Term of Award

Spring 2015

Degree Name

Master of Science in Applied Engineering (M.S.A.E.)

Document Type and Release Option

Thesis (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Department of Electrical Engineering

Committee Chair

Christopher Kadlec

Committee Member 1

John O'Malley

Committee Member 2

Russell Thackston

Abstract

Abstract

Information Technology, as an industry, is growing very quickly to keep pace with increased data storage and computing needs. Data growth, if not planned or managed correctly, can have larger efficiency implications on your data center as a whole. The long term reduction in efficiency will increase costs over time and increase operational overhead. Similarly, increases in processor efficiency have led to increased system density in data centers. This can increase cost and operational overhead in your data center infrastructure.

This paper proposes the idea that balanced data center workloads are more efficient in comparison to similar levels of data center workloads that are not balanced across the data center facility. Identifying and documenting this effect would enable system architects to better plan data center system expansions and migrations effectively, while keeping in mind the total cost of the data center facility.

I conducted a scale experiment of data center heat job placement and collected data during multiple data runs. The scale experiment apparatus will allow the researchers to directly control the utilization of servers at all times while collecting data. Data collected will include processor utilization as well as the temperatures of both the hot and cold aisles during the entirety of the experimental procedure.

The experimental research hopes to show that the balanced workload has a positive effect on the temperature difference observed across the hot and cold aisle for the balanced workload tests. A rise in temperature difference would support the conclusion that is proposed by this research.

Share

COinS