Machine Learning-Based Latency Prediction in Wavelength-Switched Data Center Interconnects
Keywords:
wavelength-switched data center interconnects; latency prediction; machine learning; optical circuit switching; data center networks; resource scheduling; robustness; sustainability; governance; fairnessAbstract
Wavelength-switched data center interconnects promise substantial gains in energy efficiency and bandwidth scalability by replacing or augmenting packet-switched electrical fabrics with reconfigurable optical paths. However, the operational benefits of such architectures depend heavily on their ability to meet stringent latency requirements under highly dynamic traffic conditions. This paper examines machine learning-based latency prediction as a system-level capability for wavelength-switched data center interconnects. It argues that latency prediction is not merely a performance optimization problem but a socio-technical infrastructure challenge involving architecture, scheduling, governance, robustness, fairness, and sustainability. The analysis begins with the sources of latency in optical circuit and wavelength-switched fabrics, including path reconfiguration delays, clock synchronization, buffering, contention, and workload-induced variability. It then explores how supervised learning, sequence modeling, and representation learning can estimate end-to-end latency from telemetry, traffic traces, and topology-aware features. The paper discusses deployment trade-offs between centralized and distributed inference, model freshness, observability overhead, and control-plane coupling. It further considers robustness under failures and adversarial conditions, fairness across tenants and services, and policy implications for service-level agreements in shared optical infrastructure. Evaluation methodology, operational monitoring, and cross-domain comparisons with electrical packet switching are also examined. The conclusion emphasizes that accurate latency prediction can enable proactive wavelength assignment, admission control, and workload placement, but only if prediction systems are governed as critical infrastructure with transparency, accountability, and sustainability constraints. The paper contributes a research agenda for integrating predictive intelligence into wavelength-switched data center interconnects without sacrificing reliability or equitable service delivery.
References
1. 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.
2. Farrington, N., Porter, G., Radhakrishnan, S., Bazzaz, H. H., Subramanya, V., Fainman, Y., Papen, G., & Ford, J. (2010). Helios: A hybrid electrical/optical switch architecture for modular data centers. ACM SIGCOMM Computer Communication Review, 40(4), 339–350.
3. Al-Fares, M., Loukissas, A., & Vahdat, A. (2008). A scalable, commodity data center network architecture. ACM SIGCOMM Computer Communication Review, 38(4), 63–74.
4. Guo, C., Lu, G., Li, D., Wu, H., Zhang, X., Shi, Y., Tian, C., Zhang, Y., & Lu, S. (2009). BCube: A high performance, server-centric network architecture for modular data centers. ACM SIGCOMM Computer Communication Review, 39(4), 63–74.
5. Poutievski, L., Mashayekhi, O., Ong, J., Singh, A., Tariq, M., MacCauley, J., ... & Vahdat, A. (2022). Jupiter evolving: Transforming Google's datacenter network via optical circuit switches and software-defined networking. In Proceedings of the ACM SIGCOMM 2022 Conference (pp. 66–85). ACM.
6. 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.
7. Musumeci, F., Rottondi, C., Nag, A., Macaluso, I., Zibar, D., Ruffini, M., & Tornatore, M. (2019). An overview on application of machine learning techniques in optical networks. IEEE Communications Surveys & Tutorials, 21(2), 1383–1408.
8. Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., & Caicedo, O. M. (2018). A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities. Journal of Internet Services and Applications, 9(1), 16.
9. Wang, M., Cui, Y., Wang, X., Xiao, S., & Jiang, J. (2018). Machine learning for networking: Workflow, advances and opportunities. IEEE Network, 32(2), 92–99.
10. Kandula, S., Sengupta, S., Greenberg, A., Patel, P., & Chaiken, R. (2009). The nature of data center traffic: Measurements and analysis. In Proceedings of the 9th ACM SIGCOMM conference on Internet measurement (pp. 202–208). ACM.
11. Alizadeh, M., Greenberg, A., Maltz, D. A., Padhye, J., Patel, P., Prabhakar, B., Sengupta, S., & Sridharan, M. (2010). Data center TCP (DCTCP). ACM SIGCOMM Computer Communication Review, 40(4), 63–74.
12. Mittal, R., Lam, V. T., Dukkipati, N., Blem, E., Wassel, H., Ghobadi, M., Vahdat, A., Wang, Y., Wetherall, D., & Zats, D. (2015). TIMELY: RTT-based congestion control for the datacenter. ACM SIGCOMM Computer Communication Review, 45(4), 537–550.
13. Zhu, Y., Eran, H., Firestone, D., Guo, C., Lipshteyn, M., Liron, Y., Padhye, J., Raindel, S., Yahia, M. H., & Zhang, M. (2015). Congestion control for large-scale RDMA deployments. ACM SIGCOMM Computer Communication Review, 45(4), 523–536.
14. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
15. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
16. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (Vol. 30, pp. 5998–6008). Curran Associates.
17. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
18. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016). Concrete problems in AI safety. arXiv preprint arXiv:1606.06565.
19. Zilberman, N., Watts, P. M., & Rotsos, C. (2015). Optical interconnects for data centers. In Optical Fiber Communication Conference (pp. W3I.1). Optical Society of America.
20. Kachris, C., Kanonakis, K., & Tomkos, I. (2013). Optical interconnection networks in data centers: Recent trends and future challenges. IEEE Communications Magazine, 51(9), 39–45.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Engineering and 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.
