Japanese telecom giant NTT, its mobile arm DoCoMo, and vendor Nokia touted significant technology milestones that integrate artificial intelligence (AI), machine learning (ML), and sub-terahertz spectrum to power potential 6G services.

The first milestone was integrating AI and ML into the radio air interface, which they ominously stated “effectively giving 6G radios the ability to learn.” Technically, the move allows the 6G radio to work through signal degradation issues, which reduced signaling overhead and supported a 30% improvement in signal throughput.

The companies also linked the integration to network slicing use cases, stating the 6G radios would gain “the flexibility to adapt to the type of connection demanded by an application, device, or user.”

“For instance, a network in a factory can be optimized for industrial sensors at one moment and then reconfigured for robotic systems or video surveillance,” the firms noted in a statement. “In the public network, an AI-enhanced network can provide an optimized connection for a pedestrian in an [extended reality] session as well as an emergency vehicle traveling at high speed.”

The spectrum part of the trial involved using a big chunk of sub-THz spectrum to generate high throughput speeds. Specifically, the trial used 144 megahertz of spectrum, a single 256 quadrature amplitude modulation (QAM) transmission scheme, and antenna beamforming to produce network speeds of 25 Gb/s.

The sub-THz spectrum bands, which are bands above 100 GHz, are a challenge for telecommunication networks due to their limited propagation characteristics. However, there is a lot of untapped spectrum in those bands and the limited propagation characteristics play into better re-use opportunities that can be advantageous in confined environments.

NTT and Nokia noted that the combination of smarter radio transmission capabilities and the THz spectrum are “well suited for high-accuracy radio sensing, which will likely be another key feature of 6G.”

6G remains a nebulous concept as standards work has yet to officially begin. However, many expect the technology will include increased reliance on distributed cloud and edge computing resources, and a further push up the spectrum scale.

Analysts have noted that radio sensing will be an important part of network deployments that tap into the higher-frequency millimeter-wave (mmWave) and sub-THz spectrum bands.

Jeff Wang, global 5G and networks lead at Accenture, noted in a recent interview with SDxCentral that those higher spectrum bands are going to force a complete re-think of deployment models to take into account their more challenging propagation characteristics.

“Accenture is working constantly with clients on how do we deploy this because that density is not easy economically,” Wang said.

As an example, he noted that if a sub-1 GHz-based network required 50,000 cell sites to cover the U.S., using sub-6 GHz, which many operators are rolling out as part of their highly touted mid-band updates, or millimeter wave (mmWave) will need hundreds of thousands of sites.

“If you put that much stress on any process you have to be able to build in a new level of automation, a new level of intelligence, a new level of rigor to this and if you even let your mind go toward sub-terahertz [spectrum], it’s very hard to imagine,” Wang said. “If we don’t figure this out now, how we bring intelligence in, how we automate this, how we self-heal this, it’s just an unmanageable, logistical nightmare.”

The NTT and Nokia trial builds on an initial 6G agreement between the firms announced last year. That agreement, which also included NEC and Fujitsu, was focused on the technology advances used in the latest trial.

The companies had noted that they did not expect actual 6G deployments to begin until later this decade, though NTT DoCoMo CTO Naoki Tani noted in a statement that the “6G studies are progressing two or three years ahead of that of 5G.”

Outside of the Nokia trial, NTT DoCoMo late last year struck a deal with SK Telecom to align their plans and timelines for 6G technology. This will include joint research and development, standardization, and joint testing to begin early this year.

This work echoes similar efforts across Europe.

Ericsson, for instance, is setting up a 6G-focused research unit in the United Kingdom as part of a 10-year, multi-million-dollar investment into that country’s wireless technology future.

German telecom giant Deutsche Telekom is heading up that country’s Federal Ministry of Education and Research (BMBF) 6G Native Extensions for XR Technologies (NeXt) project to target network architecture for the testing of extended reality (XR) services using 6G technologies. Nokia is participating in a similar BMBF project.

Nokia CEO Pekka Lundmark sprinkled in some 6G expectations during the vendor’s latest earnings call, stating the vendor expects 6G technology to begin making a financial impact as soon as 2028.