Machine Learning applied to hourly forecasting of Temperature and Irradiance
Main Article Content
Abstract
To enable the efficient and reliable exploitation of photovoltaic power in Sub-Saharan Africa, particularly in Chad, this work aims to forecast hourly temperature and Global Horizontal Irradiance (GHI), which are key parameters influencing the production of photovoltaic power plants. In this study, we employ the ensemble methods represented by the Random Forest (RF) and Extreme Gradient Boosting (XGB), whose performances are compared to those of the Support Vector Regression (SVR). As the initial dataset consisted of daily data, to obtain hourly data, we introduced an original approach for discretizing variables, utilizing mathematical and physical assumptions that took into account the nature of the meteorological parameters in this study. As a result, our approach provides a better reproduction of GHI with a R2 of 0.93; however, it provides a low reproduction rate of temperature with a R2 of 0.37. Forecasts show interesting scores with the XGB model, which presents itself as the best model, displaying a R2 of 0.927 and 0.894, respectively, on hourly temperature and GHI. Finally, this study shows that models captured temperature variations more effectively than GHI. Furthermore, it highlights the advantage of the ensemble methods, which exhibit both high robustness and greater computational efficiency with shorter training times.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
-
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
-
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
How to Cite
References
Abumohsen, M., Owda, A. Y., Owda, M., Abumihsan, A., & Stergioulas, L. (2024). Forecasting Solar Power Generation Using Extreme Gradient Boosting : A Machine Learning Approach. 2024 4th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), 505-510. https://doi.org/10.1109/ICSINTESA62455.2024.10748030
Andrade, J. R., & Bessa, R. J. (2017). Improving Renewable Energy Forecasting With a Grid of Numerical Weather Predictions. IEEE Transactions on Sustainable Energy, 8(4), 1571-1580. https://doi.org/10.1109/TSTE.2017.2694340
Anthony, K., & Arunachalam, V. (2024). Voltage stability monitoring and improvement in a renewable energy dominated deregulated power system : A review. e-Prime - Advances in Electrical Engineering, Electronics and Energy, 100893. https://doi.org/10.1016/j.prime.2024.100893
Balog, I., Caputo, G., Iatauro, D., Signoretti, P., & Spinelli, F. (2023). Downscaling of Hourly Climate Data for the Assessment of Building Energy Performance. Sustainability, 15(3), 2762. https://doi.org/10.3390/su15032762
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
Butt, O. M., Zulqarnain, M., & Butt, T. M. (2021). Recent advancement in smart grid technology : Future prospects in the electrical power network. Ain Shams Engineering Journal, 12(1), 687-695. https://doi.org/10.1016/j.asej.2020.05.004
Cao, W., Zhou, J., Xu, Q., Zhen, J., & Huang, X. (2022). Short-Term Forecasting and Uncertainty Analysis of Photovoltaic Power Based on the FCM-WOA-BILSTM Model. Frontiers in Energy Research, 10. https://doi.org/10.3389/fenrg.2022.926774
Chen, T., & Guestrin, C. (2016, août). XGBoost : A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939785
Chen, X., Chen, W., Dinavahi, V., Liu, Y., & Feng, J. (2023). Short-Term Load Forecasting and Associated Weather Variables Prediction Using ResNet-LSTM Based Deep Learning. IEEE Access, 11, 5393-5405. IEEE Access. https://doi.org/10.1109/ACCESS.2023.3236663
Das, S., Chakraborty, R., & Maitra, A. (2017). A random forest algorithm for nowcasting of intense precipitation events. Advances in Space Research, 60(6), 1271-1282. https://doi.org/10.1016/j.asr.2017.03.026
