AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Building Simulation Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article

Hot spot temperature prediction and operating parameter estimation of racks in data center using machine learning algorithms based on simulation data

Xianzhong Chen1, Rang Tu1( ), Ming Li1, Xu Yang2, Kun Jia3
School of Civil and Resources Engineering, University of Science and Technology Beijing, Beijing 100083, China
School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
China Electronics Engineering Design Institute CO., LTD., Beijing 100142, China
Show Author Information

Abstract

In this paper, models to predict hot spot temperature and to estimate cooling air’s working parameters of racks in data centers were established using machine learning algorithms based on simulation data. First, simulation models of typical racks were established in computational fluid dynamics (CFD). The model was validated with field test results and results in literature, error of which was less than 3%. Then, the CFD model was used to simulate thermal environments of a typical rack considering different factors, such as servers’ power, which is from 3.3 kW to 20.1 kW, cooling air’s inlet velocity, which is from 1.0 m/s to 3.0 m/s, and cooling air’s inlet temperature, which is from 16 ℃ to 26 ℃. The highest temperature in the rack, also called hot spot temperature, was selected for each case. Next, a prediction model of hot spot temperature was built using machine learning algorithms, with servers’ power, cooling air’s inlet velocity and cooling air’s inlet temperature as inputs, and the hot spot temperatures as outputs. Finally, based on the prediction model, an operating parameters estimation model was established to recommend cooling air’s inlet temperatures and velocities, which can not only keep the hot spot temperature at the safety value, but are also energy saving.

Keywords

data centerCFD simulationhot spot temperaturemachine learning algorithmprediction and estimation models

Electronic Supplementary Material

Download File(s)
bs-16-11-2159_ESM.pdf (593.4 KB)

References

 

Ahmadi VE, Erden HS (2020). A parametric CFD study of computer room air handling bypass in air-cooled data centers. Applied Thermal Engineering, 166: 114685.
Crossref Google Scholar
 

Asgari S, MirhoseiniNejad S, Moazamigoodarzi H, et al. (2021a). A gray-box model for real-time transient temperature predictions in data centers. Applied Thermal Engineering, 185: 116319.
Crossref Google Scholar
 

Asgari S, Moazamigoodarzi H, Tsai PJ, et al. (2021b). Hybrid surrogate model for online temperature and pressure predictions in data centers. Future Generation Computer Systems, 114: 531–547.
Crossref Google Scholar
 
ASHRAE (2011). ASHRAE Thermal Guidelines for Data Processing Environments—Expanded Data Center Classes and Usage Guidance. Atlanta, GA, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.
 
ASHRAE (2015). Thermal Guideline for Liquid Cooled Data Processing Environments. Atlanta, GA, USA: American Society of Heating, Refrigerating and Air-Conditioning Engineers.
 

Athavale J, Yoda M, Joshi Y (2019). Comparison of data driven modeling approaches for temperature prediction in data centers. International Journal of Heat and Mass Transfer, 135: 1039–1052.
Crossref Google Scholar
 
Ban D (2019). Research on Energy-saving Control system of intelligent street lamp based on neural network. Master Thesis, University of Electronic Science and Technology of China. (in Chinese)
 

Chang Y, Niu W, Wang W (2009). Numerical simulation and flow analysis of labyrinth path of drip irrigation emitters. Journal of Northwest A & F University (Natural Science Edition), 37(2): 203–208. (in Chinese)
Google Scholar
 

Chen X, Tu R, Li M, et al. (2022). Prediction models of air outlet states of desiccant wheels using multiple regression and artificial neural network methods based on criterion numbers. Applied Thermal Engineering, 204: 117940.
Crossref Google Scholar
 

Chinese Association of Refrigeration (2021). China Data Center Cooling Technology Annual Development Research Report. Beijing: China Architecture and Building Press. (in Chinese)
 

Cho J, Woo J (2020). Development and experimental study of an independent row-based cooling system for improving thermal performance of a data center. Applied Thermal Engineering, 169: 114857.
Crossref Google Scholar
 

