This paper presents the results of forecasting electricity consumption in a humid zone, taking Togo as a case study. Consumption data were analyzed with the following input variables: Temperature (T), Relative Humidity (R), Precipitation (P), Wind Speed (W), and Sunshine Duration (S). XGBoost, ANFIS, and RNN are explored as modeling methods, with performance evaluated using R², MAE, MSE, and RMSE. A correlation analysis was conducted among all variables. The findings reveal correlations of 83% between relative humidity and precipitation; 73% between power consumption and precipitation; and 67% between power consumption and relative humidity. In contrast, only 8% correlation is observed between power consumption and temperature, and 4% between wind speed and sunshine duration. With respect to modeling, ANFIS metrics are found to be unsatisfactory. Its best performance yields R² = 41.3498% under the TRPWS configuration. XGBoost provides moderate results, with R² = 51.39% for the TRPWS configuration, representing its most acceptable model. By comparison, RNN delivers superior outcomes, with the majority of R² values exceeding 71%. The lowest performance, obtained with the PWS configuration, records RMSE = 909.7192, MAE = 567.9969, MSE = 827,589.1092, and R² = 71.45%. The highest performance, obtained with the TRPWS configuration, yields RMSE = 846.1036, MAE = 490.9964, MSE = 715,891.3167, and R² = 75.31%. Furthermore, residual analysis confirms that the distribution of errors aligns well with the Gaussian normal law. It is therefore concluded that RNN is well-suited for predicting electricity consumption in humid zones using the considered meteorological variables.
| Published in | American Journal of Energy Engineering (Volume 13, Issue 4) |
| DOI | 10.11648/j.ajee.20251304.14 |
| Page(s) | 189-212 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Electricity Consumption, Humid Zone, Meteorological Variables, Modeling
| [1] | O. Yankovyi, E. Kuznietsov, R. Hrinchenko, O. Gura, and O. Orlenko, “Improvement Of The Enterprise’s Production Program As A Way To Adapt To Market Changes,” Natsionalnyi Hirnychyi Universytet Nauk. Visnyk, no. 5, pp. 171–177, 2023. |
| [2] | N. Dhameliya, “Power Electronics Innovations: Improving Efficiency and Sustainability in Energy Systems,” Asia Pac. J. Energy Environ., vol. 9, no. 2, pp. 71–80, 2022. |
| [3] | J. Adams, M. Maslin, and E. Thomas, “Sudden climate transitions during the Quaternary,” Prog. Phys. Geogr., vol. 23, no. 1, pp. 1–36, 1999. |
| [4] | D. Shindell, “Estimating the potential for twenty-first century sudden climate change,” Philos. Trans. R. Soc. Math. Phys. Eng. Sci., vol. 365, no. 1860, pp. 2675–2694, 2007. |
| [5] | A. Jakušenoks and A. Laizāns, “Weather impact on the household electric energy consumption,” Res. Rural Dev., vol. 1, pp. 248–253, 2016. |
| [6] | A. Alsulaili, N. Aboramyah, N. Alenezi, and M. Alkhalidi, “Advancing Electricity Consumption Forecasts in Arid Climates through Machine Learning and Statistical Approaches,” Sustainability, vol. 16, no. 15, p. 6326, 2024. |
| [7] | M. J. Best, “Progress towards better weather forecasts for city dwellers: from short range to climate change,” Theor. Appl. Climatol., vol. 84, no. 1, pp. 47–55, 2006. |
| [8] | G. W. Brier and R. A. Allen, “Verification of weather forecasts,” in Compendium of Meteorology: Prepared under the Direction of the Committee on the Compendium of Meteorology, Springer, 1951, pp. 841–848. |
| [9] | A. Felinger, Data analysis and signal processing in chromatography, vol. 21. Elsevier, 1998. |
| [10] | R. Guillot et al., “Development of a machine learning model to assist in prescribing individualized dosages for patients treated with amoxicillin via continuous infusion.”, J. Epidemiol. Popul. Health, vol. 72, p. 202294, 2024. |
