Experimental Demonstration of Cognitive Provisioning and Alien Wavelength Monitoring in Multi-domain EON

Abstract

This paper proposes a cognitive multi-domain EON architecture with machine-learning aided RMSA and alien wavelength monitoring. Testbed experiments show modulation format recognition, QoT monitoring and cognitive routing for a 160 GBd alien multi-wavelength lightpath.

Machine Learning for QoT Estimation of Unseen Optical Network States

“…. These values are used because the BER at the receiver nodes is known only for the already established connections (through OPM [5,6]).…”

“…An abstracted framework incorporating the ML application is illustrated in Fig. 1, where an optical network is centrally controlled by an SDN-based controller [5] that dynamically monitors and configures the data plane. A database platform collects and stores real-time network state information and optical network monitoring information through OPM [5,6].…”

“…This, however, results in inefficient utilization of the spectrum resources, especially when the worst-case PLIs are highly overestimated [3]. To alleviate these problems, machine learning (ML) techniques have been recently applied for inferring, from the QoT data of previously established connections, QoT models that are not a function of the PLIs and are robust to network changes [2,4,5]. Among the ML methods applied (K-nearest neighbors, logistic regression, support vector machines, and neural networks (NNs)), NNs have shown to present better generalization and higher accuracy [4].…”

“…Among the ML methods applied (K-nearest neighbors, logistic regression, support vector machines, and neural networks (NNs)), NNs have shown to present better generalization and higher accuracy [4]. NNs' accuracy is also experimentally demonstrated in [5], while a software defined networking (SDN)-based implementation scheme incorporating the data-driven QoT estimation framework is presented in [6].…”

“…Related work [2,4,5], to the best of our knowledge, apply ML aiming at finding QoT estimation models that are a function only of the new (unestablished) lightpath. Consequenlty, these models cannot capture the crosstalk (XT) effect between the new and the established lightpahts.…”