Two artificial neural network (ANN) models are presented to predict power profiles over C+L–band in presence of inter-channel stimulated Raman scattering (ISRS) and to support non-linear interference (NLI) modeling. High prediction accuracy is obtained with maximum errors ≤ 0.1 dB over thousands different partial loads.
Machine Learning for Power Profiles Prediction in Presence of Inter-channel Stimulated Raman Scattering / Rosa Brusin, A. M.; Zefreh, M. Ranjbar; Poggiolini, P.; Piciaccia, S.; Forghieri, F.; Carena, A.. - ELETTRONICO. - (2021), pp. 1-4. (Intervento presentato al convegno 2021 European Conference on Optical Communication (ECOC) tenutosi a Bordeaux (France) nel 13-16 Sept. 2021) [10.1109/ECOC52684.2021.9605807].
Machine Learning for Power Profiles Prediction in Presence of Inter-channel Stimulated Raman Scattering
Rosa Brusin, A. M.;Poggiolini, P.;Carena, A.
2021
Abstract
Two artificial neural network (ANN) models are presented to predict power profiles over C+L–band in presence of inter-channel stimulated Raman scattering (ISRS) and to support non-linear interference (NLI) modeling. High prediction accuracy is obtained with maximum errors ≤ 0.1 dB over thousands different partial loads.File | Dimensione | Formato | |
---|---|---|---|
ECOC_2021___MLPP_supporting_NLI_modeling.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
242.43 kB
Formato
Adobe PDF
|
242.43 kB | Adobe PDF | Visualizza/Apri |
Machine_Learning_for_Power_Profiles_Prediction_in_Presence_of_Inter-channel_Stimulated_Raman_Scattering.pdf
non disponibili
Descrizione: Versione ufficiale dell'editore
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
845.59 kB
Formato
Adobe PDF
|
845.59 kB | 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.
https://hdl.handle.net/11583/2947716