Interchannel nonlinearity compensation using a perturbative machine learning technique

We propose an extension of the perturbation-based approach for fiber nonlinearity compensation that is capable of mitigating both intra-and interchannel nonlinearity with a moderate increase in implementation complexity. Being guided by inverse perturbation theory we develop a straight-forward modification of the conventional model that takes into account nonlinear interactions between symbols from neighboring spectral channels. We employ machine learning techniques such as the normal equation model with regularization for joint identification of perturbation coefficients that are responsible for intra-and interchannel interactions. We investigate the application of the proposed approach for compensating nonlinear signal distortions in a 1200 km fiber-optic 3 x 400 Gbit/s WDM DP-64QAM transmission link. It was shown up to 0.83 dB and 0.51 dB Q2-factor improvement compared to chromatic dispersion equalization and one step per span two samples per symbol digital back-propagation technique, respectively. We estimate the implementation complexity of the approach.

Automated summary

The proposed extension of the perturbation-based approach for fiber nonlinearity compensation can effectively mitigate both intra-and interchannel nonlinearity with a moderate increase in implementation complexity. By utilizing machine learning techniques and regularization, the joint identification of perturbation coefficients for nonlinear interactions between symbols from neighboring spectral channels is achieved, resulting in improved compensation of nonlinear signal distortions in the transmission link.