Modeling and forecasting energy demand

Abstract

Energy demand is an important factor; it represents the industrial development of a country. In this work, we use ARIMA (Auto Regressive Integrated Moving Average) to model Morocco's energy demand. The model is validated by various statistical approaches such as the determination coefficient, R square, R-square stationary. Additionally, the performance of the model is assessed using mean absolute percentage error MAPE (eq 1), root means square error RMSE (eq 2) and means absolute error MAE (eq 3). The demand history is used for forecasting Morocco's demand from 2015 to 2025.The results show that the proposed model can give good predictions for the Moroccan demand.