Verizon is working with long-standing network vendor Ericsson to integrate AI into RAN automation, a move that includes the nationwide rollout of Ericsson’s Intelligent Controller (EIC) by year-end and furthers the operator’s push toward more autonomous control over its network assets.

The latest work will see Verizon deploy the EIC platform in support of the running of AI-native rApps developed by Ericsson and Verizon. These rApps are microservices-based applications operating in non-real time (rApps) that provide an operator with more control over their open RAN environments. A more advanced version are dubbed “xApps” and are able to operate in near-real time.

Verizon specifically pointed to an already implemented connected mode inter-radio access technology handover methodology from its 4G LTE network to its 5G standalone (SA) network for fixed-wireless access (FWA) devices, a move it claims eliminates “the need for manual intervention on handover failures.”

Matt Butz, VP of network planning at Verizon, noted in a statement that the work has already shown measurable results. This includes the use of AI to control massive multiple-input, multiple-output (MIMO) antennas and traffic steering that provided a near 9% improvement in downlink data radio bearer throughput and up to an 8% improvement in uplink user equipment throughput.

The pair also plans to test and deploy new rApps, including a cell anomaly detector, root cause explainer, and an anomaly general optimizer, moves the carrier noted will accelerate its network autonomy journey toward so-called level-four control.

TM Forum defines level-four autonomy as providing “decision-making based on intent-driven, predictive analysis, and the capability to perform closed-loop management of service-driven and customer experience-driven networks via AI modeling and continuous learning.”

EIC is part of Ericsson’s broader Intelligent Automation Platform (EIAP) that is targeted at providing an open platform that can support multivendor and multitechnology systems running 4G and 5G RAN. EIAP is being used by a number of operators worldwide, including underpinning Verizon rival AT&T’s $14 billion network overhaul program.

Verizon’s latest work with Ericsson builds on recent efforts between the industry players, including a pre-standard “6G” field call in the 7 GHz band at a site in California, and Verizon Business tapping Ericsson to power international private 5G services. Ericsson is also part of the Verizon-led 6G Innovation Forum that launched last year.

Verizon accelerates AI-leaning velocity

“We're using that to iterate and train the AI to get better at our job using that,” Tenorio said. The next step is to graduate the agents from university and have them specialize in different tools that we operate in a system that we currently have in prototype, so I want to put that in production in the next three months.”

Tenorio downplayed the “level” classification of such a move, noting, “the important point is it'll be like a complex network of agents and sub-agents that are monitoring the network 24/7 spotting patterns and anomalies, and then calling a network of sub-agents specialized on different tasks to come up with a root-cause analysis and a solution autonomously.”

This early work has already seen “real-life tasks” that would have taken hours to resolve “done in 90 seconds.”

“I want that in production before the end of the year,” Tenorio said of that work. “We'll probably start with the radio, but very quickly will take on transport and core, so hopefully within the next six months my agents will graduate from university, and they will find a job in operations.”

Verizon had previously tapped network equipment vendor Samsung and chip giant Qualcomm as part of a multivendor deployment using AI-RAN management applications running on a RAN intelligent controller (RIC). That work included the deployment of a Samsung-developed network-efficiency managing rApp.