面向工业无线确定性传输的多路径路由与调度联合优化

陈荣均; 王洪超; 王钦定; 乔凯; 田伟康; 杨冬

doi:10.12263/DZXB.20250734

您当前的位置：

首页 >

文章列表页 >

面向工业无线确定性传输的多路径路由与调度联合优化

学术论文 | 更新时间：2026-04-29

- 面向工业无线确定性传输的多路径路由与调度联合优化
- Joint Optimization of Multipath Routing and Scheduling for Industrial Wireless Deterministic Transmission
- 电子学报 2026年54卷第1期页码：68-85
- 作者机构：
  
  北京交通大学电子信息工程学院，北京 100044
- 作者简介：
  
  [ "陈荣均男，1997年9月生，湖北十堰人。现为北京交通大学博士研究生。主要研究方向为无线自组织网络、确定性网络传输技术、资源调度等。E-mail: rongjun.chen@bjtu.edu.cn" ]
  [ "王洪超男，1982年12月生，河北衡水人。现为北京交通大学电子信息工程学院副教授、硕士生导师。主要研究方向为新一代信息网络关键理论与技术、工业互联网、空天地信息网络技术等。E-mail: hcwang@bjtu.edu.cn" ]
  [ "王钦定男，1992年8月生，甘肃白银人。现为北京交通大学博士研究生。主要研究方向为未来网络体系架构、算力网络、算网融合等。中国电子学会会员编号：E190131238A。E-mail: 22110022@bjtu.edu.cn" ]
  [ "乔凯男，1997年7月生，山西吕梁人。现为北京交通大学博士研究生。主要研究方向为无线网络、资源分配、强化学习等。E-mail: kaiqiao@bjtu.edu.cn" ]
  [ "田伟康男，1999年3月生，重庆人。现为北京交通大学博士研究生。主要研究方向为未来确定性网络统一资源调度技术、异构网络人工智能优化算法等。E-mail: weikangtian@bjtu.edu.cn" ]
  [ "杨冬男，1980年12月生，山西大同人。现为北京交通大学电子信息工程学院教授、博士生导师。主要研究方向为新一代信息网络关键理论与技术以及工业互联网、网络智能化技术等。中国电子学会会员编号：E190035787M。E-mail: dyang@bjtu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62425104)
- DOI：10.12263/DZXB.20250734
  中图分类号： TN913.21;
- 收稿：2025-08-21，
  
  录用：2025-12-30，
  
  纸质出版：2026-01-25
- 稿件说明：
移动端阅览
陈荣均, 王洪超, 王钦定, 等. 面向工业无线确定性传输的多路径路由与调度联合优化[J]. 电子学报, 2026, 54(01): 68-85.

CHEN Rongjun, WANG Hongchao, WANG Qinding, et al. Joint Optimization of Multipath Routing and Scheduling for Industrial Wireless Deterministic Transmission[J]. Acta Electronica Sinica, 2026, 54(01): 68-85.
陈荣均, 王洪超, 王钦定, 等. 面向工业无线确定性传输的多路径路由与调度联合优化[J]. 电子学报, 2026, 54(01): 68-85. DOI：10.12263/DZXB.20250734

CHEN Rongjun, WANG Hongchao, WANG Qinding, et al. Joint Optimization of Multipath Routing and Scheduling for Industrial Wireless Deterministic Transmission[J]. Acta Electronica Sinica, 2026, 54(01): 68-85. DOI：10.12263/DZXB.20250734

