Performance-oriented investment decision for small modular reactors with renewable energy systems using intelligent molecular fuzzy genetic algorithms

The integration of small modular reactors (SMRs) with renewable energy systems provides some advantages, such as low cost and safe energy production. Identifying the most essential determinants helps businesses use their limited resources more effectively. However, in the literature, the numbers of these studies are quite limited. Hence, there is a need for more studies in the literature on how this integration can be optimized. This study develops an innovative decision-making model using molecular fuzzy genetic algorithms and q-learning to optimize performance-oriented investment strategies for SMRs and renewable energy integration. The study addresses gaps in the literature by providing a comprehensive framework for integrating SMRs and renewable energy. This situation contributes to long-term sustainability and economic efficiency. The study introduces a novel and integrated methodology by combining molecular fuzzy sets with genetic algorithms and Q-learning. Unlike traditional fuzzy models, the proposed approach enables dynamic, precise, and learning-based evaluation of investment criteria under uncertainty. The results show that thermal energy utilization (weight = .379) is the most critical criterion, followed by fuel cycle efficiency (.260), load-following flexibility (.189), and energy storage capacity (.171). • Small-scale nuclear reactors and renewable energy integration is analyzed. • This issue contributes to long-term sustainability and economic efficiency. • Energy utilization is the most critical criterion. • Fuel cycle efficiency plays also a key role.