This article proposes a multi-objective optimal scheduling model for microgrids based on an improved particle swarm optimization (PSO) algorithm. The model aims to minimize both operational and environmental costs while enhancing the efficiency of microgrid operations. The improved PSO algorithm incorporates inertia factors and particle adaptive mutation to enhance convergence speed and accuracy. Simulation results show that the improved algorithm achieves a total cost of CNY 836.23, a reduction from the pre-improvement optimal value of CNY 850. The model considers various constraints, including power balance, operational requirements, and pollution emission control, and optimizes the scheduling of distributed power sources, energy storage systems, and micro gas turbines. The improved PSO algorithm outperforms traditional PSO in terms of convergence speed, accuracy, and global search capability. The study also compares the performance of different optimization strategies, including single-objective and multi-objective approaches, highlighting the benefits of multi-objective optimization in reducing both operational and environmental costs. The results demonstrate that the improved PSO algorithm is effective in optimizing microgrid scheduling and reducing energy consumption and pollution.This article proposes a multi-objective optimal scheduling model for microgrids based on an improved particle swarm optimization (PSO) algorithm. The model aims to minimize both operational and environmental costs while enhancing the efficiency of microgrid operations. The improved PSO algorithm incorporates inertia factors and particle adaptive mutation to enhance convergence speed and accuracy. Simulation results show that the improved algorithm achieves a total cost of CNY 836.23, a reduction from the pre-improvement optimal value of CNY 850. The model considers various constraints, including power balance, operational requirements, and pollution emission control, and optimizes the scheduling of distributed power sources, energy storage systems, and micro gas turbines. The improved PSO algorithm outperforms traditional PSO in terms of convergence speed, accuracy, and global search capability. The study also compares the performance of different optimization strategies, including single-objective and multi-objective approaches, highlighting the benefits of multi-objective optimization in reducing both operational and environmental costs. The results demonstrate that the improved PSO algorithm is effective in optimizing microgrid scheduling and reducing energy consumption and pollution.