Bulletin of the American Physical Society
71st Annual Meeting of the APS Division of Fluid Dynamics
Volume 63, Number 13
Sunday–Tuesday, November 18–20, 2018; Atlanta, Georgia
Session G32: Machine Learning and Data Driven Models II
10:35 AM–12:45 PM,
Monday, November 19, 2018
Georgia World Congress Center
Room: B404
Chair: Alireza Yazdani, Brown University
Abstract ID: BAPS.2018.DFD.G32.4
Abstract: G32.00004 : CFD simulations of a data center to train an artificial neural network model*
11:14 AM–11:27 AM
Presenter:
Jayati Athavale
(Georgia Institute of Technology)
Authors:
Jayati Athavale
(Georgia Institute of Technology)
Minami Yoda
(Georgia Institute of Technology)
Yogendra Kumar Joshi
(Georgia Institute of Technology)
Data centers, large facilities that host computing and networking equipment for dealing with large volumes of data, are the physical manifestation of the “cloud.” This study presents an experimentally validated room-level computational fluid dynamics (CFD) simulation of a raised-floor data center configuration consisting of one cold aisle with six racks on each side, and three computer room air conditioning units around the room periphery. Predictions from the finite-volume software package Future Facilities 6SigmaDCX, employing a pressure-based solver, are in good agreement with experimental measurements of total air flow rate and rack inlet temperatures, with average discrepancies less than 4% and 1.7 °C, respectively. The numerical predictions using this approach over a variety of operating conditions are used to train an artificial neural network (ANN)-based model to predict temperature and airflow distributions in near real time. The ANN model, with its rapid prediction capability, can then be used to develop a control framework to minimize power consumption in data centers, which accounts for more than 2% of total American electricity consumption.
*Supported by the NSF Industry/University Cooperative Research Center on Energy Smart Electronic Systems (ES2)
To cite this abstract, use the following reference: http://meetings.aps.org/link/BAPS.2018.DFD.G32.4
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2025 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700