Modern IT environments must support a dramatic rise in the amount of data being generated. This data needs to be collected, analyzed and shared in real time to deliver valuable business insights.

This is driving the need for greater network capacity and optical networking technology to accommodate this growth, using optics within data centers and optical systems between data centers. Cisco Systems Inc. is well aware of this need and is delivering innovative solutions for both areas.

“The only way to get that is through automation,” said Bill Gartner (pictured), senior vice president and general manager at Cisco. “As an example with routed optical networking, the answer isn’t take your optical team and make them IP experts and take your IP team and make them optical experts. The answer is to automate out those things that really require human engineering and let those people be the experts in the areas that they need to be experts.”

Gartner spoke with theCUBE Research analysts John Furrier and Dave Vellante at MWC Barcelona, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how Cisco’s Routed Optical Networking solution propels operational efficiency and simplicity through its optical switching technology. (* Disclosure below.)

Cisco’s solution to transforming data transport

Prior to routed optical networking technologies, organizations needed to use dedicated optical systems, such as dense wave division multiplexing, or DWDM, to send large amounts of data across metro and wide area networks. Both service providers and enterprises employed this technology, but it is expensive and requires new skill sets. Cisco Systems Inc.’s Routed Optical Networking solution is geared toward addressing these issues by leveraging sophisticated, pluggable optics that reduce cost, improve network efficiency and integrate seamlessly with IP routers, Gartner explained.

“Routed Optical Networking was really born out of an insight that we had that was driven by the fact that we’re seeing massive, massive scalability now with new silicon technologies,” he said. “Cisco has a technology that we refer to as Silicon One. It’s based on an acquisition [of Leaba] we did five or six years ago. We’ve developed a complete portfolio of routing products that leverages this silicon.”

When Gartner arrived at Cisco about 15 years ago, it had a 40-gig line card on a router and 14 ASICs that were required to deliver a 40-gig signal. Today, the company has one ASIC that delivers 25 terabits of capacity.

“If you think about it, the cost of an ASIC is about the cost of an ASIC; the cost per bit today for that 25-terabit signal is much, much, much lower than the cost per bit of a 40-gig signal 15 years ago,” Gartner explained. “This innovation lowers the cost of having that router signal transmitted over a long distance.”

Independent analysis has shown that adopting this plug-in technology can lead to a 35% reduction in capital expenditures for a particular network. In some cases, it can even result in operational expense savings of more than 50%, according to Gartner.

How Routed Optical Networking fits into the artificial intelligence picture

Within the data center, Cisco provides optical transceivers that are used to connect fiber to every port on a switch or router, for both Cisco or competitors’ products. This enables organizations to provide a wide range of network capacity for workloads, including up to 800GB to support skyrocketing AI environments.

“A customer can buy our optics and plug them into a competitor router or switch, and that’s basically a transceiver business — little transceivers that are about the size of a cigarette lighter that plug into a router or switch and can terminate anywhere from one gig to 800 gig today, whatever a customer might need for their given application,” Gartner said. “That’s going to have a huge impact for AI, because interconnecting all of these workloads is going to be done optically with these transceivers.”

It’s not just the transceivers that play role for AI. The optical systems also enable these emerging AI environments to move data between data centers and provide opportunities for hyperscalers, service providers and enterprises.

“The technology has been available for just a little bit over a year,” Gartner said. “I would say it’s very high acceptance in the hyperscaler community, because many of the hyperscalers for things like AI loads that you mentioned are seeing massive capacity needs in moving traffic between data centers. It’s a perfect solution in that application where it’s relatively short distance, maybe 100 kilometers up to 1,000 kilometers between data centers, but we’ve got over 100 service provider customers now deploying this technology as well.”

Here’s the complete video discussion, part of SiliconANGLE’s and theCUBE Research’s coverage of MWC Barcelona:

(* Disclosure: TheCUBE is a paid media partner for the MWC Barcelona event. No sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE