首页|基于深度强化学习的无人机集群通信与网络资源优化调度

基于深度强化学习的无人机集群通信与网络资源优化调度

扫码查看
无人机(Unmanned Aerial Vehicle,UAV)集群通信与网络亟需解决频谱效率、可靠性、低时延等一系列基础问题,应用深度强化学习(Deep Reinforcement Learning,DRL)来优化UAV集群通信网络是目前较好的解决方法.面向UAV集群通信与网络中的资源优化调度问题,进行了较为全面的调研,归纳总结了通信与网络领域采用DRL方法进行资源优化调度的研究成果,对未来的技术发展进行了展望.
Optimized Scheduling of UAV Cluster Communication and Network Resources Based on Deep Reinforcement Learning
There are a series of basic problems such as spectral efficiency,reliability and low latency need to be solved urgently for Unmanned Aerial Vehicle(UAV)cluster communication and network.It is a good solution at present to use Deep Reinforcement Learning(DRL)for optimization of UAV cluster communication network.A comprehensive investigation is conducted on optimized scheduling of resources in UAV cluster communication and network.The research results of using DRL method for optimized scheduling of resources in communication and network are summarized,and the future development of the technology is prospected.

DRLUAVcommunicationnetworkresource scheduling

王庆、孙玮、张程程、秦真、廖勇

展开 >

杭州长望智创科技有限公司,浙江 杭州 310012

重庆大学物理学院,重庆 401331

重庆大学微电子与通信工程学院,重庆 400044

深度强化学习 无人机 通信 网络 资源调度

2024

无线电工程
中国电子科技集团公司第五十四研究所

无线电工程

影响因子:0.667
ISSN:1003-3106
年,卷(期):2024.54(12)