Machine Learning Approaches to Short-Term Solar Irradiance Forecasting: Performance Comparison of Random Forest and Multilayer Perceptron Models

Year 2026, Volume: 6 Issue: 1, 48 - 58, 27.02.2026

Rabia Sultan Yıldırım

https://doi.org/10.5152/tepes.2026.25039

https://izlik.org/JA93PY53DL

Abstract

This study presents a comprehensive framework for short-term solar irradiance forecasting in the Adana Organized Industrial Zone, one of Türkiye’s most solarrich regions. High-resolution irradiance data collected throughout 2024 using ISO 9060–compliant pyranometers were analyzed to capture seasonal and daily variations, with annual cumulative global horizontal irradiance measured at ~1346 kWh/m2. Two machine learning approaches were applied to predict hourly irradiance: Random Forest (RF) regression and multilayer perceptron (MLP) neural networks. Input features included persistence-based irradiance values, diurnal and seasonal indicators, and time-series variables. Model performance was evaluated using mean absolute error, root mean square error (RMSE), and R2 metrics. Results indicated that RF achieved superior accuracy (R2 = 0.891, RMSE = 0.472 kWh/m2) compared to MLP (R2 = 0.874, RMSE = 0.514 kWh/m2), highlighting the robustness of ensemble methods for short-term forecasting. Uncertainty analysis confirmed that measurement errors and cloudy-day conditions remain key challenges. Unlike previous studies, this work provides one of the first high-resolution, region-specific datasets for industrial-scale solar forecasting in Türkiye. Overall, the findings demonstrate that data-driven forecasting can effectively support photovoltaic (PV) system operation, smart grid integration, and regional energy planning, providing valuable insights for the sustainable energy transition in Türkiye.

Keywords

Adana OSB , machine learning , MLP regressor , photovoltaic systems , Random Forest , solar irradiance forecasting

