Systems and methods for random access channel procedure-based beam management using user-equipment-sided artificial intelligence / machine learning models

Abstract

Systems and methods for random access channel (RACH) procedure-based beam management using user equipment (UE)-sided artificial intelligence (AI) / machine learning (ML) models are discussed herein. In some embodiments, a UE receives a mapping of a set of RACH occasions (ROs) to a set of network narrow beams. The UE then applies its measurements of synchronization signal blocks (SSBs) transmitted by the network to an AI / ML model to identify a predicted network narrow beam. The RO corresponding to the predicted network narrow beam is used for a RACH transmission such that the predicted network narrow beam is identified to the network. In alternative cases, the network identifies that the UE is capable of using the AI / ML model based on a RACH transmission and uses a random access response message to instruct the UE to indicate the predicted network narrow beam in a contention resolution message.

Description

SYSTEMS AND METHODS FOR RANDOM ACCESS CHANNEL PROCEDURE¬BASED BEAM MANAGEMENT USING USER-EQUIPMENT-SIDED ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODELSTECHNICAL FIELD

[0001] This application relates generally to wireless communication systems, including wireless communication systems implementing the use of artificial intelligence (AI) / machine learning (ML) models for beam management (BM).BACKGROUND

[0002] 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®).

[0003] 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).

[0004] 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). In1P69799WO1 4896-5552-6508' 1certain deployments, the E-UTRAN may also implement NR RAT. In certain deployments, NG-RAN may also implement LTE RAT.

[0005] 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 g Node B or gNB).

[0006] 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).

[0007] 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

[0008] 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.

[0009] FIG. 1 illustrates a flow diagram for a RACH procedure between a UE and a network according to first embodiments discussed herein.

[0010] FIG. 2 illustrates a diagram for the measurement of the SSBs on corresponding SSB beams according to beam sweeping at both a network and a UE.

[0011] FIG. 3 illustrates a diagram for the use of an AI / ML model 308 for identifying a predicted network narrow beam based on SSB measurements and that is located at a UE.2P69799WO1 4896-5552-650811

[0012] FIG. 4 illustrates a diagram illustrating the use and reception of a RACH transmission on an RO that corresponds to a network narrow beam.

[0013] FIG. 5 illustrates a RACH -ConfigCommon IE as may be used to configure a first mapping of a first set of ROs to SSB beams and a second mapping of a second set of ROs to a set of network narrow beams, as discussed in embodiments herein.

[0014] FIG. 6 illustrates a diagram visualizing a RACH configuration of a first set of ROs that is mapped to a set of SSB beams and a second set of ROs that is mapped to a set of network narrow beams.

[0015] FIG. 7 illustrates a flow diagram for a RACH procedure between a UE and a network, according to second embodiments discussed herein.

[0016] FIG. 8 illustrates a table for RAR message content field sizes, according to embodiments discussed herein.

[0017] FIG. 9 illustrates a method of a UE, according to embodiments discussed herein.

[0018] FIG. 10 illustrates a method of a base station, according to embodiments discussed herein.

[0019] FIG. 11 illustrates a method of a UE, according to embodiments discussed herein.

[0020] FIG. 12 illustrates a method of a base station, according to embodiments discussed herein.

[0021] FIG. 13 illustrates an example architecture of a wireless communication system, according to embodiments disclosed herein.

[0022] FIG. 14 illustrates a system for performing signaling between a wireless device and a network device, according to embodiments disclosed herein.DETAILED DESCRIPTION

[0023] 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.3P69799WO1 4896-5552-650811

[0024] Various wireless communication systems that use AI / ML based beam management procedures use life cycle management (LCM) behaviors that assume that the UE and the network are in a connected mode (e.g., a radio resource control (RRC) CONNECTED mode). For example, it may be that for the case of a network-sided AI / ML model (an AI / ML model that is located at the network) corresponding to such circumstances, mechanisms for data collection for training, inference and performance monitoring may be implemented. Further, it may be that for a UE-sided AI / ML model (an AI / ML model that is located at the UE) corresponding to such circumstances, mechanisms for the use of an association identifier (ID) to ensure consistency between training and inferencing and / or LCM related signaling including data collection, inferencing control, feedback, and performance monitoring may be used.

[0025] Discussion herein relates to the use of AI / ML models to make predictions with respect to a set A of beams in view of information about a set B of beams. In some such cases, it may be understood that a set A of beams represents a set of beams from which a predicted beam is to be identified, while a set B of beams represents a set of beams for which measurements are actually taken, with those measurement then used with the AI / ML model in order to identify the predicted beam from among the set A of beams.

