Growing demand for dense and high-performing IT compute capacity to support deep learning and artificial intelligence workloads necessitates data centers to look for more robust thermal management strategies. Today, data centers across the world are turning to liquid-based cooling solutions to keep up with the increased cooling demand for high power racks approaching 100kW of heat dissipation. Deploying direct-to-chip cold plate liquid cooling is one of the mainstream approaches which allows targeted cooling of high-power processors. This study provides the framework for a hybrid in row cooler (IRC) with liquid-to-air (L2A) heat exchanger (HX) system delivering chilled coolant to liquid-cooling cold plates mounted to the high heat dissipation electronics. This approach is useful for high heat density cooling of racks where no primary facility coolant is available at the data center. The present study aims to investigate the thermo-hydraulic performance of a distinct L2A IRC system that supplies cold secondary coolant (PG 25%) into the cooling loops of liquid-cooled servers in racks within an existing air-cooled data center. Thermal test vehicles (TTVs) are built to replicate actual high heat density servers. From the cold plate to data center level the proper choice of each level component was described based on their cooling performance and relevance. Three different cooling loop/rack designs are characterized experimentally, and detailed analytical and numerical (FNM) simulations are developed to analyze the heat exchanger performance. The FNM and CFD model of a data center are done in two steady and transient forms to study the performance of the L2A IRC in a data center.
Due to the surge in electronics power density, single-phase liquid cooling technologies are emerging to replace legacy air-cooling technologies. However, this surge in electronics power densities is accelerating abruptly, which will cause a single-phase liquid cooling operational lifetime to be much shorter than air cooling. Accordingly, it is essential to look for alternative cooling technologies such as two-phase cooling to replace liquid cooling when its time is up. This work presents comprehensive analyses of two-phase rack-level cooling systems deployment. These analyses can be divided into three main categories which are benchtop testing, rack-level deployment, and choosing a green refrigerant replacement. On the benchtop part of the project, five different cold plates that have different internal geometry are considered. These cold plates are used to build cooling loops with various configurations namely parallel, serial, and hybrid (parallel and serial). An EES code is used to design and evaluate the cold plates and cooling loops based on the existing correlations and modeling techniques. To evaluate this code, a benchtop two-phase experimental setup is built. This setup is designed to test single cold plates and full cooling loops while maintaining system stability. In this setup, high-power-density TTVs with 2.5 kW rated heaters are used to test these cold plates and cooling loops. The work on the benchtop level is just a preparation stage for the rack level deployment, where a custom-built CDU distributes refrigerant to the cooling loops through rack and row manifolds. These cooling loops are placed in multiple racks and attached to TTVs to simulate the thermal load of high-power density servers. In this part of the study, some design perspectives are introduced, and the impact of different operational parameters on CDU performance is explored. The last part of this study discusses the criteria for choosing a green refrigerant to replace existing high GWP ones. Most commonly used refrigerants such as R134a are expected to be phased out very soon due to their high GWP. Therefore, it is necessary to look for an alternative green refrigerant that can be adopted in the system without significantly impacting its performance. Preliminary results showed that R1234yf is the most appropriate replacement for R134a in two-phase rack-level cooling systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.