摘要

随着工业无线网络和无线通信技术的快速发展，无线网络的确定性传输已成为一个重要的研究方向。然而，无线信道中的不确定因素，如多径衰落和同频干扰，给无线网络的确定性传输带来了诸多挑战。为了解决这些问题，Internet工程任务组（Internet Engineering Task Force，IETF）提出了可靠可用无线（Reliable and Available Wireless，RAW）架构，并在工业无线网络场景中使用时隙跳频（Time-Slotted Channel Hopping，TSCH）作为底层实现技术。为了确保可靠性和严格的时延要求，RAW设计了多种保障机制，包括通过数据包复制、消除与排序功能（Packet Replication， Elimination and Ordering Functions，PREOF）技术利用路径冗余提升传输的可靠性和确定性。然而，现有的调度方案未充分考虑PREOF以及路由和调度的联合优化，导致时频资源分配时存在冗余和资源浪费，从而影响了网络对关键流的调度能力。本文面向确定性流量传输的多路径路由与调度联合优化问题进行建模，并提出了一种基于分层强化学习的资源分配算法（Herarchical Reinforcement Resource Allocation，HRRA）。其中，高层策略负责多路径路由的选择，低层策略则基于高层策略的路由决策进行时频资源的分配，同时考虑PREOF在聚合节点对冗余包的删除。针对拓扑规模的变化和流量的异构性，在高层策略引入图神经网络（Graph Neural Network，GNN）增强对输入特征的表征能力。HRRA算法能够根据流的截止时间、可靠性等需求选择合适的动作，从而最大化调度流数量和资源利用效率。通过这种跨层优化架构和对PREOF的支持，HRRA不仅有效解决了资源冗余和调度能力不足的问题，还增强了对流的确定性通信需求的支持。实验表明，相比于DGRL+MWIS和EDF-MO等基准算法，HRRA分别提升了10.6%和36.6%的调度能力，同时实现了更高的资源利用效率。

Abstract

With the rapid development of industrial wireless networks and wireless communication technologies

deterministic transmission in wireless networks has emerged as an important research direction. However

the inherent uncertainties of wireless channels

such as multipath fading and co-channel interference

pose significant challenges to achieving deterministic transmission. To address these challenges

the internet engineering task force (IETF) proposed the reliable and available wireless (RAW) architecture

which adopts time-slotted channel hopping (TSCH) as the underlying technology in industrial wireless network scenarios. In order to ensure reliability and stringent delay requirements

RAW incorporates a variety of mechanisms

including the use of packet replication

elimination and ordering functions (PREOF) to exploit path redundancy and thereby enhance transmission reliability and determinism. Nevertheless

existing scheduling schemes have not sufficiently considered PREOF or the joint optimization of routing and scheduling. This results in redundancy and inefficient resource allocation in the time-frequency domain

limiting the network’s ability to support critical flows. In this work

we formulate the joint optimization problem of multipath routing and scheduling for deterministic flow transmission and propose a hierarchical reinforcement learning-based resource allocation algorithm

termed hierarchical reinforcement resource allocation (HRRA). In HRRA

the high-level policy is responsible for selecting multipath routes

while the low-level policy allocates time-frequency resources based on the high-level routing decisions

explicitly accounting for the elimination of redundant packets by PREOF at aggregation nodes. To address variations in topology size and heterogeneous traffic demands

a graph neural network (GNN) is integrated into the high-level policy to enhance feature representation. The HRRA algorithm selects appropriate actions according to flow requirements such as deadlines and reliability

thereby maximizing both the number of schedulable flows and overall resource utilization. Through this cross-layer optimization framework and explicit support for PREOF

HRRA not only mitigates redundancy and improves scheduling efficiency but also better supports deterministic communication requirements. Experimental results demonstrate that

compared to baseline schemes such as DGRL+MWIS and EDF-MO

HRRA improves scheduling capability by 10.6% and 36.6%

respectively

while achieving higher resource utilization.

关键词

Keywords

references

Sisinni E , Saifullah A , Han Song , et al . Industrial internet of things: Challenges, opportunities, and directions [J ] . IEEE Transactions on Industrial Informatics , 2018 , 14 ( 11 ): 4724 - 4734 .

Wang Quan , Jiang Jin . Comparative examination on architecture and protocol of industrial wireless sensor network standards [J ] . IEEE Communications Surveys & Tutorials , 2016 , 18 ( 3 ): 2197 - 2219 .

Lu Yuqian , Liu Chao , Wang K I K , et al . Digital twin-driven smart manufacturing: Connotation, reference model, applications and research issues [J ] . Robotics and Computer-Integrated Manufacturing , 2020 , 61 : 101837 .

Kotsiou V , Papadopoulos G Z , Chatzimisios P , et al . LDSF: Low-latency distributed scheduling function for industrial internet of things [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 9 ): 8688 - 8699 .

