Research Papers

Effectiveness of Rack-Level Fans—Part I: Energy Savings Through Consolidation

[+] Author and Article Information
Richard Eiland

Mechanical and Aerospace Engineering Department,
University of Texas at Arlington,
P.O. Box 19023,
Arlington, TX 76013
e-mail: richard.eiland@mavs.uta.edu

John Edward Fernandes

Mechanical and Aerospace Engineering Department,
University of Texas at Arlington,
P.O. Box 19023,
Arlington, TX 76013
e-mail: john.fernandes@mavs.uta.edu

Bharath Nagendran

Amazon Lab 126,
Thermal Engineer,
Enterprise Way,
Sunnyvale, CA 94089
e-mail: bhanagen@amazon.com

Veerendra Mulay

Facebook Inc.,
Senior R&D Engineer,
Menlo Park, CA 425081
e-mail: vmulay@fb.com

Dereje Agonafer

Fellow ASME
Mechanical and Aerospace Engineering Department,
University of Texas at Arlington,
P.O. Box 19023,
Arlington, TX 76013
e-mail: agonafer@uta.edu

1Corresponding author.

Contributed by the Electronic and Photonic Packaging Division of ASME for publication in the JOURNAL OF ELECTRONIC PACKAGING. Manuscript received February 16, 2017; final manuscript received October 10, 2017; published online October 27, 2017. Assoc. Editor: Pradip Dutta.

J. Electron. Packag 139(4), 041011 (Oct 27, 2017) (7 pages) Paper No: EP-17-1021; doi: 10.1115/1.4038235 History: Received February 16, 2017; Revised October 10, 2017

In general, smaller fans operate at lower efficiencies than larger fans of proportional linear dimensions. In this work, the applicability of replacing smaller, 60 mm baseline fans from within the chassis of web servers with an array of larger, geometrically proportional 80 mm and 120 mm fans consolidated to the back of a rack is experimentally tested. Initial characterization of the selected fans showed that the larger fans operate at double peak total efficiency of the smaller fans. A stack of four servers were used in a laboratory setting to represent a rack of servers. When all four servers were stressed at uniform computational loadings, the 80 mm fans resulted in 50.1–52.6% reduction in total rack fan power compared to the baseline fans. The 120 mm fans showed similar reduction in rack fan power of 47.6–54.0% over the baseline. Since actual data centers rarely operate at uniform computational loading across servers in a rack, a worst case scenario test was conceived in which the array of larger fans were controlled by a single server operating at peak computational workload while the other three in the rack remained idle. Despite significant overcooling in the three idle servers, the 80 mm and 120 mm fan configurations still showed 35% and 34% reduction in total rack fan power compared to the baseline fans. The findings strongly suggest that a rack-level fan scheme in which servers share airflow from an array of consolidated larger fans is superior to traditional chassis fans.

Copyright © 2017 by ASME
Topics: Fans , Temperature
Your Session has timed out. Please sign back in to continue.


