面向卫星车载MEC网络的协同计算卸载方法

doi:10.19678/j.issn.1000-3428.0069784

摘要/Abstract

摘要：

车联网(IoV)环境中任务的动态性提高了实时计算卸载的复杂性。针对IoV场景中地面网络覆盖受限导致的实时任务难以及时完成的问题，提出一种面向卫星车载移动边缘计算网络(SVMECN)的协同计算卸载方法。首先，构建卫星与地面间的几何关系模型，计算设备与卫星、地面网关与卫星之间的传输速率，并基于该模型计算任务处理时延，模型充分考虑任务的实时性，动态调整卫星移动对地面数据传输的影响，通过卫星与地面网关的协作处理来满足车载应用对时延的要求；其次，提出一种基于指针注意力机制和Actor-Critic(ST-PART)的协同计算卸载算法，根据任务的实时性动态调整任务优先级，按照优先级顺序对任务进行计算卸载，并在不同计算节点之间动态选择和协同处理任务，以最小化任务处理时延。在SVMECN中对所提算法进行仿真，结果显示，与传统的启发式算法相比，所提算法在提高运行效率方面表现突出。实验和分析结果表明，所提算法在满足任务实时性需求的同时能够显著降低任务处理时延，与地面和卫星未协同的算法相比，该算法能够降低2.35%~68.68%的时延成本。

关键词: 星地协同网络, 移动边缘计算, 指针注意力, 强化学习, 计算卸载

Abstract:

The dynamic nature of tasks in Internet of Vehicles (IoV) environments increases the complexity of real-time computational offloading. To address the difficulty of completing real-time tasks in a timely manner owing to limited terrestrial network coverage in IoV scenarios, this study proposes a collaborative computational offloading approach for Satellite Vehicular Mobile Edge Computing Networks (SVMECN). First, a geometric relationship model between satellites and the ground is constructed to calculate the transmission rates between devices and satellites, as well as between terrestrial gateways and satellites. The task processing delay is computed based on this model. The model fully considers the real-time nature of tasks and dynamically adjusts for the impact of satellite movement on terrestrial data transmission. Through collaborative processing between satellites and terrestrial gateways, the latency requirements of in-vehicle applications are met. Second, the study proposes a collaborative computational offloading algorithm based on Pointer Attention Mechanism and Actor-Critic (ST-PART). This algorithm dynamically adjusts task priorities according to their real-time nature, offloads tasks for computation in order of priority, and dynamically selects and collaboratively processes tasks among different computing nodes to minimize task processing delays. The proposed algorithm is simulated in an SVMECN environment. Compared with traditional heuristic algorithms, the proposed algorithm improves operational efficiency. Experimental and analytical results indicate that the proposed algorithm can significantly reduce task processing delays while meeting the real-time requirements of tasks. Compared with algorithms without collaboration between terrestrial and satellite components, the proposed algorithm can reduce latency costs by 2.35%-68.68%.

Key words: collaborative satellite-terrestrial network, Mobile Edge Computing (MEC), pointer attention, Reinforcement Learning (RL), computation offloading

赵季红, 臧若雨, 刘振. 面向卫星车载MEC网络的协同计算卸载方法[J]. 计算机工程, 2025, 51(9): 49-58.

ZHAO Jihong, ZANG Ruoyu, LIU Zhen. Collaborative Computation Offloading Method for Satellite Vehicle-Mounted Mobile Edge Computing Networks[J]. Computer Engineering, 2025, 51(9): 49-58.

https://www.ecice06.com/CN/Y2025/V51/I9/49

图/表 13

图1 卫星车载MEC网络的系统场景

Fig.1 System scenario of satellite vehicle-mounted MEC network

图2 单颗卫星对地覆盖的几何关系

Fig.2 Geometric relation of ground coverage of a single satellite

图3 MDP动作选择过程

Fig.3 MDP action selection procedure

图4 代理的结构

Fig.4 Structure of agency

图5 不同任务数量下的卸载时间

Fig.5 Unloading time under different task quantities

图6 不同任务数据大小下的卸载时间

Fig.6 Unloading time under different task data sizes

图7 不同卫星并行计算任务数量下的卸载时间

Fig.7 Unloading time under different numbers of satellite parallel computing tasks

