Using a Combined Method to Forecasting Electricity Demand

Abstract

In electric market, accurate electricity demand forecasting is often needed. Because electricity demand forecasting has become needful for creators and purchasers in the electric markets at present. But in electricity demand forecasting, noise signals, caused by various unstable factors, often corrupt demand series. In order to seek accurate demand forecasting methods, this article proposed a new combined electric load forecasting method (WSENN) which based on Wavelet Transform (WT), Seasonal Adjustment (SA) and Elman Neural Network (ENN) to forecast electricity demand. The effectiveness of WSENN is tested by applying the data from New South Wales (NSW) of Australia. Experimental results demonstrate that the WSENN model can offer more precise results than other methods that had mentioned in other literatures.