Estimating Solar Power Generation with RF, GB, and SVR Algorithms Based on Meteorological Data and Orientation Angles: Adıyaman Case Study
DOI:
https://doi.org/10.64470/elene.2025.1006Keywords:
Solar Energy, Machine Learning, Air Pollution, Orientation Angle, Energy GenerationAbstract
This study attempts to develop precise machine learning algorithms for estimating solar power generation using meteorological data, including air pollution (PM2.5, PM10) for different orientation angles in the dual-axis solar panel tracking system. Our study focused on maximizing energy generation for multivariable input factors in Adıyaman, rather than optimizing environmental parameters for fixed panels as previously studied. Three machine learning algorithms—Random Forest (RF), Gradient Boosting (GB), and Support Vector Regression (SVR)—were studied. The experimental setup was designed to measure power, temperature, humidity, wind speed/direction, pressure, air pollution data, and to adjust orientation angles (tilt and azimuth angles). Algorithm performances were assessed using R², MSE, and RMSE metrics. RF yielded the best results (R²: 0.83, MSE: 5.32, RMSE: 2.26). Including cumulative air pollution data improved prediction accuracy, implying particulate matter indirectly affects solar radiation and energy output.
Downloads
References
Al-Mohamad, A. (2004). Efficiency improvements of photo-voltaic panels using a Sun-tracking system. Applied Energy, 79(3), 345–354. https://doi.org/10.1016/j.apenergy.2003.12.004
AL-Rousan, N., Mat Isa, N. A., Mat Desa, M. K., & AL-Najjar, H. (2021). Integration of logistic regression and multilayer perceptron for intelligent single and dual axis solar tracking systems. International Journal of Intelligent Systems, 36(10), 5605–5669. https://doi.org/10.1002/int.22525
Ankarali, H., Temel, G. O., Tasdelen, B., & Ozge, A. (2012). Boosting Tree As a Stronger Approach in Classification: An Application of Carpal Tunnel Syndrome. Journal of Turgut Ozal Medical Center, 19(4), 228–233. https://doi.org/10.7247/jtomc.19.4.5
Arslan, M., & Çunkaş, M. (2024). An experimental study on determination of optimal tilt and orientation angles in photovoltaic systems. Journal of Engineering Research (Kuwait), July. https://doi.org/10.1016/j.jer.2024.07.015
Aslan, M., Ulum, T., & Türkmenler, H. (2021). Adıyaman İlinin Yenilenebilir Enerji Potansiyelinin Belirlenmesi Üzerine Bir Değerlendirme. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 33(1), 263–274. https://doi.org/10.35234/fumbd.791647
Bakırcı, K. (2009). A simple calculation method for estimation of instantaneous global solar radiation on horizontal surface. Journal of Thermal Scıence and Technology, 29(2), 53–58.
Bayrakçı, H. C., & Gezer, T. (2019). Bir Güneş Enerjisi Santralinin Maliyet Analizi: Aydın İli Örneği. Teknik Bilimler Dergisi, 9(2), 46–54. https://doi.org/10.35354/tbed.574190
Bengio, Y., & Grandvalet, Y. (2004). No Unbiased Estimator of the Variance of K-Fold Cross-Validation. Journal of Machine Learning Research, 5, 1089–1105.
Boyacı, Ö., & Kocaman, Ç. (2018). Matlab / Simulink Üzerinden Gerçek Zamanlı Gömülü Sistem Tabanlı Güneş Takip Sisteminin Tasarımı ve Uygulaması. Anka E-Dergi, 3(1), 1–15. http://dergipark.gov.tr/anka/issue/36841/370502
Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
Demirtaş, M., Akkoyun, N., Akkoyun, E., & Çetinbaş, İ. (2019). Akıllı Şebekelerde Güneş Enerjisi Üretiminin Zamana Bağlı Olasılıksal Tahmini. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 7(2), 411–424. https://doi.org/10.29109/gujsc.549704
Fahad, H. M., Islam, A., Islam, M., Hasan, M. F., Brishty, W. F., & Rahman, M. M. (2019). Comparative Analysis of Dual and Single Axis Solar Tracking System Considering Cloud Cover. 2019 International Conference on Energy and Power Engineering (ICEPE), 1–5. https://doi.org/10.1109/CEPE.2019.8726646
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An Introduction to Statistical Learning: with Applications in Python. Springer Berlin Heidelberg.
Jia, W., Chen, X.-Y., Zhang, H., Xiong, L.-D., Lei, H., & Deng, S.-H. (2019). Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization. Journal of Electronic Science and Technology, 17(1), 26–40. https://doi.org/https://doi.org/10.11989/JEST.1674-862X.80904120
Kaçan, E., & Ülgen, K. (2012). Güneş Enerjisi Toplayıcılarında Eğim ve Yönlendirmenin Yararlanabilirliğe Etkisi. Journal of the Faculty of Engineering and Architecture of Gazi University, 27(4), 837–846.
Kaul, J. D., & Weed, G. D. (2021). Prototype Development for Adaptive Solar Tracking and Optimization of Data Communication Protocol. American Society for Engineering Education, 8.
