Deep Reinforcement Learning for Adaptive Bandwidth Allocation in Cloud Optical Networks
Keywords:
cloud optical networks, deep reinforcement learning, bandwidth allocation, optical data center networks, network control, fairness, sustainability, governanceAbstract
Cloud optical networks are becoming a foundational substrate for distributed computing, artificial intelligence services, and latency-sensitive applications. Adaptive bandwidth allocation in such environments must reconcile high capacity, deterministic performance, energy efficiency, and multi-tenant fairness. This paper examines how deep reinforcement learning can be integrated into cloud optical network control planes to support adaptive bandwidth allocation. It frames the problem as a socio-technical systems challenge rather than a purely algorithmic one, emphasizing architecture, governance, deployment, robustness, sustainability, and policy. The analysis begins with the structural characteristics of optical data center fabrics and the limitations of static or rule-based provisioning. It then explains how deep reinforcement learning can learn allocation policies from telemetry, traffic dynamics, and service-level objectives, while also introducing risks related to non-stationarity, reward misspecification, fragility under distribution shift, and opaque decision-making. The paper evaluates architectural choices including centralized, hierarchical, and federated control; interactions with software-defined networking and network function virtualization; and the role of optical circuit switching, elastic spectrum assignment, and frequency-referenced multiplexing. Particular attention is given to resilience under failure, fairness across tenants, energy-aware operation, observability, and human oversight. Deployment pathways are discussed in terms of simulation-to-production transfer, safety envelopes, staged rollouts, and regulatory accountability. The conclusion argues that deep reinforcement learning can improve bandwidth allocation only when embedded within robust governance and infrastructure constraints. The most credible future systems will combine learning-based adaptation with verifiable fallback mechanisms, transparent performance accounting, and institutional rules that protect fairness and public-interest values.
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. Kachris, C., & Tomkos, I. (2012). A survey on optical interconnects for data centers. IEEE Communications Surveys & Tutorials, 14(4), 1021–1036.
3. 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.
4. Poutievski, L., Singh, A., Ong, J., Obenshain, D., Tariq, M., Hines, A., ... & Vahdat, A. (2022). Jupiter evolving: Transforming Google's datacenter network via optical circuit switches and software-defined networking. Proceedings of the ACM SIGCOMM 2022 Conference, 66–85.
5. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
6. Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971.
7. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.
8. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
9. Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017). Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine, 34(6), 26–38.
10. Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016). Resource management with deep reinforcement learning. Proceedings of the 15th ACM Workshop on Hot Topics in Networks, 50–56.
11. 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.
12. Xu, Z., Tang, J., Yin, C., Wang, Y., & Xue, G. (2018). Experience-driven networking: A deep reinforcement learning based approach. IEEE INFOCOM 2018 - IEEE Conference on Computer Communications, 1871–1879.
13. 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.
14. Chen, X., Guo, J., Zhu, Z., Proietti, R., Castro, A., & Yoo, S. J. B. (2018). Deep-RMSA: A deep reinforcement learning framework for routing, modulation and spectrum assignment in elastic optical networks. Journal of Lightwave Technology, 36(20), 4895–4906.
15. Zhou, Z., Wei, J., Luo, Y., Clark, K. A., Sillekens, E., Deakin, C., ... & Liu, Z. (2023). Communications with guaranteed bandwidth and low latency using frequency-referenced multiplexing. Nature Electronics, 6(9), 694-702.
16. 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.
17. Thyagaturu, A. S., Mercian, A., McGarry, M. P., Reisslein, M., & Kellerer, W. (2016). Software defined optical networks (SDONs): A comprehensive survey. IEEE Communications Surveys & Tutorials, 18(4), 2738–2766.
18. Mijumbi, R., Serrat, J., Gorricho, J. L., Bouten, N., De Turck, F., & Boutaba, R. (2016). Network function virtualization: State-of-the-art and research challenges. IEEE Communications Surveys & Tutorials, 18(1), 236–262.
19. Mittelstadt, B. D., Allo, P., Taddeo, M., Wachter, S., & Floridi, L. (2016). The ethics of algorithms: Mapping the debate. Big Data & Society, 3(2), 2053951716679679.
20. Cath, C. (2018). Governing artificial intelligence: Ethical, legal and technical opportunities and challenges. Philosophical Transactions of the Royal Society A, 376(2133), 20180080.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Engineering Systems and Digital Innovation
This work is licensed under a Creative Commons Attribution 4.0 International License.
