Device and method for performing multi-user precoding in wireless communication system

A communication device comprising:

• at least one processor;
• and
• at least one computer memory connected to the at least one processor and configured to store instructions that direct operations as executed by the at least one processor,
• wherein the operations comprise:
• transmitting configuration information related to channel state information (CSI) feedback to candidate devices;
• transmitting reference signals corresponding to the configuration information;
• receiving CSI feedback signals from the candidate devices;
• determining precoding vectors for participating devices that are at least part of the candidate devices;
• performing precoding for data to the participating devices using the precoding vectors;
• and
• transmitting the precoded data,
• wherein the participating devices are determined based on information including magnitude values of precoding vectors for the candidate devices determined by a decoder neural network based on the CSI feedback signals generated by an encoder neural network.

A device for performing multiuser precoding in a wireless communication system, the device comprising:

• a transceiver;
• and
• a processor connected to the transceiver,
• wherein the processor is configured to:
• transmit configuration information related to channel state information (CSI) feedback to candidate devices;
• transmit reference signals corresponding to the configuration information;
• receive CSI feedback signals from the candidate devices;
• determine precoding vectors for participating devices that are at least part of the candidate devices;
• perform precoding for data to the participating devices using the precoding vectors;
• and
• transmit the precoded data,
• wherein the participating devices are determined based on information including magnitude values of precoding vectors for the candidate devices determined by a decoder neural network based on the CSI feedback signals generated by an encoder neural network.