Energy Efficient Resource Scheduling through VM Consolidation in Cloud Computing

Abstract

In modern computing paradigms, energy consumption is of foremost importance because it constitutes a major percentage of the operational expenses. Virtual Machines (VMs) are consolidated on a fewer number of servers to significantly reduce the overall power consumption. The idle servers are then turned off by using Dynamic threshold Voltage Scaling (DTVS). The VM monitor checks for under-utilized, partially filled, over-utilized, and empty servers. The VM monitor then transfers the tasks to suitable servers for execution if subject to a set of constraints. As a result, many servers those were under-utilized get idle and are turned off by using DTVS to save power. Simulation results affirm our study and a substantial reduction is observed in the overall power consumption of the cloud data centers.