光链路中深度神经网络均衡器性能的实验研究
信号处理
2021-06-25 v1
摘要
我们提出了一种卷积-循环信道均衡器，并在450公里TWC光纤上的单信道及96×WDM、DP-16QAM传输中实验证明了1dB Q因子提升。该新均衡器优于先前基于神经网络的方法以及每跨段3步的DBP。
引用
@article{arxiv.2106.13133,
title = {Experimental Study of Deep Neural Network Equalizers Performance in Optical Links},
author = {Pedro J. Freire and Yevhenii Osadchuk and Bernhard Spinnler and Wolfgang Schairer and Antonio Napoli and Nelson Costa and Jaroslaw E. Prilepsky and Sergei K. Turitsyn},
journal= {arXiv preprint arXiv:2106.13133},
year = {2021}
}
备注
Optical Fiber Communication Conference and Exhibition (OFC) 2021 - Oral Presentation