An Optimized Hybrid Bio-Inspired Framework for Machine Learning-Based 5G Resource Allocation
Proceedings of Engineering and Technology Innovation · 15.09.2026 · 34 · 01-16
DOI: 10.46604/peti.2026.16627 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of Engineering and Technology Innovation, online erschienen am 15.09.2026. Verfasst von Esraa Taha Heussien und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study presents a lightweight hybrid framework for optimizing radio resource allocation in 5G networks, enabling high prediction accuracy with low computational complexity for edge deployment. A binary grey wolf optimization (BGWO) algorithm is used for feature selection, while a continuous GWO algorithm is used for hyperparameter adjustment of nine regression models trained using machine learning on a pre-processed public dataset for 5G networks. To ensure evaluation integrity, the dataset is segmented for training, validation, and testing before feature selection and expansion, preventing data leakage. Model performance is assessed using mean squared error (MSE) and the coefficient of determination (R²). The optimized decision tree achieves the best overall performance, improving R² from 46.32% to 99.44% and reducing MSE from 0.00470 to 0.00005, while random forest and support vector machine (SVM) exceed 99% R². These results demonstrate that the proposed framework achieves accurate and computationally efficient resource allocation for 5G networks.
Zitieren
APA
Heussien, E. T., & Abdulwahab, W. K. (2026). An Optimized Hybrid Bio-Inspired Framework for Machine Learning-Based 5G Resource Allocation. Proceedings of Engineering and Technology Innovation, 34, 01-16. https://doi.org/10.46604/peti.2026.16627
Vancouver
Heussien ET, Abdulwahab WK. An Optimized Hybrid Bio-Inspired Framework for Machine Learning-Based 5G Resource Allocation. Proceedings of Engineering and Technology Innovation. 2026;34:01-16. doi:10.46604/peti.2026.16627
BibTeX
@article{Heussien2026,
author = {Heussien, Esraa Taha and Abdulwahab, Walled Khalid},
title = {An Optimized Hybrid Bio-Inspired Framework for Machine Learning-Based 5G Resource Allocation},
journal = {Proceedings of Engineering and Technology Innovation},
year = {2026},
volume = {34},
pages = {01--16},
doi = {10.46604/peti.2026.16627}
}
EUVIMED