高速公路自治车联云下基于QoS的任务分配策略的研究

发布时间：2018-05-13 15:08

本文选题：自治车联云 + 任务分配　；参考：《内蒙古大学》2017年硕士论文

【摘要】：自治车联云将分散的、可视为移动计算机的车辆资源进行聚合,像云计算一样提供统一资源的按需分配。合理的任务分配一方面可以使车联云中的大量闲置资源得到充分利用,另一方面可以提高任务的执行效率。服务质量问题是车联云任务分配研究中的关键问题,而时间指标又是服务质量指标中的重要指标之一。在有时间指标的要求时,任务承担车辆的选择将影响到有特定时间要求的任务成功率。这是由于在高速公路自治车联云下,车辆具有高移动性,各个车辆与任务请求车辆之间的通信链路持续时间是不同的,而且各个车辆的运算速度也是不同的。所选执行任务车辆的不同,将直接导致有特定时间要求的任务的成功率不同。为此,本文提出了一种在高速公路自治车联云下满足服务质量(Quality of Service,QoS)要求的任务承担车辆选择策略。本策略综合考虑了车辆之间的通信链路持续时间以及车辆的运算速度等因素,设计了任务承担车辆节点需要重选时的最优选择方案。最后采用OPNET(Optimized Performance Network Engineering Tools)网络仿真平台对提出策略的有效性进行了模拟仿真。仿真结果表明,本文提出的任务分配策略与随机选择任务承担车辆节点的策略相比,任务的成功率提高了 8.7%～10.4%。
[Abstract]:Autonomous vehicle cloud will be dispersed, can be regarded as mobile computer vehicle resources aggregation, like cloud computing to provide a unified allocation of resources according to demand. On the one hand, reasonable task allocation can make full use of a large number of idle resources in the vehicle network, on the other hand, it can improve the efficiency of task execution. The quality of service (QoS) is a key problem in the research of vehicle network task allocation, and the time index is one of the most important indexes in the quality of service (QoS). When there is a time target, the choice of a task bearing vehicle will affect the task success rate with a specific time requirement. This is due to the high mobility of the vehicle under the autonomous vehicle cloud of the freeway, the difference of the communication link duration between each vehicle and the vehicle requesting the task, and the different computing speed of each vehicle. Different vehicles selected to perform tasks will directly lead to different success rates for tasks with specific time requirements. For this reason, this paper proposes a vehicle selection strategy to meet the requirement of quality of Service (QoS) in expressway autonomous vehicle network. This strategy takes into account the communication link duration between vehicles and the speed of the vehicle operation, and designs the optimal selection scheme when the task bearing vehicle nodes need to be reselected. Finally, the effectiveness of the proposed strategy is simulated using OPNET(Optimized Performance Network Engineering Tools) network simulation platform. The simulation results show that the task assignment strategy proposed in this paper increases the success rate of task by 8.7 / 10.4 compared with the strategy of random selection of vehicle nodes.
【学位授予单位】：内蒙古大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：U495;TP391.9

【参考文献】