Abstract
This study examines queuing dynamics in peer-to-peer energy trading systems by integrating Q-learning assessment with hybrid molecular fuzzy modeling. Using large expert datasets, the framework evaluates decision-making strategies that influence energy allocation, efficiency, and market stability. The approach captures the interplay between adaptive learning and uncertainty, offering insights into how decentralized participants manage trading behavior under varying demand and supply conditions. Results demonstrate that the proposed modeling system effectively identifies patterns of cooperation, competition, and equilibrium formation in blockchain-enabled trading environments. By framing queuing as both a technical and behavioral process, the analysis connects individual choices with system-level performance. Beyond methodological contributions, the findings underscore the relevance of intelligent computational tools for addressing challenges in sustainable energy distribution. This work highlights the broader significance of combining artificial intelligence, fuzzy systems, and decentralized market mechanisms to advance resilient and efficient resource management.