This paper presents an implementation of the stochastic fractal search (SFS) algorithm to solve the distribution network reconfiguration (DNR) problem in the presence of distributed generations (DGs). The SFS is a meta-heuristic algorithm inspired by the fractal theory for solving optimization problems. For dealing with the formulated DNR problem, the loss sensitivity factor (LSF) was first used to determine the optimal location of DGs and SFS was then applied to find the best size of DGs and configuration of the network. The proposed SFS algorithm was tested on 33-bus, 69-bus, 84-bus, 119-bus, and 136-bus distribution networks with seven different scenarios. The results obtained from SFS were compared to those from other methods in the literature and the result comparison has showed that SFS obtained better solutions than other methods. Therefore, SFS can be a very favorable method for solving the reconfiguration problem considering the participation of DGs in distribution networks. © 2019 Ain Shams University