基于人工智能的光纤非线性均衡算法研究概述

doi:10.11959/j.issn.1000-0801.2020054

电信科学 ›› 2020, Vol. 36 ›› Issue (3): 61-70.doi: 10.11959/j.issn.1000-0801.2020054

基于人工智能的光纤非线性均衡算法研究概述

李亚杰,赵永利,刘守东,张杰()

北京邮电大学信息光子学与光通信国家重点实验室，北京 100876

修回日期:2020-02-25 出版日期:2020-03-20 发布日期:2020-03-26
作者简介:李亚杰（1990- ），男，博士，北京邮电大学师资博士后，主要研究方向为光网络智能控制和安全光通信|赵永利（1981- ），男，北京邮电大学教授、博士生导师，主要研究方向为人工智能光网络和安全光通信|刘守东（1995- ），男，北京邮电大学硕士生，主要研究方向为人工智能与安全光传输|张杰（1972- ），男，博士，北京邮电大学教授、博士生导师，光电信息学院院长，信息光子学与光通信国家重点实验室副主任，主要研究方向为安全光通信等
基金资助:
国家电网有限公司科技项目(5100-201940006A-0-0-00)

Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence

Yajie LI,Yongli ZHAO,Shoudong LIU,Jie ZHANG()

State Key Laboratory of Information Photonics and Optical Communications,Beijing University of Posts and Telecommunications,Beijing 100876,China

Revised:2020-02-25 Online:2020-03-20 Published:2020-03-26
Supported by:
The Technology Project of State Grid Corporation of China(5100-201940006A-0-0-00)

摘要/Abstract

摘要：

概述了非线性均衡算法在光传输系统中的必要性与重要性，阐述了经典的非线性均衡算法原理，指出了经典算法的缺点与局限性。结合近几年的研究现状，详细介绍了 4 种基于人工智能的非线性均衡算法，包括人工神经网络、支持向量机、无监督聚类和深度神经网络，并从性能、复杂度、实时性、应用灵活性等方面进行了对比，最后展望分析了基于人工智能的非线性均衡未来的发展趋势。

关键词: 非线性均衡, 人工神经网络, 支持向量机, 聚类, 深度神经网络

Abstract:

The necessity and importance of nonlinear equalization algorithm in optical transmission systems were outlined.The principle of classical nonlinear equalization algorithm was described,and the shortcomings and limitations of classical algorithms were presented.Combined with the status in recent years,four kinds of nonlinear equalization algorithms based on artificial intelligence were introduced in detail.These algorithms include artificial neural networks,support vector machine,unsupervised clustering and deep neural network.All the nonlinear equalization algorithms mentioned were compared in terms of performance,complexity,instantaneity and application flexibility.Finally,the future development trend of nonlinear equalization algorithm based on artificial intelligence was analyzed.

Key words: nonlinear equalization, artificial neural network, support vector machine, clustering, deep neural network

中图分类号:

TN911.22

李亚杰,赵永利,刘守东,张杰. 基于人工智能的光纤非线性均衡算法研究概述[J]. 电信科学, 2020, 36(3): 61-70.

Yajie LI,Yongli ZHAO,Shoudong LIU,Jie ZHANG. Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence[J]. Telecommunications Science, 2020, 36(3): 61-70.