[0026] Various cases for downlink (DL) transmit (Tx) beam prediction at both UE- sided AI / ML models and network-sided AI / ML models for purposes of beam management are now considered. In a first of such cases (“BM-Casel”), a spatial-domain DL Tx beam prediction for a Set A of beams may be based on measurement results of a Set B of beams. In another of such cases ( ‘BM-Case2”), a temporal DL Tx beam prediction for a Set A of beams may be based on historic measurement results of a Set B of beams.

[0027] In order to facilitate LCM operations corresponding to these beam management cases, it may be beneficial to specify corresponding signaling and / or other mechanisms. Further, methods for ensuring consistency between training and inference regarding any network-side additional conditions (if identified) that affect an inference at the UE may be used. Implementations for such aspects that use a common framework design that supports both BM-Casel and BM-Case2 are beneficial.

[0028] Various wireless communication systems are configured to use random access channel (RACH) procedures. Such RACH procedures may be used between a UE and the network prior to the establishment of a connected mode (e.g., RRC CONNECTED)4P69799WO1 4896-5552-6508' 1between the UE and the network. In some examples, RACH procedures are used to (e.g., as a result of the RACH procedure) establish the connected mode between the UE and the network.

[0029] Signaling related to an example four-step RACH procedure is now described. Note preliminarily that embodiments herein may assume that there is a beam correspondence as between the Tx and Rx domains at the UE. Thus, discussion herein may understand a beam of the UE to represent a same beamforming as used in either / both of the Tx direction and the Rx direction, as context requires. Further, embodiments herein may (also) assume that there is a beam correspondence as between the Tx and Rx domains at the network. Thus, discussion herein may understand a beam of the network to represent a same beamforming as used in either / both of the Tx direction and the Rx direction, as context requires.

[0030] Preliminarily, a UE measures synchronization signal blocks (SSBs) that are transmitted by the network on a corresponding set of network beams for the SSBs (SSB beams), where each of the SSB beams corresponds to one of the transmitted SSBs. The UE performs these measurements using a receive (Rx) beam sweeping through a set of UE beams. The measurements so generated may be, for example, reference signal received power (RSRP) values (e g., layer 1 RSRP (Ll-RSRP) values). The UE then identifies a best (e.g., strongest) of these measurements, and the SSB beam and the UE beam corresponding to this best measurement are identified as a best beam pair between the UE and the network. Note that these SSB beams are relatively wide beams as compared to, for example, channel state information reference signal (CSI-RS) beams that may later be used by the network.

[0031] A “Message 1” (Msg 1) of the RACH procedure is then transmitted by the UE. The Msg 1 may be referred to herein as a RACH transmission. The UE performs the RACH transmission using the UE beam of the best beam pair as identified during the SSB measurement procedure.

[0032] The UE sends this RACH transmission in a RACH occasion (RO) corresponding to the SSB for the SSB beam in the best beam pair previously identified. The use of this particular RO identifies, to the base station, the SSB (and thus the SSB beam) on which the UE registered the best measurement. To facilitate the identification of this particular RO by the UE, for a Type-1 random access procedure, the UE is provided a number N of SSB indexes that are each associated with one RO and a number R of contention-based5P69799WO1 4896-5552-6508' 1RACH preambles per SSB index per valid RO in an ssb-perRACH-OccasionAndCB- PreamblesPerSSB information element (IE).

[0033] A “Message 2” (Msg 2) of the RACH procedure is then transmitted by the network. The Msg 2 may be referred to herein as a random access response (RAR) message. The network sends the RAR message to the UE. This RAR message includes an RAR grant field, indicating scheduling information for a contention resolution message to be used by the UE.

[0034] A “Message 3” (Msg 3) is then sent by the UE. The Msg 3 may be referred to herein as a contention resolution message. The contention resolution message may be sent as scheduled by the prior RAR message. This contention resolution message includes additional information based on the RAR grant that is used for contention resolution purposes. To send the Msg 3, the UE uses the same UE beam as it used to send the Msg 1. Further, the base station receives the Msg 3 using the SSB beam identified by / corresponding to the RO used for the UE:s transmission of Msg 1.

