AT&T is constructing an edge computing test zone in Palo Alto, Calif., where third-party developers and companies are invited to test applications such as self-driving cars, augmented reality and virtual reality, and drones.
The site is expected to be ready for use in early 2018. At first the test zone will use a 4G LTE connection, but AT&T expects to upgrade to 5G once final standards and equipment are prepared, potentially by the end of 2018. AT&T has previously said it plans to launch standards-based mobile 5G in that same timeframe.
“Edge computing is the next step in the evolution of the network,” Melissa Arnoldi, president of AT&T Technology and Operations, said in a statement. “As connectivity becomes ubiquitous and fast, it also needs to become smart. Edge computing puts a supercomputer in your pocket, on your wrist, in your car, and right in front of your eyes.”
The goal is to bring data processing closer to the user, because in today’s network the physical distance between users and data centers can be hundreds or thousands of miles. This results in too much latency and a worse experience for applications like AR.
“With edge computing, we’ll install graphics processors and other computers in cell towers, small cells, and other parts of our network that are never more than a few miles from our customers,” AT&T said. “This is what’s known as the edge of the network.”
The operator said there are no specific projects up and running yet, but foresees projects dealing with AR/VR, drones, and autonomous cars. In addition to getting developers’ projects connected to the network, AT&T also indicated it would help turn concepts into prototypes.
“Our goal in this experiment is to find the right architecture, the right services, and the right business value in this ecosystem,” Igal Elbaz, head of the AT&T Foundry, noted. “It’s all about moving quickly and collaborating closely with third-party innovators and developers.”
AT&T said the initial test area will span several miles and could expand over time.
The company also just published a whitepaper detailing some of the technical elements behind edge computing, which you can find here.