基于高斯过程回归的光纤非线性信道补偿方法

吴彪; 李嘉浩; 张召才

doi:10.13756/j.gtxyj.2022.06.006

您当前的位置：

首页 >

文章列表页 >

基于高斯过程回归的光纤非线性信道补偿方法

光通信系统与网络技术 | 更新时间：2023-01-29

- 基于高斯过程回归的光纤非线性信道补偿方法
- Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link
- 光通信研究 2022年第6期页码：35-38,76
- 作者机构：
  
  1.国网电力科学研究院武汉南瑞有限责任公司，武汉　430074
  2.武汉大学　电气与自动化学院，武汉　430072
  3.北京空间科技信息研究所，北京　100094
- 作者简介：
  
  吴彪(1976-)，男，湖北汉川人。高级工程师，硕士，主要研究方向为雷电监测与电子通信技术。
  张召才，高级工程师。E-mail：zhangzhaocai@gmail.com
- 基金信息：
- DOI：10.13756/j.gtxyj.2022.06.006
  中图分类号： TP309
- 纸质出版日期：2022-12-10，
  
  收稿日期：2022-05-05，
扫描看全文
吴彪, 李嘉浩, 张召才. 基于高斯过程回归的光纤非线性信道补偿方法[J]. 光通信研究, 2022,(6):35-38,76.

WU Biao, LI Jia-hao, ZHANG Zhao-cai. Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link[J]. Study on Optical Communications, 2022,(6):35-38,76.
吴彪, 李嘉浩, 张召才. 基于高斯过程回归的光纤非线性信道补偿方法[J]. 光通信研究, 2022,(6):35-38,76. DOI： 10.13756/j.gtxyj.2022.06.006.

WU Biao, LI Jia-hao, ZHANG Zhao-cai. Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link[J]. Study on Optical Communications, 2022,(6):35-38,76. DOI： 10.13756/j.gtxyj.2022.06.006.

摘要

为了降低光纤传输系统中非线性噪声带来的影响，文章提出了基于高斯过程回归 (GPR) 的非线性信道均衡器(CE)，并在强度调制和直接检测光纤链路中进行了实验验证。在文章所提方案中，GPR模型用于估计预处理后的传输符号或相应的非线性噪声。实验结果表明，基于GPR的非线性CE比传统的线性或非线性CE具有更好的性能。实验结果还表明，非线性信道均衡过程中的GPR模型可以理解为具有无限宽度的单层神经网络模型。

Abstract

In order to mitigate the effect of nonlinear noise nonlinear Channel Equalizer (CE) based on Gaussian Processes for Regression (GPR) is proposed and experimentally demonstrated in an intensity modulation and direct detection fiber link. In this scheme

the GPR model is used to estimate the transmitted symbols or the corresponding nonlinear noise after pre-processing. The experimental results show that the nonlinear CE based on GPR has better performance than conventional linear and nonlinear filter-based CE. In addition

it is shown that the GPR model in the nonlinear channel equalization process can be understood as an optimized single-layer neural network model with infinite width.

关键词

高斯过程回归信道均衡器单层神经网络

Keywords

GPRCEsingle-layer neural network

references

Cartledge J C, Guiomar F P, Kschischang F R, et al. Digital Signal Processing for Fiber Nonlinearities[J]. Optics Express, 2017, 25(3): 1916-1936.

Pierluigi P, Bosco G. Long-haul WDM IMDD Transmission at 10.7 Gbit/s in a Dispersion-managed Multispan System Using MLSE Receivers[J]. Journal of Lightwave Technology, 2008, 26(17): 3041-3047.

Peddanarappagari K V, Brandt-Pearce M. Volterra Series Transfer Function of Single-mode Fibers[J]. Journal of Lightwave Technology, 1997, 15(12): 2232-2241.

Giacoumidis E, Son T L, Ghanbarisabagh M, et al. Fiber Nonlinearity-induced Penalty Reduction in CO-OFDM by ANN-based Nonlinear Equalization[J]. Optics Letters, 2015, 40(21): 5113-5116.

Sidelnikov O, Alexey R, Stylianos Sygletos M, et al. Advanced Convolutional Neural Networks for Nonlinearity Mitigation in Long-haul WDM Transmission Systems[J]. Journal of Lightwave Technology, 2021, 39(8): 2397-2406.

Yang Z, Gao F, Fu S, et al. Radial Basis Function Neural Network Enabled C-band 4× 50 Gb/s PAM-4 Transmission over 80 km SSMF[J]. Optics Letters, 2018, 43(15): 3542-3545.

Nguyen T, Mhatli S, Giacoumidis E, et al. Fiber Nonlinearity Equalizer based on Support Vector Classification for Coherent Optical OFDM[J]. IEEE Photonics Journal, 2016, 8(2): 2528886.

Deligiannidis S, Bogris A, Mesaritakis C, et al. Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-term Memory Neural Networks[J]. Journal of Lightwave Technology, 2020, 38(21): 5991-5999.

Rasmussen C E, Williams C K I. Gaussian Processes for Machine Learning[M]. Cambridge, Massachusetts, USA: MIT Press, 2006.

Cruz F, Fuentes J M, Caro S. Nonlinear Channel Equalization with Gaussian Processes for Regression[J]. IEEE Trans.on Signal Processing, 2008, 56(10): 5283-5286.

Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-Learn: Machine Learning in Python[J]. Journal of Machine Learning Research, 2011, 12: arXiv.1201.0490.

Kamalov V, Jovanovski L, Vusirikala V, et al. Evolution from 8QAM Live Traffic to PS 64-QAM with Neural-network based Nonlinearity Compensation on 11 000 km Open Subsea Cable[C]//2018 Optical Fiber Communications Conference and Exposition. San Diego, US: OFC, 2018: Th4D.5.

更多指标>

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据