基于LDBP的色散和光纤非线性损伤补偿

陈志轩; 蔡炬; 张洪波; 张敏; 蒙建宇; 张倩武

doi:10.13756/j.gtxyj.2024.230047

您当前的位置：

首页 >

文章列表页 >

基于LDBP的色散和光纤非线性损伤补偿

光通信系统与网络技术 | 更新时间：2024-08-05

- 基于LDBP的色散和光纤非线性损伤补偿
- Chromatic Dispersion and Fiber Nonlinear Impairment Compensation based on LDBP
- 光通信研究 2024年第4期页码：23004701-23004705
- 作者机构：
  
  1.成都信息工程大学　通信工程学院，成都　610225
  2.四川大学，成都　610065
  3.上海大学　特种光纤与光接入网省部共建重点实验室，上海　200072
- 作者简介：
  
  陈志轩（1999－），男，四川成都人。硕士，主要研究方向为高速光纤通信和人工智能。
  蔡炬，教授。E-mail：caiju@cuit.edu.cn
- 基金信息：
  
  四川省科技计划资助项目(2021YFG0149);上海市科委重点实验室资助项目(SKLSFO2019-06);高等学校学科创新引智计划资助项目（111）(D20031)
- DOI：10.13756/j.gtxyj.2024.230047
  中图分类号： TN929
- 纸质出版日期：2024-08-10，
  
  收稿日期：2023-08-08，
  
  修回日期：2023-08-20，
- 稿件说明：
扫描看全文
陈志轩，蔡炬，张洪波，等. 基于LDBP的色散和光纤非线性损伤补偿[J]. 光通信研究，2024(4)：230047.

Chen Z X, Cai J, Zhang H B, et al. Chromatic Dispersion and Fiber Nonlinear Impairment Compensation based on LDBP [J]. Study on Optical Communications, 2024(4)：230047.
陈志轩，蔡炬，张洪波，等. 基于LDBP的色散和光纤非线性损伤补偿[J]. 光通信研究，2024(4)：230047. DOI： 10.13756/j.gtxyj.2024.230047.

Chen Z X, Cai J, Zhang H B, et al. Chromatic Dispersion and Fiber Nonlinear Impairment Compensation based on LDBP [J]. Study on Optical Communications, 2024(4)：230047. DOI： 10.13756/j.gtxyj.2024.230047.

摘要

【目的】

在长距离光通信系统中，由于克尔非线性、色散和放大自发辐射噪声之间的相互作用，使用传统的数字信号处理（DSP）来补偿光纤非线性损伤十分困难。机器学习算法可以用于在传统DSP的基础上对信号进行进一步处理，以缓解光纤非线性损伤并提高长距离光纤传输系统的性能。

【方法】

为了更好地补偿光纤传输中色散和非线性损伤，文章将传统的数字反向传播（DBP）算法和深度神经网络（DNN）相结合，将DBP中的线性步长和非线性步长作为一个神经元，即将线性步长看作DNN的权重矩阵，非线性步长看作激活函数，并将DSP作为DNN的静态层，提出了一种基于DNN的自学习DBP（LDBP）算法。

【结果】

为了验证文章所提算法的可行性，在单通道偏振复用16阶正交幅度调制（QAM）的光传输系统中进行了仿真。综合数值仿真结果表明，与线性均衡相比较，每跨一步的LDBP算法将最佳发射功率从－2 dBm提高至1 dBm。同时，与相同计算复杂度的DBP算法相比，LDBP算法在1 200 km的传输距离下，信噪比（SNR）提高了0.82 dB。此外，与线性均衡和相同计算复杂度的DBP算法相比，LDBP算法所对应传输系统的SNR随着传输距离的增加，下降速度更加缓慢，并且该算法可以在无需预知链路参数的情况下工作，具有普适性和鲁棒性。

【结论】

文章所提LDBP算法与传统DBP算法相比，更加适用于实际的长距离相干光通信系统。

Abstract

【Objective】

In long-distance optical communication systems

compensating fiber nonlinear impairment through traditional Digital Signal Processing (DSP) is difficult due to intractable interactions between Kerr nonlinearity

chromatic dispersion and amplified spontaneous emission noise. Machine learning algorithm can be used to further process signals on the basis of traditional DSP to mitigate fiber nonlinear impairment and improve long-distance transmission performance.

【Methods】

In this paper

the traditional Digital Back Propagation (DBP) algorithm is combined with Deep Neural Network (DNN)

where the linear step size and nonlinear step size in DBP are taken as one neuron. It means that the linear step size is taken as the weight matrix of DNN

the nonlinear step size is taken as the activation function

and DSP is taken as the static layer of DNN. A DNN-based Learned Digital Back Propagation (LDBP) algorithm is proposed.

