Improving Data Center Energy Efficiency With Advanced Thermal Management

Chainer, Timothy; Schultz, Mark; Parida, Pritish R.; Gaynes, Michael

doi:10.1109/tcpmt.2017.2661700

Cited by 57 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The thermal management system has played an increasingly essential and promising role in such fields as data center [1], building [2], electric/fuel cell vehicles [3][4][5], energy storage [6], and spacecraft [7,8]. For example, with the development of the Cloud service and the 5th generation wireless systems, data processing centers with high-power electric devices require a higher efficiency thermal management system.…”

Section: Introductionmentioning

confidence: 99%

The Integrated Component-System Optimization of a Typical Thermal Management System by Combining Empirical and Heat Current Methods

2020

View full text Add to dashboard Cite

Integration of modeling and optimization of a thermal management system simultaneously depends on heat transfer performance of the components and the topological characteristics of the system. This paper introduces a heat current method to construct the overall heat current layout of a typical double-loop thermal management system. We deduce the system heat transfer matrix as the whole system constraint based on the overall heat current layout. Moreover, we consider the influences of structural and operational parameters on the thermal hydraulic performances of each heat exchanger by combining the empirical correlations of the heat transfer and pressure drop. Finally, the minimum pressure drop is obtained by solving these optimal governing equations derived by the Lagrange multiplier method considering the physical constraints and operational conditions. The optimization results show that the minimum pressure drop reduces about 8.1% with the optimal allocation of mass flow rates of each fluid. Moreover, the impact analyses of structural and operating parameters and boundary conditions on the minimum and optimal allocation present that the combined empirical correlation-heat current method is feasible and significant for achieving integrated component-system modeling and optimization.

show abstract

Section: Introductionmentioning

confidence: 99%

The Integrated Component-System Optimization of a Typical Thermal Management System by Combining Empirical and Heat Current Methods

2020

View full text Add to dashboard Cite

show abstract

“…The electrical power consumed in exascale data centers is large and growing. The largest data center today uses ∼ 150 MW [1] of power and 100 MW centers are not uncommon [2]. As the world attempts to reduce its carbon footprint and use electrical power more efficiently, the size and number of data centers continues to grow exponentially [3].…”

Section: Introductionmentioning

confidence: 99%

Open loop control theory algorithms for high-speed 3D MEMS optical switches

et al. 2020

View full text Add to dashboard Cite

There is a worldwide push to create the next generation all-optical transmission and switching technologies for exascale data centers. In this paper we focus on the switching fabrics. Many different types of 2D architectures are being explored including MEMS/waveguides and semiconductor optical amplifiers. However, these tend to suffer from high, path dependent losses and crosstalk issues. The technologies with the best optical properties demonstrated to date in large fabrics (>100 ports) are 3D MEMS beam steering approaches. These have low average insertion losses, and equally important, a narrow loss distribution. However, 3D MEMS fabrics are generally dismissed from serious consideration for this application because of their slow switching speeds (∼few milliseconds) and costs ($100/port). In this paper we show how novel feedforward open loop controls can solve both problems by improving switching speeds by two orders of magnitude and costs by one order of magnitude. With these improvements in hand, we believe 3D MEMS fabrics can become the technology of choice for data centers.

show abstract

“…They successfully dissipated a total heat load of 4 kW on a single board via two separate cooling loops (2 kW per loop) using 12 serried cold plates per loop. Although there are numerous studies available on the chip-scale two-phase cooling [3,6,[10][11][12][13][14][15], the literature on the rack scale pumped two-phase cooling systems is limited. Valenzuela et al [16] studied the behavior of a pumped refrigerant two-phase cooling system by considering two evaporators at different elevations to mimic a rack-scale system.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Investigation on the Fluid Distribution in a Two-Phase Cooled Rack Under Steady and Transient Information Technology Loads

Khalili

Rangarajan

Gektin

et al. 2020

Journal of Electronic Packaging

View full text Add to dashboard Cite

Increasing power densities in data centers due to the rise of Artificial Intelligence (AI), high-performance computing (HPC) and machine learning compel engineers to develop new cooling strategies and designs for high performance information technology (IT) equipment. Two-phase cooling is a promising technology that exploits the latent heat of the coolant which is much more effective in removing high heat fluxes than when using the sensible heat of the fluid. Also, utilizing the latent heat allows operating at lower coolant flow rates and implies more uniformity in the temperature of the heated surface. Despite the benefits of two-phase cooling, the phase change adds complexities to a system when multiple evaporators (exposed to different heat fluxes potentially) are connected to a single coolant distribution unit (CDU). In this paper, a commercial CDU is used to investigate pumped two-phase cooling in rack scale. Seventeen 2-rack unit (RU) servers from two distinct models are retrofitted with thirty-four impinging jet evaporators and deployed in a rack. Four case studies are presented to provide insights into the complex behavior of a pumped two-phase cooling system with several evaporators. The flow rates and pressure distribution across the rack are studied in various filling ratios. Also, investigated is the transient behavior of the cooling system due to a step change in the IT workload. Finally, a control system is designed to regulate the temperature of the supplied coolant in response to the step change in the IT workload and is tested.

show abstract

Improving Data Center Energy Efficiency With Advanced Thermal Management

Cited by 57 publications

References 24 publications

The Integrated Component-System Optimization of a Typical Thermal Management System by Combining Empirical and Heat Current Methods

The Integrated Component-System Optimization of a Typical Thermal Management System by Combining Empirical and Heat Current Methods

Open loop control theory algorithms for high-speed 3D MEMS optical switches

An Experimental Investigation on the Fluid Distribution in a Two-Phase Cooled Rack Under Steady and Transient Information Technology Loads

Contact Info

Product

Resources

About