Machine learning is becoming a buzzword—arguably an overused one—among companies that deal with networking. Recent announcements have touted machine learning capabilities at Google, Hewlett Packard Enterprise (HPE), and Nokia, for instance.
But machine learning isn’t being applied to networking itself. Why is that?
The intersection of machine learning and networking is where David Meyer, chief scientist at Brocade, has been working. After serving a term as the first chairman of the OpenDaylight Project’s Technical Steering Committee (TSC), Meyer shifted his work into the realm of artificial intelligence.
Even though networking has “just massively more compute and massively more data” available, it’s not yet clear how machine learning can be applied there, Meyer says.
What’s missing, he believes, is a theory of networking.
A rich body of academic work backs the networks we use today, certainly, but there is no unifying theory defining how a network, in an abstract sense, ought to behave, or how it ought to be structured. The networks that form the Internet certainly share some core principles, but they weren’t built from a central theory. They emerged through trial-and-error, “some good ideas and people telling each other how to do it,” Meyer says.
Machine learning, on the other hand, “is just math,” he says, and math requires models.
This is why machine learning is good at vision-based problems such as image processing or handwriting recognition. Vision can be studied in nature; there’s an entire body of theory that can be applied to make a machine behave like an eye.
“We’re trying to figure out if there’s some general way to think of a network,” Meyer says. “If such a thing doesn’t exist, then it’s possible that every network is a kind of one-off.”
That would be bad, because it would mean each network has to be “learned” separately. It wouldn’t play into one of the strengths of machine learning—namely, the ability to “take that trained neural network and add your own things to it, custom things,” Meyer says. “The data set and the way you interpret them have to be somewhere similar for you to be able to do that.”
Lack of a theoretical model is only one obstacle that machine learning faces in networking. The other is people. Machine learning and networking are different skills, and the pipeline of people well versed in both is thin.
“Either we [the networking people] are going to have to somehow work closely with people who know this stuff, or we’re going to have to learn it ourselves,” Meyer says. He’s banking on the latter approach.
“I’m really trying to build up some opportunities for people to learn about what’s going on here, earlier in their careers,” Meyer says. “Just to incorporate it in their thinking. It’s an experiment.”