Forecasting Electricity Consumption Using a Data Grouping Method Based on the Grey Model in Malaysia

Electricity consumption contributes significantly to the global increase in total energy consumption, which is strongly correlated with economic growth. Therefore, a study on electricity consumption prediction is required. This research aims to develop a model for seasonal data using a data grouping method-based grey model which consists of a data grouping of grey model DGGM(1,1), fractional grey model DGFGM(1,1), optimization of background value in DGGMOPT and DGFGMOPT to predict quarterly electricity consumption in Malaysia using data from 2012Q1 to 2019Q4. First, all quarterly time sequences is separated into four groups (each containing only time sequence data from the same quarter) following the suggested method. The new set of four quarters, each involving specific seasonal properties, is then used to develop models. Following that, a comprehensive quarterly time sequence is created using the forecasted data for all four quarters of these models, taking seasonal fluctuations into consideration. Each forecasting method's level of predicting accuracy is evaluated using the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) criterion. The outcomes demonstrated the higher level of flexibility and forecasting accuracy of DGFGMOPT (1,1).