Abstract

A normalized batch gradient descent optimizer is proposed to improve the first-order regular perturbation coefficients of the Manakov equation, often referred to as kernels. The optimization is based on the linear parameterization offered by the first-order regular perturbation and targets enhanced low-complexity models for the fiber channel. We demonstrate that the optimized model outperforms the analytical counterpart where the kernels are numerically evaluated via their integral form. The enhanced model provides the same accuracy with a reduced number of kernels while operating over an extended power range covering both the nonlinear and highly nonlinear regimes. A 6–7 dB gain, depending on the metric used, is obtained with respect to the conventional first-order regular perturbation.

Inverse regular perturbation with ML-assisted phasor correction for fiber nonlinearity compensation

Hubert Dzieciol, Toshiaki Koike-Akino, Ye Wang, and Kieran Parsons
Opt. Lett. 47(14) 3471-3474 (2022)

Optical imaging: three-dimensional approximation and perturbation approaches for time-domain data

Regine Model, Matthias Orlt, Monika Walzel, and Rolf Hünlich
Appl. Opt. 37(34) 7968-7976 (1998)

Impact of the input OSNR on data-driven optical fiber channel modeling

Gao Ye, Junjiang Xiang, Gai Zhou, Meng Xiang, Jianping Li, Yuwen Qin, and Songnian Fu
J. Opt. Commun. Netw. 15(2) 78-86 (2023)

First-order perturbation theory for changes in the surrounding of open optical resonators

S. Both and T. Weiss
Opt. Lett. 44(24) 5917-5920 (2019)

Memory-efficient iterative process on a two-dimensional first-order regular graph

S. C. Park and H. Jeong
Opt. Lett. 33(1) 74-76 (2008)