Wednesday, April 17, 2024
HomeNewsletterLatest NewsletterAnalysis: 5G Advanced, Wireless AI could release cell networks’ true potential

Analysis: 5G Advanced, Wireless AI could release cell networks’ true potential

As wireless connectivity moves to 5G, systems have become more complex and challenging to manage, leaving the industry to find new system design methods — which could include embracing wireless artificial intelligence (AI), Counterpoint Research reports.

5G Advanced (5.5G) is expected to expand wireless AI’s role across 5G networks with new AI applications that will “enhance the design and operation of networks and devices” during the next three to five years. AI is expected to be a key part of 5G Advanced, as well in the end-to-end (E2E) design and optimization of wireless systems, according to Counterpoint.

Wireless devices are no stranger to AI. It’s been used in smartphones and other mobile devices for years. The difference now is AI is being used in the actual wireless network. However, AI is typically used on the mobile device or in the network —not both. This independent usage has prevented end-to-end systems from reaching their full performance potential across devices and networks.

One of the reasons for this is that on-device AI training has not been possible until recently. The personalized data then stays local to the device rather than shared with the cloud, improving reliability and decreasing security concerns. The solution isn’t just limited to smartphones — it can be applied to consumer devices, sensors and industrial equipment.

Going forward, on-device AI will help improve E2E 5G network optimization, delivering key benefits for operators and users. On-device AI allows processing to be distributed over millions of devices, bringing in all of their computational powers. Additionally, on-device AI enables AI model learning to be tailored to a user’s personalized data, according to Counterpoint.

On-device AI will be critical to improving 5G networks’ E2E performance, but overall systems optimization isn’t at its best if AI is implemented independently, according to Counterpoint. AI Training needs to be done on a systems-wide basis to ensure true E2E performance optimization — collaboratively across the network and devices.

“Making this a reality in wireless system design requires not only AI know-how but also deep wireless domain knowledge,” Counterpoint said. “This so-called cross-node AI is a key focus of 5G Advanced with a number of use cases being defined in 3GPP’s Release 18 specification and further use cases expected to be added in later releases.”

The aforementioned 3GPP Release 18 has served as a starting-off point for more extensive wireless AI use that’s expected in 6G. One use case example is cross-node machine learning to adapt the Channel State Information (CSI) feedback mechanism between a base station and a device, allowing for coordinated performance optimization between networks and devices.

Additional use cases included using machine learning to enable intelligent beam management at the base station and device to improve usable network capacity and device battery life; and using machine learning to improve device positioning accuracy in outdoor and indoor environments.

“5G Advanced wireless AI/ML will be the foundation for much more AI innovation in 6G and will result in many new network capabilities,” Counterpoint said. For instance, the ability of the 6G AI native air interface to refine existing communication protocols and learn new protocols coupled with the ability to offer E2E network optimization will result in wireless networks that can be dynamically customized to suit specific deployment scenarios, radio environments and use cases. This will a boon for operators, enabling them to automatically adapt their networks to target a range of applications, including various niche and vertical-specific markets.”

- Advertisement -
- Advertisment -spot_img

Industry News

- Advertisement -