Predictive model of load and price for restructured power system using neural network

Abstract

Load and price prediction are an important component in the economic and secures operation of the competitive restructured power system energy market. This paper presents the use of an artificial neural network to half hourly ahead load prediction and half hourly ahead price prediction applications. By using historical weather, load consumption, price and calendar data, a multi-layer feed forward (FF) neural network trained with Back propagation (BP) algorithm was developed for the half hour ahead prediction. The developed algorithm for half hourly prediction has been tested with Australian market data. The result of ANN prediction model is compared with the conventional Multiple Regression (MR) prediction model.