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
Pages: 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.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.