面向工业智能体互联网的通信-控制协同原子化重构机制

陈乐; 马彰超; 董芃; 张荣辉; 牛子儒; 王健全

doi:null

您当前的位置：

首页 >

文章列表页 >

面向工业智能体互联网的通信-控制协同原子化重构机制

更新时间：2026-02-26

- 面向工业智能体互联网的通信-控制协同原子化重构机制
- Communication-control collaborative atomic reconfiguration mechanism for Industrial Internet of Agents
- 通信学报 2026年
- 作者机构：
  
  北京科技大学自动化学院，北京 100083
- 作者简介：
  
  [ "陈乐（2000- ），男，广西贵港人，北京科技大学博士生，主要研究方向为工业互联网、网络化控制系统。" ]
  [ "马彰超（1984- ），男，山西晋城人，博士，北京科技大学副教授、硕士生导师，主要研究方向网算控一体化的智能开放工业控制系统。" ]
  [ "董芃（1998- ），男，天津人，北京科技大学博士生，主要研究方向为工业互联网、信息物理系统。" ]
  [ "张荣辉（1987- ），男，河南驻马店人，博士，北京科技大学副教授、硕士生导师，主要研究方向为通信感知计算控制一体化。" ]
  [ "牛子儒（2002- ），男，内蒙古通辽人，北京科技大学硕士生，主要研究方向为工业互联网、任务编排。" ]
  [ "王健全（1974- ），男，山西平遥人，博士，北京科技大学教授、博士生导师，主要研究方向为工业泛在网络、工业互联网、工业互联网安全、网络协同与智能制造等。" ]
- 基金信息：
  
  国家自然科学基金联合基金资助项目(U25A20433);国家自然科学基金资助项目(62471069);山西省重大专项(202301020101001)
- DOI：
  中图分类号： TP2;TN91
- 收稿：2025-12-24，
  
  修回：2026-02-14，
  
  录用：2026-02-26，
- 稿件说明：
移动端阅览
陈乐, 马彰超, 董芃, 等. 面向工业智能体互联网的通信-控制协同原子化重构机制[J/OL]. 通信学报, 2026.

CHEN Le, MA Zhangchao, DONG Peng, et al. Communication-control collaborative atomic reconfiguration mechanism for Industrial Internet of Agents[J/OL]. Journal on Communications, 2026.
陈乐, 马彰超, 董芃, 等. 面向工业智能体互联网的通信-控制协同原子化重构机制[J/OL]. 通信学报, 2026. DOI：

CHEN Le, MA Zhangchao, DONG Peng, et al. Communication-control collaborative atomic reconfiguration mechanism for Industrial Internet of Agents[J/OL]. Journal on Communications, 2026. DOI：

摘要

针对工业智能体互联网（Internet of Agents

IoA）中智能体间的协同关系与通信拓扑难以根据高层意图进行动态、原子化调整的挑战，本文提出一种支持“通信-控制”协同原子化重构的意图驱动协同控制架构。首先，提出一个“协同状态”的形式化模型，该模型将智能体内部的控制逻辑与其外部的通信拓扑统一封装为一个可动态演化的整体。其次，针对“协同状态”转移过程中严苛的原子性、实时性与连续性工业约束，设计了一种基于双缓冲的原子化协同状态转移（Atomic Collaborative-State Transition

ACST）机制。该机制通过后台重构与原子化切换相结合，实现了智能体内部行为与外部网络连接的微秒级、无中断同步演化。特别地，在通信适配层面，该架构在控制器内构建了支持动态增删的协议驱动与数据缓存池，并通过“增量预热、存量延后”的资源清理策略，保障了多协议网络拓扑重构过程中的数据一致性与时序确定性。物理平台实验结果表明，所提架构根据视觉传感器触发的协同意图，通过ACST机制在极短延迟（< 17.4µs）内原子化地完成协同状态的切换，最终实现了高精度（同步误差 < 4.1ms）的动态协同分拣任务，证明了该架构在按需构建高保真智能体协同网络方面的卓越性能。

