Abstract: In order to solve the problem that the traditional multi-objective particle swarm optimization（MOPSO） is easy to fall into the local optimal solution when solving the optimal scheduling model of microgrid in grid-connected mode, a linear differential decreasing weight is proposed and a mutation strategy is introduced to improve MOPSO to enhance the optimization ability of the algorithm.Combined with the constraints of system power balance, output limitation of each unit, energy storage device, etc., with the goal of minimizing the cost of system operation and maintenance and pollution control, a multi-objective optimal scheduling model of microgrid including wind turbine, photovoltaic, diesel generator, micro gas turbine and storage battery was established, and the improved MOPSO was used to solve the optimized model. The results show that the improved MOPSO proposed in this paper can effectively reduce the comprehensive cost of microgrid operation and reasonably optimize the operation efficiency of microgrid.