Forecast of electricity consumption in the Cameroonian residential sector by Grey and vector autoregressive models

• Published in: Energy (Oxford) Vol. 214; p. 118791
• Main Authors: Guefano, Serge, Tamba, Jean Gaston, Azong, Tchitile Emmanuel Wilfried, Monkam, Louis
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.01.2021; Elsevier BV
• Subjects: Autoregressive models; Cameroon; Electric industries; Electric power demand; Electricity; Electricity consumption; Forecast; Hybrid model GM(1,1)-VAR; Mastering; Residential areas; Residential energy; Residential sector; Cameroon; Hybrid model GM(1,1)-VAR; Cameroon; Electricity consumption; Forecast; Residential sector
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2020.118791

Cameroon is highly growing in energy as a whole, and in electricity in particular. This growth is expected to increase within the next years, thanks to the current emergence as well as the country’s major projects. Therefore, mastering electricity demand in the residential sector is one of State’s priorities. In fact, this falls under the development plan of the electricity sector by 2025. Therefore, this paper highlights the forecast of the electricity consumption regarding the residential sector in Cameroon. The new GM(1,1)-VAR(1) hybrid model which is based on the VAR and Grey models, is used for this purpose. Results from the new model show that the previsional GM(1,1)-VAR(1) model is strong and reliable, just like some recent and modern hybrid models. Electricity needs of the residential sector by 2025 are estimated at 2641.632 GWh, with a 1.628% MAPE, and a 15.42 RMSE. Consequently, the new hybrid model should be a reliable previsional tool that makes it possible to monitor the evolution of electricity demand of the residential sector in cameroon. •Forecasting of electricity consumption regarding the residential sector in Cameroon is made.•The Grey and Vector Autoregressive models are coupled for forecasting.•Five economic and demographic parameters are included in the new hybrid model.•The proposed new hybrid model is better than some recent hybrid models.