基于机器学习的相干光通信系统传输性能评估

陈中盛; 高冠军; 刘鸿飞

doi:10.13756/j.gtxyj.2021.04.004

您当前的位置：

首页 >

文章列表页 >

基于机器学习的相干光通信系统传输性能评估

光通信系统与网络技术

- 基于机器学习的相干光通信系统传输性能评估
- Transmission Performance Evaluation of Coherent Optical Communication System based on Machine Learning
- 光通信研究 2021年第4期页码：15-20
- 作者机构：
  
  1.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
  2.中国科学院国家天文台FAST重点实验室，北京　100101
- 作者简介：
  
  陈中盛，硕士。E-mail：zhongshengchen520@163.com
- 基金信息：
  
  国家自然科学基金资助项目(U1831110);北京邮电大学行动计划资助项目(2019XD-A15);信息光子学与光通信国家重点实验室自主研究课题资助项目(IPOC2020ZZ02)
- DOI：10.13756/j.gtxyj.2021.04.004
  中图分类号： TN914
- 纸质出版日期：2021-08-10，
  
  收稿日期：2020-12-28，
扫描看全文
陈中盛, 高冠军, 刘鸿飞. 基于机器学习的相干光通信系统传输性能评估[J]. 光通信研究, 2021,(4):15-20.

CHEN Zhong-sheng, GAO Guan-jun, LIU Hong-fei. Transmission Performance Evaluation of Coherent Optical Communication System based on Machine Learning[J]. Study on Optical Communications, 2021,(4):15-20.
陈中盛, 高冠军, 刘鸿飞. 基于机器学习的相干光通信系统传输性能评估[J]. 光通信研究, 2021,(4):15-20. DOI： 10.13756/j.gtxyj.2021.04.004.

CHEN Zhong-sheng, GAO Guan-jun, LIU Hong-fei. Transmission Performance Evaluation of Coherent Optical Communication System based on Machine Learning[J]. Study on Optical Communications, 2021,(4):15-20. DOI： 10.13756/j.gtxyj.2021.04.004.

摘要

针对传统相干光通信系统中光纤链路传输性能评估方法理论计算复杂且计算时间较长的问题，文章采用机器学习技术对调制格式和输入光功率等参数各异信道的相干光传输系统传输性能进行关联式建模和精确评估。建模和评估结果表明，该机器学习模型能够代替复杂的理论计算，并且能够较为准确地给出预测值，理论计算值与模型预测

值整体的平均误差为0.27 dB，理论计算值与模型预测光信噪比（OSNR）值整体的平均误差为0.33 dB；采用机器学习模型的计算时间稳定在4.4 s左右，而采用理论计算的时间随着干扰信道个数的增加计算时间逐渐增加。

Abstract

In view of the complexity of theoretical calculation and long calculation time of traditional evaluation method of optical fiber link transmission performance in coherent optical communication system

this paper uses machine learning technology to build correlation model and accurately evaluate the transmission performance of coherent optical transmission system with different modulation format and input optical power parameters. Through the training model

the results show that the machine learning model can replace the complex theoretical calculation

and can more accurately predict the predicted value

The overall average error between the theoretical value and the predicted

value is 0.27 dB. The overall average error between the theoretical value and the predicted Optical Signal to Noise Ratio (OSNR) value is 0.33 dB. The calculation time of machine learning model is about 4.4 s

while the theoretical calculation time increases with the increase of the number of interference channels.

关键词

机器学习相干光通信传输性能评估

Keywords

machine learningcoherent optical communicationtransmission performance evaluation

references

李炜, 陈宝靖, 柴京, 等.100 Gb/s PDM-QPSK系统传输性能评估技术研究[J].光通信技术, 2015, 39(4): 15-17.

Huang Y, Heritage J P, Mukherjee B. Connection Provisioning with Transmission Impairment Consideration in Optical WDM Networks with High-Speed Channels[J]. Journal of Lightwave Technology, 2005, 23(3): 982-993.

Ramamurthy B, Datta D, Feng H, et al. Impact of Transmission Impairments on the Teletraffic Performance of Wavelength-routed Optical Networks[J]. Journal of Lightwave Technology, 1999, 17(10): 1713-1723.

Martins-Filho J F, Bastos-Filho C J A, Arantes E A J.et al. Novel Routing Algorithm for Transparent Optical Networks based on Noise Figure and Amplifier Saturation[C]//Proceedings of the 2003 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference-IMOC 2003. Foz do Iguacu, Brazil: IEEE, 2003: 1242704.

Poggiolini P, Carena A, Curri V, et al. Analytical Modeling of Nonlinear Propagation in Uncompensated Optical Transmission Links[J]. IEEE Photonics Technology Letters, 2011, 23(11): 742-744.

Rottondi C, Barletta L, Giusti A, et al. Machine-Learning Method for Quality of Transmission Prediction of Unestablished Lightpaths[J]. Journal of Optical Communications and Networking, 2018, 10(2): A286-A297.

Seve E, Pesic J, Delezoide C, et al. Learning Process for Reducing Uncertainties on Network Parameters and Design Margins[J]. Journal of Optical Communications and Networking, 2018, 10(2): A298-A306.

Sartzetakis I, Christodoulopoulos K, Varvarigos E. Formulating Qo TEstimation with Machine Learning[C]//2018 European Conference on Optical Communication(ECOC). Rome, Italy: IEEE, 2018: 8535429.

Dar R, Feder M, Mecozzi A, et al. Properties of Nonlinear Noise in Long, Dispersion-Uncompensated Fiber Links[J]. Optics Express, 2013, 21(22): 25685-25699.

Poggiolini P, Jiang Y. Recent Advances in the Modeling of the Impact of Non-Linear Fiber Propagation Effects on Uncompensated Coherent Transmission Systems[J]. Journal of Lightwave Technology, 2017, 35(3): 458-480.

刘卫华.基于TensorFlow神经网络的数据中心故障预测研究[J].电子测试, 2019(16): 64-65, 130.

陈豪, 吴健.基于神经网络的正弦波函数拟合实现研究[J].现代信息科技, 2019, 3(21): 4-6.

更多指标>

浏览量

144

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于OFDM系统中双相位共轭孪生波的仿真研究

基于GCNet的毫米波波束选择算法

光纤分布式传感系统在变电站维护中的应用

迁移学习辅助基于机器学习的传输质量评估

基于机器学习的调制格式识别算法研究