systematic distinction between common and variable elements characterizing net-zero pathways. The proposed framework extends energy system modeling beyond single-optimum solutions toward interpretable decision-support analytics for long-term net-zero planning under deep uncertainty.