Short-term load forecasting based on wavelet transform and BP neural network

In order to improve the accuracy of short-term electric power load forecasting, we use DB wavelet and the BP neural network method for short-term power load forecasting. Firstly, the load sequence was decomposed into different sub-sequences by using the wavelet transform, high-frequency son sequence and low frequency son sequence Then, these sub-sequences were forecasted by neural networks .Finally, the load forecasting sequence was obtained by the reconstruction of the forecasted results from the sub-sequences. In the example we use hebei baoding area ´s historical load data, and we compare the algorithm with BP neural network method. The simulation results show that the proposed method possesses high forecasting accuracy.