To address the bottleneck issues in achieving green and efficient operation of municipal solid waste incineration (MSWI) processes, this paper proposes an intelligent operational optimization method for MSWI based on a niching differential evolution algorithm, aiming to simultaneously improve combustion efficiency and reduce flue gas pollutant emissions. First, an operational index evaluation model based on a multi-module neural network is developed to enable online assessment of both combustion efficiency and pollutant emission concentrations during the incineration process. Then, a niching differential evolution algorithm is proposed: a fast density-based clustering algorithm is introduced to dynamically partition niches, thereby enhancing population diversity; different mutation strengths are assigned according to niche density differences to balance global exploration and local exploitation; and individuals are preferentially selected based on local entropy to obtain a high-quality set of globally optimal solutions. Subsequently, the entropy weight–TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method is employed to determine the optimal setpoints for furnace temperature and flue gas oxygen content. Finally, the effectiveness and feasibility of the proposed method are validated using real-world operational data.