EP-4740566-A1 - METHOD AND PROCEDURE FOR PERFORMANCE MONITORING AND FEEDBACK

Abstract

A user equipment device (UE) may encode a data collection request, for training a CSI prediction Al-model, for transmission of the data collection request to a next generation node B (gNB) for monitoring and feedback procedure for an artificial intelligence based (Al-based) channel state information (CSI) prediction model. The UE may decode network configuration information (NCI) for monitoring the Al based CSI prediction model, received from the gNB. The NCI identifies a CSI-RS configuration of a CSI-RS resource set to be received at the UE to enable the UE to monitor the Al-based CSI prediction model. The UE may perform one or more UE measurements on a CSI-RS in the CSI-RS resource set according to the NCI. The UE may monitor a performance of the AI- based CSI prediction model relative to the UE measurements of the CSI-RS. The UE may encode a performance monitoring report based on the monitored performance.

Inventors

• NIU, HUANING
• YANG, WEIDONG
• HE, HONG
• ZENG, WEI
• ZHANG, DAWEI
• OTERI, OGHENEKOME
• SUN, HAITONG

Assignees

• Apple Inc.

Dates

Publication Date

20260513

Application Date

20240802

Claims (20)

1. 1. An apparatus of a user equipment (UE) configured to perform a monitoring and feedback procedure for an artificial intelligence based (Al-based) channel state information (CSI) prediction model, the apparatus comprising: one or more processors, coupled to a memory, configured to: decode network configuration information for monitoring the Al based CSI prediction model, received from a next generation node B (gNB), wherein the network configuration information identifies a CSI Reference Signals (CSI- RS) configuration of a CSI-RS resource set to be received at the UE to enable the UE to monitor the Al-based CSI prediction model; perform one or more UE measurements on a CSI-RS in the CSI-RS resource set according to the network configuration information; monitor a performance of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI-RS; and encode a performance monitoring report based on the monitored performance for transmission to the gNB.
2. 2. The apparatus of claim 1, wherein the performance monitoring report includes information to request permission from the gNB, to: switch the Al-based CSI prediction model to an alternative Al-based CSI prediction model; deactivate the Al-based CSI prediction model; or activate the Al-based CSI prediction model.
3. 3. The apparatus of claim 1, wherein the one or more processors are further configured to decode, at the UE, a message from the gNB providing instructions for the UE to fall back to a non- Al based CSI prediction model based on the performance monitoring report.
4. 4. The apparatus of claim 1, wherein the one or more processors are further configured to encode the performance monitoring report based on the monitored performance for periodic transmission to the gNB to enable a network of the gNB to provide instructions to the UE to: switch the UE to an alternative Al-based CSI prediction model; deactivate the Al-based CSI prediction model used by the UE; or activate the Al-based CSI prediction model used by the UE.
5. 5. The apparatus of claim 1, wherein the one or more processors are further configured to decode, at the UE, a message from the gNB providing instructions for the UE to fall back to a non- Al based CSI prediction model based on the performance monitoring report.
6. 6. The apparatus of claim 1, wherein the network configuration information includes information to enable the one or more processors to: identify a UE channel prediction window time period for channel prediction at the UE using the Al-based CSI prediction model; determine an overlap of an existing CSI-RS comprising a periodic CSI- RS or a semi-persistent CSI-RS configured to be received at the UE during the UE channel prediction window time period; and monitor the performance of the Al-based CSI prediction model using a comparison of the channel prediction at the UE and a measurement of the existing CSI-RS during the UE channel prediction window time period.
7. 7. The apparatus of claim 1, wherein the network configuration information includes information to enable the one or more processors to: identify a CSI-RS configuration set for performance monitoring; measure a CSI-RS received at the UE according to the CSI-RS configuration set; and monitor the performance of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI-RS in the CSI-RS configuration set.
8. 8. The apparatus of claim 7, wherein the network configuration information includes a new CSI-RS resource set to be used at the UE for periodic performance monitoring to enable the UE to use the new CSI-RS resource set when a prediction window of the Al-based CSI prediction model does not align with periodic or semi -persistent transmission of periodic or semi-persistent CSI-RS received from the gNB or when there is an absence of any CSI-RS configuration information received from the gNB.
9. 9. The apparatus of claim 1, wherein the one or more processors are further configured to estimate, using the Al-based CSI prediction model, a future channel at a future CSI-RS location based on a previous one or more UE measurements of the CSI-RS.
