The successful deployment of solar energy systems necessitates accurate forecasting of electricity production by photovoltaic power stations (PPS) to ensure the stable operation of power supply networks. This requirement stems from the need to maintain a real-time balance between electricity generation and consumption, which is achieved through the implementation of complex hierarchical control systems governing available energy sources. In this context, short-term forecasting of solar power generation is particularly critical, as it enables operational planning, economic dispatching, and grid stability.
This study presents the results of developing and validating forecasting methods while examining the impact of meteorological data structure and quality on prediction accuracy. Particular attention is paid to assessing the significance of various meteorological parameters using statistical correlation methods, including Pearson’s linear correlation, Spearman’s rank correlation, and Kendall’s tau, as well as the Boruta feature selection algorithm. These methods provide complementary insights into the relevance and influence of environmental variables.
Based on the extracted significant predictors, a data-driven model using the k-Nearest Neighbors (kNN) algorithm was implemented. The research employed two distinct meteorological datasets, both containing environmental measurements and actual energy output data from the same photovoltaic facility. The first dataset was obtained from a weather station installed directly at the solar plant, offering high temporal and spatial precision. The second dataset was derived from open- access satellite-based weather sources linked to the plant’s geographic coordinates, which are often used when on-site instrumentation is unavailable.
The results confirm that the use of on-site meteorological observations significantly improves model performance. For the kNN algorithm, the coefficient of determination (R2) reached 0.99 using local data, compared to 0.95 with the satellite- based set. Additionally, metrics such as MAPE, MAE, and generation forecast error (PFG) support the superiority of models trained on accurate, high-resolution inputs. These findings highlight the importance of equipping solar energy facilities with dedicated meteorological sensors and integrating refined data into intelligent prediction frameworks.
[1] Pelland, S., Remund, J., Kleissl, J., Oozeki, T., & De Brabandere, K. (2013). Photovoltaic and solar forecasting: State of the art (Report IEA-PVPST14-01:2013). IEA PVPS. ISBN 978-3-906042-13-8.
[2] Tsmots, I. G., Tesliuk, V. M., Podolsky, M. R., & Dubuk, V. I. (2020). Tools of visualization of power balances and analytical support of energy efficiency management of region. Ukrainian Journal of Information Technology, 2(1), 01–07. https://doi.org/10.23939/ujit2020.02.001
[3] Kuznetsov, M. P., & Lysenko, O. V. (2017). Capabilities of short-term solar energy forecasting. Renewable Energy, 2017(1), 25–32. http://nbuv.gov.ua/UJRN/vien_2017_1_6
[4] Matushkin, D. S., Bosak, A. V., & Kulakovskyi, L. Y. (2020). Analysis of factors for predicting electricity generation by solar power plants. Energetics: Economics, Technology, Ecology, 4 (2020), 62. https://doi.org/10.20535/1813-5420. 4.2020.233597
[5] Solcast Toolkit (n. d.). Retrieved April 2025, from https://toolkit.solcast.com.au/
[6] Ashan, D. K., & Geekiayange, V. (2021). Reliability comparison of weather data of PVGIS, NREL and Solcast for PV solar energy generation forecasting. Unpublished report. https://doi.org/10.13140/RG.2.2.14453.50400
[7] Kursa, Miron & Rudnicki, Witold. (2010). Feature Selection with Boruta Package. Journal of Statistical Software, 36, 1–13. 10.18637/jss.v036.i11.
[8] Alresheedi, А., А., & Al-Hagery, М., А. (2020). Hybrid artificial neural networks with Boruta algorithm for prediction of global solar radiation: Case study in Saudi Arabia. International Journal of Computer Science and Network, 9(2), (April). ISSN (Online): 2277-5420.
[9] Rinchi, B., Ayadi, O., Al-Dahidi, S., & Dababseh, R. (2024). A universal tool for estimating monthly solar radiation on tilted surfaces from horizontal measurements: A machine learning approach. Energy Conversion and Management, 314, 118703. https://doi.org/10.1016/j.enconman.2024.118703
[10] Shakhovska, N., Medykovskyi, M., Gurbych, О., Mamchur, M., & Melnyk, М. (2024). Enhancing solar energy production forecasting using advanced machine learning and deep learning techniques: A comprehensive study on the impact of meteorological data. Computers, Materials & Continua, 81(2), 3147–3163. https://doi.org/10.32604/cmc.2024.056542
[11] Ahmed, R., Sreeram, V., Mishra, Y., & Arif, M. D. (2020). A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization. Renewable and Sustainable Energy Reviews, 124, 109792. https://doi.org/ 10.1016/j.rser.2020.109792
[12] Meenal, R., Binu, D., Ramya, K. C., Michael, P. A., Kumar, K. V., Rajasekaran, E., & Sangeetha, B. (2022). Weather forecasting for renewable energy system: A review. Archives of Computational Methods in Engineering, 29(5), 2875–2891. https://doi.org/10.1007/s11831-021-09695-3
[13] Zhuravel, I. M., Onyshko, V. R., Zhuravel, Yu. I., & Ambroziak, K. A. (2024). Quantitative assessment of the visual quality of digital images based on the laws of human visual perception. Ukrainian Journal of Information Tecnology, 6(1), 17–25. https://doi.org/10.23939/ujit2024.01.017
[14] Li, B., & Zhang, J. (2020). A review on the integration of probabilistic solar forecasting in power systems. Solar Energy, 210, 68–86. https://doi.org/10.1016/j.solener.2020.07.066
[15] Asghar, R., Fulginei, F., R., Quercio, M., & Mahrouch, A. (2024). Artificial neural networks for photovoltaic power forecasting: A review of five promising models. IEEE Access, 12, 90461–90485. https://doi.org/10.1109/ACCESS.2024. 3420693
[16] Zhou, H., Liu, Q., Yan, K., & Du, Y. (2021). Deep learning enhanced solar energy forecasting with AI-driven IoT. Wireless Communications and Mobile Computing, 2021, 1– 11. https://doi.org/10.1155/2021/9249387
[17] Li, G., Xie, S., Wang, B., Xin, J., Li, Y., & Du, S. (2020). Photovoltaic power forecasting with a hybrid deep learning approach. IEEE Access, 8, 175871–175880. https://doi.org/ 10.1109/ACCESS.2020.3025860
[18] Obileke, K. I. K. (2024). Short-term forecasting of photovoltaic power using multilayer perceptron neural net- work, convolutional neural network, and k-nearest neighbors’ algorithms. Optics, 5(2), 293–309. https://doi.org/10.3390/ opt5020021
[19] Perehuda, O. V., Kapustian, O. A., & Kuryilko, O. B. (2022). Statistical data processing: Educational manual. Electronic edition, 103 p. Retrieved from [https://www.mechmat. univ.kiev.ua/wp-content/uploads/2022/02/navch_pos_ perehuda.pdf]
[20] Ramli, Nor Azuana & Abdul Hamid, Mohd Fairuz & Azhan, Nurul Hanis. (2019). Solar Power Generation Prediction by using k-Nearest Neighbor Method. AIP Conference Proceedings, 2129. 10.1063/1.5118124.
[21] Mas’ud, Abdullahi. (2021). Comparison of three machine learning models for the prediction of hourly PV output power in Saudi Arabia. Ain Shams Engineering Journal, 13, 101648. 10.1016/j.asej.2021.11.017.