2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于网络演算的时间敏感网络时延上界分析模型研究

胡文学 孙雷 王健全 朱渊 毕紫航

胡文学, 孙雷, 王健全, 朱渊, 毕紫航. 基于网络演算的时间敏感网络时延上界分析模型研究. 自动化学报, 2023, 49(11): 2297−2310 doi: 10.16383/j.aas.c220577
引用本文: 胡文学, 孙雷, 王健全, 朱渊, 毕紫航. 基于网络演算的时间敏感网络时延上界分析模型研究. 自动化学报, 2023, 49(11): 2297−2310 doi: 10.16383/j.aas.c220577
Hu Wen-Xue, Sun Lei, Wang Jian-Quan, Zhu Yuan, Bi Zi-Hang. Research on a latency upper-bound analysis model based on network calculus in time-sensitive networking. Acta Automatica Sinica, 2023, 49(11): 2297−2310 doi: 10.16383/j.aas.c220577
Citation: Hu Wen-Xue, Sun Lei, Wang Jian-Quan, Zhu Yuan, Bi Zi-Hang. Research on a latency upper-bound analysis model based on network calculus in time-sensitive networking. Acta Automatica Sinica, 2023, 49(11): 2297−2310 doi: 10.16383/j.aas.c220577

基于网络演算的时间敏感网络时延上界分析模型研究

doi: 10.16383/j.aas.c220577
基金项目: 国家重点研发计划基金(2020YFB1708800), 广东省重点领域研发计划基金(2020B0101130007), 中央高校基本科研业务费专项资金(FRF-BD-19-002A)资助
详细信息
    作者简介:

    胡文学:北京科技大学自动化学院博士研究生. 主要研究方向为工业确定性网络, 时间敏感网络路由与调度联合技术. E-mail: liter_ustb@xs.ustb.edu.cn

    孙雷:北京科技大学副教授. 主要研究方向为5G-TSN, 时间敏感网络和资源管理技术. 本文通信作者. E-mail: sun_lei@ustb.edu.cn

    王健全:北京科技大学教授. 主要研究方向为工业互联网与异构网络协同, 移动通信和网络关键技术. E-mail: wangjianquan@ustb.edu.cn

    朱渊:北京科技大学自动化学院硕士研究生. 主要研究方向为5G-TSN协同架构. E-mail: m202120748@xs.ustb.edu.cn

    毕紫航:北京科技大学自动化学院硕士研究生. 主要研究方向为工业网络流量调度整形机制. E-mail: zihang5663@163.com

Research on a Latency Upper-bound Analysis Model Based on Network Calculus in Time-sensitive Networking

Funds: Supported by National Key Research and Development Program of China (2020YFB1708800), Guangdong Provincial Key Research and Development Program (2020B0101130007), and the Fundamental Research Funds for the Central Universities (FRF-BD-19-002A)
More Information
    Author Bio:

    HU Wen-Xue Ph.D. candidate at the School of Automation and Electrical Engineering, University of Science and Technology Beijing. His research interest covers industrial deterministic network, routing and scheduling co-design for time-sensitive networking

    SUN Lei Associate professor at University of Science and Technology Beijing. His research interest covers 5G-TSN, time-sensitive networking, and resource management technologies. Corresponding author of this paper

    WANG Jian-Quan Professor at University of Science and Technology Beijing. His research interest covers industrial internet and heterogeneous network collaboration, mobile communication, and key technologies of network

    ZHU Yuan Master student at the School of Automation and Electrical Engineering, University of Science and Technology Beijing. His main research interest is 5G-TSN cooperation architecture

    BI Zi-Hang Master student at the School of Automation and Electrical Engineering, University of Science and Technology Beijing. His main research interest is traffic shaping mechanism in industrial internet

  • 摘要: 时间敏感网络(Time-sensitive networking, TSN)作为一种新兴工业通信技术, 能够为工业控制业务提供高可靠及确定性时延保障. 针对时间敏感网络在工业场景中广泛采用的时间感知整形(Time-aware shaper, TAS)机制, 提出一种基于网络演算的时延上界分析模型, 对多节点组网下端到端时延上界进行定量分析, 用以评估门控 (Gate control list, GCL)设置是否满足业务服务质量(Quality of service, QoS)需求, 有助于简化多节点组网场景下门控设置复杂度. 模型仿真部分对影响端到端时延的主要因素进行了对比分析, 并通过OMNeT++ 实时仿真验证了所提出时延上界分析模型的有效性.
  • 图  1  基于网络演算的性能指标分析

