10.57647/ijeee.2025.1602.06

Feature Selection and Seasonal Variability in Forecasting Global Horizontal Irradiance: Insights from Riyadh Meteorology

Show Details XML PDF
  • Debasish Sarker*1,
  • Mohammad K Hossain2,
  • Md Arifuzzaman3,
  1. Department of Mechanical Engineering, International University of Business Agriculture and Technolog, Dhaka, Bangladesh
  2. King Fahd University of Petroleum and Minerals College of Science, Dhahran, Eastern Province, Saudi Arabia
  3. Civil and Environmental Engineering, King Faisal Universit, Al Ahsa, Eastern Province, Saudi Arabia

Received: 2025-12-16

Accepted: 2025-01-25

Published in Issue 2025-06-30

Copyright (c) 2025 Debasish Sarker, Mohammad K Hossain, Md Arifuzzaman (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Sarker, D., Hossain, M. K., & Arifuzzaman, M. (2025). Feature Selection and Seasonal Variability in Forecasting Global Horizontal Irradiance: Insights from Riyadh Meteorology. International Journal of Energy and Environmental Engineering, 16(02). https://doi.org/10.57647/ijeee.2025.1602.06
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 174

Abstract

This study investigates the seasonal variability of meteorological feature importance in forecasting Global Horizontal Irradiance (GHI) using machine learning (ML) and deep learning models. High-resolution solar and meteorological data from NREL’s NSRDB (24.25°N, 45.34°E, 740 m) were seasonally partitioned into winter, spring, summer, and autumn. Feature selection was conducted using Pearson correlation (threshold 0.25), followed by dimensionality reduction through Principal Component Analysis (PCA). Six ML models XGBoost, LightGBM, Random Forest, SVR, MLP, and LSTM were trained on the processed datasets, and SHAP analysis was used to interpret feature contributions. The results revealed that clear-sky irradiance parameters (GHI, DNI, DHI) consistently dominated GHI prediction (correlation >0.95; SHAP >10⁻¹), while features like temperature and relative humidity varied across seasons. Wind direction, though weakly correlated, showed increased influence in winter. PCA enhanced model stability in spring and winter but slightly reduced accuracy during periods of high irradiance variability. Overall, XGBoost and Random Forest models provided the most accurate and reliable forecasts across seasons.

Keywords

  • Renewable energy,
  • Solar Forecasting,
  • Machine learning,
  • Seasonal effect,
  • Feature selection
PDF

References

  1. Barhmi, Khadija, Chris Heynen, Sara Golroodbari, and Wilfried van Sark. "A review of solar forecasting techniques and the role of artificial intelligence." In Solar, vol. 4, no. 1, pp. 99-135. MDPI, 2024.
  2. Tercha, Wassila, Sid Ahmed Tadjer, Fathia Chekired, and Laurent Canale. "Machine learning-based forecasting of temperature and solar irradiance for photovoltaic systems." Energies 17, no. 5 (2024): 1124.
  3. Dos Reis, Josivan R., Jonathan M. Tabora, Matheus C. Lima, Flávia P. Monteiro, Suzane CA Monteiro, Ubiratan H. Bezerra, and Maria EL Tostes. "Medium and Long Term Energy Forecasting Methods: A Literature Review." IEEE Access (2025).
  4. Boubii, Chaymae, Ismail El Kafazi, Rachid Bannari, Brahim El Bhiri, Badre Bossoufi, Hossam Kotb, Kareem M. AboRas, Ahmed Emara, and Badr Nasiri. "Synergizing wind and solar power: An advanced control system for grid stability." Sustainability 16, no. 2 (2024): 815.
  5. Shair, Jan, Haozhi Li, Jiabing Hu, and Xiaorong Xie. "Power system stability issues, classifications and research prospects in the context of high-penetration of renewables and power electronics." Renewable and Sustainable Energy Reviews 145 (2021): 111111.
  6. Alajrash, Ban H., Mohamed Salem, Mahmood Swadi, Tomonobu Senjyu, Mohamad Kamarol, and Saad Motahhir. "A comprehensive review of FACTS devices in modern power systems: Addressing power quality, optimal placement, and stability with renewable energy penetration." Energy Reports 11 (2024): 5350-5371.
  7. Gaboitaolelwe, Jwaone, Adamu Murtala Zungeru, Abid Yahya, Caspar K. Lebekwe, Dasari Naga Vinod, and Ayodeji Olalekan Salau. "Machine learning based solar photovoltaic power forecasting: A review and comparison." IEEe Access 11 (2023): 40820-40845.
  8. AlKandari, Mariam, and Imtiaz Ahmad. "Solar power generation forecasting using ensemble approach based on deep learning and statistical methods." Applied Computing and Informatics 20, no. 3/4 (2024): 231-250.
  9. Singh, Upma, Shekhar Singh, Saket Gupta, Majed A. Alotaibi, and Hasmat Malik. "Forecasting rooftop photovoltaic solar power using machine learning techniques." Energy Reports 13 (2025): 3616-3630.
  10. Jung, Yoonhwa, Jaehoon Jung, Byungil Kim, and SangUk Han. "Long short-term memory recurrent neural network for modeling temporal patterns in long-term power forecasting for solar PV facilities: Case study of South Korea." Journal of Cleaner Production 250 (2020): 119476.
  11. Das, Utpal Kumar, Kok Soon Tey, Mohd Yamani Idna Bin Idris, Saad Mekhilef, Mehdi Seyedmahmoudian, Alex Stojcevski, and Ben Horan. "Optimized support vector regression-based model for solar power generation forecasting on the basis of online weather reports." IEEE Access 10 (2022): 15594-15604.
  12. Obiora, Chibuzor N., Ahmed Ali, and Ali N. Hasan. "Implementing extreme gradient boosting (XGBoost) algorithm in predicting solar irradiance." In 2021 IEEE PES/IAS PowerAfrica, pp. 1-5. IEEE, 2021.
  13. Muhammad Ehsan, R., Sishaj P. Simon, and P. R. Venkateswaran. "Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron." Neural Computing and Applications 28 (2017): 3981-3992.
  14. Liu, Da, and Kun Sun. "Random forest solar power forecast based on classification optimization." Energy 187 (2019): 115940.
  15. Sharadga, Hussein, Shima Hajimirza, and Robert S. Balog. "Time series forecasting of solar power generation for large-scale photovoltaic plants." Renewable Energy 150 (2020): 797-807.
  16. Bett, Philip E., Hazel E. Thornton, Alberto Troccoli, Matteo De Felice, Emma Suckling, Laurent Dubus, Yves-Marie Saint-Drenan, and David J. Brayshaw. "A simplified seasonal forecasting strategy, applied to wind and solar power in Europe." Climate services 27 (2022): 100318.
  17. Chattopadhyay, Sameep, Pulkit Paliwal, Sai Shankar Narasimhan, Shubhankar Agarwal, and Sandeep P. Chinchali. "Context Matters: Leveraging Contextual Features for Time Series Forecasting." arXiv preprint arXiv:2410.12672 (2024).
  18. Wogrin, Sonja. "Time series aggregation for optimization: One-size-fits-all?." IEEE Transactions on Smart Grid 14, no. 3 (2023): 2489-2492.
  19. Castangia, Marco, Alessandro Aliberti, Lorenzo Bottaccioli, Enrico Macii, and Edoardo Patti. "A compound of feature selection techniques to improve solar radiation forecasting." Expert Systems with Applications 178 (2021): 114979.