NEW APPROACH TO DAILY AND PEAK LOAD PREDICTIONS USING A RANDOM VECTORFUNCTIONAL-LINK NETWORK

A functional-link neural network based short-term electric load foreca sting system is presented in this paper. The electric load forecasting model is assumed to consist of a load time series and a weather depen dent component modeled as a function expansion of the weather variable s like temperature or humidity. The parameters of the functional link neural network model are identified using a weight adjustment algorith m based on Widrow-Hoff delta rule. The non linear weight adjustment al gorithm adapts the weights every 24-hour or 168-hour producing a MAPE mostly less than 2% for a 24-hour ahead forecast and 2.5% for a 168-ho ur ahead forecast. The results of forecast for a period over 2 years i ndicate that the new model produces more accurate and robust forecasts in comparison to simple adaptive neural network or statistical approa ches.