On 21 January 2021 Nokia and China Mobile (CMCC) announced that they have successfully completed live trials of an AI-powered radio access network (RAN) over CMCC’s network. Utilizing CMCC’s 4G and 5G networks, the companies completed an AI-based real-time user equipment (UE) traffic bandwidth forecast trial in Shanghai as well as a network anomaly detection trial in Taiyuan, the capital city of China’s Shanxi province.
During the trial, China Mobile introduced its ‘i-wireless-intelligent and simplicity 5G network’ concept, a series of technologies designed to create a greener, smarter, and more efficient 5G network. The near-real-time RAN Intelligent Controller (RIC) is one of these technologies and a new network element that enables near real-time control and optimization of RAN elements enabled by real-time data exposure and cross-layer perception capabilities utilizing AI and ML applications.
In the trial, the RIC was included in the edge cloud using Nokia’s AirFrame Open Edge server platform. The RIC platform enables increased network optimization capabilities through policy-guided, closed-loop automation. These are fundamental to further advance the 5G RAN architecture, enabling a wide range of intelligent, real-time data-driven, network automation, and optimization applications.
In Shanghai, the trial confirmed that AI-based real-time user equipment (UE) traffic prediction accuracy exceeded 90 percent in a live 5G network test. This was achieved by estimating the UE radio quality and related throughput for 100 milliseconds. With the real-time RAN data exposure capability, Nokia’s 5G AirScale base station was able to send UE radio quality information to the RIC in real-time, which is critical for the accuracy of the predictions.
Nokia and CMRI worked together to design the trial solution The trial’s test specifications were defined by the China Mobile Research Institute (CMRI), Shanghai Mobile, and Nokia.
Nokia, Shanxi Mobile and the China Mobile Research Institute (CMRI) also trialed network anomaly detection technology. The trial 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. The AI/ML-powered anomaly detection solution can drastically decrease the time needed to analyze issues and find the root cause. For operators, it represents a cost saving of more than 70 percent on human resources required to process the issues. Nokia’s anomaly detection platform software (SW) architecture offers a distributed and split SW architecture and is suitable for non-real-time and near-real-time RIC deployment.
Huang Yuhong, Deputy Director of China Mobile Research Institute, said: “RIC plays a key role in enabling AI/ML capability in the RAN, which is of great significance to realize the concept of the ‘i-wireless-intelligent and simplicity 5G network’. Nokia and CMCC’s trials are very meaningful for RIC commercialization. China Mobile has put effort into the AI-assisting RAN network technology. We are pleased to complete these trials using AI to forecast UE transmission bandwidth and detect anomalies on CMCC’s live network with our partner Nokia. The field trial proved the availability of RIC enabling network enhancements through customized real-time BTS data analysis and control.”
Pasi Toivanen, Head of Edge Cloud Platforms BU at Nokia, commented: “We are excited to have worked with China Mobile on this project to advance RAN network intelligence. We believe it will be a key asset in improving the wireless network efficiency and the experience of its subscribers. This is an example of Nokia’s commitment to supporting our customers in the delivery of world-class network performance.”
An overall results of the trial are
- Trials on CMCC’s live network used Artificial Intelligence (AI) to forecast bandwidth and detect anomalies with 90 percent accuracy.
- Operators set to make significant cost savings of over 70 percent due to the lack of human intervention required to process issues.
- Nokia’s RAN Intelligent Controller acts as a gateway to AI and Machine Learning (ML) technologies, enabling a range of real-time data-driven network enhancements.