| [11] | Z. Zhang, S. Wang, B. Ye, and Y. Ma, “A feature prediction-based method for energy consumption prediction of electric buses,” Energy, vol. 314, p. 134345, 2025. |
| [12] | A. Al-Hmouz, J. Shen, R. Al-Hmouz, and J. Yan, “Modeling and simulation of an adaptive neuro-fuzzy inference system (ANFIS) for mobile learning,” IEEE Trans. Learn. Technol., vol. 5, no. 3, pp. 226–237, 2011. |
| [13] | U. Çaydaş, A. Hasçalık, and S. Ekici, “An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM,” Expert Syst. Appl., vol. 36, no. 3, pp. 6135–6139, 2009. |
| [14] | A. Talei, L. H. C. Chua, and T. S. Wong, “Evaluation of rainfall and discharge inputs used by Adaptive Network-based Fuzzy Inference Systems (ANFIS) in rainfall–runoff modeling,” J. Hydrol., vol. 391, no. 3–4, pp. 248–262, 2010. |
| [15] | A. B. K. Kpomone, B. Yao, P. E. T. Gnadi, and T. Pidename, “Approaches: Model Predictive Control, Support Vector Machine and Simple Linear Regression for the transformation of the CEET power grid in Lome, Togo, into a smart grid,” in 2024 1st International Conference on Smart Energy Systems and Artificial Intelligence (SESAI), IEEE, 2024, pp. 1–10. |
| [16] | Q. Wang, S. Bu, and Z. He, “Achieving predictive and proactive maintenance for high-speed railway power equipment with LSTM-RNN,” IEEE Trans. Ind. Inform., vol. 16, no. 10, pp. 6509–6517, 2020. |
| [17] | S. O. Djandja, A. A. Salami, K. K. A. Bara, and K.-S. Bedja, “Estimation of soil electrical resistivity using LP, RBF, ANFIS and SVM approaches.” International Journal of Advanced Research (IJAR), Int. J. Adv. Res. 7(5), 48-60. DOI URL: |
| [18] | D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” Peerj Comput. Sci., vol. 7, p. e623, 2021. |
APA Style
Palanga, E. T. G., Bara, K. K. A., Barate, M. (2025). Modeling of Electric Energy Consumption in Humid Zones Using Selected Meteorological Variables Through XGBoost, ANFIS, and RNN Approaches. American Journal of Energy Engineering, 13(4), 189-212. https://doi.org/10.11648/j.ajee.20251304.14
ACS Style
Palanga, E. T. G.; Bara, K. K. A.; Barate, M. Modeling of Electric Energy Consumption in Humid Zones Using Selected Meteorological Variables Through XGBoost, ANFIS, and RNN Approaches. Am. J. Energy Eng. 2025, 13(4), 189-212. doi: 10.11648/j.ajee.20251304.14
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajee.20251304.14,
author = {Eyouleki Tcheyi Gnadi Palanga and Komla Kpomone Apaloo Bara and Mohamed Barate},
title = {Modeling of Electric Energy Consumption in Humid Zones Using Selected Meteorological Variables Through XGBoost, ANFIS, and RNN Approaches},
journal = {American Journal of Energy Engineering},
volume = {13},
number = {4},
pages = {189-212},
doi = {10.11648/j.ajee.20251304.14},
url = {https://doi.org/10.11648/j.ajee.20251304.14},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajee.20251304.14},
abstract = {This paper presents the results of forecasting electricity consumption in a humid zone, taking Togo as a case study. Consumption data were analyzed with the following input variables: Temperature (T), Relative Humidity (R), Precipitation (P), Wind Speed (W), and Sunshine Duration (S). XGBoost, ANFIS, and RNN are explored as modeling methods, with performance evaluated using R², MAE, MSE, and RMSE. A correlation analysis was conducted among all variables. The findings reveal correlations of 83% between relative humidity and precipitation; 73% between power consumption and precipitation; and 67% between power consumption and relative humidity. In contrast, only 8% correlation is observed between power consumption and temperature, and 4% between wind speed and sunshine