Abstract

Machine learning (ML) is more and more used to address the challenges of managing the physical layer of increasingly heterogeneous and complex optical networks. In this tutorial, we illustrate how simple and more sophisticated machine learning methods can be used in lightpath quality of transmission (QoT) estimation and forecast tasks. We also discuss data processing strategies with the aim to determine relevant features to feed the ML classifiers and predictors. We then introduce a preliminary study on the application of transfer learning to try to overcome the scarcity of field data.

Machine learning regression for QoT estimation of unestablished lightpaths

Memedhe Ibrahimi, Hatef Abdollahi, Cristina Rottondi, Alessandro Giusti, Alessio Ferrari, Vittorio Curri, and Massimo Tornatore
J. Opt. Commun. Netw. 13(4) B92-B101 (2021)

Decentralizing machine-learning-based QoT estimation for sliceable optical networks

Tania Panayiotou, Giannis Savva, Ioannis Tomkos, and Georgios Ellinas
J. Opt. Commun. Netw. 12(7) 146-162 (2020)

Scalability analysis of machine learning QoT estimators for a cloud-native SDN controller on a WDM over SDM network

C. Manso, R. Vilalta, R. Muñoz, N. Yoshikane, R. Casellas, R. Martínez, C. Wang, F. Balasis, T. Tsuritani, and I. Morita
J. Opt. Commun. Netw. 14(4) 257-266 (2022)

Assessment of cross-train machine learning techniques for QoT-estimation in agnostic optical networks

Ihtesham Khan, Muhammad Bilal, and Vittorio Curri
OSA Continuum 3(10) 2690-2706 (2020)

Sample-distribution-matching-based transfer learning for QoT estimation in optical networks

Zhiqun Gu, Tangze Qin, Yuhang Zhou, Jiawei Zhang, and Yuefeng Ji
J. Opt. Commun. Netw. 15(9) 649-663 (2023)