A Comparative Analysis of Techniques for Forecasting Electricity Consumption

Abstract

The issue of obtaining reliable forecasting methods for electricity consumption has been widely discussed by past research work. This is due to the increased demand for electricity and as a result, the development of efficient pricing models. Several techniques have been used in past research for forecasting electricity consumption. This includes the use of forecasting, time-series technique (FTST) and artificial neural networks (ANN). This paper introduces a modified Newton's model (MNM) to forecast electricity consumption. Forecasting models are developed from historical data and predictive estimates are obtained. This research work utilizes data from Universiti Malaysia Sarawak, a public university in Malaysia, from 2009 to 2012. The variables considered in this research include electricity consumption for different months over the years.