SEASONAL AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODEL FOR PREDICTION OF ELECTRICAL ENERGY DEMAND OF A BASE TRANSCEIVER STATION
DOI:
https://doi.org/10.4314/njt.2026.4923Keywords:
SARIMA, BTS, Time-series forecasting, electrical energy demand, Homer optimizationAbstract
Efficient energy management is essential for the continuous operation of Base Transceiver Stations (BTS), which are critical to mobile communication infrastructure. Power shortages can lead to service disruptions, necessitating accurate energy demand forecasting for optimal energy planning. This study developed a dual SARIMA models using 36 months (May 2021–April 2024) of field-measured hourly and daily electrical energy data from a BTS in Abeokuta, Nigeria with average load of 4.2 kW. The long-term daily model SARIMA (0,1,0)(1,0,1)₇ captures weekly traffic seasonality, while the short-term hourly model SARIMA(1,0,0)(0,1,2)₂₄ addresses diurnal peaks. The performance of the model was evaluated using Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Results showed that the long-term approach had a lower MAPE (7.67%) compared to the short-term approach (13.32%), indicating better accuracy. However, the short-term approach outperformed in terms of RMSE (0.63 kW) and MSE (0.40 kW), compared to 0.78 kW and 0.62 kW, respectively, for the long-term approach. Utilizing the forecasted energy demand, HOMER Pro software was employed to design an optimized hybrid energy system integrating solar energy and a biogas co-fired generator. Results yielded an economically optimal solar-biogas-battery configuration: 40 kW Canadian Solar PV, 16 kW CAT biogas generator, and 32.8 kWh LiFePO₄ storage delivering zero unmet loads. Key metrics include Levelized Cost of Energy (COE) of $0.01666/kWh, Net Present Cost (NPC) of $15,000, and 8-year payback, representing a 75% cost reduction versus diesel-only alternatives. SARIMA forecasting thus bridges precise BTS load prediction with cost-effective renewable sizing, enabling sustainable telecom expansion across off-grid regions.
References
[1] Wang, J., Liu, L. and Kadoch, M. “Edge Computing in Wireless Multimedia Communications: Empowering Low-latency and High-Quality Services.,” International Conference on Information Processing and Network Provisioning, pp. 197-211, 2025. https://doi.org/10.1007/978-981-96-6462-7_18
[2] Afzal, S., Mehran, N., Ourimi, Z.A., Tashtarian, F., Amirpour, H., Prodan, R. and Timmerer, C. “A Survey on Energy Consumption and Environmental Impact of Video Streaming,” ArXiv, pp. 1-34, 2024. https://doi.org/10.48550/arXiv.2401.09854
[3] Deevela, N.R., Kandpal, T.C. and Singh, B. “A Review of Renewable Energy Based Power Supply Options for Telecom Towers” Environment, Development and Sustainability, 26(2), pp.2897-2964, 2024. https://doi.org/10.1007/s10668-023-02917-7
[4] Buertey, J.T., Atsrim, F., Emmanuel, A.K. and Boateng, K. “Managing the Deployment of Telecommunication Towers in Ghana: An Urban-Integrated Sustainable Approach,” Urban, Planning and Transport Research, 12(1), p.2413138, 2024. https://doi.org/10.1080/21650020.2024.2413138
[5] Rao, C., Zhang, Y., Wen, J., Xiao, X. and Goh, M. “Energy Demand Forecasting in China: A Support Vector Regression-Compositional Data Second Exponential Smoothing Model,” Energy, 263, p.125955, 2022. https://doi.org/10.1016/j.energy.2022.125955
[6] Fang, T. and Lahdelma, R. “Evaluation of a Multiple Linear Regression Model and SARIMA Model in Forecasting Heat Demand for District Heating System,” Applied Energy, 179, pp. 544–552, 2016. https://doi.org/10.1016/j.apenergy.2016.06.133
[7] Aimran, N., Afthanorhan, A., Ishak, A., Asmadi, D., Jamaludin, N. and Borhan, N. “A Comparison Between the Exponential Smoothing, Methods of Average and Box Jenkins Techniques in Forecasting the Ageing Population in Malaysia,” AIP Conference Proceedings, 3123(1), p. 070003, 2024. https://doi.org/10.1063/5.0223872
[8] Zaim, S., Yaziz, S.R., Zakaria, R., Mohamad, N.N. and Radi, N.F.A. “Electricity Demand Forecasting in Malaysia using Seasonal Box-Jenkins Model,” Journal Technological (Sciences and Engineering), 87(2), pp. 239-252, 2025. https://doi.org/10.11113/jurnalteknologi.v87.21867
