Nokia and China Mobile test AI-powered RAN

22 Jan 2021

China Mobile and Nokia have completed trials of an artificial intelligence (AI)-powered RAN over the cellco’s 4G and 5G networks. The tests comprised an AI-based real-time user equipment (UE) traffic bandwidth forecast trial in Shanghai as well as a network anomaly detection trial in Taiyuan, and incorporated China Mobile’s ‘i-wireless-intelligent and simplicity 5G network’ concept – described as a series of technologies designed to create a greener, smarter and more efficient 5G network. One such technology was a RAN Intelligent Controller (RIC), which Nokia claims supports ‘near real-time’ control and optimisation of RAN elements enabled by ‘real-time data exposure and cross-layer perception capabilities utilising AI and machine learning (ML) applications’. During the trial, the RIC was included in the edge cloud using Nokia’s AirFrame Open Edge server platform.

In Shanghai, the tests achieved traffic prediction accuracy of 90% in a live 5G network according to the Finnish vendor. The network anomaly detections tests in Taiyuan, meanwhile, examined network operation automation using CMCC’s 4G/5G network across more than 10,000 cells. With the AI/ML technology assistant, network problems were detected more accurately and automatically.

Commenting on the trials, Huang Yuhong, Deputy Director of China Mobile Research Institute (CMRI), was quoted as saying: ‘RIC plays a key role in enabling AI/ML capability in the RAN, which is of great significance to realise the concept of the “i-wireless-intelligent and simplicity 5G network”. Nokia and [China Mobile’s] trials are very meaningful for RIC commercialisation … We are pleased to complete these trials using AI to forecast UE transmission bandwidth and detect anomalies on China Mobile’s live network with our partner Nokia. The field trial proved the availability of RIC enabling network enhancements through customised real-time BTS data analysis and control.’