INVESTIGATING THE IMPACT OF TEMPERATURE ON DAILY ELECTRIC LOAD IN DRY SEASON IN THREE LOCATIONS OF AGBOR, ASABA AND ABRAKA, DELTA STATE
DOI:
https://doi.org/10.60787/jnamp.vol71no.612Keywords:
Temperature impact, Electric load, Dry season, Energy demand, LSTM-RF modelAbstract
This study investigates temperature variations impact on daily electric load consumption during dry seasons using sophisticated forecasting models and empirical data analysis. The comprehensive dataset comprised 547 daily observations from three Delta State metropolitan cities—Agbor, Asaba, and Abraka—spanning 18 months (October 2022 to March 2024). The statistical analysis employed descriptive statistics, correlation analysis, regression modeling, and time-series decomposition, utilizing advanced techniques including Pearson correlation analysis, multiple linear regression, and machine learning models (LSTM, Random Forest, hybrid approaches). The analysis used R version 4.3.2, Python 3.9, TensorFlow 2.12, Scikit-learn, Prophet, and ARIMA models, featuring a novel hybrid LSTM-RF ensemble approach combining Long Short-Term Memory networks' sequential learning with Random Forest robustness. Results revealed strong positive correlation between ambient temperature and daily electric load demand (r = 0.847, p < 0.001). Dry season average daily load (2,847.3 MW) exceeded wet season levels (2,234.7 MW) by 27.4%. The hybrid LSTM-RF model achieved 94.2% forecasting accuracy with temperature variables versus 76.8% without temperature variables. Peak loads occurred during maximum daily temperatures (13:00-16:00), with temperature of 40.1 0C as the highest at an average of 81.2 MW per degree Celsius. The load-to-temperature ratio is comparatively constant throughout the day demonstrating temperature as a crucial predictor for electric load demand with significant implications for tropical region capacity planning and grid management.
Downloads
References
Behmiri, N. B., Fezzi, C., & Ravazzolo, F. (2023). Incorporating air temperature into mid-term electricity load forecasting models using time-series regressions and neural networks. Energy, 278, 127831. https://doi.org/10.1016/j.energy.2023.127831
Sawadogo, W., Abiodun, B. J., & Okogbue, E. C. (2020). Impacts of global warming on photovoltaic power generation over West Africa. Renewable Energy, 151, 263–277. https://doi.org/10.1016/j.renene.2019.11.055
Al-Ghezi, M. K. S., Ahmed, R. T., & Chaichan, M. T. (2022). The influence of temperature and irradiance on performance of the photovoltaic panel in the middle of Iraq. International Journal of Renewable Energy Development, 11, 501–513. https://doi.org/10.14710/ijred.2022.43864
Maoulida, F., Djedjig, R., Kassim, M. A., & El Ganaoui, M. (2023). Numerical study for the evaluation of the effectiveness and benefits of using photovoltaic-thermal (PV/T) system for hot water and electricity production under a tropical African climate: Case of Comoros. Energies, 16, 240. https://doi.org/10.3390/en16010240
Asim, M., Milano, J., Khan, H. I., Tahir, M. H., Mujtaba, M. A., Shamsuddin, A. H., Abdullah, M., & Kalam, M. A. (2022). Investigation of mono-crystalline photovoltaic active cooling thermal system for hot climate of Pakistan. Sustainability, 14, 10228. https://doi.org/10.3390/su141610228
Figueiró, I. C., da Rosa, A. A., Neto, N. K., Silva, L. N., & Beluco, A. (2023). Hierarchical short-term load forecasting considering weighting by meteorological region. IEEE Latin America Transactions, 21(11), 1191–1198. https://doi.org/10.1109/TLA.2023.10223610
Bian, H., Wang, Q., Xu, G., Zhao, Y., Liu, Y., & Li, S. (2022). Load forecasting of hybrid deep learning model considering accumulated temperature effect. Energy Reports, 8, 205–215. https://doi.org/10.1016/j.egyr.2021.11.155
Fan, C., Nie, S., Xiao, L., Zhao, Y., & Ding, Y. (2024). A multi-stage ensemble model for power load forecasting based on decomposition, error factors, and multi-objective optimization algorithm. International Journal of Electrical Power & Energy Systems, 155, 109620. https://doi.org/10.1016/j.ijepes.2023.109620
Wang, Y., Sun, S., & Cai, Z. (2023). Daily peak-valley electric-load forecasting based on an SSA-LSTM-RF algorithm. Energies, 16(24), 7964. https://doi.org/10.3390/en16247964
Hasan, K., Yousuf, S. B., Tushar, M. S. H. K., Das, B. K., Das, P., & Islam, M. S. (2022). Effects of different environmental and operational factors on the PV performance: A comprehensive review. Energy Science & Engineering, 10, 656–675. https://doi.org/10.1002/ese3.1050
Karakilic, A. N., Karafil, A., & Genc, N. (2022). Effects of temperature and solar irradiation on performance of monocrystalline, polycrystalline and thin-film PV panels. International Journal of Technical and Physical Problems of Engineering, 51, 254–260.
Bhat, A. Y., & Qayoum, A. (2023). Synergistic impact of tube configuration and working fluid on photovoltaic-thermal system performance. Renewable Energy, 207, 205–217. https://doi.org/10.1016/j.renene.2023.02.020
Li, X., Wang, Y., Ma, G., Wang, L., Zhang, Y., & Xu, Q. (2022). Electric load forecasting based on long short-term memory network via simplex optimizer during COVID-19. Energy Reports, 8, 1–12. https://doi.org/10.1016/j.egyr.2022.01.020
Sharma, A., & Jain, S. K. (2022). A novel seasonal segmentation approach for day-ahead load forecasting. Energy, 257, 124752. https://doi.org/10.1016/j.energy.2022.124752
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Journals of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
