In view of the volatility and randomness of distributed power sources in the distribution network, a self-healing optimization method of distribution network based on chaotic adaptive artificial fish swarm algorithm is proposed in this paper. Based on the mathematical modeling and node division of wind power, photovoltaics and household energy storage, with the minimum active power loss of the system as the objective function, a self-healing distribution network structure optimization model of distribution network including distributed generation and household energy storage is established. The chaotic adaptive artificial fish swarm algorithm is used to realize the optimization of the self-healing distribution network structure of distribution network through adaptively and dynamically adjusting the step parameters. According to the output characteristics of the household energy storage system, the self-healing distribution network structure is divided into two typical work scenarios. The effectiveness of the method proposed in this paper is verified by a simulation example of an IEEE33 node test system with distributed generation. The simulation results show that the method proposed in this paper provides a theoretical basis for the development of intelligent active distribution network and self-healing test technology.