Multi-objective Optimization of a Data Center Modeling Using Response Surface
CHALLENGE - Energy consumption and thermal management have become key challenges in the design of large-scale data centers. 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 remains the biggest challenge. Here response surface methodology based on radial basis function is used to significantly reduce the running time for generating a large set of generations during a two-objective minimization process.
SOLUTION - Three design parameters including mass flow inlet, inlet temperature, and server heat load are investigated for a two-objective optimization using optimizer modeFRONTIER. The goal is to minimize both the temperature difference and the maximum temperature inside the data center and search for a range of design parameters that satisfy both of these objectives. Numerous radial basis function models are studied and compared.
BENEFITS - Numerous radial basis function models are studied and compared. A set of Pareto designs from the Pareto front is obtained. These designs are equally good and non-dominant of each other in terms of the two objectives. It is found that for an inlet temperature range and an inlet mass flow rate range of 11.8 – 12.62 °C, 7.36 – 7.67 kg/s, respectively, the two objectives are equally achieved. Also, all of the Pareto designs have a server heat load of 900W.