0
Research Papers

Numerical and Experimental Study of the Effect of Underfloor Blockages on Data Center Performance

[+] Author and Article Information
Siddharth Bhopte, Bahgat Sammakia

 Binghamton University, Binghamton, NY 13902

Madhusudan Iyengar, Roger Schmidt

 IBM Corporation, Poughkeepsie, NY 12601

J. Electron. Packag 133(1), 011007 (Mar 09, 2011) (7 pages) doi:10.1115/1.4003603 History: Received October 13, 2009; Revised December 02, 2010; Published March 09, 2011; Online March 09, 2011

Due to the increase in computer rack equipment power in recent years, thermal management of data centers has become a challenging problem. Data center facilities with raised floor plenums are the most popular configuration from a thermal management perspective. Considerable ongoing research efforts focus on optimizing the room layouts and equipment design in order to achieve the desired cooling. However, the detrimental impact of underfloor blockages, which occur widely, is seldom addressed. These blockages often take the form of chiller pipes, cabling, and wires. They impede the flow of cold air from the air conditioning units and yield unpredictable and undesirable air flow patterns. In this paper the effect of such underfloor blockages on data center performance is characterized in detail. A representative data center is modeled using a commercial computational fluid dynamics code with typical underfloor blockages. Blockages are shown to have a significant impact on tile flow rates and rack inlet temperatures. Based on the detailed numerical study broad guidelines are presented on managing the underfloor blockages for improved data center performance. Established guidelines are experimentally validated on a different data center cell. A detailed comparison between the experimental and numerical results is presented. Based on the numerical and experimental study it is concluded that blockages if placed in “critical” path can potentially have a detrimental impact on data center performance. Case studies are presented where blockages in “safe” path will have a minimum effect on data center performance.

Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

A typical raised floor data center with alternating hot and cold aisle arrangements (1)

Grahic Jump Location
Figure 2

(a) Magnified view of pipes that circulate coolant to and from A/C units. (b) Chiller pipes running under the floor tiles.

Grahic Jump Location
Figure 3

(a) Plan view of rack layout of data center. (b) Blower and system characteristics curves given by vendor (2-7).

Grahic Jump Location
Figure 4

(a) Temperature contours for the baseline case at a height of 1.8 m above the raised floor. (b) Pressure contours for the baseline case at 0.5 m plenum depth (0.1 m below perforated tiles).

Grahic Jump Location
Figure 5

Plan view of the data center highlighting critical and safe flow paths

Grahic Jump Location
Figure 6

(a) Parallel pipes in critical flow path. (b) Perpendicular pipes in critical flow path.

Grahic Jump Location
Figure 7

Colors showing two parametric locations for one pair of perpendicular chiller pipes

Grahic Jump Location
Figure 8

Pressure contours for perpendicular pipes in the critical path

Grahic Jump Location
Figure 9

Thermal performance comparison for perpendicular piping pattern

Grahic Jump Location
Figure 10

Tile flow rates for baseline case and safe perpendicular blockage case

Grahic Jump Location
Figure 11

(a) Recommended parallel chiller piping pattern. (b) Recommended perpendicular chiller piping pattern.

Grahic Jump Location
Figure 12

Example of a complex data center room with highlighted critical paths and possible safe piping pattern

Grahic Jump Location
Figure 13

Examples of cluster of cables and wires lying carelessly under the rack

Grahic Jump Location
Figure 14

Plenum color code demonstrating broad guidelines on managing underfloor blockages for improved data center performance

Grahic Jump Location
Figure 15

Test facility at Poughkeepsie, NY

Grahic Jump Location
Figure 16

Two tile designs 16% open (left) and 30% open (right) are used during the measurements (6)

Grahic Jump Location
Figure 17

Alnor velometer used for the measurement of air flow rates through the perforated tiles (3,6-8)

Grahic Jump Location
Figure 18

Layout with six 16% open (R1–R6) supply tiles. Seven 30% open tiles (T1–T7) are located between CRAC and supply tiles. Behind CRAC are five fully open tiles (O1–O5).

Grahic Jump Location
Figure 19

Safe and critical paths under plenum for the layout

Grahic Jump Location
Figure 20

(a) Comparison between numerical and experimental values when the numerical model has idealized plenum (no underfloor blockages are included). (b) Comparison between numerical and experimental values when the numerical model includes underfloor blockages in plenum.

Grahic Jump Location
Figure 21

Flexible plastic pipes, similar to CRAC pipes, are additionally installed alternately in critical and safe flow paths (3,6)

Grahic Jump Location
Figure 22

Layout showing additional blockages in critical (behind tile T1–T7) path and safe path (near the right wall of the room)

Grahic Jump Location
Figure 23

(a) Comparison between experimental and numerical results for Layout 1 with no additional blockage. (b) Comparison between experimental and numerical results for Layout 1 with additional blockage in critical flow path. (c) Comparison between experimental and numerical results for Layout 1 with additional blockage in safe flow path.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In