Research On Medium-Term Electric Load Forecasting Model Based On Elman Neural Network

The load of power system is influenced by many factors, and they are variable and nonlinear. The relation between them is dynamic. It is impossible to forecast the load of power system accurately by traditional methods. According to the Elman neural network having the performance of reflecting the dynamic vividly and directly, medium-term load forecasting model of power system based on Elman neural network is established, and some prediction is done. On one hand, the prediction accuracy of Elman neural network with one layer, the one with two layers and the one with three layers is compared, and the experiments show that the Elman neural network with two layers is of good dynamic, quickly convergence speed and high forecasting precision. On the other hand, the prediction accuracy of Elman neural network and BP neural network is compared, the results show that the performance of the above model with three Elman neural network is superior to BP neural network. It is proved that Elman neural network is a new and reliable method for predicting the load of power system, which has a good prospect of application.