Systems and methods for beam management using artificial intelligence / machine learning model-based downlink transmit beam prediction

Abstract

Systems and methods for beam management using artificial intelligence (AI) / machine learning (ML) model-based downlink (DL) transmit (Tx) beam prediction are discussed. A user equipment (UE) receives, from a base station, beam measurement configuration information; determines, based on a δ value found in the beam measurement configuration information, to generate, using an AI / ML model, one or more DL Tx beam predictions comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams; generates the one or more DL Tx beam predictions comprising the one or more predicted values for the one or more predicted DL Tx beams; and sends, to the base station, the beam report comprising the spatial domain DL Tx beam prediction. Aspects for spatial domain and temporal domain DL Tx beam predictions are discussed. Corresponding network behaviors are discussed.

Description

SYSTEMS AND METHODS FOR BEAM MANAGEMENT USING ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODEL-BASED DOWNLINK TRANSMIT BEAM PREDICTIONCROSS-REFERENCE TO RELATED APPLCIATION

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 574,863, filed April 4. 2024, entitled “SYSTEMS AND METHODS FOR BEAM MANAGEMENT USING ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODEL-BASED DOWNLINK TRANSMIT BEAM PREDICTION,” which is hereby incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] This application relates generally to wireless communication systems, including wireless communication systems using artificial intelligence (AI) / machine learning (ML)-based beam management mechanisms.BACKGROUND

[0003] Wireless mobile communication technology uses various standards and protocols to transmit data between a base station and a wireless communication device. Wireless communication system standards and protocols can include, for example, 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard for Wireless Local Area Networks (WLAN) (commonly known to industry groups as Wi-Fi®).

[0004] As contemplated by the 3GPP, different wireless communication systems' standards and protocols can use various radio access networks (RANs) for communicating between a base station of the RAN (which may also sometimes be referred to generally as a RAN node, a network node, or simply a node) and a wireless communication device known as a user equipment (UE). 3GPP RANs can include, for example. Global System for Mobile communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next-Generation Radio Access Network (NG-RAN).

[0005] Each RAN may use one or more radio access technologies (RATs) to perform communication between the base station and the UE. For example, the GERAN implements GSM and / or EDGE RAT, the UTRAN implements Universal Mobile Telecommunication System (UMTS) RAT or other 3GPP RAT, the E-UTRAN implements LTE RAT (sometimes simply referred to as LTE), and NG-RAN implements NR RAT (sometimes referred to herein as 5G RAT, 5G NR RAT, or simply NR). In certain deployments, the E-UTRAN may also implement NR RAT. In certain deployments, NG-RAN may also implement LTE RAT.

[0006] A base station used by a RAN may correspond to that RAN. One example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E- UTRAN) Node B (also commonly denoted as evolved Node B, enhanced Node B, eNodeB, or eNB). One example of an NG-RAN base station is a next generation Node B (also sometimes referred to as a gNodeB or gNB).

[0007] A RAN provides its communication services with external entities through its connection to a core network (CN). For example, E-UTRAN may utilize an Evolved Packet Core (EPC) while NG-RAN may utilize a 5G Core Network (5GC).

[0008] Frequency bands for 5G NR may be separated into two or more different frequency ranges. For example, Frequency Range 1 (FR1) may include frequency bands operating in sub-6 gigahertz (GHz) frequencies, some of which are bands that may be used by previous standards, and may potentially be extended to cover new spectrum offerings from 410 megahertz (MHz) to 7125 MHz. Frequency Range 2 (FR2) may include frequency bands from 24.25 GHz to 52.6 GHz. Note that in some systems, FR2 may also include frequency bands from 52.6 GHz to 71 GHz (or beyond). Bands in the millimeter wave (mmWave) range of FR2 may have smaller coverage but potentially higher available bandwidth than bands in FR1. Skilled persons will recognize these frequency ranges, which are provided by way of example, may change from time to time or from region to region.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0009] To easily identify the discussion of any particular element or act. the most significant digit or digits in a reference number refer to the figure number in which that element is first introduced.

[0010] FIG. 1A, FIG. IB and FIG. 1C illustrate a flow diagram of UE-sided AI / ML model beam training, UE-sided AI / ML model inference, and UE-sided AI / ML model performance monitoring.

[0011] FIG. 2A illustrates a flow diagram of network-sided AI / ML model training, performing AI / ML model inference and performing AI / ML model performance monitoring.

[0012] FIG. 2B illustrates a flow diagram of a network-sided AI / ML model performing inference and model monitoring.

[0013] FIG. 3 illustrates a diagram for CSI reporting.

[0014] FIG. 4 illustrates a diagram for a mechanism for CSI-RS-based beam management, according to embodiments herein.

[0015] FIG. 5 illustrates a diagram for a mechanism for synchronization signal block (SSB)-based beam management, according to embodiments herein.

[0016] FIG. 6 illustrates a diagram for concepts corresponding to beam management mechanisms according to embodiments herein.

[0017] FIG. 7 illustrates a diagram for concepts corresponding to beam management mechanisms according to embodiments herein.

[0018] FIG. 8 illustrates Rx beam assumptions that may exist.

[0019] FIG. 9 illustrates a diagram for concepts corresponding to beam management mechanisms according to embodiments herein.

[0020] FIG. 10 illustrates a method of a UE, according to embodiments discussed herein.

[0021] FIG. 11 illustrates a method of a base station, according to embodiments discussed herein.

[0022] FIG. 12 illustrates a method of a UE. according to embodiments discussed herein.

[0023] FIG. 13 illustrates a method of a base station, according to embodiments discussed herein.

[0024] FIG. 14 illustrates an example architecture of a wireless communication system, according to embodiments disclosed herein.

[0025] FIG. 15 illustrates a system for performing signaling between a wireless device and a network device, according to embodiments disclosed herein.DETAILED DESCRIPTION

[0026] Various embodiments are described with regard to a UE. However, reference to a UE is merely provided for illustrative purposes. The example embodiments may be utilized with any electronic component that may establish a connection to a network and is configured with the hardware, software, and / or firmware to exchange information and data with the network. Therefore, the UE as described herein is used to represent any appropriate electronic component.

[0027] One possible use case for the use of artificial intelligence (AI) / machine learning (ML) models within wireless communication systems is for beam management (BM). Within a beam management context, use cases involving downlink (DL) transmit (Tx) beam prediction for both / either UE-sided AI / ML models and / or network-sided AI / ML models may be of interest.

[0028] Uses of DL Tx beam prediction may be understood according to multiple possible cases. First such cases for DL Tx beam prediction may be understood as “spatial domain DL Tx beam prediction” cases. In such cases, a DL Tx beam prediction is made for a first set (Set A) of one or more predicted DL Tx beams by an AI / ML model using actual measurement results of a (e.g., different, smaller) second set (Set B) of one or more measured DL Tx beams. In this case, the DL Tx beam prediction may be understood to have an effective time that is the time that the prediction is generated and / or reported. Note the case of “spatial domain DL Tx beam prediction” may also be referred to herein as “BM-Casel.”

[0029] Second such cases for DL Tx beam prediction may be understood as “temporal domain DL Tx beam prediction” cases. In such cases, one or more DL Tx beam predictions is made for a first set (Set A) of one or more predicted DL Tx beams by an AI / ML model using actual measurement results of a (e.g., different, smaller) second set (Set B) of one or more measured DL Tx beams. In this case, multiple measurements of the Set B of beams may be taken. Further, the one or more DL Tx beam predictions may be understood to each have (e.g.. different) effective times that may be later than the time that the prediction itself is generated and / or reported (these later effective times may also be generated by the AI / ML model during the course of generating the one ormore DL Tx beam predictions). Note the case of ‘‘temporal domain DL Tx beam prediction’" may also be referred to herein as “BM-Case2.”

[0030] It may be beneficial to develop a common framework (e.g., a common signaling and / or operational framework) that incorporates / allows for the use of both BM-Casel and BM-Case2. For example, it may be beneficial to develop a wireless communication system that uses a single configuration scheme / configuration mechanism that allows the network to dynamically configure the UE for either BM-Casel or BM-Case2 operation. This may reduce the implementation burden of system hardware and signaling at system devices, and / or reduce network signaling overhead (e.g., as compared to cases where separate configuration and signaling schemes are used with the UE for each of BM- Casel and BM-Case2).

[0031] Signaling and / or mechanism(s) for facilitating lifecycle management (LCM) operations specific to beam management use cases may be of interest. Further, method(s) to ensure consistency between training and inference regarding network side additional conditions (if identified) for an inference at UE may be desirable.

[0032] A general framework for Al / ML model use for one-sided AI / ML models may include consideration of, for example, signaling and protocol aspects of LCM, including enabling functionality' and / or issues of AI / ML model selection, activation, deactivation, switching, fallback, and optionally further including the use of identification related signaling in relation to these tasks; signaling and / or mechanism(s) for LCM to facilitate AI / ML model training, inference, performance monitoring, data collection for both / either UE-sided and network-sided models; and / or signaling mechanisms for applicable functionalities / AI / ML models.

[0033] Aspects with respect to data collection and / or consistency assurance of an Al eco-system in this AI / ML model context may include benefits and details of model identification concepts and procedures in the context of LCM. Further, CN / operations administration and maintenance (OAM) / over the top (OTT) collection of UE-sided model training data aspects may be considered, including issues of identification of corresponding contents of UE data collection for AI / ML wireless communications use cases and / or related UE data collection mechanisms, along with the implications and limitations of each of the related methods. Further, with respect to model transfer / delivery, standardized solutions for transferring / delivering AI / ML model(s)considering at least the solutions identified during with respect to AI / ML wireless communications use may be considered.

[0034] Aspects with respect to testability and interoperability' regarding AI / ML model use as described herein may include considerations of testing frameworks and / or procedures for one-sided models and / or testing options for two-sided models. These issues may be considered in view of, for example: any relation to existing requirements (e.g., according to any existing standard for such wireless communications systems); performance monitoring and LCM aspects considering use-case specifics; generalization aspects; static / non-static scenarios / conditions and propagation conditions for testing (e.g.. cluster delay lined (CDL), field data, etc.); and / or UE processing capability and / or limitations; post-deployment validation due to AI / ML model change / drift.

[0035] A CSI reference resource for a serving cell may be defined as follows. In the frequency domain, the CSI reference resource is defined by the group of downlink physical resource blocks corresponding to the band to which the derived CSI relates. In the time domain, the CSI reference resource for a CSI reporting in uplink slot n' is defined by a single downlink slot n — nCSI ref, where n = n' • and iiDLand fj.ULarethe subcarrier spacing configurations for DL and UL. respectively. For periodic and semi-persistent CSI reporting, if a single CS1-RS / SSB resource is configured for channel measurement, nCSI ref is the smallest value greater than or equal to 4 •1101-, such that it corresponds to a valid downlink slot, or. if multiple CSI-RS / SSB resources are configured for channel measurement, nCSI ref is the smallest value greater than or equal to 5 • 2DL, such that it corresponds to a valid downlink slot.

