Title :
A Simplified Method of Measurement of Energy Consumption in Cloud and Virtualized Environment
Author :
Murwantara, I. Made ; Bordbar, Behzad
Author_Institution :
Sch. of Comput. Sci., Univ. of Birmingham, Birmingham, UK
Abstract :
Measuring energy consumption is an essential step in the development of policies for the management of energy in every IT system. There is a wide range of methods using both hardware and software for measuring energy consumed by the system accurately. However, most of these methods measure energy consumed by a machine or a cluster of machines. In environments such as Cloud that an application can be built from components with comparable characteristics, measuring energy consumed by a single component can be extremely beneficial. For example, if we can measure energy consumed by different HTTP servers, then we can establish which one consumes less energy performing a given task. As a result, the Cloud provider can provide incentives, so that, application developers use the HTTP server that consume less energy. Indeed, considering size of the Cloud, even a small amount of saving per Virtual Machine can add up to a substantial saving. In this paper, we propose a technique to measure energy consumed by an application via measuring energy consumed by the individual processes of the application. We shall deal with applications that run in a virtualized environment such as Cloud. We present two implementations of our idea to demonstrate the feasibility of the approach. Firstly, a method of measurement with the help of Kernel-Based Virtual Machine running on a typical laptop is presented. Secondly, in a commercial Cloud such as Elastic host, we describe a method of measuring energy consumed by processes such as HTTP servers. This will allow commercial providers to identify which product consumes less energy on their platform.
Keywords :
cloud computing; power aware computing; power consumption; software metrics; virtual machines; virtualisation; HTTP servers; IT system; cloud environment; elastic host; energy consumption measurement; energy management; kernel-based virtual machine; virtualized environment; Energy consumption; Energy measurement; Portable computers; Power measurement; Servers; Software; Software measurement; cloud; energy; virtual machine;
Conference_Titel :
Big Data and Cloud Computing (BdCloud), 2014 IEEE Fourth International Conference on
Conference_Location :
Sydney, NSW
DOI :
10.1109/BDCloud.2014.47