Fulpagare Y, Bhargav A, Joshi Y (2019). Dynamic thermal characterization of raised floor plenum data centers: Experiments and CFD. Journal of Building Engineering, 25: 100783.
Crossref Google Scholar
 

Gao C, Yu Z, Wu J (2013). Thermal environment analysis and air distribution optimization for a typical data room. Heating Ventilating & Air Conditioning, 43(9): 101–106. (in Chinese)
Google Scholar
 

Gao C, Yu Z, Wu J (2015). Investigation of airflow pattern of a typical data center by CFD simulation. Energy Procedia, 78: 2687–2693.
Crossref Google Scholar
 
Ge X (2021). Based on random forest regression algorithm of grass root period forecast system research. Master Thesis, Nanjing University of Information Science and Technology. (in Chinese)
 
Grand View Research (2019). Virtual Data Room Market Size & Share Report (2020–2027). Available at https://www.grandviewresearch.com/industry-analysis/virtual-data-room-market.
 

Hassan NMS, Khan MMK, Rasul MG (2013). Temperature monitoring and CFD analysis of data centre. Procedia Engineering, 56: 551–559.
Crossref Google Scholar
 

He Z, He Z, Zhang X, et al. (2016). Study of hot air recirculation and thermal management in data centers by using temperature rise distribution. Building Simulation, 9: 541–550.
Crossref Google Scholar
 

He Y, Schnabel MA, Mei Y (2020). A novel methodology for architectural wind environment study by integrating CFD simulation, multiple parametric tools and evaluation criteria. Building Simulation, 13: 609–625.
Crossref Google Scholar
 

Huang Z, Dong K, Sun Q, et al. (2017). Numerical simulation and comparative analysis of different airflow distributions in data centers. Procedia Engineering, 205: 2378–2385.
Crossref Google Scholar
 

Lee YT, Wen CY, Shih YC, et al. (2022). Numerical and experimental investigations on thermal management for data center with cold aisle containment configuration. Applied Energy, 307: 118213.
Crossref Google Scholar
 
Liu Y (2018). Application research of finite element model modification based on Gaussian Process Regression (GPR). Master Thesis, Nanchang University. (in Chinese)
 

Liu Y, Le DV, Tan R (2022). A data-assisted first-principle approach to modeling server outlet temperature in air free-cooled data centers. Future Generation Computer Systems, 129: 225–235.
Crossref Google Scholar
 

Meng X, Zhou J, Zhang X, et al. (2020). Optimization of the thermal environment of a small-scale data center in China. Energy, 196: 117080.
Crossref Google Scholar
 
MOHURD (2017). GB50174-2017: Data Center Design Code. Ministry of Housing and Urban-Rural Development of China. (in Chinese)
 

Park BR, Choi YJ, Choi EJ, et al. (2022). Adaptive control algorithm with a retraining technique to predict the optimal amount of chilled water in a data center cooling system. Journal of Building Engineering, 50: 104167.
Crossref Google Scholar
 

Qin B, Yang X, Ya T, et al. (2020). Research on air distribution of data center cold channel closed room based on thermal environment evaluation index. Heating Ventilating & Air Conditioning, 50(8): 123–128. (in Chinese)
Google Scholar
 
Rojas R (1996). Neural Networks: A Systematic Introduction. Berlin: Springer.
Crossref
 

Rumelhart D, McClelland J (1986). Parallel Distributed Processing. Cambridge, MA, USA: MIT Press.
Crossref
 

Saiyad A, Fulpagare Y, Bhargav A (2022). Comparison of detached eddy simulation and standard k-ε RANS model for rack-level airflow analysis inside a data center. Building Simulation, 15: 1595–1610.
Crossref Google Scholar
 

Su Z (2021). Design optimization and analysis of data rack inlet air temperature for an IDC center. Building Energy & Environment, 40(4): 55–59. (in Chinese)
Google Scholar
 