Kayri, I., & Gencoglu, M. T. (2019). Predicting power production from a photovoltaic panel through artificial neural networks using atmospheric indicators. Neural Computing and Applications, 31(8), 3573–3586. https://doi.org/10.1007/s00521-017-3271-6
Keddouda, A., Ihaddadene, R., Boukhari, A., Atia, A., Arıcı, M., Lebbihiat, N., & Ihaddadene, N. (2023). Solar photovoltaic power prediction using artificial neural network and multiple regression considering ambient and operating conditions. Energy Conversion and Management, 288(April), 117186. https://doi.org/10.1016/j.enconman.2023.117186
Kılıç, B., & Kumaş, K. (2016). Burdur İli Güneşlenme Değerlerinin Yapay Sinir Ağları Metodu İle Tahmini. SDÜ Teknik Bilimler Dergisi, 6(1), 38–44.
Magee, L. (1990). R2 Measures Based on Wald and Likelihood Ratio Joint Significance Tests. The American Statistician, 44(3), 250–253. https://doi.org/10.1080/00031305.1990.10475731
Oviedo, D., Romero-Ternero, M. C., Carrasco, A., Sivianes, F., Hernandez, M. D., & Escudero, J. I. (2013). Multiagent system powered by neural network for positioning control of solar panels. IECON Proceedings (Industrial Electronics Conference), 3615–3620. https://doi.org/10.1109/IECON.2013.6699710
Oviedo, D., Romero-Ternero, M. C., Hernández, M. D., Sivianes, F., Carrasco, A., & Escudero, J. I. (2014). Multiple intelligences in a MultiAgent System applied to telecontrol. Expert Systems with Applications, 41(15), 6688–6700. https://doi.org/10.1016/j.eswa.2014.04.048
Ozbeyaz, A., & Demirci, Y. (2019). Investigation of Correlation between the Solar Energy Efficiency And Air Pollution Using Decision Tree Algorithm. 4th International Engineering and Natural Sciences Conference, 782–789.
Pierce, B. G., Braid, J. L., Stein, J. S., Augustyn, J., & Riley, D. (2022). Solar Transposition Modeling via Deep Neural Networks with Sky Images. IEEE Journal of Photovoltaics, 12(1), 145–151. https://doi.org/10.1109/JPHOTOV.2021.3120508
Postawa, K., Czarnecki, M., Wrzesińska-Jędrusiak, E., Łyskawiński, W., & Kułażyński, M. (2024). Cascade-Forward, Multi-Parameter Artificial Neural Networks for Predicting the Energy Efficiency of Photovoltaic Modules in Temperate Climate. Applied Sciences (Switzerland), 14(7). https://doi.org/10.3390/app14072764
Schapire, R. E. (1990). The Strength of Weak Learnability. In Machine Learning (pp. 197–227).
Sharma, M. K., & Bhattacharya, J. (2020). A novel stationary concentrator to enhance solar intensity with absorber-only single axis tracking. Renewable Energy, 154, 976–985. https://doi.org/10.1016/j.renene.2020.03.064
Shim, J., Park, S., & Song, D. (2025). Impact of particulate matter (PM10, PM2.5) on global horizontal irradiance and direct normal irradiance in urban areas. Building and Environment, 271(September 2024), 112610. https://doi.org/10.1016/j.buildenv.2025.112610
Stone, M. (1974). Cross-Validatory Choice and Assessment of Statistical Predictions. Journal of the Royal Statistical Society Series B: Statistical Methodology, 36(2), 111–133. https://doi.org/10.1111/j.2517-6161.1974.tb00994.x
Temel, G. O., Ankaralı, H., Taşdelen, B., Erdoğan, S., & Özge, A. (2014). A Comparison of Boosting Tree and Gradient Treeboost Methods for Carpal Tunnel Syndrome. Turkey Clinicians Journal of Biostatistics, 6(2), 67–73.
Uz, Ö., Özdemir, T., & Özmen, Ö. T. (2022). Estimating Energy Production of Solar Power Plant at the University of Bakırçay Using Artificial Neural Networks Based on Meteorological Conditions. Artificial Intelligence Theory and Applications, 2(1), 27–40.
Wu, Y., & Zhou, J. (2019). Risk assessment of urban rooftop distributed PV in energy performance contracting (EPC) projects: An extended HFLTS-DEMATEL fuzzy synthetic evaluation analysis. Sustainable Cities and Society, 47, 101524. https://doi.org/10.1016/j.scs.2019.101524
Yadav, A. K., & Chandel, S. S. (2013). Tilt angle optimization to maximize incident solar radiation: A review. Renewable and Sustainable Energy Reviews, 23, 503–513. https://doi.org/10.1016/j.rser.2013.02.027
Zhou, X., Cao, Z., Ma, Y., Wang, L., Wu, R., & Wang, W. (2016). Concentrations, correlations and chemical species of PM2.5/PM10 based on published data in China: Potential implications for the revised particulate standard. Chemosphere, 144, 518–526. https://doi.org/10.1016/j.chemosphere.2015.09.003
Downloads
Published
Data Availability Statement
No datasets were generated or analyzed during the current study.
Issue
Section
License
Copyright (c) 2025 Abdurrahman Özbeyaz
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright of their work and grant the journal the right to publish it under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This allows for maximum dissemination and reuse with appropriate citation.
ORCID 
