Li Lei, Guo Mian, Ma Lihong, Mao Huiyun, Guan Quansheng
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510641, China.
School of Electronic and Information Engineering, Guangdong University of Petrochemical Technology, Maoming 525000, China.
Sensors (Basel). 2019 Sep 4;19(18):3830. doi: 10.3390/s19183830.
Fog computing has recently emerged as an extension of cloud computing in providing high-performance computing services for delay-sensitive Internet of Things (IoT) applications. By offloading tasks to a geographically proximal fog computing server instead of a remote cloud, the delay performance can be greatly improved. However, some IoT applications may still experience considerable delays, including queuing and computation delays, when huge amounts of tasks instantaneously feed into a resource-limited fog node. Accordingly, the cooperation among geographically close fog nodes and the cloud center is desired in fog computing with the ever-increasing computational demands from IoT applications. This paper investigates a workload allocation scheme in an IoT-fog-cloud cooperation system for reducing task service delay, aiming at satisfying as many as possible delay-sensitive IoT applications' quality of service (QoS) requirements. To this end, we first formulate the workload allocation problem in an IoT-edge-cloud cooperation system, which suggests optimal workload allocation among local fog node, neighboring fog node, and the cloud center to minimize task service delay. Then, the stability of the IoT-fog-cloud queueing system is theoretically analyzed with Lyapunov drift plus penalty theory. Based on the analytical results, we propose a delay-aware online workload allocation and scheduling (DAOWA) algorithm to achieve the goal of reducing long-term average task serve delay. Theoretical analysis and simulations have been conducted to demonstrate the efficiency of the proposal in task serve delay reduction and IoT-fog-cloud queueing system stability.
雾计算作为云计算的一种扩展，最近在为对延迟敏感的物联网（IoT）应用提供高性能计算服务方面崭露头角。通过将任务卸载到地理位置较近的雾计算服务器而非远程云，可以大大提高延迟性能。然而，当大量任务瞬间涌入资源有限的雾节点时，一些物联网应用可能仍会经历相当大的延迟，包括排队和计算延迟。因此，随着物联网应用对计算需求的不断增加，在雾计算中，地理位置相近的雾节点与云中心之间的合作是很有必要的。本文研究了物联网 - 雾 - 云协作系统中的一种工作负载分配方案，旨在减少任务服务延迟，以满足尽可能多的对延迟敏感的物联网应用的服务质量（QoS）要求。为此，我们首先在物联网 - 边缘 - 云协作系统中制定工作负载分配问题，该问题提出了在本地雾节点、相邻雾节点和云中心之间进行最优工作负载分配，以最小化任务服务延迟。然后，利用李雅普诺夫漂移加罚理论对物联网 - 雾 - 云排队系统的稳定性进行了理论分析。基于分析结果，我们提出了一种延迟感知在线工作负载分配与调度（DAOWA）算法，以实现降低长期平均任务服务延迟的目标。进行了理论分析和仿真，以证明该方案在降低任务服务延迟和物联网 - 雾 - 云排队系统稳定性方面的效率。
