Google has a lot of data centers around the world and it seems like it’s always looking to build more to increase its capacity. During the Data Centers Europe 2014, which is currently happening in France, Google said that it had started to use machine learning and artificial intelligence to increase efficiency in its data centers.
Taking pride in his work, Joe Kava, Google vice president for data centers, talked about the company’s use of a neural network during the conference. The tool that Google built analyzes all data it collects about its servers and recommends ways to improve them, always finding solutions to make them better.
Basically, the search giant has built a computer that knows more about its data centers than even the engineers who built them. By making use of artificial intelligence, Google will be able to predict how data centers would act in various situations and to mold its next projects accordingly.
Despite the fact that the project hasn’t been around for long, it’s already extremely fine-tuned. For instance, the neural network has managed to predict with a 99.6 percent accuracy how power efficient the data centers are going to be.
“In a dynamic environment like a data center, it can be difficult for humans to see how all of the variables interact with each other. We’ve been at this for a long time. All of the obvious best practices have already been implemented, and you really have to look beyond that,” said Kava.