Construction of Neural Network Fuzzy Control System of Smart grid based on Genetic Algorithm

Abstract

The genetic algorithm has a good ability of self-learning, self-adaptation and generalization. At the same time, the choice of the number of grid nodes in the hidden layer affects the effect of smart grid control. In this paper, based on the empirical formula, the number of grid nodes of genetic algorithm is reduced, and the number of grid nodes of optimal genetic algorithm is searched in a small range. According to the characteristics of the global optimization of genetic algorithms, using genetic algorithm to optimize the initial threshold of training can avoid the problem of the genetic algorithm falling into the local minimum. In the neural network fuzzy control of the smart grid, the example analysis shows that this method can accurately and effectively construct the neural network fuzzy control system.