AWS data centers harness liquid cooling for maximum efficiency – SiliconANGLE

Building modern data centers requires inventive solutions, especially in the age of energy-sucking artificial intelligence.

Amazon Web Services Inc. has focused on creating highly efficient and reliable data centers. The company is embracing liquid cooling techniques and scalable infrastructure to save more energy, according to Kevin Miller (pictured), vice president of global data centers at AWS.

“We build our own data centers, and we really rethought the way that works,” he said. “We are now using industrial software to manage [diagnosing failures], where instead of hours … the software takes two seconds. It can identify the problem and then change the configuration of our electrical system to fix that problem. Therefore, we don’t even have to run a generator.”

Miller spoke with theCUBE Research’s John Furrier for theCUBE’s “Cloud AWS re:Invent Coverage,” during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how Amazon is effectively building modern data centers.

Driving efficiency in developing data centers

AWS has seen a 46% improvement in efficiency during peak cooling times by using computational fluid dynamics to reduce unnecessary cooling, according to Miller. These measures are all a part of AWS’ efforts to decrease costs and carbon output.

“Instead of working on discrete, highly featured components in data centers, similar to the way we build services, we actually look at simplifying and building smaller building blocks that we can scale up and so it’s been in a different approach,” Miller explained. “A lot of that is our own development, but we certainly work with a broad ecosystem of partners around it.”

AWS’ data centers have made significant improvements in liquid cooling and carbon efficiency. The company has also worked toward reducing the blast radius of its data centers by almost 90%, with the goal of matching efficiency with reliability.

“What’s really important with AI for training in particular, we want training to be efficient,” Miller said. “For it to be efficient, you actually need to pack as many chips as you can into as small a physical space as you can because that reduces latency, and the latency is what drives efficiency.”

Another aspect of Miller’s work in data centers is partnering with local communities to modernize the surrounding grid. AWS has encouraged workforce development in the areas near its data centers, starting at a young age.

“Oftentimes we build programs like Think Big Space, which is an idea where we go into a local school and build a space where bring in 3D printers and Lego kits and Technic kits and really see a ton of engagement with younger kids,” Miller said. “It’s literally planting trees and helping communities just do what they want to do in their community effectively.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s “Cloud AWS re:Invent Coverage”:

Photo: SiliconANGLE