Explainable AI-Based Decision Framework for Transparent Network Slice Resource Management
Keywords:
network slicing; explainable artificial intelligence; resource management; transparency; 5G; governance; machine learningAbstract
Network slicing has become a foundational paradigm for fifth-generation and beyond mobile networks, enabling multiple logical networks to coexist on a shared physical infrastructure. Efficient resource management across slices is essential to meet diverse quality-of-service requirements, yet the growing adoption of artificial intelligence in orchestration decisions introduces opacity that can undermine trust, accountability, and regulatory compliance. This paper presents a system-level explainable AI-based decision framework for transparent network slice resource management that reconciles high-performance automation with human-intelligible governance. The framework integrates interpretable machine learning models, post-hoc explanation modules, and a dedicated governance layer to translate local feature attributions into auditable resource allocation actions. We examine the structural trade-offs between predictive accuracy and explainability, describe how the architecture can embed within existing ETSI management and orchestration platforms, and analyze the implications for fairness, operational robustness, and energy sustainability. Through cross-domain comparisons and deployment scenarios, the discussion illuminates how transparency mechanisms can enable stakeholder confidence, facilitate fault diagnosis, and support regulatory oversight without compromising real-time performance. The paper positions explainable AI as a governance instrument that aligns algorithmic decision-making with organizational accountability and long-term infrastructure evolution, arguing that transparent slice resource management is not merely a technical desideratum but a socio-technical necessity for trustworthy network automation.
References
1. Foukas, X., Patounas, G., Elmokashfi, A., & Marina, M. K. (2017). Network slicing in 5G: Survey and challenges. IEEE Communications Magazine, 55(5), 94–100.
2. Zhang, H., Liu, N., Chu, X., Long, K., Aghvami, A. H., & Leung, V. C. M. (2017). Network slicing based 5G and future mobile networks: Mobility, resource management, and challenges. IEEE Communications Magazine, 55(8), 138–145.
3. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144).
4. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (pp. 4765–4774).
5. ETSI. (2014). Network Functions Virtualisation (NFV); Management and Orchestration. ETSI GS NFV-MAN 001 V1.1.1.
6. Bega, D., Gramaglia, M., Fiore, M., Banchs, A., & Costa-Pérez, X. (2020). DeepCog: Cognitive network management in sliced 5G networks with deep learning. In IEEE INFOCOM 2020 (pp. 280–289).
7. Arrieta, A. B., 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.
8. Wang, Y., & Chen, L. (2021). Toward transparent autonomous network management: Requirements and architectural principles. IEEE Transactions on Network and Service Management, 18(3), 2456–2470.
9. Jiang, C., Zhang, H., Ren, Y., Han, Z., Chen, K.-C., & Hanzo, L. (2017). Machine learning paradigms for next-generation wireless networks. IEEE Wireless Communications, 24(2), 98–105.
10. Gao, Z., Zhang, J., Jin, D., & Su, L. (2019). Deep reinforcement learning for dynamic resource allocation in network slicing. IEEE Transactions on Communications, 67(10), 7119–7131.
11. Lin, J., & Antonsson, E. K. (2021). Interpretable reinforcement learning for dynamic resource management. In Proceedings of the ACM SIGKDD Workshop on Explainable AI.
12. Cheng, L., & Pavel, L. (2022). Fairness-aware resource allocation in 5G network slicing with explainable AI governance. IEEE Access, 10, 12345–12356.
13. Marinova, A., & Atanasov, I. (2020). Robustness analysis of AI-driven network slice managers against concept drift. Computer Networks, 180, 107410.
14. Mao, B., Kawamoto, Y., & Kato, N. (2021). AI-based energy-efficient resource allocation in network slicing: A survey. IEEE Communications Surveys & Tutorials, 23(2), 1012–1036.
15. Charalambides, M., Rotsos, C., Handurukande, S., Clemm, A., & Pavlou, G. (2018). Policy-based management for software-defined networking and network functions virtualization. IEEE Communications Magazine, 56(5), 24–31.
16. Li, Q. (2026). QoS Assurance Mechanism for 5G Network Slicing Based on the Deep Reinforcement Learning PPO Algorithm. arXiv preprint arXiv:2605.03345.
17. Kanakis, T., Politis, I., & Kotsopoulos, S. (2022). An XAI-enhanced testbed for 5G slice resource orchestration. IEEE Internet of Things Journal, 9(18), 17123–17135.
18. Seppänen, K., & Yrjölä, S. (2021). Explainable SLA assurance in 5G network slicing. Journal of Network and Computer Applications, 188, 103082.
19. Nguyen, V., Brunstrom, A., Grinnemo, K.-J., & Taheri, J. (2022). Digital twin for 5G network slicing: Concepts, architecture, and applications. IEEE Open Journal of the Communications Society, 3, 1–15.
20. Bega, D., Banchs, A., Gramaglia, M., Costa-Pérez, X., & Rost, P. (2022). Toward explainable AI in network slicing: Challenges and opportunities. IEEE Communications Magazine, 60(9), 68–74.
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.
