A Sensitivity Analysis of Flexibility from GPU-Heavy Data Centers

TL;DR

This paper analyzes how energy-aware job scheduling in GPU-heavy data centers can enhance power flexibility during peak electricity prices, balancing profit and grid stability.

Contribution

It demonstrates that optimized scheduling increases flexibility and profit, especially in data centers with diverse job characteristics and lower queue lengths.

Findings

Efficient scheduling improves power flexibility during peak prices.

Lower queue length and diverse job profiles enhance flexibility potential.

Demand reduction is highly sensitive to electricity prices.

Abstract

The rapid growth of GPU-heavy data centers has significantly increased electricity demand and creating challenges for grid stability. Our paper investigates the extent to which an energy-aware job scheduling algorithm can provide flexibility in GPU-heavy data centers. Compared with the traditional first-in first-out (FIFO) baseline, we show that more efficient job scheduling not only increases profit, but also brings latent power flexibility during peak price period. This flexibility is achieved by moving lower energy jobs, preferentially executing jobs with lower GPU utilization and smaller node requirements, when the electricity price is high. We demonstrate that data centers with lower queue length and higher variance in job characteristics such as job GPU utilization and job size, offer the greatest flexibility potential. Finally we show that data center flexibility is highly price sensitive, a 7% demand reduction is achieved with a small incentive, but unrealistically high prices are required to achieve a 33% reduction.