Reinforcement Learning for Dynamic Optical Circuit Switching in Data Centers
Keywords:
dynamic optical circuit switching; reinforcement learning; data center networks; optical interconnects; resource allocation; sustainability; governance; fairnessAbstract
Data centers increasingly require network fabrics that can adapt rapidly to bursty, heterogeneous, and temporally shifting traffic while remaining energy efficient, resilient, and fair across tenants. Dynamic optical circuit switching offers a compelling physical-layer response to these demands because it can provide high-bandwidth, low-latency, and potentially low-energy paths that bypass conventional electrical packet-switching bottlenecks. However, the control problem is difficult: optical circuits must be scheduled, reconfigured, and reconciled with packet-switched traffic under uncertainty, partial observability, hardware constraints, and stringent service-level expectations. This paper examines reinforcement learning as a control paradigm for dynamic optical circuit switching in data centers from a system-level perspective. It argues that the central challenge is not merely optimizing a switching policy but integrating learning agents into operational governance, telemetry, safety, and multi-tenant policy structures. The discussion covers architectural trade-offs between centralized and distributed control, the role of low-latency optical interconnects, robustness under distribution shift, deployment economics, sustainability implications, and fairness in shared infrastructure. It also considers evaluation methodology, case illustrations, and cross-domain lessons from reinforcement learning in routing, congestion control, and video streaming. The paper concludes that reinforcement learning can meaningfully improve dynamic optical circuit switching only when treated as a socio-technical capability embedded in accountable infrastructure, not as an isolated algorithmic substitute for network engineering 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.
2. Farrington, N., Porter, G., Radhakrishnan, S., Bazzaz, H., Subramanya, V., Fainman, Y., Papen, G., & Vahdat, A. (2010). Helios: A hybrid electrical/optical switch architecture for modular data centers. ACM SIGCOMM Computer Communication Review, 40(4), 339–350.
3. Kachris, C., & Tomkos, I. (2012). A survey on optical interconnects for data centers. IEEE Communications Surveys & Tutorials, 14(4), 1021–1036.
4. Chen, K., Singla, A., Singh, A., Ramachandran, K., Xu, L., Zhang, Y., Wen, X., & Chen, Y. (2014). OSA: An optical switching architecture for data center networks with unprecedented flexibility. IEEE/ACM Transactions on Networking, 22(2), 498–511.
5. Porter, G., Strong, R., Farrington, N., Forencich, A., Chen-Sun, P., Rosing, T., Fainman, Y., Papen, G., & Vahdat, A. (2013). Integrating microsecond circuit switching into the data center. ACM SIGCOMM Computer Communication Review, 43(4), 447–458.
6. Ghobadi, M., Mahajan, R., Phanishayee, A., Devanur, N., Kulkarni, J., Ranade, G., Blanche, P.-A., Rastegarfar, H., Glick, M., & Kilper, D. (2016). Projector: Agile reconfigurable data center interconnect. ACM SIGCOMM Computer Communication Review, 46(4), 216–229.
7. Mellette, W. M., McGuinness, R., Roy, A., Forencich, A., Papen, G., Snoeren, A. C., & Porter, G. (2017). RotorNet: A scalable, low-complexity, optical datacenter network. ACM SIGCOMM Computer Communication Review, 47(4), 267–280.
8. Ballani, H., Costa, P., Behrendt, R., Cletheroe, D., Haller, I., Jozwik, K., Karoui, K., Kopp, P., Lu, B., Reiffer, A., Sajan, A., Zhao, Y., & Williams, H. (2020). Sirius: A flat datacenter network with nanosecond optical switching. Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication, 782–797.
9. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
10. Chen, L., Lingys, J., Chen, K., & Liu, F. (2018). AuTO: Scaling deep reinforcement learning for datacenter-scale automatic traffic optimization. Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 191–205.
11. Jiang, J., Sun, H., Liu, B., & Chen, H. (2018). Experience-driven networking: A deep reinforcement learning based approach. IEEE INFOCOM 2018 - IEEE Conference on Computer Communications, 1871–1879.
12. Valadarsky, A., Schapira, M., Shahaf, D., & Tamar, A. (2017). Learning to route. Proceedings of the 16th ACM Workshop on Hot Topics in Networks, 185–191.
13. Jay, N., Rotman, N., Godfrey, P. B., Schapira, M., & Tamar, A. (2019). A deep reinforcement learning perspective on internet congestion control. Proceedings of the 36th International Conference on Machine Learning, 3050–3059.
14. Mao, H., Netravali, R., & Alizadeh, M. (2017). Neural adaptive video streaming with Pensieve. Proceedings of the Conference of the ACM Special Interest Group on Data Communication, 197–210.
15. Chen, X., Li, B., Proietti, R., Lu, H., Zhu, Z., & Yoo, S. J. B. (2019). DeepRMSA: A deep reinforcement learning framework for routing, modulation and spectrum assignment in elastic optical networks. Journal of Lightwave Technology, 37(16), 4155–4163.
16. Suárez-Varela, J., Mestres, A., Yu, J., Kuang, L., Feng, H., Barlet-Ros, P., & Cabellos-Aparicio, A. (2019). Routing based on deep reinforcement learning in optical transport networks. Optical Fiber Communication Conference, M2A.6.
17. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
18. 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.
19. Masanet, E., Shehabi, A., Lei, N., Smith, S., & Koomey, J. (2020). Recalibrating global data center energy-use estimates. Science, 367(6481), 984–986.
20. Mittelstadt, B. (2019). Principles alone cannot guarantee ethical AI. Nature Machine Intelligence, 1(11), 501–507.
21. Rahwan, I. (2018). Society-in-the-loop: Programming the algorithmic social contract. Ethics and Information Technology, 20(1), 5–14.
22. Barocas, S., Hardt, M., & Narayanan, A. (2019). Fairness and machine learning. MIT Press.
23. Wiesner, P., Behnke, I., Scheinert, D., Gontarska, K., & Thamsen, L. (2021). Let's wait awhile: How temporal workload shifting can reduce carbon emissions in the cloud. Proceedings of the 22nd International Middleware Conference, 260–272.
24. Jain, S., Kumar, A., Mandal, S., Ong, J., Poutievski, L., Singh, A., Venkata, S., Wanderer, J., Zhou, J., Zhu, M., Zolla, J., Hölzle, U., Stuart, S., & Vahdat, A. (2013). B4: Experience with a globally-deployed software defined WAN. ACM SIGCOMM Computer Communication Review, 43(4), 3–14.
25. 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 Publishers.
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.