[0035] A “Message 4"’ (Msg 4) is then sent by the network. The Msg 4 may be referred to herein as a contention resolution response message. This contention resolution response message may carry an RRC reconfiguration message that delivers, to the UE, a configuration for the UE to use for subsequent signaling. In the case that the UE was not previously in a connected mode with the network, the use of these settings for the subsequent signaling corresponds to the establishment of the connected mode (e.g., RRC CONNECTED) between the UE and the network.

[0036] A “Message 5" (Msg 5) is then sent by the UE. Msg 5 may be transmitted with a typical size that is larger than other messages discussed herein. For example, a size of one Msg 5 may be at or around 118 bytes, as it may contain an RRCSetupComplete message (around 102 bytes), power headroom (PHR) and buffer status report (BSR) information (10 bytes), and sub-layer (including, packet data convergence protocol (PDCP), radio link control (RLC) and medium access control (MAC)) header overhead (6 bytes). It may be understood that the Msg 5 is transmitted in a physical uplink control channel (PUSCH).

[0037] A Msg 5 may thus be understood to correspond to / represent an undesirable bottleneck for communications between the UE and the network, due to its relatively larger payload size (e.g., as compared to a payload size for a Msg 3). For this signaling,6P69799WO1 4896-5552-6508' 1the UE and the base station may use the beams discussed above in the discussion for Msg 3.

[0038] In the context of various wireless communication systems, existing RACH procedures represent a relative bottleneck with respect to coverage. This is especially the case in FR2 implementations, due to the use of relatively wide beams (e.g.. SSB beams) as part of the RACH procedure. Corresponding to various cases using existing RACH procedures, it is noted that relatively narrower / finer beams only become available for use in performing signaling after the UE enters the connected mode (e.g., RRC CONNECTED) with the network and further configuration of CSI-RS ports are configured for beam measurement / management purposes (more generally, the narrower / finer beams only become available after separate follow-on configuration that occurs after a RACH procedure occurs).

[0039] Some existing implementations for AI / ML based beam management reduce the amount of reference signal / reference signal measurement overhead using an AI / ML model that implements a spatial domain beam prediction. In such cases, the measurements of beams (e.g., relatively wide beams and / or relatively more narrow / fine beams) may be predicted without using an actual CSI-RS port configuration for narrow / fine beam management. However, these existing implementations do not improve coverage aspects with respect to RACH procedures, at least because they pre-suppose that the CSI-RS port configuration has already occurred (which cannot be assumed in the case of all RACH procedures, such as RACH procedures for initial access).

[0040] Various embodiments herein relate to mechanisms for the use AI / ML models to predict appropriate communication beams as part of a RACH procedure in order to accelerate the identification of such communication beams as compared to such existing mechanisms (e.g., existing mechanisms that perform AI / ML model-based beam predictions only after the UE has established a connected mode with the network).

[0041] Embodiments herein disclose RACH procedures that incorporate the identification and use of relatively narrower / finer beams of the network using an AI / ML model located at a UE. Such RACH procedures exhibit improved coverage aspects and / or facilitate an earlier-in-time identification of relatively narrow beams useful for communication purposes over existing mechanisms.

[0042] In first embodiments discussed herein, a coverage enhancement due to the use of a network narrow beam extends from Msg 1 to Msg 5 of a RACH procedure. A system7P69799WO1 4896-5552-6508' 1information block (SIB) 1 (SIB1) that is broadcast by the network includes an association ID and a configuration that maps a set of RACH occasions (ROs) to a set of network narrow beams from which a predicted network narrow beams. The UE then performs RACH transmissions corresponding to predicted beam of the set of network narrow beams and the mapping of the set of ROs to the set of network narrow beams.

[0043] In second embodiments discussed herein, a coverage enhancement due to the use of a network narrow beam extends to at least Msg 5 (the most bottlenecked channel corresponding to the RACH procedure). It is observed that a relative comparison of payload sizes of messages of the RACH procedure may typically be (Msg 1 < Msg 3 < Msg 5). Thus. Msg 5 may be understood as the bottleneck transmission due to its largest payload size for uplink (UL) transmission. Second embodiments enhance the transmission of Msg 5 by identifying a network narrow beam for use using a Msg 3 of the RACH procedure.

[0044] Accordingly, it will be understood that while first embodiments discussed herein have a relatively higher RO overhead as compared to second embodiments, they enable the application of the narrower / finer beam for a larger portion of the RACH procedure. Second embodiments enjoy the advantage of the relatively lower RO resource overhead as compared to the first embodiments.

