Abstract
We propose the use of spectral data-driven LSTM-based machine learning to improve generalized signal-to-noise ratio (gSNR) quality-of-transmission estimation in component parameter-agnostic network scenarios. We show gSNR estimation improvements up to 1.1 dB for unseen networks.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Lars E. Kruse, Sebastian Kühl, and Stephan Pachnicke
Tu5.41 European Conference and Exhibition on Optical Communication (ECOC) 2022
Giacomo Borraccini, Stefano Straullu, Alessio Giorgetti, Rocco D’Ingillo, Davide Scano, Andrea D’Amico, Emanuele Virgillito, Antonino Nespola, Nicola Sambo, Filippo Cugini, and Vittorio Curri
M4F.5 Optical Fiber Communication Conference (OFC) 2022
Omran Ayoub, Andrea Bianco, Davide Andreoletti, Sebastian Troia, Silvia Giordano, and Cristina Rottondi
M3F.5 Optical Fiber Communication Conference (OFC) 2022