Characterizing task completion latencies in multi-point multi-quality fog computing systems
Characterizing task completion latencies in multi-point multi-quality fog computing systems
复制标题
DOI：
10.1016/j.comnet.2020.107526
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
M. Gorlatova;Hazer Inaltekin;M. Chiang
中科院分区：
文献类型：
--
作者：
M. Gorlatova;Hazer Inaltekin;M. Chiang
雾计算将计算资源分配到物联网（IoT）设备和云之间的多个位置，正在引起学术界和工业界的广泛关注。然而，尽管人们对雾计算的潜力感到兴奋，但很少有人对雾计算架构的特性进行全面的定量研究。在本文中，我们研究了雾计算任务完成延迟的统计特性，这对于理解开发将物联网节点的任务与雾计算基板内的最佳执行点相匹配的算法非常重要。为了描述任务完成延迟，我们在6个不同的位置开发并部署了一组基准测试，其中包括不同等级的本地节点、两个不同区域的传统云计算服务，以及Amazon Web services （AWS）和Microsoft Azure无服务器计算选项。使用已开发的基础设施，我们对一个节点在不同位置和不同条件下调用我们的基准进行了一系列有针对性的实验。实证研究阐明了任务执行延迟的几个重要特性，包括不同执行点和执行选项之间的延迟变化，以及相对于时间的稳定性。该研究还展示了无服务器执行选项的重要属性，并表明计算延迟的统计结构可以基于少量（仅10-50）延迟样本来准确表征。作为这项研究的一部分，我们获得的完整测量集是公开的。
Fog computing, which distributes computing resources to multiple locations between the Internet of Things (IoT) devices and the cloud, is attracting considerable attention from academia and industry. Yet, despite the excitement about the potential of fog computing, few comprehensive studies quantitatively characterizing the properties of fog computing architectures have been conducted. In this paper we examine the statistical properties of fog computingtask completion latencies, which are important to understand to develop algorithms that match IoT nodes’ tasks with the best execution points within the fog computing substrate. Towards characterizing task completion latencies, we developed and deployed a set of benchmarks in 6 different locations, which included local nodes of different grades, conventional cloud computing services in two different regions, and Amazon Web Services (AWS) and Microsoft Azure serverless computing options. Using the developed infrastructure, we conducted a series of targeted experiments with a node invoking our benchmarks from different locations and in different conditions. The empirical study elucidated several important properties of task execution latencies, including latency variation across different execution points and execution options, and stability with respect to time. The study also demonstrated important properties of serverless execution options, and showed that statistical structure of computing latencies can be accurately characterized based on a small number (only 10–50) of latency samples. The complete measurement set we have captured as part of this study is publicly available.