With 3GPP Release 18, 5G Advanced is officially launched. Among the goals of 5G Advanced are to enhance the capabilities of 5G and to expand its use across new devices, deployments, and industries. As network designs become increasingly complex, including a wide range of deployment and usage options, conventional approaches will be unable to provide swift solutions. As manual reconfiguration of cellular communication systems is costly and inefficient, it becomes necessary to automate operational processes using Artificial Intelligence (AI) and Machine Learning (ML), which are expected to reduce costs by automating functions that require human interaction. Through the use of large amounts of data collected from wireless networks, Artificial Intelligence (AI) and Machine Learning (ML) can solve complex and unstructured network problems.
3GPP TSG RAN Meeting #94e document RP-213599 (title: Study on Artificial Intelligence (AI)/Machine Learning (ML) for NR Air Interface) throws some light on the initial set of use cases including CSI feedback enhancement (e.g., overhead reduction, improved accuracy, prediction), beam management (e.g., beam prediction in time, and/or spatial domain for overhead and latency reduction, beam selection accuracy improvement), and positioning accuracy enhancements. According to the document, the specific AI/ML models are not expected to be specified and are left to implementation.
As per Qualcomm, AI can be used in the core and RAN (radio access network) to enable intelligent network operations (e.g., enhanced QoS, enhanced efficiency, simplified deployment, and improved security). Furthermore, on-device AI will be beneficial to the overall 5G system. The underlying enabling capability is radio awareness, which provides valuable knowledge through environmental and contextual sensing that can reduce overheads and latency. Through radio awareness, the 5G system can support enhanced device experiences such as intelligent beam forming and power management, improved system performance such as reduced interference and better spectrum utilization, and improved radio security like better detection and protection against malicious attacks.
Figure 1 shows a general taxonomy of AI/ML use-cases in 5G.
Figure 1: Taxonomy of AI/ML use-cases in 5G
Now, let us take a brief look at the state-of-art of the AI/ML in 5G.
The chart below shows the innovation trend in the field of AI/ML in 5G technology. A significant rise in the patent filing trend can be seen from 2015.
The chart below shows the key market players in the field of AI/ML in 5G technology. Among the leading players, Ericsson is the market leader, followed by LG, Huawei, Samsung, Qualcomm and Nokia.
The chart below shows the innovation hubs in the field of AI/ML in 5G technology. China and the US are ahead of other jurisdictions in terms of innovation activity.
Conclusion: Wireless operators can use artificial intelligence and machine learning to transform their network operations and maintenance processes from a human-driven management model to a self-driven automatic management model. As AI/ML is integrated into 5G advanced, intelligent base stations are capable of making their own decisions, and mobile devices can create dynamically adaptable clusters based on learned data. As a result, network applications will run more efficiently, have lower latency, and be more reliable.
The use of artificial intelligence and machine learning in wireless communication is still in its infancy, but in the coming years they will become more sophisticated and innovative for creating smarter wireless networks. As a result, the next generation of wireless networks will be driven by artificial intelligence and machine learning.
Please note that all the charts shown above are based on raw data and limited to the results of H04W* CPC/IPC. To draw more insights a deeper investigation/manual filtering of the patent data would be required. For a detailed analysis report, please contact us at firstname.lastname@example.org.