Game Theoretic Task Allocation to Reduce Energy Consumption in Containerized Cloud

Abstract

Cloud computing provides information technology based solutions to the end-users as a utility. Virtual machine or the virtualization technology is the backbone of implementing cloud computing technologies. However, such implementation encounters the problem of tremendous energy consumption. One of the foremost issues in implementing cloud computing is high energy consumption. This can be reduced to some extent by proper allocation and efficient utilization of resources. At present, containerization is one of the broadly discussed techniques as an alternative to traditional virtualization solutions. In this paper, we propose a game-theoretic approach for resource allocation and a containerized cloud architecture which drastically reduces energy consumption than a virtual machine based cloud. We have used Google cluster traces data set for our experiment in the cloud with virtual machine and containerized cloud. Experimental results show that the energy consumption is minimized in the containerized cloud than a cloud with virtual machines.