Energy consumption and thermal management have become key challenges in the design of large-scale data centers, where perforated tiles are used together with cold and hot aisles configuration to improve thermal management. Although full-field simulations using computational fluid dynamics and heat transfer (CFD/HT) tools can be applied to predict the flow and temperature fields inside data centers, their running time remain the biggest challenge to most modelers. In this paper, a reduced order modeling method is used to drastically reduce the running time (up to 600 times faster) while still acceptably preserving the accuracy of the model. The results obtained from Proper Orthogonal Decomposition (POD) method are in good agreement with the results obtained from CFD/HT model simulation with a mean temperature difference as low as 0.183oC. In addition, a 3D POD approach has also been proposed to obtain the entire temperature profiles of the data center model.