Abstract

In this work, we address the question of the adaptability of artificial neural networks (NNs) used for impairments mitigation in optical transmission systems. We demonstrate that by using well-developed techniques based on the concept of transfer learning, we can efficaciously retrain NN-based equalizers to adapt to the changes in the transmission system, using just a fraction (down to 1%) of the initial training data or epochs. We evaluate the capability of transfer learning to adapt the NN to changes in the launch power, modulation format, symbol rate, or even fiber plants (different fiber types and lengths). The numerical examples utilize the recently introduced NN equalizer consisting of a convolutional layer coupled with bi-directional long-short term memory (biLSTM) recurrent NN element. Our analysis focuses on long-haul coherent optical transmission systems for two types of fibers: the standard single-mode fiber (SSMF) and the TrueWave Classic (TWC) fiber. We underline the specific peculiarities that occur when transferring the learning in coherent optical communication systems and draw the limits for the transfer learning efficiency. Our results demonstrate the effectiveness of transfer learning for the fast adaptation of NN architectures to different transmission regimes and scenarios, paving the way for engineering flexible and universal solutions for nonlinearity mitigation.

Bi-directional gated recurrent unit neural network based nonlinear equalizer for coherent optical communication system

Xinyu Liu, Yongjun Wang, Xishuo Wang, Hui Xu, Chao Li, and Xiangjun Xin
Opt. Express 29(4) 5923-5933 (2021)

Transfer learning assisted deep neural network for OSNR estimation

Le Xia, Jing Zhang, Shaohua Hu, Mingyue Zhu, Yingxiong Song, and Kun Qiu
Opt. Express 27(14) 19398-19406 (2019)

Optimizations and investigations for transfer learning of iteratively pruned neural network equalizers for data center networking

Jiawang Xiao, Lin Sun, Caoyang Liu, and Gordon Ning Liu
Opt. Express 30(20) 36358-36367 (2022)

Recurrent neural networks achieving MLSE performance for optical channel equalization

Sai-Chandra-Kumari Kalla, Christian Gagné, Ming Zeng, and Leslie A. Rusch
Opt. Express 29(9) 13033-13047 (2021)

Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer

Ivan Aldaya, Elias Giacoumidis, Athanasios Tsokanos, Mutsam Jarajreh, Yannuo Wen, Jinlong Wei, Gabriel Campuzano, Marcelo L. F. Abbade, and Liam P. Barry
Opt. Lett. 45(20) 5820-5823 (2020)