[0036] For aperiodic CSI reporting, if the UE is indicated by the DCI to report CSI in the same slot as the CSI request, nCS[ ref is such that the reference resource is in the same valid downlink slot as the corresponding CSI request. Otherwise, nCSI ref is the smallest value greater than or equal tosuch that slot n —ncsi_ref corresponds to a valid downlink slot, where Z' corresponds to a delayrequirement.

[0037] When periodic or semi-persistent CSI-RS / channel state information interference measurement (CSI-IM) or SSB is used for channel / interference measurements, the UE is not expected to measure channel / interference on the CS1-RS / CSI-IM / SSB whose lastOFDM symbol is received up to Z' symbols before transmission time of the first OFDM symbol of the aperiodic CSI reporting.

[0038] A slot in a serving cell shall be considered to be a valid downlink slot if it comprises at least one higher layer configured downlink or flexible symbol, and it does not fall within a configured measurement gap for that UE.

[0039] Note that in some carrier aggregation (CA) and / or non-terrestrial network (NTN) contexts, changes to / differences within the formulas described in the preceding definition may be applicable in some wireless communications systems.

[0040] FIG. 1A, FIG. IB and FIG. 1C illustrate a flow diagram 100 of UE-sided AI / ML model beam training, UE-sided AI / ML model inference, and UE-sided AI / ML model performance monitoring.

[0041] The flow diagram 100 illustrates the training of a UE-sided AI / ML model 208, UE-sided AI / ML model inference 128, and UE-sided model performance monitoring 154. The flow diagram 100 begin as the UE 102 may transmit 110 AI / ML data collection capability signaling to the network 104 (also referred to as “step 1”). Then, the network 104 may transmit 112 an AI / ML data collection configuration including a reference signaling configuration to the UE 102 (also referred to as “step 2’"). The AI / ML data collection configuration transmitted to the UE 102 may also include dataset ID and assistance information 114. Accordingly, the network 104 may transmit 116 collected reference data to the UE 102 (also referred to as “step 3”). Then, the UE 102 may perform training 118 on the received reference data collection (also referred to as "step 4"). Subsequently, the UE 102 may forward 120 the training data obtained by performing training 118 at the UE 102 to the training entity of the network-sided AI / ML model 106 (also referred to as “step 5"). Note that the training entity of the network-sided AI / ML model 106 may take the form of an OTT server, an 0 AM server, and / or a common name server 122. Based on the received training data, the training entity of the network-sided AI / ML model 106 may perform training 124 of a neural network (NN) model (an AI / ML model) (also referred to as “step 6”). Then, the training entity of the network-sided AI / ML model 106 may transmit 126 the NN model / AI / ML model to the UE 102 (also referred to as "step 7")

[0042] UE-sided AI / ML model inference 128 as a part of flow diagram 100 is now discussed. The UE 102 and the network 104 may transmit 130 AI / ML inference and / or monitoring capability7signaling between the UE 102 and the network 104 (also referredto as “step 8”). Note that the UE 102 and the network 104 may use, for functionalitybased LCM or model-ID based LCM, capability’ signaling and / or RRCReconfigurationComplete signaling 132. Then, the UE 102 and the network 104 may transmit 134 a model identification between the two entities (the signaling may be transparent or non-transparent for 3GPP signaling) (also referred to as “step 9’"). Accordingly, the network 104 may transmit 136 AI / ML beam management inference configuration including reference signal configuration to the UE 102 (also referred to as “step 10”). Note that for training and / or inference consistency the network may provide 138 a dataset ID and / or assistance information to the UE 102. Then, the network 104 may perform 140 a reference signal transmission to the UE 102 (also referred to as “step 11”). Subsequently, the UE 102 may perform 142 AI / ML model inference (also referred to as "step 12") (e.g., using / based on a measurement of the transmitted reference signal). In response to the performed inference, the UE 102 may transmit 144 a beam report to the network 104 (also referred to as "step 13"). In some cases, the best beam or a set of good beams (of the Set A beams) may be recommended 146 according to various examples of representative information, such as beam indices, predicted reference signal received power (RSRP) values, probabilities, and / or predicted confidence values.

[0043] Optionally, as a confirmation step for the beam prediction, the network 104 may transmit 148 the top Set A beams to the UE 102 (also referred to as “step 14”). In response, the UE 102 may transmit 150 beam reporting of the top Set A beams to the network 104 (also referred to as “step 15”).

[0044] Then, the network 104 may transmit 152 a beam indication to the UE 102 to update control beam(s) and / or data beam(s) (also referred to as “step 16”).

[0045] UE-sided model performance monitoring 154 as part of flow diagram 100 is now discussed. The network 104 may transmit 156 a reference signal configuration and / or perform a transmission including at least Set B beams for beam management of control beam(s) and / or data beam(s) (also referred to as “step 17”). Then, the network 104 may transmit 158 a reference signal to the UE 102 (also referred to as “step 18”). Accordingly, the UE 102 may then transmit 160 a beam report on the Set B beams and Set A beams to the network 104 for analysis (also referred to as “step 19”) and in response, the network 104 may transmit 162 LCM management information to the UE 102 (also referred to as “step 20”) based on the analysis of the Set B beams and the Set A beam.

[0046] As illustrated in flow diagram 100, for UE-sided AI / ML model training and UE- sided AI / ML model inference, analog beam design information may be embedded in the training data from a time T-l. Beneficially, it may be that no extra assistance information is needed in reference to the analog beams. In some cases, different modules may be used for different bands at the same site under the same operator and the trained AI / ML model may be band-specific. Note that there may not be strict chronological requirements between the training steps and the inference steps.

[0047] FIG. 2A and FIG. 2B illustrate a flow diagram 200 of network-sided AI / ML model training, performing AI / ML model inference and performing AI / ML model performance monitoring.

[0048] The flow diagram 200 illustrates the training of a network-sided AI / ML model 208. The UE 202 may transmit 210 AI / ML data collection capability signaling to the network 204 (also referred to as ‘"step I”). Note that capability signaling. RRCReconfigurationComplete for functionality-based LCM or model-ID based LCM may be used 212. Then, the network 204 may transmit 214 an AI / ML data collection configuration including a reference signaling configuration to the UE 202 (also referred to as “step 2"). Subsequently, the network 204 may perform 216 a reference signal transmission to the UE 202 (also referred to as “step 3”). Then, the UE 202 may perform 218 beam measurement to collect training data (also referred to as “step 4”).Accordingly, the UE 202 may feedback 220 the training data to the network 204 (e.g., in mobile data terminal (MDT) or Layer 1 (LI) signaling) (also referred to as “step 5”). Then, the network 204 may forward 222 to the training data the training entity of network-sided AI / ML model 206 (also referred to as “step 6") and the training entity of netw ork-sided AI / ML model 206 may perform 224 training of a neural netw ork AI / ML model (also referred to as “step 7’'). Accordingly, the training entity of network-sided AI / ML model 206 may transmit 226 the neural network AI / ML model to the network 204, thus deploying it (also referred to as “step 8”).

[0049] The flow diagram 200 further illustrates AI / ML inference and performance monitoring with a network-sided AI / ML model 228. The UE 202 transmits 230 AI / ML inference and / or monitoring capability signaling to the network 204 (also referred to as “step 9"). Then, in response, the network 204 may transmit 232 a reference signal configuration (including at least Set B beams for beam management of control beam(s) and / or data beam(s) (also referred to as “step 10"). Subsequently, the network 204 mayperform 234 a reference signal transmission to the UE 202 (also referred to as ‘‘step 11"). Then, the UE 202 may transmit 236 a beam report on the Set B beams to the network 204 and optionally may transmit other beams to the network 204 (also referred to as ‘'step 12"). Accordingly, the network 204 may perform 238 inference at the network on the AI / ML model (also referred to as “step 13").

[0050] Optionally, the network 204 may transmit 240 a transmission of tap Set A beams (for beam confirmation) to the UE 202 (also referred to as “step 14"). Still optionally, in response, the UE 202 may perform 242 beam measurement (for beam confirmation) (also referred to as “step 15"). Yet still optionally, the UE 202 may transmit 244, to the network 204, beam reporting of the top Set A beams (for beam confirmation) (also referred to as “step 16").

[0051] Then, the network 204 may transmit 246 a beam indication to the UE 202 to update control beam(s) and / or data beam(s) (also referred to as “step 17").

[0052] As illustrated in flow diagram 200, for network-sided AI / ML model training and network-sided inference, analog beam design information may be embedded in the training data from a time T-l. Beneficially, a previous beam management procedure may be kept at a large degree, and enhancements may be limited to time T2, (e g., increasing the number of reported beams). Note that there may not be strict chronological requirements between training steps and inference steps. Prior to inference step 4, discussed herein, if the network is not sure of the inferred Tx beams, the network may transmit a number of candidate beams from Set A to the UE, and the UE may report the Set A beam RSRPs or the best Tx beams back to the network. Similarly, for the UE- sided AI / ML model training, inference, and performance monitoring, the same may arise.

[0053] FIG. 3 illustrates a diagram 300 for CSI reporting. The diagram 300 may correspond to cases of, for example, a 3GPP type II codebook use invoking (in some cases) CSI prediction. The various parameters discussed may be configured via radio resource control (RRC) signaling in some cases.

[0054] Aspects of the diagram 300 related to measurement resources are now discussed. The diagram 300 illustrates the use of a number K of measurement resources 302 of a channel measurement resource (CMR). In the given example, the K measurement resources 302 are channel state information reference signal (CSI-RS) resources (e.g.,aperiodic CSI-RS resources (AP-CSI-RS resources). Note that in various cases, K may take various values (e.g., K G {4, 8, 12}).

[0055] The diagram 300 further illustrates the use of a measurement resource offset 304 that is denoted m. The value m represents an offset between two adjacent ones of the measurement resources 302 of the CMR in slots. The value m may take various values (e.g., m {1, 2} slots).

[0056] Aspects of the diagram 300 related to CSI reporting for / corresponding to DL Tx beams are now discussed. The diagram 300 illustrates a CSI report 310 that is based on measurements of the measurement resources 302. The diagram 300 illustrates that the CSI report 310 contains a number N of predicted CSI 308 that are based on measurement of the measurement resources 302. Note that in various cases, N4 may take various values (e.g.. N4 G { 1. 2, 4, 8}). Each of the predicted CSI 308 has an effective time as indicated on the timeline 314.

