The current trend in end-user devices' advancements in computing and communication capabilities makes edge computing an attractive solution to pave the way for the coveted ultra-low latency services. The success of the edge computing networking paradigm depends on the proper orchestration of the edge servers. Several Edge applications and services are intolerant to latency, especially in 5G and beyond networks, such as intelligent video surveillance, E-health, Internet of Vehicles, and augmented reality applications. The edge devices underwent rapid growth in both capabilities and size to cope with the service demands. Orchestrating it on the cloud was a prominent trend during the past decade. However, the increasing number of edge devices poses a significant burden on the orchestration delay. In addition to the growth in edge devices, the high mobility of users renders traditional orchestration schemes impractical for contemporary edge networks. Proper segmentation of the edge space becomes necessary to adapt these schemes to address these challenges. In this paper, we introduce a segmentation technique employing lax clustering and segregated mobility-based clustering. We then apply latency mapping to these clusters. The proposed scheme's main objective is to create subspaces (segments) that enable light and efficient edge orchestration by reducing the processing time and the core cloud communication overhead. A bench-marking simulation is conducted with the results showing decreased mobility-related failures and reduced orchestration delay.
翻译:终端用户装置在计算和通信能力方面的进步趋势使目前终端用户装置在计算和通信能力方面的进步趋势在计算上成为一个有吸引力的解决方案,为令人羡慕的超低潜伏服务铺平了道路。边缘计算网络模式的成功取决于边端服务器的正确调控。一些边缘应用和服务对延缓性是不容忍的,特别是在5G和5G网络以外的网络,例如智能视频监视、电子保健、车辆互联网,以及扩大的现实应用。边缘装置在能力和规模上都经历了快速增长,以应对服务需求。在云层上布置是过去十年的一个突出趋势。然而,边端装置数量的增加给交织延迟带来了沉重的负担。除了边端装置的增长外,用户的高度机动性使得传统的调控计划对当代边端网络不切实际。有必要对边缘空间进行适当分割,以调整这些计划来应对这些挑战。在本文中,我们采用了一种分化技术,使用松散的集群和隔离的机动集聚体来应对服务需求。我们随后在云层上绘制定位图,这是过去十年的一个突出的趋势。拟议办法的主要目标是通过降低低调调制的轨道来降低云层处理和降低云层的频率,通过降低电路段。