Výsledky vyhledávání - "Antoine Lavignotte"

Reinforcement Learning for Compensating Power Excursions in Amplified WDM Systems

Autor: Dipankar Sengupta, Christine Tremblay, Catherine Lepers, Maria Freire-Hermelo, Antoine Lavignotte

Publikováno v: Journal of Lightwave Technology. 39:6805-6813

Wavelength-dependent power excursions in gain-controlled erbium doped fiber amplifiers (EDFA) is a challenging issue in optical networks. We investigate a launch channel power control method using reinforcement learning (RL) to mitigate the power exc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b862be53578873fc046956696ab82373
https://doi.org/10.1109/jlt.2021.3107774

Zobrazit plný text záznamu

Fault Prediction for Heterogeneous Networks using Machine Learning : a Survey

Autor: antoine lavignotte, Catherine Lepers, Killian Murphy

This manuscript provides a survey of Network Fault Prediction using Machine Learning from the years 1997 to 2021. Operational elements from the industry are shared to provide context. An overview of the different ML techniques that have been applied

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31a091ddcca5a65844a216cde7dc2c3e
https://doi.org/10.36227/techrxiv.18857759.v1

Zobrazit plný text záznamu

Dynamic Modulation Format and Wavelength Assignment in Optical Networks using Reinforcement Learning

Autor: Antoine Lavignotte, Maria Freire-Hermelo, Catherine Lepers

Publikováno v: OSA Advanced Photonics Congress 2021.

In this paper, we present the strategy we have adopted to reduce the adding or dropping channel blocking probability using reinforcement learning in comparison with other methods. We demonstrate 27 % reduction with 40 % channel load.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::59206fe2eb83f17616fb2f3d523ab840
https://doi.org/10.1364/networks.2021.nef2b.4

Zobrazit plný text záznamu

Optical Amplifier Control in Optical Networks using Machine Learning

Autor: Maria Freire-Hermelo, Catherine Lepers, Christine Tremblay, Dipankar Sengupta, Antoine Lavignotte

Publikováno v: OSA Advanced Photonics Congress (AP) 2020 (IPR, NP, NOMA, Networks, PVLED, PSC, SPPCom, SOF).

Optical amplifiers exhibit wavelength dependent gain resulting in power excursion. We present gain equalization techniques not suitable for flexible optical networks and focus on machine learning as an alternative solution to solve the problem.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4d9d30cef3fc9a0d5410913cf5a71ff7
https://doi.org/10.1364/networks.2020.nem3b.5

Zobrazit plný text záznamu

Experimental characterization of an SOA-based photonic integrated switch

Autor: Maria Freire, Antoine Lavignotte, Cédric Ware, Eloise De Carvalho Rodrigues, Atchutananda Surampudi, Franck Gillet, Catherine Lepers

Publikováno v: Proceedings ACP 2018 : Asia Communication and Photonics Conference
ACP 2018 : Asia Communication and Photonics Conference
ACP 2018 : Asia Communication and Photonics Conference, Oct 2018, Hangzhou, China. pp.1-3, ⟨10.1109/ACP.2018.8595878⟩

International audience; A semiconductor Optical Amplifier (SOA)-based 2x2 photonic integrated switch has been designed and fabricated in the framework of the ANR N-GREEN project (1),(2). Here, we report on the experimental setup and the results obtai

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06ca2734a2223153bad9daa9f4bc38ca
https://hal.archives-ouvertes.fr/hal-01980405

Zobrazit plný text záznamu

Predicting optical power excursions in erbium doped fiber amplifiers using neural networks

Autor: Maria Freire, Antoine Lavignotte, Catherine Lepers, Franck Gillet, Djamel Amar, Sebastien Mansfeld

International audience; We report on a Machine Learning approach based on artificial Neural Networks to predict optical power excursion in Erbium Doped Fiber Amplifiers. Its flexibility and adaptability could be valuable for future optical networks d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa2ce4b6c4d77cce21e9d1217a5655db
https://hal.archives-ouvertes.fr/hal-01980287

Zobrazit plný text záznamu

Multi-provider secure virtual network embedding

Autor: Hervé Debar, Antoine Lavignotte, Ion Popescu, Stéphane Betge-Brezetz, Gregory Blanc, Francois Boutigny

Publikováno v: Proceedings NTMS 2018 : 9th IFIP International Conference on New Technologies, Mobility and Security
NTMS 2018 : 9th IFIP International Conference on New Technologies, Mobility and Security
NTMS 2018 : 9th IFIP International Conference on New Technologies, Mobility and Security, Feb 2018, Paris, France. pp.1-5, ⟨10.1109/NTMS.2018.8328706⟩
NTMS

International audience; Network virtualization enables tenants to lease computing and networking resources from one or more infrastructure provider (InP), like in Infrastructure as a Service (IaaS). As such, tenants outsource their networks, fully or

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::306228d0d2ff77fd2a3e24de747e7f42
https://hal.archives-ouvertes.fr/hal-01868949

Zobrazit plný text záznamu

Quality of Experience, a very personal experience !

Autor: Jacques Fayolle, Julien Subercaze, Christophe Gravier, Antoine Lavignotte

Publikováno v: 24th International Workshop on Database and Expert Systems Applications
DEXA Workshops
DEXA Workshops, Aug 2013, Prague, European Union. pp.231-235, ⟨10.1109/DEXA.2013.30⟩

International audience; At the Pervasive Computing area, end users expect to receive a multimedia service with an acceptable quality, anytime, and anywhere. Measuring this acceptability is usually referred to Quality of Experience (QoE). Unlike Quali

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6560161b8dcc98dbdc40475c3328c651
https://hal-ujm.archives-ouvertes.fr/ujm-00990156

Zobrazit plný text záznamu