计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (12): 37-45.doi: 10.11896/jsjkx.240200063

• 数字孪生网络与人工智能融合 • 上一篇    下一篇

面向数字孪生的混合业务确定性传输调度机制

王克文1,2, 张维庭3, 廖培希3   

  1. 1 北京交通大学电气工程学院 北京 100044
    2 国能新朔铁路有限责任公司 内蒙古 鄂尔多斯 010300
    3 北京交通大学电子信息工程学院 北京 100044
  • 收稿日期:2024-02-19 修回日期:2024-07-12 出版日期:2024-12-15 发布日期:2024-12-10
  • 通讯作者: 张维庭(wtzhang@bjtu.edu.cn)
  • 作者简介:(81349177@qq.com)
  • 基金资助:
    国家自然科学基金(62201029);中国博士后科学基金(2022M710007,BX20220029)

Deterministic Transmission Scheduling Mechanism for Mixed Traffic Flows Towards Digital Twin Networks

WANG Kewen1,2, ZHANG Weiting3, LIAO Peixi3   

  1. 1 School of Electronics and Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China
    2 Guoneng Xinshuo Railway Co., LTD., Ordos, Inner Mongolia 010300, China
    3 School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
  • Received:2024-02-19 Revised:2024-07-12 Online:2024-12-15 Published:2024-12-10
  • About author:WANG Kewen,born in 1980,master,senior engineer.His main research interests include railway information,communication,and automation.
    ZHANG Weiting,born in 1992,Ph.D,associate professor.His main research interests include industrial Internet of Things,deterministic networks,edge intelligence,and machine learning for network optimization.
  • Supported by:
    National Natural Science Foundation of China(62201029) and China Postdoctoral Science Foundation(2022M710007,BX20220029).

PDF (PC)

182

摘要： 针对铁路运维场景中混合业务流的端到端传输,提出了数字孪生架构下基于深度强化学习的确定性传输调度机制,即在线混合业务流端到端传输调度机制(End-to-End Transmission Scheduling Mechanism for Online Mixed-traffic,E2ETSM-OMT)。该机制基于差异化调度策略的思想,将业务流分为监控与数据采集流、控制与执行业务流和数据分析与业务优化流3类,通过确定性技术实现跨域端到端低时延传输。进一步地,通过模型映射和行为映射,将物理空间全方位、高精度地映射到虚拟空间,在数字孪生网络中构建混合业务的拓扑结构,预先分配数据传输路径和时隙资源,从而减少不同业务流之间的调度冲突和资源竞争。同时,通过深度强化学习(Deep Reinforcement Learning,DRL)智能体在线决策,兼顾效果与效率,对不同收益的业务流进行调度。与已有机制相比,数字孪生技术可以实现物理世界与虚拟世界的相互映射,实现非平稳通信环境下DRL的应用,避免在现实网络中探索造成的服务质量下降。仿真结果表明,所提出的面向数字孪生的确定性传输调度机制在保障成功调度混合业务流的同时,以较低的端到端整体时延实现了较高的传输收益。

关键词: 数字孪生, 确定性网络, 跨域传输, 差异化调度, 深度强化学习

Abstract: A deterministic transmission scheduling mechanism based on deep reinforcement learning under the digital twin architecture is proposed for the end-to-end transmission of mixed traffic flows in railway operation and maintenance scenarios,namely end-to-end transmission scheduling mechanism for online mixed-traffic(E2ETSM-OMT).Based on the idea of differentiated scheduling strategy,the proposed mechanism divides traffic flows into three categories:monitoring and data collection flow,control and execution traffic flow,and data analysis and business optimization flow,implementing cross domain end-to-end low latency transmission through deterministic technologies.Meanwhile,through model mapping and behavior mapping,the physical space is projected to the virtual space with high precision in all directions.In the digital twin network,after constructing the topology of mixed flows,deep reinforcement learning(DRL) agent makes pre-allocation decisions of transmission path and time slot resources,taking the effect and efficiency into account,so as to reduce scheduling conflicts and resource competition among different traffic flows.Compared with the existing mechanisms,digital twin technologies can realize the mutual mapping between the phy-sical world and the virtual world,realize the application of DRL in non-stationary communication environment,and avoid the loss of service quality caused by exploration in the real network.Simulation results show that the digital twin-oriented deterministic transmission scheduling mechanism achieves high transmission benefits with low end-to-end overall delay while ensuring successful scheduling of mixed traffic flows.

