Email this article A Data-Driven Machine Learning Approach to Solar Energy Generation Forecasting Using Meteorological Variables
Abstract
The production of solar power is highly dependent on weather conditions, including temperature, humidity, wind velocity, wind direction, cloud coverage, and solar radiation. These relations must be well understood to develop photovoltaic systems with high efficiency and reliability. A solar power prediction model is proposed in this paper based on meteorological data with more than 30,000 samples gathered at La Trobe University, Victoria, Australia. The purpose is to determine the most significant atmospheric variables and to improve prediction performance by modeling linear and non-linear relationships between solar output and meteorological parameters. Three machine learning (ML) algorithms: Ridge Regression (RR), Elastic Net Regression (ELNET), and Kernel Ridge Regression (KRR) have been employed and compared based on Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-Squared evaluation measure. SHapley Additive exPlanations (SHAP) was utilized to explain model outcomes and the significance of the variables. Among all the exemplified approaches, kernel ridge regression provides the best forecasting results. Air temperature, wind direction, wind speed, and relative humidity were the top four important features affecting solar power generation identified from SHAP analysis. The results show the potential of using machine learning techniques for accurate solar energy prediction, leading to enhanced grid management, renewable energy integration, and sustainable energy planning.
Citation: Tharushika, D., Napagoda, N., & Ekanayake, E. (2026). A Data-Driven Machine Learning Approach to Solar Energy Generation Forecasting Using Meteorological Variables. Trends in Renewable Energy, 12(2), 162-176. doi:http://dx.doi.org/10.17737/tre.2026.12.2.00203
Keywords
Full Text:
FULL TEXT (PDF)References
Herrera, J. M., Häner, L. L., Holzkämper, A., & Pellet, D. (2018). Evaluation of ridge regression for country-wide prediction of genotype-specific grain yields of wheat. Agricultural and Forest Meteorology, 252, 1-9.
Weng, X., Forster, G. L., & Nowack, P. (2022). A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019. Atmospheric Chemistry and Physics, 22(12), 8385-8402.
Satpathi, A., Setiya, P., Das, B., Nain, A. S., Jha, P. K., Singh, S., & Singh, S. (2023). Comparative analysis of statistical and machine learning techniques for rice yield forecasting for Chhattisgarh, India. Sustainability, 15(3), 2786.
Shao, D., Li, H., Wang, J., Hao, X., Che, T., & Ji, W. (2022). Reconstruction of a daily gridded snow water equivalent product for the land region above 45∘ N based on a ridge regression machine learning approach. Earth System Science Data, 14(2), 795-809.
Qona’ah, N., Ferawati, K., & Nirwana, M. B. (2020, April). Temperature Forecast Using Ridge Regression as Model Output Statistics. In Proceeding International Conference on Science and Engineering (Vol. 3, pp. 383-388).
Pinto, T., Santos, G., Marques, L., Sousa, T. M., Praça, I., Vale, Z., & Abreu, S. L. (2015). Solar intensity characterization using data-mining to support solar forecasting. In Distributed Computing and Artificial Intelligence, 12th International Conference (pp. 193-201). Springer International Publishing.
Malakouti, S. M., Menhaj, M. B., & Suratgar, A. A. (2023). The usage of 10-fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction. Cleaner Engineering and Technology, 15, 100664.
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
Kim, S. G., Jung, J. Y., & Sim, M. K. (2019). A two-step approach to solar power generation prediction based on weather data using machine learning. Sustainability, 11(5), 1501.
Ahmed, L. (2020). Using ridge regression to analysis the meteorological data in sulaimani. Iraqi Journal of Statistical Sciences, 17(2), 51-57.
Anuradha, K., Erlapally, D., Karuna, G., Srilakshmi, V., & Adilakshmi, K. (2021). Analysis of solar power generation forecasting using machine learning techniques. In E3S Web of Conferences (Vol. 309, p. 01163). EDP Sciences.
Blessing, E., & Klaus, H. (2023). Normalization and Standardization: Methods to preprocess data to have consistent scales and distributions. 2237. 10.
Nur, A. R., Jaya, A. K., & Siswanto, S. (2023). Comparative Analysis of Ridge, LASSO, and Elastic Net Regularization Approaches in Handling Multicollinearity for Infant Mortality Data in South Sulawesi. Jurnal Matematika, Statistika dan Komputasi, 20(2), 311-319.
Manorathna, R. (2020). k-fold cross-validation explained in plain English (For evaluating a model’s performance and hyperparameter tuning).
Frasso, G., & Eilers, P. H. (2012, September). Smoothing parameter selection using the L-curve. In 27th International Workshop on Statistical Modelling, Prague, Czech Republic
learner101. (2024). SHAP Summary Plot and Mean Values displaying together. Stack Overflow. https://stackoverflow.com/questions/72087719/shap-summary-plot-and-mean-values-displaying-together
CDAClab. (2022, November 9). Unisolar Solar Power Generation Dataset. Kaggle. https://www.kaggle.com/datasets/cdaclab/unisolar
DOI: http://dx.doi.org/10.17737/tre.2026.12.2.00203
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 D. D. H. Tharushika, N.A.D.N. Napagoda, E.M.P. Ekanayake
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 License.Copyright @2014-2026 Trends in Renewable Energy (ISSN: 2376-2136, online ISSN: 2376-2144)