ASHRAE, 2012, “ IT Equipment Thermal Management and Controls,” American Society of Heating, Refrigerating and Air-Conditioning Engineers, Atlanta, GA, Document No. ASHRAE TC 9.9. https://tc0909.ashraetcs.org/documents/ASHRAE%202012%20IT%20Equipment%20Thermal%20Management%20and%20Controls_V1.0.pdf
Alkharabsheh, S. , Fernandes, J. , Gebrehiwot, B. , Agonafer, D. , Ghose, K. , Ortega, A. , Joshi, Y. , and Sammakia, B. , 2015, “ A Brief Overview of Recent Developments in Thermal Management in Data Centers,” ASME J. Electron. Packag., 137(4), p. 040801.
Strike, N. D. , 2015, “Fan Efficiency, an Increasingly Important Selection Criteria,” NMB Technologies Corporation, Tempe, AZ, accessed Jan. 21, 2015, http://www.nmbtc.com/fans/white-papers/fan_efficiency_important_selection_criteria/
Greenheck, 2013, “ Understanding Fan Efficiency Grades (FEG),” Greenheck Fan Corp, Schofield, WI, Report No. CS/104-13 http://www.greenheck.com/library/articles/88.
AMCA, 2010, “Energy Efficiency Classification for Fans,” American Movement and Control Association, Arlington Heights, IL, Standard No. 205. http://www.amca.org/feg/codes-and-standards.aspx#AMCA205
Holohan, M. F. , and Elison, B. P. , 2007, “Fan Laws for Rack Systems,” ASME Paper No. IPACK2007-33892.
Kodama, Y. , Itoh, S. , Shimizu, T. , Sekiguchi, S. , Nakamura, H. , and Mori, N. , 2013, “ Imbalance of CPU Temperatures in a Blade System and Its Impact for Power Consumption of Fans,” Cluster Comput., 16(1), pp. 27–37. [CrossRef]
Nagendran, B. , Nagaraj, S. , Fernandes, J. , Eiland, R. , Agonafer, D. , and Mulay, V. , 2014, “ Improving Cooling Efficiency of Servers by Replacing Smaller Chassis Enclosed Fans With Larger Rack-Mount Fans,” IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), Orlando, FL, May 27–30.
Frachtenberg, E. , Heydari, A. , Li, H. , Michael, A. , Na, J. , Nisbet, A. , and Sarti, P. , 2011, “ High-Efficiency Server Design,” International Conference for High Performance Computing, Networking, Storage, and, Analysis (SC), Seattle, WA, Nov. 12–18.
Li, H. , and Michael, A. , 2011, “Intel Motherboard Hardware v1.0,” Open Compute Project, accessed Nov. 22, 2015, http://opencompute.org/wp/wp-content/uploads/2011/07/Server-Intel-Motherboard-Specifications-v1.pdf
AMCA/ASHRAE, 2007, “ Laboratory Methods of Testing Fans for Certified Aerodynamic Performance Rating,” Air Movement and Control Association International, Inc./American Society of Heating, Refrigerating and Air Conditioning Engineers, Arlington Heights, IL/Atlanta, GA, ANSI/AMCA Standard No. 210-07, ANSI/ASHRAE Standard No. 51-2007. https://www.scribd.com/doc/125459372/Laboratory-Methods-of-Testing-Fans-for-Aerodynamic-Performance-Rating
Carraway, D. , 2013, “Lookbusy—A Synthetic Load Generator,” Version 1.4, accessed Oct. 23, 2017, http://www.devin.com/lookbusy
Skillern, R. , 2015, “Meet the Future of Data Center Rack Technologies,” Data Center Knowledge, San Francisco, CA, accessed Jan. 21, 2015, http://www.datacenterknowledge.com/archives/2013/02/20/meet-the-future-of-data-center-rack-technologies/


Grahic Jump Location
Fig. 1

Intel-based Open Compute server used for this study. The partition separates airflow of the motherboard fans from that of the power supply (PSU) fan air stream, simplifying the geometry for the analysis of this work.

Grahic Jump Location
Fig. 2

Depiction of the consolidation of fans to a shared array at the back of the rack

Grahic Jump Location
Fig. 3

Peak total efficiencies for the 60 mm, 80 mm, and 120 mm at their maximum fan speeds in the rack configuration

Grahic Jump Location
Fig. 4

Laboratory test setup of four servers stacked to represent a rack. Pertinent testing equipment is identified accordingly.

Grahic Jump Location
Fig. 5

Relation between total rack fan power and CPU die temperatures for each of the four servers when operated at uniform computational workloads of idle, 30%, and 98% CPU utilization in the baseline 60 mm fan configuration

Grahic Jump Location
Fig. 6

Location of the discrete system operating temperatures when the fans are internally controlled lie directly one the curve fit lines of the externally controlled tests across all computational loadings

Grahic Jump Location
Fig. 7

Comparison between cooling performance of 60 mm, 80 mm, and 120 mm fans at idle, 30%, and 98% CPU utilizations

Grahic Jump Location
Fig. 8

Depiction of (a) the “best case scenario” for the 60 mm fans in which all servers are operating at idle computational load and (b) the “worst case scenario” for the rack-level fans in which a single, high computationally loaded server dictates the speed of all the fans in the array



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