Key words: Digital twin, Deterministic network, Cross-domain transmission, Differentiated scheduling, Deep reinforcement learning

中图分类号: 

  • TP393
[1]DUAN X D,LIU P,LU L,et al.Review of Deterministic Network Technology[J].Telecommunications Science,2023,39(11):1-12.
[2]YAO J,WANG L,ZHOU Z,et al.Burst-Aware Mixed FlowScheduling in Time-Sensitive Networks for Power Business[C]//2023 IEEE 7th Information Technology and Mechatronics Engineering Conference(ITOEC).2023.
[3]TAN W,WU B.Long-distance Deterministic Transmissionamong TSN Networks:Converging CQF and DIP[J].arXiv:2111.03246,2021.
[4]CHEN C L,ZHANG Y Z,XU Q M,et al.A Time SensitiveNetwork Gating Mechanism Traffic Shaping and Routing Planning Scheduling Method:CN111740924A[P].2020-10-02[2024-02-07].https://wenku.baidu.com/view/293fd38b4ad7c1c708a1284ac850ad02df800719?fr=xueshu_top&_wkts_=1727075609594&needWelcomeRecommand=1.
[5]YANG S J,ZHUANG L,SONG Y,et al.Intelligent scheduling mechanism for time sensitive network modes in multimodal networks[J].Journal of Communications,2022,43(5):82-91.
[6]SHEN Z,WANG H,WEI M,et al.Research on Global Deterministic Direct Forwarding and Scheduling of Mixed Flow Based on Time-Sensitive Network in Substation[J].Electronics,2023,12(19):4101.
[7]LI Y H,ZHANG P,ZHOU Y C,et al.A Data ForwardingMechanism based on Deep Reinforcement Learning for Deterministic Networks[C]//IEEE Conference on Computer Communications Workshops(INFOCOM WKSHPS).Institute of Electrical and Electronics Engineers,2020:285-290.
[8]ZHANG Y,ZHANG H,LIU X,et al.Digital twin-enabled deep reinforcement learning for joint scheduling of ultra-reliable low latency communication and enhanced mobile broad band:A reliability-guaranteed approach[J].Transactions on Emerging Telecommunications Technologies,2023,34(3):e4705.
[9]WANG J X,YANG S J,ZHUANG L,et al.Multi objective online mixed traffic scheduling algorithm in time sensitive networks[J].Computer Science,2023,50(7):286-292.
[10]ZHENG J Y,AN J S.SpaceFiber Low Delay DeterministicScheduling Algorithm for Spaceborne Data Networks[J].Journal of National University of Defense Technology,2023,45(2):179-187.
[11]QIANG L,LIU B Y,YU D L,et al.Large scale deterministic network forwarding technology[J].Telecommunications Science,2019(9):8.
[12]LEGUAY J,KROLIKOWSKI J,MEDAGLIANI P,et al.Joint routing and scheduling for large-scale deterministic IP networks[J].Computer Communications,2021,165:33-42.
[13]PENG G,WANG S,HUANG Y,et al.Traffic Shaping at theEdge:Enabling Bounded Latency for Large-scale Deterministic Networks[C]//2021 IEEE International Conference on Communications Workshops(ICC Workshops).IEEE,2021.
[14]KROLIKOWSKI J,MARTIN S,MEDAGLIANI P,et al.Joint Routing and Scheduling for Large-Scale Deterministic IP Networks[J].arXiv:2004.02717,2020.
[15]WU B W,WANG S,TAN W Q.An end-to-end deterministic network transmission scheduling mechanism with cross domain decoupling[J].Journal of Beijing University of Posts and Telecommunications,2023,46(5):47-52.
[16]TAN W Q,WU B W,WANG S.Deterministic Network Cross Domain Transmission Architecture and DRL Traffic Scheduling Algorithm[J].Journal of Beijing University of Posts and Telecommunications,2023,46(3):37-42.
[17]LIU J H,SU Q,CHEN J J,et al.Research on Railway Operation and Maintenance Visualization Based on WebGL Extended Model[J].Journal of Railway Science and Engineering,2022,19(4):892-900.
[18]XU S,XU F M,ZHAO C L.Research on self optimization technology of computing power networks based on digital twins[J].ZTE Technology,2023,29(3):46-50.
[19]WU W,XU O.Digital twins and digital operations[J].Intelligent Building Electrical Technology,2023,17(3):115-119.
[20]YE X Q,WANG D,LIU Y Y,et al.Optimization of unmannedwarehouse scheduling based on digital twins and deep reinforcement learning[J].Logistics Technology,2023,42(9):97-100,121.
[21]QI B,LIU S F,LI B,et al.Optimization Algorithm for Power Demand Response Business Scheduling Based on Business Priority and SRLG[J].Grid Technology,2019,43(7):10.
[22]WANG Y F,WANG C,XU Y T,et al.Digital Twin TaskScheduling Method for Intelligent Manufacturing Unit Operations under Edge Cloud Collaboration[J].Journal of Mechanical Engineering,2024,60(6):137-152.
[23]LU Y,ZHAO G,XU C,et al.A Framework for Digital Twin-Based Deterministic Communication in Satellite Time Sensitive Networks[C]//IEEE International Conference on Communication(ICC 2023).2023:6301-6306.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发