Thermal Performance of an Air-Cooled Data Center With Raised-Floor and Non-Raised-Floor Configurations

Nagarathinam, Srinarayana; Fakhim, Babak; Behnia, Masud; Armfield, S.W.

doi:10.1080/01457632.2013.828559

Cited by 31 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the exploitation of hot/cold aisle separation can also avoid overheating of the computer rack due to sufficient reduction of airflow mixing. Srinarayana [3] found that using a ceiling return strategy for the return of hot exhaust air to the CRAC units gives a better thermal performance of the data center, for both raised-and non-raised-floor strategy, as compared to the room return. Patankar et al [4] had studied the airflow distribution of perforated tiles.…”

Section: Literatures Reviewmentioning

confidence: 99%

Improvements of Airflow Distribution in a Container Data Center

2015

View full text Add to dashboard Cite

The present study aims at improvements of the airflow and temperature distribution in a container data center. Simulation is carried out based on a raised floor design. It is found that the height of raised floor casts significant impact on the flow distribution. Generally, the flow rate of the perforated tile near the entrance region of CRAC unit is lower than that of the rear part of the perforated tile. The mal-distribution becomes even more severe when the height of the raised floor is reduced. The mal-distribution can be significantly improved using a smaller opening perforated tile but it also gives rise to higher pumping power and impairs the effective flow rate from CRAC. Hence, a variable opening design with a larger opening near the CRAC outlet, followed subsequently with smaller opening perforated tiles, the mal-distribution can be eliminated without additional pumping power. For improvement of the airflow/temperature distribution into the rack, we propose a drawer-type rack which can increase the effective hot aisle space and reducing the cold aisle space. Through this design, hot air recirculation and cold air bypass will be significantly reduced. As a result, the rack maximum inlet temperature of drawer-type rack can be reduced as much as 13.3 C when compared with the traditional one.

show abstract

Section: Literatures Reviewmentioning

confidence: 99%

Improvements of Airflow Distribution in a Container Data Center

2015

View full text Add to dashboard Cite

show abstract

“…The potential to increase the thermal performance of a server room by the use of partial or full aisle containment has been verified in several studies, but mainly for cold aisles only. Srinarayana et al [8] numerically compared room and ceiling return strategies in both hard and raised floor configurations. Arghode et al [9] compared numerical and experimental results of a contained cold aisle to an open cold aisle for both the under-and over-provisioning of supply air.…”

Section: Introductionmentioning

confidence: 99%

Comparing Performance Metrics of Partial Aisle Containments in Hard Floor and Raised Floor Data Centers Using CFD

2019

View full text Add to dashboard Cite

In data centers, efficient cooling systems are required to both keep the energy consumption as low as possible and to fulfill the temperature requirements. The aim of this work is to numerically investigate the effects of using partial aisle containment between the server racks for hard and raised floor configurations. The computational fluid dynamics (CFD) software ANSYS CFX was used together with the Reynolds stress turbulence model to perform the simulations. Velocity measurements in a server room were used for validation. Boundary conditions and the load of each rack were also retrieved from the experimental facility, implying an uneven load between the racks. A combination of the performance metrics Rack Cooling Index (RCI), Return Temperature Index (RTI) and Capture Index (CI) were used to evaluate the performance of the cooling systems for two supply flow rates at a 100% and 50% of operating condition. Based on the combination of performance metrics, the airflow management was improved in the raised floor configurations. With the supply flow rate set to operating conditions, the RCI was 100% for both raised floor and hard floor setups. The top- or side-cover fully prevented recirculation for the raised floor configuration, while it reduced the recirculation for the hard floor configuration. However, the RTI was low, close to 40% in the hard floor case, indicating poor energy efficiency. With the supply flow rate decreasing with 50%, the RTI increased to above 80%. Recirculation of hot air was indicated for all the containments when the supply rate was 50%, but the values of RCI still indicated an acceptable performance of the cooling system.

show abstract

“…However, recent data centers have widely adopted aisle containment architecture and the variable air volume CRAH system (which fixes the CRAH supply air temperature and changes the supply air volume according to the cooling load by sensing the temperature, rack inlet air, or pressure difference of the aisles [18][19][20][21]) because of their superior cooling efficiency [22][23][24][25][26]. In this case, there may be a large difference between the predicted and real data center energy consumptions when the conventional fixed CRAH temperature difference is utilized in energy consumption simulations, especially under high ambient conditions, because the IT equipment's heat generation and cooling fan airflow vary according to the real-time changes in the IT workload (i.e., server utilization) and equipment ambient temperature [27][28][29] [30] performed thermal modeling of servers and a rack unit through using computational fluid dynamics (CFD), but CFD is unsuitable for considering a data center's dynamic thermal characteristics because of the long computing time.…”

Section: Introductionmentioning

confidence: 99%