AT&T says it is leaning into edge computing (EC) to better deliver next-generation applications like virtual and augmented reality (VR/AR).
The operator reports its drive toward EC comes as part of its push toward a software-defined network capable of achieving single-digit millisecond latency. Such performance will be necessary for 5G applications, including VR and AR, autonomous cars, and others, that demand “massive amounts of near-real time computation.”
For VR/AR in particular, AT&T says edge computing could help address obstacles like insufficient processing power on devices and battery life by shifting to the cloud the computation work needed to deliver those experiences. Edge computing can also cut down on VR/AR lag by slashing the distance information needs to travel across the network, the operator notes.
“Edge computing fulfills the promise of the cloud to transcend the physical constraints of our mobile devices,” Andre Fuetsch, president of AT&T Labs and chief technology officer, comments. “The capabilities of tomorrow’s 5G are the missing link that will make edge computing possible. And few companies have the sheer number of physical locations that AT&T has that are needed to solve the latency dilemma.”
Rather than utilizing just a few data centers across the country, AT&T says it will move to a model that includes “tens of thousands of central offices, macro towers, and small cells.” These, the company notes, are “usually never farther than a few miles from our customers,” effectively bringing the cloud closer to users. Eventually, edge computing systems could even be installed in smart infrastructure, like traffic lights, AT&T adds.
EC-capable services are already being deployed to AT&T’s enterprise customers via its FlexWare service, and additional applications – such as EC for public safety – are on the way, AT&T says.