Local Scheduling in KubeEdge-Based Edge Computing Environment

Abstract

KubeEdge is an open-source platform that orchestrates containerized Internet of Things (IoT) application services in IoT edge computing environments. Based on Kubernetes, it supports heterogeneous IoT device protocols on edge nodes and provides various functions necessary to build edge computing infrastructure, such as network management between cloud and edge nodes. However, the resulting cloud-based systems are subject to several limitations. In this study, we evaluated the performance of KubeEdge in terms of the computational resource distribution and delay between edge nodes. We found that forwarding traffic between edge nodes degrades the throughput of clusters and causes service delay in edge computing environments. Based on these results, we proposed a local scheduling scheme that handles user traffic locally at each edge node. The performance evaluation results revealed that local scheduling outperforms the existing load-balancing algorithm in the edge computing environment.

An Automated Edge Computing Approach for IoT Device Registration and Application Deployment

“…By leveraging Kubernetes, this platform specifically focuses on orchestrating containerized IoT application services within IoT edge computing environments. In a recent article authored by Kim [39], an in-depth evaluation of the framework is presented, encompassing aspects such as the distribution of computational resources and the latency experienced between various edge nodes. However, configuring KubeEdge can be challenging, requiring complex knowledge about networking and operating system to deploy it [40].…”

An Automated Edge Computing Approach for IoT Device Registration and Application Deployment

“…The architecture of KubeEdge, visually represented in Figure 2, illustrates its structural components and their interactions. In a recent article authored by Kim [37], an in-depth evaluation of the framework is presented, encompassing aspects such as the distribution of computational resources and the latency experienced between various edge nodes.…”

Research on Integration Management of Big Data Application Precision Portrait Marketing Resources based on Cloud and Edge Collaborative Computing

“…In order to clarify this issue, the article will first introduce the roles played by edge computing and cloud computing, and then explain why enterprises need edge computing and how to choose the solution of big data precision portrait marketing resource integration of edge cloud collaboration, and finally explain the complexity of edge computing. Edge computing is an architecture of distributed processing and storage that is closer to the source of the data [2]Kim SeongHyun & Kim Taehong(2023) proposed a local scheduling scheme to process user traffic locally at each edge node [4]. A mix of edge and cloud computing is often considered a best practice for building enterprise-class iot solutions as opposed to cloud computing.Figure 1 shows the key components that are often used in edge computing.…”