Optimizing Vehicle-to-Vehicle (V2V) Charging in Electric Vehicles by Adaptive Q-learning Implication for Smart Tourism

This study investigates the utilisation of adaptive Q-learning to optimise Vehicle-to-Vehicle (V2V) charging among electric vehicles (EVs) in dynamic smart tourism destinations within developing nations. V2V charging presents a viable solution to extend the range of EVs and improve operational efficiency by enabling direct energy transfer between vehicles. However, refining this process in volatile and high-demand sectors requires complex decision-making to ensure both energy efficiency and system integrity. To address these issues, this research introduces an advanced adaptive Q-learning approach that evaluates the current state and adjusts learning parameters accordingly. A bespoke simulation environment was developed to model a fleet of EVs capable of charging one another, incorporating factors such as energy demand, state of charge, and geographical location. The simulation environment also considers real-world variables, such as the vehicles' state of charge, their spatial positioning, and variable energy demands. The reward function favours an even and efficient energy flow, ensuring compatibility with the specific needs of smart tourism destinations. The simulation results demonstrate that the adaptive Q-learning algorithm significantly outperforms rule-based methods, achieving a 20% increase in energy efficiency, a 25% improvement in the average state of charge (SOC), better transfer efficiency, and enhanced system robustness. These findings underscore the potential of adaptive Q-learning as a scalable and effective solution for intelligent energy management in V2V charging systems. Future research should explore its integration with real-time traffic and vehicle movement patterns to further enhance its applicability in smart tourism ecosystems.