Parking Edge Computing：Task Offloading Based on Roadside Parking in Vehicle Ad Hoc Networks
DU Tian1，ZHU Jin-qi1，LIU Nian-bo2，CAO Ke1，GUO Yang-long1
1(School of Computer and Information Engineering，Tianjin Normal University，Tianjin 300387，China)2(School of Computer Science and Engineering，University of Electronic Science and Technology of China，Chengdu 610054，China)
摘要 为解决车载自组织网络(Vehicle Ad Hoc Neteorks，VANETs )中基础设施建设的不足以及路侧单元(Roadside Uints，RSUs)通信范围受限的问题，提出停车边缘计算的思想，把拥有大量闲置计算资源的路边停放车辆组织成停车簇，令停车簇充当天然边缘计算节点，在RSUs或边缘计算服务器缺失情况下，及时执行周围移动车辆的卸载任务.分析了任务的完成时间，为最大化成功完成的任务数量，设计改进的SAC(Sampling-and-Classification，SAC)算法实现执行任务的停放车辆选择和资源的分配.基于真实城市道路停车调查的模拟实验结果证明，与其他几种任务调度策略相比，本文所提策略具有较高的任务完成率和卸载率.
Abstract：In order to resolve the shortage of infrastructure construction in Vehicle Ad Hoc Networks(VANETs) and the limited communication range of the Roadside Units(RSUs)，the idea of parking edge computing is proposed，in which roadside parked vehicles are organized into parking clusters.In the case of RSUs or mobile edge computing servers are missing，parking clusters with a large number of idle computing resources can act as natural edge computing nodes to perform the offloaded tasks from the surrounding mobile vehicles to reduce the task completion time.The task completion time is analyzed.To maximize the number of successfully completed tasks，an improved SAC(Sampling-and-Classification)algorithm is designed to jointly determine the selection of parked vehicle nodes and the resource allocation.Simulation results based on the real parking survey of the road in the city show that compared with other task scheduling strategies，the proposed strategy owns both higher task completion rate and offloading rate.
杜恬,朱金奇,刘念伯,曹轲,郭杨隆. 停车边缘计算：车载自组织网络中基于路边停车的任务卸载[J]. 小型微型计算机系统, 2022, 43(2): 416-421.
DU Tian,ZHU Jin-qi,LIU Nian-bo,CAO Ke,GUO Yang-long. Parking Edge Computing：Task Offloading Based on Roadside Parking in Vehicle Ad Hoc Networks. Journal of Chinese Computer Systems, 2022, 43(2): 416-421.
2022, Vol. 43 
