Design and Implementation of Cloud Docker Application Architecture Based on Machine Learning in Container Management for Smart Manufacturing
Byoung Soo Kim, Sang Hyeop Lee, Ye Rim Lee, Yong Hyun Park, Jongpil Jeong
Abstract
Manufacturers are expanding their business-process innovation and customized manufacturing to reduce their information technology costs and increase their operational efficiency. Large companies are building enterprise-wide hybrid cloud platforms to further accelerate their digital transformation. Many companies are also introducing container virtualization technology to maximize their cloud transition and cloud benefits. However, small- and mid-sized manufacturers are struggling with their digital transformation owing to technological barriers. Herein, for small- and medium-sized manufacturing enterprises transitioning onto the cloud, we introduce a Docker Container application architecture, a customized container-based defect inspection machine-learning model for the AWS cloud environment developed for use in small manufacturing plants. By linking with open-source software, the development was improved and a datadog-based container monitoring system, built to enable real-time anomaly detection, was implemented.