End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model

Vladislav Neskorniuk; Andrea Carnio; Vinod Bajaj; Domenico Marsella; Sergei K. Turitsyn; Jaroslaw E. Prilepsky; Vahid Aref

End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model

Signal Processing 2021-07-27 v1 Information Theory Machine Learning math.IT

Authors: Vladislav Neskorniuk , Andrea Carnio , Vinod Bajaj , Domenico Marsella , Sergei K. Turitsyn , Jaroslaw E. Prilepsky , Vahid Aref

View on arXiv ↗ PDF ↗

Abstract

We present a novel end-to-end autoencoder-based learning for coherent optical communications using a "parallelizable" perturbative channel model. We jointly optimized constellation shaping and nonlinear pre-emphasis achieving mutual information gain of 0.18 bits/sym./pol. simulating 64 GBd dual-polarization single-channel transmission over 30x80 km G.652 SMF link with EDFAs.

Keywords

end-to-end learning coherent optical communications regular perturbation model autoencoder constellation shaping nonlinear pre-emphasis mutual information

Cite

@article{arxiv.2107.12320,
  title  = {End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model},
  author = {Vladislav Neskorniuk and Andrea Carnio and Vinod Bajaj and Domenico Marsella and Sergei K. Turitsyn and Jaroslaw E. Prilepsky and Vahid Aref},
  journal= {arXiv preprint arXiv:2107.12320},
  year   = {2021}
}

Comments

4 pages; accepted for presentation at ECOC 2021 in September 2021

End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model

Abstract

Keywords

Cite

Comments

Related papers