Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11722 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911297559330816 |
|---|---|
| author | Sarkar, Soumyendu Guillen-Perez, Antonio Carmichael, Zachariah J Naug, Avisek Cam, Refik Mert Gundecha, Vineet Babu, Ashwin Ramesh Ghorbanpour, Sahand Gutierrez, Ricardo Luna |
| author_facet | Sarkar, Soumyendu Guillen-Perez, Antonio Carmichael, Zachariah J Naug, Avisek Cam, Refik Mert Gundecha, Vineet Babu, Ashwin Ramesh Ghorbanpour, Sahand Gutierrez, Ricardo Luna |
| contents | Reducing energy consumption and carbon emissions in data centers by enabling real-time temperature prediction is critical for sustainability and operational efficiency. Achieving this requires accurate modeling of the 3D temperature field to capture airflow dynamics and thermal interactions under varying operating conditions. Traditional thermal CFD solvers, while accurate, are computationally expensive and require expert-crafted meshes and boundary conditions, making them impractical for real-time use. To address these limitations, we develop a vision-based surrogate modeling framework that operates directly on a 3D voxelized representation of the data center, incorporating server workloads, fan speeds, and HVAC temperature set points. We evaluate multiple architectures, including 3D CNN U-Net variants, a 3D Fourier Neural Operator, and 3D vision transformers, to map these thermal inputs to high-fidelity heat maps. Our results show that the surrogate models generalize across data center configurations and significantly speed up computations (20,000x), from hundreds of milliseconds to hours. This fast and accurate estimation of hot spots and temperature distribution enables real-time cooling control and workload redistribution, leading to substantial energy savings (7\%) and reduced carbon footprint. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11722 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast 3D Surrogate Modeling for Data Center Thermal Management Sarkar, Soumyendu Guillen-Perez, Antonio Carmichael, Zachariah J Naug, Avisek Cam, Refik Mert Gundecha, Vineet Babu, Ashwin Ramesh Ghorbanpour, Sahand Gutierrez, Ricardo Luna Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Systems and Control Reducing energy consumption and carbon emissions in data centers by enabling real-time temperature prediction is critical for sustainability and operational efficiency. Achieving this requires accurate modeling of the 3D temperature field to capture airflow dynamics and thermal interactions under varying operating conditions. Traditional thermal CFD solvers, while accurate, are computationally expensive and require expert-crafted meshes and boundary conditions, making them impractical for real-time use. To address these limitations, we develop a vision-based surrogate modeling framework that operates directly on a 3D voxelized representation of the data center, incorporating server workloads, fan speeds, and HVAC temperature set points. We evaluate multiple architectures, including 3D CNN U-Net variants, a 3D Fourier Neural Operator, and 3D vision transformers, to map these thermal inputs to high-fidelity heat maps. Our results show that the surrogate models generalize across data center configurations and significantly speed up computations (20,000x), from hundreds of milliseconds to hours. This fast and accurate estimation of hot spots and temperature distribution enables real-time cooling control and workload redistribution, leading to substantial energy savings (7\%) and reduced carbon footprint. |
| title | Fast 3D Surrogate Modeling for Data Center Thermal Management |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Systems and Control |
| url | https://arxiv.org/abs/2511.11722 |