Abstract: In order to further improve the reliability of active distribution network, the fault recovery strategy of active distribution network based on adaptive gray wolf algorithm is proposed, aiming at the problems of prematurity, large computation and low computation efficiency of traditional fault recovery algorithms. By introducing an adaptive convergence factor, this method solves the problem of local optimization, enlarges population diversity, and improves global convergence ability. It is proved that the proposed method is suitable for the fault recovery model of active distribution network, and can effectively improve the node voltage and reduce the active power loss.