Visual Intelligence· 2026Q1
PIGNN3D: an accelerated physics-informed graph neural network for 3D thermal field simulation in data centers
- 0citations
- Q1SCImago
- 2026year
Short summary
PIGNN3D, a physics-informed graph neural network, accelerates 3D thermal field simulation in data centers by simplifying architecture and optimizing message passing, achieving accuracy comparable to other methods with reduced VRAM usage and faster convergence.
AI-generated from the title and abstract; the full text is not read.
Key points
- PIGNN3D is a physics-informed graph neural network for 3D thermal field simulation in data centers.
- It features architectural simplifications and optimized message passing for faster training and reduced memory usage.
- Experimental results show comparable accuracy to other methods with significant reductions in VRAM and faster convergence.
- The method aims to enable practical AI-driven thermal simulation for data center management.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. Visual Intelligence, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Mechanical Engineering
Mechanical EngineeringEngineering