de Aquino, R. R. B., Gouveia, H. T. V., Lira, M. M. S., Ferreira, A. A., Neto, O. N., & Carvalho, M. A. (2012). Wind forecasting and wind power generation : Looking for the best model based on artificial intelligence. The 2012 International Joint Conference on Neural Networks (IJCNN), 1-8. https://doi.org/10.1109/IJCNN.2012.6252526
Dietterich, T. G. (2000). Ensemble Methods in Machine Learning. Multiple Classifier Systems, 1-15. https://doi.org/10.1007/3-540-45014-9_1
Fan, J., Wu, L., Zhang, F., Cai, H., Zeng, W., Wang, X., & Zou, H. (2019). Empirical and machine learning models for predicting daily global solar radiation from sunshine duration : A review and case study in China. Renewable and Sustainable Energy Reviews, 100, 186-212. https://doi.org/10.1016/j.rser.2018.10.018
Faraji, J., Ketabi, A., Hashemi-Dezaki, H., Shafie-Khah, M., & Catalao, J. P. S. (2020). Optimal Day-Ahead Self-Scheduling and Operation of Prosumer Microgrids Using Hybrid Machine Learning-Based Weather and Load Forecasting. IEEE Access, 8, 157284-157305. IEEE Access. https://doi.org/10.1109/ACCESS.2020.3019562
Frifra, A., Maanan, M., Maanan, M., & Rhinane, H. (2024). Harnessing LSTM and XGBoost algorithms for storm prediction. Scientific Reports, 14(1), 11381. https://doi.org/10.1038/s41598-024-62182-0
Gbémou, S., Eynard, J., Thil, S., Guillot, E., & Grieu, S. (2021). A Comparative Study of Machine Learning-Based Methods for Global Horizontal Irradiance Forecasting. Energies, 14(11). https://doi.org/10.3390/en14113192
Georgiades, P., Economou, T., Proestos, Y., Araya, J., Lelieveld, J., & Neira, M. (2025). Global projections of heat stress at high temporal resolution using machine learning. Earth System Science Data, 17(3), 1153-1171. https://doi.org/10.5194/essd-17-1153-2025
Halpern-Wight, N., Konstantinou, M., Charalambides, A. G., & Reinders, A. (2020). Training and Testing of a Single-Layer LSTM Network for Near-Future Solar Forecasting. Applied Sciences, 10(17), 5873. https://doi.org/10.3390/app10175873
Haque, E., Tabassum, S., & Hossain, E. (2021). A Comparative Analysis of Deep Neural Networks for Hourly Temperature Forecasting. IEEE Access, 9, 160646-160660. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3131533
Helienek, L., Rusnak, J., Schnierer, B., Opatovsky, M., Dvonc, L., Fanego, V. L., Skoczek, A., & Cebecauer, T. (2023). Uncertainties in PV Power Simulation Chain. 2023 IEEE 50th Photovoltaic Specialists Conference (PVSC), 1-6. https://doi.org/10.1109/PVSC48320.2023.10359583
Hill, A. J., Herman, G. R., & Schumacher, R. S. (2020). Forecasting Severe Weather with Random Forests. Monthly Weather Review, 148(5), 2135-2161. https://doi.org/10.1175/MWR-D-19-0344.1
Hossain, M. S., & Mahmood, H. (2020). Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast. IEEE Access, 8, 172524-172533. IEEE Access. https://doi.org/10.1109/ACCESS.2020.3024901
Hou, J., Wang, Y., Zhou, J., & Tian, Q. (2022). Prediction of hourly air temperature based on CNN-LSTM. Geomatics, Natural Hazards and Risk, 13(1), 1962-1986. https://doi.org/10.1080/19475705.2022.2102942
Hu, X. (2024). Weather Phenomena Monitoring : Optimizing Solar Irradiance Forecasting With Temporal Fusion Transformer. IEEE Access, 12, 194133-194149. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3517144
IEA. (2022a). Africa Energy Outlook 2022. https://www.iea.org/reports/africa-energy-outlook-2022
IEA. (2022b, août 26). Special Report on Solar PV Global Supply Chains. https://doi.org/10.1787/9e8b0121-en
IRENA. (2023). Tripling renewable power and doubling energy efficiency by 2030 : Crucial steps towards 1.5°C. https://www.irena.org/Publications/2023/Oct/Tripling-renewable-power-and-doubling-energy-efficiency-by-2030
IRENA. (2025). A just energy transition for communities : Large-scale wind and solar projects in Sub-Saharan Africa.
