Net
Docker Swarm and Kubernetes Containers for Smart Home Gateway
페이지 정보
| PUBLICATION | IEEE IT Professional, August 20, 2021 |
| AUTHORS | Byungseok Kang, Jaeyeop Jeong, Hyunseung Choo |
ABSTRACT
Abstract
nternet of Things (IoT) for warehouse automation in new generation industries and for home gateway in smart homes have very tight latency requirements for data computation and response. To satisfy the requirements, many studies have moved the computation close to IoT devices by virtualizing the services using containers and deploying them on IoT gateways. They do not account for limited resources at IoT gateways, and without careful provisioning IoT gateways can easily become overloaded and inevitably increase the computation time. To enable efficient service provisioning on IoT gateways, this paper presents the empirical evaluation of Docker Swarm (DS) and Kubernetes (K8s) container solutions, on resource constrained devices such as Raspberry Pi boards. We have used multiple open source Intrusion Detection Systems (IDS) and Deep Learning (DL) based data analytic solutions in our experiments to evaluate creation time, CPU utilization, and memory usage. Our results reveal that creation time and memory usage of containers are critical factors in constrained environments. The lessons learned from our empirical case studies provide essential guidelines for micro services architectures in IoT gateways.
nternet of Things (IoT) for warehouse automation in new generation industries and for home gateway in smart homes have very tight latency requirements for data computation and response. To satisfy the requirements, many studies have moved the computation close to IoT devices by virtualizing the services using containers and deploying them on IoT gateways. They do not account for limited resources at IoT gateways, and without careful provisioning IoT gateways can easily become overloaded and inevitably increase the computation time. To enable efficient service provisioning on IoT gateways, this paper presents the empirical evaluation of Docker Swarm (DS) and Kubernetes (K8s) container solutions, on resource constrained devices such as Raspberry Pi boards. We have used multiple open source Intrusion Detection Systems (IDS) and Deep Learning (DL) based data analytic solutions in our experiments to evaluate creation time, CPU utilization, and memory usage. Our results reveal that creation time and memory usage of containers are critical factors in constrained environments. The lessons learned from our empirical case studies provide essential guidelines for micro services architectures in IoT gateways.