A machine learning framework predicting pump powers and noise figure profile for a target distributed Raman amplifier gain profile is experimentally demonstrated. We employ a single-layer neural network to learn the mapping from the gain profiles to the pump powers and noise figures. The obtained results show highly accurate gain profile designs and noise figure predictions, with a maximum error on average of ∼ 0.3 dB. This framework provides a comprehensive characterization of the Raman amplifier and thus is a valuable tool for predicting the performance of next-generation optical communication systems, expected to employ Raman amplification.

Simultaneous gain profile design and noise figure prediction for Raman amplifiers using machine learning / de Moura, U. C.; Rosa Brusin, A. M.; Carena, A.; Zibar, D.; da Ros, F.. - In: OPTICS LETTERS. - ISSN 0146-9592. - ELETTRONICO. - 46:5(2021), pp. 1157-1160. [10.1364/OL.417243]

Simultaneous gain profile design and noise figure prediction for Raman amplifiers using machine learning

Rosa Brusin A. M.;Carena A.;
2021

Abstract

A machine learning framework predicting pump powers and noise figure profile for a target distributed Raman amplifier gain profile is experimentally demonstrated. We employ a single-layer neural network to learn the mapping from the gain profiles to the pump powers and noise figures. The obtained results show highly accurate gain profile designs and noise figure predictions, with a maximum error on average of ∼ 0.3 dB. This framework provides a comprehensive characterization of the Raman amplifier and thus is a valuable tool for predicting the performance of next-generation optical communication systems, expected to employ Raman amplification.
File in questo prodotto:
File Dimensione Formato  
OpticsLetters2021_RamanDesign_NF.pdf

embargo fino al 01/03/2022

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 449.02 kB
Formato Adobe PDF
449.02 kB Adobe PDF Visualizza/Apri
ol-46-5-1157.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.82 MB
Formato Adobe PDF
1.82 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2902912