Karmakar, R., Kundu, S., Biswas, S. K., & Tripathi, D. (2024). Efficacy of Ensemble Learning Method over Individual Classifier for Rainfall Forecasting in Eastern India. Journal of The Institution of Engineers (India) : Series B, 105(4), 929-939. https://doi.org/10.1007/s40031-024-01011-4
Kumar, S., Kaur, P., & Gosain, A. (2022). A Comprehensive Survey on Ensemble Methods. 2022 IEEE 7th International conference for Convergence in Technology (I2CT), 1-7. https://doi.org/10.1109/I2CT54291.2022.9825269
Lai, C. S., Zhong, C., Pan, K., Ng, W. W. Y., & Lai, L. L. (2021). A deep learning based hybrid method for hourly solar radiation forecasting. Expert Systems with Applications, 177, 114941. https://doi.org/10.1016/j.eswa.2021.114941
Liuyi, C., Bocheng, H., Xuesong, W., Jiazhen Zhao, Z., Wenke, Y., & Zhengyi, Y. (2023). Machine Learning Methods in Weather and Climate Applications : A Survey. Applied Sciences, 13(21). https://doi.org/10.3390/app132112019
Loken, E. D., Clark, A. J., & Karstens, C. D. (2020). Generating probabilistic next-day severe weather forecasts from convection-allowing ensembles using random forests. Weather and Forecasting, 35(4), 1605-1631.
Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30. https://proceedings.neurips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
Lyu, C., & Eftekharnejad, S. (2024). Probabilistic Solar Generation Forecasting for Rapidly Changing Weather Conditions. IEEE Access, 12, 79091-79103. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3407778
Magesh, T., Supriya, S., Yuvaprakash, Vishvapriya R, T., Nisha, C., & P, G. (2024). Hybrid Weather Forecasting : Integrating LSTM Neural Networks and Random Forest Models for Enhanced Accuracy. 2024 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), 1-5. https://doi.org/10.1109/RAEEUCCI61380.2024.10547997
Mai, X., Zhong, H., & Li, L. (2021). Research on Rain or Shine Weather Forecast in Precipitation Nowcasting Based on XGBoost. In H. Meng, T. Lei, M. Li, K. Li, N. Xiong, & L. Wang (Eds.), Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery (p. 1313-1319). Springer International Publishing. https://doi.org/10.1007/978-3-030-70665-4_143
Massaoudi, M., Chihi, I., Sidhom, L., Trabelsi, M., Refaat, S. S., & Oueslati, F. S. (2021). Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements. Energies, 14(13), Article 13. https://doi.org/10.3390/en14133992
Meenal, R., Angel, P., Pamela, D., & Rajasekaran, E. (2021). Weather prediction using random forest machine learning model. Indonesian Journal of Electrical Engineering and Computer Science, 22, 1208. https://doi.org/10.11591/ijeecs.v22.i2.pp1208-1215
Mei, F., Gu, J., Lu, J., Lu, J., Zhang, J., Jiang, Y., Shi, T., & Zheng, J. (2020). Day-Ahead Nonparametric Probabilistic Forecasting of Photovoltaic Power Generation Based on the LSTM-QRA Ensemble Model. IEEE Access, 8, 166138-166149. IEEE Access. https://doi.org/10.1109/ACCESS.2020.3021581
Michel, A., Sharma, V., Lehning, M., & Huwald, H. (2021). Climate change scenarios at hourly time-step over Switzerland from an enhanced temporal downscaling approach. International Journal of Climatology, 41(6), 3503-3522. https://doi.org/10.1002/joc.7032
Mienye, I. D., & Sun, Y. (2022). A Survey of Ensemble Learning : Concepts, Algorithms, Applications, and Prospects. IEEE Access, 10, 99129-99149. IEEE Access. https://doi.org/10.1109/ACCESS.2022.3207287
Mugware, F. W., Sigauke, C., & Ravele, T. (2024). Evaluating Wind Speed Forecasting Models : A Comparative Study of CNN, DAN2, Random Forest and XGBOOST in Diverse South African Weather Conditions. Forecasting, 6(3), 672-699. https://doi.org/10.3390/forecast6030035
