Dynamic decision-making algorithm for remote fee control based on reinforcement learning and game theory

The increasing complexity of remote fee control systems in energy management demands advanced decision-making algorithms that adapt to dynamic and competitive environments. This paper proposes a novel dynamic decision-making algorithm that integrates reinforcement learning (RL) and game theory to optimize remote fee control strategies. Reinforcement learning is employed to enable adaptive policy generation based on real-time feedback, while game-theoretic principles model interactions between multiple decision-making agents, such as energy providers and consumers. The proposed algorithm incorporates a multi-agent framework and a Nash equilibrium-based solution to ensure optimal and stable strategies. Experimental results demonstrate that the algorithm achieves higher efficiency and adaptability compared to traditional approaches, reducing operational costs and improving system reliability. This study provides a scalable and robust decision-making framework for modern energy systems, paving the way for innovative applications in energy management and control.