Predictive AIOps Framework for Autonomous Fault Detection and QoS Assurance in 5G Slice Networks
Keywords:
5G network slicing, AIOps, fault detection, QoS assurance, deep reinforcement learning, predictive maintenance, autonomous operationsAbstract
The proliferation of 5G network slicing imposes unprecedented demands on operational continuity and service-level guarantees across logically isolated virtual networks that share a common physical substrate. As slicing architectures evolve toward highly dynamic, multi-domain deployments, traditional rule-based fault management and static quality-of-service (QoS) enforcement mechanisms become inadequate, giving rise to the need for predictive, autonomous operations. This paper presents a comprehensive predictive AIOps framework designed for autonomous fault detection and QoS assurance in 5G slice networks. The framework integrates telemetry ingestion, streaming anomaly detection, causal graph reasoning, and deep reinforcement learning-powered policy optimization into a closed-loop architecture that operates across network, service, and business layers. We examine the structural design choices governing telemetry granularity, model lifecycle management, federated learning topologies, and the interplay between reactive and proactive actuation. Particular emphasis is placed on system-level trade-offs involving prediction accuracy, latency budgets, computational overhead, and the risks of over-automation. The discussion extends to governance dimensions, including explainability mandates, algorithmic fairness when slices serve heterogeneous verticals, and regulatory alignment with emerging network resilience standards. Deployment considerations such as greenfield versus brownfield integration, energy proportionality, and multi-vendor interoperability are analyzed to ground the framework in operational reality. By synthesizing advances in AIOps, network orchestration, and zero-touch management, the paper offers a forward-looking perspective on how predictive intelligence can be responsibly embedded into the operational fabric of 5G slices while balancing technical performance with socio-technical accountability.
References
1. Foukas, X., Patounas, G., Elmokashfi, A., & Marina, M. K. (2017). Network slicing in 5G: A survey of principles, enabling technologies, and solutions. IEEE Communications Surveys & Tutorials, 19(3), 643–674.
2. Ordonez-Lucena, J., Ameigeiras, P., Lopez, D., Ramos-Munoz, J. J., Lorca, J., & Folgueira, J. (2017). Network slicing for 5G with SDN/NFV: Concepts, architectures, and challenges. IEEE Communications Magazine, 55(5), 80–87.
3. Taleb, T., Ksentini, A., & Kobbane, A. (2017). A survey of network slicing management: Architecture, techniques, and open issues. IEEE Communications Surveys & Tutorials, 20(1), 242–275.
4. Dang, Y., Lin, Q., & Huang, P. (2019). AIOps: Real-world challenges and research innovations. In 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (pp. 4–5). IEEE.
5. Hyun, J., Park, S., & Yoo, J. H. (2020). A survey of fault management in telecommunication networks: Trends, challenges and future directions. IEEE Access, 8, 217718–217740.
6. Ahmed, M., Naser Mahmood, A., & Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19–31.
7. Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
8. Li, R., Zhao, Z., Zhou, X., Ding, G., Chen, Y., Wang, Z., & Zhang, H. (2018). Deep reinforcement learning for autonomous network slicing in 5G. IEEE Communications Magazine, 56(8), 86–93.
9. Zhao, J., Liu, Y., Gong, Y., Wang, C., & Fan, L. (2019). QoS-aware resource allocation for network slicing via deep reinforcement learning. IEEE Access, 7, 111908–111920.
10. Wang, P., Xu, J., Wan, J., Kozloski, J., & Song, H. (2020). AIOps: Machine learning in production. IEEE Software, 37(4), 69–76.
11. Karray, F., Alemzadeh, M., Abou Saleh, J., & Arab, M. N. (2020). Predictive maintenance in the telecommunications industry: A survey. IEEE Access, 8, 142046–142061.
12. Habibi, M. A., Nasimi, M., Han, B., & Schotten, H. D. (2019). A survey on 5G network slicing: Concepts, challenges, and open issues. IEEE Access, 7, 140560–140595.
13. Li, Q. (2026). QoS Assurance Mechanism for 5G Network Slicing Based on the Deep Reinforcement Learning PPO Algorithm. arXiv preprint arXiv:2605.03345.
14. Floridi, L., & Cowls, J. (2019). A unified framework of five principles for AI in society. Harvard Data Science Review, 1(1).
15. Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.
16. Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y. C., Yang, Q., ... & Miao, C. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(3), 2031–2063.
17. Wu, J., Zhang, Y., Zukerman, M., & Yung, E. K. N. (2017). Energy-efficient base stations: A survey. IEEE Communications Surveys & Tutorials, 19(2), 1355–1394.
18. Ksentini, A., & Nikaein, N. (2017). Toward enforcing network slicing on RAN: Flexibility and resources abstraction. IEEE Communications Magazine, 55(6), 102–108.
19. Mijumbi, R., Serrat, J., Gorricho, J. L., Bouten, N., De Turck, F., & Boutaba, R. (2016). Network function virtualization: State-of-the-art and research challenges. IEEE Communications Surveys & Tutorials, 18(1), 236–262.
20. Mastorakis, G., Mavromoustakis, C. X., Pallis, E., & Markakis, E. K. (2020). Service assurance in 5G networks: A review of recent developments and open challenges. IEEE Access, 8, 145708–145726.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
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.
