AT&T is putting down a marker in the sand for mobile edge computing, stating this week that having network resources closer to the edge in 5G will help to enable new services like the connected car.
AT&T says that the challenge of next-generation applications like augmented or virtual reality, and the connected car, is that they will eat mountains of data. The carrier states that by some estimates, self-driving cars will generate as much as 3.6 terabytes of data per hour from the clusters of cameras on board and other sensors. Some of this -- like braking -- will always be handled locally at the car, but much -- such as mapping -- can be offloaded to the cloud.
The incredibly low latency of 5G networks -- measured at around 1 millisecond -- is part of how this can happen, and mapping updates will happen in near-real-time. The other aspect, however, is getting the mobile cloud -- the servers that store this information -- as close to the user as possible.
The operator hasn't put any concrete numbers on how this might affect radio access network (RAN) build-out and other initiatives. But it has said in a statement that updates will involve "tens of thousands of central offices, macro towers, and small cells usually never farther than a few miles from our customers."
That could mean a lot of new infrastructure, albeit on a smaller scale than the hulking cell towers of today.
— Dan Jones, Mobile Editor, Light Reading