AI-Driven SLA-Aware Resource Allocation in Edge Computing for 5G Slices
Keywords:
5G network slicing, edge computing, service level agreement, resource allocation, deep reinforcement learning, proximal policy optimization, fairness, sustainabilityAbstract
The convergence of fifth-generation (5G) mobile networks with edge computing offers unprecedented capabilities for low-latency, high-throughput services across diverse verticals. Network slicing enables operators to carve logically isolated virtual networks tailored to specific service requirements, each governed by a Service Level Agreement (SLA). However, the dynamic and multi-tenant nature of edge environments, coupled with stringent 5G performance targets, makes static resource allocation infeasible. This paper presents a comprehensive examination of AI-driven SLA-aware resource allocation strategies for 5G slices in edge computing infrastructures. We argue that deep reinforcement learning, particularly proximal policy optimization (PPO) algorithms, provides a robust framework for continuous, adaptive allocation decisions that respect SLA constraints while optimizing utilization. The architectural discussion spans edge-cloud continuum topologies, slice orchestration layers, and the role of AI agents in real-time monitoring and reconfiguration. System-level trade-offs between latency guarantees, energy consumption, fairness among slices, and infrastructure resilience are analyzed in depth. Governance and policy implications, including spectrum sharing, tenant isolation, and regulatory compliance, are considered from a socio-technical perspective. A detailed comparison with prior optimization techniques and rule-based heuristics illustrates the superiority of learning-based approaches in non-stationary environments. The paper also addresses deployment challenges such as model training overhead, data privacy, and explainability of AI decisions. Forward-looking perspectives highlight the need for multi-agent coordination, federated learning for cross-domain resource pooling, and sustainable edge architectures that align with net-zero objectives. This work aims to serve as a foundational reference for researchers and practitioners designing next-generation slice-aware edge systems.
References
1. 3GPP, "System architecture for the 5G system (5GS)," 3GPP TS 23.501, version 17.0.0, 2021.
2. NGMN Alliance, "5G White Paper," Next Generation Mobile Networks, 2015.
3. T. Taleb, K. Samdanis, B. Mada, H. Flinck, S. Dutta, and D. Sabella, "On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration," IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1657–1681, 2017.
4. P. Mach and Z. Becvar, "Mobile Edge Computing: A Survey on Architecture and Computation Offloading," IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1628–1656, 2017.
5. Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, "A Survey on Mobile Edge Computing: The Communication Perspective," IEEE Access, vol. 5, pp. 14510–14531, 2017.
6. J. Li, W. Shi, and S. Zhang, "Deep Reinforcement Learning for Resource Allocation in Mobile Edge Computing," IEEE Wireless Communications, vol. 26, no. 4, pp. 26–32, 2019.
7. M. Chen, S. Xiao, and Z. Zhao, "Multi-Agent Deep Reinforcement Learning for Edge Resource Allocation in Multi-Access Edge Computing," IEEE Internet of Things Journal, vol. 7, no. 6, pp. 5334–5344, 2020.
8. C. Xu, J. Ren, L. Song, M. C. Gursoy, and H. V. Poor, "SLA-Aware Resource Allocation for Network Slicing in 5G Mobile Networks," IEEE Transactions on Network and Service Management, vol. 17, no. 3, pp. 1489–1502, 2020.
9. S. Wang, M. A. Hossain, and M. A. Razzaque, "A Survey on Service Level Agreement in Network Slicing for 5G," IEEE Access, vol. 9, pp. 21386–21408, 2021.
10. Y. Sun, M. Peng, and H. V. Poor, "Deep Reinforcement Learning for 5G Network Slicing Resource Allocation," IEEE Journal on Selected Areas in Communications, vol. 38, no. 8, pp. 1790–1804, 2020.
11. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, "Proximal Policy Optimization Algorithms," arXiv preprint arXiv:1707.06347, 2017.
12. A. Ksentini and M. Jebalia, "On 5G Network Slicing: A Survey," IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1166–1189, 2019.
13. A. S. Shafigh, L. A. DaSilva, and M. Melo, "Machine Learning for Network Slicing in 5G," IEEE Communications Magazine, vol. 58, no. 3, pp. 66–72, 2020.
14. Li, Q. (2026). QoS Assurance Mechanism for 5G Network Slicing Based on the Deep Reinforcement Learning PPO Algorithm. arXiv preprint arXiv:2605.03345.
15. S. Yousif, M. Elhabob, and A. Ahmed, "Fairness in Network Slicing: A Survey," IEEE Access, vol. 10, pp. 44768–44786, 2022.
16. M. Bennis, M. Simsek, A. Czylwik, W. Saad, S. Valentin, and M. Debbah, "Ultra-Reliable and Low-Latency Communications: A New Paradigm for 5G," IEEE Communications Magazine, vol. 53, no. 5, pp. 62–72, 2015.
17. R. Li, Z. Zhao, X. Zhou, H. Zhang, and V. C. M. Leung, "Resource Allocation for Network Slicing in 5G: A Survey," IEEE Transactions on Vehicular Technology, vol. 68, no. 7, pp. 7130–7144, 2019.
18. R. Mijumbi, J. Serrat, J. L. Gorricho, N. Bouten, F. De Turck, and S. Davy, "Network Function Virtualization: State-of-the-Art and Research Challenges," IEEE Communications Surveys & Tutorials, vol. 18, no. 1, pp. 236–262, 2016.
19. F. Giust, V. Shakhov, and D. T. Hoang, "MEC in NFV-Based Networks: A Survey," IEEE Communications Surveys & Tutorials, vol. 20, no. 4, pp. 3020–3045, 2018.
20. I. F. Akyildiz, P. Wang, and S. C. Lin, "5G Network Slicing: A New Architecture," IEEE Communications Magazine, vol. 54, no. 3, pp. 57–63, 2016.
21. R. Jain, D. Chiu, and W. Hawe, "A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer Systems," DEC Research Report TR-301, 1984.
22. H. Mao, M. Alizadeh, B. K. H. Low, and L. K. S. Tan, "Resource Management for Network Slicing: A Constrained Reinforcement Learning Approach," in Proceedings of the ACM SIGCOMM, 2022, pp. 312–326.
23. D. Z. Zhang, H. Liu, and S. Shen, "Fairness-Aware Deep Reinforcement Learning for Edge Resource Allocation with Slice Isolation," IEEE Transactions on Mobile Computing, vol. 21, no. 5, pp. 1680–1694, 2022.
24. K. Zhang, Y. Mao, S. Leng, A. Vinel, and Y. Zhang, "Energy-Efficient Offloading for Mobile Edge Computing with Deep Reinforcement Learning," IEEE Internet of Things Journal, vol. 5, no. 5, pp. 3943–3954, 2018.
25. T. Chen, L. Xu, and M. Li, "Green Edge Resource Allocation via Deep Reinforcement Learning," IEEE Transactions on Green Communications and Networking, vol. 6, no. 2, pp. 1052–1064, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
