DefinePK

Abstract

The best planning of electricity consumption is needed in order to sustain the increasing of development activities. An important way to achieve that goal is to have the best forecasting model that could accurately modelling the pattern usage of electricity by using the data from January 2009 until December 2017 and forecast for the electricity consumption from January 2018 to December 2018. The purpose of this paper is to apply two differences forecasting method to forecast the electricity consumption Universiti Tun Hussein Onn Malaysia (UTHM). This paper compared the performance of Holt’s Linear Trend method and Holt-Winters method both in long-term forecasting. The results show that both methods performing well and Holt-Winters’ with the lowest error compared to Holt’s Linear Trend method. The mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) were calculated and pointed as a bench mark for both methods applied.