Optimization Strategies for Underfloor Air Distribution in a Small-Scale Data Center

Abstract: The development of 5G application technology has led to a rapid expansion in the scale of internet data center rooms and the number of servers. Due to the high heat generation of data center server equipment and the mixing of hot and cold airflows within the rooms, the thermal environment of these rooms fails to meet operational requirements with increasing energy consumption and thermal density. This study utilized the 6SigmaDC software to simulate and analyze the characteristics and existing problems of airflow distribution in a small-scale data center. Based on identified issues with current airflow patterns, two optimization schemes were proposed, analyzing the effects of raised floor height and the closure of aisles on airflow optimization. The return heat index (RHI) was used as an evaluation metric to assess airflow patterns before and after optimization. When the raised floor height was 600 mm, the maximum temperature at the cabinet inlet and outlet were 19.3 °C and 34 °C respectively, which were the lowest, and the RHI value was 0.9622. Compared with unclosed aisles and closed hot aisles, closed cold aisles effectively reduced the cabinet inlet and outlet temperature and increased the RHI. In addition, closed cold aisles increased the air supply temperature from 18 °C to 20 °C, further reducing the energy consumption of the air conditioning system. This study can provide guidance and act as a reference for optimizing airflow design and energy conservation in small data centers.