[0057] The diagram 300 illustrates a distance 312 (denoted d) between two of the predicted CSI 308. The value d may be denoted in slots. In the case of periodic CSI-RS (P-CSI-RS) or semi-persistent CSI-RS (SP-CSI-RS), the value d may equal the periodicity of the CSI-RS resource. For aperiodic CSI-RS resource, d may take various values (e.g., d G {1, m} slots).

[0058] Embodiments corresponding to the diagram 300 may also rely on a number of selected time / Doppler basis (denoted Q for the number of Doppler frequencies). Note that in some embodiments where N4 > 1, Q G {2}.

[0059] Finally, the diagram 300 illustrates the use of a 8 value 306 (denoted <5) representing a number of slots from the slot of the CSI report 310 slot to the effective time of the first of the predicted CSI 308 from the CSI report 310. In various embodiments, 8 G {-ncsi ref, 0. 1, 2} slots (where ncsi ^ / represents the distance between the slot of the CSI report 310 and the slot of the last of the measurement resources 302).

[0060] Corresponding to embodiments according to FIG. 3, essentially two modes of operations are supported based on the applicable configuration for 3 (the interval between CSI report and targeted effect time of the reported CSI).

[0061] In the case of <5 = -ncsi_ref. non-predictive CSI is reported in the CSI report 310 using existing CSI reporting processes.

[0062] In the case of 3 E {0, 1, 2} the reported CSI is predictive CSI (as the effective time for each of the N4 predicted CSI 308 is for a future occasion, representing a BM- Case2 as described herein).

[0063] It is contemplated that the case of 3 = -ncsi «■ / may be modified such that when 3 = -ncsi_ref, spatial domain DL Tx beam prediction is used in the corresponding CSI report. Such a case thus corresponds to a unified arrangement for dynamically configuring for one of BM-Casel and BM-Case2 at / to the UE, where BM-Casel is supported / indicated when 3 = -ncsi_ref. and BM Case2 is supported / indicated when 3 > 0 (when <5 takes a non-negative value).

[0064] To further develop such a unified scheme, it may be desirable to resolve additional issues. For example, it may be desirable to associate BM-Case2 embodiments (where 3 > 0) with one or more pre-trained AI / ML models for temporal domain DL Tx beam prediction that is available to the UE. It may be that such models may be trained with fixed time intervals between the measurement resources and the associated predicted results (e.g., a fixed value such as 20 milliseconds (ms), 40 ms, etc. may have been used). However, in the arrangement discussed above in relation to FIG. 3, the effective time(s) for the predicted results (e.g., the predicted CSI 308) is / are understood as relative to the timing of the CSI report 310 (according to 3) (and not understood in directly relative terms to the measurement resources 302). Accordingly, mechanisms for preserving accurate alignment between 3 as configured and the particular AI / ML model used to generate the temporal domain DL Tx beam prediction are discussed herein.

[0065] Subject to UE capability7, a UE configured with a CSI-ReportConfig with the higher layer parameter N4 and reportQuantity set to cri-RI-PMI-CQI’ may be assumed to support UE-side CSI prediction. The reported PMI indicates predicted precoder matrices associated with A4consecutive slot intervals, each with duration of d slots, where a value of N4E {1,2, 4, 8} is configured by higher layer parameter N4. If the UE is configured with an aperiodic CSI-RS resource set for channel measurement, the value, in number of slots, of a time unit d E {l,m} is configured by higher layer parameter d, where m is a defined value. If the UE is configured with a periodic or semi-persistent CSI-RS resource set for channel measurement, the value of d is equal to the periodicity of the CSI-RS resource. The earliest of the N4slot intervals starts at slot I — n + 8, where n is the uplink slot in which the CSI is reported and the slot offset 6 E{— nCSI ref, 0,1,2} is configured by higher layer parameter delta, where ncsl ref is a defined value and the value of 8 = — nCSI fcan be configured subject to UE capability.

[0066] For / V4= 1. the UE is expected to report a predicted PMI for slot interval [I. I + d - 1] and the slot offset value 8 = —nCSI ref can be configured only for d > 1. A UE can be configured with JV4= 1 if the higher layer parameter codebookType is set to ‘typell- Doppler-rl8?or ‘typeII-Doppler-PortSelection-rl8’. The reported CQI is associated with slot / and the reported PMI.

[0067] For A4> 1, the UE may be expected to report a PMI which indicates predicted precoder matrices associated with slot intervals [ / + j • d, I + (J + 1) • d — 1]. for j = 0, ... , N4- 1. A UE can be configured with 7V4> 1 if the higher layer parameter codebookType is set to ‘typeII-Doppler-rl8'.

[0068] The UE may be configured by a higher layer parameter TDCQI to report X E {1,2} CQIs for each subband in the CSI reporting band, if cqi-Formatlndicator is set to ‘subbandCQI’, or X E {1,2} CQIs for the entire CSI reporting band, if cqi- Format Indicator is set to ‘widebandCQT. For X= 2, the second CQI includes a 4-bit wideband CQI index and, if subband CQI reporting is configured, a 2-bit subband CQI index, calculated independently from the first CQI, and the two CQIs are reported in the same CSI report.

[0069] FIG. 4 illustrates a diagram 600 for a mechanism for CSI-RS-based beam management, according to embodiments herein. The diagram 400 contemplates cases where an AI / ML model at the UE is used to perform one or more beam predictions of a Set A of DL Tx beams based on a Set B of DL Tx beams, where the Set B of DL Tx beams is represented by one or more CSI-RS resource sets. It is contemplated that the various parameters to be discussed may be configured to the UE that is using the AI / ML model using RRC signaling.

[0070] Aspects of the diagram 400 related to measurement resources are now discussed. The diagram 400 illustrates the use of a number K of measurement resources 402 of a CMR. In the given example, the K measurement resources 402 are each CSI-RS resource sets (e.g., AP-CSI-RS resource sets). It may be that each of the K CSI-RS resource sets is a different CSI-RS resource set. It is also contemplated that the K CSI-RS resource sets may include one or more repetitions of a same CSI-RS resource set.

[0071] Note that across varying embodiments, K may take various values. It may be that in cases corresponding to the use BM-Casel. K = 1, while for cases corresponding to the use of BM-Case2, K > 1. In some embodiments, for cases of periodic and / or semi- persistent measurement resources (e.g., P-CSI-RS resource sets and / or SP-CSI-RS resource sets), K may be up to UE implementation.

[0072] Each of the K AP-CSI-RS resource sets includes one or more CSI-RS resources (e.g., for / as part of the Set B of beams). In the illustration, the four downwards arrows 416 illustrated from one of the CSI-RS resource sets in the measurement resources 402 represent four CSI-RS resources under that CSI-RS resource set (and note that the rest of the CSI-RS resource sets illustrated in FIG. 4 may be similarly constituted). Various values for a number of CSI-RS resources in a CSI-RS resource set (e.g., other than four) may be used in other embodiments. Each of the CSI-RS resources in the CSI-RS resource set may represent (be sent using) a DL Tx beam that is accordingly being measured by the UE as part of the Set B of DL Tx beams, as discussed herein.

[0073] The diagram 400 further illustrates the use of a measurement resource offset 404 that is denoted m. The value m represents an offset between two adjacent ones of the measurement resources 402 of the CMR in slots. The value m may take various values (e.g., in E {10, 20} slots, or a value in milliseconds, etc ).

[0074] Aspects of the diagram 400 related to CSI reporting / beam reporting are now discussed. The diagram 400 illustrates a beam report 410 that is based on measurements of the measurement resources 402. The diagram 400 illustrates that the beam report 410 contains a number N4 of beam predictions 408 that are based on measurement of the measurement resources 402. Each of the illustrated “Predicted beam(s)'’ shown in the beam predictions 408 may relate a predicted information for a Set A of DL Tx beams as discussed herein. Note that in various cases, N4 may take various values (e.g., N4 E {1, 2, 4, 8}). Corresponding to such cases, values of N4 > 1 may be reserved for / indicate the use of BM-Case2. Each of the beam predictions 408 has an effective time as indicated on the timeline 414.

[0075] The diagram 400 illustrates a distance 412 (denoted d) between two of the beam predictions 408. The value d may be denoted in slots. In the case of P-CSI-RS or SP- CSI-RS, the value d may equal the periodicity of CSI-RS resources used in the CSI-RS resource sets in the measurement resources 402. For the case of AP-CSI-RS, d may take various values (e.g., d E {1, m} slots). However, depending on the AI / ML training, dmay not be directly related to the periodicity' of measurement resources or the time-gap between two neighboring measurement resources.

[0076] Finally, the diagram 400 illustrates the use of a 5 value 406 (denoted <5) representing a number of slots from the slot of the beam report 410 to the effective time of the first of the beam predictions 408 from the beam report 410 (which is at slot I as denoted in FIG. 4). In various embodiments, 3 E {-n si ref, 0, 1, 2} slots (where ncsi ref represents the distance between the slot of the beam report 410 and the slot of the last of the measurement resources 402). Corresponding to such cases, values of 3 = -ncsi _re / (or other negative values 8) may be reserved for / indicate the use of BM-Casel, while nonnegative values of 3 may be reserved for / indicate the use of BM-Case2.

[0077] FIG. 5 illustrates a diagram 500 for a mechanism for synchronization signal block (SSB)-based beam management, according to embodiments herein. The diagram 500 contemplates cases where an AI / ML model at a UE is used to perform one or more beam predictions of a Set A of beams based on a Set B of beams, where the Set B of beams is represented by one or more SSB bursts. It is contemplated that the various parameters to be discussed may be configured to the UE that is using the AI / ML model using RRC signaling.

[0078] Aspects of the diagram 500 related to measurement resources are now discussed. The diagram 500 illustrates the use of a number K of measurement resources 502 of a CMR. In the given example, the K measurement resources 402 are each SSB bursts.

[0079] Note that across vary ing embodiments, K may take various values. In some embodiments, K may be up to UE implementation.

[0080] Each of the K SSB bursts includes one or more SSBs (e.g., for / as part of the Set B of beams). In the illustration, the four downwards arrows 516 illustrated off of one of the SSB bursts in the measurement resources 502 represent four SSBs under that SSB burst (and note that the rest of the SSB bursts illustrated in FIG. 5 may be similarly constituted). Various values for a number of SSBs in an SSB burst (e.g., other than four) may be used in other embodiments. Each of the SSBs in the SSB burst set may represent (be sent using) a DL Tx beam that is accordingly being measured by the UE as part of the Set B of DL Tx beams, as discussed herein.

