ADVANCED DATA CENTER COLD AISLE AIRFLOW ORGANIZATION OPTIMIZATION USING AN ADJUSTABLE FAN UNIT

摘要

The real-time smart data center cooling has become a key to maintenance and operation of energy-efficient data centers, primarily including the server inlet airflow/thermal domains. Here, the cold-aisle airflow phenomena in a widely-used cold/hot aisle data center configuration was under parametric investigation, This concern is mainly because of the airflow separation and recirculation from the stream emerging from the server outlet and returning to the computer room air-conditioning unit. In order to achieve a better understanding and to correspondingly eliminate the negative effects of the hot air over-tack recirculation towards a satisfied effectiveness, an addition of a rack-level adjustable fan unit (AFU), which is placed inside the cold aisle, was considered at an early stage and the model prototype was numerically analyzed with respects to differently predefined parameters. The cooling performance consequence, consisting of the server-neighbored inflow rates and maximum server inlet temperatures explored by computational fluid dynamics (CFD) observation panel and sensors, demonstrates that the over-rack air recirculation and its resulting hot spot, in comparison with the case in absence of the AFU, can be suppressed. The results additionally concludes the extents to which the optimized airflow organization and temperature drop of the rack-level region (e.g., from the bottom towards the top of the rack unit) can be achieved with/without the AFU addition.