MADRL-Based Resource Allocation for 5G HetNets: A Comprehensive Performance Benchmark Against Bio-Inspired and Hybrid Optimization Schemes

Agbon E. E., Sokyes Armak Lapak, Salihu Angulu Rakiya, Utev Terlumun Athanisius, Andrew Habila John, Aliyu Umar Abubakar

Abstract


The rapid proliferation of 5G heterogeneous networks (HetNets) has introduced unprecedented challenges in network selection and resource allocation due to dynamic traffic conditions, diverse quality-of-service (QoS) requirements, and network heterogeneity. Conventional heuristic and optimization-based approaches such as the Hybrid Snow Leopard–Dark Forest Algorithm (HSL-DFA) exhibit limited adaptability to real-time variabilities and fixed objective weighting, which constrains practical performance. To address these limitations, this study formulates the joint network selection and resource allocation problem as a dynamic, multi-objective optimization task and proposes a Multi-Agent Deep Reinforcement Learning (MADRL) framework that autonomously learns contextual policies for intelligent decision making. The proposed method demonstrates superior adaptability, automatic objective balancing, and scalability in dynamic scenarios. Preliminary results show that reinforcement learning-based allocation substantially improves spectral efficiency, reduces latency, and enhances energy management compared to traditional heuristics, making it a promising solution for next-generation 5G systems. 


Full Text:

PDF

References


Alrifai, B. M., Alsbatin, L., & Zawaideh, F. (2025). Optimizing 5G resource allocation with reinforcement learning: A Q-Learning and Deep Q-Network (DQN) approach. Journal of Advances in Information Technology, 16(11), 1586–1594.

Bikkasani, D. C. (2024). AI-Driven 5G Network Optimization: A Comprehensive Review of Resource Allocation, Traffic Management, and Dynamic Network Slicing. Preprints.org.

Dobruna, J., Fazliu, Z. L., Humar, I., & Volk, M. (2025). On Optimizing Resource Allocation: A Comparative Review of Resource Allocation Strategies in HetNets. Computer Modeling in Engineering & Sciences (CMES), 142(3).

Havolli, A., & Fetaji, M. (2025). AI-driven resource allocation strategies for enhanced quality of service in 5G networks. International Journal on Information Technologies and Security, 17(2), 77–88.

Hussien, O., & Jahankhani, H. (2025). Optimizing 5G resource allocation in PSO with machine learning approach to Open RAN architectures. Journal of Next-Generation Research 5.0.

Khan, S. A., Shayea, I., Ergen, M., & Mohamad, H. (2022). Handover management over dual connectivity in 5G technology with future ultra-dense mobile heterogeneous networks: A review. Engineering Science and Technology, an International Journal, 35, 101172.

Lu, M. (2024). Application of machine learning algorithms in resource allocation for wireless communications. Applied and Computational Engineering, 102.

Manathala Vijayan, R., Granelli, F., & Umamakeswari, A. (2025). An adaptive framework for resource allocation management in 5G vehicular networks. International Journal of Interactive Multimedia and Artificial Intelligence.

Salah Alhazmi, A., & Arafah, M. A. (2025). Neural network–based adaptive resource allocation for 5G heterogeneous ultra-dense networks. Sensors, 25(24), 7521.

Shao, Z., Wu, Q., Fan, P., Cheng, N., Fan, Q., & Wang, J. (2024). Semantic-aware resource allocation based on deep reinforcement learning for 5G-V2X HetNets. arXiv.

Zhu, R., Aiyyappan, A., Varatharaj, J. R., & Jeya Sheela John, J. (2025). A standard network selection and resource allocation mechanism in 5G heterogeneous networks using hybrid heuristic algorithm with multi-objective constraints. EURASIP Journal on Wireless Communications and Networking, 2025(1), 1-31.


Refbacks

  • There are currently no refbacks.