Abstract:At present, the research of distribution network fault location mainly focuses on intelligent algorithms such as genetic algorithm. This paper focuses on the defects of conventional genetic algorithm in local convergence and optimization speed, and proposes an improved method. Based on the global optimization ability of genetic algorithm, the method introduces adaptive adjustment coefficient to optimize the parameters and comprehensively consider the population diversity level. On the basis of maintaining high convergence and optimization ability, the method enhances the global optimization ability and effectively avoids the local optimal solution. At the same time, the optimization speed of the algorithm is improved by selecting individuals during the mutation operation. The number of iterations is reduced, and the optimization efficiency is significantly improved. Finally, through the simulation of a 20-node distribution network fault location experiment, it is proved that the algorithm can complete accurate fault location under the condition of information integrity and information distortion, and the optimization effect is significantly better than the traditional algorithm, with good effectiveness and advantages.