【Results】

In order to verify the feasibility of the proposed LDBP algorithm

the simulation was carried out in a single-channel polarization division multiplexing 16-ary Quadrature Amplitude Modulation (QAM) optical transmission system. The numerical simulation results demonstrate that the 1-step-per-span LDBP algorithm improves the optimal launched power from -2 dBm to 1 dBm in compared to linear equalization. Meanwhile

compared with DBP with the same computational complexity

the proposed algorithm improves Signal-to-Noise Ratio (SNR) by 0.82 dB at the transmission distance of 1 200 km. In addition

compared with DBP with the same computational complexity and linear equalization

the SNR of the transmission system corresponding to LDBP method decreases more slowly with the increase of transmission distance

and the algorithm can work without knowing the link parameters

showing the characteristic of universality and robustness.

【Conclusion】

The proposed LDBP algorithm is more suitable for practical long-distance coherent optical communication system than the traditional DBP algorithm.

关键词

色散补偿非线性损伤补偿深度神经网络自学习数字反向传播

Keywords

chromatic dispersion compensationnonlinear impairment compensationDNNLDBP

references

Winzer P J, Neilson D T, Chraplyvy A R. Fiber-optic Transmission and Networking: The Previous 20 and the Next 20 Years[J]. Optics Express, 2018, 26(18):24190-24239.

Winzer P J, Neilson D T. From Scaling Disparities to Integrated Parallelism: A Decathlon for a Decade[J]. Journal of Lightwave Technology, 2017, 35(5):1099-1115.

Zhao J, Liu Y, Xu T. Advanced DSP for Coherent Optical Fiber Communication[J]. Applied Sciences, 2019, 9(19):4192.

Ip E, Kahn J M. Compensation of Dispersion and Nonlinear Impairments Using Digital Backpropagation[J]. Journal of Lightwave Technology, 2008, 26(20):3416-3425.

Gonçalves J, Martins C S, Guiomar F P, et al. Nonlinear Compensation with DBP Aided by a Memory Polynomial[J]. Optics Express, 2016, 24(26):30309-30316.

Ferreira F M, Sillekens E, Karanov B, et al. Digital Back Propagation via Sub-band Processing in Spatial Multiplexing Systems [J]. Journal of Lightwave Technology, 2021, 39(4):1020-1026.

Saavedra G, Liga G, Bayvel P. Volterra-assisted Optical Phase Conjugation: a Hybrid Optical-digital Scheme for Fiber Nonlinearity Compensation [J]. Journal of Lightwave Technology, 2019, 37(10):2467-2479.

Sharan Yadav G, Chuang C Y, Feng K M, et al. Reducing Computation Complexity by Using Elastic Net Regularization based Pruned Volterra Equalization in a 80 Gbps PAM-4 Signal for Inter-data Center Interconnects[J]. Optics Express, 2020, 28(26):38539-38552.

Yu Y, Wang W, Townsend P D, et al. Modified Phase-conjugate Twin Wave Schemes for Spectral Efficiency Enhancement[C]//2015 European Conference on Optical Communication (ECOC). Valencia, Spain: IEEE, 2015: 7341994.

Husain S S, Hmood J K. Performance Enhancement of PCTWs Technique by Employing RZ-coding in Phase-modulated Optical Communication Systems[C]//AIP Conference Proceedings. Baghdad, Iraq: AIP Publishing, 2020: 020094.

Jordan M I, Mitchell T M. Machine Learning: Trends, Perspectives, and Prospects[J]. Science, 2015, 349(6245):255-260.

Lau A P T, Khan F N, Fan Q, et al. Application of Machine Learning Techniques in Fiber-optic Communication Systems[C]//Signal Processing in Photonic Communications. Washington, US: OSA, 2018: SpW4G.1.

Häger C, Pfister H D. Nonlinear Interference Mitigation via Deep Neural Networks[C]//Optical Fiber Communication Conference. San Diego, California, Washington, US: OSA, 2018: W3A.4.

Fan Q, Lu C, Lau A P T. Combined Neural Network and Adaptive DSP Training for Long-haul Optical Communications[J]. Journal of Lightwave Technology, 2021, 39(22):7083-7091.

Fan Q, Zhou G, Gui T, et al. Advancing Theoretical Understanding and Practical Performance of Signal Processing for Nonlinear Optical Communications through Machine Learning[J]. Nature Communications, 2020, 11(1):3694.

Sarroff A M. Complex Neural Networks for Audio[D]. Hanover Town, New Hampshire, USA: Dartmouth College, 2018.

Luo L C, Xiong Y H, Liu Y, et al. Adaptive Gradient Methods with Dynamic Bound of Learning Rate[EB/OL]. (2019-02-26)[ 2023-08-08]. http://arxiv.org/abs/1902.09843http://arxiv.org/abs/1902.09843.

李韦萍, 孔淼, 余建军. 基于偏振复用光调制器产生PDM-16QAM射频信号[J]. 光学学报, 2020, 40(23):2306002.

Li W P, Kong M, Yu J J. Generation of PDM-16QAM Radio Frequency Signal based on a Polarization Multiplexing Optical Modulator [J]. Acta Optica Sinica, 2020, 40(23):2306002.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

水下可见光通信星座几何整形和人工智能技术

基于深度神经网络的IMDD系统光性能监测技术

基于深度神经网络的EON自适应调制方法研究

基于信号功率非线性变换的光信噪比监测

啁啾光纤光栅色散补偿方案研究