AI-Assisted Fault Detection in High-Capacity Data Center Fiber Networks
Keywords:
AI-assisted fault detection; data center fiber networks; optical telemetry; network resilience; observability; governance; sustainability; machine learning; fault localization; socio-technical systemsAbstract
High-capacity data center fiber networks have become foundational to cloud computing, artificial intelligence training, financial settlement, public-sector digital services, and real-time industrial coordination. As optical links grow in capacity and density, fault detection shifts from a narrow physical-layer maintenance task to a socio-technical problem involving telemetry, machine learning, network orchestration, operational governance, and sustainability. This paper examines AI-assisted fault detection in high-capacity data center fiber networks from a system-level perspective. It argues that detection accuracy alone is an insufficient design objective. Instead, architectures must balance latency, observability, false-positive burden, localization precision, energy consumption, and operator trust. The paper reviews the architectural context of modern data center fabrics, including leaf-spine topologies, software-defined control, optical interconnects, and high-availability design principles. It then analyzes AI-assisted detection pipelines, data quality constraints, centralized and distributed inference trade-offs, and fault localization under partial observability. Governance concerns are treated as first-order requirements because automated remediation can alter service levels, accountability, and fairness across tenants. Deployment challenges such as model drift, technical debt, and resilience under correlated failures are discussed alongside sustainability implications. Through cross-domain comparisons with power grids, aviation, and wide-area networks, the paper identifies institutional and infrastructural conditions for robust adoption. The conclusion emphasizes that AI-assisted fault detection should be designed as an accountable, observable, and adaptable capability rather than as a black-box replacement for human judgment.
References
1. Al-Fares, M., Loukissas, A., & Vahdat, A. (2008). A scalable, commodity data center network architecture. ACM SIGCOMM Computer Communication Review, 38(4), 63-74. https://doi.org/10.1145/1402946.1402967
2. Barroso, L. A., Clidaras, J., & Hölzle, U. (2013). The datacenter as a computer: An introduction to the design of warehouse-scale machines (2nd ed.). Morgan & Claypool. https://doi.org/10.2200/S00516ED2V01Y201306CAC024
3. Cisco. (2020). Cisco annual internet report (2018-2023) white paper. Cisco Systems.
4. Chen, M., Mao, S., & Liu, Y. (2014). Big data: A survey. Mobile Networks and Applications, 19(2), 171-209. https://doi.org/10.1007/s11036-013-0489-0
5. Zhou, Z., Dzieciol, H., Clark, K., Luo, Y., Richardson, D., Poletti, F., ... & Liu, Z. (2023). Low-latency wavelength-switched clock-synchronized intra-data center interconnects enabled by hollow core fiber. Optics Express, 31(15), 24739-24748.
6. Kreutz, D., Ramos, F. M. V., Veríssimo, P. E., Rothenberg, C. E., Azodolmolky, S., & Uhlig, S. (2015). Software-defined networking: A comprehensive survey. Proceedings of the IEEE, 103(1), 14-76. https://doi.org/10.1109/JPROC.2014.2371999
7. Greenberg, A., Hamilton, J., Maltz, D. A., & Patel, P. (2008). The cost of a cloud: Research problems in data center networks. ACM SIGCOMM Computer Communication Review, 39(1), 68-73. https://doi.org/10.1145/1496091.1496103
8. Govindan, R., Minei, I., Kallahalla, M., Koley, B., & Vahdat, A. (2016). Evolve or die: High-availability design principles drawn from Google's network infrastructure. Proceedings of the 2016 ACM SIGCOMM Conference, 58-72. https://doi.org/10.1145/2934872.2934891
9. Hong, C.-Y., Kandula, S., Mahajan, R., Zhang, M., Gill, V., Nanduri, M., & Wattenhofer, R. (2013). Achieving high utilization with software-driven WAN. ACM SIGCOMM Computer Communication Review, 43(4), 15-26. https://doi.org/10.1145/2534169.2486012
10. Jain, S., Kumar, A., Mandal, S., Ong, J., Poutievski, L., Singh, A., ... & Vahdat, A. (2013). B4: Experience with a globally-deployed software defined WAN. ACM SIGCOMM Computer Communication Review, 43(4), 3-14. https://doi.org/10.1145/2534169.2486019
11. Mestres, A., Rodriguez-Natal, A., Carner, J., Barlet-Ros, P., Alarcón, E., Solé, M., ... & Cabellos-Aparicio, A. (2017). Knowledge-defined networking. ACM SIGCOMM Computer Communication Review, 47(3), 2-10. https://doi.org/10.1145/3138808.3138810
12. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
13. Musumeci, F., Rottondi, C., Nag, A., Macaluso, I., Zibar, D., Ruffini, M., & Tornatore, M. (2019). A survey on application of machine learning techniques in optical communication. Journal of Lightwave Technology, 37(4), 1100-1111. https://doi.org/10.1109/JLT.2018.2877413
14. Li, Y., Li, D., Cui, W., Zhang, R., & Wang, Y. (2021). Artificial intelligence in optical networks: A survey. IEEE Communications Surveys & Tutorials, 23(3), 1780-1815. https://doi.org/10.1109/COMST.2021.3073088
15. Gandomi, A., & Haider, M. (2015). Beyond the hype: Big data concepts, methods, and analytics. International Journal of Information Management, 35(2), 137-144. https://doi.org/10.1016/j.ijinfomgt.2014.10.007
16. Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., ... & Dennison, D. (2015). Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems, 28, 2503-2511.
17. Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From theory to algorithms. Cambridge University Press.
18. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929-1958.
19. Vahdat, A., Al-Fares, M., Farrington, N., Mysore, R. N., Porter, G., & Radhakrishnan, S. (2018). Scale-out networking in the data center. IEEE Micro, 38(4), 32-40. https://doi.org/10.1109/MM.2018.043191110
20. Zhang, Q., Cheng, L., & Boutaba, R. (2010). Cloud computing: State-of-the-art and research challenges. Journal of Internet Services and Applications, 1(1), 7-18. https://doi.org/10.1007/s13174-010-0007-6
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.
