Perforated Floor Tiles Research Articles

Guidance for data-center CFD (RP-1675)

This article reviews and summarizes research conducted during and related to ASHRAE RP-1675, Guidance for Data Center CFD. The ultimate objective is to provide users and vendors of computational fluid dynamics (CFD) tools with best-practice modeling advice to support greater adoption of the technology to design and operate reliable and sustainable facilities. RP-1675 identified and developed good CFD modeling practices by benchmarking CFD simulations against experimental measurements for a “laboratory data center,” considering past and concurrent research, and performing additional sensitivity studies in CFD. This article provides a detailed review of the experimental and CFD work conducted during RP-1675, which focused on the modeling of computer room air handler units (CRAHs) with vertical-axis blowers located in the raised-floor plenum, and modeling perforated floor tiles, and raised-floor stanchions. This article ultimately summarizes current guidance for data-center CFD.

Cooling Effectiveness of a Data Center Room under Overhead Airflow via Entropy Generation Assessment in Transient Scenarios

Forecasting data center cooling demand remains a primary thermal management challenge in an increasingly larger global energy-consuming industry. This paper proposes a dynamic modeling approach to evaluate two different strategies for delivering cold air into a data center room. The common cooling method provides air through perforated floor tiles by means of a centralized distribution system, hindering flow management at the aisle level. We propose an idealized system such that five overhead heat exchangers are located above the aisle and handle the entire server cooling demand. In one case, the overhead heat exchangers force the airflow downwards into the aisle (Overhead Downward Flow (ODF)); in the other case, the flow is forced to move upwards (Overhead Upward Flow (OUF)). A complete fluid dynamic, heat transfer, and thermodynamic analysis is proposed to model the system’s thermal performance under both steady state and transient conditions. Inside the servers and heat exchangers, the flow and heat transfer processes are modeled using a set of differential equations solved in MATLAB™ 2017a. This solution is coupled with ANSYS-Fluent™ 18, which computes the three-dimensional velocity, temperature, and turbulence on the Airside. The two approaches proposed (ODF and OUF) are evaluated and compared by estimating their cooling effectiveness and the local Entropy Generation. The latter allows identifying the zones within the room responsible for increasing the inefficiencies (irreversibilities) of the system. Both approaches demonstrated similar performance, with a small advantage shown by OUF. The results of this investigation demonstrated a promising approach of data center on-demand cooling scenarios.

Experimentally Validated Computational Fluid Dynamics Model for Data Center With Active Tiles

Abstract This paper presents an experimentally validated room-level computational fluid dynamics (CFD) model for raised-floor data center configurations employing active tiles. Active tiles are perforated floor tiles with integrated fans, which increase the local volume flow rate by redistributing the cold air supplied by the computer room air conditioning (CRAC) unit to the under-floor plenum. The numerical model of the data center room consists of one cold aisle with 12 racks arranged on both sides and three CRAC units sited around the periphery of the room. The commercial CFD software package futurefacilities6sigmadcx is used to develop the model for three configurations: (a) an aisle populated with ten (i.e., all) passive tiles; (b) a single active tile and nine passive tiles in the cold aisle; and (c) an aisle populated with all active tiles. The predictions from the CFD model are found to be in good agreement with the experimental data, with an average discrepancy between the measured and computed values for total flow rate and rack inlet temperature less than 4% and 1.7 °C, respectively. The validated models were then used to simulate steady-state and transient scenarios following cooling failure. This physics-based and experimentally validated room-level model can be used for temperature and flow distributions prediction and identifying optimal number and locations of active tiles for hot spot mitigation in data centers.

