Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration

Chen Juan; Zhong Jie; Wu Zongling; Tian Di; Chen Yujie

doi:10.11959/j.issn.2096-3750.2026.00507

您当前的位置：

首页 >

文章列表页 >

Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration

Theory and Technology | 更新时间：2026-04-16

- Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration
- Chinese Journal on Internet of Things Vol. 10, Issue 1, Pages: 189-201(2026)
- 作者机构：
  
  1.西华大学计算机与软件工程学院，四川成都 610039
  2.云南财经大学云南省服务计算重点实验室，云南昆明 650221
  3.西南交通大学信息科学与技术学院，四川成都 611756
- 作者简介：
- 基金信息：
  
  The Project of Sichuan Network Culture Research Center(WLWHZX-09);the Open Project of Key Laboratory Service Science and Innovation of Sichuan Province(KL2411);the Foundation of Yunnan Key Laboratory of Service Computing(YNSC24118)
- DOI：10.11959/j.issn.2096-3750.2026.00507
  CLC： TP393.08
- Received：16 April 2025，
  
  Revised：2025-06-22，
  
  Accepted：18 July 2025，
  
  Published：30 March 2026
- 稿件说明：
移动端阅览
陈娟,钟杰,吴宗玲等.星地协同中基于多智能体的时敏任务调度优化策略[J].物联网学报,2026,10(01):189-201.

Chen Juan,Zhong Jie,Wu Zongling,et al.Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration[J].Chinese Journal on Internet of Things,2026,10(01):189-201.
陈娟,钟杰,吴宗玲等.星地协同中基于多智能体的时敏任务调度优化策略[J].物联网学报,2026,10(01):189-201. DOI： 10.11959/j.issn.2096-3750.2026.00507.

Chen Juan,Zhong Jie,Wu Zongling,et al.Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration[J].Chinese Journal on Internet of Things,2026,10(01):189-201. DOI： 10.11959/j.issn.2096-3750.2026.00507.

摘要

随着智能物联技术与5G/6G通信技术的深度融合，卫星边缘计算（SatEC

satellite edge computing）凭借空天协同计算网络，为地面网络覆盖薄弱区域提供了新型算力服务。然而，SatEC系统面临星地动态资源分配失衡与多维时空约束下任务优先级控制不足的双重挑战。现有方法在分层决策、时空特征提取及任务紧急度量化映射方面存在缺陷，导致时敏任务处理效率受限。为此，提出了一种基于自注意力时间卷积网络的多智能体深度强化学习算法。该算法通过构建多智能体架构实现任务优先级排序与资源分配的联合优化，采用融合时空特征的混合神经网络精准提取星地协同场景的动态关联特性，并建立基于概率模型的动态调度机制，协同优化时延约束与任务完成率。仿真结果表明，相较于基准算法，该算法在任务完成率与时延控制方面均实现了显著的提升，验证了其在复杂卫星边缘计算场景中的有效性与优越性。

Abstract

With the deep integration of intelligent Internet of things technology and 5G/6G communication technology

satellite edge computing (SatEC) offers new computational services to areas with weak terrestrial network coverage through its aerospace collaborative computing network. However

the SatEC system faces dual challenges of unbalanced dynamic resource allocation between satellite and ground and insufficient task priority control under multi-dimensional spatiotemporal constraints. Existing methods have defects in hierarchical decision-making

spatiotemporal feature extraction

and task urgency quantification mapping

which limit the efficiency of time-sensitive task processing. To address this problem

a multi-agent deep reinforcement learning algorithm based on self-attention temporal convolutional networks was proposed in this paper. The algorithm achieved joint optimization of task prioritization and resource allocation by constructing a multi-agent architecture

employed a hybrid neural network integrating spatiotemporal features to accurately extract dynamic correlation characteristics of satellite-ground collaboration scenarios

and established a dynamic scheduling mechanism based on a probabilistic model to synergistically optimize latency constraints and task completion rates. Simulation results show that

compared with the baseline algorithm

the proposed algorithm achieves significant improvements in both task completion rate and delay control

demonstrating its effectiveness and superiority in complex satellite edge computing scenarios.

关键词

Keywords

references

Chen H L , Wen Y Q , Huang Y M , et al . Edge computing enabling Internet of ships: a survey on architectures, emerging applications, and challenges [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 2 ): 1509 - 1528 .

Li D B , Sun Y C , Peng J L , et al . Dual network computation offloading based on DRL for satellite-terrestrial integrated networks [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 3 ): 2270 - 2284 .

Zhou J , Zhao Y C , Zhao L , et al . Adaptive task offloading with spatiotemporal load awareness in satellite edge computing [J ] . IEEE Transactions on Network Science and Engineering , 2024 , 11 ( 6 ): 5311 - 5322 .

Zuo Y , Yue M Y , Yang H Y , et al . Integrating communication, sensing and computing in satellite Internet of things: challenges and opportunities [J ] . IEEE Wireless Communications , 2024 , 31 ( 3 ): 332 - 338 .

Zhang C Z , Yang J . An energy-efficient collaborative offloading scheme with heterogeneous tasks for satellite edge computing [J ] . IEEE Transactions on Network Science and Engineering , 2024 , 11 ( 6 ): 6396 - 6407 .

Chen Y , Hu J , Zhao J , et al . Qos-aware computation offloading in LEO satellite edge computing for IoT: a game-theoretical approach [J ] . Chinese Journal of Electronics , 2024 , 33 ( 4 ): 875 - 885 .

Liu L , Mao W P , Li W W , et al . Edge computing offloading strategy for space-air-ground integrated network based on game theory [J ] . Computer Networks , 2024 , 243 : 110331 .

