Sparse identification for nonlinear optical communication systems: SINO method.

@article{Sorokina2016SparseIF,
  title={Sparse identification for nonlinear optical communication systems: SINO method.},
  author={Mariia Sorokina and Stylianos Sygletos and Sergei K. Turitsyn},
  journal={Optics express},
  year={2016},
  volume={24 26},
  pages={
          30433-30443
        }
}
We introduce low complexity machine learning method method (based on lasso regression, which promotes sparsity, to identify the interaction between symbols in different time slots and to select the minimum number relevant perturbation terms that are employed) for nonlinearity mitigation. The immense intricacy of the problem calls for the development of "smart" methodology, simplifying the analysis without losing the key features that are important for recovery of transmitted data. The proposed… 

Figures and Tables from this paper

A Machine Learning-Based Detection Technique for Optical Fiber Nonlinearity Mitigation

The performance of a machine learning classification technique, called the Parzen window, to mitigate the fiber nonlinearity in the context of dispersion managed and dispersion unmanaged systems is investigated and a performance improvement up to 0.4 dB in terms of Q factor is observed.

Compensation of Nonlinear Impairments Using Inverse Perturbation Theory With Reduced Complexity

A model based on perturbation analysis of an inverse Manakov problem, where the received signal is used as the initial condition and Manakov equations are solved in the reversed direction, effectively implementing a perturbative digital backward propagation enhanced by machine learning techniques.

Perturbative Machine Learning Technique for Nonlinear Impairments Compensation in WDM Systems

A perturbation-based receiver-side machine-learning equalizer for inter- and intra-channel nonlinearity compensation in WDM systems is proposed and dB improvement compared with linear equalization and DBP is shown.

A Novel Nonlinear Noise Power Estimation Method Based on Error Vector Correlation Function Using Artificial Neural Networks For Coherent Optical Fiber Transmission Systems

The results in this work verified that the ANN with EVC, ANC and PNC as input can make the trained model feasible to accurately estimate the nonlinear noise power in high speed optical coherent communication systems.

Multidimensional fiber echo state network analogue

The developed MD-FESNA is the first neuromorphic technology which augments all aforementioned advantages of FESNA with multidimensional spatio-temporal processing by utilizing multi-mode fiber non-linearity.

Perturbation-Based FEC-Assisted Iterative Nonlinearity Compensation for WDM Systems

It is shown by numerical simulations and transmission experiments that a feedback from the FEC decoder enables improved compensation performance, allowing the receiver to operate very close to the full data-aided performance bounds.

Dispersion-Managed Fiber Echo State Network Analogue With High (Including THz) Bandwidth

A design for high (including THz) bandwidth neuromorphic signal processing based on fiber echo state network analogue is proposed and its efficiency for distortion mitigation in optical communications with high-order formats is demonstrated.

Fiber echo state network analogue for high-bandwidth dual-quadrature signal processing.

This work proposes a fiber echo state network analogue (FESNA) - the first optical technology that provides both high bandwidth and dual-quadrature signal processing and demonstrates applicability of the designed system for prediction tasks and for the mitigation of distortions in optical communication systems with multilevel dual- quadrature encoded signals.

A Survey on Machine Learning for Optical Communication [Machine Learning View]

For the first time, this paper reviews ML for OC literature from ML viewpoint, and has worth to mention that compared with other works, this survey reviews much more investigations, and gives the reader to have a comprehensive overview on this topic.
...

References

SHOWING 1-10 OF 21 REFERENCES

Nonlinear Compensation Using Backpropagation for Polarization-Multiplexed Transmission

  • E. Ip
  • Physics
    Journal of Lightwave Technology
  • 2010
Digital backpropagation (BP) is a universal method for jointly compensating dispersion and nonlinear impairments in optical fiber and is applicable to signals of any modulation format. In this paper,

Efficient nonlinear equalizer for intra-channel nonlinearity compensation for next generation agile and dynamically reconfigurable optical networks.

A novel low-complexity technique for fiber nonlinearity compensation that achieved a transmission distance of 2818 km for a 32-GBaud dual-polarization 16QAM signal and the complexity of the proposed algorithm is lower than previously studied nonlinear equalizers by more than one order of magnitude.

Multiplier-Free Intrachannel Nonlinearity Compensating Algorithm Operating at Symbol Rate

Intrachannel nonlinearity is considered a major distortion in high-capacity transmission systems particular for the case without inline optical chromatic dispersion compensation. In this paper, a

Reducing the complexity of perturbation based nonlinearity pre-compensation using symmetric EDC and pulse shaping.

Perturbation based nonlinearity pre-compensation has been performed for a 128 Gbit/s single-carrier dual-polarization 16-ary quadrature-amplitude-modulation (DP 16-QAM) signal. Without any

Capacity limits of systems employing multiple optical phase conjugators.

It is identified that the optimum noise suppression is achieved for an odd number of phase conjugators, and that the noise may be further suppressed by up to 3dB by partial digital back propagation (or fractional spans at the ends of the links).

Perturbation Analysis of Nonlinear Propagation in a Strongly Dispersive Optical Communication System

We discuss an analytical model that predicts the impact of the Kerr nonlinearity in optical communication systems when the signal spectrum is wide and the accumulated dispersion during propagation is

Volterra series transfer function of single-mode fibers

A nonrecursive Volterra series transfer function (VSTF) approach for solving the nonlinear Schrodinger (NLS) wave equation for a single-mode optical fiber is presented. The derivation of the VSTF is

Nonlinear Propagation in Multimode and Multicore Fibers: Generalization of the Manakov Equations

We investigate theoretically nonlinear transmission in space-division multiplexed (SDM) systems using multimode fibers exhibiting rapidly varying birefringence. A primary objective is to generalize

MMSE-Based Optimization of Perturbation Coefficients Quantization for Fiber Nonlinearity Mitigation

In perturbation-based digital fiber nonlinearity mitigation methods, such as pre-distortion and post-equalization, quantization of perturbation coefficients is employed to reduce the computational

Overcoming Kerr-induced capacity limit in optical fiber transmission

It is demonstrated that optical carrier stability plays a critical role in canceling Kerr-induced distortions and that nonlinear wave interaction in silica can be substantially reverted if optical carriers possess a sufficient degree of mutual coherence, indicating that fiber information capacity can be notably increased over previous estimates.