Power distribution network reactive power optimization method based on multi-objective fish swarm clustering algorithm

The invention relates to a power distribution network reactive power optimization method based on a multi-objective fish swarm clustering algorithm. The method comprises steps as follows: a, related grid raw data information is guided into a program, and the raw data information comprises power network static parameters of resistance and reactive resistance of a line in a grid structure as well as the maximum active load and the maximum reactive load of nodes all day long; b, load flow is calculated, and effective data sets of all grids are obtained; c, sensitivity data are subjected to clustering analysis through a k-means clustering algorithm, so that the range of a to-be-compensated point can be rapidly found out; d, two different objective fish swarms are called, two objective functions are optimized respectively, and the optimal solutions under different objective conditions are acquired; and e, concentration of foods for different objective fish swarms is mutually interchanged, and then, the step b is operated till multiple globally optimal solutions are obtained. According to the method, the optimization speed of the algorithm is increased, the system power loss can be effectively reduced, the voltage quality is improved, and the compensation capacity is reduced.