10. 10. The apparatus of claim 1, wherein the one or more processors are further configured to estimate, using the Al-based CSI prediction model, a future channel at a future CSI-RS location of a periodic CSI-RS plus a delta offset time t, based on a previous one or more UE measurements of the periodic CSI-RS, wherein t is a time period less than a periodic time period of the periodic CSI-RS.
11. 11. The apparatus of claim 1, wherein the CSI-RS configuration of the CSI-RS resource set to monitor the performance of the Al-based CSI prediction model comprises one or more of: a monitoring periodicity of the CSI-RS resource set comprising a measurement window and a prediction window; or a time, a frequency, and a port of a CSI-RS RS resource in the CSI- RS resource set that occurs within the measurement window of CSI-RS in a measurement set of the CSI-RS resource set; or a time, a frequency, and a port of a CSI-RS RS resource in the CSI- RS resource set that occurs within a prediction window of a channel prediction that is made using the Al-based CSI prediction model, wherein the channel prediction is based on the CSI-RS in the measurement window.
12. 12. The apparatus of claim 11, wherein the CSI-RS configuration includes a CSI-RS resource set that enables the UE to periodically monitor the performance of the Al-based CSI prediction model by performing a comparison of a measurement of a CSI-RS within the CSI-RS resource set with a channel prediction of the Al-based CSI-prediction model, wherein the comparison is configured to occur within a measurement window, or within a prediction window.
13. 13. The apparatus of claim 11, wherein the one or more processors are configured to decode a radio resource control (RRC) message from the gNB providing the CSI- RS configuration of the CSI-RS resource set.
14. 14. The apparatus of claim 13, wherein the one or more processors are configured to receive, via downlink control information (DCI) or a media access channel (MAC) control element (CE), an activation or a deactivation of the CSI-RS configured by the RRC message.
15. 15. The apparatus of claim 14, wherein the one or more processors are configured to encode a preferred CSI-RS monitoring set request for transmission from the UE to the gNB to select a preferred resource set of the CSI-RS resource set configured by the RRC message.
16. 16. The apparatus of claim 15, wherein the RRC message is a UE assistance information (UAI) message used to select the preferred resource set.
17. 17. The apparatus of claim 14, wherein the RRC message is event driven, the event comprising one or more selected from the group consisting of: a change in speed of the UE by more than a threshold amount (i.e., from 30 Kph to 60 Kph); or a change in antenna type at the gNB.
18. 18. The apparatus of claim 1, wherein the one or more processors are configured to encode the performance monitoring report, wherein the performance monitoring report comprises one or more of: key performance indicators (KPI) calculated at the UE, comprising: normalized mean square error (NMSE) between a channel prediction of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI- RS; squared generalized cosine similarity (SGCS) of a precoding matrix indicator (PMI) of a predicted channel relative to the one or more UE measurements of the CSI-RS; or information to enable key performance indicators to be calculated at a network, comprising: the channel predictions of the Al-based CSI prediction model; the one or more UE measurements of the CSI-RS; predicted PMI values; and measured PMI values.
19. 19. The apparatus of claim 1, wherein the one or more processors are configured to generate the performance monitoring report based on the performance of the AI- based CSI prediction model relative to the one or more UE measurements of the CSI-RS to identify an indication of error and an indication of success, comprising: identify the indication of error when an output of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI-RS is outside of a threshold level; identify the indication of success when the output of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI-RS is within the threshold level; increment a counter when the indication of error occurs; reset the counter when the indication of success occurs; and generate the performance monitoring report when the counter increments to a counter threshold level.
20. 20. An apparatus of a user equipment (UE) configured to perform monitoring and feedback procedure for an artificial intelligence based (Al-based) channel state information (CSI) prediction model, the apparatus comprising: one or more processors, coupled to a memory, configured to: decode network configuration information for monitoring the Al based CSI prediction model, received from a next generation node B (gNB), wherein the network configuration information identifies a CSI Reference Signals (CSI- RS) configuration of a CSI-RS resource set to be received at the UE to enable the UE to monitor the Al-based CSI prediction model; perform one or more UE measurements on a CSI-RS in the CSI-RS resource set according to the network configuration information; monitor a performance of the Al-based CSI prediction model relative to the one or more UE measurements of the CSI-RS; and encode a performance monitoring report based on the monitored performance for transmission to the gNB; wherein the performance monitoring report includes information to request permission from the gNB, to: switch the Al-based CSI prediction model to an alternative AI- based CSI prediction model; deactivate the Al-based CSI prediction model; or activate the Al-based CSI prediction model.

