Rising power densities at the server level due to increasing performance demands are being met by using efficient thermal management methods such as direct-to-chip liquid cooling. The use of cold plates that are directly installed yields a lower thermal resistance path from the chip to the ambient. In a hybrid-cooled server arrangement, high-heat-generating components are cooled with water or a water-based fluid, while the rest of the components are cooled with air using server-level fans. It is imperative to characterize the heat capture ratio for various server boundary conditions to ascertain the best possible liquid and airflow rates and temperatures. These parameters serve as inputs in defining the Total Cost of Ownership (TCO). The present investigation numerically evaluates the heat capture ratio in a hybrid cooled server for peak server load and varying inlet temperature for air and liquid. The CFD model of a Cisco Series C220 server with direct-to-chip liquid-cooled CPUs was developed. The cold plate for the CPU was experimentally characterized for pressure drop and thermal resistance characteristics and a black-box model was used for CFD simulations using 25% propylene glycol as the coolant. The heat capture ratio value was obtained under the varied temperature and flow rate boundary conditions of air and liquid. Based on the heat capture ratio values obtained, optimum values of inlet temperatures and flow rates are recommended for air and liquid for the server being investigated.
In recent years, there has been a significant increase in cloud computing, networking, virtualization, and storage applications, leading to an increase in demand for high-performance servers. The increase in performance demands is currently being met by increasing CPU and GPU power densities that require more efficient cooling technologies as compared to air traditional cooling methods. Cold plate-based liquid cooling in air-cooled servers enables efficient thermal management with minimal changes to existing air-cooling infrastructure. In a hybrid cooled server, the demand for air cooling is reduced as the primary heat-generating components are indirectly cooled by cold plates. In this study, experiments are performed with optimized chassis of a hybrid cooled Cisco C220 server. The chassis design is optimized to improve the airflow by providing additional vents on the chassis to allow more low-temperature airflow rather than the heated airflow approaching from the drive bay. Also, the design of the heat sink baffle is improved which allows a more streamlined flow to approach the heat sinks. This is done by designing and manufacturing a new 3-D printed baffle. This optimized baffle design helps in reducing the pressure drop across the system hence helping in the reduction of fan speeds and reducing the fan power consumption. Results are generated by iterating the fan speed and inlet temperature of air and comparing them with the baseline design of the server. Conclusions are made on the reduction in fan power due to the improved chassis design and any reduction in temperatures of air-cooled components.
Direct to chip liquid-cooling technique has been widely implemented for the cooling of processors with high thermal design power. To further enhance the efficiency of liquid cooling, ongoing research focuses on the optimizations at the cold plate level or by changing the flow configurations. But in all cases, the coolant which is pumped across the rack is pumped at a constant flow rate irrespective of the workload utilization at the individual server, resulting in excess pumping of coolant. A practical approach is to dynamically vary the flow rate to each server as per server workload utilization. In this study, transient analysis is performed by varying the flow rate across individual servers at rack level using CFD. A CFD model mimicking four servers placed at different heights on a standard 42U rack is developed. The flow variation through each of the servers is done using a damper arrangement representing a flow control device. A controller is integrated to automate the process of opening and closing of FCD to vary the flow based on the average outlet temperature from each server. A baseline simulation with all servers running at maximum power dissipation with a constant coolant flow rate is compared with cases where the coolant flow rate is controlled dynamically for varying thermal design power (TDP). The results shown analyze the impact of the dynamic response of the flow control device on transient thermal and hydraulic characteristics across the rack is done.
Due to increasing computational workload and thermal design power requirements of high power-density microelectronics, low heat carrying capacity and poor thermal conductivity of air renders air-cooling insufficient to meet the cooling demands of component heat generation in high-performance servers. A more effective method of removing heat from these high-powered components is by using single-phase immersion cooling with a dielectric fluid of superior thermal properties and high boiling point. This study compares traditional forced-air cooling with forced convection single-phase immersion cooling to minimize chip junction temperatures of a 776 W high powered data center server using CFD simulations. The server is of spread-core configuration consisting of 2 CPU heatsink assemblies and 32 DIMM units with their specified chip thermal design power (TDPs). The first method consists of forced-air cooling with a 28°C air inlet supply and 110 CFM inlet air flowrate to establish baseline thermal performance. The second method is forced convection single-phase immersion cooling of the server in EC-110 dielectric fluid at 28 °C temperature and 2 GPM flow rate to observe server performance improvement in CPU case temperatures, maximum DIMM temperature, and server pressure drop through immersion cooling method. Lastly, CFD simulations are performed at different fluid inlet temperatures of 30, 40 and 50 °C, and 2 GPM fluid inlet flow rate, and the percentage change in the CPU case temperatures, server pressure drop and the maximum DIMM temperatures with fluid inlet temperature were studied.
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.