duration. With respect to modeling, ANFIS metrics are found to be unsatisfactory. Its best performance yields R² = 41.3498% under the TRPWS configuration. XGBoost provides moderate results, with R² = 51.39% for the TRPWS configuration, representing its most acceptable model. By comparison, RNN delivers superior outcomes, with the majority of R² values exceeding 71%. The lowest performance, obtained with the PWS configuration, records RMSE = 909.7192, MAE = 567.9969, MSE = 827,589.1092, and R² = 71.45%. The highest performance, obtained with the TRPWS configuration, yields RMSE = 846.1036, MAE = 490.9964, MSE = 715,891.3167, and R² = 75.31%. Furthermore, residual analysis confirms that the distribution of errors aligns well with the Gaussian normal law. It is therefore concluded that RNN is well-suited for predicting electricity consumption in humid zones using the considered meteorological variables.},
year = {2025}
}
TY - JOUR T1 - Modeling of Electric Energy Consumption in Humid Zones Using Selected Meteorological Variables Through XGBoost, ANFIS, and RNN Approaches AU - Eyouleki Tcheyi Gnadi Palanga AU - Komla Kpomone Apaloo Bara AU - Mohamed Barate Y1 - 2025/12/29 PY - 2025 N1 - https://doi.org/10.11648/j.ajee.20251304.14 DO - 10.11648/j.ajee.20251304.14 T2 - American Journal of Energy Engineering JF - American Journal of Energy Engineering JO - American Journal of Energy Engineering SP - 189 EP - 212 PB - Science Publishing Group SN - 2329-163X UR - https://doi.org/10.11648/j.ajee.20251304.14 AB - This paper presents the results of forecasting electricity consumption in a humid zone, taking Togo as a case study. Consumption data were analyzed with the following input variables: Temperature (T), Relative Humidity (R), Precipitation (P), Wind Speed (W), and Sunshine Duration (S). XGBoost, ANFIS, and RNN are explored as modeling methods, with performance evaluated using R², MAE, MSE, and RMSE. A correlation analysis was conducted among all variables. The findings reveal correlations of 83% between relative humidity and precipitation; 73% between power consumption and precipitation; and 67% between power consumption and relative humidity. In contrast, only 8% correlation is observed between power consumption and temperature, and 4% between wind speed and sunshine duration. With respect to modeling, ANFIS metrics are found to be unsatisfactory. Its best performance yields R² = 41.3498% under the TRPWS configuration. XGBoost provides moderate results, with R² = 51.39% for the TRPWS configuration, representing its most acceptable model. By comparison, RNN delivers superior outcomes, with the majority of R² values exceeding 71%. The lowest performance, obtained with the PWS configuration, records RMSE = 909.7192, MAE = 567.9969, MSE = 827,589.1092, and R² = 71.45%. The highest performance, obtained with the TRPWS configuration, yields RMSE = 846.1036, MAE = 490.9964, MSE = 715,891.3167, and R² = 75.31%. Furthermore, residual analysis confirms that the distribution of errors aligns well with the Gaussian normal law. It is therefore concluded that RNN is well-suited for predicting electricity consumption in humid zones using the considered meteorological variables. VL - 13 IS - 4 ER -
Polytechnic School of Lome (EPL), University of Lome, Lome, Togo;Regional Center of Excellence for Electricity Management (CERME), University of Lome, Lome, Togo
Polytechnic School of Lome (EPL), University of Lome, Lome, Togo;Regional Center of Excellence for Electricity Management (CERME), University of Lome, Lome, Togo
Polytechnic School of Lome (EPL), University of Lome, Lome, Togo;Regional Center of Excellence for Electricity Management (CERME), University of Lome, Lome, Togo
Information