The Container Scheduling Method Based on the Min-Min in Edge Computing

Abstract

With the rapid development of the Internet of Things (IoT), the number of edge devices grows exponentially. Recently, Edge computing and edge cloud data center have been proposed to solve some problem, such as delay, Quality of Service (QoS), energy consumption. Similar to the cloud data center, the edge data center will generate a lot of energy consumption. There is a large amount of literature researched the problem of cloud data center, but less focus on energy problem of the forefront file, edge data center. In order to reduce energy consumption in the edge data center, we designed a target function for physical machine's energy consumption in heterogeneous edge data center and proposed a container scheduling method based on the Min-Min. According to the target function, each container is placed on the physical machine with the least increase in energy consumption. Meanwhile, we specially hypothesis the happening by considering their resource utilization balance when the estimated minimum energy consumption is the same. The simulation results show that the proposed container scheduling method reduced the energy consumption generated by the physical machine hosting container up to 56.7% compared with the FirstFit.