We have been using the cross layer design tools that have been extremely successful in the wireless domain to develop algorithms for efficient operation of optical networks. These algorithms will leverage the recent advances in optical real time measurements and dynamic optical devices (such devices enable, for example, dynamic power, bandwidth, and modulation control) to adapt the behavior of the optical networks based on real time measurements, traffic patterns, and service level agreements. Dynamic operation will lead to significantly improved performance in terms of throughput, delay, and energy consumption. Moreover, enabling dynamic operation at the optical domain will provide an important step towards Software Defined Networking (SDN) for the optical (physical) layer.
Our work in this area is done in collaboration with the Columbia Lightwave Research Lab and takes places mostly within the NSF Center for Integrated Access Networks (CIAN) Engineering Research Center (ERC). The center develops the CIAN Box which is an information aggregation node that uses real-time optical performance measurements and energy consumption monitoring, to enable application and impairment-aware switching, regeneration, and adaptive coding. Due to the capability of the CIAN Box to react to measurements of the optical link and to adapt to traffic characteristics, there is a need for network management algorithms that span the various layers of the protocol stack. As a first step, we developed and evaluated a network-wide optimization algorithm that leverages measurements to dynamically control the wavelengths’ power levels. Hence, it allows adding and dropping wavelengths quickly while mitigating the impacts of impairments caused by these actions, thereby facilitating efficient operation of higher layer protocols. The video below includes a presentation of a paper about the topic in IEEE ICNP’13 by WiMNet Ph.D. student Berk Birand.
J. Yu, S. Zhu, C. Gutterman, G. Zussman, and D. Kilper, “Machine learning based EDFA gain estimation,” Journal of Optical Communications and Networking (invited), vol. 13, no. 4, pp. B83–B91, Apr. 2021.
A. Minakhmetov, C. Gutterman, T. Chen, J. Yu, C. Ware, L. Iannone, D. Kilper, and G. Zussman, “Experiments on cloud-RAN wireless handover using optical switching in a dense urban testbed,” in Proc. OSA OFC’20, Th2A.25, 2020.
J. Yu, C. Gutterman, A. Minakhmetov, M. Sherman, T. Chen, S. Zhu, G. Zussman, I. Seskar, and D. Kilper, “Dual use SDN controller for management and experimentation in a field deployed testbed,” in Proc. OSA OFC’20, T3J.3, 2020.
C. Gutterman, A. Minakhmetov, J. Yu, M. Sherman, T. Chen, S. Zhu, I. Seskar, D. Raychaudhuri, D. Kilper, and G. Zussman, “Programmable optical x-haul network in the COSMOS testbed,” in Proc. IEEE ICNP’19 Workshop Midscale Education and Research Infrastructure and Tools (MERIT), 2019.
D. Kilper, K. Bergman, G. Zussman, and B. Birand, “Resilient optical networking, US Patent US10,158,447B2.” Dec-2018.
W. Mo, C. Gutterman, Y. Li, S. Zhu, G. Zussman, and D. Kilper, “Deep neural network based wavelength selection and switching in ROADM systems,” Journal of Optical Communications and Networking, vol. 10, no. 10, pp. D1–D11, Oct. 2018.
C. Gutterman, W. Mo, S. Zhu, Y. Li, D. Kilper, and G. Zussman, “Neural network based wavelength assignment in optical switching,” in Proc. ACM SIGCOMM Workshop on Big Data Analytics and Machine Learning for Data Communication Networks (Big-DAMA’17), 2017.
Y. Huang, C. Gutterman, P. Samadi, P. Cho, W. Samoud, C. Ware, M. Lourdiane, G. Zussman, and K. Bergman, “Dynamic mitigation of EDFA power excursions with machine learning,” Optics Express, vol. 25, no. 3, pp. 2245–2258, Feb. 2017.
Y. Huang, W. Samoud, C. Gutterman, C. Ware, M. Lourdiane, G. Zussman, P. Samadi, and K. Bergman, “A machine learning approach for dynamic optical channel add/drop strategies that minimize EDFA power excursions,” in Proc. ECOC’16, 2016.
G. Grebla, B. Birand, P. van de Ven, and G. Zussman, “Joint transmission in cellular networks with CoMP - Stability and scheduling algorithms,” Performance Evaluation, Special Issue from IFIP Performance 2015, vol. 91, pp. 38–55, Sep. 2015.
P. Samadi, V. Gupta, B. Birand, H. Wang, R. Jensen, G. Zussman, and K. Bergman, “Software-addressable optical accelerators for data-intensive applications in cluster-computing platforms,” in Proc. ECOC’14, 2014.
P. Samadi, V. Gupta, B. Birand, H. Wang, G. Zussman, and K. Bergman, “Accelerating incast and multicast traffic delivery for data-intensive applications using physical layer optics,” in Poster description in Proc. ACM SIGCOMM’14, 2014.
B. Birand, H. Wang, K. Bergman, D. Kilper, T. Nandagopal, and G. Zussman, “Real-time power control for dynamic optical networks - algorithms and experimentation,” IEEE Journal on Selected Areas in Communications, Special Issue on Energy Efficiency in Optical Networks, vol. 32, no. 8, pp. 1615–1628, Aug. 2014.
R. Cannistra, B. Carle, M. Johnson, J. Kapadia, Z. Meath, M. Miller, D. Young, C. M. DeCusatis, T. Bundy, G. Zussman, K. Bergman, A. Carranza, C. Sher-DeCusatis, A. Pletch, and R. Ransom, “Enabling autonomic provisioning in SDN cloud networks with NFV service chaining,” in Proc. OSA OFC’14, Tu2I.4, 2014.