Field Trial of Gaussian Process Learning of Function-Agnostic Channel Performance Under Uncertainty

We model and experimentally demonstrate a novel performance learning method based on monitoring and Gaussian process. After 436km dark fiber transmission the model captures most of the test data with reasonable prediction error and enables a robust QoT predictor.

[1]  Yvan Pointurier,et al.  Design of low-margin optical networks , 2017, IEEE/OSA Journal of Optical Communications and Networking.

[2]  Mounia Lourdiane,et al.  Quality of Transmission Prediction with Machine Learning for Dynamic Operation of Optical WDM Networks , 2017, 2017 European Conference on Optical Communication (ECOC).

[3]  R. Nejabati,et al.  Field trial of a novel SDN enabled network restoration utilizing in-depth optical performance monitoring assisted network re-planning , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[4]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[5]  Alan E. Willner,et al.  Transmission of many WDM channels through a cascade of EDFA's in long-distance links and ring networks , 1995 .

[6]  Reza Nejabati,et al.  Robust Self-Learning Physical Layer Abstraction Utilizing Optical Performance Monitoring and Markov Chain Monte Carlo , 2017, 2017 European Conference on Optical Communication (ECOC).