Method and apparatus for reference symbol pattern adaptation
Capability of a user equipment to support machine learning adaptation by a base station of a reference signal pattern is signaled between the base station and the user equipment. Configuration information from the base station indicates one or more of enabling or disabling of machine learning adaptation of the reference signal pattern, a machine learning model used for machine learning adaptation of the reference signal pattern, updated model parameters for the machine learning model, or whether model parameters received from the user equipment will be used for machine learning adaptation of the reference signal pattern. Model training may be performed or model parameters received, and reference signals are received from the base station. Information on a reference signal pattern may be transmitted by the user equipment to the serving base station. Assistance information may be transmitted by the user equipment to the base station, which configures a reference signal pattern.
1. A user equipment (UE), comprising:
a processor; and
a transceiver operably coupled to the processor, the transceiver configured to:
transmit, to a base station (BS), information indicating capability of the UE to support adaptation of a reference signal (RS) pattern,
receive, from the BS, first configuration information, the first configuration information indicating one or more of enabling or disabling of adaptation of the RS pattern, a machine learning (ML) model used for ML adaptation of the RS pattern, updated model parameters for the ML model, or whether model parameters received from the UE will be used for ML adaptation of the RS pattern,
receive, from the BS, second configuration information, the second configuration information indicating a first RS pattern,
receive an RS with the first RS pattern,
transmit, to the BS, assistance information,
in response to transmitting the assistance information, receive, from the BS, third configuration information indicating a second RS pattern, wherein the first RS pattern is different from the second RS pattern, and
receive the RS with the second RS pattern.
2. The UE of claim 1 , wherein the transceiver is further configured to one of transmit information on one of a downlink RS pattern or an uplink RS pattern to the BS or receive a configuration of one of a downlink RS pattern or an uplink RS pattern from the BS.
3. The UE of claim 1 , wherein the transceiver is configured to receive, from the BS, a configuration of the first RS pattern or the second RS pattern via radio resource control (RRC) signaling, wherein the configuration is indicated by one of an RS pattern index or a time/frequency density for the RS pattern.
4. The UE of claim 1 , wherein the transceiver is configured to transmit, to the BS, assistance information to support adaptation of an RS pattern, wherein:
the assistance information comprises one or more of UE location, UE speed, UE trajectory, estimated downlink (DL) channel delay spread, estimated DL channel Doppler spread, estimated DL channel coherence bandwidth, estimated DL channel coherence time, or radio resource management (RRM) metrics,
the assistance information is used for model inference of an RS pattern,
a format for the assistance information is transmitted via a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH), and
the format for the assistance information comprises one of a new uplink control information (UCI) type, a new PUCCH format, or a new media access control control element (MAC CE).
5. The UE of claim 4 , wherein:
the assistance information includes an ML model inference result, and
the ML model inference result comprises one or more of a recommendation for a reference symbol pattern index, a recommendation for a reference symbol density in the time domain, or a recommendation for a reference symbol density in the frequency domain.
6. The UE of claim 1 , wherein the transceiver is configured to receive a configuration of one of a UE-specific or site-specific codebook or an update for the one of the UE-specific or site-specific codebook, the one of the UE-specific or site-specific codebook including:
common parts and UE-specific or site-specific parts,
a UE-specific or site-specific RS pattern, and
artificial intelligence (AI) or ML parameters for channel state information (CSI) feedback.
7. The UE of claim 6 , wherein the UE is configured to use a default codebook in addition to the one of the UE-specific or site-specific codebook.
8. The UE of claim 1 , wherein;
the processor is configured to perform ML model training, or
the transceiver is further configured to receive trained ML model parameters.
9. A method, comprising:
transmitting, from a user equipment (UE) to a base station (BS), information indicating capability of the UE to support adaptation of a reference signal (RS) pattern;
receiving, from the BS, first configuration information, the first configuration information indicating one or more of enabling or disabling of adaptation of the RS pattern, a machine learning (ML) model used for ML adaptation of the RS pattern, updated model parameters for the ML model, or whether model parameters received from the UE will be used for ML adaptation of the RS pattern;
receiving, from the BS, second configuration information, the second configuration information indicating a first RS pattern;
receiving an RS with the first RS pattern;
transmitting, to the BS, assistance information;
in response to transmitting the assistance information, receiving, from the BS, third configuration information indicating a second RS pattern, wherein the first RS pattern is different from the second RS pattern; and
receiving the RS with the second RS pattern.
