A Comparison of Parametric and Multivariable Optimization Techniques in a Raised-Floor Data Center

Abstract

It is well known that the flow distribution in data centers can be effected by a variety of parameters such as rack and computer room air conditioning (CRAC) positions, raised-floor height, ceiling height, and percentage opening of perforated tiles. In the present paper, numerical simulations are conducted to optimize the layout of a raised-floor data center with respect to these parameters. Two different approaches have been used: parametric optimization; and a multivariable approach using response surface optimization. In the parametric optimization procedure, the data center is optimized with respect to the maximum temperature in the room. While in the multivariable approach, a cost function is constructed from all the rack inlet temperatures and is minimized. The results show that the multivariable approach is computationally economical and the optimized layout gives a better thermal performance compared to that of parametric optimization.