Experimental Demonstration of SPM Compensation Based on Digital Signal Processing Using a Complex-Valued Neural Network for 40-Gbit/s Optical 16QAM Signals

2018 23rd Opto-Electronics and Communications Conference (OECC) Pub Date : 2018-07-01 DOI:10.1109/OECC.2018.8730139

Yuta Fukumoto, Shotaro Owaki, T. Sakamoto, N. Yamamoto, Moriya Nakamura

引用次数: 6

Abstract

We experimentally demonstrated a novel nonlinearity-mitigation scheme based on a complex-valued neural network. A 40-Gbit/s optical 16QAM signal distorted by SPM was successfully compensated, accelerating the learning speed, and improving EVM by about 15%.

查看原文本刊更多论文

基于复值神经网络的40gbit /s光16QAM信号SPM补偿的实验验证

实验证明了一种新的基于复值神经网络的非线性缓解方案。成功地补偿了被SPM畸变的40gbit /s光16QAM信号，提高了学习速度，EVM提高了约15%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