[0081] The diagram 500 further illustrates the use of a measurement resource offset 504 that is denoted m. The value m represents an offset between two adjacent ones of themeasurement resources 502 of the CMR in slots. The value m may take various values (e.g.. m e { 10. 20} slots, or a value in milliseconds, etc.).

[0082] Aspects of the diagram 500 related to CSI reporting / beam reporting are now discussed. The diagram 500 illustrates a beam report 510 that is based on measurements of the measurement resources 502. The diagram 500 illustrates that the beam report 510 contains a number N4 of beam predictions 508 that are based on measurements of the measurement resources 502. Each of the illustrated “Predicted beam(s)” shown in the beam predictions 508 may relate predicted information for a Set A of DL Tx beams as discussed herein. Note that in various cases. N4 may take various values (e.g., N4 E {1, 2, 4, 8}). Corresponding to such cases, values of N4 > 1 may be reserved for / indicate the use of BM-Case2. Each of the beam predictions 508 has an effective time as indicated on the timeline 514.

[0083] The diagram 500 illustrates a distance 512 (denoted d) between two of the beam predictions 508. The value d may be denoted in slots. In some cases, to the use of SSB burst use as in FIG. 5, it may be that d equals a periodicity of the SSBs used in the SSB bursts. In other such cases, it may be that d is a configured value.

[0084] Finally, the diagram 500 illustrates the use of a 5 value 506 (denoted 3) representing a number of slots from the slot of the beam report 510 to the effective time of the first of the beam predictions 508 from the beam report 510 (which is at slot I as denoted in FIG. 5). In various embodiments, 3 E {-ncsi ref. 0, 1. 2} slots (where ncsi ref represents the distance between the slot of the beam report 510 and the slot of the last of the measurement resources 502). Corresponding to such cases, values of 3 = -ncsi_ref(oi other negative values <5) may be reserved for / indicate the use of BM-Casel, while nonnegative values of 3 may be reserved for / indicate the use of BM-Case2.

[0085] FIG. 6 illustrates a diagram 600 for concepts corresponding to beam management mechanisms according to embodiments herein. The diagram 600 contemplates cases where an AI / ML model at a UE is used for beam prediction. Note that while the diagram 600 expressly illustrates the case of a CSI-RS-based beam management mechanism (e.g., as has been described in relation to FIG. 4), it will be understood that the principles discussed in relation to FIG. 6 are applicable for other beam management mechanisms (e.g., the SSB-based beam management mechanism of FIG. 5).

[0086] For cases involving the use of AI / ML models for BM-Case2 (AI / ML models for temporal domain DL Tx beam prediction), various aspects with respect to the determinability of effective times for the beam predictions 602 at the various participants (UE, base station) of the illustrated procedure are contemplated.

[0087] FIG. 6 illustrates that, as has been described elsewhere herein, it may be that effective times of the beam predictions 602 are defined in terms of a 5 value 604 between the beam report 606 and the first beam prediction 608 of the beam predictions 602 (labelled "Predicted beam(s) 1" in FIG. 6). As will be understood, this means that the effective time for the first beam prediction 608 is a function of the timing of the beam report 606. It will then be understood that the timing of any additional beam predictions in the beam predictions 602 are also dependent on the timing of the beam report 606 (because they are timed according to the distance 610 (denoted d) between any two of the beam predictions 602).

[0088] It is noted that this dependency on the timing of the beam report 606 also exists in the case of BM-Casel / spatial domain DL Tx beam prediction.

[0089] It may be that an AI / ML model for such beam management cases as illustrated by the diagram 600 is trained based on an assumed time gap 612 between the measurement resources 614 and the beam predictions 602. The assumption of a known time gap 612 at the training stage may facilitate the training of multiple AI / ML models (e.g.. ahead of time) in a systematic way.

[0090] In the case that AI / ML models for use in such cases are indeed trained according to such time gap assumptions, it will then be beneficial to make multiple such AI / ML models available at the UE. The network (which ultimately controls the timing of the beam report 606 to be sent by the UE via scheduling) may configure the UE to use a 5 value 604 (that is measured relative to the beam report 606) that is compatible with / consistent with a time gap 612 used to train at least one applicable AI / ML model at the UE. That AI / ML model will then be used by the UE to generate the beam predictions 602 for the beam report 606 based on the measurement resources 614. Accordingly, it will be understood that the provision / availability at / to the UE of multiple AI / ML models trained according to different values for the time gap 612 provides the network with the ability to correspondingly variably configure the 5 value 604 used. In such cases, the 5 value 604 may be understood / set in terms of the value -ncsi ref (which aligns with thebeginning of the time gap 612) plus the value of the time gap, e.g., (5 G {-ncsi _ref. -ncsi ref + 20. -ncsi_ref + 40,

[0091] Within this context, it may be that a UE has a capability' of supporting a particular number of and / or particular values for supported time gaps (according to its available / useable AI / ML models). It is contemplated that the UE capability to support a given time gap 612 may be understood in terms of raw time (e.g., 20 ms, 40 ms) and / or in terms of slots (e.g., 20 slots, 40 slots).

[0092] In some embodiments, it may be that the UE supports the use of a variable time gap within a range of values (e.g., a time gap in the range of 20 ms to 40 ms is supported, a time gap in the range of 20 ms to 30 ms is supported, etc.).

[0093] In some embodiments, such capabilities may be set according to specifications for the wireless communication system (e.g., in terms of a minimum set), thus enabling the base station to accordingly select a compatible 5 value 604 for a known available capability (a known useable time gap 612) at the UE.

[0094] In some embodiments, it may be that the UE may report capability information about the number of and / or values for its time gaps 612 it can support with its available AI / ML models (e.g., 20 ms, 40 ms, 20 slots. 40 slots, etc.) to the base station so that the base station is aware of the UE capability and can accordingly select a 6 value 604 to configure to the UE that is compatible with at least one such indicated time gap.

[0095] In some embodiments, it may be that the UE may report capability information about a range of values for which a variable time gap is supported (e.g., a time gap in the range of 20 ms to 40 ms, a time gap in the range of 20 ms to 30 ms, etc.) to the base station so that the base station is aware of the UE capability and can accordingly' select a 5 value 604 to configure to the UE that is compatible with at least one such indicated range.

[0096] It will be noted that in cases where the time gap is understood and / or reported in number of slots rather than raw time, the time gap as understood in terms of raw time can be sub-carrier spacing dependent.

[0097] FIG. 7 illustrates a diagram 700 for concepts corresponding to beam management mechanisms according to embodiments herein. The diagram 700 contemplates cases where an AI / ML model at a base station is used for beam prediction. In such cases, it may be understood that the UE is not engaging in generating beampredications for its beam report 702; rather, it is reporting actual measured values corresponding to the measurement resources 704 in the beam report 702, which are then subsequently used for predictive behavior by the AI / ML model at the base station (not illustrated).

[0098] FIG. 7 thus illustrates the operation of a unified scheme for configuration as discussed herein for the case that the AI / ML model is operated by the network. Note that while the diagram 700 expressly illustrates the case of a CSI-RS-based beam management mechanism, it will be understood that the principles discussed in relation to FIG. 7 are applicable for other beam management mechanisms (e.g., an SSB-based beam management mechanism).

[0099] Aspects of the diagram 700 related to measurement resources are now discussed. The diagram 700 illustrates the use of a number K of measurement resources 704 of a CMR. In the given example, the K measurement resources 704 are each CSI-RS resource sets (e.g., AP-CSI-RS resource sets). It may be that each of the K CSI-RS resource sets is a different CSI-RS resource set. It is also contemplated that the K CSI-RS resource sets may include one or more repetitions of a same CSI-RS resource set.

[0100] Note that across varying embodiments, K may take various values. It may be that in cases corresponding to the use BM-Casel, K = 1, while for cases corresponding to the use of BM-Case2, K > 1. In some embodiments, for cases of periodic and / or semi- persistent measurement resources (e.g., P-CSI-RS resource sets and / or SP-CSI-RS resource sets), K may be up to UE implementation.

[0101] Each of the K AP-CSI-RS resource sets includes one or more CSI-RS resources (e.g.. for / as part of the Set B of beams). In the illustration, the downwards arrows 706 illustrated off of each of the CSI-RS resource sets in the measurement resources 704 represent CSI-RS resources under that corresponding CSI-RS resource set. Various values for a number of CSI-RS resources in a CSI-RS resource set (e.g., other than four) may be used in other embodiments. Each of the CSI-RS resources in the CSI-RS resource set may represent (be sent using) a DL Tx beam that is accordingly being measured by the UE as part of the Set B of DL Tx beams, as discussed herein.

[0102] The diagram 700 further illustrates the use of a measurement resource offset 708 that is denoted m. The value m represents an offset between two adjacent ones of the measurement resources 704 of the CMR in slots. The value m may take various values (e.g., m G {10, 20} slots, or a value in milliseconds, etc.).

[0103] The following is an example of a CSI-ResourceConfig IE that may be used to configure a UE for a beam management mechanism as described herein:CSI-ResourceConfig ::= SEQUENCE { csi-ResourceConfigld CSI-ResourceConfigld, csi-RS-ResourceSetList CHOICE { nzp-CSI-RS-SSB SEQUENCE { nzp-CSI-RS-ResourceSetList SEQUENCE (SIZE (l..maxNrofNZP-CSI-RS-ResourceSetsPerConfig)) OF NZP-CSI-RS-ResourceSetld OPTIONAL, - Need R csi-SSB-ResourceSetList SEQUENCE (SIZE (1 ..maxNrofCSI-SSB-ResourceSetsPerConfig)) OF CSI-SSB-ResourceSetld OPTIONAL— Need R }, csi-IM-ResourceSetList SEQUENCE (SIZE (L.maxNrofCSI-IM-ResourceSetsPerConfig)) OF CSI-IM-ResourceSetld }, bwp-Id BWP-Id. resourceType ENUMERATED { aperiodic, semiPersistent, periodic },[[ csi-SSB-ResourceSetListExt-r!7 CSI-SSB-ResourceSetld OPTIONAL—Need R]]}

[0104] The following is an example of a NZP-C SI -RS-Re sourceSet IE that may be used to configure a UE for a beam management mechanism as described herein:NZP-CSI-RS-ResourceSet ::= SEQUENCE { nzp-CSI-ResourceSetld NZP-CSI-RS-ResourceSetld, nzp-CSI-RS-Resources SEQUENCE (SIZE (L.maxNrofNZP-CSI-RS-ResourcesPerSet)) OF NZP-CSI-RS-Resourceld, repetition ENUMERATED { on, off } OPTIONAL, - Need S aperiodicTriggeringOffset INTEGER(0..6) OPTIONAL, — Need S trs-Info ENUMERATED {true} OPTIONAL, - Need R[[ aperiodicTriggeringOffset-rl6 INTEGER(0..31) OPTIONAL— Need S]], [[ pdc-Info-rl 7 ENUMERATED {true} OPTIONAL,- Need R cmrGroupingAndPairing-rl7 CMRGroupingAndPairing-rl7 OPTIONAL,—Need R aperiodicTriggeringOffset-rl7 INTEGER 0..124) OPTIONAL,- Need S aperiodicTriggeringOffsetL2-rl7 INTEGER 0..31) OPTIONAL- Need R ]]}

[0105] It may be that to configure for the use of a Set B of beams as described herein, the measurement beams are configured with a repetition value of the NZP-CSI-RS- ResourceSe IE set to “off.”

