空天地融合车载网络场景下基于GAT-MADRL的缓存策略

朱思峰; 史科选; 赵伟丰; 张宗辉; 郁有建; 张青华; 朱海

doi:null

您当前的位置：

首页 >

文章列表页 >

空天地融合车载网络场景下基于GAT-MADRL的缓存策略

更新时间：2026-05-20

- 空天地融合车载网络场景下基于GAT-MADRL的缓存策略
- Caching Strategy Based on GAT-MADRL for Space-Air-Ground Integrated Vehicular Networks
- 物联网学报 2026年
- 作者机构：
  
  1.天津城建大学计算机与信息工程学院，天津 300384
  2.天津城建大学图书馆，天津 300384
  3.河南工程学院计算机学院，郑州，河南 451191
- 作者简介：
  
  赵伟丰，zhaowf@tcu.edu.cn
- 基金信息：
  
  国家自然科学基金项目(62172457);天津城建大学研究生创新项目(2025YKC077;2025YKC079);河南省科技发展计划项目(252103810011;252103810206;261111211200)
- DOI：
  中图分类号： TP929.5
- 收稿：2026-03-23，
  
  修回：2026-04-10，
  
  录用：2026-05-18，
- 稿件说明：
移动端阅览
朱思峰, 史科选, 赵伟丰, 等. 空天地融合车载网络场景下基于GAT-MADRL的缓存策略[J/OL]. 物联网学报, 2026.

ZHU Sifeng, SHI Kexuan, ZHAO Weifeng, et al. Caching Strategy Based on GAT-MADRL for Space-Air-Ground Integrated Vehicular Networks[J/OL]. Chinese Journal on Internet of Things, 2026.
朱思峰, 史科选, 赵伟丰, 等. 空天地融合车载网络场景下基于GAT-MADRL的缓存策略[J/OL]. 物联网学报, 2026. DOI：

ZHU Sifeng, SHI Kexuan, ZHAO Weifeng, et al. Caching Strategy Based on GAT-MADRL for Space-Air-Ground Integrated Vehicular Networks[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

针对空天地融合车载网络中节点异构性强、拓扑动态变化频繁以及协同缓存困难等挑战，本文构建了面向空天地融合车载网络的有向异构图模型，设计了融合图注意力网络与多智能体深度强化学习的分布式缓存决策框架，提出了一种基于图注意力网络与多智能体深度强化学习的缓存策略优化方法。实验结果表明，与随机策略、GA策略、MADQN策略、MADDPG策略相比，所提的策略在任务平均时延方面分别降低了51.61%、38.12%、26.83%、22.12%，系统总能耗分别降低了71.68%、67.53%、43.23%、24.21%，缓存命中率分别提升了261.19%、49.11%、21.43%、6.21%。

Abstract

To address the challenges of strong node heterogeneity

frequent dynamic topology changes

and difficult cache coordination in Space-Air-Ground Integrated Vehicular Network (SAGVN)

this paper constructs a directed heterogeneous graph model for SAGVNs

designs a distributed caching decision framework that integrates Graph Attention Network (GAT) and Multi-Agent Deep Reinforcement Learning (MADRL)

and proposes a caching strategy optimization method based on GAT and MADRL. Experimental results show that

compared to the Random strategy

GA strategy

MADQN strategy

and MADDPG strategy

the proposed strategy reduces the average task delay by 51.61%

38.12%

26.83%

and 22.12%

lowers the total system energy consumption by 71.68%

67.53%

43.23%

and 24.21%

and improves the cache hit rate by 261.19%

49.11%

21.43%

and 6.21%

respectively.

关键词

Keywords

references

Rajkumar Y , Santhosh Kumar S V N . A comprehensive survey on communication techniques for the realization of intelligent transportation systems in IoT based smart cities [J ] . Peer-to-Peer Networking and Applications , 2024 , 17 ( 3 ): 1263 - 1308 .

Ju Y , Gao Z , Wang H , et al . Energy-efficient cooperative secure communications in mmWave vehicular networks using deep recurrent reinforcement learning [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 , 25 ( 10 ): 14460 - 14475 .

Moghaddasi K , Rajabi S , Gharehchopogh F S . An enhanced asynchronous advantage actor-critic-based algorithm for performance optimization in mobile edge computing-enabled internet of vehicles networks [J ] . Peer-to-Peer Networking and Applications , 2024 , 17 ( 3 ): 1169 - 1189 .