References

• 1. “İklim Değişikliğine uyum Stratejisi ve eylem planı 2024-2030,” Available: https:// iklim.go v.tr/db/ turkce/i cerikler /files/.
• 2. A. J. Samimi, and M. Ahmadpour, “Comparison of Environmental Performance Index (EPI) in OIC countries: Before and after financial crisis,” Adv. Environ. Biol., pp. 201–209, 2011.
• 3. M. S. Naveed, I. Iqbal, M. F. Hanif, J. Xiao, X. Liu, and J. Mi, “Enhanced accuracy in solar irradiance forecasting through machine learning stackbased ensemble approach,” Int. J. Green Energ., vol. 22, no. 10, pp. 2126–2149, 2025.
• 4. S. T. Asiedu, A. Suvedi, Z. Wang, H. M. Rekabdarkolaee, and T. M. Hansen, “Spatiotemporal downscaling model for solar ırradiance forecast using nearest-neighbor random forest and Gaussian process,” Energies, vol. 18, no. 10, p. 2447, 2025.
• 5. Y. Mariappan, K. Ramasamy, and D. Velusamy, “An optimized deep learning based hybrid model for prediction of daily average global solar irradiance using CNN SLSTM architecture,” Sci. Rep., vol. 15, no. 1, p. 10761, 2025.
• 6. O. Trull, J. C. García-Díaz, and A. Peiró-Signes, “A comparative study of statistical and machine learning methods for solar irradiance forecasting using the Folsom PLC dataset,” Energies, vol. 18, no. 15, p. 4122, 2025.
• 7. S. R. Pattnaik, R. Bisoi, and P. K. Dash, “Solar irradiance forecasting using hybrid long-short-term-memory-based recurrent ensemble deep random vector functional link network,” Comput. Electr. Eng., vol. 123, p. 110174, 2025.
• 8. U. Singh, S. Singh, S. Gupta, M. A. Alotaibi, and H. Malik, “Forecasting rooftop photovoltaic solar power using machine learning techniques,” Energy Rep., vol. 13, pp. 3616–3630, 2025.
• 9. V. Demir, “Evaluation of solar radiation prediction models using AI: A performance comparison in the high-potential region of Konya, Türkiye,” Atmosphere, vol. 16, no. 4, p. 398, 2025.
• 10. T. Dewi, E. N. Mardiyati, P. Risma, and Y. Oktarina, “Hybrid machine learning models for PV output prediction: Harnessing random forest and LSTM-RNN for sustainable energy management in aquaponic system,” Energy Convers. Manag., vol. 330, p. 119663, 2025.
• 11. S. Mohan, “Applying ensemble machine learning models to predict hydrogen production rates from conventional and novel solar PV/T water collectors,” Int. J. Hydrog. Energy, vol. 102, pp. 1377–1398, 2025.
• 12. A. Hu, Z. Duan, Y. Zhang, Z. Huang, T. Ji, and X. Yin, “Impact of PM2.5 pollution on solar photovoltaic power generation in Hebei Province, China,” Energies, vol. 18, no. 15, p. 4195, 2025.
• 13. I. Benrabia, and D. Söffker, “Modeling and evaluation of forecasting models for energy production in wind and photovoltaic systems,” Energies, vol. 18, no. 3, p. 625, 2025.
• 14. S. Zator, J. Osuchowski, S. S. Kasana, N. A. Shelke, and M. Tomaszewski, “Energy generation in a multi-sided photovoltaic system: Analysis of the prediction effectiveness,” Renew. Energy, vol. 251, p. 123325, 2025.
• 15. F. V. Mucomole, C. A. S. Silva, and L. L. Magaia, “Modeling parametric forecasts of solar energy over time in the mid-north area of Mozambique,” Energies, vol. 18, no. 6, p. 1469, 2025.
• 16. D. T. Bui, D. N. Nguyen, and T. L. H. Pham, “A reinforcement learningbased framework for short-term and long-term solar irradiance forecasting in microgrid,” Smart Grids Sustain. Energy, vol. 10, no. 2, pp. 1–21, 2025.
• 17. A. Tandon, A. Awasthi, K. C. Pattnayak, A. Tandon, T. Choudhury, and K. Kotecha, “Machine learning-driven solar irradiance prediction: Advancing renewable energy in Rajasthan,” Discov. Appl. Sci., vol. 7, no. 2, p. 107, 2025.
• 18. C. Voyant, M. Despotovic, G. Notton, Y.-M. Saint-Drenan, M. Asloune, and L. Garcia-Gutierrez, “On the importance of clearsky model in shortterm solar radiation forecasting,” Sol. Energy, vol. 294, p. 113490, 2025.
• 19. F. W. Mugware, T. Ravele, and C. Sigauke, “Short-term predictions of global horizontal ırradiance using recurrent neural networks, support vector regression, gradient boosting, random forest, and advanced stacking ensemble approaches,” Computation, vol. 13, no. 3, p. 72, 2025.
• 20. B. Ladjal et al., “Hybrid deep learning CNN-LSTM model for forecasting direct normal irradiance: A study on solar potential in Ghardaia, Algeria,” Sci. Rep., vol. 15, no. 1, p. 15404, 2025.
• 21. C. Vanlalchhuanawmi, S. Deb, M. M. Islam, and T. S. Ustun, “Solar radiation prediction: A multi-model machine learning and deep learning approach,” AIP Adv., vol. 15, no. 5, 2025.
• 22. Y. Zhang, “Enhancing solar irradiance prediction for sustainable energy solutions employing a hybrid machine learning model; improving hydrogen production through Photoelectrochemical device,” Appl. Energy, vol. 382, p. 125280, 2025.
• 23. S. Benkaciali, G. Notton, and C. Voyant, “Comparative study of feature selection techniques for machine learning-based solar ırradiation forecasting to facilitate the sustainable development of photovoltaics: Application to Algerian climatic conditions,” Sustainability, vol. 17, no. 14, p. 6400, 2025.
• 24. A. A. Hassan, D. M. Atia, H. T. El-Madany, and F. ElGhannam, “Multi-label machine learning for power forecasting of a grid-connected photovoltaic solar plant over multiple time horizons,” Sci. Rep., vol. 15, no. 1, p. 32676, 2025.
• 25. N. Vilakazi, and T. van Zyl, “Deep learning forecasting of photovoltaics output using digital twin data,” in Southern African Conference for Artificial Intelligence Research, 2024, pp. 405–419: Springer.
• 26. M. Diantoro, T. Suprayogi, A. Hidayat, A. Taufiq, A. Fuad, and R. Suryana, “Shockley’s equation Fit analyses for solar cell parameters from I‐V Curves,” Int. J. Photoenergy, vol. 2018, no. 1, pp. 1–7, 2018.
• 27. U. Grömping, “Variable importance assessment in regression: Linear regression versus random forest,” Am. Stat., vol. 63, no. 4, pp. 308–319, 2009.
• 28. E. Yassine, and K. Mohammed, “A comparative analysis of decision trees, bagging, and random forests for predictive modeling in monetary poverty: Evidence from Morocco,” Appl. Math. Inf. Sci., vol. 18, no. 2, pp. 233–240, 2024.
• 29. A. Pinkus, “Approximation theory of the MLP model in neural networks,” Acta Numer., vol. 8, pp. 143–195, 1999.
• 30. S. Abdullah, M. Ismail, and A. Ahmed, “Multi-layer perceptron model for air quality prediction,” Malays, J. Math. Sci., vol. 13, pp. 85–95, 2019.