As mobile networks seek to use spectrum and infrastructure more efficiently to keep pace with rising data demand, UK operator O2 has announced that it has worked with Nokia on the UK’s first live deployment of radio access network (RAN) technology with artificial intelligence (AI) built in at its Giga Site in London’s Paddington Station.
Giga Sites are regarded as the operator’s “most advanced” mobile sites, combining low-, mid- and high-band spectrum with Massive MIMO technology, and designed to boost network performance by giving customers faster speeds, better coverage and greater capacity, helping meet rapidly growing demand for mobile data.
The roll-out is part of O2’s plan to increase network capacity where it is needed most, with each Giga Site built to deliver 10 times more capacity than previous infrastructure. The operator said this will enable more customers to stay connected, stream content, make video calls and access online services, even in some of the busiest locations across the country.
Putting its trial into context, O2 said mobile sites generally rely on largely static algorithms to manage radio resources. By contrast, Nokia’s AI-based technology is said to take a more dynamic approach, continuously learning from network conditions and automatically adjusting how spectrum and capacity are allocated across the site.
London’s Paddington is one of the UK’s busiest transport hubs, where the technology operated on O2’s live network and served customers throughout the trial. Using predictive AI embedded in the radio network, the feature analysed network conditions and anticipated changes in demand, enabling the site to respond automatically to shifting traffic patterns without manual intervention.
During the live trial, the deployed technology is claimed to have improved spectral efficiency by about 20%. In practical terms, it is said to have allowed the site to carry more data using the same spectrum and existing network capacity, delivering significant throughput gains during periods of high demand while maintaining stable network accessibility and reliability.
O2 believes the results demonstrate how AI can help it manage growing mobile traffic more efficiently, supporting faster downloads, higher-quality video streaming and reduced buffering for customers in busy locations where demand can fluctuate.
This live trial with Nokia showed how AI can improve network efficiency and help us respond more effectively to changing customer demand Jeanie York, O2
“Mobile data demand continues to grow, so we need smarter ways to make the most of the spectrum and infrastructure we already have,” remarked O2’s chief technology officer, Jeanie York. “This live trial with Nokia showed how AI can improve network efficiency and help us respond more effectively to changing customer demand. By making better use of existing network resources, we can deliver a better experience for customers while supporting future traffic growth.”
Nokia’s president of mobile networks, Emma Falck, added: “This milestone demonstrates how AI is moving from experimentation to delivering measurable benefits in live mobile networks. By embedding intelligence directly into the RAN, operators can make better use of existing spectrum resources, improve network performance and create a stronger foundation for future AI-driven services.”
The project also forms part of the operator’s £700m Mobile Transformation Plan, which is upgrading mobile coverage, reliability and performance across the UK and will see investment in 2026 to expand mobile network coverage, improve reliability and boost mobile speeds through new sites, small cells, 4G and 5G upgrades, automation and additional spectrum deployment.
It is designed to focus investment in areas of the network that experience the highest demand and where connectivity is most critical. Priority areas where the operator is looking to deliver significant improvements include railways, roads, dense urban areas, hard-to-reach remote locations, stadiums and other venues.