[0106] The following is an example of a CSI-SSB-ResourceSet IE that may be used to configure a UE for a beam management mechanism as described herein:CSI-SSB-ResourceSet ::= SEQUENCE { csi-SSB-ResourceSetld CSI-SSB-ResourceSetld, csi-SSB-ResourceList SEQUENCE (SIZE(l..maxNrofCSI-SSB-ResourcePerSet)) OF SSB-Index,LI servingAdditionalPCIList-r!7 SEQUENCE (SIZE(l..maxNrofCSI-SSB- ResourcePerSet)) OFServingAdditionalPCIIndex-rl7 OPTIONAL— Need R]]}ServingAdditionalPCIIndex-rl 7 ::= Integer(0..maxNrofAdditionalPCI-rl 7)

[0107] FIG. 8 illustrates receive (Rx) beam assumptions that may exist. Note that while the diagram 800 is illustrated as consistent with cases where an AI / ML model at a UE is used for beam prediction, principles discussed in relation to FIG. 8 also apply in cases where the AI / ML model at a base station is used for beam prediction. Note also that while the diagram 800 expressly illustrates the case of a CSI-RS-based beam management mechanism, it will be understood that the principles discussed in relation toFIG. 8 are applicable for other kinds of beam management mechanisms (e.g., SSB-based beam management mechanisms).

[0108] The diagram 800 illustrates a case of K = 4, where the measurement resources 802 are accordingly made up of a first CSI-RS resource set 804, a second CSI-RS resource set 806, a third CSI-RS resource set 808, and a fourth CSI-RS resource set 810. Accordingly, four measurement instances (one for each CSI-RS resource in the measurement resources 802) are used at the UE.

[0109] The diagram 800 illustrates the case where the UE uses various different Rx beams for measurements at each of the measurement instances, where the four measurement instances respectively correspond to the use by the UE of the first Rx beam 812, the second Rx beam 814, again the first Rx beam 812, and then the third Rx beam 816.

[0110] Such an arrangement (where differing Rx beams are used at the UE to measure within the measurement resources 802) may lead to erroneous results in beam prediction.

[0111] FIG. 9 illustrates a diagram 900 for concepts corresponding to beam management mechanisms according to embodiments herein. Note that while the diagram 900 is illustrated as consistent with cases where an AI / ML model at a UE is used for beam prediction, principles discussed in relation to FIG. 9 also apply in cases where the AI / ML model at a base station is used for beam prediction. Note also that while the diagram 900 expressly illustrates the case of a CSI-RS-based beam management mechanism, it will be understood that the principles discussed in relation to FIG. 9 are applicable for other kinds of beam management mechanisms (e.g., SSB-based beam management mechanisms).

[0112] The diagram 900 illustrates a case of K = 4, where the measurement resources 902 are accordingly made up of a first CSI-RS resource set 904, a second CSI-RS resource set 906, a third CSI-RS resource set 908, and a fourth CSI-RS resource set 910. Accordingly, four measurement instances (one for each CSI-RS resource in the measurement resources 902) are used at the UE.

[0113] The diagram 900 illustrates the case where the UE uses the same first Rx beam 912 for measurements at each of the measurement instances.

[0114] Such an arrangement (where the same Rx beam is used at the UE to measure within the measurement resources 902) may lead to relatively better results when usingan AI / ML model as compared to the case where different Rx beams are used at the UE within a set of K measurement resources.

[0115] Accordingly, it is contemplated that for beam management mechanisms according to embodiments herein, it may be defined and / or configured to the UE that the same Rx beam is used to measure all / each of the measurement resources in a set of K measurement resources.

[0116] It is further noted that if a confirmation step is involved (e.g., as described in relation to Step 14 and Step 15 as illustrated in and described in relation to the flow diagram 100 and / or as described in relation to Step 14, Step 15, and Step 16 as illustrated in and described in relation to the flow diagram 200), the same Rx beam is used for the referred-to Set A beams.

[0117] A description correpsonding to a timeRestrictionForChannelMeasurements IE of a CSI-ReportConfig IE as may be used in some wireless communications systems now follows.

[0118] With respect to Ll-RSRP reporting: for Ll-RSRP computation, the UE may be configured with CSI-RS resources, SS / PBCH block resources or both CSI-RS and SS / PBCH block resources when resource-wise quasi co-located with ‘type C’ and ‘typeD’ when applicable. The UE may be configured with CSI-RS resource setting up to 16 CSI-RS resource sets having up to 64 resources within each set. The total number of different CSI-RS resources over all resource sets is no more than 128.

[0119] Then, for Ll-RSRP reporting, if the higher layer parameter nrofReportedRS in CSl-ReportConflg is configured to be one, or if the higher layer parameters [noOfReportedCells] and [noOfReportedRS-PerCell are both configured to be one, the reported Ll-RSRP value is defined by a 7-bit value in the range [-140, -44] decibel- milliwatts (dBm) with 1 decibel (dB) step size, if the higher layer parameter nrofReportedRS is configured to be larger than one, or if the higher layer parameter groupBasedBeamReporting is configured as ‘enabled’, or if the higher layer parameter groupBasedBeamReporting-r 17 is configured, or if any of the higher layer parameters [noOfReportedCells and [noOfReportedRS-PerCell] is configured to be larger than one, the UE shall use differential Ll-RSRP based reporting, where the largest measured value of Ll-RSRP is quantized to a 7-bit value in the range [-140. -44] dBm with IdB step size, and the differential Ll-RSRP is quantized to a 4-bit value. The differential Ll- RSRP value is computed with 2 dB step size with a reference to the largest measured LI-RSRP value which is part of the same Ll-RSRP reporting instance. The mapping between the reported Ll-RSRP value and the measured quantity is described in a standard for the wireless communication system.

[0120] When the higher layer parameter groupBasedBeamReporting-r 17 in CSI- ReportConfig is configured, the UE may indicate the CSI Resource Set associated with the largest measured value of Ll-RSRP, and for each group, CRI or SSBRI of the indicated CSI Resource Set may be present first.

[0121] If the higher layer parameter UmeRestrictionForChannelMeasurements in CSI- ReportConfig is set to “notConfigured” , the UE may derive the channel measurements for computing Ll-RSRP value reported in uplink slot n based on only the SS / PBCH or NZP CSI-RS, no later than the CSI reference resource associated with the CSI resource setting.

[0122] If the higher layer parameter timeRestrictionForChannelMeasurements in CSI- ReportConfig is set to “Configured” , the UE may derive the channel measurements for computing Ll-RSRP value reported in uplink slot n based on only the most recent, no later than the CSI reference resource, occasion of SS / PBCH or NZP CSI-RS associated with the CSI resource setting.

[0123] When the UE is configured with SSB-MTC-AdditionalPCI, a CSI-SSB- ResourceSet configured for Ll-RSRP reporting may include one set of SSB indices and one set of PCI indices, where each SSB index is associated with a PCI index.

[0124] When the UE is configured with a CSI-ReportConfig with the higher layer parameter reportQuantity set to ‘cri-RSRP-lndex" or 'ssb-Index-RSRP Index" an index of UE capability value set, indicating the maximum supported number of SRS antenna ports, may be reported along with the pair of SSBRI / CRI and Ll / RSRP.

[0125] In various systems, it may be that the UmeRestrictionForChannelMeasurements IE that can be set to “notConfigured" or “Configured.” as shown. In such cases, when “Configured” is set, a “one-shot” measurement is performed by UE.

[0126] It is contemplated that, in some embodiments, a timeRestrictionForChannelMeasurements IE may be used to indicate to the UE that it is to use a same Rx beam to perform measurements at each of a set of K measurement resources. Accordingly, in such embodiments, to ensure that the network and UE have the same understanding regarding same Rx beam use in this manner (and potentially Tx beam use as well), it may be that the timeRestrictionForChannelMeasurements IE is setto a new value other than “notConfigured" or “Configured ” For example, it may be set to a numerical value k, such as k = 4.

[0127] In some embodiments, a “Following-K,” IE may be configured in order to prescribe / indicate that a same sequence of Tx beams are applied by the base station during each of the K measurement resources (and this may be done additionally and / or optionally in conjunctions with the use by the UE of a same Rx beam for corresponding receptions, as described).

[0128] It is also contemplated that different IE (such as a timeRestrictionForHistoricChannelMeasurement IE) may be used to indicate to the UE to use the same Rx beam for a set of K measurement resources. The nature of such an indication may vary (could be Boolean value, a numerical value, etc.)

[0129] FIG. 10 illustrates a method 1000 of a UE, according to embodiments discussed herein. The method 1000 includes receiving 1002, from a base station, beam reporting configuration information. The method 1000 further includes determining 1004, based on a 5 value found in the beam reporting configuration information, to generate, using an AI / ML model, a spatial domain DL Tx beam prediction comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the spatial domain DL Tx beam prediction to a second slot for an effective time for the spatial domain DL Tx beam prediction. The method 1000 further includes generating 1006 the spatial domain DL Tx beam prediction comprising the one or more predicted values for the one or more predicted DL Tx beams. The method 1000 further includes sending 1008, to the base station, the beam report comprising the spatial domain DL Tx beam prediction.

[0130] In some embodiments of the method 1000, the determining, based on the 5 value, to generate the spatial domain DL Tx beam prediction comprises determining that the 5 value is a negative value.

[0131] In some embodiments of the method 1000, the 5 value is equal to -ncsi ref, where ncsi _re is a reference value that is configured to identify, relative to the first slot for the beam report, the second slot for the effective time for the spatial domain DL Tx beam prediction of the one or more first DL Tx beams as a measurement slot at which the first one or more measurements of the one or more measured DL Tx beams occurs. Insome such embodiments, the method 1000 further includes sending, to the base station, an indication that the UE is capable of using -ncsi re / as the 5 value.

[0132] In some embodiments of the method 1000, the one or more measured DL Tx beams comprise one or more CSI-RS beams.

