Research on OTN Service Delay Estimation Method based on Machine Learning

YANG Ganggang; SHAO Zhugui; JIANG Xianrong

doi:10.13756/j.gtxyj.2024.230114

您当前的位置：

首页 >

文章列表页 >

Research on OTN Service Delay Estimation Method based on Machine Learning

更新时间：2024-12-05

- Research on OTN Service Delay Estimation Method based on Machine Learning
- Study on Optical Communications Issue 6, Pages: 23011401-23011406(2024)
- 作者机构：
  
  中国电信股份有限公司研究院，北京　102209
- 作者简介：
- 基金信息：
- DOI：10.13756/j.gtxyj.2024.230114
  CLC： TP393
- Published：10 December 2024，
  
  Received：20 November 2023，
  
  Revised：16 December 2023，
- 稿件说明：
移动端阅览
杨刚刚，邵珠贵，姜先荣. 基于机器学习的OTN业务时延估算方法研究[J]. 光通信研究，2024(6):230114.

Yang G G, Shao Z G, Jiang X R. Research on OTN Service Delay Estimation Method based on Machine Learning [J]. Study on Optical Communications, 2024(6):230114.
杨刚刚，邵珠贵，姜先荣. 基于机器学习的OTN业务时延估算方法研究[J]. 光通信研究，2024(6):230114. DOI： 10.13756/j.gtxyj.2024.230114.

Yang G G, Shao Z G, Jiang X R. Research on OTN Service Delay Estimation Method based on Machine Learning [J]. Study on Optical Communications, 2024(6):230114. DOI： 10.13756/j.gtxyj.2024.230114.

摘要

【目的】

为满足时延敏感型应用场景对时延数据的时效性、准确性和完整性要求，需要实现光传送网络（OTN）端到端业务时延估算。

【方法】

文章分析了OTN业务的传输特点，根据子网连接采集业务路由信息，并将业务路由中的网元（NE）、链路和交叉等基础数据离散化，得到时延估算的特征变量，提出了基于工程现网数据的时延估算模型，并采用多种机器学习算法进行了仿真比较。

【结果】

基于支持向量机回归（SVR）和决策树回归的时延预测结果的平均绝对百分比误差（MAPE）分别为3.362 8%和1.284 9%。

【结论】

文章基于机器学习、结合OTN业务传输特点提出的OTN业务时延估算方法准确性高，具有广泛的应用场景。

Abstract

【Objective】

To meet the requirements of timeliness

accuracy

and completeness of delay data in delay-sensitive application scenarios

it is necessary to implement end-to-end service delay estimation in Optical Transport Networks (OTN).

【Methods】

This paper first analyzes the transmission characteristics of OTN services

and collects service routing information according to the sub-net connections. Next

it discretizes the basic data such as Network Elements (NE)

links

and cross-connection in service route. Then the characteristic variables for delay estimation are obtained. Finally

the paper proposes a delay estimation model based on engineering live network

and compares the simulation results of various machine learning algorithms.

【Results】

The Mean Absolute Percentage Errors (MAPE) of the delay estimation results based on Support Vector Regression (SVR) and decision tree regression were 3.362 8% and 1.284 9%

respectively.

【Conclusion】

The OTN service delay estimation method based on machine learning and the characteristic of OTN transmission in this paper has high accuracy and wide application scenarios.

关键词

光传送网络时延估算机器学习

Keywords

OTNdelay estimationmachine learning

references

ITU-T G. 709-2009, Interfaces for the Optical Transport Network[S].

张旭, 邓庆林, 陈鹏, 等. 基于Telemetry架构的OTN设备性能采集系统研究[J]. 光通信研究, 2023(6):45-50.

Zhang X, Deng Q L, Chen P, et al. Research on OTN Equipment Performance Collection System based on Telemetry Architecture[J]. Study on Optical Communications, 2023(6):45-50.

荆瑞泉, 霍晓莉, 李俊杰, 等. 以OSU为核心的M-OTN技术创新与验证[J]. 电信科学, 2021, 37(4):116-124.

Jing R Q, Huo X L, Li J J, et al. OSU based M-OTN Technology Innovation and Verification[J]. Telecommunications Science, 2021, 37(4):116-124.

李世峰. 基于改进BP网络的时延预测建模与仿真[J]. 唐山师范学院学报, 2022, 44(6):56-59.

Li S F. Modeling and Simulation of Time Delay Prediction based on Improved BP Network[J]. Journal of Tangshan Normal University, 2022, 44(6):56-59.

吴上, 邓浩江, 盛益强. 基于门控循环神经网络的网络时延预测模型[J]. 网络新媒体技术, 2021, 10(6):29-37.

Wu S, Deng H J, Sheng Y Q. A Network Latency Prediction Model based on Gated Recurrent Neural Network[J]. Network New Media Technology, 2021, 10(6):29-37.

苏旭东, 衷璐洁. 基于BPNN端到端时延预测的多路传输调度[J]. 计算机工程与设计, 2022, 43(1):66-72.

Su X D, Zhong L J. Multipath Scheduling based on BPNN for End to End Transmission Delay Prediction[J]. Computer Engineering and Design, 2022, 43(1):66-72.

Chang C C, Lin C J. LIBSVM: a Library for Support Vector Machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):1-27.

Deb K, Pratap A, Agarwal S, et al. A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Satellite Internet of Things Load Estimation and Prediction

Nonlinear Equalization Method based on Machine Learning in 30 Tbit/s DP-16QAM Transmission System

Optical Network Monitoring and Optimization Methods based on Machine Learning

Beam Selection Algorithm in Millimeter Wave based on GCNet

Application of Optical Fiber Distributed Sensing System in Substation Maintenance

Related Author

ZHANG Gengxin

WANG Haitao

MAO Xiwen

LUO Ming

YANG Chao

FAN Runzhe

LUO Min

LIU Wu

Related Institution

School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications

National Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation

Wuhan Research Institute of Posts and Telecommunications

National Key Laboratory of Optical Communication Technologies and Networks, China Information and Communication Technologies Group Corporation

Wuhan Research Institute of Posts and Telecommunications Co., Ltd., China Information and Communication Technologies Group Corporation

Postal code：430205
Technical support is provided by Beijing Founder electronics co., LTD 鄂ICP备2022010197 鄂公网安备 42011202002092号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：118284 Visits Today：53

⁰