Report
Job Class Thermal Intent Aware Liquid Cooling Allocation for AI Data Centers
| Τίτλος: | Job Class Thermal Intent Aware Liquid Cooling Allocation for AI Data Centers |
|---|---|
| Συγγραφείς: | Sunkara, Krishna Chaitanya |
| Έτος έκδοσης: | 2026 |
| Θεματικοί όροι: | Distributed, Parallel, and Cluster Computing, Performance, Systems and Control, C.4; D.4.1; I.6.8 |
| Περιγραφή: | GPU-dense AI data centers need to run on liquid cooling as air simply cannot shed the heat at these power densities. Yet the cooling loops themselves are blind to what workloads are about to run; they crank up flow only after a sensor catches a temperature climb, which can take 30 to 50 seconds. We built Job-Class Thermal Intent (JCTI) to close that window. The scheduler already knows a job is coming and what class it belongs to; JCTI feeds that information straight to the cooling controller so it can stage coolant before the heat shows up. We pulled the thermal signatures for each job class out of MLPerf GPU power traces and tuned arrival patterns against Alibaba cluster data. Over 120 paired Monte Carlo trials the numbers come out to 56.4% fewer thermal violations and 60.2% less cumulative overshoot than a straight PI loop. As AI data centers evolving towards gigawatt grid loads with highly fluctuating power swings, thermally-aware scheduling reduces sudden demand and improves load prediction in grid side. Cooling and scheduling have been running as two separate systems for years despite each one knowing something the other needs, JCTI wires them together. 6 pages, 5 figures, IEEE conference paper, first submitted to IEEE ICCSP 2026 02/02/2026 |
| Τύπος εγγράφου: | Working Paper |
| DOI: | 10.48550/arXiv.2609.30785 |
| Σύνδεσμος πρόσβασης: | https://arxiv.org/abs/2609.30785 |
| Αριθμός Καταχώρησης: | edsarx.2609.30785 |
| Βάση Δεδομένων: | arXiv |
καταχωρήστε σχόλιο πρώτοι!