Grouping model application on artificial neural networks for short-term load forecasting

With the development of our countrypsilas electricity market, power system load forecasting, especially short-term load forecasting (STLF), has been get more and more important function in the reliable, security, and economical operation of power system. The paper has introduced the principle of artificial neural networks and how we can use it to forecast electric power load. In this paper, a three-layer feed-forward back-propagation (BP) network is applied for short-term load forecasting. In order to improve the accuracy of short-term load forecasting, the data were detached into three groups: workday data, weekend data and festival data which were used to be trained for grouping forecasting models. The proposed networks are trained with 2-year (2002-2003) actual data of Nanchang city and are tested for target years (2004) including workday model, weekend model and festival model. Very reasonable results have been obtained for sample data.