Machine Learning Guided Cooling System Optimization for Data Center

TL;DR

This paper introduces a physics-guided machine learning framework to identify and reduce cooling energy waste in data centers, achieving significant efficiency improvements through interpretable, safe setpoint adjustments.

Contribution

The paper presents a novel three-stage framework combining machine learning and physics constraints to quantify and recover excess cooling energy in high-performance data centers.

Findings

Achieved a mean absolute error of 0.026 MW in power prediction.

Identified approximately 85 MWh of annual cooling inefficiency.

Recovered up to 96% of excess cooling energy through setpoint adjustments.

Abstract

Effective data center cooling is crucial for reliable operation; however, cooling systems often exhibit inefficiencies that result in excessive energy consumption. This paper presents a three-stage, physics-guided machine learning framework for identifying and reducing cooling energy waste in high-performance computing facilities. Using one year of 10-minute resolution operational data from the Frontier exascale supercomputer, we first train a monotonicity-constrained gradient boosting surrogate that predicts facility accessory power from coolant flow rates, temperatures, and server power. The surrogate achieves a mean absolute error of 0.026 MW and predicts power usage effectiveness within 0.01 of measured values for 98.7% of test samples. In the second stage, the surrogate serves as a physics-consistent baseline to quantify excess cooling energy, revealing approximately 85 MWh of annual inefficiency concentrated in specific months, hours, and operating regimes. The third stage evaluates guardrail-constrained counterfactual adjustments to supply temperature and subloop flows, demonstrating that up to 96% of identified excess can be recovered through small, safe setpoint changes while respecting thermal limits and operational constraints. The framework yields interpretable recommendations, supports counterfactual analyses such as flow reduction during low-load periods and redistribution of thermal duty across cooling loops, and provides a practical pathway toward quantifiable reductions in accessory power. The developed framework is readily compatible with model predictive control and provides a template that, with site-specific recalibration, could be adapted to other liquid-cooled data centers with different configurations and cooling requirements.