A multi-objective optimal scheduling method for integrated energy system based on Q-learning genetic algorithm

To solve the problem of low efficiency in multi-objective optimization of integrated energy systems (IES), this paper proposes a Q-Learning-based multi-objective memetic algorithm (Q-MOMA) for system optimization to improve the efficiency of multi-objective optimization of IES. Current IES multi-objective optimization faces several challenges, including balancing economic operating costs, carbon emissions and energy efficiency, which affects the system's overall performance. To solve this problem, the proposed model uses the global search ability of genetic algorithm to explore the vast solution space, and the adaptive learning ability of Q-learning algorithm to optimize the decision-making process, so that the model can accelerate convergence in complex multi-objective optimization problems.