图/表 5

图1

图2

图3

图4

表1

参考文献 30

[1]	吴金达, 卢瑾 . 基于广义回归神经网络的CO-OFDM系统非线性均衡[J]. 光学学报, 2018,38(9): 78-86.
	WU J D , LU J . Nonlinear equalizer based on general regression neural network in coherent optical OFDM system[J]. Acta Optica Sinica, 2018,38(9): 78-86.
[2]	LU C H , FENG K M . Reduction of high PAPR effect with FEC enhanced deep data clipping ratio in an optical OFDM system[C]// Proceedings of Conference on Lasers and Electro-Opticals Society. Piscataway:IEEE Press, 2007: 941-942.
[3]	BULAKCI O , SCHUSTER M , BUNGE C A ,et al. Precoding based peak-to-average power ratio reduction for optical OFDM demonstrated on compatible single sideband modulation with direct detection[C]// Proceedings of 2008 National Fiber Optic Engineers Conference. Piscataway:IEEE Press, 2008: 1-3.
[4]	KRONGOLD B S , TANG Y , SHIEH W . Fiber non-linearity mitigation by PAPR reduction in coherent optical OFDM systems via active constellation extension[C]// Proceedings of 2008 34th European Conference on Optical Communication. Piscataway:IEEE Press, 2008: 1-2.
[5]	GIACOUMIDIS E . Harnessing machine learning for fiber-induced nonlinearity mitigation in long-haul coherent optical OFDM[J]. Future Internet, 2019,11(1): 1-20.
[6]	GIACOUMIDIS E . Blind non-linearity equalization by machine-learning-based clustering for single-and multichannel coherent optical OFDM[J]. Journal of Lightwave Technology, 2018,36(6): 721-727.
[7]	IP E M , KAHN J M . Fiber impairment compensation using coherent detection and digital signal processing[J]. Journal of Lightwave Technology, 2010,28(4): 502-519.
[8]	GAO G J , ZHANG J , GU W Y . Analytical evaluation of practical DBP-based intra-channel nonlinearity compensators[J]. IEEE Photonics Technology Letters, 2013,25(8): 717-720.
[9]	CHUN-YEN C , . Sparse volterra nonlinear equalizer by employing pruning algorithm for high-speed PAM-4 850-nm VCSEL optical interconnect[C]// Proceedings of Optical Fiber Communication Conference. Piscataway:IEEE Press, 2019.
[10]	JARAJREH M A . Artificial neural network nonlinear equalizer for coherent optical OFDM[J]. IEEE Photonics Technology Letters, 2015,27(4): 387-390.
[11]	GIACOUMIDIS E , . Intra and inter-channel nonlinearity compensation in WDM coherent optical OFDM using artificial neural network based nonlinear equalization[C]// Proceedings of Process Optical Fiber Communication Conference. Piscataway:IEEE Press, 2019.
[12]	AHMED G R . Nonlinear equalizer based on neural networks for PAM-4 signal transmission using DML[J]. IEEE Photonics Technology Letters, 2018,30(15): 1416-1419.
[13]	VAQUERO F J , . Joint estimation of linear and non-linear signal-to-noise ratio based on neural networks[C]// Proceedings of Optical Fiber Communication Conference. Piscataway:IEEE Press, 2019.
[14]	WANG D S , . Nonlinear decision boundary created by a machine learning-based classifier to mitigate nonlinear phase noise[C]// Proceedings of European Conference on Optical Communications.[S.l.:s.n]. 2015.
[15]	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): 711-721.
[16]	GIACOUMIDIS E . Reduction of nonlinear inter-subcarrier intermixing in coherent optical OFDM by a fast newton-based support vector machine nonlinear equalizer[J]. Journal of Lightwave Technology, 2017,35(12): 2391-2397.
[17]	GIACOUMIDIS E . Unsupervised support vector machines for nonlinear blind equalization in CO-OFDM[J]. IEEE Photonics Technology Letters, 2018,30(12): 1091-1094.
[18]	ZHANG K , FAN Y Y , et al . Fiber nonlinear noise-to-signal ratio estimation by machine learning[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2019.
[19]	ZHANG J F . K-means-clustering-based fiber nonlinearity equalization techniques for 64-QAM coherent optical communication system[J]. Optics Express, 2017,25(22): 27570-27580.
[20]	LU X Y , . Non-linear compensation of multi-CAP VLC system employing pre-distortion base on clustering of machine learning[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2018.
[21]	CHUANG C Y , . Sparse volterra nonlinear equalizer by employing pruning algorithm for high-speed PAM-4 850-nm VCSEL optical interconnect[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2019.
[22]	GIACOUMIDIS E , . Fiber nonlinear compensation using machine learning clustering[C]// Proceedings of International Conference on Recent Innovations in Engineering and Technology.[S.l.:s.n]. 2019.
[23]	GIACOUMIDIS E , . Real-time machine learning based fiber-induced nonlinearity compensation in energy-efficient coherent optical networks[C]// Proceedings of European Conference on Optical Communications.[S.l.:s.n]. 2019.
[24]	GIACOUMIDIS E . A blind nonlinearity compensator using DBSCAN clustering for coherent optical transmission systems[J]. Applied Sciences, 2019,9(20): 4398-4406.
[25]	GAO Y L , ZIAD A . Reduced complexity nonlinearity compensation via principal component analysis and deep neural networks[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2019.
[26]	CHUANG C Y , . Convolutional neural network based nonlinear classifier for 112-Gbps high speed optical link[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2018.
[27]	LI P X , . 56 Gbit/s IM/DD PON based on 10G-class optical devices with 29 dB loss budget enabled by machine learning[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2018.
[28]	SCHAEDLER M , . Subcarrier power loading for coherent optical OFDM optimized by machine learning[C]// Proceedings of Optical Fiber Communication Conference.[S.l.:s.n]. 2018.
[29]	ZHANG S L . Field and lab experimental demonstration of nonlinear impairment conpensation using neural networks[J]. Nature Communications, 2019(10):3033.
[30]	KOIKE-AKINO T , . Neural turbo equalization to mitigate fiber nonlinearity[C]// Proceedings of European Conference on Optical Communications.[S.l.:s.n. ], 2019.

