车联网中一种基于软件定义网络与移动边缘计算的卸载策略

An Offloading Mechanism Based on Software Defined Network and Mobile Edge Computing in Vehicular Networks

在新兴的车联网络中,汽车终端请求卸载的任务对网络带宽、卸载时延等有着更加严苛的需求,而新型通信网络研究中移动边缘计算(MEC)的提出更好地解决了这一挑战。该文着重解决的是汽车终端进行任务卸载时卸载对象的匹配问题。文中引入了软件定义车载网络(SDN-V)对全局变量统一调度,实现了资源控制管理、设备信息采集以及任务信息分析。基于用户任务的差异化性质,定义了重要度的模型,在此基础上,通过设计任务卸载优先级机制算法,实现任务优先级划分。针对多目标优化模型,采用乘子法对非凸优化模型进行求解。仿真结果表明,与其他卸载策略相比,该文所提卸载机制对时延和能耗优化效果明显,能够最大程度地保证用户的效益。

In the emerging vehicular networks, the task of the car terminal requesting offloading has more stringent requirements for network bandwidth and offload delay, and the proposed Mobile Edge Computing(MEC) in the new communication network research solves better this challenge. This paper focuses on matching the offloaded objects when the car terminal performs the task offloading. By introducing the Software-Defined in-Vehicle Network(SDN-V) to schedule uniformly global variables, which realizes resource control management, device information collection and task information analysis. Based on the differentiated nature of user tasks, a model of importance is defined. On this basis, task priority is divided by designing the task to offload the priority mechanism. For the multi-objective optimization model, the non-convex optimization model is solved by the multiplier method. The simulation results show that compared with other offloading strategies, the proposed offloading mechanism has obvious effects on delay and energy consumption optimization, which can guarantee the benefit of users to the greatest extent.