Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Pedro J. Freire; Michael Anderson; Bernhard Spinnler; Thomas Bex; Jaroslaw E. Prilepsky; Tobias A. Eriksson; Nelson Costa; Wolfgang Schairer; Michaela Blott; Antonio Napoli; Sergei K. Turitsyn

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Signal Processing 2022-06-27 v1 Machine Learning

Authors: Pedro J. Freire , Michael Anderson , Bernhard Spinnler , Thomas Bex , Jaroslaw E. Prilepsky , Tobias A. Eriksson , Nelson Costa , Wolfgang Schairer , Michaela Blott , Antonio Napoli , Sergei K. Turitsyn

View on arXiv ↗ PDF ↗

Abstract

For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1 step-per-span DBP.

Keywords

fpga implementation neural network equalizer nonlinearity compensation coherent optical transmission dispersion equalizer digital backpropagation

Cite

@article{arxiv.2206.12180,
  title  = {Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems},
  author = {Pedro J. Freire and Michael Anderson and Bernhard Spinnler and Thomas Bex and Jaroslaw E. Prilepsky and Tobias A. Eriksson and Nelson Costa and Wolfgang Schairer and Michaela Blott and Antonio Napoli and Sergei K. Turitsyn},
  journal= {arXiv preprint arXiv:2206.12180},
  year   = {2022}
}

Comments

Accepted Oral in the European Conference on Optical Communication (ECOC) 2022

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Abstract

Keywords

Cite

Comments

Related papers