Research on heterogeneous task offloading methods based on CA3C in satellite-ground edge computing networks

Liu Zhiguo; Jin Xiaoyong; Wang Lin; Pan Chengsheng

doi:10.11959/j.issn.1000-0801.2026124

您当前的位置：

首页 >

文章列表页 >

Research on heterogeneous task offloading methods based on CA3C in satellite-ground edge computing networks

Research and Development | 更新时间：2026-03-31

- Research on heterogeneous task offloading methods based on CA3C in satellite-ground edge computing networks
- Telecommunications Science Vol. 42, Pages: 1-16(2026)
- 作者机构：
  
  1.大连大学信息工程学院，辽宁大连 116622
  2.大连大学通信与网络重点实验室，辽宁大连 116622
  3.大连大学环境与化学工程学院，辽宁大连 116622
  4.南京信息工程大学电子与信息工程学院，江苏南京 210044
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61931004)
- DOI：10.11959/j.issn.1000-0801.2026124
  CLC： TN927.2
- Revised：2025-12-29，
  
  Accepted：07 January 2026，
  
  Online First：30 March 2026，
  
  Published：20 April 2026
- 稿件说明：
移动端阅览
刘治国,金晓勇,汪林等.星地边缘计算网络中基于 CA3C的异构任务卸载方法研究[J].电信科学,

Liu Zhiguo,Jin Xiaoyong,Wang Lin,et al.Research on heterogeneous task offloading methods based on CA3C in satellite-ground edge computing networks[J].Telecommunications Science,
刘治国,金晓勇,汪林等.星地边缘计算网络中基于 CA3C的异构任务卸载方法研究[J].电信科学, DOI：10.11959/j.issn.1000−0801.2026124.

Liu Zhiguo,Jin Xiaoyong,Wang Lin,et al.Research on heterogeneous task offloading methods based on CA3C in satellite-ground edge computing networks[J].Telecommunications Science, DOI：10.11959/j.issn.1000−0801.2026124.

摘要

卫星边缘计算弥补了地面网络覆盖面有限的缺点，能够为稀疏网络环境下的用户提供高质量服务。但卫星边缘服务器资源受限以及用户的差异需求为制定灵活有效的任务卸载方法带来了困难。针对因异构任务卸载决策不合理而导致的卸载时延过高与能耗过大的问题，融合软件定义网络（software defined network，SDN）的卫星-地面边缘计算网络（satellite-ground edge computing network，SGECN）架构的系统模型下，提出一种基于卷积异步优势Actor-Critic（convolutional asynchronous advantage Actor-Critic，CA3C）算法的异构任务卸载方法，通过引入动态权重分配机制根据任务特征自适应地调整时延和能耗权重，并采用卷积神经网络改进了A3C（asynchronous advantage Actor-Critic）算法的网络结构，解决了异构任务多样化需求以及算法收敛速度慢的问题。仿真结果表明，CA3C在显著降低异构任务卸载时延与能耗方面具有优越性能。

Abstract

Satellite edge computing is proposed to make up for limited coverage of the terrestrial network，it can provide high-quality service for users in sparse network environment. However

limited resources of satellite edge servers and diverse demands of users make it difficult to formulate flexible and effective task offloading methods. Aiming at the problems of high offloading delays and excessive energy consumption caused by unreasonable heterogeneous task offloading strategy

a heterogeneous task offloading method based on the convolutional asynchronous advantage Actor-Critic (CA3C) algorithm was proposed based on the system model of satellite-ground edge computing network (SGECN) architecture combined with software defined network (SDN). Delay and energy consumption weights were adaptively adjusted according to task characteristics by introducing a dynamic weight distribution mechanism

and a convolutional neural network was used to improve the network structure of A3C

the problems of diverse demands of heterogeneous task and slow convergence speed of the algorithm were solved. Simulation results show that the CA3C method performed better in effectively reducing the offloading time delay and energy consumption of heterogeneous task.

关键词

Keywords

references

Ranaweera P , Jurcut A D , Liyanage M . Survey on multi-access edge computing security and privacy [J ] . IEEE Communications Surveys & Tutorials , 2021 , 23 ( 2 ): 1078 - 1124 .

Liu Y Q , Peng M G , Shou G C , et al . Toward edge intelligence: multiaccess edge computing for 5G and Internet of Things [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 8 ): 6722 - 6747 .

Yang J Y , Zhang Y J , Xiao Z Y , et al . Joint access selection and computation offloading in LEO ubiquitous edge computing networks: an alternating DRL-based approach [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 3 ): 1870 - 1886 .

Ji Z , Wu S , Jiang C X . Cooperative multi-agent deep reinforcement learning for computation offloading in digital twin satellite edge networks [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 11 ): 3414 - 3429 .

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 .

Lai Z Q , Li H W , Wu Q , et al . Futuristic 6G pervasive on-demand services: integrating space edge computing with terrestrial networks [J ] . IEEE Vehicular Technology Magazine , 2023 , 18 ( 1 ): 80 - 90 .

Xie R C , Tang Q Q , Wang Q N , et al . Satellite-terrestrial integrated edge computing networks: architecture, challenges, and open issues [J ] . IEEE Network , 2020 , 34 ( 3 ): 224 - 231 .

Tang Q Q , Fei Z S , Li B , et al . Computation offloading in LEO satellite networks with hybrid cloud and edge computing [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 11 ): 9164 - 9176 .

Zhang S H , Cui G F , Long Y T , et al . Joint computing and communication resource allocation for satellite communication networks with edge computing [J ] . China Communications , 2021 , 18 ( 7 ): 236 - 252 .

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 .

