SHORT TERM LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORK

Abstract

Accurate short term load forecasting is an essential task in power system planning, operation, and control. This paper discusses significant role of artificial intelligence (AI) in short -term load forecasting (STLF). A new artificial neural network (ANN) has been designed to compute the forecasted load. The ANN model is trained on hourly data from the ISO New England market from 2004 to 2008 and tested on out-of-sample data from 2009. Load forecast for ISO New England market is much better with temperature data as input than without taking it. This is due to the fact that temperature and weather data are having high degree of correlation with load of that particular region. This indicates that temperature data is a very important parameter for load forecasting using ANN.