Study on Load Prediction Based on the MPGA-BP Neural Network Model

In order to improve the accuracy of power load prediction with randomness and complexity, a new power load prediction method is constructed by using multiple group genetic algorithms (MPGA). By improving the genetic algorithm, using the traditional genetic algorithm to optimize the weights and threshold of neurons in BP neural network, improve the prediction accuracy of BP neural network, thus greatly improve the prediction performance of BP neural network, but at the same time, because the traditional genetic algorithm is easy to precocious, into the local optimal, so the choice on this method for improvement. By comparing the prediction error of genetic algorithm (Geneticalgorithm, GA) - BP neural network model and MPGA-BP neural network model, it is found that the prediction results of MPGA-BP neural network model are better than GA-BP and BP neural network model, which proves that the proposed method can better improve the accuracy of load prediction. The results show that the prediction performance of multiple genetic GA is better than GABP and BP methods.