We propose a novel approach to perform QoT estimation relying on joint exploitation of machine learning and analytical formula that offers accurate estimation when applied to scenarios with heterogeneous span profiles and sparsely occupied links. Our approach significantly outperforms the widely used lightpath-level QoT estimation.

A Novel Approach for Joint Analytical and ML-assisted GSNR Estimation in Flexible Optical Network / Arpanaei, F.; Shariati, B.; Safari, P.; Ranjbar Zefreh, M.; Hernandez, J. A.; Carena, A.; Fischer, J.; Larrabeiti, D.. - ELETTRONICO. - (2022). (Intervento presentato al convegno 2022 European Conference on Optical Communication, ECOC 2022 tenutosi a Basel, Switzerland nel 18-22 September 2022).

A Novel Approach for Joint Analytical and ML-assisted GSNR Estimation in Flexible Optical Network

Arpanaei F.;Carena A.;
2022

Abstract

We propose a novel approach to perform QoT estimation relying on joint exploitation of machine learning and analytical formula that offers accurate estimation when applied to scenarios with heterogeneous span profiles and sparsely occupied links. Our approach significantly outperforms the widely used lightpath-level QoT estimation.
2022
978-1-957171-15-9
File in questo prodotto:
File Dimensione Formato  
264_ecoc2022.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 810.71 kB
Formato Adobe PDF
810.71 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
ECOC2022_ML_QoT_threeLevel_v9.0.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 249.24 kB
Formato Adobe PDF
249.24 kB Adobe PDF Visualizza/Apri
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: https://hdl.handle.net/11583/2984829