[0133] In some embodiments of the method 1000, the one or more measured DL Tx beams are SSB beams.

[0134] In some embodiments, the method 1000 further includes performing, after sending the spatial domain DL Tx beam prediction, second one or more measurements of a subset of the one or more predicted DL Tx beams using a same receive (Rx) beam that was used to perform the first one or more measurements of the one or more predicted DL Tx beams; identifying one or more best DL Tx beams based on the second one or more measurements; and reporting, to the base station, the one or more best DL Tx beams.

[0135] FIG. 11 illustrates a method 1100 of a base station, according to embodiments discussed herein. The method 1100 includes sending 1102, to a UE. beam reporting configuration information comprising a 5 value configured to indicate to the UE to generate, using an AI / ML model, a spatial domain DL Tx beam prediction comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the spatial domain DL Tx beam prediction to a second slot for an effective time for the spatial domain DL Tx beam prediction. The method 1100 further includes transmitting 1104, to the UE, the one or more measured DL Tx beams. The method 1100 further includes receiving 1106, from the UE. the beam report comprising the spatial domain DL Tx beam prediction.

[0136] In some embodiments of the method 1100, the 5 value is a negative value.

[0137] In some embodiments of the method 1100, the 5 value is equal to -ncsi ref, where ncsi re / is a reference value that is configured to identify, relative to a first slot for the beam report, a second slot for an effective time for the spatial domain DL Tx beam prediction of the one or more first DL Tx beams as a measurement slot at which the first one or more measurements of the one or more measured DL Tx beams occurs. In some such embodiments, the method 1100 further includes receiving, from the UE, an indication that the UE is capable of using -ncsi ref as the 5 value, wherein the base station uses -ncsi ref as the 5 value in response to the indication.

[0138] In some embodiments of the method 1100, the one or more measured DL Tx beams comprise one or more CSI-RS beams.

[0139] In some embodiments of the method 1100, the one or more measured DL Tx beams are SSB beams.

[0140] FIG. 12 illustrates a method 1200 of a UE, according to embodiments discussed herein. The method 1200 includes receiving 1202, from a base station, beam reporting configuration information. The method 1200 further includes determining 1204, based on a 5 value found in the beam reporting configuration information, to generate, using an AI / ML model, one or more temporal DL Tx beam predictions corresponding to one or more effective times for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the one or more temporal domain DL Tx beam predictions to a second slot for a first effective time of the one or more effective times for a first spatial domain DL Tx beam prediction of the one or more spatial domain DL Tx beam predictions, and wherein the 5 value is configured such that second slot for the first effective time occurs after the first one or more measurements of the one or more measured DL Tx beams according to a time gap between the first one or more measurements of the one or more measured DL Tx beams and the one or more effective times for one or more temporal DL Tx beam predictions that is supported by the AI / ML model. The method 1200 further includes performing 1206 the one or more spatial temporal DL Tx beam predictions for the one or more predicted DL Tx beams. The method 1200 further includes sending 1208, to the base station, the beam report comprising the one or more temporal domain DL Tx beam predictions.

[0141] In some embodiments, the method 1200 further includes sending, to the base station, capability information indicating the time gap that is supported by the AI / ML model.

[0142] In some embodiments of the method 1200. the time gap that is supported by the AI / ML model comprises one of: 20 ms; 40 ms; 20 slots; and 40 slots.

[0143] In some embodiments, the method 1200 further includes sending, to the base station, capability information indicating a time gap range that is supported by the AI / ML model, wherein the time gap falls within the time gap range.

[0144] In some embodiments of the method 1200, the determining, based on the 5 value, to generate the spatial domain DL Tx beam prediction comprises determining thatthe 5 value is a non-negative value. In some such embodiments, the 5 value is equal to one of zero, one, and two.

[0145] In some embodiments of the method 1200, the one or more measured DL Tx beams are one or more CSI-RS beams that are part of a same CSI-RS resource set, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements of the same CSI-RS resource set.

[0146] In some embodiments of the method 1200, the one or more measured DL Tx beams comprise one or more CSI-RS beams that are part of different CSI-RS resource sets.

[0147] In some embodiments of the method 1200, the one or more measured DL Tx beams are SSB beams, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements a plurality of SSB bursts having the one or more SSB beams.

[0148] In some embodiments of the method 1200. the one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements, and the method 1200 further includes: receiving, from the base station, an indication to use a same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams; and using, based on the instruction, the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams. In some such embodiments, the indication to use the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beam is received in one of: a timeRestrictionForChannelMeasurements IE; and a timeRestrictionForHistoricChannelMeasurements IE.

[0149] In some embodiments, the method 1200, further includes performing, after sending the one or more temporal domain DL Tx beam predictions, second one or more measurements of a subset of the one or more predicted DL Tx beams using a same Rx beam that was used to perform the first one or more measurements of the one or more predicted DL Tx beams; identifying one or more best DL Tx beams based on the second one or more measurements; and reporting, to the base station, the one or more best DL Tx beams.

[0150] FIG. 13 illustrates a method 1300 of a base station, according to embodiments discussed herein. The method 1300 includes sending 1302. to a UE, beam reporting configuration information comprising a 5 value configured to indicate to the UE togenerate, using a first AI / ML model, one or more temporal DL Tx beam predictions corresponding to one or more effective times for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the one or more temporal domain DL Tx beam predictions to a second slot for a first effective time of the one or more effective times for a first spatial domain DL Tx beam prediction of the one or more spatial domain DL Tx beam predictions, and wherein the 5 value is selected by the base station so that the second slot for the first effective time occurs after the first one or more measurements of the one or more measured DL Tx beams according to a time gap between the first one or more measurements of the one or more measured DL Tx beams and the one or more effective times for one or more temporal DL Tx beam predictions that is supported by the AI / ML model. The method 1300 further includes transmitting 1304, to the UE, the one or more measured DL Tx beams. The method 1300 further includes receiving 1306, from the UE, the beam report comprising the one or more temporal domain DL Tx beam predictions.

[0151] In some embodiments, the method 1300 further includes receiving, from the UE, capability7information indicating the time gap that is supported by the AI / ML model.

[0152] In some embodiments of the method 1300, the time gap that is supported by the AI / ML model comprises one of: 20 ms; 40 ms; 20 slots; and 40 slots.

[0153] In some embodiments, the method 1300 further includes receiving, from the UE, capability information indicating a time gap range that is supported by the AI / ML model, wherein the time gap falls within the time gap range.

[0154] In some embodiments of the method 1300. the 5 value is a non-negative value. In some such embodiments, the 8 value is equal to one of zero, one, and two.

[0155] In some embodiments of the method 1300, the one or more measured DL Tx beams are one or more CSI-RS beams that are part of a same CSI-RS resource set. and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements of the same CSI-RS resource set.

[0156] In some embodiments of the method 1300. the one or more measured DL Tx beams are one or more CSI-RS beams that are part of a same CSI-RS resource set, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality7of measurements of the same CSI-RS resource set.

[0157] In some embodiments of the method 1300, the one or more measured DL Tx beams are SSB beams, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements, a plurality of SSB bursts having the one or more SSB beams.

[0158] In some embodiments, the method 1300 further includes sending, to the UE, an indication to use a same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams. In some such embodiments, the indication to use the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams is received in one of: a timeRestrictionForChannelMeasurements IE; and a timeRestrictionForHistoricChannelMeasurements IE.

[0159] FIG. 14 illustrates an example architecture of a wireless communication system 1400, according to embodiments disclosed herein. The following description is provided for an example wireless communication system 1400 that operates in conjunction with the LTE system standards and / or 5G or NR system standards as provided by 3 GPP technical specifications.

[0160] As shown by FIG. 14. the wireless communication system 1400 includes UE 1402 and UE 1404 (although any number of UEs may be used). In this example, the UE 1402 and the UE 1404 are illustrated as smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more cellular networks), but may also comprise any mobile or non-mobile computing device configured for wireless communication.

[0161] The UE 1402 and UE 1404 may be configured to communicatively couple with a RAN 1406. In embodiments, the RAN 1406 may be NG-RAN. E-UTRAN, etc. The UE 1402 and UE 1404 utilize connections (or channels) (shown as connection 1408 and connection 1410, respectively) with the RAN 1406, each of which comprises a physical communications interface. The RAN 1406 can include one or more base stations (such as base station 1412 and base station 1414) that enable the connection 1408 and connection 1410.

[0162] In this example, the connection 1408 and connection 1410 are air interfaces to enable such communicative coupling, and may be consistent with RAT(s) used by the RAN 1406, such as. for example, an LTE and / or NR.

[0163] In some embodiments, the UE 1402 and UE 1404 may also directly exchange communication data via a sidelink interface 1416. The UE 1404 is shown to be configured to access an access point (shown as AP 1418) via connection 1420. By wayof example, the connection 1420 can comprise a local wireless connection, such as a connection consistent with any IEEE 802.11 protocol, wherein the AP 1418 may comprise a Wi-Fi* router. In this example, the AP 1418 may be connected to another network (for example, the Internet) without going through a CN 1424.

[0164] In embodiments, the UE 1402 and UE 1404 can be configured to communicate using orthogonal frequency division multiplexing (OFDM) communication signals with each other or with the base station 1412 and / or the base station 1414 over a multicarrier communication channel in accordance with various communication techniques, such as, but not limited to, an orthogonal frequency division multiple access (OFDMA) communication technique (e.g., for downlink communications) or a single carrier frequency division multiple access (SC-FDMA) communication technique (e g., for uplink and ProSe or sidelink communications), although the scope of the embodiments is not limited in this respect. The OFDM signals can comprise a plurality of orthogonal subcarriers.

[0165] In some embodiments, all or parts of the base station 1412 or base station 1414 may be implemented as one or more software entities running on server computers as part of a virtual network. In addition, or in other embodiments, the base station 1412 or base station 1414 may be configured to communicate with one another via interface 1422. In embodiments where the wireless communication system 1400 is an LTE system (e.g., when the CN 1424 is an EPC), the interface 1422 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs and the like) that connect to an EPC. and / or between two eNBs connecting to the EPC. In embodiments where the wireless communication system 1400 is an NR system (e.g., when CN 1424 is a 5GC), the interface 1422 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs and the like) that connect to 5GC. between a base station 1412 (e.g., a gNB) connecting to 5GC and an eNB, and / or between two eNBs connecting to 5GC (e.g., CN 1424).

[0166] The RAN 1406 is shown to be communicatively coupled to the CN 1424. The CN 1424 may comprise one or more network elements 1426, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UE 1402 and UE 1404) who are connected to the CN 1424 via the RAN 1406. The components of the CN 1424 may be implemented in one physical device, or separate physical devices including components to read and execute instructions from a machine-readable or computer-readable medium (e g., a non-transitory machine-readable storage medium).

