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
为保证电力应急物资及时配送,使其可快速恢复供电,减少经济损失,以地理信息系统为基础,提出电力应急物资配送路径的规划方法。先基于GIS(Geographic Information System)地理信息系统中的Map X组件,构建地理空间数据预处理模型,然后根...为保证电力应急物资及时配送,使其可快速恢复供电,减少经济损失,以地理信息系统为基础,提出电力应急物资配送路径的规划方法。先基于GIS(Geographic Information System)地理信息系统中的Map X组件,构建地理空间数据预处理模型,然后根据处理后数据,建立配送路径规划数学模型与约束条件,最后融合遗传算法、爬山算法与蚁群算法,循环运算数学模型,取得最优配送路径。实验以某次电力设备突发事件为背景,当满足物资需求时,规划路径在道路状况正常与非正常条件下的配送时间各减少14 min和30 min,成本分别减少10.9元和5.09元,证明所设计的规划方法具有显著优越性。展开更多
基金supported in part by the Project of International Cooperation and Exchanges NSFC under Grant No.61860206005in part by the Joint Funds of the NSFC under Grant No.U22A2003.
文摘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).