Murdan, A. P., & Armoogum, V. (2023). Comparing Machine Learning Techniques for Hourly Solar Power Generation Prediction. In J. Lu, H. Guo, I. McLoughlin, E. G. Chekole, U. Lakshmanan, W. Meng, P. C. Wang, & N. Heng Loong Wong (Eds.), Proceedings of the 9th IRC Conference on Science, Engineering, and Technology (p. 365-376). Springer Nature. https://doi.org/10.1007/978-981-99-8369-8_34
Olulope, P., Folly, K., & Venayagamoorthy, G. (2013). Modeling and simulation of hybrid distributed generation and its impact on transient stability of power system. Proceedings of the IEEE International Conference on Industrial Technology, 1757-1762. https://doi.org/10.1109/ICIT.2013.6505941
Phan, Q. T., Wu, Y. K., & Phan, Q. D. (2021). A Hybrid Wind Power Forecasting Model with XGBoost, Data Preprocessing Considering Different NWPs. Applied Sciences, 11(3), Article 3. https://doi.org/10.3390/app11031100
Phan, Q.-T., Wu, Y.-K., & Phan, Q.-D. (2021). Short-term Solar Power Forecasting Using XGBoost with Numerical Weather Prediction. 2021 IEEE International Future Energy Electronics Conference (IFEEC), 1-6. https://doi.org/10.1109/IFEEC53238.2021.9661874
Raudhah, I. R., & Ahmad, F. M. N. (2020). Voltage Stability Analysis of Electric Power System with Integration of Renewable Energy. ResearchGate. https://doi.org/10.30880/eeee.2020.01.01.011
Sarmah, U., Borah, P., & Bhattacharyya, D. K. (2024). Ensemble Learning Methods : An Empirical Study. SN Computer Science, 5(7), 924. https://doi.org/10.1007/s42979-024-03252-y
Suksamosorn, S., Hoonchareon, N., & Songsiri, J. (2021). Post-Processing of NWP Forecasts Using Kalman Filtering With Operational Constraints for Day-Ahead Solar Power Forecasting in Thailand. IEEE Access, 9, 105409-105423. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3099481
Waqas, M., Humphries, U. W., Chueasa, B., & Wangwongchai, A. (2024). Artificial intelligence and numerical weather prediction models : A technical survey. Natural Hazards Research. https://doi.org/10.1016/j.nhres.2024.11.004
Yang, R., Hu, J., Li, Z., Mu, J., Yu, T., Xia, J., Li, X., Dasgupta, A., & Xiong, H. (2024). Interpretable machine learning for weather and climate prediction : A review. Atmospheric Environment, 338, 120797. https://doi.org/10.1016/j.atmosenv.2024.120797
Yu, G. Z., Lu, L., Tang, B., Wang, S. Y., & Chung, C. Y. (2023). Ultra-Short-Term Wind Power Subsection Forecasting Method Based on Extreme Weather. IEEE Transactions on Power Systems, 38(6), 5045-5056. https://doi.org/10.1109/TPWRS.2022.3224557
Zhang, J., & Fu, H. (2024). An Integrated Modeling Strategy for Wind Power Forecasting Based on Dynamic Meteorological Visualization. IEEE Access, 12, 69423-69433. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3401588
Zhang, L., Wang, J., Qian, Y., & Li, Z. (2025). Photovoltaic power uncertainty quantification system based on comprehensive model screening and multi-stage optimization tasks. Applied Energy, 381, 125061. https://doi.org/10.1016/j.apenergy.2024.125061
Zhang, T., Zhang, X., Rubasinghe, O., Liu, Y., Chow, Y. H., Iu, H. H. C., & Fernando, T. (2024). Long-Term Energy and Peak Power Demand Forecasting Based on Sequential-XGBoost. IEEE Transactions on Power Systems, 39(2), 3088-3104. IEEE Transactions on Power Systems. https://doi.org/10.1109/TPWRS.2023.3289400
Zhou, L., Chen, H., Xu, L., Cai, R.-H., & Chen, D. (2024). Deep learning-based postprocessing for hourly temperature forecasting. Meteorological Applications, 31(2), e2194. https://doi.org/10.1002/met.2194