Issue |
EPJ Web of Conferences
Volume 25, 2012
EFM11 – Experimental Fluid Mechanics 2011
|
|
---|---|---|
Article Number | 01051 | |
Number of page(s) | 15 | |
Section | Experimental Fluid Mechanics 2011 | |
DOI | https://doi.org/10.1051/epjconf/20122501051 | |
Published online | 16 April 2012 |
https://doi.org/10.1051/epjconf/20122501051
Investigation of flow in data rack
1
Czech Technical University in Prague, Faculty of Mechanical Engineering, Technická 4, Praha 6, 166 07, Czech Republic
lukas.manoch@fs.cvut.cz. ; jiri.nozicka@fs.cvut.cz.
2
CONTEG, spol. s.r.o., Na Vítězné pláni 1719/4, Praha 4, 140 00, Czech Republic
p.pohan@conteg.cz.
The main purpose of this paper was to set up a functioning numerical model of data rack verified by an experimental measurement. The verification of the numerical model was carried out by means of the PIV method (Particle Image Velocimetry). The numerical model was "found" while using the assumed and preset values from the experimental measurement which represent boundary conditions. The server model was conceived as a four-channel with a controlled flow rate without simulation of heat transfer. The flow rate in each channel was implemented by means of pressure loss. The numerical model was further used for simulation of several phases and configurations of data rack (21U rack space) fitted with two server workstations Dell Precision R5400. The flow field in the inlet of data rack in the front of the workstations were observed and evaluated in such a way that a 2U-dimensional free space between the workstations was being left and the remaining inlet space was blanked-off/fully opened. The results of this paper will serve for designing optimization treatment of data rack from the viewpoint of cooling efficiency both within the data rack and within the data center design.
© Owned by the authors, published by EDP Sciences, 2012
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.