With 5G, AI at the edge promises a compute-everywhere future

With 5G, AI at the edge promises a compute-everywhere future

Luxury car maker Audi is leading the full force into Industry 4.0, using artificial intelligence heuristics and computer vision on the factory floor with robotic welders who can interact in real time and fix problems that may arise when welding a car frame. This is just one example of how the company is moving toward its ultimate vision of building smart factories with a scalable and flexible platform that will enable data analytics, communications, and processing at the edge, powered by 5G.

In the past, welding required a lot of manual intervention and inspection to ensure adequate quality, says Nick McKeown, senior vice president and general manager of Network and Edge Group at Intel, which works with Audi. Now, with cameras reviewing the quality of the weld, the need for human intervention has decreased dramatically.

“If you want, or need to process data in real time, you have to actually bring the computation into the data, to the point of data creation and consumption.”

Sandra Rivera

“Advance computing takes the technology resources we have developed over many years for the computing industry and uses them to analyze and process data at the edge,” says McKeown. The concept of edge computing is to store data close to where it was created and used – like on the factory floor – rather than in the cloud, meaning it can be processed in real or near real time.

“If you want or need to process data in real time, you really have to bring computing to the data, to the point of data creation and consumption,” explains Sandra Rivera, Executive Vice President and General Manager of Data Center AI Group at Intel. Not having to transfer large amounts of data improves security and increases reliability while reducing latency. And because the data is kept more private, there’s an extra layer of data sovereignty available when needed, McKeown adds.

5G opportunities are growing on the edge

As telecom operators continue to roll out 5G infrastructure, “there are opportunities starting to emerge because the data rate, the latency, and the control you have over the 5G network means we can start using it for applications we didn’t have before thought to be appropriate for cellular technology,” says McKeown. .

In the Audi factory example, real-time robot arm control requires either a cable, wire, or Ethernet cable attached to it to ensure connectivity, the required data rate and low latency control — or it should be replaced with a wireless link, he says.

“Now imagine the robot moving,” McKeown says. “You really don’t want a wire to roll around on the floor for other robots to get stuck. You really want it to be a wireless link.” “The problem is that the wi-fi isn’t really quite there yet in the quality you want it to be. What 5G offers, particularly 5G in particular, is much more reliable, much lower latency, and much more controllable—through software experience.”

Source link

Leave a Comment