AI/ML-Based Approach to Solar Irradiance Prediction and Energy Suitability

Year : 2025 | Volume : 16 | Issue : 03 | Page : 36 48
    By

    Kavya Srivastava,

  • Krati Garg,

  • Palak Agarwal,

  • Pallavi Gupta,

  • Ravi Kumar,

  1. Student, Department of Computer Science Engineering (Data-Science), ABES Engineering College, Ghaziabad, Uttar Pradesh, India
  2. Student, Department of Computer Science Engineering (Data-Science), ABES Engineering College, Ghaziabad, Uttar Pradesh, India
  3. Student, Department of Computer Science Engineering (Data-Science), ABES Engineering College, Ghaziabad, Uttar Pradesh, India
  4. Student, Department of Computer Science Engineering (Data-Science), ABES Engineering College, Ghaziabad, Uttar Pradesh, India
  5. Student, Department of Computer Science Engineering (Data-Science), ABES Engineering College, Ghaziabad, Uttar Pradesh, India

Abstract

In this paper, due to challenges in precisely predicting solar irradiance, which is essential for solar power system optimization, we employed six diverse machine learning (ML) techniques: Linear Regression, Decision Tree, Random Forest, Gradient Boosting methods (including XGBoost), and Neural Networks—to analyze and predict outcomes using a dataset containing meteorological and temporal features. Key variables include wind speed, humidity, and temperature, which significantly influence the model’s predictive capability. Each method is evaluated for its accuracy, interpretability, and computational efficiency. Linear Regression provides a baseline, Decision Trees offer interpretability, Random Forests enhance robustness, Gradient Boosting improves precision through sequential learning, and Neural Networks capture complex nonlinear patterns. This comparative approach enables selection of the most effective model for the given prediction task. Ensemble models, especially Random Forest and Gradient Boosting, are excellent in capturing intricate data correlations, according to performance measures like RMSE, MAE, and MAPE. This study also highlights the role of feature selection in enhancing the effectiveness of the model. The results in this study show the revolutionary potential of ML in improving solar energy systems and highlight the importance of temporal aspects in improving forecast accuracy. This research focuses on enhancing the reliability of solar irradiance predictions, which in turn support the wider use of solar energy and advancing the global shift toward renewable energy solutions.

Keywords: Solar irradiance prediction, solar energy machine learning, renewable energy, energy forecasting, ensemble learning, random forest, gradient boosting

[This article belongs to Journal of Alternate Energy Sources & Technologies ]

How to cite this article:
Kavya Srivastava, Krati Garg, Palak Agarwal, Pallavi Gupta, Ravi Kumar. AI/ML-Based Approach to Solar Irradiance Prediction and Energy Suitability. Journal of Alternate Energy Sources & Technologies. 2025; 16(03):36-48.
How to cite this URL:
Kavya Srivastava, Krati Garg, Palak Agarwal, Pallavi Gupta, Ravi Kumar. AI/ML-Based Approach to Solar Irradiance Prediction and Energy Suitability. Journal of Alternate Energy Sources & Technologies. 2025; 16(03):36-48. Available from: https://journals.stmjournals.com/joaest/article=2025/view=227564


References

  1. Blaga R, Sabadus A, Stefu N, Verscea M, Dughir C, Paulescu M, et al. A current perspective on the accuracy of incoming solar energy forecasting. Prog Energy Combust Sci. 2019;70:119–44.
  2. Chakkaravarthy AN, Subathra MSP, Pradeep PJ, Kumar NM. Solar irradiance forecasting and energy optimization for achieving nearly net zero energy building. J Renew Sustain Energy. 2018;10(3).
  3. Piri J, Shamshirband S, Chau KW, Tong CW, Malvoni M, Hossain U, et al. Prediction of the solar radiation on the Earth using support vector regression technique. Infrared Phys Technol. 2015;73:179–85.
  4. Jebli I, Belouadha F-Z, Kabbaj MI, Tilioua A. Prediction of solar energy guided by Pearson correlation using machine learning. Energy. 2021;224:120109.
  5. Wang F, Xuan Z, Zhen Z, Yu Y, Li K, Liu K, et al. A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model. Energy Convers Manag. 2020;220:113070.
  6. Ahmad T, Zhang D, Cai H, Hui H, Zhang D, Song C, et al. Artificial intelligence in sustainable energy industry: Status quo, challenges and opportunities. J Clean Prod. 2021;289:125449.
  7. Wang L, Meng M, Jia X, Zhang Z, Li H, Zhang H, et al. Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model. Energy. 2023;262:125444.
  8. Alzahrani A, Shamsi P, Dagli C, Ferdowsi M. Solar irradiance forecasting using deep neural networks. Procedia Comput Sci. 2017;114:304–13.
  9. Lima MAFB, Pereira CR, Costa MGF, Fernandes R, Bezerra B, Portela B, et al. Improving solar forecasting using deep learning and portfolio theory integration. Energy. 2020;195:116925.
  10. Marquez R, Coimbra CF. Proposed metric for evaluation of solar forecasting models. Sol Energy. 2013;102:313–8.
  11. Yang D. Standard of reference in operational day-ahead deterministic solar forecasting. J Renew Sustain Energy. 2019;11:036102.
  12.  Mayer MJ, Gróf G. Extensive comparison of physical models for photovoltaic power forecasting. Appl Energy. 2021;283:116239.
  13. Sharma R, Saini LM. Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction. Renew Sustain Energy Rev. 2022;161:112280.
  14. Antonanzas J, Osorio N, Escobar R, Urraca R, Martinez-de-Pison FJ, Antonanzas-Torres F. Review of photovoltaic power forecasting. Sol Energy. 2016;136:78–111.
  15. Mellit A, Massi Pavan AM, Lughi V, Ayadi O. Deep learning neural networks for short-term photovoltaic power forecasting. Renew Energy. 2021;172:276–88.
  16. Yagli GM, Yang D, Srinivasan D. Automatic hourly solar forecasting using machine learning models. Renew Sustain Energy Rev. 2019;105:487–98.
  17. Wang J, Ouyang A, Ruan B. Potential solar energy use in the global petroleum sector. Energy. 2017;118:884–92.
  18. Roig K, Ayub A, Al-Ammar R, Radwan K. Sensitivity analysis for solar-generated steam for enhanced oil recovery. Soc Pet Eng. 2018.
  19. Sandler J, Freeman G, Curtis K, Kumar A. Solar-generated steam for oil recovery: Reservoir simulation, economic analysis, and life cycle assessment. Energy Procedia. 2012;29:176–85.
  20. O’ onnell J , eller-Lessmann M, McGregor C. Solar-generated steam for oil recovery: Process integration options, net energy fraction, and carbon market impacts. Energy Procedia. 2015;69:1390–9.
Regular Issue Subscription Original Research
Volume 16
Issue 03
Received 05/07/2025
Accepted 12/08/2025
Published 19/09/2025
Publication Time 76 Days
160

Login


My IP

PlumX Metrics