Logo image
Energy and Locational Workload Management in Data Centers
Conference proceeding

Energy and Locational Workload Management in Data Centers

Sabrina Spatari, Nagarajan Kandasamy, Dara Kusic, Eugenia V. Ellis and IEEE
2011 IEEE INTERNATIONAL SYMPOSIUM ON SUSTAINABLE SYSTEMS AND TECHNOLOGY (ISSST)
01 Jan 2011

Abstract

Computer Science Computer Science, Theory & Methods Engineering Engineering, Electrical & Electronic Science & Technology Technology
Data centers are growing consumers of energy and emitters of greenhouse gases (GHG) worldwide. This paper examines data center power and locational workload management as strategies for energy savings and GHG emissions reduction. The case study examined focuses on GHG emissions from the electricity grid supply in a controlled small-scale computer cluster experiment and location (Philadelphia, PA). Virtualization is a technique that consolidates multiple online services onto fewer computing resources within a data center and deploys computing resources only as needed. The method can be applied not only within a data center, but also among multiple data centers in different locations, thereby taking advantage of deploying data centers that are linked to "low-carbon" electricity grids. Understanding the interaction between data center location and real time power consumption is critical to optimizing computer cluster usage, since demand during certain times of the day may rely on coal as the marginal source. Using the power savings results generated from the virtualization experiments performed on a small computer cluster at Drexel University, and power supply from the electricity grid serving the data center over a 24-hour day during a peak electricity summer month, we examine the time of day for shifting data center workloads in order to minimize GHG emissions.

Metrics

11 Record Views
1 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being
#11 Sustainable Cities and Communities

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
Web of Science research areas
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Logo image