[0167] In embodiments, the CN 1424 may be an EPC, and the RAN 1406 may be connected with the CN 1424 via an SI interface 1428. In embodiments, the SI interface 1428 may be split into two parts, an SI user plane (Sl-U) interface, which carries traffic data between the base station 1412 or base station 1414 and a serving gateway (S-GW), and the SI -MME interface, which is a signaling interface between the base station 1412 or base station 1414 and mobility management entities (MMEs).

[0168] In embodiments, the CN 1424 may be a 5GC, and the RAN 1406 may be connected with the CN 1424 via an NG interface 1428. In embodiments, the NG interface 1428 may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the base station 1412 or base station 1414 and a user plane function (UPF), and the SI control plane (NG-C) interface, which is a signaling interface between the base station 1412 or base station 1414 and access and mobility management functions (AMFs).

[0169] Generally, an application server 1430 may be an element offering applications that use internet protocol (IP) bearer resources with the CN 1424 (e g., packet switched data services). The application server 1430 can also be configured to support one or more communication services (e g., VoIP sessions, group communication sessions, etc.) for the UE 1402 and UE 1404 via the CN 1424. The application server 1430 may communicate with the CN 1424 through an IP communications interface 1432.

[0170] FIG. 15 illustrates a system 1500 for performing signaling 1534 between a wireless device 1502 and a network device 1518, according to embodiments disclosed herein. The system 1500 may be a portion of a wireless communications system as herein described. The wireless device 1502 may be, for example, a UE of a wireless communication system. The network device 1518 may be, for example, a base station (e.g.. an eNB or a gNB) of a wireless communication system.

[0171] The wireless device 1502 may include one or more processor(s) 1504. The processor(s) 1504 may execute instructions such that various operations of the wireless device 1502 are performed, as described herein. The processor(s) 1504 may include one or more baseband processors implemented, using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardwaredevice, a firmware device, or any combination thereof configured to perform the operations described herein.

[0172] The wireless device 1502 may include a memory 1506. The memory' 1506 may be a non-transitory' computer-readable storage medium that stores instructions 1508 (which may include, for example, the instructions being executed by the processor(s) 1504). The instructions 1508 may also be referred to as program code or a computer program. The memory 1506 may also store data used by, and results computed by, the processor(s) 1504.

[0173] The wireless device 1502 may include one or more transceiver(s) 1510 that may include radio frequency (RF) transmitter circuitry' and / or receiver circuitry that use the antenna(s) 1512 of the wireless device 1502 to facilitate signaling (e.g., the signaling 1534) to and / or from the wireless device 1502 with other devices (e.g., the network device 1518) according to corresponding RATs.

[0174] The wireless device 1502 may include one or more antenna(s) 1512 (e.g., one, two, four, or more). For embodiments with multiple antenna(s) 1512, the wireless device 1502 may leverage the spatial diversity of such multiple antenna(s) 1512 to send and / or receive multiple different data streams at the same time and frequency resources. This behavior may be referred to as, for example, multiple input multiple output (MIMO) behavior (referring to the multiple antennas used at each of a transmitting device and a receiving device that enable this aspect). MIMO transmissions by the wireless device 1502 may be accomplished according to precoding (or digital beamforming) that is applied at the wireless device 1502 that multiplexes the data streams across the antenna(s) 1512 according to known or assumed channel characteristics such that each data stream is received with an appropriate signal strength relative to other streams and at a desired location in the spatial domain (e.g., the location of a receiver associated with that data stream). Certain embodiments may use single user MIMO (SU-MIMO) methods (where the data streams are all directed to a single receiver) and / or multi user MIMO (MU-MIMO) methods (where individual data streams may be directed to individual (different) receivers in different locations in the spatial domain).

[0175] In certain embodiments having multiple antennas, the wireless device 1502 may implement analog beamforming techniques, whereby phases of the signals sent by the antenna(s) 1512 are relatively adjusted such that the (joint) transmission of the antenna(s) 1512 can be directed (this is sometimes referred to as beam steering).

[0176] The wireless device 1502 may include one or more interface(s) 1514. The interface(s) 1514 may be used to provide input to or output from the wireless device 1502. For example, a wireless device 1502 that is a UE may include interface(s) 1514 such as microphones, speakers, a touchscreen, buttons, and the like in order to allow for input and / or output to the UE by a user of the UE. Other interfaces of such a UE may be made up of transmitters, receivers, and other circuitry’ (e.g., other than the transceiver(s) 1510 / antenna(s) 1512 already described) that allow for communication between the UE and other devices and may operate according to known protocols (e g., Wi-Fi®, Bluetooth®, and the like).

[0177] The wireless device 1502 may include an AI / ML enabled beam management module 1516. The AI / ML enabled beam management module 1516 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML enabled beam management module 1516 may be implemented as a processor, circuit, and / or instructions 1508 stored in the memory 1506 and executed by the processor(s) 1504. In some examples, the AI / ML enabled beam management module 1516 may be integrated within the processor(s) 1504 and / or the transceiver(s) 1510. For example, the AI / ML enabled beam management module 1516 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g.. logic gates and circuitry) within the processor(s) 1504 or the transceiver(s) 1510.

[0178] The AI / ML enabled beam management module 1516 may be used for various aspects of the present disclosure, for example, aspects of FIG. 1 through FIG. 12. The AI / ML enabled beam management module 1516 may configure the wireless device 1502 to receive, from a base station, beam measurement configuration information; determine, based on a 5 value found in the beam measurement configuration information, to generate, using an AI / ML model, one or more DL Tx beam predictions comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams; generate the one or more DL Tx beam predictions comprising the one or more predicted values for the one or more predicted DL Tx beams; and send, to the base station, the beam report comprising the DL Tx beam prediction, according to various embodiments discussed herein.

[0179] The network device 1518 may include one or more processor(s) 1520. The processor(s) 1520 may execute instructions such that various operations of the networkdevice 1518 are performed, as described herein. The processor(s) 1520 may include one or more baseband processors implemented, using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0180] The network device 1518 may include a memory’ 1522. The memory 1522 may be a non-transitory computer-readable storage medium that stores instructions 1524 (which may include, for example, the instructions being executed by the processor(s) 1520). The instructions 1524 may also be referred to as program code or a computer program. The memory’ 1522 may also store data used by. and results computed by, the processor(s) 1520.

[0181] The network device 1518 may include one or more transceiver(s) 1526 that may include RF transmitter circuitry’ and / or receiver circuitry that uses the antenna(s) 1528 of the network device 1518 to facilitate signaling (e.g., the signaling 1534) to and / or from the network device 1518 with other devices (e g., the wireless device 1502) according to corresponding RATs.

[0182] The network device 1518 may include one or more antenna(s) 1528 (e.g., one, two, four, or more). In embodiments having multiple antenna(s) 1528, the network device 1518 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as has been described.

[0183] The network device 1518 may include one or more interface(s) 1530. The interface(s) 1530 may be used to provide input to or output from the network device 1518. For example, a network device 1518 that is a base station may include interface(s) 1530 made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver(s) 1526 / antenna(s) 1528 already described) that enables the base station to communicate with other equipment in a core network, and / or that enables the base station to communicate with external networks, computers, databases, and the like for purposes of operations, administration, and maintenance of the base station or other equipment operably connected thereto.

[0184] The network device 1518 may include an AI / ML enabled beam management module 1532. The AI / ML enabled beam management module 1532 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML enabled beam management module 1532 may be implemented as a processor, circuit, and / or instructions 1524 stored in the memory’ 1522 and executed by the processor(s) 1520. Insome examples, the AI / ML enabled beam management module 1532 may be integrated within the processor(s) 1520 and / or the transceiver(s) 1526. For example, the AI / ML enabled beam management module 1532 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g., logic gates and circuitry) within the processor(s) 1520 or the transceiver(s) 1526.

[0185] The AI / ML enabled beam management module 1532 may be used for various aspects of the present disclosure, for example, aspects of FIG. 1 through FIG. 12. The AI / ML enabled beam management module 1532 may configure the network device 1518 to send, to a user equipment (UE). beam measurement configuration information comprising a 5 value configured to indicate to the UE to generate, using an AI / ML model, a DL Tx beam prediction comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams; transmit, to the UE, the one or more measured DL Tx beams; and receive, from the UE, the beam report comprising the DL Tx beam prediction, according to various embodiments discussed herein.

[0186] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the method 1000 and the method 1200. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1502 that is a UE, as described herein).

[0187] Embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of any of the method 1000 and the method 1200. This non-transitory computer-readable media may be, for example, a memory of a UE (such as a memory 1506 of a wireless device 1502 that is a UE, as described herein).

[0188] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any of the method 1000 and the method 1200. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1502 that is a UE, as described herein).

[0189] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors toperform one or more elements of any of the method 1000 and the method 1200. This apparatus may be. for example, an apparatus of a UE (such as a wireless device 1502 that is a UE, as described herein).

[0190] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the method 1000 and the method 1200.

[0191] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processor is to cause the processor to carry out one or more elements of any of the method 1000 and the method 1200. The processor may be a processor of a UE (such as a processor(s) 1504 of a wireless device 1502 that is a UE, as described herein). These instructions may be, for example, located in the processor and / or on a memory of the UE (such as a memory’ 1506 of a wireless device 1502 that is a UE, as described herein).

[0192] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the method 1100 and the method 1300. This apparatus may be. for example, an apparatus of a base station (such as a network device 1518 that is a base station, as described herein).

[0193] Embodiments contemplated herein include one or more non -transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of any of the method 1100 and the method 1300. This non-transitory computer-readable media may be, for example, a memory of a base station (such as a memory' 1522 of a network device 1518 that is a base station, as described herein).

[0194] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any of the method 1100 and the method 1300. This apparatus may be, for example, an apparatus of a base station (such as a network device 1518 that is a base station, as described herein).

[0195] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of any of the method 1100 and the method 1300. This apparatus may be, for example, an apparatus of a base station (such as a network device 1518 that is a base station, as described herein).

[0196] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the method 1100 and the method 1300.

[0197] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processing element is to cause the processing element to carry out one or more elements of any of the method 1100 and the method 1300. The processor may be a processor of a base station (such as a processor(s) 1520 of a network device 1518 that is a base station, as described herein). These instructions may be, for example, located in the processor and / or on a memory of the base station (such as a memory 1522 of a network device 1518 that is a base station, as described herein).

[0198] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a baseband processor as described herein in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein.