Li J , Shi Y , Dai C , et al . A learning-based stochastic game for energy efficient optimization of UAV trajectory and task offloading in space/aerial edge computing [J ] . IEEE Transactions on Vehicular Technology , 2025 , 74 ( 6 ): 9717 - 9733 .

Xi S Y , Shang B D , Zhang H X , et al . Energy optimization in multisatellite-enabled edge computing systems [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 12 ): 21715 - 21726 .

Sun J C , Chen X , Jiang C X , et al . Distributionally robust optimization of on-orbit resource scheduling for remote sensing in space-air-ground integrated 6G networks [J ] . IEEE Journal on Selected Areas in Communications , 2025 , 43 ( 1 ): 382 - 395 .

Zhou J , Yang Q , Zhao L , et al . Mobility-aware computation offloading in satellite edge computing networks [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 10 ): 9135 - 9149 .

Shuai J Q , Cui H X , He Y J , et al . Dynamic satellite edge computing offloading algorithm based on distributed deep learning [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 16 ): 27790 - 27802 .

Liu Z G , Dong X Q , Wang L , et al . Satellite network task deployment method based on SDN and ICN [J ] . Sensors , 2022 , 22 ( 14 ): 5493 .

Zhang Z Y , Dong T , Yin J , et al . A particle swarm optimization-based queue scheduling and optimization mechanism for large-scale low-earth-orbit satellite communication networks [J ] . Sensors , 2025 , 25 ( 4 ): 1069 .

Zhuo M , Feng Y M , Yang P , et al . Optimizing topology in satellite-UAV collaborative IoT: a graph partitioning simulated annealing approach [J ] . Drones , 2024 , 8 ( 2 ): 44 .

Zhang S , Cai T Z , Wu D , et al . IoRT data collection with LEO satellite-assisted and cache-enabled UAV: a deep reinforcement learning approach [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 4 ): 5872 - 5884 .

Waqar N , Ali Hassan S , Mahmood A , et al . Computation offloading and resource allocation in MEC-enabled integrated aerial-terrestrial vehicular networks: a reinforcement learning approach [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 11 ): 21478 - 21491 .

Yang W T , Liu Z B , Liu X W , et al . Deep reinforcement learning-based low-latency task offloading for mobile-edge computing networks [J ] . Applied Soft Computing , 2024 , 166 : 112164 .

Sun Y , He Q J . Joint task offloading and resource allocation for multi-user and multi-server MEC networks: a deep reinforcement learning approach with multi-branch architecture [J ] . Engineering Applications of Artificial Intelligence , 2023 , 126 : 106790 .

Chai F R , Zhang Q , Yao H P , et al . Joint multi-task offloading and resource allocation for mobile edge computing systems in satellite IoT [J ] . IEEE Transactions on Vehicular Technology , 2023 , 72 ( 6 ): 7783 - 7795 .

Zhang H Y , Liu R K , Kaushik A , et al . Satellite edge computing with collaborative computation offloading: an intelligent deep deterministic policy gradient approach [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 10 ): 9092 - 9107 .

Cai H N , Yang X M , Wu H N , et al . Freshness-aware task offloading and resource scheduling for satellite edge computing [C ] // Proceedings of the 2024 IEEE Wireless Communications and Networking Conference (WCNC) . Piscataway : IEEE Press , 2024 : 1 - 6 .

Shannon C E . A mathematical theory of communication [J ] . Bell System Technical Journal , 1948 , 27 ( 3 ): 379 - 423 .

Song Z Y , Hao Y Y , Liu Y W , et al . Energy-efficient multiaccess edge computing for terrestrial-satellite Internet of things [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 18 ): 14202 - 14218 .

Cheng L , Feng G , Sun Y , et al . Energy-constrained satellite edge computing for satellite-terrestrial integrated networks [J ] . IEEE Transactions on Vehicular Technology , 2025 , 74 ( 2 ): 3359 - 3374 .

Lyu T , Xu Y Q , Liu F F , et al . Task offloading and resource allocation for satellite-terrestrial integrated networks [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 1 ): 262 - 275 .

Qu Y B , Zhang T T , Feng Y , et al . Computation offloading and resource allocation for E2E tasks in satellite edge computing networks [J ] . Space: Science & Technology , 2024 , 4 : 144 .

Xiong J Y , Guo P , Wang Y , et al . Multi-agent deep reinforcement learning for task offloading in group distributed manufacturing systems [J ] . Engineering Applications of Artificial Intelligence , 2023 , 118 : 105710 .

Mienye I D , Swart T G , Obaido G . Recurrent neural networks: a comprehensive review of architectures, variants, and applications [J ] . Information , 2024 , 15 ( 9 ): 517 .

Vaswani A , Shazeer N , Parmar N , et al . Attention is all you need [J ] . Advances in Neural Information Processing Systems , 2017 , 30 : 5998 - 6008 .

Bai S , Kolter J Z , Koltun V . An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [PP ] . arXiv preprint , 2018 , arxiv: 1803.01271 .

Vinyals O , Fortunato M , Jaitly N . Pointer networks [C ] // Proceedings of the Advances in Neural Information Processing Systems 28 (NIPS 2015) . Montreal, Canada : Curran Associates, Inc. , 2015 : 2692 - 2700 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intent-driven dual-time-scale resource allocation approach for Internet of things

Joint spectrum sensing and resource allocation mechanism with untrusted sensing nodes

Related Author

Chen Juan

Zhong Jie

Tian Di

Chen Yujie

Song Hang

Cai Jian

Yuan Yundong

Zhang Yu

Related Institution

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

SINO-PIPELINE International Company

School of Cyber Science and Engineering, Xi′an Jiaotong University, Xi′an

School of Information and Communication Engineering, Xi′an Jiaotong University, Xi′an

College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics

⁰