The efficiency of optical networks employing flexible wavelength division multiplexing (WDM) can be increased by maximizing the throughput of each individual channel, provided that the position of its neighboring channel is known with sufficient accuracy in order to avoid inter-channel interference. In this manuscript, we propose a digital signal processing (DSP) algorithm, leveraging the use of an artificial neural network (ANN), to estimate the neighboring channels distance by processing raw digital samples from a standard coherent receiver. We present an efficient dataset design approach, based on latin hypercube sampling (LHS), in order to effectively optimize and validate the algorithm under different assumptions on the optical WDM channels. We investigate the accuracy of the ANN-based DSP scheme through simulation analysis, highlighting its potential in relation to the characteristics of the optical network. Finally, we validate our approach in an experimental setup using standard commercial coherent transceivers. The experimental results show that the distance from the neighboring WDM channels can be estimated with a Root Mean Square Error (RMSE) of less than 1.5 GHz for a channel under test with symbol rate of 52 GBaud.

DSP-based Inter-Channel Interference Monitoring in Flexible Wavelength Routed Networks / Minelli, Leonardo; Bosco, Gabriella; Straullu, Stefano; Nespola, Antonino; Piciaccia, Stefano; Pilori, Dario. - In: JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING. - ISSN 1943-0620. - ELETTRONICO. - 16:6(2024), pp. 695-705. [10.1364/jocn.523440]

DSP-based Inter-Channel Interference Monitoring in Flexible Wavelength Routed Networks

Minelli, Leonardo;Bosco, Gabriella;Pilori, Dario
2024

Abstract

The efficiency of optical networks employing flexible wavelength division multiplexing (WDM) can be increased by maximizing the throughput of each individual channel, provided that the position of its neighboring channel is known with sufficient accuracy in order to avoid inter-channel interference. In this manuscript, we propose a digital signal processing (DSP) algorithm, leveraging the use of an artificial neural network (ANN), to estimate the neighboring channels distance by processing raw digital samples from a standard coherent receiver. We present an efficient dataset design approach, based on latin hypercube sampling (LHS), in order to effectively optimize and validate the algorithm under different assumptions on the optical WDM channels. We investigate the accuracy of the ANN-based DSP scheme through simulation analysis, highlighting its potential in relation to the characteristics of the optical network. Finally, we validate our approach in an experimental setup using standard commercial coherent transceivers. The experimental results show that the distance from the neighboring WDM channels can be estimated with a Root Mean Square Error (RMSE) of less than 1.5 GHz for a channel under test with symbol rate of 52 GBaud.
File in questo prodotto:
File Dimensione Formato  
AcceptedManuscript.pdf

embargo fino al 31/05/2025

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 2.91 MB
Formato Adobe PDF
2.91 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
523440.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 3.41 MB
Formato Adobe PDF
3.41 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2988902