No abstract

No abstract

A novel lattice Boltzmann method (LBM) -based 3D computational fluid dynamics (CFD) technique has been implemented on the graphics processing unit (GPU) for the purpose of simulating the indoor environment in real-time . We study the time evolution of the turbulent air flow and temperature inside a test chamber and in a simple model of a four-bed hospital room. The predicted results from LBM are compared with traditional CFD-based large eddy simulations (LES). Reasonable agreement between LBM results and LES method are observed with significantly faster computational times.

Simulation tools for thermal management of data centers help to improve layout of new builds or analyse thermal problems in existing data centers. The development of LBM on remote GPUs as an approach for such simulations is discussed making use of VirtualGL and prioritised multi-threaded implementations of an existing LBM code. The simulation is configured to model an existing and highly monitored test data center. Steady-state root mean square averages of measured and simulated temperatures are compared showing good agreement. The full capability of this simulation approach is demonstrated when comparing rack temperatures against a time varying workload, which employs time-dependent boundary conditions.

This paper uses three different numerical simulation technologies to analyse the thermal airflow distribution in a simple example data center layout. The numerical approaches used are based on finite element, finite volume and lattice Boltzmann methods and are respectively implemented via commercial Multiphysics software, opensource CFD code and GPU based code developed by the authors. Each method includes an appropriate turbulence model and the simulation results focus on comparison of the three methods when applied to 2 rows of datacom racks with cool air supplied by a computer room air conditioner and distributed via an underfloor plenum. Good quantitative agreement between the three methods is seen in terms of the inlet temperatures to the Datacom equipment.Key Words: Data center cooling, Lattice Boltzmann, Finite Element, Finite Volume. IntroductionData centers are facilities hosting information and communications technology (ICT) infrastructure, usually laid out in rows of 2m tall racks. Their operation provides digital services across a range of sectors. The quantity and density of these ICT systems results in a distributed and complex dynamic generation of heat throughout the facility that needs to be transported away from the ICT, referred to as datacom, equipment. This is usually achieved by air cooling, where the heat is transferred and ultimately rejected to the outside environment. The growth of these facilities has been considerable, with data centers consuming only 0.12% of US energy consumption for the year 2000 [1] and that figure having risen to over 2% only ten years later, in 2010 [2]. Globally this figure is currently closer to 1.5%, at a growth of roughly 11% per year over the last decade [3], and approximately 45% of this energy is used in the removal of heat [4]. Improvements to the energy efficiency of these facilities are rapidly becoming paramount, due to the need to reduce both running costs and environmental impact [5].