Abstract

To address the challenge of dynamically and atomically adjusting the cooperative relationship and communication topology among agents in the Internet of Agents (IoA) based on high-level intentions

this paper proposes an intention-driven collaborative control architecture that supports the atomic reconfiguration of "communication-control" collaboration. Firstly

a formal model of "cooperative state" is proposed

which encapsulates the control logic within agents and their external communication topology as a dynamically evolvable whole. Secondly

to meet the strict atomicity

real-time

and continuity industrial constraints during the "cooperative state" transition

an atomic cooperative state transition (ACST) mechanism based on double buffering is designed. This mechanism combines background reconfiguration with atomic switching to achieve microsecond-level

interruption-free synchronous evolution of the internal behavior of agents and their external network connections. Particularly

at the communication adaptation level

the architecture builds a protocol-driven and data cache pool within the controller that supports dynamic addition and deletion

and through an "incremental preheating

incremental delay" resource cleaning strategy

it ensures data consistency and timing determinacy during the multi-protocol network topology reconfiguration process. Physical platform experimental results show that the proposed architecture atomically switches the cooperative state within an extremely short delay (< 17.4µs) based on the cooperative intention triggered by visual sensors

and ultimately achieves a high-precision (synchronization error < 4.1ms) dynamic cooperative sorting task

demonstrating the outstanding performance of this architecture in on-demand construction of high-fidelity agent cooperative networks.

关键词

Keywords

references

Didden J B H C , Dang Q V , Adan I J B F . Decentralized learning multi-agent system for online machine shop scheduling problem [J ] . Journal of Manufacturing Systems , 2023 , 67 : 338 - 360 .

张平 , 刘会永 , 李文璟 , 等 . 工业智能网——工业互联网的深化与升级 [J ] . 通信学报 , 2018 , 39 ( 12 ): 134 - 140 .

胡玉姣 , 黄韬 , 贾庆民 , 等 . 通算存智一体协同的未来网络模型 [J ] . 通信学报 , 2024 , 45 ( 05 ): 12 - 28 .

Xu W , Gu J , Zhang W , et al . Multi-agent reinforcement learning for flexible shop scheduling problem: a survey [J ] . Frontiers in Industrial Engineering , 2025 , 3 : 1611512 .

Sasiain J , Franco D , Atutxa A , et al . Toward the integration and convergence between 5G and tsn technologies and architectures for industrial communications: a survey [J ] . IEEE Communications Surveys & Tutorials , 2024 , 27 ( 1 ): 259 - 321 .

Höse K , Amaral A , Götze U , et al . Manufacturing flexibility through industry 4.0 technological concepts—impact and assessment [J ] . Global Journal of Flexible Systems Management , 2023 , 24 ( 2 ): 271 - 289 .

Liu L , Xu Z , Qu X . A reconfigurable architecture for industrial control systems: Overview and challenges [J ] . Machines , 2024 , 12 ( 11 ): 793 .

Zeydan E , Mangues J , Arslan S S , et al . Reconfigurable Production Lines for Industrial 5.0 Automation: An Intent-based Approach [J ] . IEEE Open Journal of the Computer Society , 2025 , 6 : 1341 - 1352 .

杨静雅 , 唐晓刚 , 周一青 , 等 . 意图抽象与知识联合驱动的6G内生智能网络架构 [J ] . 通信学报 , 2023 , 44 ( 02 ): 12 - 26 .

张汝云 , 肖戈扬 , 单麒赫 , 等 . 多模态网络下多智能体协同控制的通信拓扑重构方法 [J ] . 通信学报 , 2022 , 43 ( 04 ): 50 - 59 .

Leivadeas A , Falkner M . A survey on intent-based networking [J ] . IEEE Communications Surveys & Tutorials , 2022 , 25 ( 1 ): 625 - 655 .

Mehmood K , Kralevska K , Palma D . Intent-driven autonomous network and service management in future cellular networks: A structured literature review [J ] . Computer Networks , 2023 , 220 : 109477 .

Filinis N , Tzanettis I , Spatharakis D , et al . Intent-driven orchestration of serverless applications in the computing continuum [J ] . Future Generation Computer Systems , 2024 , 154 : 72 - 86 .

王义涛 , 王俊森 , 石章松 , 等 . 基于改进快速搜索树和合同网的多智能体目标分配算法 [J ] . 兵工学报 , 2025 , 46 ( 05 ): 29 - 40 .

Liu Y , Xia Z , Gui W . Multiobjective distributed optimization via a predefined-time multiagent approach [J ] . IEEE Transactions on Automatic Control , 2023 , 68 ( 11 ): 6998 - 7005 .

Chang H , Liu Y , Sheng Z . Distributed multi-agent reinforcement learning for collaborative path planning and scheduling in blockchain-based cognitive internet of vehicles [J ] . IEEE Transactions on Vehicular Technology , 2023 , 73 ( 5 ): 6301 - 6317 .

Strasser T , Zoitl A , Christensen J H , et al . Design and execution issues in IEC 61499 distributed automation and control systems [J ] . IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) , 2010 , 41 ( 1 ): 41 - 51 .

