期刊文献+
共找到1篇文章
< 1 >
每页显示 20 50 100
Information Freshness-Oriented Trajectory Planning and Resource Allocation for UAV-Assisted Vehicular Networks
1
作者 Hao Gai Haixia Zhang +1 位作者 Shuaishuai Guo Dongfeng Yuan 《China Communications》 SCIE CSCD 2023年第5期244-262,共19页
In this paper,multi-UAV trajectory planning and resource allocation are jointly investigated to improve the information freshness for vehicular networks,where the vehicles collect time-critical traffic information by ... In this paper,multi-UAV trajectory planning and resource allocation are jointly investigated to improve the information freshness for vehicular networks,where the vehicles collect time-critical traffic information by on-board sensors and upload to the UAVs through their allocated spectrum resource.We adopt the expected sum age of information(ESAoI)to measure the network-wide information freshness.ESAoI is jointly affected by both the UAVs trajectory and the resource allocation,which are coupled with each other and make the analysis of ESAoI challenging.To tackle this challenge,we introduce a joint trajectory planning and resource allocation procedure,where the UAVs firstly fly to their destinations and then hover to allocate resource blocks(RBs)during a time-slot.Based on this procedure,we formulate a trajectory planning and resource allocation problem for ESAoI minimization.To solve the mixed integer nonlinear programming(MINLP)problem with hybrid decision variables,we propose a TD3 trajectory planning and Round-robin resource allocation(TTPRRA).Specifically,we exploit the exploration and learning ability of the twin delayed deep deterministic policy gradient algorithm(TD3)for UAVs trajectory planning,and utilize Round Robin rule for the optimal resource allocation.With TTP-RRA,the UAVs obtain their flight velocities by sensing the locations and the age of information(AoI)of the vehicles,then allocate the RBs to the vehicles in a descending order of AoI until the remaining RBs are not sufficient to support another successful uploading.Simulation results demonstrate that TTP-RRA outperforms the baseline approaches in terms of ESAoI and average AoI(AAoI). 展开更多
关键词 information freshness for vehicular networks multi-UAV trajectory planning resource allocation deep reinforcement learning
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部