Quality of transmission prediction with machine learning for dynamic operation of optical WDM networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Quality of transmission prediction with machine learning for dynamic operation of optical WDM networks

Résumé

We propose a cognitive scalable method based on neural network to address dynamic and agile provisioning of optical physical layer without prior knowledge of network specifications. Experimental demonstrations on a mesh network achieve 90th percentile OSNR prediction of 0.25dB Root-Mean-Suared-Error
Fichier non déposé

Dates et versions

hal-01791300 , version 1 (14-05-2018)

Identifiants

Citer

Payman Samadi, Djamel Amar, Catherine Lepers, Mounia Lourdiane, Keren Bergman. Quality of transmission prediction with machine learning for dynamic operation of optical WDM networks. ECOC 2017 : 43rd Europeen Conference and exhibition on Optical Communication, Sep 2017, Gothenburg, Sweden. pp.1 - 3, ⟨10.1109/ECOC.2017.8346216⟩. ⟨hal-01791300⟩
33 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More