An Improved NSGA-II–TOPSIS Integrated Framework for Multi-Objective Optimization of Electric Vehicle Charging Station Siting

Against the backdrop of global energy transition and carbon emission reduction, the scientific siting of electric vehicle (EV) charging stations has become a key issue constraining the sustainable development of the industry. To address the common shortcomings of existing research, such as single-objective bias and the tendency of traditional optimization algorithms to fall into local optima, this paper proposes a multi-objective siting optimization method that couples an improved NSGA-II algorithm with an improved TOPSIS model. First, a charging station location model is established with the dual objectives of minimizing total operator costs and maximizing user satisfaction, where user satisfaction comprehensively incorporates factors such as charging distance and queuing time. Second, at the algorithmic level, chaotic mapping, opposition-based learning, and adaptive crossover–mutation operators are introduced to enhance global search capability and solution diversity. Then, an improved entropy-weighted TOPSIS model is used to select the optimal compromise solution from the Pareto set, achieving objective weight determination and stabilized ranking outcomes. Finally, simulation experiments show that the proposed method outperforms the standard NSGA-II algorithm in both operating cost reduction and user satisfaction improvement, while also exhibiting superior performance in hypervolume (HV), inverted generational distance (IGD), and diversity metrics. The results verify that the integrated improved NSGA-II–TOPSIS framework provides an efficient, scientific, and interpretable decision-support tool for the planning of EV charging infrastructure.