首页|基于MATD3的空地网络资源优化

基于MATD3的空地网络资源优化

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
移动边缘计算通过将计算任务卸载到无线网络边缘，可有效减少任务延迟与终端能耗。对于偏远地区分布的大量物联设备(如风电、光伏等电力物联终端)，现有地面网络无法为其提供有效的网络服务。因此，本文重点研究空地一体化异构网络模型，通过联合设计无人机轨迹、任务卸载与计算资源分配，以最大限度地减少物联设备任务执行延迟与能耗。针对目标函数的非凸性和网络动态造成的信息不确定性，本文将问题建模为马尔可夫(Markov)决策过程，并提出一种基于MATD3的UAV轨迹与网络资源协同优化算法。实验结果表明，与基准算法相比，本文提出的方案在系统计算能耗和时延方面性能更优。
Air-ground integrated network resource optimization based on MATD3
Mobile edge computing effectively reduces service latency and terminal energy consumption by offloading tasks to the edge of the wireless networks.For tremendous IoT devices distributed in remote areas(e.g.,wind power,photovoltaic,and other power IoT terminals),existing terrestrial communication networks are not able to provide effective computing services.Therefore,in this paper,we comprehensively consider an air-ground integrated heterogeneous network model to minimize the sum of execution delay and energy consumption of IoT devices by jointly designing UAV trajectory,task offloading,and computing resource allocation.Regarding the non-convexity of the objective function and the information uncertainty caused by network dynamics,the problem is modeled as a Markov decision process,and we propose a joint UAV trajectory and network resource optimization algorithm based on MATD3.Experimental results show that compared with other baselines,the proposed scheme has superior performance in system computing energy consumption and delay.

air-ground integrated heterogeneous networkoffloading decision-makingresource allocationUAV trajectory optimizationmulti-agent deep reinforcement learning(MADRL)

秦鹏、王硕、付民、赵雄文

展开 >

华北电力大学电气与电子工程学院,北京 102206

中国电信股份有限公司河北分公司,石家庄 050036

空地一体化异构网络 卸载决策 资源分配 UAV轨迹优化 多智能体深度强化学习

国家自然科学基金河北省自然科学基金中央高校基本科研业务费专项

62201212F20225020172023JC003

2024

10.1360/SSI-2023-0223

中国科学F辑
中国科学院,国家自然科学基金委员会

中国科学F辑

CSTPCD北大核心
影响因子：1.438
ISSN：1674-5973
年,卷(期)：2024.54(6)