[0199] Any of the above described embodiments may be combined with any other embodiment (or combination of embodiments), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

[0200] Embodiments and implementations of the sy stems and methods described herein may include various operations, which may be embodied in machine-executable instructions to be executed by a computer system. A computer system may include one or more general-purpose or special-purpose computers (or other electronic devices). The computer system may include hardware components that include specific logic for performing the operations or may include a combination of hardware, software, and / or firmware.

[0201] It should be recognized that the systems described herein include descriptions of specific embodiments. These embodiments can be combined into single systems. partially combined into other systems, split into multiple systems or divided or combined in other ways. In addition, it is contemplated that parameters, attributes, aspects, etc. of one embodiment can be used in another embodiment. The parameters, attributes, aspects, etc. are merely described in one or more embodiments for clarity’, and it is recognized that the parameters, attributes, aspects, etc. can be combined with or substituted for parameters, attributes, aspects, etc. of another embodiment unless specifically disclaimed herein.

[0202] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry’ or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.

[0203] Although the foregoing has been described in some detail for purposes of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles thereof. It should be noted that there are many alternative ways of implementing both the processes and apparatuses described herein. Accordingly, the present embodiments are to be considered illustrative and not restrictive, and the description is not to be limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.

Claims

CLAIMS1. A method of a user equipment (UE), comprising: receiving, from a base station, beam reporting configuration information; determining, based on a 5 value found in the beam measurement configuration information, to generate, using an artificial intelligence (AI) / machine learning (ML) model, a spatial domain downlink (DL) transmit (Tx) beam prediction comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the spatial domain DL Tx beam prediction to a second slot for an effective time for the spatial domain DL Tx beam prediction; generating the spatial domain DL Tx beam prediction comprising the one or more predicted values for the one or more predicted DL Tx beams; and sending, to the base station, the beam report comprising the spatial domain DL Tx beam prediction.

2. The method of claim 1, wherein the determining, based on the 6 value, to generate the spatial domain DL Tx beam prediction comprises determining that the 5 value is a negative value.

3. The method of claim 1, wherein the 5 value is equal to -ncsi ref, where ncsi ref is a reference value that is configured to identify, relative to the first slot for the beam report, the second slot for the effective time for the spatial domain DL Tx beam prediction of the one or more first DL Tx beams as a measurement slot at which the first one or more measurements of the one or more measured DL Tx beams occurs.

4. The method of claim 3, further comprising sending, to the base station, an indication that the UE is capable of using -ncsi ref as the 5 value.

5. The method of claim 1, wherein the one or more measured DL Tx beams comprise one or more (CSI) reference signal (CSI-RS) beams.

6. The method of claim 1, wherein the one or more measured DL Tx beams are synchronization signal block (SSB) beams.

7. The method of claim 1, further comprising: performing, after sending the spatial domain DL Tx beam prediction, second one or more measurements of a subset of the one or more predicted DL Tx beams using a same receive (Rx) beam that was used to perform the first one or more measurements of the one or more predicted DL Tx beams; identifying one or more best DL Tx beams based on the second one or more measurements; and reporting, to the base station, the one or more best DL Tx beams.

8. A method of a base station, comprising: sending, to a user equipment (UE). beam reporting configuration information comprising a 5 value configured to indicate to the UE to generate, using an artificial intelligence (AI) / machine learning (ML) model, a spatial domain downlink (DL) transmit (Tx) beam prediction comprising one or more predicted values for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the spatial domain DL Tx beam prediction to a second slot for an effective time for the spatial domain DL Tx beam prediction; transmitting, to the UE, the one or more measured DL Tx beams; and receiving, from the UE. the beam report comprising the spatial domain DL Tx beam prediction.

9. The method of claim 8, wherein the 5 value is a negative value.

10. The method of claim 8, wherein the 8 value is equal to -ncsi ref, where ncsi _re / is a reference value that is configured to identify, relative to a first slot for the beam report, a second slot for an effective time for the spatial domain DL Tx beam prediction of the one or more first DL Tx beams as a measurement slot at which the first one or more measurements of the one or more measured DL Tx beams occurs.

11. The method of claim 10, further comprising receiving, from the UE, an indication that the UE is capable of using -ncsi ref as the 6 value, wherein the base station uses - ncsi ref as the 3 value in response to the indication.

12. The method of claim 8, wherein the one or more measured DL Tx beams comprise one or more (CSI) reference signal (CSI-RS) beams.

13. The method of claim 8, wherein the one or more measured DL Tx beams are synchronization signal block (SSB) beams.

14. A method of a user equipment (UE), comprising: receiving, from a base station, beam reporting configuration information; determining, based on a 5 value found in the beam reporting configuration information, to generate, using an artificial intelligence (AI) / machine learning (ML) model, one or more temporal DL Tx beam predictions corresponding to one or more effective times for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the one or more temporal domain DL Tx beam predictions to a second slot for a first effective time of the one or more effective times for a first spatial domain DL Tx beam prediction of the one or more spatial domain DL Tx beam predictions, and wherein the 5 value is configured such that the second slot for the first effective time occurs after the first one or more measurements of the one or more measured DL Tx beams according to a time gap between the first one or more measurements of the one or more measured DL Tx beams and the one or more effective times for one or more temporal DL Tx beam predictions that is supported by the AI / ML model: performing the one or more spatial temporal DL Tx beam predictions for the one or more predicted DL Tx beams; and sending, to the base station, the beam report comprising the one or more temporal domain DL Tx beam predictions.

15. The method of claim 14, further comprising sending, to the base station, capability information indicating the time gap that is supported by the AI / ML model.

16. The method of claim 14, wherein the time gap that is supported by the AI / ML model comprises one of:20 milliseconds (ms);40 ms;20 slots; and40 slots.

17. The method of claim 14, further comprising sending, to the base station, capability information indicating a time gap range that is supported by the AI / ML model, wherein the time gap falls within the time gap range.

18. The method of claim 14, wherein the determining, based on the 5 value, to generate the spatial domain DL Tx beam prediction comprises determining that the 5 value is a non-negative value.

19. The method of claim 18, wherein the 5 value is equal to one of zero, one, and two.

20. The method of claim 14, wherein the one or more measured DL Tx beams are one or more channel state information (CSI) reference signal (CSI-RS) beams that are part of a same CSI-RS resource set, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements of the same CSI-RS set.

21. The method of claim 14, wherein the one or more measured DL Tx beams comprise one or more channel state information (CSI) reference signal (CSI-RS) beams that are part of different CSI-RS resource sets.

22. The method of claim 14, wherein the one or more measured DL Tx beams are synchronization signal block (SSB) beams, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements a plurality of SSB bursts having the one or more SSB beams.

23. The method of claim 14, wherein the one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements, and further comprising: receiving, from the base station, an indication to use a same receive (Rx) beam for each of the plurality of measurements of the one or more measured DL Tx beams; and using, based on the instruction, the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams.

24. The method of claim 23, wherein the indication to use the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beam is received in one of: a timeRestriction 'orChannelMeasurements IE; anda timeRestrictionForHistoricChannelMeasurements IE.

25. The method of claim 14, further comprising: performing, after sending the one or more temporal domain DL Tx beam predictions, second one or more measurements of a subset of the one or more predicted DL Tx beams using a same Rx beam that was used to perform the first one or more measurements of the one or more predicted DL Tx beams; identifying one or more best DL Tx beams based on the second one or more measurements; and reporting, to the base station, the one or more best DL Tx beams.

26. A method of a base station, comprising: sending, to a user equipment (UE), beam reporting configuration information comprising a 5 value configured to indicate to the UE to generate, using a first artificial intelligence (AI) / machine learning (ML) model, one or more temporal DL Tx beam predictions corresponding to one or more effective times for one or more predicted DL Tx beams based on first one or more measurements of one or more measured DL Tx beams, wherein the 5 value represents a number of slots from a first slot for a beam report comprising the one or more temporal domain DL Tx beam predictions to a second slot for a first effective time of the one or more effective times for a first spatial domain DL Tx beam prediction of the one or more spatial domain DL Tx beam predictions, and wherein the 5 value is selected by the base station so that the second slot for the first effective time occurs after the first one or more measurements of the one or more measured DL Tx beams according to a time gap between the first one or more measurements of the one or more measured DL Tx beams and the one or more effective times for one or more temporal DL Tx beam predictions that is supported by the AI / ML model; transmitting, to the UE, the one or more measured DL Tx beams; and receiving, from the UE, the beam report comprising the one or more temporal domain DL Tx beam predictions.

27. The method of claim 26, further comprising receiving, from the UE, capability information indicating the time gap that is supported by the AI / ML model.

28. The method of claim 26, wherein the time gap that is supported by the AI / ML model comprises one of:20 milliseconds (ms);40 ms;20 slots; and40 slots.

29. The method of claim 26, further comprising receiving, from the UE, capability information indicating a time gap range that is supported by the AI / ML model, wherein the time gap falls within the time gap range.

30. The method of claim 26, wherein the 8 value is a non-negative value.

31. The method of claim 30, wherein the 6 value is equal to one of zero, one, and two.

32. The method of claim 26, wherein the one or more measured DL Tx beams are one or more channel state information (CSI) reference signal (CSI-RS) beams that are part of a same CSI-RS resource set, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements of the same CSI-RS resource set.

33. The method of claim 26, wherein the one or more measured DL Tx beams are one or more channel state information (CSI) reference signal (CSI-RS) beams that are part of a same CSI-RS resource set, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements of the same CSI-RS resource set.

34. The method of claim 26, wherein the one or more measured DL Tx beams are synchronization signal block (SSB) beams, and the first one or more measurements of the one or more measured DL Tx beams comprises a plurality of measurements a plurality of SSB bursts having the one or more SSB beams.

35. The method of claim 26, further comprising sending, to the UE, an indication to use a same receive (Rx) beam for each of the plurality of measurements of the one or more measured DL Tx beams.

36. The method of claim 35, wherein the indication to use the same Rx beam for each of the plurality of measurements of the one or more measured DL Tx beams is received in one of: a timeRestrictionForChcinnelMeasurements IE; and a timeRestrictionForHistoricChannelMeasurements IE.

37. An apparatus comprising means to perform the method of any of claim 1 to claim 36.

38. A computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform the method of any of claim 1 to claim 36.

39. An apparatus comprising logic, modules, or circuitry to perform the method of any of claim 1 to claim 36.

40. A baseband processor for a user equipment (UE) that is configured to perform one or more elements of any one of claim 1 to claim 7 and claim 14 to claim 25.

41. A baseband processor for a base station that is configured to perform one or more elements of any one of claim 8 to claim 13 and claim 26 to claim 36.

Images