A Unified AI Model for Fault Localization and Service Restoration in Multi-Operator Telecom Networks
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V1I1P105Keywords:
Fault Localization, Service Restoration, Multi-Operator Networks, AI in Telecom, Self-Healing Networks, Root Cause AnalysisAbstract
Contemporary telecom infrastructures have become increasingly complex, as they typically consist of multiple service providers operating on diverse network planes and across different network areas. Localization of the fault and effective service repair within such multi-operator environments is still a problem and a challenge as a result of data fragmentation, lack of interoperability among operators and the speed of network events. Historical and siloed machine learning alert types are typically ineffective at identifying root causes in real-time and triggering cross-operator corrective action. The presented paper introduces a unified artificial intelligence-based framework, in which fault localization and service restoration are incorporated as coherent intelligence, with additional multi-operator telecom networks being targeted. The system takes in various data sources (such as telemetry, alarm logs, event traces, and topology graphs) that different operators provide and normalizes them through a federated data processing pipeline, and submits them to a hybrid architecture that uses Graph Neural Networks (GNNs) and reinforcement networks to perform root cause inference and autonomous restoration decisions. The model provides real-time learning, is scalable across operators, and supports data protection through secure edge-layer abstraction. The Mean Time To Repair (MTTR) improved by 35 percent, the mean false positive alerts by 41 percent and the downtime experienced in services declined by 28 percent, compared to traditional methods, according to empirical data collected in simulated multi-vendor environments with real-world datasets. The results portend that the developed unified model contributes remarkably to network resilience, self-healing, and scalability of future autonomy within telecom systems
References
[1] Mijumbi, R., Serrat, J., Gorricho, J. L., Bouten, N., De Turck, F., & Boutaba, R. (2015). Network function virtualization: State-of-the-art and research challenges. IEEE Communications surveys & tutorials, 18(1), 236-262.
[2] Fonseca, P. C., & Mota, E. S. (2017). A survey on fault management in software-defined networks. IEEE Communications Surveys & Tutorials, 19(4), 2284-2321.
[3] Luong, N. C., Hoang, D. T., Gong, S., Niyato, D., Wang, P., Liang, Y. C., & Kim, D. I. (2019). Applications of deep reinforcement learning in communications and networking: A survey. IEEE Communications Surveys & Tutorials, 21(4), 3133-3174.
[4] Kreutz, D., Ramos, F. M., Verissimo, P. E., Rothenberg, C. E., Azodolmolky, S., & Uhlig, S. (2014). Software-defined networking: A comprehensive survey. Proceedings of the IEEE, 103(1), 14-76.
[5] Sood, K., et al. (2018). Performance modeling and comparison of NFV integrated with SDN. Computer Networks, 145, 200–214.
[6] Rizou, S., Dürr, F., & Rothermel, K. (2010, August). Solving the Multi-Operator Placement Problem in Large-Scale Operator Networks. In ICCCN (pp. 1-6).
[7] Zheng, H., Wang, R., Yang, Y., Yin, J., Li, Y., Li, Y., & Xu, M. (2019). Cross-domain fault diagnosis using knowledge transfer strategy: A review. IEEE Access, 7, 129260-129290.
[8] Fischer, W. D., Xie, G. G., & Young, J. D. (2008, October). Cross-domain fault localization: A case for a graph digest approach. In 2008, IEEE Internet Network Management Workshop (INM) (pp. 1-6). IEEE.
[9] Korbicz, J., Koscielny, J. M., Kowalczuk, Z., & Cholewa, W. (Eds.). (2012). Fault diagnosis: models, artificial intelligence, applications. Springer Science & Business Media.
[10] Effah, E., & Thiare, O. (2018). Survey: Faults, fault detection and fault tolerance techniques in wireless sensor networks. Int. J. Comput. Sci. Inf. Secur. (IJCSIS), 16(10), 1-14.
[11] Barco, R., et al. (2017). Towards proactive context-aware self-healing for 5G networks. Computer Networks, 129, 641–657.
[12] Xiao, Y., Krunz, M., & Shu, T. (2019). Multi-operator network sharing for massive IoT. IEEE Communications Magazine, 57(4), 96-101.
[13] Yu, Y., Li, X., Leng, X., Song, L., Bu, K., Chen, Y., ... & Xiao, X. (2018). Fault management in software-defined networking: A survey. IEEE Communications Surveys & Tutorials, 21(1), 349-392.
[14] Covo, A. A., Moruzzi, T. M., & Peterson, E. D. (1989, November). AI-assisted telecommunications network management. In 1989, IEEE Global Telecommunications Conference and Exhibition Technology for the 1990s and Beyond' (pp. 487-491). IEEE.
[15] Mismar, F. B., & Evans, B. L. (2018). Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement. In Proc. Asilomar Conf. on Signals, Systems, and Computers.
[16] Pillai, D. S., Blaabjerg, F., & Rajasekar, N. (2019). A comparative evaluation of advanced fault detection approaches for PV systems. IEEE Journal of Photovoltaics, 9(2), 513-527.
[17] Sisto, R., et al. (2009). Fault Location in Telecommunications Networks Using Bayesian Networks. US Patent US20090292948A1.
[18] Alaez, R. M., Calero, J. M. A., Belqasmi, F., El-Barachi, M., Badra, M., & Alfandi, O. (2016). Towards an open source architecture for multi-operator LTE core networks. Journal of Network and Computer Applications, 75, 101-109.
[19] Antonopoulos, A., Kartsakli, E., Bousia, A., Alonso, L., & Verikoukis, C. (2015). Energy-efficient infrastructure sharing in multi-operator mobile networks. IEEE Communications Magazine, 53(5), 242-249.
[20] Gürer, D. W., Khan, I., Ogier, R., & Keffer, R. (1996). An artificial intelligence approach to network fault management. Sri International, 86.
