Exploring of Related Issues of BP Algorithm in Load Forecasting

In this paper, the establishment of the neural network model of forecasting short-term power load in an electric power grid is studied. Basing on the model, the BP algorithm for power load is explored. The research on BP network model includes determining the hidden layer number, hidden layer nodes number, training frequency and accuracy of learning rate. In this paper, we focus on that how to give initial weights, select training sample method of normalizing sample and so on. With more further qualitative and quantitative analysis, and through an actual example as comparative test, we have got useful conclusions.