Assessing the Dynamics of kilowatt per capita in Nigeria; Evidence from Non-Seasonal ARIMA modeling
Main Article Content
Keywords
Non-seasonal ARIMA, Kilowatt Per capita, Dynamics, Ljung-box
Abstract
Using data from 1990 to 2023, this study examines the suitability of a non-seasonal ARIMA (0,1,1) model with drift for short-term forecasting of Nigeria's annual per-capita electricity consumption (kWh). ACF/PACF analysis was used to determine the model specification, which was ARIMA (0,1,1) with drift (μ = 1.6456). The mean of the first differences was subtracted to estimate the drift. A moving average coefficient (θ = -0.2246) was obtained by maximum likelihood estimation, and a Ljung–Box test (p = 0.2941) verified the model's adequacy and showed no discernible residual autocorrelation. Per-capita electricity use is expected to rise gradually between 2024 and 2026, with prediction intervals increasing over time to reflect growing uncertainty. These findings imply that the parsimonious ARIMA (0,1,1) with drift is a useful and interpretable tool for policy and planning in situations with limited data since it accurately captures the central trend in Nigeria's per-capita electricity consumption and offers trustworthy short-term forecasts.
Article Metrics Graph
References
[2] D.O. Akinyele, R.K. Rayudu, Review of energy storage technologies for sustainable power networks, Sustain. Energy Technol. Assess. 8 (2014) 74–91.
[3] M.S. Al-Musaylh, R.C. Deo, J.F. Adamowski, Y. Li, Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia, Adv. Eng. Inform. 35 (2018) 1–16.
[4] International Energy Agency, World Energy Outlook 2022, IEA, Paris, 2022.
[5] M.B. Jebli, S.B. Youssef, N. Apergis, The dynamic linkage between CO₂ emissions, economic growth, renewable energy consumption, number of tourist arrivals and trade, Ecol. Econ. 117 (2016) 123–135.
[6] V.Ş. Ediger, S. Akar, ARIMA forecasting of primary energy demand by fuel in Turkey, Energy Policy35 (3) (2007) 1701–1708.
[7] M. Ekpenyong, E.C. Okonkwo, O. Orukpe, Forecasting of electricity consumption in Nigeria using hybridized ARIMA–ANN model, Nig. J. Technol.*39 (1) (2020) 220–228.
[8] S. Ghosh, Import demand of crude oil and economic growth: Evidence from India, Energy Policy 37 (2) (2009) 699–702.
[9] J. Henry, A. Peter, Application of autoregressive integrated moving average (ARIMA) model to forecast electricity consumption for Nigeria, J. Environ. Energy Econ. 2 (1) (2024) 13–21.
[10] T.O. Maku, M.U. Adehi, M.O. Adenomon, Modeling and forecasting electricity consumption in Nigeria using ARIMA and ARIMAX time series models, Sci. World J. 18 (3) (2023) 414–421.
[11] V.A. Micheal, D.O. Olayemi, Time series forecast of Nigeria’s electricity using auto-regressive integrated moving average (ARIMA) model, Big Data Anal. 1 (2) (2025).
[12] S.O. Olayemi, Energy consumption and economic growth in Nigeria: A causality analysis, Int. J. Energy Econ. Policy 2 (4) (2012) 238–249.
[13] S.O. Oyedepo, Towards achieving energy for sustainable development in Nigeria, Renew. Sustain. Energy Rev. 34 (2014) 255–272.
[14] S.O. Oyedepo, Energy and sustainable development in Nigeria: The way forward, Energy Sustain. Soc. 2 (1) (2012) 1–17.
[15] World Bank, World Development Indicators, 2023. Available from: [https://data.worldbank.org]