一种基于遗传算法的车载边缘计算卸载方案  

An offloading scheme of vehicle edge computing based on the genetic algorithm

作　　者：王珺[1] 刘家豪 宋巧凤 WANG Jun;LIU Jiahao;SONG Qiaofeng(School of Communications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学通信与信息工程学院,江苏南京210003

出　　处：《南京邮电大学学报（自然科学版）》2022年第6期1-9,共9页Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition

基　　金：江苏省重点研发计划(BE2020084-5);江苏省研究生科研与实践创新计划(46006CX21732)资助项目

摘　　要：延迟敏感型和计算密集型车辆应用的出现,给计算资源有限的车联网带来了巨大的挑战。移动边缘计算(Mobile Edge Computing,MEC)是云计算的一种补充,可以有效解决车辆计算资源有限等问题,但是车辆的高机动性以及中心云距离较远导致数据卸载延迟较大,对卸载效率产生较大影响。现有方案大多对车辆的高机动性以及空闲资源的利用方面考虑不足,因此,文中提出一种基于遗传算法的车载边缘计算卸载方案(Genetic Algorithm⁃based Vehicle Edge Computing Offloading Scheme,GAVECOS)。在该方案中,考虑了任务车辆周围的本地车辆、路边基站上的边缘服务器和空闲车辆的计算资源来卸载任务,然后提出一个以系统总成本最小为目标的优化问题,并利用遗传算法求解该优化问题。最后通过搭建仿真平台对方案进行了验证。仿真结果显示,在综合考虑系统的时延和能耗这两个因素的情况下,该方案与其他4种方案相比总成本有明显的降低。The emergence of delay⁃sensitive and computation⁃intensive vehicle applications has imposed great challenges on the Internet of vehicles with limited computing resources.As a supplement to cloud computing,mobile edge computing(MEC)can effectively solve problems like limited computing resources of vehicles.But the high mobility of vehicles and the long distance between the central cloud and the vehicles decrease the offloading efficiency.Most existing schemes neither consider the high mobility of vehicles nor fully use the idle resources around the vehicles.In order to solve the above challenges,an offloading scheme of vehicle edge computing based on the genetic algorithm(GAVECOS)is proposed.In this scheme,we consider the computing resources of local vehicles,edge servers and idle vehicles around the task vehicles to offload the task.Then an optimization problem is developed to minimize the total cost of the system.And we use the genetic algorithm to solve this optimization problem.Finally,a simulation platform is built to verify the algorithm.The simulation results show that the total system cost of this scheme is significantly lower than that of the other four schemes when the delay consumption and energy consumption are considered.

关 键 词：车联网 移动边缘计算 遗传算法 计算卸载 

分 类 号：TN929[电子电信—通信与信息系统] TP311[电子电信—信息与通信工程]