期刊
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
卷 39, 期 1, 页码 131-141出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSAC.2020.3036962
关键词
Servers; Task analysis; Resource management; Delays; Unmanned aerial vehicles; Quality of service; Wireless communication; Vehicular networks; multi-access edge computing; unmanned aerial vehicle; multi-dimensional resource management; multi-agent DDPG
资金
- Natural Sciences and Engineering Research Council (NSERC) of Canada
This paper investigates multi-dimensional resource management for unmanned aerial vehicles (UAVs) assisted vehicular networks, proposing a MADDPG-based method for resource allocation at MEC servers. Simulation results show that the MADDPG method can converge within 200 training episodes and achieve higher delay/QoS satisfaction ratios than SADDPG and random schemes.
In this paper, we investigate multi-dimensional resource management for unmanned aerial vehicles (UAVs) assisted vehicular networks. To efficiently provide on-demand resource access, the macro eNodeB and UAV, both mounted with multi-access edge computing (MEC) servers, cooperatively make association decisions and allocate proper amounts of resources to vehicles. Since there is no central controller, we formulate the resource allocation at the MEC servers as a distributive optimization problem to maximize the number of offloaded tasks while satisfying their heterogeneous quality-of-service (QoS) requirements, and then solve it with a multi-agent deep deterministic policy gradient (MADDPG)-based method. Through centrally training the MADDPG model offline, the MEC servers, acting as learning agents, then can rapidly make vehicle association and resource allocation decisions during the online execution stage. From our simulation results, the MADDPG-based method can converge within 200 training episodes, comparable to the single-agent DDPG (SADDPG)-based one. Moreover, the proposed MADDPG-based resource management scheme can achieve higher delay/QoS satisfaction ratios than the SADDPG-based and random schemes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据