算法	原理	性能	复杂度	实时性	应用灵活性
简单DSP算法	降低OFDM峰均比	一般	低	差	一般
常用DSP算法（如DBP）	非线性薛定谔方程建模	较好	高	差	一般
基于ANN的非线性均衡算法	非线性判决或非线性映射	较好	较高	较好	较好
基于SVM的非线性均衡算法	非线性判决或非线性映射	较好	较高	较好	较好
基于聚类的非线性均衡算法	非线性判决	较好	低	好	好
基于DNN的非线性均衡算法	非线性判决或非线性映射	较好	较高	较好	较好

基于人工智能的光纤非线性均衡算法研究概述

Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 30

相关文章 15

Metrics

推荐阅读 0

[1]	卢敏, 秦泽豪, 陈志辉, 张敏, 乐光学. 基于1D-Concatenate的信道估计DNN模型优化方法[J]. 电信科学, 2023, 39(4): 71-86.
[2]	刘昊双, 张永, 曹莹波. 基于K-means聚类的子结构相关适配迁移学习方法[J]. 电信科学, 2023, 39(3): 124-134.
[3]	李攀攀, 谢正霞, 乐光学, 刘鑫. 基于深度学习的无线通信接收方法研究进展与趋势[J]. 电信科学, 2022, 38(2): 1-17.
[4]	李世通, 全大英, 唐泽雨, 陈赟, 汪晓峰, 金小萍. 基于时频图像和高次频谱特征的雷达信号识别[J]. 电信科学, 2022, 38(2): 84-91.
[5]	赵海波, 相志军, 肖林松. 基于异构数据的电力短期负荷大数据预测方案[J]. 电信科学, 2022, 38(12): 103-111.
[6]	金宁, 王庆扬. 基于聚类算法的6G典型应用场景研究[J]. 电信科学, 2022, 38(1): 121-131.
[7]	陆勰, 徐雷, 张曼君. 基于聚类的安全分级虚拟网络映射方法[J]. 电信科学, 2021, 37(9): 112-117.
[8]	孙姝君, 彭盛亮, 姚育东, 杨喜. 基于深度学习的调制识别综述[J]. 电信科学, 2021, 37(5): 82-90.
[9]	刘子豪, 贾小军, 张素兰, 徐志玲, 张俊. 一种融合MeanShift聚类分析和卷积神经网络的Vibe++背景分割方法[J]. 电信科学, 2021, 37(3): 133-145.
[10]	吴季桦, 朱鹏宇, 吴子辰, 顾彬, 洪涛, 郭波, 王晶, 王敬宇. 基于无监督聚类和频繁子图挖掘的电力通信网缺陷诊断与自动派单[J]. 电信科学, 2021, 37(11): 51-63.
[11]	李想,李原,张子飞,杨哲. 基于密度聚类的网络性能故障大数据分析方法[J]. 电信科学, 2020, 36(9): 51-58.
[12]	闵锐. 高效深度神经网络综述[J]. 电信科学, 2020, 36(4): 115-124.
[13]	孙洋,粟栗,张星,王峰生,杜海涛. 基于子语义空间的挖掘短文本策略方法[J]. 电信科学, 2020, 36(3): 83-94.
[14]	刘汉生,唐洪玉,薄明霞,牛剑锋,李天博,李玲晓. 基于机器学习的多源威胁情报质量评价方法[J]. 电信科学, 2020, 36(1): 119-126.
[15]	张溶芳,许丹丹,王元光,潘思宇,李正茂. 机器学习在物联网虚假用户识别中的运用[J]. 电信科学, 2019, 35(7): 136-144.