Welcome to the InfoSci Platform
Reference Hub3
A Power Monitoring System Based on a Multi-Component Power Model

A Power Monitoring System Based on a Multi-Component Power Model

Weiwei Lin, Haoyu Wang, Wentai Wu
Copyright: © 2018 |Volume: 10 |Issue: 1 |Pages: 15
ISSN: 1938-0259|EISSN: 1938-0267|EISBN13: 9781522543367|DOI: 10.4018/IJGHPC.2018010102
Cite Article Cite Article

MLA

Lin, Weiwei, et al. "A Power Monitoring System Based on a Multi-Component Power Model." IJGHPC vol.10, no.1 2018: pp.16-30. http://doi.org/10.4018/IJGHPC.2018010102

APA

Lin, W., Wang, H., & Wu, W. (2018). A Power Monitoring System Based on a Multi-Component Power Model. International Journal of Grid and High Performance Computing (IJGHPC), 10(1), 16-30. http://doi.org/10.4018/IJGHPC.2018010102

Chicago

Lin, Weiwei, Haoyu Wang, and Wentai Wu. "A Power Monitoring System Based on a Multi-Component Power Model," International Journal of Grid and High Performance Computing (IJGHPC) 10, no.1: 16-30. http://doi.org/10.4018/IJGHPC.2018010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

As the increasing IT energy consumption emerged as a prominent issue, computer system energy consumption monitoring and optimization has gradually become a significant research forefront. However, most existing energy monitoring methods are limited to hardware-based measurement or coarse-grained energy consumption estimation. They cannot provide fine-grained energy consumption data (i.e., component energy consumption) and high-scalability for distributed cloud environments. In this article, the authors first study widely-used power models of CPUs, memory and hard disks. Then, following an investigation into disk power behaviors in sequential I/O and random I/O, they propose an improved I/O-mode aware disk power model with multiple variables and thresholds. They developed EnergyMeter, a monitoring software utility that can provide accurate power estimate by exploiting a multi-component power model. Experiments based on PCMark prove that the average error of EnergyMeter is merely 5% under a variety of workloads

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.