10. The method of claim 9 , comprising one of transmitting information on one of a downlink RS pattern or an uplink RS pattern to the BS or receiving a configuration of one of a downlink RS pattern or an uplink RS pattern from the BS.
11. The method of claim 9 , comprising receiving, from the BS, a configuration of the first RS pattern or the second RS pattern via radio resource control (RRC) signaling, wherein the configuration is indicated by one of an RS pattern index or a time/frequency density for the RS pattern.
12. The method of claim 9 , comprising transmitting, to the BS, assistance information to support adaptation of an RS pattern, wherein:
the assistance information comprises one or more of UE location, UE speed, UE trajectory, estimated downlink (DL) channel delay spread, estimated DL channel Doppler spread, estimated DL channel coherence bandwidth, estimated DL channel coherence time, or radio resource management (RRM) metrics,
the assistance information is used for model inference of an RS pattern,
a format for the assistance information is transmitted via a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH), and
the format for the assistance information comprises one of a new uplink control information (UCI) type, a new PUCCH format, or a new media access control control element (MAC CE).
13. The method of claim 12 , wherein:
the assistance information includes an ML model inference result, and
the ML model inference result comprises one or more of a recommendation for a reference symbol pattern index, a recommendation for a reference symbol density in the time domain, or a recommendation for a reference symbol density in the frequency domain.
14. The method of claim 9 , comprising receiving a configuration of one of a UE-specific or site-specific codebook or an update for the one of the UE-specific or site-specific codebook, the one of the UE-specific or site-specific codebook including:
common parts and UE-specific or site-specific parts,
a UE-specific or site-specific RS pattern, and
artificial intelligence (AI) or ML parameters for channel state information (CSI) feedback.
15. The method of claim 14 , wherein the UE is configured to use a default codebook in addition to the one of the UE-specific or site-specific codebook.
16. The method of claim 14 , wherein the one of the UE-specific or site-specific codebook is a precoding matric indicator (PMI)-based codebook in which a set of precoding matrices and corresponding indices are UE-specifically or site-specifically configured.
17. A base station (BS), comprising:
a processor; and
a transceiver configured to
receive, from a user equipment (UE), information indicating capability of the UE to support machine learning (ML) adaptation of a reference signal (RS) pattern,
transmit, to the UE, first configuration information, the first configuration information indicating one or more of enabling or disabling of adaptation of the RS pattern, an ML model used for ML adaptation of the RS pattern, updated model parameters for the ML model, or whether model parameters received from the UE will be used for ML adaptation of the RS pattern,
transmit, to the UE, second configuration information, the second configuration information indicating a first RS pattern,
transmit an RS with the first RS pattern,
receive, from the UE, assistance information,
in response to receiving the assistance information, transmit, to the UE, third configuration information indicating a second RS pattern, wherein the first RS pattern is different from the second RS pattern, and
transmit the RS with the second RS pattern.
18. The BS of claim 17 , wherein the transceiver is configured to transmit a configuration of one of a downlink RS pattern or an uplink RS pattern to the UE.
19. The BS of claim 17 , wherein the transceiver is configured to transmit, to the UE, a configuration of the first RS pattern or the second RS pattern via radio resource control (RRC) signaling, wherein the configuration is indicated by one of an RS pattern index or a time/frequency density for the RS pattern.
20. The BS of claim 17 , wherein the transceiver is configured to receive, from the UE, assistance information to support adaptation of an RS pattern, wherein:
the assistance information comprises one or more of UE location, UE speed, UE trajectory, estimated downlink (DL) channel delay spread, estimated DL channel Doppler spread, estimated DL channel coherence bandwidth, estimated DL channel coherence time, or radio resource management (RRM) metrics,
the assistance information is used for model inference of an RS pattern,
a format for the assistance information is transmitted via a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH), and
the format for the assistance information comprises one of a new uplink control information (UCI) type, a new PUCCH format, or a new media access control control element (MAC CE).