Abstract: Combining the study of multi-agent technology，coordinating strategies with PSO，a Multi-Agent Particle Swarm Optimization（MA-PSO） algorithm is presented to handle distribution network reconfiguration problem.It applies Von Neuman architecture of Particle Swarm Optimization algorithm to the composition of multi-agent system.An agent in MA-PSO represents a particle to PSO and a candidate solution to the optimization problem.In order to decrease fitness value quickly，agents compete and cooperate with their agent of neighboring area.Making use of these agent-agent interactions，MA-PSO realizes the purpose of minimizing the value of objective function.The rules of particle renovating reduce unfeasible solution in the process of particle renovating，which raises the algorithm efficiency greatly.The experiment results indicate the prominent efficiency and significant global optima searching performance of MS-PSO.