ENERGY EFFICIENT SCHEDULING OF REAL-TIME TASKS FOR CLOUD APPLICATION USING DVFS

Abstract

Cloud computing is a modern technology which contains a network of systems that form a cloud. Energy conservation is one of the major concern in cloud computing. Large amount of energy is wasted by the computers and other devices and the carbon dioxide (CO2) gas is released into the atmosphere polluting the environment. Green computing is an emerging technology which focuses on preserving the environment by reducing various kinds of pollutions. Pollutions include excessive emission of greenhouse gas, disposal of e-waste and so on leading to greenhouse effect. So pollution needs to be reduced by lowering the energy usage. By doing this, utilization of resources should be increased and with less usage of energy, maximum resource utilization should be possible. To accomplish this purpose, many green task scheduling algorithms are used so that the energy consumption can be minimized in servers of cloud data centers. The growth of energy consumption has been explosive in current data centers, super computers, and public cloud systems. Reports estimate the energy consumptions of these data centers to be between 1.1% and 1.5% of the worldwide electricity consumption. This explosion has led to greater advocacy of green computing, and many efforts and works focus on the task scheduling in order to reduce energy dissipation. While most researchers have focused on reducing energy consumption of cloud data centers via server consolidation, we propose an approach for reducing the power required to execute real-time tasks. Energy efficient task scheduling is an effective technique to decrease the energy consumption in the Cloud Computing Systems. It exploits intelligent scheduling combined with the Dynamic Voltage and Frequency Scaling (DVFS) capability of modern CPU processors to keep the CPU operating at the minimized frequency level (and consequently minimizing power consumption) that enables the application to complete before a user-defined deadline. In this thesis we proposed scheduling algorithm is to dynamically scale the frequency of CPUs assigned to a virtual machine in such a way that tasks sequentially executed in the VM complete before their deadlines. In a cloud environment, hardware is shared among VMs. It means that the energy consumption of a host is not determined by a single VM, but by the combined state of all the VMs. Furthermore, when scheduling a task, the physical location of v the VM can be taken into consideration, in such a way that requests are preferentially submitted to VMs whose host is already in use (i.e., other VMs in the same host are already executing tasks). This enables the system to consolidate the load whenever possible. This in turns helps in reducing the total energy consumption of the infrastructure, as it enables unused hosts to be suspended or kept in low power states. Experiments demonstrate that our approach reduces energy consumption as we promising.