基于移动边缘计算的GI/GI/1排队建模与调度算法EI北大核心CSCD

针对车联网环境下路侧边缘计算节点部署不均衡、服务密度小、实时调度计算压力大等问题,提出一种基于智能车移动边缘计算(Mobile edge computing,MEC)的任务排队建模与调度算法,提供弹性计算服务,将具备感知、计算、控制功能的智能车作为移动边缘计算服务器,设计了车联网环境下的MEC体系架构.首先基于虚拟化技术对智能车进行虚拟化抽象,利用排队论对虚拟车任务构建了GI/GI/1排队模型.然后基于云平台Voronoi分配算法对虚拟车任务进行分配绑定,进而实现了智能车的优化调度与分布式弹性服务,解决了边缘计算任务分配不均衡等问题.最后通过城市交通路网中的车辆污染排放的实时计算实验,验证了该方法的有效性.

GI/GI/1 Queuing Model and Task Scheduling for Mobile Edge Computing

The edge computing of internet of vehicles is confronted with some challenges, such as the unbalanced arrangement, the service inflexible and the time delay for the real-time computing of roadside nodes. In this paper, a new queuing model and scheduling algorithm of mobile edge computing (MEC) is proposed based on intelligent vehicles integrating the sensing, computing and control together. The GI/GI/1 task queuing model is firstly set up for the distributed services of vehicular networks, in which intelligent vehicles are virtualized into virtual vehicles. Moreover, according to the Voronoi allocation algorithm, the tasks generated by virtual vehicles are allocated and bound to intelligent vehicles. The optimal scheduling and distributed elastic service of intelligent vehicles are presented to solve the problem of unbalanced distribution of tasks in edge computing. The simulation experiment of the vehicle pollutant emission illustrates the effectiveness of the proposed method.