Thubert P , Papadopoulos G , Buddenberg R . Reliable and available wireless architecture/framework [D ] . [ S.l. ] : IMT Atlantique, Cisco Systems [France](Cisco) , 2020 .

Varga B , Farkas J , Malis A . RFC 9566: Deterministic networking (DetNet) packet replication, elimination, and ordering functions (PREOF) via MPLS over UDP/IP [R/OL ] . 2024-06-26 . https://datatracker.ietf.org/doc/rfc9566/ https://datatracker.ietf.org/doc/rfc9566/ .

De Armas J , Tuset P , Chang Tengfei , et al . Determinism through path diversity: Why packet replication makes sense [C ] // Proceedings of the 2016 International Conference on Intelligent Networking and Collaborative Systems . Ostrava : IEEE , 2016 : 150 - 154 .

Bernardos C J , Papadopoulos G Z , Thubert P , et al . Reliable and available wireless (RAW) use cases: RFC 9450 [S/OL ] . [ S.l. ] : IETF , 2023 .

Chang T , Vučinić M , Vilajosana X , et al . 6Ti SCH minimal scheduling function (MSF): RFC 9033 [S/OL ] . Fremont : IETF , 2021 .

Tanaka Y , Minet P , Vučinić M , et al . YSF: A 6TiSCH scheduling function minimizing latency of data gathering in IIoT [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 11 ): 8607 - 8615 .

Mozaffari Ahrar E , Nassiri M , Theoleyre F . Multipath aware scheduling for high reliability and fault tolerance in low power industrial networks [J ] . Journal of Network and Computer Applications , 2019 , 142 : 25 - 36 .

杨冬 , 程宗荣 , 田伟康 , 等 . 广义确定性标识网络 [J ] . 电子学报 , 2024 , 52 ( 1 ): 1 - 18 .

Yang Dong , Cheng Zongrong , Tian Weikang , et al . Generalized deterministic identification networks [J ] . Acta Electronica Sinica , 2024 , 52 ( 1 ): 1 - 18 . (in Chinese)

Palattella M R , Accettura N , Dohler M , et al . Traffic aware scheduling algorithm for reliable low-power multi-hop IEEE 802.15.4e networks [C ] // Proceedings of the 2012 IEEE 23rd International Symposium on Personal, Indoor and Mobile Radio Communications . Sydney : IEEE , 2012 : 327 - 332 .

Lagos Jenschke T , Koutsiamanis R A , Papadopoulos G Z , et al . ODeSe: On-demand selection for multi-path RPL networks [J ] . Ad Hoc Networks , 2021 , 114 : 102431 .

Gaitán M G , Almeida L , Santos P M , et al . EDF scheduling and minimal-overlap shortest-path routing for real-time TSCH networks [C ] // Proceedings of the second workshop on next generation real-time embedded systems (NG-RES 2021) . Budapest : Schloss Dagstuhl--Leibniz-Zentrum für Informatik , 2021 : 2 : 1 - 2 : 12 .

Wijayasekara S K , Sasithong P , Hsieh H Y , et al . Optimization of packet transmission scheduling and node parent selection for 802.15.4e Time Slotted Channel Hopping (TSCH) [J ] . ICT Express , 2024 , 10 ( 2 ): 442 - 450 .

Chen Wuhui , Qiu Xiaoyu , Cai Ting , et al . Deep reinforcement learning for internet of things: A comprehensive survey [J ] . IEEE Communications Surveys & Tutorials , 2021 , 23 ( 3 ): 1659 - 1692 .

Li Jieling , Xiao Liang , Qi Xuchen , et al . Reinforcement learning based energy-efficient fast routing for FANETs [J ] . IEEE Transactions on Communications , 2024 , 72 ( 11 ): 7063 - 7076 .

Jurado-Lasso F F , Orfanidis C , Jurado J F , et al . HRL-TSCH: A hierarchical reinforcement learning-based TSCH scheduler for IIoT [J ] . IEEE Transactions on Cognitive Communications and Networking , 2024 , 10 ( 6 ): 2102 - 2118 .

Jiang Weiwei , Han Haoyu , Zhang Yang , et al . Graph neural networks for routing optimization: Challenges and opportunities [J ] . Sustainability , 2024 , 16 ( 21 ): 9239 .

