Estimation of energy production of solar panels installed in agricultural areas with machine learning algorithms

Year 2025, Volume: 9 Issue: 1, 221 - 232, 17.03.2025

Taşkın Tez , Erhan Akyol

https://doi.org/10.31015/2025.1.24

Abstract

Predicting solar power generation is used to ensure that solar power plants operate with optimum efficiency, meet the demands of the energy grid and stabilize energy prices. This study aims to predict the medium-term electricity generation of photovoltaic panels with machine learning algorithms. Boosting Regression, Decision Tree Regression, K-Nearest Neighbors Regression, Neural Network Regression, Random Forest Regression, Regularized Linear Regression, and Support Vector Machine Regression algorithms were evaluated. Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-Squared (R²) were calculated. It was found that the Random Forest algorithm has the best prediction metrics. A hypothesis was formulated to evaluate the difference between the actual energy generation of the photovoltaic panels and the predicted energy by the Random Forest algorithm. The hypothesis was evaluated by the Mann-Whitney U hypothesis test and the p-value was calculated as greater than 0.05. It was concluded that there is no significant difference between the predicted energy by the Random Forest (RF) algorithm and the actual energy generated by photovoltaic panels. Based on the results of this study, we recommend using the Random Forest algorithm for medium-term energy generation prediction for photovoltaic solar panels.

Keywords

Photovoltaic, Energy, Prediction, Machine Learning

References

• Akman, T., Yılmaz, C., & Sönmez, Y. (2018). Elektrik Yükü Tahmin Yöntemlerinin Analizi. Gazi Mühendislik Bilimleri Dergisi, 4(3), 168-175. DOI: 10.30855/GJES.2018.04.03.003
• AlSkaif, T., Dev, S., Visser, L., Hossari, M., Sark, W. (2020). A systematic analysis of meteorological variables for PV output power estimation. Renewable Energy, 153, 12-22. https://doi.org/10.1016/j.renene.2020.01.150
• Anupong, W., Jweeg, M., Alani, S., Al-Kharsan, I., Alviz-Meza, A., & Cárdenas-Escrocia, Y. (2023). Comparison of Wavelet Artificial Neural Network, Wavelet Support Vector Machine, and Adaptive Neuro-Fuzzy Inference System Methods in Estimating Total Solar Radiation in Iraq. Energies, 16(2), 985. https://doi.org/10.3390/en16020985
• Arce, J. M. M., & Macabebe E. Q. B. (2019). Real-Time Power Consumption Monitoring and Forecasting Using Regression Techniques and Machine Learning Algorithms. IEEE International Conference on Internet of Things and Intelligence System (IoTaIS), 135-140. DOI: 10.1109/IoTaIS47347.2019.8980380
• Cattani, G. (2023). Combining data envelopment analysis and Random Forest for selecting optimal locations of solar PV plants. Energy and AI, 11, 100222. https://doi.org/10.1016/j.egyai.2022.100222
• Chicco, D., Warrens, M., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci., 1-24. DOI: 10.7717/peerj-cs.623
• Das, K., & Imon, A. H. M. R. (2016). A Brief Review of Tests for Normality. American Journal of Theoretical and Applied Statistics, 5(1), 5-12. DOI: 10.11648/j.ajtas.20160501.12
• Didavi, A. B. K., Agbokpanzo, R. G., & Agbomahena, M. (2021). Comparative study of Decision Tree, Random Forest and XGBoost performance in forecasting the power output of a photovoltaic system. 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART), 1-5. DOI: 10.1109/BioSMART54244.2021.9677566
• Heumann, C., Schomaker, M., & Shalabh (2022). Introduction to Statistics and Data Analysis With Exercises, Solutions and Applications in R. Springer International Publishing
• IEA (2022). data-and-statistics/data-tools. Retrieved in August, 19, 2023 from https://www.iea.org/data-and-statistics/data-tools/energy-statistics-data-browser?country=WORLD&fuel=Energy%20consumption&indicator=TotElecCons
• jamovi.org (2023). https://www.jamovi.org/download.html. Retrieved in May, 19, 2023 from https://www.jamovi.org/
• jasp-stats.org (2023). https://jasp-stats.org/download/. Retrieved in May, 19, 2023 from https://jasp-stats.org/
• Jebli, I., Belouadha, F.-Z., Kabbaj, M. I., & Tilioua, A. (2021). Prediction of solar energy guided by pearson correlation using machine learning. Energy, 224, 1-20. https://doi.org/10.1016/j.energy.2021.120109
• Li, G., Wang, H., Zhang, S., Xin, J., & Liu, H. (2019). Recurrent Neural Networks Based Photovoltaic Power Forecasting Approach. Energies, 12(13), 2538. DOI:10.3390/en12132538
• Li, G., Xie, B., Xin, J., Li, Y., & Du, S. (2020). Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach. IEEE Access, 8, 175871-175880. DOI:10.1109/ACCESS.2020.3025860
• Liu, D., & Sun, K. (2019). Random forest solar power forecast based on classification optimization. Energy, 187, 115940. https://doi.org/10.1016/j.energy.2019.115940
• Mahmud, K., Azam, S., Karim, A., Zobead, S., Shanmugam, B., & Mathur, D. (2021). Machine Learning Based PV Power Generation Forecasting in Alice Springs. IEEE Access, 9, 46117-46128. DOI: 10.1109/ACCESS.2021.3066494
• Munawar, U., & Wang, Z. (2020). A Framework of Using Machine Learning Approaches for Short-Term Solar Power Forecasting. J. Electr. Eng. Technol, 15, 561-569. https://doi.org/10.1007/s42835-020-00346-4
• Qu, Y., Xu, J., Sun, Y., & Liu, D. (2021). A temporal distributed hybrid deep learning model for day-ahead distributed PV power forecasting, Applied Energy, 304, 117704. https://doi.org/10.1016/j.apenergy.2021.117704
• Rabaia, M. K. H., Abdelkareem, M. A., Sayed, E. T., Elsaid, K., Chae, K.-J., Wilberforce, T., & Olabi, A. (2021). Environmental impacts of solar energy systems: A review. Science of The Total Environment, 754, 1-19. https://doi.org/10.1016/j.scitotenv.2020.141989
• Sadorsky, P. (2021). A Random Forests Approach to Predicting Clean Energy Stock Prices. J. Risk Financial Manag, 14(2), 48. https://doi.org/10.3390/jrfm14020048
• Shapsough, S., Dhaouadi, R., & Zualkernan, I. (2019). Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules. Procedia Computer Science, 155, 463-470. https://doi.org/10.1016/j.procs.2019.08.065
• Sridharan, M., Jayaprakash, G., Chandrasekar, M., Vigneshwar, P., Paramaguru, S., & Amarnath, K. (2018). Prediction of Solar Photovoltaic/Thermal Collector Power Output Using Fuzzy Logic. Journal of Solar Energy Engineering, 140(6), 061013. https://doi.org/10.1115/1.4040757
• Visser, L., AlSkaif, T., & Sark, W. (2022). Operational day-ahead solar power forecasting for aggregated PV systems with a varying spatial distribution. Renewable Energy, 183, 267-282. https://doi.org/10.1016/j.renene.2021.10.102
• Zhang, H., & Zhu, T. (2022). Stacking Model for Photovoltaic-Power-Generation Prediction. Sustainability, 14(9), 5669. https://doi.org/10.3390/su14095669