JUCS - Journal of Universal Computer Science 32(3): 448-483, doi: 10.3897/jucs.160204
Grey Wolf Optimization and Deep Belief Networks for Data-Efficient Forecasting in Smart Renewable Energy Systems
Abdulhadi Altherwi‡, Md. Mottahir Alam§, Mastoor M. Abushaega‡, Ahmed Hamzi‡, Abdulmajeed Azyabi‡, Shabbir Hassan|, Asif Irshad Khan|‡ Jazan University, Jazan, Saudi Arabia§ Indian Institute of Technology Patna, Patna, India| Aligarh Muslim University, Aligarh, India
Corresponding author: Asif Irshad Khan ( airshad.cs@amu.ac.in ) © Abdulhadi Altherwi, Md. Mottahir Alam, Mastoor M. Abushaega, Ahmed Hamzi, Abdulmajeed Azyabi, Shabbir Hassan, Asif Irshad Khan. This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Citation:
Altherwi A, Alam MdM, Abushaega MM, Hamzi A, Azyabi A, Hassan S, Khan AI (2026) Grey Wolf Optimization and Deep Belief Networks for Data-Efficient Forecasting in Smart Renewable Energy Systems. JUCS - Journal of Universal Computer Science 32(3): 448-483. https://doi.org/10.3897/jucs.160204 |  |
Abstract
The integration of hybrid renewable energy systems (HRES) has introduced both opportunities and challenges in managing multisource power systems such as wind and solar. Accurate forecasting of HRES performance is critical to efficient planning and grid stability. This paper proposes a data efficient hybrid framework that combines Grey Wolf Optimization (GWO) for feature selection with Deep Belief Networks (DBN) for predictive modeling. GWO effectively selects relevant features from high dimensional environmental and system parameters, reducing computational burden and enhancing learning performance. The DBN is then trained on the optimized input set to forecast system performance. Two public datasets capturing wind and solar power production across distinct geographic conditions were used for validation. The proposed model significantly outperforms conventional methods, achieving a mean square error of 0.0207, RMSE of 0.144, and an energy efficiency of 98.32%. These results demonstrate the framework’s potential for deployment in smart grid forecasting environments.
Keywords
Computational Intelligence, Deep Belief Network, Grey Wolf Optimization, Hybrid Renewable Energy Systems, Metaheuristic Feature Selection, Smart Grid Forecasting