Massimo Tornatore, Associate Professor, Politecnico di Milano, Italy
Massimo Tornatore is an Associate Professor at Politecnico di Milano and he also holds an appointment as Adjunct Professor at University of California, Davis. His research interests include performance evaluation and optimization of communication and cloud networks (with emphasis on optical-networking technologies). He co-authored about 300 publications in these fields.
Title: An Introduction to Machine Learning in Optical Transport networks
Abstract: This tutorial provides introductory concepts of Machine Learning (ML) and an overview of its main applications in optical networks. Then our experience in developing some specific applications, as QoT estimation and soft-failure identification, is described in more detail.
Josep Prat, Professor, Universitat Politècnica de Catalunya
Prof. Josep Prat is full professor in the Optical Communications Group (www.tsc.upc.edu/gco) of the Signal Theory and Communications Department of the UPC. He has participated, among others, in the European projects on optical transport and access networks COCONUT, ACCORDANCE, Euro-Fos, BONE, ePhoton/One, LION, MEPHISTO, MOON, SONATA, RACE1027, and led the FP7 European project SARDANA on next-generation FTTH networks, wining the 2011 Global Telecommunications Business Innovation Award in the Fixed Network Infrastructure category. He was a guest scientist in the University College of London in 1998, and in the Stanford University in 2016.
Title: Simple tuneable transmitters for ultra-dense WDM access and metro networks
Abstract: Light generation and modulation constitutes a critical element in the network spectral management and transceiver cost. Ultra-dense WDM has been recently proposed for access networks to highly increase its capacity without adding substantial complexity at the optical network units, by means of statistical WDM and by means of direct phase modulation. In this tutorial, the different possible transceiver architectures for access and metro networks will be reviewed, and the proposed design will be compared in terms of performance and complexity.
