Reduction of Nonlinear Inter-Subcarrier Intermixing in Coherent Optical OFDM by a Fast Newton-based Support Vector Machine Nonlinear Equalizer

Sofien Mhatli, Marc F. C. Stephens, Athanasios Tsokanos, Jinlong Wei, Mary E. McCarthy, Nick J. Doran, Andrew D. Ellis

Research output: Contribution to journalArticlepeer-review

24 Citations (Scopus)
176 Downloads (Pure)

Abstract

A fast Newton-based support vector machine (N-SVM) nonlinear equalizer (NLE) is experimentally demonstrated, for the first time, in 40 Gb/s 16-quadrature amplitude modulated coherent optical orthogonal frequency division multiplexing at 2000 km of transmission. It is shown that N-SVM-NLE extends the optimum launched optical power by 2 dB compared to the benchmark Volterra-based NLE. The performance improvement by N-SVM is due to its ability of tackling both deterministic fiber-induced nonlinear effects and the interaction between nonlinearities and stochastic noises (e.g. polarization-mode dispersion). N-SVM is more tolerant to inter-subcarrier nonlinear crosstalk effects than Volterra-based NLE, especially when applied across all subcarriers simultaneously. In contrast to the conventional SVM, the proposed algorithm is of reduced classifier complexity offering lower computational load and execution time. For a low C -parameter of 4 (a penalty parameter related to complexity), an execution time of 1.6 sec is required for N-SVM to effectively mitigate nonlinearities. Compared to conventional SVM, the computational load of N-SVM is ~6 times lower.
Original languageEnglish
Pages (from-to) 2391-2397
Number of pages7
JournalJournal of Lightwave Technology
Volume35
Issue number12
Early online date8 Mar 2017
DOIs
Publication statusPublished - 15 Jun 2017

Keywords

  • coherent optical OFDM
  • coherent detection
  • nonlinearity mitigation
  • support vector machines

Fingerprint

Dive into the research topics of 'Reduction of Nonlinear Inter-Subcarrier Intermixing in Coherent Optical OFDM by a Fast Newton-based Support Vector Machine Nonlinear Equalizer'. Together they form a unique fingerprint.

Cite this