Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Yvan Pointurier"'
Publikováno v:
Journal of Optical Communications and Networking.
Publikováno v:
Optical Fiber Communication Conference (OFC) 2023.
We propose a technique to estimate lumped losses thus OSNR, nonlinear SNR, GSNR, and SNR in C+L optical networks. We show with simulations that SNR estimation accuracy is within 0.5dB and that the technique is robust to uncertainty due to aging.
Publikováno v:
Journal of Optical Communications and Networking. 15:333
Digital twins capable of quality of transmission (QoT) estimation and prediction are powerful tools for efficient design and operation of optical networks. In this paper, we employ machine learning techniques to enhance both the QoT estimation and pr
Publikováno v:
Journal of Optical Communications and Networking. 15:C20
We experimentally observe the signal-to-noise ratio (SNR) degradation of previously established services induced by loading new services in a network, and we mitigate this degradation by periodic power re-optimization via two different strategies: (1
Autor:
Alessio Ferrari, Venkata Virajit Garbhapu, Dylan Le Gac, Ivan Fernandez de Jauregui Ruiz, Gabriel Charlet, Yvan Pointurier
Publikováno v:
Optical Fiber Communication Conference (OFC) 2022.
We demonstrate a network automation framework called AI-Light able to: create a digital twin based on the monitoring, perform an SNR-based optimization by leveraging the digital twin and, push the optimized configuration into the network.
Autor:
Oleg Karandin, Francesco Musumeci, Alessio Ferrari, Gabriel Charlet, Yvan Pointurier, Massimo Tornatore
We quantify spectrum usage and transponder cost when deploying next-generation transponders that support up to 1.6 Tbit/s, in both C- and C+L bands. We compare two transponder architectures: a) single-carrier, operating beyond 100 Gbaud and b) multi-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cfbfe01d5365e954039573c5e224bda
http://hdl.handle.net/11311/1212977
http://hdl.handle.net/11311/1212977
Publikováno v:
Optical Fiber Communication Conference (OFC) 2022.
The robustness of a ML-based QoT input parameters refinement technique in partially loaded networks (both static and dynamic) is assessed using experimental data. SNR prediction error is reduced by up to 1dB over >40000 services.
Autor:
Yvan Pointurier, Venkata Virajit Garbhapu, Ivan Fernandez de Jauregui Ruiz, Alessio Ferrari, Dylan Le Gac, Gabriel Charlet
Publikováno v:
ECOC
Autor:
Sebastien Bigo, Wolfram Lautenschlaeger, Lars Dembeck, Yvan Pointurier, Nihel Benzaoui, Jose Estaran, Mijail Szczerban Gonzalez, Haik Mardoyan, Ulrich Gebhard
Publikováno v:
Journal of Lightwave Technology. 37:3465-3474
Today's network infrastructure evolves into two seemingly opposite directions: cloudification centralizes functions that used to be distributed for economies of scale, at the expense of latency, while latency-constrained applications are surging. Thi