Energy-Efficient Resource Allocation in 5G Networks Using AI-Driven Optimization Techniques | IJCT Volume 12 – Issue 6 | IJCT-V12I6P48
International Journal of Computer Techniques
ISSN 2394-2231
Author
Ms. C.Kalaivani, Ms. S.Dhivya
Abstract
Energy consumption in 5G networks is steadily increasing due to ultra-dense deployments, massive MIMO, and the growing demand for high-speed data services. Conventional resource allocation strategies often struggle to adapt efficiently to highly dynamic network conditions, resulting in higher energy usage and reduced network sustainability. In this work, we propose an AI-driven optimization framework that combines deep reinforcement learning (DRL) with meta-heuristic algorithms to achieve energy-efficient power allocation, spectrum management, and user association in 5G networks. The framework intelligently adapts to varying network states, optimizing resource utilization while maintaining stringent quality of service (QoS) requirements. Simulation results demonstrate that the proposed approach significantly reduces total energy consumption, improves spectral efficiency, and enhances latency performance compared to conventional DRL-only or heuristic-based methods. These findings highlight the potential of AI-enabled resource management in achieving sustainable, high-performance next-generation wireless networks and provide a practical pathway toward energy-efficient, intelligent communication infrastructures.
Keywords
5G, energy efficiency, AI optimization, resource allocation, deep reinforcement learning, wireless networks.
Conclusion
This paper presented a hybrid Deep Reinforcement Learning (DRL) and Meta-Heuristic framework for energy-efficient resource allocation in 5G networks. By combining the real-time adaptability of DRL with the global optimization capability of meta-heuristic methods, the proposed approach addresses the limitations of conventional resource allocation techniques, particularly in dynamic and heterogeneous network environments. Extensive simulations demonstrated that the hybrid framework significantly reduces total energy consumption while improving spectral efficiency and maintaining high QoS satisfaction, even under varying traffic loads and user mobility. Compared to DRL-only and heuristic-only approaches, the hybrid method achieved up to 35% energy savings and 10–15% improvement in spectral efficiency, ensuring reliable network performance for diverse user demands. The results confirm that integrating adaptive learning with global optimization provides a robust solution for energy-aware and QoS-compliant resource management in next-generation wireless networks. The proposed framework is therefore highly suitable for dense 5G deployments and paves the way for further exploration of AI-driven green communication strategies.
References
[1] Y. Sun, S. Zhou, and J. Xu, “Energy-efficient resource allocation for 5G ultra-dense networks: A deep reinforcement learning approach,” IEEE Transactions on Wireless Communications, vol. 20, no. 8, pp. 5150–5162, Aug. 2021.
[2] M. Peng and S. Yan, “Energy-efficient edge intelligence for 5G/6G networks,” IEEE Network, vol. 36, no. 4, pp. 22–28, Jul./Aug. 2022.
[3] L. Liang, H. Ye, and G. Y. Li, “Reinforcement learning for resource allocation in wireless networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 4, pp. 1774–1786, Apr. 2021.
[4] M. K. Abdel-Aziz and A. Mohamed, “AI-driven optimization for green 6G networks,” IEEE Internet of Things Journal, vol. 8, no. 22, pp. 16444–16455, Nov. 2021.
[5] Z. Yang, W. Xu, and Y. Liu, “A survey on 6G communications: Emerging technologies, challenges and future research,” IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 112–150, 2021.
[6] A. Alkhateeb, “Deep learning for mmWave and massive MIMO: Overview, challenges, and future directions,” IEEE Communications Magazine, vol. 59, no. 1, pp. 24–31, Jan. 2021.
[7] M. Bennis, M. Debbah, and H. V. Poor, “Ultrareliable and low-latency wireless communication: Tail, risk and scale,” Proceedings of the IEEE, vol. 109, no. 2, pp. 205–210, Feb. 2021.
[8] S. K. Sharma, S. Chatzinotas, and B. Ottersten, “Deep reinforcement learning techniques for 6G resource management,” IEEE Open Journal of the Communications Society, vol. 3, pp. 155–170, 2022.
[9] C. Huang et al., “Reconfigurable intelligent surfaces for energy-efficient wireless communications,” IEEE Transactions on Wireless Communications, vol. 21, no. 8, pp. 6523–6538, Aug. 2022.
[10] X. Hu, M. Ozger, and T. Mahmoodi, “Energy-efficient slicing and resource allocation for 5G/6G networks using deep learning,” IEEE Transactions on Network and Service Management, vol. 20, no. 2, pp. 1450–1463, Apr. 2023.
[11] H. Tataria et al., “6G wireless systems: Vision, requirements, and key enabling technologies,” IEEE Access, vol. 11, pp. 8810–8840, 2023.
[12] S. Chen, Y. Wang, and C. Zhang, “Deep reinforcement learning for joint power and spectrum allocation in green 6G,” IEEE Transactions on Mobile Computing, vol. 23, no. 5, pp. 2551–2564, 2024.
[13] K. B. Letaief, W. Chen, Y. Shi, et al., “The roadmap to 6G—AI-empowered wireless networks,” IEEE Communications Magazine, vol. 61, no. 1, pp. 32–38, Jan. 2023.
[14] P. Yang, Y. Xiao, and S. Li, “A comprehensive survey on AI-enabled resource allocation for 6G,” IEEE Communications Surveys & Tutorials, vol. 25, no. 1, pp. 1–32, 2023.
[15] G. Gui et al., “AI-assisted green communications for 6G: Techniques, challenges, and future trends,” IEEE Wireless Communications, vol. 31, no. 2, pp. 18–25, Apr. 2024.
How to Cite This Paper
Ms. C.Kalaivani, Ms. S.Dhivya (2025). Energy-Efficient Resource Allocation in 5G
Networks Using AI-Driven Optimization Techniques. International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.
