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%.
Skip Nav Destination
Article navigation
June 2012
Research Papers
Neural Network-Based Prediction and Control of Air Flow in a Data Center
Flavio de Lorenzi,
Flavio de Lorenzi
Zurich University of Applied Sciences
, ZHAW, CH-8401 Winterthur,Switzerland
Search for other works by this author on:
Christof Vömel
Christof Vömel
Zurich University of Applied Sciences
, ZHAW, CH-8401 Winterthur,Switzerland
Search for other works by this author on:
Flavio de Lorenzi
Zurich University of Applied Sciences
, ZHAW, CH-8401 Winterthur,Switzerland
Christof Vömel
Zurich University of Applied Sciences
, ZHAW, CH-8401 Winterthur,Switzerland
J. Thermal Sci. Eng. Appl. Jun 2012, 4(2): 021005 (8 pages)
Published Online: April 16, 2012
Article history
Received:
August 30, 2011
Accepted:
November 7, 2011
Online:
April 16, 2012
Published:
April 16, 2012
Citation
de Lorenzi, F., and Vömel, C. (April 16, 2012). "Neural Network-Based Prediction and Control of Air Flow in a Data Center." ASME. J. Thermal Sci. Eng. Appl. June 2012; 4(2): 021005. https://doi.org/10.1115/1.4005605
Download citation file:
Get Email Alerts
Cited By
Variable Thermal Conductivity Metamaterials Applied to Passive Thermal Control of Satellites
J. Thermal Sci. Eng. Appl (December 2023)
Numerical investigation of the heat transfer characteristics of liquid lithium metal in spiral tubes
J. Thermal Sci. Eng. Appl
Experimental and numerical investigations on flexible paraffin/fiber composite phase change material
J. Thermal Sci. Eng. Appl
Related Articles
A Simulation-Based Approach to Data Center Thermal Efficiency Optimization
J. Eng. Sustain. Bldgs. Cities (February,2020)
Experimental and Computational Investigations of the Thermal Environment in a Small Operational Data Center for Potential Energy Efficiency Improvements
J. Electron. Packag (September,2020)
Experimental and Numerical Analysis of Data Center Pressure and Flow Fields Induced by Backward and Forward CRAH Technology
J. Electron. Packag (September,2022)
Data Center Housing High Performance Supercomputer Cluster: Above Floor Thermal Measurements Compared To CFD Analysis
J. Electron. Packag (June,2010)
Related Proceedings Papers
Related Chapters
Fans and Air Handling Systems
Thermal Management of Telecommunications Equipment
Energy Consumption Forecasting in Taiwan Based on ARIMA and Artificial Neural Networks Models
International Conference on Advanced Computer Theory and Engineering, 4th (ICACTE 2011)