期刊
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
卷 7, 期 4, 页码 2416-2428出版社
IEEE COMPUTER SOC
DOI: 10.1109/TNSE.2020.2978856
关键词
Servers; Resource management; Wireless fidelity; Task analysis; Computational modeling; Quality of service; Radio spectrum management; Vehicular networks; multi-access edge computing; multi-dimensional resource management; deep reinforcement learning; DDPG
资金
- Natural Sciences and Engineering Research Council (NSERC) of Canada
In this paper, we study joint allocation of the spectrum, computing, and storing resources in a multi-access edge computing (MEC)-based vehicular network. To support different vehicular applications, we consider two typical MEC architectures and formulate multi-dimensional resource optimization problems accordingly, which are usually with high computation complexity and overlong problem-solving time. Thus, we exploit reinforcement learning (RL) to transform the two formulated problems and solve them by leveraging the deep deterministic policy gradient (DDPG) and hierarchical learning architectures. Via off-line training, the network dynamics can be automatically learned and appropriate resource allocation decisions can be rapidly obtained to satisfy the quality-of-service (QoS) requirements of vehicular applications. From simulation results, the proposed resource management schemes can achieve high delay/QoS satisfaction ratios.
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