Aiming at the complexity of distribution network topology caused by various types of distributed power access in distribution network, this paper proposes an improved particle swarm optimization algorithm applied to distribution network reconfiguration, particle swarm optimization algorithm and cuckoo the bird algorithm is effectively combined and uses a two-layer population framework. In order to improve the global search ability of the particle swarm optimization algorithm, the median clustering algorithm is used to reorganize the underlying particle swarm, the particle swarm optimization algorithm is used to optimize the various small populations in the lower layer, and then send them to the upper layer, using the bucking algorithm for deep search. excellent.The simulation analysis of various cases is carried out by numerical examples to verify the superiority of the improved algorithm in distribution network reconstruction.The results show that the algorithm can effectively reduce the active network loss of the distribution network and improve the voltage level of each node.This study provides reference and reference for the development of distributed power access distribution network in China.