Given the increase of distributed power supply in the power distribution network, and considering the influence of its volatility and intermittent nature on grid stability and safety, this paper puts forward a reconfiguration strategy for an active distribution network with a distributed power supply. Taking the minimum network loss as the objective function, an improved teaching and learning optimization algorithm is applied for fast optimization of power supply paths in active distributed networks. The active distribution network with distributed power supply is analyzed using an example. It verifies the superiority of the improved algorithm in the reconstruction of the distribution network. The results show that the method has fast convergence, short optimization time and stable operation. The research provides a reference for the optimization of a distributed power supply connected to the distribution network in China. This work is supported by National Natural Science Foundation of China (No. 51477184) and Science and Technology Project of Jiangxi Provincial Government (No. 20192BBE50007).