T Mobile and Ericsson AI Native Scheduler Commercial Trials Prove Massive Performance Gains for 5G Advanced Networks Through Real Time Neural Network Optimization
The relationship between T Mobile and Ericsson is set to extend even further as they've introduced the AI native Scheduler into wide commercial trials on real 5G Advanced network traffic. This is a key step in radio access network development as it uses a neural network to forecast radio conditions in real time, this software will work with Ericsson hardware designed with the total cost of ownership in mind to boost spectral efficiency and downlink speeds.
During the live network trials T Mobile reported a 10% boost in spectral efficiency and the data showed a 15% improvement in downlink throughput when compared with traditional rule based scheduling. Both figures match what was previously observed in small scale 1 st phase environment tests so the technology has proven itself to scale and work in different geographical areas.
Grant Castle (SVP, RAN Engineering at T Mobile) stated that:
"This is the next phase of our milestone last year becoming the first carrier in the US to deploy 5G Advanced"
the SVR said:
"Our work with Ericsson on AI native Scheduler with Link Adaptation demonstrates how real time AI driven optimization can enhance spectral efficiency and throughput while delivering a more consistent experience for customers at scale."
With the AI native Scheduler network stability will be maintained at both maximum load and at locations with bad radio frequency condition. This will mean that it is more likely to get quick response at mobile gaming or quality on video call for the final user. The Head of product line RAN Software at Ericsson Johan Hultell stated that intelligence is the basic in our high performing and programmable networks now.
"AI is central to our vision for high performing programmable networks. By embedding intelligence directly into RAN software we can deliver real time performance gains that enhance user experience while helping operators like T Mobile maximize the value of their spectrum."
The technology demonstration is another prime example of how AI native RAN functionality can be deployed in a live network. Both companies state they plan to continue to work together to find other methods of utilizing ML to increase cell density and network efficiency. The companies aim to gain further spectrum value as 5G Advanced is adopted.
