PIGNN3D: an accelerated physics-informed graph neural network for 3D thermal field simulation in data centers

Abstract Efficient thermal management is critical in data centers, where computational fluid dynamics (CFD) simulations provide high-fidelity airflow and temperature predictions but remain computationally demanding and time-intensive. While data-driven methods have emerged as promising alternatives, most existing works are limited to small-scale or 2D flow simulations and face challenges when extended to complex 3D domains. To overcome these challenges, we present PIGNN3D, a physics-informed graph neural network designed for fast and efficient 3D thermal field simulation in data centers. PIGNN3D introduces architectural simplifications and optimized message passing to significantly accelerate training and reduce memory usage, while preserving the physical consistency of CFD-based modelling. Experimental results demonstrate significant reduction in video random access memory (VRAM) usage and faster convergence while maintaining accuracy comparable to other methods. This advancement brings artificial intelligence (AI)-driven thermal simulation closer to practical deployment for speedy and sustainable data center management.