    Fig.  1  The performance indicators analysis based on network calculus

    图  2  到达曲线图形

    Fig.  2  The diagram of the arrival curve

    图  3  服务曲线样例

    Fig.  3  Service curve sample

    图  4  低优先级队列干扰时的门控形式

    Fig.  4  The gate control setting under the interference from the low-priority queue

    图  5  来自高优先级队列干扰的4种门控设置场景

    Fig.  5  Four scenes of the gate control setting under the interference from the high-priority queue

    图  6  最大等待时间示意图

    Fig.  6  The diagram of maximum waiting time

    图  7  到达−服务曲线模型

    Fig.  7  Arrival-service curve model

    图  8  网络拓扑结构

    Fig.  8  Network topology

    图  9  同一队列业务流的到达过程示意图

    Fig.  9  The arrival process of the traffic on the same queue

    图  10  SW1 门控仿真图

    Fig.  10  The simulation diagram of SW1's gate control

    图  11  SW1高优先级队列服务曲线

    Fig.  11  The service curve of the high-priority queue at SW1

    图  12  SW1高优先级业务流的 “到达−服务曲线” 模型

    Fig.  12  The “arrival-service curve” model of the high-priority traffic at SW1

    图  13  SW2高优先级业务流的 “到达−服务曲线” 模型

    Fig.  13  The “arrival-service curve” model of the high-priority traffic at SW2

    图  14  重叠程度对时延上界变化的影响

    Fig.  14  The influence of overlap on the latency upper-bound

    图  15  OMNeT++ 仿真场景

    Fig.  15  The simulation scene of OMNeT++

    图  16  高优先级业务流端到端时延分布统计

    Fig.  16  The end-to-end delay distribution statistics of the high-priority traffic

    表  1  基本参数符号

    Table  1  Basic parameter symbols

    符号 符号含义
    $f$ 业务流
    $p_f$ 业务流优先级
    $T_f$ 业务流到达周期
    $M$ 队列集合
    $p_m$ 队列优先级
    $T_m$ 队列门控周期
    $T_{\rm GCL}$ GCL超周期
    $G_m(t)$ 门控状态
    $t^{o, i}$ 第$i$个门控窗口的开启时间
    $t^{c, i}$ 第$i$个门控窗口的关闭时间
    $l^{\max}$ 数据帧的最大长度
    $C_{\rm out}$ 数据帧出队时的转发速率
    $\overline{L}^{i}$ 门控窗口的保证服务时隙
    $o^{j, i}$ 不同门控窗口之间的相对偏移量
    $S^{i}$ 最大等待时间
    $t_{up}$ 时延分布值上界
    下载: 导出CSV

    表  2  仿真参数设定

    Table  2  Simulation parameters setting

    参数 大小
    数据帧长度 400 Bytes
    发送速率 1 Gb/s
    链路传播时延 0.1 μs
    交换机处理时延 5 μs
    下载: 导出CSV

    表  3  业务流信息定义

    Table  3  The traffic information definition

    业务流 发送源端 周期T (μs) 到达时间$t_0$(μs)
    高优先级 ES1 100 40
    ES2 80
    ES5 20
    下载: 导出CSV

    表  4  SW1的GCL定义

    Table  4  The GCL definition of SW1

    交换机 优先级队列 组别 初始门控开闭时间(μs) 门控周期(μs)
    SW1 1 20 60 150
    2 20 60
    3 20 60
    4 20 70
    5 10 50
    1 45 80 150
    2 60 95
    3 40 75
    4 55 90
    5 35 70
    1 10 25 150
    2 5 20
    3 15 30
    4 10 25
    5 0 15
    下载: 导出CSV

    表  5  SW2的GCL定义

    Table  5  The GCL definition of SW2

    交换机 优先级队列 组别 初始门控开闭时间(μs) 门控周期(μs)
    SW2 1 60 100 150
    2 60 100
    3 60 100
    4 60 110
    5 50 90
    1 45 70 150
    2 35 60
    3 50 75
    4 45 70
    5 35 60
    1 95 110 150
    2 100 115
    3 90 105
    4 105 120
    5 85 100
    下载: 导出CSV

    表  6  各交换机WCD的上界

    Table  6  The upper-bound of WCD at each switch

    业务流 组别 WCD的上界(μs)
    SW1 SW2
    高优先级 1 82.9 124.7
    2 76.5 119.7
    3 82.9 126.1
    4 72.9 114.7
    5 82.9 124.7
    下载: 导出CSV

    表  7  组别1各交换机内部时延

    Table  7  The internal delay of each switch in the group 1

    交换机 交换机内部时延(μs)
    时延上界 处理时延 总时延$t_{\mathrm{SW}}$
    SW1 82.9 5 87.9
    SW2 124.7 5 129.7
    下载: 导出CSV

