Method and apparatus for support of machine learning or artificial intelligence-assisted CSI feedback

A base station (BS), comprising:

• a transceiver configured to:
• receive capability information indicating a capability of a user equipment (UE) to support a machine learning (ML) based parameter configuration associated with channel state information (CSI) reports,
• transmit configuration information that indicates parameters for the ML based parameter configuration associated with the CSI reports,
• transmit CSI reference signals (RSs), and
• receive the CSI report associated with configuration parameters in one or more domains, the configuration parameters in the one or more domains associated with the configuration information, the CSI-RSs, and information related to localized observations of channel statistics in the one or more domains,
• wherein the parameters include at least one of (i) a resource utilization threshold, (ii) a channel similarity threshold, and (iii) a channel similarity metric;
• wherein, when the parameters include the resource utilization threshold:
• when a resource utilization level is equal to or higher than the resource utilization threshold, the CSI report is based on a first method, and
• when the resource utilization level is lower than the resource utilization threshold, the CSI report is based on a second method;
• wherein, when the parameters include at least one of the channel similarity threshold and the channel similarity metric:
• a channel similarity value is determined based on the channel similarity metric,
• when a channel similarity value is equal to or higher than the channel similarity threshold, the CSI report is based on the first method, and
• when the channel similarity value is lower than the channel similarity threshold, the CSI report is based on the second method;
• and
• wherein the first method is a non-ML-based method and the second method is a ML-based method.

A method performed by a user equipment (UE), the method comprising:

• transmitting capability information indicating a capability of the UE to support a machine learning (ML) based parameter configuration associated with channel state information (CSI) reports;
• receiving configuration information that indicates parameters for the ML based parameter configuration associated with the CSI reports;
• receiving CSI reference signals (RSS);
• measuring the CSI-RSs;
• determining, based on the configuration information, the measured CSI-RSs, and information related to localized observations of channel statistics in one or more domains, configuration parameters in the one or more domains for the CSI reports;
• determining, based on the configuration parameters in the one or more domains, a CSI report;
• and
• transmitting the CSI report,
• wherein the parameters include at least one of (i) a resource utilization threshold, (ii) a channel similarity threshold, and (iii) a channel similarity metric;
• wherein, when the parameters include the resource utilization threshold:
• when a resource utilization level is equal to or higher than the resource utilization threshold, the method further comprises determining the CSI report based on a first method, and
• when the resource utilization level is lower than the resource utilization threshold, the method further comprises determining the CSI report based on a second method;
• wherein, when the parameters include at least one of the channel similarity threshold and the channel similarity metric:
• the method further comprises determining, based on the channel similarity metric, a channel similarity value,
• when the channel similarity value is equal to or higher than the channel similarity threshold, the method further comprises determining the CSI report based on the first method, and
• when the channel similarity value is lower than the channel similarity threshold, the method further comprises determining the CSI report based on the second method;
• and
• wherein the first method is a non-ML-based method and the second method is a ML-based method.