東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Design and CFD Analysis of a Tank So...

Khanvilkar, Siddhesh Manohar,

Linked to FindBook

Google Book

Amazon

博客來

Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers // Siddhesh Manohar Khanvilkar.
Author:	Khanvilkar, Siddhesh Manohar,
Description:	1 electronic resource (56 pages)
Notes:	Source: Masters Abstracts International, Volume: 83-01.
Contained By:	Masters Abstracts International83-01.
Subject:	Mechanical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28667649
ISBN:	9798516907524

Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers /
Khanvilkar, Siddhesh Manohar,

Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers /Siddhesh Manohar Khanvilkar. - 1 electronic resource (56 pages)

Source: Masters Abstracts International, Volume: 83-01.

The issue of thermal management of data centers is becoming even more challenging with increasing chip power densities. This has been primarily driven by increasing demands in artificial intelligence and machine learning-based applications, increased usage of cloud-based services, and high-performance computing. The development of these applications has led to a corresponding increment in high performance and high power density CPUs and GPUs. Liquid cooling technologies are outperforming the traditional air cooling approach in dissipating high heat fluxes. Out of these technologies, single-phase immersion cooling offers advantages like substantially lower PUE values, simplified data center infrastructure, ease of deployment for edge data centers, improved reliability, and even temperature profile on the servers. This study focuses on the development of a natural convection-based single-phase immersion cooling solution for edge data centers. Eight servers were immersed in a tank filled with mineral oil were analyzed using CFD. The tank is directly cooled with integrated heat exchanging plates to cool down the hot fluid. The inlet flow rate and temperatures of the coolant in the plates were varied to determine the optimal value of the required flow rate. The baseline results of the air-cooled heat sink were also compared with the improved heat sink better suited for natural convection. The CPU temperatures and the temperatures of auxiliary components on the motherboard were also analyzed. A pumping power comparison of the baseline case where the entire tank is cooled using forced convection was also performed.

English

ISBN: 9798516907524Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Cloud-based services

Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers /
LDR:03113nmm a22004333i 4500 001 2437009
005 20251119142623.5
006 m o d
007 cr|nu||||||||
008 261011s2021 miu||||||m |||||||eng d
020 $a 9798516907524
035 $a (MiAaPQD)AAI28667649
035 $a (MiAaPQD)2502vireo2414Khanvilkar
035 $a AAI28667649
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Khanvilkar, Siddhesh Manohar, $e author. $3 3827868
245 1 0 $a Design and CFD Analysis of a Tank Solution for Natural Convection Based Single-Phase Immersion Cooling of Servers / $c Siddhesh Manohar Khanvilkar.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 1 electronic resource (56 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-01.
500 $a Advisors: Agonafer, Dereje Committee members: Bozlar, Michael.
502 $b M.S.M.E. $c The University of Texas at Arlington $d 2021.
520 $a The issue of thermal management of data centers is becoming even more challenging with increasing chip power densities. This has been primarily driven by increasing demands in artificial intelligence and machine learning-based applications, increased usage of cloud-based services, and high-performance computing. The development of these applications has led to a corresponding increment in high performance and high power density CPUs and GPUs. Liquid cooling technologies are outperforming the traditional air cooling approach in dissipating high heat fluxes. Out of these technologies, single-phase immersion cooling offers advantages like substantially lower PUE values, simplified data center infrastructure, ease of deployment for edge data centers, improved reliability, and even temperature profile on the servers. This study focuses on the development of a natural convection-based single-phase immersion cooling solution for edge data centers. Eight servers were immersed in a tank filled with mineral oil were analyzed using CFD. The tank is directly cooled with integrated heat exchanging plates to cool down the hot fluid. The inlet flow rate and temperatures of the coolant in the plates were varied to determine the optimal value of the required flow rate. The baseline results of the air-cooled heat sink were also compared with the improved heat sink better suited for natural convection. The CPU temperatures and the temperatures of auxiliary components on the motherboard were also analyzed. A pumping power comparison of the baseline case where the entire tank is cooled using forced convection was also performed.
546 $a English
590 $a School code: 2502
650 4 $a Mechanical engineering. $3 649730
650 4 $a Packaging. $3 585030
650 4 $a Electrical engineering. $3 649834
653 $a Cloud-based services
653 $a Liquid cooling technologies
653 $a Heat fluxes
653 $a PUE values
690 $a 0548
690 $a 0544
690 $a 0549
710 2 $a The University of Texas at Arlington. $b Mechanical and Aerospace Engineering. $e degree granting institution. $3 3823781
720 1 $a Agonafer, Dereje $e degree supervisor.
773 0 $t Masters Abstracts International $g 83-01.
790 $a 2502
791 $a M.S.M.E.
792 $a 2021
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28667649