迁移学习辅助基于机器学习的传输质量评估

王家馨

doi:10.13756/j.gtxyj.2022.06.008

您当前的位置：

首页 >

文章列表页 >

迁移学习辅助基于机器学习的传输质量评估

光通信系统与网络技术 | 更新时间：2023-01-29

- 迁移学习辅助基于机器学习的传输质量评估
- Transfer Learning Assisted Transmission Quality Evaluation based on Machine Learning
- 光通信研究 2022年第6期页码：45-49
- 作者机构：
  
  南京邮电大学　电子与光学工程学院、柔性电子(未来技术)学院，南京　210023
- 作者简介：
  
  王家馨，硕士。E-mail：1002054577@qq.com
- 基金信息：
- DOI：10.13756/j.gtxyj.2022.06.008
  中图分类号： TN929.11
- 纸质出版日期：2022-12-10，
  
  收稿日期：2022-04-07，
扫描看全文
王家馨. 迁移学习辅助基于机器学习的传输质量评估[J]. 光通信研究, 2022,(6):45-49.

WANG Jia-xin. Transfer Learning Assisted Transmission Quality Evaluation based on Machine Learning[J]. Study on Optical Communications, 2022,(6):45-49.
王家馨. 迁移学习辅助基于机器学习的传输质量评估[J]. 光通信研究, 2022,(6):45-49. DOI： 10.13756/j.gtxyj.2022.06.008.

WANG Jia-xin. Transfer Learning Assisted Transmission Quality Evaluation based on Machine Learning[J]. Study on Optical Communications, 2022,(6):45-49. DOI： 10.13756/j.gtxyj.2022.06.008.

摘要

当光纤链路的数据分布发生变化时，机器学习评估链路传输质量需要重新搜集数据并重新训练，这个过程是耗时的、复杂的。迁移学习直接将以前学到的知识应用到现在的任务，需要更少的数据。因此，文章提出在具有相关性的光通信系统中，使用两种迁移学习方式辅助基于机器学习的多分类器，仿真结果表明，迁移学习结合微调技术的机器学习多分类器比直接迁移的机器学习多分类器多分类指标分数提高0.25以上，减少了样本不均衡的影响，每个类别都具有高性能，证实迁移学习结合微调技术的机器学习多分类器能够减小数据集，降低了搜集数据集的成本，提高了光纤链路传输质量评估问题的效率。

Abstract

When the data distribution of optical fiber link changes

machine learning can be used to evaluate the transmission quality of link

which needs to recollect data and retrain. This process is time-consuming and complex. Transfer learning directly applies the previously learned knowledge to the current task

which requires less data. Therefore

it is proposed to use two transfer learning methods to realize multi classifier based on machine learning in the correlated optical communication system. The simulation results show that the multi classifier of machine learning combined with transfer learning and fine-tuning technology improves the multi classification index score by more than 0.25 compared with the direct transfer machine learning multi classifier. It is also shown that the impact of sample imbalance is reduced

and each category has high performance. It is proved that the machine learning multi classifier combined with transfer learning and fine-tuning technology can reduce the size of data set

reduce the cost of collecting data set

and improve the efficiency of transmission quality evaluation process in optical fiber link.

关键词

光纤链路传输质量机器学习迁移学习

Keywords

fiber optical linksquality of transmissionmachine learningtransfer learning

references

Rottondi C, Marino R D, Nava M, et al. On the Benefits of Domain Adaptation Techniques for Quality of Transmission Estimation in Optical Networks[J]. Journal of Optical Communications and Networking, 2021, 13(1): A34-A43.

Yu J, Mo W, Huang Y K, et al. Model Transfer of QoT Prediction in Optical Networks based on Artificial Neural Networks[J]. Journal of Optical Communications and Networking, 2019, 11(10): C48-C57.

Xu Y L, Wang D S, Zhang M, et al. Deep Transfer Learning based Multi-Impairment Diagnosis for PAM-4 Optical Communication Systems[C]//2019 18th International Conference on Optical Communications and Networks (ICOCN). Huangshan, China: IEEE, 2019: 1-3.

Liu Y L, Chen X L, Proietti R, et al. Evol-TL: Evolutionary Transfer Learning for QoT Estimation in Multi-domain Networks[C] //Optical Fiber Communications Conference and Exhibition (OFC). San Diego, USA: IEEE, 2020: 1-3.

Aladin S, Tremblay C. Cognitive Tool for Estimating the QoT of New Lightpaths[C]//Optical Fiber Communication Conference and Exposition (OFC). San Diego, USA: IEEE, 2018: 1-3.

Carena A. Modeling of the Impact of Nonlinear Propagation Effects in Uncompensated Optical Coherent Transmission Links[J]. Journal of Lightwave Technology, 2012, 30(10): 1524-1539.

Tremblay C, Allogba S, Aladin S. Machine Learning Techniques for Estimating Quality of Transmission Estimation of Lightpaths[C]//2018 IEEE Photonics Society Summer Topical Meeting Series (SUM). Hilton Waikoloa Village, USA: IEEE, 2018.

Tremblay C, Allogba S, Aladin S. Quality of Transmission Estimation and Performance Prediction of Lightpaths Using Machine Learning[C]//45th European Conference on Optical Communication (ECOC 2019). Dublin, Ireland: IEEE, 2019: 1-3.

Pointurier Y. Design of Low-margin Optical Networks[J]. Journal of Optical Communications and Networking, 2017, 9(1): A9-A17.

Poggiolini P, Bosco G, Carena A, et al. The GN-model of Fiber Non-linear Propagation and Its Applications[J]. Journal of Lightwave Technology, 2014, 32(4): 694-721.

Aurélien Géron(奥雷利安·杰龙). 机器学习实战：基于机器Scikit_Learn, Keras和Tensorflow[M]. 宋能辉, 李娴，译. 北京: 机械工业出版社, 2020.

Aurélien Géron.Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Second Edition[M]. BO’Reilly Media, Inc., 2020.

Morais R M, Pedro J. Machine Learning Models for Estimating Quality of Transmission in DWDM Networks[J]. Journal of Optical Communications and Networking, 2018, 10(10): D84-D99.

Khan I, Bilal M, Curri V. Assessment of Cross-train Machine Learning Techniques for QoT-estimation in Agnostic Optical Networks[J]. OSA Continuum, 2020, 3(10): 2690-2706.

Khan F N, Fan Q, Lu C, et al. An Optical Communication’s Perspective on Machine Learning and Its Applications[J]. Journal of Lightwave Technology, 2019, 37(2): 493-516.

周志华. 机器学习[M]. 北京: 清华大学出版社, 2018.

Zhou Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2018.

Albon C(克里斯阿尔本). Python机器学习手册：从数据预处理到深度学习[M]. 韩慧昌, 林然, 徐江，译. 北京: 电子工业出版社, 2018.

Chris Albon.Python: Machine Learning with Python Cookbook[M]. BO’Reilly Media, Inc., 2018.

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

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

基于机器学习的调制格式识别算法研究

基于机器学习的相干光通信系统传输性能评估

基于机器学习的软件定义光网络入侵检测策略