Energy Efficient Genetic Algorithm for Container Consolidation in Cloud System

Abstract

A lot of work has been done and extensive research is going on for reducing the energy consumption of large-scale cloud data centers along with the maximization of host level utilization. Because of on-demand service provisioning, the number of users’ requests increases which leads to an increase in the number of physical machines and data center size. This results in increased energy consumption in the data center as energy consumption is directly proportional to the number of the active physical machine. The container is a lightweight approach to operating system virtualization, offers an opportunity to improve the efficiency in cloud data centers. Containerized cloud gaining widespread popularity in recent years, so an efficient container consolidation is an open research challenge. Container consolidation is used to optimize energy consumption, as the resource utilization by the containers is directly relates to energy consumption. Container consolidation is an NP-Hard problem which can be solved by heuristic and metaheuristic algorithm. Therefore, in this paper, we implemented the heuristic and metaheuristic algorithm for energy reduction in the cloud. We implemented the next fit, best fit, best fit decreasing, first fit, first fit decreasing and compare their result. The experimental result shows that the best fit decreasing and first fit decreasing gave the almost same result. Further, this result is compared with the proposed Energy Efficient Genetic Algorithm(EEGA). We got the best result with the proposed EEGA.