Dong Guimin , Tang Mingyue , Wang Zhiyuan , et al . Graph neural networks in IoT: A survey [J ] . ACM Transactions on Sensor Networks , 2023 , 19 ( 2 ): 1 - 50 .

Huang Ru , Guan Wenfan , Zhai Guangtao , et al . Deep graph reinforcement learning based intelligent traffic routing control for software-defined wireless sensor networks [J ] . Applied Sciences , 2022 , 12 ( 4 ): 1951 .

Zhao Zhongyuan , Verma G , Rao C , et al . Link scheduling using graph neural networks [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 6 ): 3997 - 4012 .

Kim M , Park J , Kim J . Learning collaborative policies to solve NP-hard routing problems [PP/OL ] . V1. arVix ( 2021-10-26 )[ 2025-10-10 ] . https://arXiv.org/abs/2110.13987 https://arXiv.org/abs/2110.13987 .

Kodialam M , Nandagopal T . Characterizing achievable rates in multi-hop wireless networks: The joint routing and scheduling problem [C ] // Proceedings of the 9th annual international conference on mobile computing and networking . San Diego : ACM , 2003 : 42 - 54 .

Kool W , Van Hoof H , Welling M . Attention, learn to solve routing problems! [C ] // Proceedings of the 7th International Conference on Learning Representations . New Orleans : ICLR , 2019 .

Bello I , Pham H , Le Q V , et al . Neural combinatorial optimization with reinforcement learning [C ] // Proceedings of the 5th International Conference on Learning Representations . Toulon : OpenReview.net , 2017 .

Chen Rongjun , Zhang Weiting , Wang Hongchao , et al . Enhancing energy efficiency in multipath routing for industrial Internet of Things [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 16 ): 33714 - 33730 .

De Vos A , Brighente A , Conti M . Threat sensitive networking: On the security of IEEE 802.1CB and (un)effectiveness of existing security solutions [C ] // Proceedings of the Computer Security . ESORICS 2022 international workshops . Copenhagen : Springer , 2022 : 67 - 80 .

IEEE Std 802.1 CB-2017 IEEE standard for local and metropolitan area networks—frame replication and elimination for reliability [S ] .

Yang Sijin , Zhuang Lei , Zhang Jianhui , et al . A multipolicy deep reinforcement learning approach for multiobjective joint routing and scheduling in deterministic networks [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 10 ): 17402 - 17418 .

Yang Liu , Wei Yifei , Yu F R , et al . Joint routing and scheduling optimization in time-sensitive networks using graph-convolutional-network-based deep reinforcement learning [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 23 ): 23981 - 23994 .

Schulman J , Wolski F , Dhariwal P , et al . Proximal policy optimization algorithms [PP/OL ] . V2.arVix ( 2017-08-28 )[ 2025-11-12 ] . https://arXiv.org/abs/1707.06347 https://arXiv.org/abs/1707.06347 .

Varga P , Peto J , Franko A , et al . 5G support for industrial IoT applications: Challenges, solutions, and research gaps [J ] . Sensors , 2020 , 20 ( 3 ): 828 .

Zubair Islam M , Shahzad , Ali R , et al . IoTactileSim: A virtual testbed for tactile industrial internet of things services [J ] . Sensors , 2021 , 21 ( 24 ): 8363 .

Valsesia D , Fracastoro G , Magli E . RAN-GNNs: Breaking the capacity limits of graph neural networks [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2023 , 34 ( 8 ): 4610 - 4619 .

Cai Chen , Wang Yusu . A note on over-smoothing for graph neural networks [PP/OL ] . V1.arVix ( 2020-06-23 )[ 2025-10-11 ] . https://arXiv.org/abs/2006.13318 https://arXiv.org/abs/2006.13318 .

Municio E , Daneels G , Vučinić M , et al . Simulating 6TiSCH networks [J ] . Transactions on Emerging Telecommunications Technologies , 2019 , 30 ( 3 ): e3494 .

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

融合大语言模型与跨域图结构的多模态对话情感识别方法

混合量子与图神经网络的多模态情感分析方法

面向全息通信的智算融合网络

基于图组合优化的高效社区搜索