Comparative mathematical benchmarking of short-term photovoltaic power forecasting model families for data-scarce African grids
Article Sidebar
Main Article Content
Abstract
Short-term photovoltaic power forecasting is increasingly important for grid integration, operational planning, and renewable energy management; however, model selection remains a challenge in African systems, where historical records, meteorological inputs, and data quality are often scarce. This study developed a comparative mathematical benchmarking framework for evaluating representative short-term photovoltaic forecasting model families under data-scarce African grid conditions. Using secondary evidence from the literature, this study compares baseline, physical or weather-assisted, classical machine-learning, deep-learning, hybrid, and probabilistic forecasting families across four sparse-data scenarios: output-only operation, limited-weather operation, weather-assisted short-history operation, and utility deployment under operational constraints. A suitability score was proposed to integrate predictive accuracy, robustness to sparse or missing data, transferability, interpretability, data burden, and computational burden. The analysis showed that no single model family was universally superior across all scenarios. Classical ensemble machine-learning models appear most suitable when limited weather information is available, weather-assisted physical models are strongest when historical records are short but forecast inputs are available, and endogenous temporal models are most relevant when only output history is available. This study contributes a context-sensitive model-selection framework for photovoltaic forecasting in African grid environments.
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
Abdulai, D., Gyamfi, S., Diawuo, F. A. & Acheampong, P. (2023). Data analytics for prediction of solar PV power generation and system performance: A real case of Bui Solar Generating Station, Ghana. Scientific African, 21, e01894. https://doi.org/10.1016/j.sciaf.2023.e01894.
Assaf, A. M., Haron, H., Abdull Hamed, H. N., Ghaleb, F. A., Qasem, S. N. & Albarrak, A. M. (2023). A review on neural network based models for short term solar irradiance forecasting. Applied Sciences, 13(14), 8332. https://doi.org/10.3390/app13148332.
Barbieri, F., Rajakaruna, S. & Ghosh, A. (2017). Very short-term photovoltaic power forecasting with cloud modeling: A review. Renewable and Sustainable Energy Reviews, 75, 242–263. https://doi.org/10.1016/j.rser.2016.10.068.
Dhaked, D. K., Dadhich, S. & Birla, D. (2023). Power output forecasting of solar photovoltaic plant using LSTM. Green Energy and Intelligent Transportation, 2(5), 100113. https://doi.org/10.1016/j.geits.2023.100113.
Fernandez-Jimenez, L. A., Monteiro, C. & Ramirez-Rosado, I. J. (2023). Short-term probabilistic forecasting models using Beta distributions for photovoltaic plants. Energy Reports, 9, 495–502. https://doi.org/10.1016/j.egyr.2023.01.059.
Gaboitaolelwe, J., Zungeru, A. M., Yahya, A., Lebekwe, C. K., Vinod, D. N. & Salau, A. O. (2023). Machine learning based solar photovoltaic power forecasting: A review and comparison. IEEE Access, 11, 40820–40845. Doi: 10.1109/ACCESS.2023.3270041.
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. Doi: 10.1109/ACCESS.2020.3024901.
Konstantinou, M., Peratikou, S. & Charalambides, A. G. (2021). Solar photovoltaic forecasting of power output using LSTM networks. Atmosphere, 12(1), 124. https://doi.org/10.3390/atmos12010124.
Li, G., Xie, S., Wang, B., Xin, J., Li, Y., & Du, S. (2020). Photovoltaic Power Forecasting With a Hybrid Doi: 10.1109/ACCESS.2020.3025860.
Li, J., & Liu, Q. (2023). Short-term photovoltaic power forecasting using SOM-based regional modelling methods. in Chinese Journal of Electrical Engineering, 9(1), 158–176. Doi: 10.23919/CJEE.2023.000004.
Mayer, M. J., & Grof, G. (2021). Extensive comparison of physical models for photovoltaic power forecasting. Applied Energy, 283, 116239. https://doi.org/10.1016/j.apenergy.2020.116239.
Mbey, C. F., Yem Souhe, F. G., Foba Kakeu, V. J., & Boum, A. T. (2024). A Novel deep learning-based data analysis model for solar photovoltaic power generation and electrical consumption forecasting in the smart power grid. Applied Computational Intelligence and Soft Computing, 9257508. https://doi.org/10.1155/2024/9257508.
Mbuya, B. H., Dimovski, A., Merlo, M., & Kivevele, T. (2022). Very short-term blackout prediction for grid-tied PV systems operating in low reliability weak electric grids of developing countries. Complexity, 4763820. https://doi.org/10.1155/2022/4763820.
Mellit, A., Massi Pavan, A., Ogliari, E., Leva, S., & Lughi, V. (2020). Advanced methods for photovoltaic output power forecasting: A review. Applied Sciences, 10(2), 487. https://doi.org/10.3390/app10020487.
Mutavhatsindi, T., Sigauke, C., & Mbuvha, R. (2020). Forecasting hourly global horizontal solar irradiance in South Africa using machine learning models. IEEE Access, 8, 198872–198885. Doi: 10.1109/ACCESS.2020.3034690.
Pandzic, F., & Capuder, T. (2024). Advances in short-term solar forecasting: A review and benchmark of machine learning methods and relevant data sources. Energies, 17(1), 97. https://doi.org/10.3390/en17010097.
Pombo, D. V., Bacher, P., Ziras, C., Bindner, H. W., Spataru, S. V., & Sørensen, P. E. (2022). Benchmarking physics-informed machine learning-based short term PV-power forecasting tools. Energy Reports, 8, 6512–6520. https://doi.org/10.1016/j.egyr.2022.05.006.
Poti, K. D., Naidoo, R. M., Mbungu, N. T., & Bansal, R. C. (2023). Intelligent solar photovoltaic power forecasting. Energy Reports, 9, 343–352. https://doi.org/10.1016/j.egyr.2023.09.004.
Ratshilengo, M., Sigauke, C., & Bere, A. (2021). Short-term solar power forecasting using genetic algorithms: An application using South African data. Applied Sciences, 11(9), 4214. https://doi.org/10.3390/app11094214.
Salamanis, A. I., Xanthopoulou, G., Bezas, N., Timplalexis, C., Bintoudi, A. D., Zyglakis, L., Tsolakis, A. C., Ioannidis, D., Kehagias, D., & Tzovaras, D. (2020). Benchmark comparison of analytical, data-based and hybrid models for multi-step short-term photovoltaic power generation forecasting. Energies, 13(22), 5978. https://doi.org/10.3390/en13225978.
Zwane, N., Tazvinga, H., Botai, C., Murambadoro, M., Botai, J., De Wit, J., Mabasa, B., Daniel, S., & Mabhaudhi, T. (2022). A bibliometric analysis of solar energy forecasting studies in Africa. Energies, 15(15), 5520. https://doi.org/10.3390/en15155520.