Method and apparatus for AI-based UE speed estimation using uplink SRS measurements

An apparatus for performing a wireless communication, the apparatus comprising:

• a communication interface configured to receive uplink (UL) Sounding Reference Signals (SRSs) from a mobile client device;
• and
• at least one processor configured to:
• buffer UL SRS measurements derived from the UL SRSs received from the mobile client device, a number of the UL SRS measurements exceeding a threshold;
• extract features from the UL SRS measurements;
• obtain a machine learning (ML) classifier for determining a category to be used for estimating mobility associated with the mobile client device;
• and
• determine the category of the mobile client device by applying the extracted features to the ML classifier,
• wherein the extracted features include a set of frequency domain Doppler Power Spectral Density measurements that are estimated by:
• deriving Channel Impulse Responses (CIRs) on a per transmit and receive antenna pair basis, from one UL SRS measurement or by combining UL SRS measurements;
• buffering a certain number of CIRs, in a sliding window, wherein each estimated CIR is formed at different SRS reception times;
• deriving a time-domain auto-correlation function obtained by correlating the buffered CIRs at different SRS reception times;
• and
• taking a Fast Fourier Transform of the time-domain auto-correlation function,
• wherein a size of the sliding window is adjustable based on the category to which the mobile client device belongs.

A method for estimating a speed of a mobile client device, the method comprising:

• measuring uplink (UL) Sounding Reference Signals (SRSs) received from a mobile client device;
• buffering UL SRS measurements derived from the UL SRS received from the mobile client device, a number of the UL SRS measurements exceeding a threshold;
• extracting features from the UL SRS measurements;
• obtaining a machine learning (ML) classifier for determining a category to be used for estimating mobility associated with the mobile client device, wherein the ML classifier is a deep neural network including at least one of multiple Convolutional Neural Network (CNN) layers;
• multiple Fully Connected (FC) Neural Network layers;
• or multiple Recurrent Neural Network layers;
• and
• determining the category of the mobile client device by applying the extracted features to the ML classifier.