ThinkSix - Is it time for wireless communication to get smart(er) with AI/ML? Part 2
What role will machine learning play in developing 3GPP Release 18 for 5G-Advanced?
Can machine learning bring innovation to improve the physical layer of a future mobile radio standard? This video looks at 3GPP Release 18 (5G-Advanced), in which industry experts start to determine whether machine learning shall bring a significant benefit, by initially studying three specific use cases.
For the air interface, the study includes an analysis of how to enhance and optimize the reporting of the downlink signal quality measurements based on Channel State Information (CSI) reference signals. Data published based on academic studies, showed an increase in efficiency when compressing and quantizing the number of required information bits when using an autoencoder. The compression factor is large enough to leave no doubt about the effectiveness of the Machine Learning-based procedure for this use case, summarized in this ThinkSix video.