图8 MHA的消融实验结果

Fig.8 Ablation experiment results of MHA

参考文献 24

1	WANG S G, LI Q, XU M W, et al. Tiansuan constellation: an open research platform[C]//Proceedings of the IEEE International Conference on Edge Computing (EDGE). Washington D.C., USA: IEEE Press, 2021: 94-101.
2	DONG F H , HUANG T , ZHANG Y S , et al. A computation offloading strategy in LEO constellation edge cloud network. Electronics, 2022, 11 (13): 2024. doi: 10.3390/electronics11132024
3	高媛, 方海, 赵扬, 等. 星地协同网络中的边缘计算技术综述. 空间电子技术, 2023, 20 (2): 15- 21.
	GAO Y , FANG H , ZHAO Y , et al. A survey on edge computing in satellite-terrestrial networks. Space Electronic Technology, 2023, 20 (2): 15- 21.
4	张晓凯, 郭道省, 张邦宁. 空天地一体化网络研究现状与新技术的应用展望. 天地一体化信息网络, 2021, 2 (4): 19- 26. doi: 10.11959/j.issn.2096-8930.2021039
	ZHANG X K , GUO D X , ZHANG B N . Research status of space-air-ground integrated network and application prospects of new technologies. Space-Integrated-Ground Information Networks, 2021, 2 (4): 19- 26. doi: 10.11959/j.issn.2096-8930.2021039
5	XU X B, ZHAO H, LIU C, et al. On the aggregated resource management for satellite edge computing[C]//Proceedings of the IEEE International Conference on Communications. Washington D.C., USA: IEEE Press, 2021: 1-6.
6	LIU J H , XUE K L , MIAO Q H , et al. MCVCO: multi-MEC cooperative vehicular computation offloading. IEEE Transactions on Intelligent Vehicles, 2024, 9 (1): 813- 826. doi: 10.1109/TIV.2023.3299381
7	OUARNOUGHI H , GRISLIN-LE STRUGEON E , NIAR S . Simulating multi-agent-based computation offloading for autonomous cars. Cluster Computing, 2022, 25 (4): 2755- 2766. doi: 10.1007/s10586-021-03440-y
8	BACCO M, DAVOLI F, GIAMBENE G, et al. Networking challenges for non-terrestrial networks exploitation in 5G[C]//Proceedings of the 2nd IEEE 5G World Forum (5GWF). Washington D.C., USA: IEEE Press, 2019: 623-628.
9	LI F , LAM K Y , SHENG Z G , et al. Agent-based spectrum management scheme in satellite communication systems. IEEE Transactions on Vehicular Technology, 2021, 70 (3): 2877- 2881. doi: 10.1109/TVT.2021.3059837
10	DING H X , ZHU S C , MENG S , et al. Matching-based resource allocation for satellite-ground network. Sensors, 2022, 22 (21): 8436. doi: 10.3390/s22218436
11	TONG M L , LI S , WANG X X , et al. Inter-satellite cooperative offloading decision and resource allocation in mobile edge computing-enabled satellite-terrestrial networks. Sensors, 2023, 23 (2): 668. doi: 10.3390/s23020668
12	CHENG L, FENG G, SUN Y, et al. Dynamic computation offloading in satellite edge computing[C]//Proceedings of the IEEE International Conference on Communications. Washington D.C., USA: IEEE Press, 2022: 4721-4726.
13	YANG C , LIU Y , CHEN X , et al. Efficient mobility-aware task offloading for vehicular edge computing networks. IEEE Access, 2019, 7, 26652- 26664. doi: 10.1109/ACCESS.2019.2900530
14	TANG Q Q , FEI Z S , LI B , et al. Stochastic computation offloading for LEO satellite edge computing networks: a learning-based approach. IEEE Internet of Things Journal, 2024, 11 (4): 5638- 5652. doi: 10.1109/JIOT.2023.3307707
15	DAI W F. Joint task offloading, resource allocation and data caching in MEC-assisted vehicular network[C]//Proceedings of the 4th International Conference on Computer Engineering and Application (ICCEA). Washington D.C., USA: IEEE Press, 2023: 70-76.
16	MOHAMMED O S, SEWISY A A A, TALOBA A I. Solving optimization problems using hybrid metaheuristics: genetic algorithm and black hole algorithm[C]//Proceedings of the 2nd International Conference on Computer and Information Sciences (ICCIS). Washington D.C., USA: IEEE Press, 2020: 1-5.
17	QIU C , YAO H P , YU F R , et al. Deep Q-learning aided networking, caching, and computing resources allocation in software-defined satellite-terrestrial networks. IEEE Transactions on Vehicular Technology, 2019, 68 (6): 5871- 5883. doi: 10.1109/TVT.2019.2907682
18	HE S X, WANG T Y, WANG S W. Load-aware satellite handover strategy based on multi-agent reinforcement learning[C]//Proceedings of the IEEE Global Communications Conference. Washington D.C., USA: IEEE Press, 2020: 1-6.
19	3rd Generation Partnership Project. Technical specification group radio access network; study on New Radio (NR) to support non-terrestrial networks (release 15)[EB/OL]. [2023-10-05]. https://www.3gpp.org/ftp/Specs/archive/38_series/38.811.
20	GHOLIPOUR N, DE ASSUNCAO M D, AGARWAL P, et al. TPTO: a transformer-PPO based task offloading solution for edge computing environments[C]//Proceedings of the 29th IEEE International Conference on Parallel and Distributed Systems (ICPADS). Washington D.C., USA: IEEE Press, 2023: 1115-1122.
21	WANG J , HU J , MIN G Y , et al. Dependent task offloading for edge computing based on deep reinforcement learning. IEEE Transactions on Computers, 2022, 71 (10): 2449- 2461. doi: 10.1109/TC.2021.3131040
22	LIN H , ZEADALLY S , CHEN Z H , et al. A survey on computation offloading modeling for edge computing. Journal of Network and Computer Applications, 2020, 169, 102781. doi: 10.1016/j.jnca.2020.102781
23	唐琳, 周爽, 李勇, 等. 嵌入位置编码的多头注意力机制在堆积脉冲幅度估计中的应用. 核技术, 2023, 46 (9): 090505.
	TANG L , ZHOU S , LI Y , et al. Application of multi-head attention mechanism with embedded positional encoding in amplitude estimation of stacked pulses. Nuclear Techniques, 2023, 46 (9): 090505.
24	TONG M L , WANG X X , LI S , et al. Joint offloading decision and resource allocation in mobile edge computing-enabled satellite-terrestrial network. Symmetry, 2022, 14 (3): 564. doi: 10.3390/sym14030564

