A Transformer-Based Thermal Surrogate Model for Cooling Control in Data Centers

Abstract

With the rapid development of data centers in the Big Data era, the operation of their cooling systems has huge energy saving potential, so the optimization of their control is of great significance for research. The main challenge in the optimization problem above is the prediction of the complicated temperature field. The most recognized Computational Fluid Dynamics (CFD) simulation consumes too much time to be applied in the real-time optimization. To address this problem, a Transformer-based thermal surrogate model is proposed. Specifically, self-attention is used for capturing the temporal and spatial characteristics in the temperature field to replace CFD. Then, the optimization problem is formulated and a surrogate model-based Soft Actor-Critic (SAC) solution framework is proposed. Finally, the control performance is verified in the CFD-based platform 6SigmaRoom and the widely-used Artificial Neural Network (ANN) is selected as the baseline. Numerical experiments demonstrate that the proposed surrogate model makes predictions faster than CFD and more accurately than ANN while the control based on it achieves a 7.12% reduction in energy consumption, finally improving the energy efficiency.