As modern data centers continue to grow in power, size, and numbers, there is an urgent need to reduce energy consumption by optimized cooling strategies. In this paper, we present a neural network-based prediction of air flow in a data center that is cooled through perforated floor tiles. With a significantly smaller execution time than computational fluid dynamics, it predicts in real-time server inlet temperatures and can detect whether prevalent air flow cools the servers sufficiently to guarantee safe operation. Combined with a cooling system model, we obtain a temperature and air flow control algorithm that is fast and accurate enough to find an optimal operating point of the data center cooling system in real-time. We also demonstrate the performance of our algorithm on a reference data center and show that energy consumption can be reduced by up to 30%.

References

1.
Koomey
,
J.
, 2007, “
Estimating Total Power Consumption by Servers in the US and the World
,” Lawrence Berkeley National Laboratory Technical Report.
2.
EPA, 2007, “
Report to Congress on Server and Data Center Energy Efficiency Public Law 109-431
,” US Environmental Protection Agency, ENERGY STAR Program, Technical Report.
3.
Greenberg
,
S.
,
Tschudi
,
B.
,
Rumsey
,
P.
, and
Myatt
,
B.
, 2006, “
Best Practices for Data Centers: Lessons Learned From Benchmarking 22 Data Centers. ACEEE Summer Study on Energy Efficiency in Buildings
,” Lawrence Berkeley National Laboratory, Technical Report.
4.
Rasmussen
,
N.
, 2006, “
Electrical Efficiency Modeling for Data Centers
,” American Power Conversion, Technical Report.
5.
Tschudi
,
W.
,
Mills
,
E.
,
Greenberg
,
S.
, and
Rumsey
,
P.
, 2006, “
Data-Center Energy Use, Heating, Piping, Air-conditioning (HPAC) Engineering
, Technical Report.
6.
Hamann
,
H. F.
,
van Kessel
,
T. G.
,
Iyengar
,
M.
,
Chung
,
J.-Y.
,
Hirt
,
W.
,
Schappert
,
M. A.
,
Claassen
,
A.
,
Cook
,
J. M.
,
Min
,
W.
,
Amemiya
,
Y.
,
Lopez
,
V.
,
Lacey
,
J. A.
, and
O’Boyle
,
M.
, 2009, “
Uncovering Energy-Efficiency Opportunities in Data Centers
,”
IBM J. Res. Dev.
,
53
(
3
), pp.
10:1
10:12
.
7.
Patel
,
C. D.
,
Bash
,
C. E.
, and
Belady
,
C.
, 2001,
Computational Fluid Dynamics Modeling of High Compute Density Data Centers
,
Proceedings of IPACK
.
8.
Samadiani
,
E.
, and
Joshi
,
Y.
, 2010, “
Multi-Parameter Model Reduction in Multi-Scale Convective Systems
,”
Int. J. Heat Mass Transfer
,
53
, pp.
2193
2205
.
9.
Sharma
,
R. K.
,
Bash
,
C. E.
,
Patel
,
C. D.
,
Friedrich
,
R. J.
, and
Chase
,
J. S.
, 2005, “
Balance of Power: Dynamic Thermal Management for Internet Data Centers
,”
IEEE Internet Comput.
,
9
, pp.
42
49
.
10.
Biller
,
P.
,
Chevillat
,
P.
,
de Lorenzi
,
F.
,
Scherer
,
T.
,
Schott
,
W.
,
Ullmann
,
R.
, and
Vömel
,
C.
, 2011, “
Efficient Cooling of Data Centers
,”
Proceedings of the World Engineering Conference
.
11.
SPX, 1982, “
The Application of Cooling Towers for Free Cooling
,” SPX Cooling Technologies, Inc., Technical Report No. H-002.
12.
Weatherzh, 2011, “
Temperature data for Zurich Region
,” http://www.wetter-bassersdorf.ch/
13.
Rambo
,
J.
, and
Joshi
,
Y.
, 2007, “
Modeling of Data Center Airflow and Heat Transfer: State
,”
Distributed and Parallel Databases
,
21
, pp.
193
225
.
14.
Schmidt
,
R. R.
,
Karki
,
K. C.
,
Kelkar
,
K. M.
,
Radmehr
,
A.
, and
Patankar
,
S. V.
, 2001, “
Measurements and Predictions of the Flow Distribution Through Perforated Tiles in Raised-Floor Data Centers
,” Proceedings IPACK2001-15728.
15.
Ansys, 2010, Ansys CFX Solver Theory Guide.
16.
Hamann
,
H. F.
,
Lacey
,
J. A.
,
OBoyle
,
M.
,
Schmidt
,
R. R.
, and
Iyengar
,
M.
, 2008, “
Rapid Three-Dimensional Thermal Characterization of Large-Scale Computing Facilities
,”
IEEE Trans. Compon. Packag. Technol.
,
31
, pp.
444
448
.
17.
Design Considerations for Datacom Equipment Centers,”
American Society of Heating, Refrigerating and Air-Conditioning Engineers, 2008. Available at: http://tc99.ashraetcs.org/documents/ASHRAE_Extended_Environmental_Envelope_Final_Aug_1_2008.pdf
18.
Tang
,
Q.
,
Mukherjee
,
T.
,
Gupta
,
S. K. S.
, and
Cayton
,
P.
, 2006, “
Sensor-Based Fast Thermal Evaluation Model For Energy Efficient High-Performance Datacenters
,”
Proceedings of the Fourth International Conference on Intelligent Sensing and Information Processing (ICISIP)
.
19.
Moore
,
J.
, 2006, “
Automated Cost-Aware Data Center Management
,” Ph.D. thesis, Department of Computer Science, Duke University.
20.
Moore
,
J.
,
Chase
,
J.
,
Farkas
,
K.
, and
Ranganathan
,
P.
, 2005, “
Data Center Workload Monitoring, Analysis, and Emulation
,”
Proceedings of the Eighth Workshop on Computer Architecture Evaluation Using Commercial Workloads
.
21.
Shrivastava
,
S. K.
,
VanGilder
,
J. W.
, and
Sammakia
,
B. G.
, 2007, “
Data Center Cooling Prediction Using Artificial Neural Network
,”
ASME Conference Proceedings
, pp.
765
771
.
22.
Rumelhart
,
D.
,
Hintont
,
G.
, and
Williams
,
R.
, 1986, “
Learning Representations by Back-Propagating Errors
,”
Nature (London)
,
323
(
6088
), pp.
533
536
.
23.
Werbos
,
P. J.
, 1974, “
Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences
,” Ph.D. thesis, Harvard University, Cambridge, MA.
24.
Bryson
,
E.
, and
Ho
,
Y. C.
, 1969,
Applied Optimal Control: Optimization, Estimation, and Control
,
Blaisdell Publishing Company
,
New York
.
25.
LeCun
,
Y.
,
Bottou
,
L.
,
Orr
,
G.
, and
Muller
,
K.
, 1998, “
Efficient backprop
,”
Neural Networks: Tricks of the Trade
,
G.
Orr
and
M. K.
, eds.,
Springer
,
New York
.
26.
Tetko
,
I. V.
,
Livingstone
,
D. J.
, and
Luik
,
A. I.
, 1995, “
Neural Network Studies. 1. Comparison of Overfitting and Overtraining
,”
J. Chem. Inf. Comput. Sci.
,
35
(
5
), pp.
826
833
.
You do not currently have access to this content.