[1]	秦敏浩, 孙未未. 基于隐状态预测的失真交通信号灯路口控制策略[J]. 计算机工程, 2025, 51(9): 1-13.
[2]	陈彦如, 刘珂良, 冉茂亮. 基于深度强化学习的外卖即时配送实时优化[J]. 计算机工程, 2025, 51(9): 328-339.
[3]	崔萌萌, 施静燕, 项昊龙. 基于空地协同的动态车载边缘任务卸载方法[J]. 计算机工程, 2025, 51(9): 25-37.
[4]	田金玮, 李晓乐, 秦尧, 王翠平, 王华. 基于多步强化学习的多目标组播路由算法[J]. 计算机工程, 2025, 51(6): 275-285.
[5]	沈思彤, 王耀吾, 谢在鹏, 唐斌. 基于角色学习的多智能体强化学习方法[J]. 计算机工程, 2025, 51(6): 102-115.
[6]	亓明凯, 王迪, 张立晔. 基于分层强化学习的在线三维装箱模型[J]. 计算机工程, 2025, 51(6): 136-145.
[7]	武小丰, 袁培燕. 一种改进蛇优化算法的边缘服务器动态放置策略[J]. 计算机工程, 2025, 51(6): 255-265.
[8]	李斌, 山慧敏. 空地算力网络中的异构资源协同优化[J]. 计算机工程, 2025, 51(5): 1-8.
[9]	吴凯峰, 刘磊, 刘晨, 梁成庆. 基于融合课程思想MADDPG的无人机编队控制[J]. 计算机工程, 2025, 51(5): 73-82.
[10]	王克文, 张维庭, 孙童. 空天地一体化算力网络资源调度机制[J]. 计算机工程, 2025, 51(5): 52-61.
[11]	吕超峰, 徐鹏飞, 罗迪, 刘金平. 基于多智能体深度强化学习的SD-IoT控制器部署[J]. 计算机工程, 2025, 51(5): 83-92.
[12]	黄思扬, 蔡瑞初, 乔杰, 郝志峰. 基于因果掩码的因果强化学习算法[J]. 计算机工程, 2025, 51(4): 66-74.
[13]	李淑怡, 阳波, 陈灵, 沈玲, 唐文胜. 自适应奖励函数的PPO曲面覆盖方法[J]. 计算机工程, 2025, 51(3): 86-94.
[14]	李思源, 钟兴宇, 李凯茵, 徐清振. 基于多层图关系和强化学习的策略教学研究[J]. 计算机工程, 2025, 51(3): 122-130.
[15]	林绍福, 陈盈盈, 李硕朋. 基于深度强化学习的多无人机能量传输与边缘计算联合优化方法[J]. 计算机工程, 2025, 51(3): 144-154.

选择文件类型/文献管理软件名称

选择包含的内容