[9] Hadwan, M., Al-Maqaleh, B.M., Al-Badani, F.N., Khan, R.U. and Al-Hagery, M.A. “A Hybrid Neural Network and Box-Jenkins Models for Time Series Forecasting,” Computers, Materials and Continua, 70(3), pp. 4829-4845, 2022. https://doi.org/10.32604/cmc.2022.017824
[10] Chudo, S.B. and Gyorgy, T. “Modeling and Forecasting Time-Series Data with Multiple Seasonal Periods Using Periodograms,” Econometrics, 13(2), 2025. https://doi.org/10.3390/econometrics13020014
[11] Rao, C., Zhang, Y., Wen, J., Xiao, X. and Goh, M. “Energy Demand Forecasting in China: A Support Vector Regression-Compositional Data Second Exponential Smoothing Model,” Energy, 263, p. 125955, 2022. https://doi.org/10.1016/j.energy.2022.125955
[12] Alzoubi, A. “Machine Learning for Intelligent Energy Consumption in Smart Homes,” International Journal of Computations, Information and Manufacturing (IJCIM), pp. 62-75, 2022. https://doi.org/10.54489/ijcim.v2i1.75
[13] Edoka, E.O., Abanihi, V.K., Amhenrior, H.E., Evbogbai, E.M.J., Bello, L.O. and Oisamoje, V. “Time Series Forecasting of Electrical Energy Consumption Using Deep Learning Algorithm,”. Nigerian Journal of Technological Development, 20(3), pp. 163-174, 2023. https://doi.org/10.63746/njtd.v20i3.1424
[14] Okakwu, I.K., Oluwasogo, E.S., Ibhaze, A.E and Imoize, A.L. “A Comparative Study of Time Series Analysis for Forecasting Energy Demand in Nigeria,” Nigerian Journal of Technology, 38(2), pp. 465-469, 2019. http://dx.doi.org/10.4314/njt.v38i2.24
[15] Habbak, H., Mahmoud, M., Metwally, K., Fouda, M.M. and Ibrahem, M.I. “Load forecasting Techniques and their Applications in Smart Grids. Energies,” 16(3), p.1480, 2023. https://doi.org/10.3390/en16031480
[16] Ebrahim, R., Lysko, A.A., Burger, C.R., Vilakazi, M., Masonta, M.T. and Banda, L. “Toward Energy Efficiency in Radio Access Networks for 5G and Beyond: A Review of the State of the Art, Comparison of Power Consumption for Popular Open 5G RANs, and Techno-Economic Cost Impact,” IEEE Access, 13, pp. 187799-187842, 2025. https://doi.org/10.1109/ACCESS.2025.3626781
[17] Faruk, N., Ayeni, A.A., Muhammad, M.Y., Olawoyin, L.A., Abdulkarim, A., Agbakoba, J. and Olufemi, M.O. “Techniques for Minimizing Power Consumption of Base Transceiver Station in Mobile Cellular Systems,” International Journal of Sustainability, 2(1), pp. 1-11, 2013. https://doi.org/10.4156/ijs.vol2.issue1.1
[18] Issa, M., Rizk, P., Boulon, L., Rezkallah, M., Rizk, R. and Ilinca, A. “Smart, Connected, and Sustainable: The Transformation of Maritime Ports Through Electrification, IOT, 5G, and Green Energy,” Sustainability, 17(17), p.7568, 2025. https://doi.org/10.3390/su17177568
[19] Aurna, N.F., Rubel, M.T.M., Siddiqui, T.A., Karim, T., Saika, S., Arifeen, M.M., Mahbub, T.N., Reza, S.S. and Kabir, H. “Time Series Analysis of Electric Energy Consumption using Autoregressive Integrated Moving Average Model and HOLT Winters Model,” TELKOMNIKA (Telecommunication Computing Electronics and Control), 19(3), pp. 991-1000, 2021
[20] Ciulla, G. and D'Amico, A.J.A.E. “Building Energy Performance Forecasting: A Multiple Linear Regression Approach,” Applied Energy, 253, p.113500, 2019. https://doi.org/10.1016/j.apenergy.2019.113500
[21] Dudek, G. “Pattern-based Local Linear Regression Models for Short-Term Load Forecasting,” Electric Power Systems Research, 130, pp. 139–147, 2016. https://doi.org/10.1016/j.epsr.2015.09.001
[22] Gochhait, S. and Sharma, D. “Regression Model-based Short-term Load Forecasting for Load Despatch Centre,” Journal of Applied Engineering and Technological Science (JAETS), 4(2), pp. 693-710, 2023. https://doi.org/10.37385/jaets.v4i2.1682
[23] Samal, U. and Kumar, A. “Enhancing Software Reliability Forecasting through a Hybrid ARIMA-ANN Model,” Arabian Journal for Science and Engineering, 49(5), pp. 7571-7584, 2024. https://doi.org/10.1007/s13369-023-08486-1
[24] Haznedar, B. and Kilinc, H.C. “A Hybrid ANFIS-GA Approach for Estimation of Hydrological Time Series,” Water resources management, 36(12), pp. 4819-4842, 2022. https://doi.org/10.1007/s11269-022-03280-4