Gao X Q , Liu R K , Kaushik A . Virtual network function placement in satellite edge computing with a potential game approach [J ] . IEEE Transactions on Network and Service Management , 2022 , 19 ( 2 ): 1243 - 1259 .

方海 , 高媛 , 赵扬 , 等 . 卫星边缘计算中任务卸载与资源分配联合优化算法 [J ] . 小型微型计算机系统 , 2023 , 44 ( 6 ): 1214 - 1219 .

Fang H , Gao Y , Zhao Y , et al . Joint optimization of task offloading and resource allocation in satellite edge computing [J ] . Journal of Chinese Computer Systems , 2023 , 44 ( 6 ): 1214 - 1219 .

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 .

Huang C , Chen G J , Xiao P , et al . Joint offloading and resource allocation for hybrid cloud and edge computing in SAGINs: a decision assisted hybrid action space deep reinforcement learning approach [J ] . IEEE Journal on Selected Areas in Communications , 2024 , 42 ( 5 ): 1029 - 1043 .

杨桂松 , 陶挺 , 何杏宇 , 等 . 卫星物联网中联合资源分配的边缘计算卸载策略 [J ] . 小型微型计算机系统 , 2024 , 45 ( 10 ): 2544 - 2550 .

Yang G S , Tao T , He X Y , et al . Strategy of joint resource allocation and computing edge offloading in satellite Internet of Things [J ] . Journal of Chinese Computer Systems , 2024 , 45 ( 10 ): 2544 - 2550 .

Wang Q T , Chen S Y , Yang C L , et al . Energy-efficient task split and resource allocation in LEO-satellite-assisted IoT network [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 21 ): 34519 - 34527 .

Zhou J , Liang J W , Zhao L , et al . Latency-energy efficient task offloading in the satellite network-assisted edge computing via deep reinforcement learning [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 4 ): 2644 - 2659 .

Zhang H Y , Zhao H B , Liu R K , et al . Dynamic user association and computation offloading in satellite edge computing networks via deep reinforcement learning [J ] . IEEE Transactions on Green Communications and Networking , 2024 , 8 ( 4 ): 1888 - 1901

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 .

Zhang H Y , Zhao H B , Liu R K , et al . Collaborative task offloading optimization for satellite mobile edge computing using multi-agent deep reinforcement learning [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 10 ): 15483 - 15498 .

Qin Z Y , Yao H P , Mai T L , et al . Multi-agent reinforcement learning aided computation offloading in aerial computing for the Internet-of-things [J ] . IEEE Transactions on Services Computing , 2023 , 16 ( 3 ): 1976 - 1986 .

Deng X H , Sun Z H , Li D , et al . User-centric computation offloading for edge computing [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 16 ): 12559 - 12568 .

Xiao T T , Chen C , Dong M X , et al . Multi-agent reinforcement learning-based trading decision-making in platooning-assisted vehicular networks [J ] . IEEE/ACM Transactions on Networking , 2024 , 32 ( 3 ): 2143 - 2158 .

Li Q , Wang S G , Ma X , et al . Battery-aware energy optimization for satellite edge computing [J ] . IEEE Transactions on Services Computing , 2024 , 17 ( 2 ): 437 - 451 .

Lv W K , Yang P F , Ding Y Q , et al . Energy-efficient and QoS-aware computation offloading in GEO/LEO hybrid satellite networks [J ] . Remote Sensing , 2023 , 15 ( 13 ): 3299 .

Dou J M , Wang X J , Liu Z , et al . MAPIRL: a hyperbolic tangent-enforced physical-informed RL for multi-IESs optimal dispatch [J ] . IEEE Transactions on Industry Applications , 2025 , 61 ( 2 ): 2549 - 2564 .

Zou J F , Hao T B , Yu C , et al . A3C-DO: a regional resource scheduling framework based on deep reinforcement learning in edge scenario [J ] . IEEE Transactions on Computers , 2021 , 70 ( 2 ): 228 - 239 .

刘治国 , 董效奇 , 汪林 , 等 . 面向ET-DQN的卫星网络任务部署算法研究 [J ] . 小型微型计算机系统 , 2024 , 45 ( 2 ): 418 - 424 .

Liu Z G , Dong X Q , Wang L , et al . Research on satellite network task deployment algorithm based on ET-DQN [J ] . Journal of Chinese Computer Systems , 2024 , 45 ( 2 ): 418 - 424 .

Jia M , Zhang L , Wu J , et al . Joint computing and communication resource allocation for edge computing towards Huge LEO networks [J ] . China Communications , 2022 , 19 ( 8 ): 73 - 84 .

Zhao Z L , Feng M J , Ke C X , et al . Federated deep recurrent Q-learning for task partitioning and resource allocation in satellite mobile-edge-computing-assisted industrial IoT [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 15 ): 26444 - 26458 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A layered collaborative resource allocation algorithm for cell-free RAN aimed at efficient resource utilization

Research on optimization of data transmission strategies based on deep reinforcement learning

Computing-network collaborative dynamic routing and scheduling algorithm based on deep reinforcement learning

Heterogeneous computing network resource management based on virtual network embedding

Research on task offloading algorithm of mobile edge computing based on deep reinforcement learning in SDCN

Related Author

SHEN Lianfeng

YAN Feng

PAN Yuqing

ZHANG Mingxuan

MIAO Weiwei

XIA Weiwei

WANG Boye

LI Jiayi

Related Institution

State Grid Suzhou Power Supply Company

Information & Telecommunication Branch, State Grid Jiangsu Electric Power Co., Ltd.

National Mobile Communication Research Laboratory of Southeast University

Beijing Normal University

Modern Education Technology Center, Chengdu Medical College

⁰