    表  8  中、低优先级业务流参数配置

    Table  8  The parameter configuration of the medium and low priority traffic

    业务流 发送源端 周期T (μs) 到达时间$t_0$ (μs)
    中优先级 ES3 150 40
    低优先级 ES4 200 15
    下载: 导出CSV
  • [1] 关新平, 陈彩莲, 杨博, 华长春, 吕玲, 朱善迎. 工业网络系统的感知−传输−控制一体化: 挑战和进展. 自动化学报, 2019, 45(1): 25−36

    Guan Xin-Ping, Chen Cai-Lian, Yang Bo, Hua Chang-Chun, Lv Ling, Zhu Shan-Ying. Towards the integration of sensing, transmission and control for industrial network systems: Challenges and recent developments. Acta Automatica Sinica, 2019, 45(1): 25-36
    [2] 蔡岳平, 姚宗辰, 李天驰. 时间敏感网络标准与研究综述. 计算机学报, 2021, 44(7): 1378−1397 doi: 10.11897/SP.J.1016.2020.01378

    Cai Yue-Ping, Yao Zong-Chen, Li Tian-Chi. A survey on time-sensitive networking: Standards and state-of-the-art. Chinese Journal of Computers, 2021, 44(7): 1378−1397 doi: 10.11897/SP.J.1016.2020.01378
    [3] 聂宏蕊, 李绍胜, 刘勇. 时间敏感网络中基于IEEE 802.1Qch标准的优化调度机制. 通信学报, 2022, 43(9): 12−26

    Nie Hong-Rui, Li Shao-Sheng, Liu Yong. Optimized scheduling mechanism based on IEEE 802.1Qch standard in time-sensitive networking. Journal on Communications, 2022, 43(9): 12−26
    [4] 时间敏感网络白皮书, 中国电子技术标准化研究院, 2020.

    Time-sensitive Networking White Paper, China Electronics Standardization Institute, 2020.
    [5] 李宗辉, 杨思琪, 喻敬海, 邓仰东, 万海. 时间敏感网络中确定性传输技术综述. 软件学报, 2022, 33(11): 4334−4355 doi: 10.13328/j.cnki.jos.006524

    Li Zong-Hui, Yang Si-Qi, Yu Jing-Hai, Deng Yang-Dong, Wan Hai. State-of-the-art survey on deterministic transmission technologies in time-sensitive networking. Journal of Software, 2022, 33(11): 4334−4355 doi: 10.13328/j.cnki.jos.006524
    [6] 张彤, 冯佳琦, 马延滢, 渠思源, 任丰原. 时间敏感网络流量调度综述. 计算机研究与发展, 2022, 59(4): 747−764 doi: 10.7544/issn1000-1239.20210203

