Field Trial of Machine-Learning-Assisted and SDN-Based Optical Network Management


In this paper, we reported machine-learning based network dynamic abstraction over a field-trial testbed. The implemented network-scale NCMDB allows the ML-based quality-of-transmission predictor abstract dynamic link parameters for further network planning.

Optical Fiber Communication Conference (OFC) 2019 (2019), paper M2E.1
Shuangyi Yan
Lecturer in High Performance Networking & Optical Network

My research focuses on AI-driven automatic dynamic optical networks with flexible network functions and fast network reconfigurations.