What is power capping?

power capping (noun)

Limiting the amount of power a computer system or data center can consume to optimize energy efficiency, prevent overheating, and ensure stable performance.

Surging demand for artificial intelligence has had a significant environmental impact, especially when it comes to data center use. The International Energy Agency has estimated that global electricity demand from data centers could double between 2022 and 2026, fueled in part by AI adoption.

Scientists at the MIT Lincoln Laboratory Supercomputing Center are exploring ways to mitigate the environmental impact of AI by working to reduce the center’s own energy consumption.

One method is power capping — specifically, limiting the amount of power feeding the processors and graphics processing units in their supercomputer foundation.

“Rather than letting them go to 100%, we limit usage to 150 or 250 watts [about 60% to 80% of their total power], depending on which processor we’re using,” said Vijay Gadepally, a senior staff member at the laboratory. “We’ve applied this to both training and inferencing workloads, and it not only reduces the overall power and energy consumption of the workloads; it reduces operating temperatures as well.”

AI has high data center energy costs — but there are solutions