Memory-aware end-to-end learning of channel distortions in optical coherent communications

Abstract

We implement a new variant of the end-to-end learning approach for the performance improvement of an optical coherent-detection communication system. The proposed solution enables learning the joint probabilistic and geometric shaping of symbol sequences by using auxiliary channel model based on the perturbation theory and the refined symbol probabilities training procedure. Due to its structure, the auxiliary channel model based on the first order perturbation theory expansions allows us performing an efficient parallelizable model application, while, simultaneously, producing a remarkably accurate channel approximation. The learnt multi-symbol joint probabilistic and geometric shaping demonstrates a considerable bit-wise mutual information gain of 0.47 bits/2D-symbol over the conventional Maxwell-Boltzmann shaping for a single-channel 64 GBd transmission through the 170 km single-mode fiber link.

Publication DOI: https://doi.org/10.1364/OE.470154
Divisions: College of Engineering & Physical Sciences > Aston Institute of Photonics Technology (AIPT)
Aston University (General)
Additional Information: Published by Optica Publishing Group under the terms of the Creative Commons Attribution 4.0 License [https://creativecommons.org/licenses/by/4.0/]. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funding: H2020 Marie Skłodowska-Curie Actions (766115); Engineering and Physical Sciences Research Council (EP/R035342/1); Leverhulme Trust (RP-2018-063).
Publication ISSN: 1094-4087
Last Modified: 02 Dec 2024 08:57
Date Deposited: 24 Jul 2023 15:50
Full Text Link:
Related URLs: https://opg.opt ... 1-1-1&id=524423 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2023-01-02
Published Online Date: 2022-12-19
Accepted Date: 2022-10-30
Authors: Neskorniuk, Vladislav (ORCID Profile 0000-0002-3358-153X)
Carnio, Andrea
Marsella, Domenico
Turitsyn, Sergei K. (ORCID Profile 0000-0003-0101-3834)
Prilepsky, Jaroslaw E. (ORCID Profile 0000-0002-3035-4112)
Aref, Vahid

Download

[img]

Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Statistics

Additional statistics for this record