Description

METHOD AND PROCEDURE FOR PERFORMANCE MONITORING AND FEEDBACK FIELD [0001] Embodiments of the invention relate to wireless communications, and more particularly to apparatuses, systems, and methods to perform monitoring and feedback procedure for an artificial intelligence based (Al-based) channel state information (CSI) prediction model, including systems, methods, and mechanisms for a UE to initiate data collection to train an Al prediction model during 5G NR communications. DESCRIPTION OF THE RELATED ART [0002] Wireless communication systems are rapidly growing in usage. In recent years, wireless devices such as smart phones and tablet computers have become increasingly sophisticated. In addition to supporting telephone calls, many mobile devices now provide access to the internet, email, text messaging, and navigation using the global positioning system (GPS), and are capable of operating sophisticated applications that utilize these functionalities. Additionally, there exist numerous different wireless communication technologies and standards. [0003] Long Term Evolution (LTE), also referred to as the Evolved Universal Terrestrial Radio Access Network (E-UTRAN), has been the technology of choice for the majority of wireless network operators worldwide, providing mobile broadband data and high-speed Internet access to their subscriber base. LTE was first proposed as an upgrade to the fourth generation (4G) of the Third Generation Partnership Project (3 GPP) in 2004 and was first standardized in 2008. Since then, as usage of wireless communication systems has expanded exponentially, demand has risen for wireless network operators to support a higher capacity for a higher density of mobile broadband users. Thus, in 2015 study of a new radio access technology began and, in 2017, a first release of the 3GPP Fifth Generation New Radio (5G NR) was standardized. 5th generation mobile networks or 5th generation wireless systems, referred to as 3GPP NR (otherwise known as 5G-NR or NR- 5G for 5G New Radio, also simply referred to as NR). NR proposes a higher capacity for a higher density of mobile broadband users, also supporting device-to-device, ultra-reliable, and massive machine communications, as well as lower latency and lower battery consumption, than LTE standards. [0004] 5G-NR provides, as compared to LTE, a higher capacity for a higher density of mobile broadband users, while also supporting device-to-device, ultra-reliable, and massive machine type communications with lower latency and/or lower battery consumption. Further, NR may allow for more flexible UE scheduling as compared to current LTE. Consequently, efforts are being made in ongoing developments of 5G-NR to take advantage of higher throughputs possible at higher frequencies. [0005] One aspect of wireless communication systems, e.g., systems for NR cellular wireless communications, is the transmission and measurement of reference signals, including channel- state information reference signals (CSLRS). In 5G-NR, Artificial Intelligence (Al) models can be used to predict CSI-RS and reduce the amount of overhead used to communicate and measure reference signals. SUMMARY [0006] Embodiments relate to wireless communications, and more particularly to apparatuses, systems, and methods for monitoring and feedback procedures for an artificial intelligence based (Al-based) channel state information (CSI) prediction model, including systems, methods, and mechanisms for a UE to perform a monitoring and feedback procedure for an Al prediction model during 5G NR communications. [0007] For example, in some embodiments, a UE may encode a data collection request, for training a CSI prediction Al-model, for transmission of the data collection request to a next generation node B (gNB). The UE may decode network configuration information for monitoring the Al based CSI prediction model, received from a next generation node B (gNB). The network configuration information identifies a CSI Reference Signals (CSI- RS) configuration of a CSI-RS resource set to be received at the UE to enable the UE to monitor the Al-based CSI prediction model. The UE may perform one or more UE measurements on a CSI-RS in the CSI-RS resource set according to the network configuration information. The UE may monitor a performance of the Al-based CSI prediction model relative to the one or more UE measurements of the CSLRS. The UE may encode a performance monitoring report based on the monitored performance for transmission to the gNB. In one embodiment, the UE may store the CSI-RS configuration in a memory. [0008] The techniques described herein may be implemented in and/or used with a number of different types of devices, including but not limited to base stations, access points, cellular phones, tablet computers, wearable computing devices, portable media players, vehicles, and any of various other computing devices. [0009] This Summary is intended to provide a brief overview of some