Neural network-based prediction and control of air flow in a data center

De Lorenzi, Flavio; Vömel, Christof

doi:10.1115/1.4005605

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Neural network-based prediction and control of air flow in a data center
Authors:	De Lorenzi, Flavio Vömel, Christof
DOI:	10.1115/1.4005605
Published in:	Journal of Thermal Science and Engineering Applications
Volume(Issue):	4
Issue:	2
Page(s):	021005
Issue Date:	2012
Publisher / Ed. Institution:	The American Society of Mechanical Engineers
ISSN:	1948-5085 1948-5093
Language:	English
Subject (DDC):	690: Building and construction
Abstract:	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%.
URI:	https://digitalcollection.zhaw.ch/handle/11475/13434
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Applied Mathematics and Physics (IAMP)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

De Lorenzi, F., & Vömel, C. (2012). Neural network-based prediction and control of air flow in a data center. Journal of Thermal Science and Engineering Applications, 4(2), 21005. https://doi.org/10.1115/1.4005605

De Lorenzi, F. and Vömel, C. (2012) ‘Neural network-based prediction and control of air flow in a data center’, Journal of Thermal Science and Engineering Applications, 4(2), p. 021005. Available at: https://doi.org/10.1115/1.4005605.

F. De Lorenzi and C. Vömel, “Neural network-based prediction and control of air flow in a data center,” Journal of Thermal Science and Engineering Applications, vol. 4, no. 2, p. 021005, 2012, doi: 10.1115/1.4005605.

DE LORENZI, Flavio und Christof VÖMEL, 2012. Neural network-based prediction and control of air flow in a data center. Journal of Thermal Science and Engineering Applications. 2012. Bd. 4, Nr. 2, S. 021005. DOI 10.1115/1.4005605

De Lorenzi, Flavio, and Christof Vömel. 2012. “Neural Network-Based Prediction and Control of Air Flow in a Data Center.” Journal of Thermal Science and Engineering Applications 4 (2): 21005. https://doi.org/10.1115/1.4005605.

De Lorenzi, Flavio, and Christof Vömel. “Neural Network-Based Prediction and Control of Air Flow in a Data Center.” Journal of Thermal Science and Engineering Applications, vol. 4, no. 2, 2012, p. 21005, https://doi.org/10.1115/1.4005605.