张鸿 , 廖彧歆 , 王汝言 , 等 . 面向密集场景的空天地网络资源分配算法 [J ] . 电子与信息学报 , 2024 , 46 ( 5 ): 1968 - 1976 .

Zhang Hong , Liao Yuxin , Wang Ruyan , et al . Resource Allocation Algorithm for Space-Air-Ground Networks in Dense Scenarios [J ] . Journal of Electronics and Information Technology , 2024 , 46 ( 5 ): 1968 - 1976 .

牛志升 , 张钦宇 , 唐余亮 . 面向沉浸式体验的空天地一体化车联网体系架构与关键技术 [J ] . 物联网学报 , 2024 , 1 ( 2 ): 17 - 27 .

Niu Zhisheng , Zhang Qinyu , Tang Yuliang . Architecture and Key Technologies of Space-Air-Ground Integrated Vehicle Networking for Immersive Experience [J ] . Chinese Journal of Internet of Things , 2024 , 1 ( 2 ): 17 - 27 .

Liang H , Yang Z , Zhang G , et al . Resource allocation for space-air-ground integrated networks: A comprehensive review [J ] . Journal of Communications and Information Networks , 2024 , 9 ( 1 ): 1 - 23 .

Li S , Liu G , Li L , et al . A review on air-ground coordination in mobile edge computing: Key technologies, applications and future directions [J ] . Tsinghua Science and Technology , 2024 , 30 ( 3 ): 1359 - 1386 .

赵雄文 , 张钰 , 秦鹏 , 等 . 空天地一体化无线光通信网络关键技术及其发展趋势 [J ] . 电子学报 , 2022 , 50 ( 1 ): 1 - 17 .

Zhao Xiongwen , Zhang Yu , Qin Peng , et al . Key Technologies and Development Trends of Space-Air-Ground Integrated Wireless Optical Communication Networks [J ] . Acta Electronica Sinica , 2022 , 50 ( 1 ): 1 - 17 .

张宗辉 , 秦祥宇 , 朱思峰 , 等 . 基于MADRL的海上物联网任务卸载优化方案 [J ] . 物联网学报 , 1 - 19 .

Zhang Zonghui , Qin Xiangyu , Zhu Sifeng , et al . MADRL-Based Task Offloading Optimization Scheme for Maritime Internet of Things [J ] . Chinese Journal on Internet of Things , 1 - 19 .

Gang Y , Zhang Y , Zhuo Z . Joint task offloading and resource allocation strategy for space-air-ground integrated vehicular networks [J ] . Tsinghua Science and Technology , 2024 , 30 ( 3 ): 1027 - 1043 .

徐煜凯 , 徐波 , 张凌豪 , 等 . 基于图学习的空天地一体化网络合作推理方法研究 [J ] . 物联网学报 , 1 - 17 .

Xu Yukai , Xu Bo , Zhang Linghao , et al . Research on Cooperative Inference Method of Space-Air-Ground Integrated Network Based on Graph Learning [J ] . Chinese Journal on Internet of Things , 1 - 17 .

Qi X , Chong J , Zhang Q , et al . Toward cooperatively caching in multi-UAV-assisted network: A queue-aware CDS-based reinforcement learning mechanism with energy-efficiency maximization [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 9 ): 16461 - 16477 .

Wu C , Xu Z , He X , et al . Proactive caching with distributed deep reinforcement learning in 6g cloud-edge collaboration computing [J ] . IEEE Transactions on Parallel and Distributed Systems , 2024 , 35 ( 8 ): 1387 - 1399 .

LI Y L , CHAI Z Y , TAN F , et al . Temporal Data Scheduling in Internet of Vehicles Using an Improved Decomposition Based Multi-Objective Evolutionary Algorithm [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 5 ): 5282 - 5295 .

周旭 , 李泰新 , 覃毅芳 , 等 . 基于边缘智能协同的天地一体化信息网络研究 [J ] . 电信科学 , 2024 , 36 ( 7 ): 71 - 79 .

Zhou Xu , Li Taixin , Qin Yifang , et al . Research on Space-Ground Integrated Information Network Based on Edge Intelligence Collaboration [J ] . Telecommunications Science , 2024 , 36 ( 7 ): 71 - 79 .

