Container Live Migration for Latency Critical Industrial Applications on Edge Computing

摘要

A new level of factory automation demands processing vast amounts of data, complex orchestration of cyberphysical systems, and coordination of computation as well as communication resources in real-time. Virtualization and decentralized computation is becoming a de-facto solution for factory automation. Edge Computing (EC) is a promising approach to achieve the low latencies required by many industrial systems. It employs resource rich edge servers distributed within a factory that are placed close to end devices and assist them in executing computation intensive tasks and also in coordinating with each other. This paper discusses the requirements and challenges of EC for factory automation applications. In a distributed EC infrastructure, safe and timely operation of industrial applications require load balancing and mobility support and thus a seamless service migration between the edge servers. With the recent advances in virtualization and due to its advantages, virtual machine (VM) and container technologies are pavings its way into factory. Though containers have some distinctive advantages over VMs in EC, the service live migration has comparatively high downtime. This paper proposes a novel live migration scheme called redundancy migration that reduces the downtime by a factor of 1.8 compared to the stock migration in linux containers.