Sun D (2004). Research on classification and regression method of support vector machine. PhD Thesis, Central South University. (in Chinese)
 
Tian Y (2005). Support Vector Regression and its application. PhD Thesis, China Agricultural University. (in Chinese)
 
Tian H (2012). Research on cooling technology of high yield heat density data room. PhD Thesis, Tsinghua University. (in Chinese)
 
Tian J (2018). State estimation of urban water supply network based on regression tree. Master Thesis, North China University of Water Resources and Electric Power. (in Chinese)
 

Tian H, Liang H, Li Z (2019). A new mathematical model for multi-scale thermal management of data centers using entransy theory. Building Simulation, 12: 323–336.
Crossref Google Scholar
 
Wang N (2016). Numerical simulation and energy-saving optimization of thermal environment in data center. Master Thesis, Wuhan Institute of Technology. (in Chinese)
 

Wang R, Kuru E, Yan Y, et al. (2022). Sensitivity analysis of factors controlling the cement hot spot temperature and the corresponding well depth using a combined CFD simulation and machine learning approach. Journal of Petroleum Science and Engineering, 208: 109617.
Crossref Google Scholar
 

Wang S, Tu R, Chen X, et al. (2023). Thermal performance analyses and optimization of data center centralized-cooling system. Applied Thermal Engineering, 222: 119817.
Crossref Google Scholar
 

Watson B, Venkiteswaran VK (2017). Universal cooling of data centres: A CFD analysis. Energy Procedia, 142: 2711–2720.
Crossref Google Scholar
 

Xu L, Zhao T (2013). Comparative study on turbulence model based on hydraulic performance of emitter. Gansu Water Resources and Hydropower Technology, 49(05): 18–20. (in Chinese)
Google Scholar
 
Yang S (2020). Gaussian process regression method for functional data research and application. Master Thesis, Dalian University of Technology. (in Chinese)
 

Yuan S, Lu S (2015). Simulation research on airflow in data center under various supply air temperature. Low Temperature and Superconductivity, 43(10): 55-61. (in Chinese)
Google Scholar
 

Yuan X, Wang Y, Liu J, et al. (2018). Experimental and numerical study of airflow distribution optimisation in high-density data centre with flexible baffles. Building and Environment, 140: 128–139.
Crossref Google Scholar
 

Yuan X, Zhou X, Liu J, et al. (2019). Experimental and numerical investigation of an airflow management system in data center with lower-side terminal baffles for servers. Building and Environment, 155: 308–319.
Crossref Google Scholar
 

Yuan X, Xu X, Liu J, et al. (2020). Improvement in airflow and temperature distribution with an in-rack UFAD system at a high-density data center. Building and Environment, 168: 106495.
Crossref Google Scholar
 

Zapater M, Risco-Martín JL, Arroba P, et al. (2016). Runtime data center temperature prediction using Grammatical Evolution techniques. Applied Soft Computing, 49: 94–107.
Crossref Google Scholar
 

Zhang L, Zhang Q, Xu F, et al. (2002). Application and research of statistical analysis model based on classification regression tree (CART) method. Journal of Zhejiang University of Technology, 30(4): 315–318. (in Chinese)
Google Scholar
 
Zhu Y (2018). Numerical simulation and feasibility study of combined air supply in data center computer room. Master Thesis, Nanjing Normal University. (in Chinese)
Building Simulation
Volume 16 Issue 11,
November 2023
Pages 2159-2176
DOI: 10.1007/s12273-023-1022-4
Cite this article:
Chen X, Tu R, Li M, et al. Hot spot temperature prediction and operating parameter estimation of racks in data center using machine learning algorithms based on simulation data. Building Simulation, 2023, 16(11): 2159-2176. https://doi.org/10.1007/s12273-023-1022-4

441

Views

3

Crossref

4

Web of Science

4

Scopus

0

CSCD

Altmetrics
Received: 11 December 2022
Revised: 01 March 2023
Accepted: 22 March 2023
Published: 10 August 2023
© Tsinghua University Press 2023
Return