Measurement of Air Flow Rate Through Perforated Floor Tiles in a Raised Floor Data Center

In a raised floor data center, cold air from a pressurized subfloor plenum reaches the data center room space through perforated floor tiles. Presently, commercial tool “Flow Hood” is used to measure the tile air flow rate. Here, we will discuss the operating principle and the shortcomings of the commercial tool and introduce two other tile air flow rate measurement tools. The first tool has an array of thermal anemometers (named as “Anemometric Tool”), and the second tool uses the principle of temperature rise across a known heat load to measure the tile air flow rate (named as “Calorimetric Tool”). The performance of the tools is discussed for different types of tiles for a wide range of tile air flow rates. It is found that the proposed tools result in lower uncertainty and work better for high porosity tiles, as compared to the commercial tool.

Modified Body Force Model for Air Flow Through Perforated Floor Tiles in Data Centers

Generally, porous jump (PJ) model is used for rapid air flow simulations (without resolving the tile pore structure) through perforated floor tiles in data centers. The PJ model only specifies a step pressure loss across the tile surface, without any influence on the flow field. However, in reality, the downstream flow field is affected because of the momentum rise of air due to acceleration through the pores, and interaction of jets emerging from the pores. The momentum rise could be captured by either directly resolving the tile pore structure (geometrical resolution (GR) model) or simulated by specifying a momentum source above the tile surface (modified body force (MBF) model). Note that specification of momentum source obviates the need of resolving the tile pore geometry and, hence, requires considerably low computational effort. In previous investigations, the momentum source was imposed in a region above the tile surface whose width and length were same as the tile dimensions with a preselected height. This model showed improved prediction with the experimental data, as well as with the model resolving the tile pore geometry. In the present investigation, we present an analysis for obtaining the momentum source region dimensions and other associated input variables so that the MBF model can be applied for general cases. The results from this MBF model were compared with the GR model and good agreement was obtained.

Experimentally Validated Computational Fluid Dynamics Model for a Data Center With Cold Aisle Containment

This paper presents the results of an experimentally validated computational fluid dynamics (CFD) model for a data center with fully implemented fan curves on both the servers and the computer room air conditioner (CRAC). Both open and contained cold aisle systems are considered in this study. This work is divided into sections for the baseline system (prior to installing containment) calibration and the fully contained cold aisle system calibration and leakage characterization. In the open system, the fan curve of the CRAC unit is extracted from the manufacturer data, while the fan curve of the load banks is obtained through experimental measurements. The experimental results are found to be in good agreement with the average model predictions. In the fully contained cold aisle system, a detailed containment CFD model is developed based on experimental measurements. The model is validated by comparing the flow rate through the perforated floor tiles and the rack inlet temperatures with the experimental measurements. The CFD results are found to be in good agreement with the experimental data with an average relative error between the measured and computed flow rate of approximately 6.7%. Temperature measurements are used to calibrate the sources of leakage in the containment and rack mounting rails. The temperature measurements and the CFD results agree well with an average difference of less than 1 °C. This study provides important modeling guidelines for data centers. In order to predict the performance of contained cold aisle systems flow distribution, it is crucial that physics based models of fan curves, server internal resistances, detailed rack models, and other design details are all accurate and experimentally verified.

Experimental Investigation of Air Flow Through a Perforated Tile in a Raised Floor Data Center

Raised floor data centers supply cold air from a pressurized plenum to the server racks through perforated floor tiles. Hence, the design of an efficient air delivery scheme requires better understanding of the flow features, through and above the perforated tiles. Different tiles with circular pores in a staggered arrangement and with the same thickness are considered. Tile sheet porosities of 23% and 40%, air flow rates of 0.56 m3/s (1177 CFM) and 0.83 m3/s (1766 CFM), and pore sizes of 3.18 mm (1/8 in.) and 6.35 mm (1/4 in.) are investigated. Tiles with 38.1 mm (1.5 in.) region blocked along the edges is compared to the base case with 12.7 mm (0.5 in.) blocked edges. Width reduced to 0.46 m (1.5 ft) from standard width of 0.61 m (2 ft) is also examined. Reduced tile width is used to simulate 0.91 m (3 ft) cold aisle instead of standard 1.22 m (4 ft) cold aisle, with potential to save floor space. A case where the rack is recessed by 76.2 mm (3 in.) from the tile edge is also included in the investigation, as there is a possibility of having racks nonadjacent to the tile edges. Particle image velocimetry (PIV) technique is used to characterize the flow field emerging from a perforated tile and entering the adjacent rack. Experiments suggest that lower tile porosity significantly increases cold air bypass from the top, possibly due to higher air jet momentum above the tile, as compared to a tile with higher porosity. For the air flow rates investigated here, the flow field was nearly identical and influence of flow rate was nondistinguishable. The influence of pore size was non-negligible, even when the porosity and flow rate for the two cases were same. Larger blockage of the tile edges resulted in higher cold air bypass from the top. Reduction in the tile width showed improved air delivery to the rack with considerably reduced cold air bypass. Recessing the rack did not affect the flow field significantly.

