Due to the large number of distributed power sources, the calculation and regulation conditions of the loop closing current of the distribution network have changed, and the traditional regulation methods such as adjusting transformer tap, capacitor and load can no longer meet the needs of complex loop closing scenarios in the new environment. In this paper, the distributed power supply is used as the regulation means, and the fuzzy C-means clustering algorithm is improved by the time period function, evaluation function and fusion of the regulation period to divide the loop closing time period and select the optimal loop closing time in advance. At the same time, with the goal of minimizing the network loss and equipment action loss, a loop closing regulation model considering the risk of loop closing operation was established, and an improved multi-objective particle swarm optimization algorithm was used to solve the model. Finally, the effectiveness of the proposed method was verified by an example analysis.