التنبؤ باستهلاك الطاقة الكهربائية في الجزائر

Abstract

This study aims to analyze and forecast electricity consumption in Algeria using time series models within the framework of econometrics. Annual data covering the period from 1990 to 2023 were used, applying the Box-Jenkins methodology to build a model capable of explaining consumption behavior and predicting its future evolution. The results show that the electricity consumption series is non-stationary in levels but becomes stationary after first differencing, indicating that it is integrated of order one I(1)I(1)I(1). Model identification revealed that the ARMA (2,2) model is the most suitable based on statistical criteria and residual diagnostics, demonstrating strong performance in capturing the dynamics of electricity consumption. Regarding forecasting, the results indicate a continued upward trend in electricity consumption in Algeria in 2024, reflecting increasing demand driven by population growth, economic development, and improved living standards. This highlights the need for forward-looking energy policies focused on expanding production capacity, rationalizing consumption, and promoting renewable energy sources to ensure energy security and sustainability.