An ANN and wavelet transformation based method for short term load forecast

A new method for short term load forecast based on an artificial neural network (ANN) and wavelet transformation is presented in this paper. The load series is mapped onto some sub-series with wavelet transformation and then the sub-series are forecast by ANN. Weather factors are taken into account in forecasting. After all sub-series of load series are forecast, the whole predicted load series can be composed or reconstructed. In addition, a new BP algorithm is proposed to speed up the training process and improve the convergence of the ANN. All experimental results show the correctness of the principles proposed and the feasibility of the algorithm.