Desirable thermal management of data center requires uniform temperature distribution along the ser-vers. Hot air recirculation and cold air bypass in data center leads to non-homogeneous cold air distribu-tion along the servers of the racks which may lead to heterogeneous temperatures distribution along theservers. The present work aims to experimentally study the possibility of controlling these heterogeneoustemperature distributions by controlling the cold air flow rates along the servers. A physical scaled datacenter model was used to conduct this investigation. The effectiveness of thermal management of theservers racks of the data centers has been expressed in terms of intake, rare and surface temperature dis-tributions along the rack servers and the supply and return heat indices (commonly symbolized as SHIand RHI; respectively). Excessive tests were firstly performed under uniform servers fans speed (uniformair flow rates through the different servers). Then the air flow rates distributions along the racks servershas been changed by regulating the server’s fans speeds using different schemes of fans speeds regula-tions at different data centers power densities. It is concluded that a uniform increase of server’s flow ratefrom the bottom to the top of servers rack cabinet provides (i) the lowest temperature at both coolingaisle (around 10%) and exhaust aisles (around 5%), (ii) the best uniform surface temperature of all rackservers (as the standard deviation is reduced from 10 to around 2), and (iii) the best values of thermalmanagement metrics (SHI and RHI) typically SHI is reduced by around 20% while RHI is increased byaround 3% to approach the targeted values; 0.1 and 0.9, respectively. |