[25] Hajirahimi, Z. and Khashei, M. “A Novel Parallel Hybrid Model Based on Series Hybrid Models of ARIMA and ANN Models,” Neural Processing Letters, 54(3), pp. 2319-2337, 2022. https://doi.org/10.1007/s11063-021-10732-2
[26] Nwagbara, D. O., Anih, L. U., and Nnadi, D. B. N. “Power Demand Forecasting and Generation Adequacy in Nigeria up to 2040”, Nigerian Journal of Technology, 2025; 44(3), pp. 433 – 441. 2025. https://doi.org/10.4314/njt.v44i3.7
[27] Singh, G. “Hybrid SARIMA-LSTM Approach for Time Series Forecasting of Energy Availability in Telecom Networks”, 2025. https://dx.doi.org/10.2139/ssrn.5269629
[28] de Oliveira, E.M. and Oliveira, F.L.C. “Forecasting Mid-Long Term Electric Energy Consumption Through Bagging ARIMA and Exponential Smoothing Methods,” Energy, 144, pp. 776-788, 2018. https://doi.org/10.1016/j.energy.2017.12.049
[29] Clements, A.E., Hurn, A.S. and Li, Z. “Forecasting Day-ahead Electricity Load using a Multiple Equation Time Series Approach,” European Journal of Operational Research, 251(2), pp. 522–530, 2016. https://doi.org/10.1016/j.ejor.2015.12.030
[30] Regmi, N. and Pandey, S.B. “A Regression Analysis into Nepali ICT’s Energy Consumption and its Implications,” 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), pp. 1–8, 2015. https://doi.org/10.1109/SKIMA.2015.7400034
[31] Obinna, I.O.N. and Osawaru, O.E. “Modelling of Power Consumption in Two Base Stations, Using Ugbor Station and Benson Idahosa University Station in Benin City as a Case Study,” International Journal of Innovative Science and Research Technology, 5(6), pp. 1153–1165, 2020. https://doi.org/10.38124/IJISRT20JUN611
[32] Sirisha, U.M., Belavagi, M.C. and Attigeri, G. “Profit Prediction using ARIMA, SARIMA and LSTM Models in Time Series Forecasting: A Comparison,”. IEEE Access, 10, pp. 124715-124727, 2022. https://doi.org/10.1109/ACCESS.2022.3224938
[33] Szostek, K., Mazur, D., Drałus, G. and Kusznier, J. “Analysis of the Effectiveness of Arima, Sarima, and SVR Models in Time Series Forecasting: A Case Study of Wind Farm Energy Production,” Energies, 17(19), p.4803, 2024. https://doi.org/10.3390/en17194803
[34] Kumari, S. and Muthulakshmi, P. “SARIMA Model: An Efficient Machine Learning Technique for Weather Forecasting,” Procedia Computer Science, 235, pp. 656-670, 2024. https://doi.org/10.1016/j.procs.2024.04.064
[35] Deretić, N., Stanimirović, D., Awadh, M.A., Vujanović, N. and Djukić, A. “SARIMA Modelling Approach for Forecasting of Traffic Accidents,” Sustainability, 14(8), p.4403, 2022. https://doi.org/10.3390/su14084403
[36] Babatunde, O., Denwigwe, I., Babatunde, D., Ayeni, A., Adedoja, T. and Adedoja, O. “Techno-Economic Assessment of Photovoltaic-diesel Generator-Battery Energy System for Base Transceiver Stations Loads in Nigeria,” Cogent Engineering, 6(1), p.1684805, 2019. https://doi.org/10.3390/en16093800
[37] Samuel, I., Ojewola, T., Awelewa, A. and Amaize, P. “Short-term Load Forecasting using the Time Series and Artificial Neural Network Methods,” IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE), 11(1), pp. 72-81, 2016. https://doi.org/10.9790/1676-11137281
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nigerian Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The contents of the articles are the sole opinion of the author(s) and not of NIJOTECH.
NIJOTECH allows open access for distribution of the published articles in any media so long as whole (not part) of articles are distributed.
A copyright and statement of originality documents will need to be filled out clearly and signed prior to publication of an accepted article. The Copyright form can be downloaded from http://nijotech.com/downloads/COPYRIGHT%20FORM.pdf while the Statement of Originality is in http://nijotech.com/downloads/Statement%20of%20Originality.pdf
For articles that were developed from funded research, a clear acknowledgement of such support should be mentioned in the article with relevant references. Authors are expected to provide complete information on the sponsorship and intellectual property rights of the article together with all exceptions.
It is forbidden to publish the same research report in more than one journal.
How to Cite
