High-Cardinality Hybrid Shaping for 4D Modulation Formats in Optical Communications Optimized via End-to-End Learning

Vinícius Oliari (Corresponding author), Boris Karanov, Sebastiaan Goossens, Gabriele Liga, Olga Vassilieva, Inwoong Kim, Paparao Palacharla, Chigo Okonkwo, Alex Alvarado

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademic

40 Downloads (Pure)

Samenvatting

In this paper we carry out a joint optimization of probabilistic (PS) and geometric shaping (GS) for four-dimensional (4D) modulation formats in long-haul coherent wavelength division multiplexed (WDM) optical fiber communications using an auto-encoder framework. We propose a 4D 10 bits/symbol constellation which we obtained via end-to-end deep learning over the split-step Fourier model of the fiber channel. The constellation achieved 13.6% reach increase at a data rate of approximately 400 Gbits/second in comparison to the ubiquitously employed polarization multiplexed 32-QAM format at a forward error correction overhead of 20%.
Originele taal-2Engels
Artikelnummer2112.10471
Pagina's (van-tot)1-5
Aantal pagina's5
TijdschriftarXiv
Volume2021
DOI's
StatusGepubliceerd - 20 dec. 2021

Trefwoorden

  • eess.SP

Vingerafdruk

Duik in de onderzoeksthema's van 'High-Cardinality Hybrid Shaping for 4D Modulation Formats in Optical Communications Optimized via End-to-End Learning'. Samen vormen ze een unieke vingerafdruk.

Citeer dit