APPLICATION OF RADIAL BASIS FUNCTION NEURAL-NETWORK MODEL FOR SHORT-TERM LOAD FORECASTING

A description and original application of a type of neural network, ca lled the radial basis function network (RBFN), to the short-term syste m load forecasting (SLF) problem is presented. The predictive capabili ty of the RBFN models and their ability to produce accurate measures t hat can be used to estimate confidence intervals for the short-term fo recasts are illustrated, and an indication of the reliability of the c alculations is given. Performance results are given for daily peak and total load forecasts for one year using data from a large-scale power system. A comparison between results from the RBFN model and the Back -propagation neural network are also presented.