MEC中的多用户上下文感知计算卸载研究  

Research on multi-user context aware computing offload in MEC

作　　者：刘春林[1] 张立祥[1] Liu Chunlin;Zhang Lixiang(Kaili University,Kaili 556011,China)

机构地区：[1]凯里学院,贵州凯里556011

出　　处：《无线互联科技》2022年第6期135-137,共3页Wireless Internet Technology

基　　金：黔东南州科技计划项目,项目名称:基于5G背景的光传送网技术研究,项目编号:黔东南科合J字[2019]147号。

摘　　要：当前,物联网应用程序从环境中感知到大量数据,这些数据需要以最小的延迟进行处理。用户终端作为无处不在的网络终端设备,由于资源有限,无法在本地处理所有的计算。多接入边缘计算是处理网络边缘计算的良好架构,解决了诸如延迟、能源和成本等挑战。如果UE无法处理计算,MEC将把任务卸载到边缘或云上。研究表明,忽略应用程序、请求、传感器、资源和网络工具的上下文信息会导致卸载方法无法完成。因此,文章将对多用户的MEC中具备上下文感知卸载方法进行研究,通过对能量消耗、执行成本、网络使用率、延迟和公平性等指标的比较,证明考虑上下文感知算法将明显优于不考虑上下文感知算法,从而对优化卸载算法提供参考依据。At present,Internet of things applications perceive a large amount of data from the environment,which needs to be processed with minimal delay.User equipment is a ubiquitous network terminal device,but due to limited resources,it is unable to process all computing locally.Multi access edge computing is a good architecture for processing network edge computing.It solves the challenges such as delay,energy and cost.If the UE cannot process the calculation,MEC will unload the task to the edge or cloud.Research shows that ignoring the context information of applications,requests,sensors,resources and network tools will lead to the failure of unloading method.Therefore,this paper will study the context aware unloading method in multi-user MEC.Through the comparison of energy consumption,execution cost,network utilization,delay and fairness,it is proved that the context aware algorithm will be significantly better than the context aware algorithm,so as to provide a reference basis for optimizing the unloading algorithm.

关 键 词：MEC 多用户 计算卸载 上下文感知 物联网 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TN929.5[自动化与计算机技术—控制科学与工程]