Nokia AI-RAN trials yield 20% spectral efficiency gain

Nokia AI-RAN trials across global carrier networks have verified a 20 percent spectral efficiency gain over standard radio configurations.

Eight telecom providers – A1 Group, Chunghwa Telecom, du, e&, Mobily, stc, TPG Telecom, and Zain Saudi – have transitioned testing from preliminary laboratory environments into live field trials. Live trial programmes with Japanese operator NTT DOCOMO continue across production base stations.

Network traffic patterns are changing rapidly. Distributed AI models and device-side workloads generate heavy uplink demand. This trend pushes carriers to extract higher network capacity out of assigned frequency allocations.

Nokia structured its AI-native RAN platform to address these compute requirements. By converting fixed-function radio access networks into programmable software nodes, the vendor supports baseband connectivity and enterprise computing workloads simultaneously on shared hardware.

Emma Falck, President of Mobile Infrastructure at Nokia, said: “AI is reshaping the future of telecommunications and creating a significant opportunity for operators to rethink the role of the radio network.

“The increasing engagement we are seeing from service providers around the world shows that AI-RAN is moving quickly from vision to commercial reality and becoming a foundational technology for the AI-native 6G era.”

NVIDIA Aerial integration improves spectral efficiency

Silicon consolidation anchors the commercial proposition. To execute baseband tasks alongside distributed workloads, Nokia integrated its AI-native ‘anyRAN’ software suite with the NVIDIA Aerial RAN Computer. This combined architecture supplies a software-defined base for 5G installations, complete with a programming pathway to future 6G standards.

Radio engineering teams verified that algorithmic optimisations delivered the 20 percent spectral efficiency gain across trial environments. Carriers can boost overall cell throughput and extract higher commercial value from existing spectrum allocations instead of funding capital-intensive physical antenna replacements.

Both companies are collaborating on software development tools designed to foster an open ecosystem alongside third-party OEMs.

Ronnie Vasishta, SVP of Telecom at NVIDIA, explained: “With NVIDIA Aerial RAN Computer and Nokia’s AI-RAN software, operators can build software-defined networks that continuously improve in performance and efficiency, while supporting entirely new AI services at the edge.

“Global operator momentum demonstrates that AI-RAN is becoming the foundation for 5G Advanced today and then software upgradable to AI-native 6G tomorrow.”

Carrier field trials expand through 2028

Field trials now span four continents. These live deployments follow earlier commercial evaluations conducted with T-Mobile in the US, SoftBank in Japan, and Indosat Ooredoo Hutchison in Indonesia.

Carrier groups evaluate the technology to curb reliance on rigid hardware refresh schedules while preparing network operations for future AI-native protocols. Independent analysts view the participation of diverse regional operators as proof of technical readiness.

Remy Pascal, Practice Leader for Mobile Infrastructure at Omdia, said: “The breadth of operator engagement announced by Nokia shows that AI-RAN is evolving from a research topic into a strategic priority for a growing number of service providers.

“What’s notable is the diversity of operators across regions, reflecting an emerging industry consensus that AI will be essential to continue improving network performance and operational efficiency, and to the evolution toward 6G.”

Nokia scheduled a multi-year software development roadmap extending through 2027–28. This engineering timeline targets compounding spectral efficiency improvements through continuous code releases. The cadence also helps carriers scale network capacity and explore new monetisation opportunities.

Engineering groups across the participating operators will monitor field performance metrics as these software iterations roll out to trial sites worldwide.

“As deployments mature, collaboration between operators, vendors, and the broader ecosystem will be critical to realising AI-RAN’s full potential,” Pascal concludes.

See also: Verizon and Samsung trial AI-native ISAC sensing on vRAN

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and is co-located with other leading technology events including the IoT Tech Expo and Cyber Security & Cloud Expo. Click here for more information.

Telecoms is powered by TechForge Media. Explore other upcoming enterprise technology events and webinars here.