基于拓扑链路识别的光网络流量数据合成算法

周刚; 吴树霖; 张江龙; 吴小华; 庄浩涛; 赵永利

doi:10.13756/j.gtxyj.2022.01.007

您当前的位置：

首页 >

文章列表页 >

基于拓扑链路识别的光网络流量数据合成算法

光通信系统与网络技术 | 更新时间：2022-06-15

- 基于拓扑链路识别的光网络流量数据合成算法
- Traffic Data Synthesis Algorithm for Optical Network based on Topological Link Recognition
- 光通信研究 2022年第1期页码：31-36
- 作者机构：
  
  1.国网福建省电力有限公司，福州　350003
  2.国网福建省电力有限公司信息通信分公司，福州　350003
  3.安徽继远软件有限公司，合肥　230088
  4.北京邮电大学，北京　100876
- 作者简介：
  
  周刚(1963-)，男，山东济南人。高级工程师，学士，主要研究方向为电力系统运行与控制研究及管理。
  庄浩涛，硕士。E-mail：zhnghaotiu@bupt.edu.cn
- 基金信息：
  
  国家电网有限公司总部科技资助项目(52130M190008)
- DOI：10.13756/j.gtxyj.2022.01.007
  中图分类号： TN915
- 纸质出版日期：2022-02-10，
  
  收稿日期：2021-05-11，
扫描看全文
周刚, 吴树霖, 张江龙, 等. 基于拓扑链路识别的光网络流量数据合成算法[J]. 光通信研究, 2022,(1):31-36.

ZHOU Gang, WU Shu-lin, ZHANG Jiang-long, et al. Traffic Data Synthesis Algorithm for Optical Network based on Topological Link Recognition[J]. Study on Optical Communications, 2022,(1):31-36.
周刚, 吴树霖, 张江龙, 等. 基于拓扑链路识别的光网络流量数据合成算法[J]. 光通信研究, 2022,(1):31-36. DOI： 10.13756/j.gtxyj.2022.01.007.

ZHOU Gang, WU Shu-lin, ZHANG Jiang-long, et al. Traffic Data Synthesis Algorithm for Optical Network based on Topological Link Recognition[J]. Study on Optical Communications, 2022,(1):31-36. DOI： 10.13756/j.gtxyj.2022.01.007.

摘要

基于深度学习的光网络流量诊断与预测等场景中，由于保密等原因，光链路的流量数据采集和存储工作受限。针对数据量少而无法支撑深度学习的问题，文章提出了一种基于拓扑链路识别的光网络流量数据合成算法，其核心思想是在生成对抗网络框架下，联合基于光网络拓扑的条件生成模型和基于光网络流量的数据合成模型，以自监督的方式合成指定光链路的流量数据。仿真结果表明，所提算法合成的光网络流量数据在自相关系数指标上与真实数据接近且使得基于全连接神经网络的流量预测模型准确率达到95%以上。

Abstract

In the scenarios of traffic diagnostic analysis and prediction in optical network based on deep learning

the work of traffic data collection and storage for optical link is limited due to security and other reasons. Aiming at the problem that the amount of traffic data is too small to support deep learning training

this paper proposes an optical network traffic data synthesis algorithm based on topology link recognition. The core idea is to combine the conditional generation model based on optical network topology and the data synthesis model based on optical network traffic in the framework of generative adversarial networks. The traffic data of the given optical link is synthesized in a self-supervised way. The simulation results show that the auto-correlation coefficients of the traffic data synthesized by the proposed algorithm is close to the real data

and the accuracy of the traffic prediction model based on fully connected neural network is more than 95%.

关键词

光网络深度学习流量预测数据合成

Keywords

optical networkdeep learningtraffic predictiondata synthesis

references

Becchi M. From Poisson Processes to Self-Similarity: a Survey of Network Traffic Models[EB/OL]. (2008-01-01)[2021-05-11]. http://www.cse.wustl.edu/jain/cse567-06/trafficmodels1.htmhttp://www.cse.wustl.edu/jain/cse567-06/trafficmodels1.htm.

Zhang X, Wang Y, Zhang Q. Self-Similar Traffic Discrimination and Generating Methods based on Fractal Brown Motion[J]. Journal of Computer Applications, 2013, 33(4): 947-949.

Flandrin P. Wavelet Analysis and Synthesis of Fractional Brownian Motion[J]. IEEE Transactions on Information Theory, 1992, 38(2): 910-917.

Mandelbrot B B. Self-Similar Error Clusters in Communication Systems and the Concept of Conditional Stationarity[J]. IEEE Transactions on Communication Technology, 1965, 13(1): 71-90.

Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Networks[J]. Advances in Neural Information Processing Systems, 2014, 3: 2672-2680.

Yu L, Zhang W, Wang J, et al. Seqgan: Sequence Generative Adversarial Nets with Policy Gradient[C]//Association for the Advancement of Artificial Intelligence. San Francisco, California, USA: AAAI, 2017: 2852-2858.

Yoon J, Jarrett D, Schaar M. Time-Series Generative Adversarial Networks[J]. Advances in Neural Information Processing Systems, 2019, 32: 5508-5518.

Lin Z, Jain A, Wang C, et al. Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions[C]//Proceedings of the ACM Internet Measurement Conference. Dublin, Ireland: IMC, 2020: 464-483.

Zeiler M, Fergus R. Visualizing and Understanding Convolutional Networks[C]//European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 818-833.

Knyazev B, Barth E, Martinetz T. Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks[C]//International Joint Conference on Neural Networks. Anchorage, Alaska: IJCNN, 2017: 2486-2493.

Sundermeyer M, Schlüter R, Ney H. LSTM Neural Networks for Language Modeling[C]//Conference of the International Speech Communication Association. Oregon, Portland: INTERSPEECH, 2012: 194-197.

Chen C, Mu S, Xiao W, et al. Improving Image Captioning with Conditional Generative Adversarial Nets[C]//Proceedings of National Conference on Artificial Intelligence Conference on Artificial Intelligence. Honolulu, Hawaii, USA: AAAI, 2019, 33(1): 8142-8150.

Arjovsky M, Chintala S, Bottou L. Wasserstein Generative Adversarial Networks[C]//International Conference on Machine Learning. Sydney, Australia: PMLR, 2017: 214-223.

Bence J R. Analysis of Short Time Series: Correcting for Autocorrelation[J]. Ecology, 1995, 76(2): 628-639.

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

电力线载波通信中基于深度学习的信道估计

深度学习在光纤通信系统损伤补偿中的应用

基于深度学习的电光调制型可编程光学频率梳

基于机器学习的调制格式识别算法研究

混合线速率的虚拟光网络映射成本优化方法