Lyu G , Brennan R W . Towards IEC 61499-based distributed intelligent automation: A literature review [J ] . IEEE Transactions on Industrial Informatics , 2020 , 17 ( 4 ): 2295 - 2306 .

Faqrizal I , Salaün G , Falcone Y . Adaptive Industrial Control Systems via IEC 61499 and Runtime Enforcement [J ] . ACM Transactions on Autonomous and Adaptive Systems , 2024 , 19 ( 4 ): 1 - 31 .

Prenzel L , Zoitl A , Provost J . IEC 61499 runtime environments: A state of the art comparison [C ] // International Conference on Computer Aided Systems Theory . Cham : Springer International Publishing , 2019 : 453 - 460 .

Martini B , Gharbaoui M , Castoldi P . Intent-based network slicing for SDN vertical services with assurance: Context, design and preliminary experiments [J ] . Future Generation Computer Systems , 2023 , 142 : 101 - 116 .

Chowdhury M . Accelerator: An intent-based intelligent resource-slicing scheme for SFC-based 6G application execution over SDN-and NFV-empowered zero-touch network [J ] . Frontiers in Communications and Networks , 2024 , 5 : 1385656 .

Barzegar S , Ruiz M , Velasco L . Autonomous flow routing for near real-time quality of service assurance [J ] . IEEE Transactions on Network and Service Management , 2023 , 21 ( 2 ): 2504 - 2514 .

Filinis N , Tzanettis I , Spatharakis D , et al . Intent-driven orchestration of serverless applications in the computing continuum [J ] . Future Generation Computer Systems , 2024 , 154 : 72 - 86 .

Ning Z , Xie L . A survey on multi-agent reinforcement learning and its application [J ] . Journal of Automation and Intelligence , 2024 , 3 ( 2 ): 73 - 91 .

Li Y , Liu Q , Li X , et al . Manufacturing resource-based self-organizing scheduling using multi-agent system and deep reinforcement learning [J ] . Journal of Manufacturing Systems , 2025 , 79 : 179 - 198 .

Straub J . A modern Blackboard Architecture implementation with external command execution capability [J ] . Software Impacts , 2022 , 11 : 100183 .

Mason F , Chiariotti F , Zanella A , et al . Multi-agent reinforcement learning for coordinating communication and control [J ] . IEEE Transactions on Cognitive Communications and Networking , 2024 , 10 ( 4 ): 1566 - 1581 .

Gielis J , Shankar A , Prorok A . A critical review of communications in multi-robot systems [J ] . Current robotics reports , 2022 , 3 ( 4 ): 213 - 225 .

Zhu C , Dastani M , Wang S . A survey of multi-agent deep reinforcement learning with communication [J ] . Autonomous Agents and Multi-Agent Systems , 2024 , 38 ( 1 ): 4 .

Tan C , Dong X , Li Y , et al . Leader–following consensus problem of networked multi‐agent systems under switching topologies and communication constraints [J ] . IET Control Theory & Applications , 2020 , 14 ( 20 ): 3686 - 3696 .

Dai W , Vyatkin V , Christensen J H , et al . Bridging service-oriented architecture and IEC 61499 for flexibility and interoperability [J ] . IEEE Transactions on Industrial Informatics , 2015 , 11 ( 3 ): 771 - 781 .

Lepuschitz W , Zoitl A , Vallée M , et al . Toward self-reconfiguration of manufacturing systems using automation agents [J ] . IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) , 2010 , 41 ( 1 ): 52 - 69 .

Seitz M , Gehlhoff F , Cruz Salazar L A , et al . Automation platform independent multi-agent system for robust networks of production resources in industry 4.0 [J ] . Journal of Intelligent Manufacturing , 2021 , 32 ( 7 ): 2023 - 2041 .

Ahrens E , Bozga M , Iosif R , et al . Reasoning about distributed reconfigurable systems [J ] . Proceedings of the ACM on Programming Languages , 2022 , 6 (OOPSLA 2 ): 145 - 174 .

Li J , Xiong H , Li Q , et al . Run-time reconfiguration strategy and implementation of time-triggered networks [J ] . Electronics , 2022 , 11 ( 9 ): 1477 .

Gundall M , Stegmann J , Reichardt M , et al . Downtime optimized live migration of industrial real-time control services [C ] // 2022 IEEE 31st International Symposium on Industrial Electronics (ISIE) . IEEE , 2022 : 253 - 260 .

Prenzel L , Hofmann S , Steinhorst S . Real-time dynamic reconfiguration for IEC 61499 [C ] // 2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS) . IEEE , 2022 : 1 - 6 .

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

暂无数据