Power data quality inspection method based on improved particle swarm algorithm

Abstract

In order to effectively solve the shortcomings of particle swarm optimization algorithms that are easy to fall into local extremes and slow convergence speed and low accuracy in the later stage of evolution, an improved particle swarm optimization algorithm that integrates multiple strategies for power grid data quality exploration is proposed. By adopting a grouping control strategy, According to fitness value, the population is divided into superior solution group and inferior solution group. The superior solution group performs genetic crossover operation, the inferior solution group performs mutation operation, and the elite strategy is used to update the population, improve the particle learning mode, and make full use of the population information to improve The mean value of the population replaces the optimal position of the individual, and probabilistic control is introduced to control the probability of the algorithm entering the crossover and mutation operations. The simulation results of the test function show that the improved algorithm can effectively take into account the global exploration and local mining capabilities, and has fast convergence speed and solution The advantages of high accuracy and avoiding local optimal solutions.