Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link

WU Biao; LI Jia-hao; ZHANG Zhao-cai

doi:10.13756/j.gtxyj.2022.06.006

您当前的位置：

首页 >

文章列表页 >

Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link

更新时间：2023-01-29

- Nonlinear Channel Equalization based on Gaussian Processes for Regression in Fiber Link
- Study on Optical Communications Issue 6, Pages: 35-38,76(2022)
- 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：
- 基金信息：
- DOI：10.13756/j.gtxyj.2022.06.006
  CLC： TP309
- Published：10 December 2022，
  
  Received：05 May 2022，
扫描看全文
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 (6):35-38,76(2022)
DOI：

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 (6):35-38,76(2022) 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>

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Postal code：430205
Technical support is provided by Beijing Founder electronics co., LTD 鄂ICP备2022010197 鄂公网安备 42011202002092号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：75848 Visits Today：3

⁰