Task and Server Assignment for Reduction of Energy Consumption in Datacenters

Abstract

Energy consumption of cloud data centers accounts for a major operational cost. This paper presents an optimization model for task scheduling to minimize task processing time and energy consumption in data centers for cloud computing. We formulate an integer programming optimization problem to minimize the expected energy consumption of homogenous tasks in a data center with a large number of servers and propose the most-efficient-server first greedy task scheduling algorithm to minimize energy expenditure. We show that the proposed task scheduling can minimize the energy expenditure while bounding the average task waiting time. We present a simulation of the proposed task scheduling scheme to show an optimum number of servers to achieve small task processing times and to minimize energy consumption.