    Zhang Tong, Feng Jia-Qi, Ma Yan-Ying, Qu Si-Yuan, Ren Feng-Yuan. Survey on traffic scheduling in time-sensitive networking. Journal of Computer Research and Development, 2022, 59(4): 747−764 doi: 10.7544/issn1000-1239.20210203
    [7] Maile L, Hielscher K S, German R. Network calculus results for TSN: An introduction. In: Proceedings of the Information Communication Technologies Conference (ICTC). Nanjing, China: IEEE, 2020. 131−140
    [8] Hu H, Li Q, Xiong H G, Fang B W. The delay bound analysis based on network calculus for asynchronous traffic shaping under parameter inconsistency. In: Proceedings of the IEEE 20th International Conference on Communication Technology (ICCT). Nanjing, China: IEEE, 2020. 908−915
    [9] Axer P, Thiele D, Ernst R, Diemer J. Exploiting shaper context to improve performance bounds of ethernet AVB networks. In: Proceedings of the 51st ACM/EDAC/IEEE Design Automation Conference (DAC). San Francisco, CA, USA: IEEE, 2014. 1−6
    [10] Mohammadpour E, Stai E, Mohiuddin M, Boudec J Y L. Latency and backlog bounds in time-sensitive networking with credit based shapers and asynchronous traffic shaping. In: Proceedings of the 30th International Teletraffic Congress (ITC 30). Vienna, Austria: IEEE, 2018. 1−6
    [11] Cao J Y, Cuijpers P J L, Bril R J, Lukkien J J. Tight worst-case response-time analysis for ethernet AVB using eligible intervals. In: Proceedings of the IEEE World Conference on Factory Communication Systems (WFCS). Aveiro, Portugal: IEEE, 2016. 1−8
    [12] Queck R. Analysis of ethernet AVB for automotive networks using network calculus. In: Proceedings of the IEEE International Conference on Vehicular Electronics and Safety (ICVES 2012). Istanbul, Turkey: IEEE, 2012. 61−67
    [13] Zhao L X, Pop P, Gong Z J, Fang B W. Improving latency analysis for flexible window-based GCL scheduling in TSN networks by integration of consecutive nodes offsets. IEEE Internet of Things Journal, 2021, 8(7): 5574−5584 doi: 10.1109/JIOT.2020.3031932
    [14] Zhao L X, Xiong H G, Zheng Z, Li Q. Improving worst-case latency analysis for rate-constrained traffic in the time-triggered ethernet network. IEEE Communications Letters, 2014, 18(11): 1927−1930 doi: 10.1109/LCOMM.2014.2358233
    [15] Zhao L X, Pop P, Li Q, Chen J Y, Xiong H G. Timing analysis of rate-constrained traffic in TTEthernet using network calculus. Real-Time Systems, 2017, 53(2): 254−287 doi: 10.1007/s11241-016-9265-0
    [16] Zhao L X, Pop P, Craciunas S S. Worst-case latency analysis for IEEE 802.1Qbv time sensitive networks using network calculus. IEEE Access, 2018, 6: 41803−41815 doi: 10.1109/ACCESS.2018.2858767
    [17] IEEE Standard for Local and Metropolitan Area Networks —— Bridges and Bridged Networks-amendment 25: Enhancements for Scheduled Traffic, IEEE Standard 802.1 Qbv, 2015.
    [18] Cruz R L. A calculus for network delay. I. Network elements in isolation. IEEE Transactions on Information Theory, 1991, 37(1): 114−131 doi: 10.1109/18.61109
    [19] Parekh A K, Gallager R G. A generalized processor sharing approach to flow control in integrated services networks: The single-node case. IEEE/ACM Transactions on Networking, 1993, 1(3): 344−357 doi: 10.1109/90.234856
    [20] Chang C S. On deterministic traffic regulation and service guarantees: A systematic approach by filtering. IEEE Transactions on Information Theory, 1998, 44(3): 1097−1110 doi: 10.1109/18.669173
    [21] Boudec J L, Thiran P. Network Calculus: A Theory of Deterministic Queuing Systems for the Internet. Berlin: Springer-Verlag, 2001.
    [22] 张晓楠. 基于随机网络演算的网络流量性能测量与分析[硕士学位论文], 北京邮电大学, 中国, 2021.

    Zhang Xiao-Nan. Measurement and Analysis of Traffic Network Performance Based on Stochastic Network Calculus [Master thesis], Beijing University of Posts and Telecommunications, China, 2021.
    [23] 李明辉. 基于网络演算的网络建模方法研究[硕士学位论文], 西南交通大学, 中国, 2007.

    Li Ming-Hui. Research on Network Modeling Based on Network Calculus [Master thesis], Southwest Jiaotong University, China, 2007.
    [24] 施金豆. 边缘网络业务性能分析模型和时延确定性传输算法研究[硕士学位论文], 南京邮电大学, 中国, 2021.

    Shi Jin-Dou. Research on Service Performance Analysis Model and Delay Deterministic Transmission Algorithm of Edge Networks [Master thesis], Nanjing University of Posts and Telecommunications, China, 2021.
    [25] Vojnovic M, Boudec J Y L. Stochastic analysis of some expedited forwarding networks. In: Proceedings of the Twenty-first Annual Joint Conference of the IEEE Computer and Communications Societies. New York, USA: IEEE, 2002. 1004−1013
    [26] Do Y, Kim M, Kim J, Jeon J. Method and analysis for the improvement of preemption performance in IEEE 802.1 TSN. In: Proceedings of the 17th International Conference on Ubiquitous Information Management and Communication (IMCOM). Seoul, South Korea: IEEE, 2023. 1−8
    [27] Integration of 5G With Time-Sensitive Networking for Industrial Communications, 5G-ACIA, 2021.
    [28] Paulon J V M, Souza B J O, Endler M. Exploring data collection on bluetooth mesh networks. Ad Hoc Networks, 2022, 130: 102809 doi: 10.1016/j.adhoc.2022.102809
    [29] 张林波, 刘彤. OMNeT++ 与无线通信网络仿真. 哈尔滨: 哈尔滨工业大学出版社, 2020. 18−23

    Zhang Lin-Bo, Liu Tong. OMNeT++ and Wireless Communication Network Simulation. Harbin: Harbin Institute of Technology Press, 2020. 18−23
  • 加载中
图(16) / 表(8)
计量
  • 文章访问数:  403
  • HTML全文浏览量:  162
  • PDF下载量:  134
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-07-19
  • 录用日期:  2023-02-10
  • 网络出版日期:  2023-07-10
  • 刊出日期:  2023-11-22

目录

    /

    返回文章
    返回