Neural Network-Based Prediction and Control of Air Flow in a Data Center

As modern data centers continue to grow in power, size, and numbers, there is an urgent need to reduce energy consumption by optimized cooling strategies. In this paper, we present a neural network-based prediction of air flow in a data center that is cooled through perforated floor tiles. With a significantly smaller execution time than computational fluid dynamics, it predicts in real-time server inlet temperatures and can detect whether prevalent air flow cools the servers sufficiently to guarantee safe operation. Combined with a cooling system model, we obtain a temperature and air flow control algorithm that is fast and accurate enough to find an optimal operating point of the data center cooling system in real-time. We also demonstrate the performance of our algorithm on a reference data center and show that energy consumption can be reduced by up to 30%.

Cluster of High-Powered Racks Within a Raised-Floor Computer Data Center: Effect of Perforated Tile Flow Distribution on Rack Inlet Air Temperatures

This paper focuses on the effect on rack inlet air temperatures as a result of maldistribution of airflows exiting the perforated tiles located adjacent to the fronts of the racks. The flow distribution exiting the perforated tiles was generated from a computational fluid dynamics (CFD) tool called Tileflow (trademark of Innovative Research, Inc.). Both raised floor heights and perforated tile-free areas were varied in order to explore the effect on rack inlet temperatures. The flow distribution exiting the perforated tiles was used as boundary conditions to the above-floor CFD model. A CFD model was generated for the room with electronic equipment installed on a raised floor. Forty racks of data processing (DP) equipment were arranged in rows in a data center cooled by chilled air exhausting from perforated floor tiles. The chilled air was provided by four A/C units placed inside a room 12.1 m wide×13.4 m long. Because the arrangement of the racks in the data center was symmetric, only half of the data center was modeled. The numerical modeling for the area above the raised floor was performed using a commercially available finite control volume computer code called Flotherm (trademark of Flomerics, Inc.). The flow was modeled using the k-e turbulence model. Results are displayed to provide some guidance on the design and layout of a data center.

A methodology for the design of perforated tiles in raised floor data centers using computational flow analysis

An important aspect of the design of data centers involves sizing of the perforated floor tiles for return of cold air, the size of the space under the raised floor, and placement of the DP equipment and modular chillers. The flow through individual perforated tiles needs to fulfil the cooling requirements of the computer equipment placed adjacent to them. The novelty of this paper lies in the treatment of the volume under the raised floor as a uniformly pressurized plenum. The accuracy of the Pressurized Plenum model is demonstrated with reference to a computational fluid dynamics (CFD) analysis of the recirculating flow under the raised floor and the limits of its validity are also identified. The simple model of the volume under the raised floor enables use of the technique of flow network modeling (FNM) for the prediction of the distribution of flow rates exiting from the various tiles. An inverse design method is proposed for one-step design of the perforated tiles and flow balancing plates for individual chillers. Subsequent use of the FNM technique enables assessment of the performance of the actual system. Further, required design changes to an existing system can also be evaluated using the FNM analysis in a simple, quick, and accurate manner. The resulting design approach is very simple and efficient, and is well suited for the design of modern data centers.