通信学报 ›› 2022, Vol. 43 ›› Issue (5): 82-91.doi: 10.11959/j.issn.1000-436x.2022078

• 学术论文 • 上一篇    下一篇

多模态网络中时间敏感网络模态的智能调度机制

杨思锦1, 庄雷1, 宋玉1, 王家兴2, 阳鑫宇2   

  1. 1 郑州大学计算机与人工智能学院,河南 郑州 450001
    2 郑州大学网络空间安全学院,河南 郑州 450002
  • 修回日期:2022-03-23 出版日期:2022-05-25 发布日期:2022-05-01
  • 作者简介:杨思锦(1990- ),女,河南商丘人,郑州大学博士生,主要研究方向为下一代互联网、时间敏感网络、确定性网络
    庄雷(1963- ),女,河南郑州人,博士,郑州大学教授、博士生导师,主要研究方向为未来网络架构、时间敏感网络、网络虚拟化等
    宋玉(1969- ),男,河南南阳人,博士,郑州大学副教授、硕士生导师,主要研究方向为下一代互联网、人工智能、机器学习等
    王家兴(1998- ),男,河南周口人,郑州大学硕士生,主要研究方向为时间敏感网络、下一代互联网
    阳鑫宇(1998- ),男,湖南邵阳人,郑州大学硕士生,主要研究方向为确定性网络、下一代互联网
  • 基金资助:
    国家电网有限公司总部科技基金资助项目(5700-202024176A-0-0-00)

Intelligent scheduling mechanism of time-sensitive network modal in polymorphic network

Sijin YANG1, Lei ZHUANG1, Yu SONG1, Jiaxing WANG2, Xinyu YANG2   

  1. 1 School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China
    2 School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, China
  • Revised:2022-03-23 Online:2022-05-25 Published:2022-05-01
  • Supported by:
    State Grid Corporation of China Science and Technology Project(5700-202024176A-0-0-00)

摘要:

针对多模态网络中时间敏感网络模态转发调度不确定、求解时间长等问题,提出了一种基于CSQF的时间敏感网络模态的联合路由与调度机制。综合考虑有界时延需求、网络状态和不同的路由机制,建立联合缓存队列和路由的混合资源调度模型,旨在优化整个网络的资源使用。基于深度强化学习方法,利用流量特征与缓存队列利用率来预测下一循环的缓存利用率。此外,基于多队列CSQF转发调度机制和基于缓存利用率的显式路由算法,提出了一种迭代调度算法,实现了确定性转发和资源分配。仿真结果表明,所提机制可以根据网络的资源使用情况有效地调整确定性应用的传输调度,与其他离线调度机制相比,具有更好的调度性能。

关键词: 时间敏感网络, 多模态网络, 确定性网络, 联合调度, 显式路由

Abstract:

For the problems of uncertain forwarding scheduling and long solving time of time-sensitive network modal in polymorphic network, a joint routing and scheduling mechanism of time-sensitive network modal based on CSQF was proposed.Considering the requirement of bounded delay, network state and different routing mechanisms, a hybrid resource scheduling problem of joint cache queue and routing was formulated to optimize the resource usage of the entire network.Then, the traffic characteristics and cache queue utilization was used to predict the cache utilization of the next cycle, which was based on deep reinforcement learning.In addition, by using multi-queue CSQF forwarding scheduling mechanism and explicit routing algorithm based on cache utilization, an iterative scheduling algorithm was proposed to achieve deterministic forwarding and resource allocation.Simulation results show that the mechanism can effectively adjust the transmission scheduling of deterministic applications according to the resource usage of the network, and has better schedulability compared with other off-line scheduling mechanisms.

Key words: time-sensitive network, polymorphic network, deterministic networking, joint scheduling, explicit routing

中图分类号: 

No Suggested Reading articles found!