Ji S , Zhou D , Sheng M , et al . Dynamic space-ground integrated mobility management strategy for mega LEO satellite constellations [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 9 ): 11043 - 11060 .

Dai M , Huang N , Wu Y , et al . Unmanned-aerial-vehicle-assisted wireless networks: Advancements, challenges, and solutions [J ] . IEEE Internet of Things Journal , 2022 , 10 ( 5 ): 4117 - 4147 .

吴红海 , 王白冰 , 马华红 , 等 . 移动车载边缘网络中基于递归深度强化学习的协作缓存接力算法 [J ] . 通信学报 , 2024 , 45 ( 11 ): 277 - 286 .

Wu Honghai , Wang Baibing , Ma Huahong , et al . Cooperative Caching Relay Algorithm Based on Recursive Deep Reinforcement Learning in Mobile Vehicular Edge Networks [J ] . Journal on Communications , 2024 , 45 ( 11 ): 277 - 286 .

Jin Z , Song T , Jia W K . An adaptive cooperative caching strategy for vehicular networks [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 10 ): 9502 - 9517 .

Chen G , Duan W , Sun J , et al . Social-aware assisted edge collaborative caching based on deep reinforcement learning joint with digital twin network in Internet of Vehicles [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 , 25 ( 10 ): 14785 - 14802 .

Yoo S , Jeong S , Kim J , et al . Cache-assisted mobile-edge computing over space–air–ground integrated net-works for extended reality applications [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 10 ): 18306 - 18319 .

Yin F , Liu Q , Liu D , et al . Joint coded caching and resource allocation for multimedia service in space-air-ground integrated networks [J ] . IEEE Transactions on Communications , 2024 , 72 ( 11 ): 6839 - 6853 .

Zhang P , Li Y , Kumar N , et al . Distributed deep reinforcement learning assisted resource allocation algorithm for space-air-ground integrated networks [J ] . IEEE Transactions on Network and Service Management , 2022 , 20 ( 3 ): 3348 - 3358 .

Y. Ran , Y. Ding , S. Chen , et al . Fully-Distributed Dynamic Packet Routing for LEO Satellite Networks: A GNN-Enhanced Multi-Agent Reinforcement Learning Approach [J ] , IEEE Transactions on Vehicular Technology , 2025 , 74 ( 3 ): 5229 - 5234 .

Wang P , Zhang J , Zhang X , et al . Convergence of satellite and terrestrial networks: A comprehensive survey [J ] . IEEE Access , 2019 , 8 : 5550 - 5588 .

D. Li , H. Zhang , H. Ding , et al ., User-Preference-Learning-Based Proactive Edge Caching for D2D-Assisted Wireless Networks [J ] , IEEE Internet of Things Journal , 2023 , 10 ( 13 ): 11922 - 11937 .

He X , Lu H , Du M , et al . QoE-based task offloading with deep reinforcement learning in edge-enabled Internet of Vehicles [J ] . IEEE Transactions on Intelligent Transportation Systems , 2020 , 22 ( 4 ): 2252 - 2261 .

Wei R , Qin T , Huang J , et al . Resource allocation scheduling scheme for task migration and offloading in 6G Cybertwin internet of vehicles based on DRL [J ] . IET Communications , 2024 , 18 ( 18 ): 1244 - 1265 .

Aishwarya R , Vetriselvi V , Meignanamoorthi D . A Review on Computational Optimization Strategies and Collaborative Techniques of Vehicular Task Offloading in the Era of Internet of Vehicles and 6G [J ] . Edge of Intelligence: Exploring the Frontiers of AI at the Edge , 2025 : 1 - 49 .

Ji Y , Wang Y , Zhao H , et al . Multi-agent reinforcement learning resources allocation method using dueling double deep Q-network in vehicular networks [J ] . IEEE Transactions on Vehicular Technology , 2023 , 72 ( 10 ): 13447 - 13460 .

Moghaddasi K , Rajabi S , Gharehchopogh F S . Multi-objective secure task offloading strategy for block-chain-enabled IoV-MEC systems: a double deep Q-network approach [J ] . IEEE Access , 2024 , 12 : 3437 - 3463 .

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

星地协同中基于多智能体的时敏任务调度优化策略

基于变分自编码器的时间序列生成及异常检测模型研究

面向非可信节点的联合频谱感知与资源分配机制设计

车联网中联邦学习模型低时延传输迁移方法研究

意图驱动的物联网双时间尺度资源分配方法