[0045] FIG. 1 illustrates a flow diagram 100 for a RACH procedure between a UE 102 and a network 104 according to first embodiments discussed herein. The behaviors of the network 104 may be understood to be carried out more particularly by, for example, a base station of the network 104.

[0046] Note preliminarily that corresponding to such cases, beam correspondence is assumed at both / each of the UE 102 side and the network 104 side. Accordingly, discussion with respect to such first embodiments understands that a beam of the UE 102 represents a same beamforming as used in either / both of the Tx direction and the Rx direction, and likewise that a beam of the network 104 represents a same beamforming as used in either / both of the Tx direction and the Rx direction.

[0047] First, as illustrated, the network 104 transmits SSBs 106 on a corresponding set of SSB beams, where each of the SSB beams corresponds to one of the transmitted SSBs. The transmission may occur using one or more SSB bursts of the SSBs on the SSB beams, in a beam sweeping manner (according to a Tx beam sweeping for the SSB bursts).8P69799WO1 4896-5552-6508' 1

[0048] The UE 102 performs a measurement of each of these SSB beams using each of a plurality of UE beams. These measurements may also be performed in beam sweeping manner (e.g., according to an Rx beam sweeping, using a different UE beam corresponding to each of the SSB bursts to take the measurements). Accordingly, the UE 102 generates a set of measurements of the SSBs as these are received using a plurality7of UE beams.

[0049] FIG. 2 illustrates a diagram 200 for the measurement of the SSBs 106 on corresponding SSB beams according to beam sweeping at both the network 104 and the UE 102. As illustrated, the network sends a number m of SSB bursts (the first SSB burst 202, the second SSB burst 204, .... until the / «-th SSB burst 206). Each SSB burst uses the set of SSBs 106 (the SSB 0 208, the SSB 1 210, the SSB 2 212, the SSB 3 214, ..., until the SSB n 216), where each of these SSBs is each sent on a corresponding one of a set of SSB beams used by the network, as illustrated. As shown, the correspondence between an SSB and its SSB beam remains the same across the different SSB bursts.

[0050] The UE 102 measures the SSBs 106 as transmitted on each of the SSB bursts using a number m of different UE beams. For example, as illustrated, the SSBs 106 as transmitted on the first SSB burst 202 are measured using the first UE beam 218, the SSBs 106 as transmitted on the second SSB burst 204 are measured using the second UE beam 220, ... , until the SSBs 106 as transmitted on the m-th SSB burst 206 are measured using the m-th UE beam 222.

[0051] Returning to FIG. 1 , as shown, the network 104 also transmits a SIB 1 108 (e g., in a beam sweeping manner) that is received at the UE 102.

[0052] The SIB1 108 carries an association ID. This association ID represents a mapping of a set A of beams (a set of beams from which a predicted beam is to be identified for use) to a set B of beams (a set of beams for which measurements are actually taken and then used to make the beam prediction within the set A of beams). Using this association ID, the UE 102 identifies an AI / ML model that may be used to identify the predicted beam from the set A of beams using the measurements of the set B of beams.

[0053] In some embodiments, the set B of beams may be the SSB beams used by the network to transmit the SSBs. Further, the set A of beams may be a set of network beams that is relatively more narrow than the SSB beams used by the network 104 to transmit the SSBs. Herein, this set of beams may be understood as a set of network narrow beams.9P69799WO1 4896-5552-6508' 1Accordingly, it is understood that the AI / ML model of the UE 102 is useful to identify a predicted network narrow beam that is predicted to be useful for subsequent communications between the UE 102 and the network 104 based on the measurements of the SSBs as sent on the SSB beams and as taken by the UE 102. In some cases, the set of network narrow beams may correspond to a CSI-RS resource set that is known to the network 104 and / or to the UE 102 (this CSI-RS resource set may also be indicated in the SIB1 108).

[0054] The SIB1 108 further carries two sets of mappings to sets of ROs configured between the UE 102 and the network 104. A first of these mappings maps a first set of ROs to the SSB beams (e.g., an RO to set B of beams mapping). A second of these mappings maps a second set of ROs to the set of network narrow beams (e.g., an RO to a set A of beams mapping).

[0055] With respect to the mapping of the second set of ROs to the set of network narrow beams, note that a size for the network narrow beams and their indexing to the set of ROs may be understood / implicitly later represented in terms of the association ID that identifies the AI / ML model during training of the AI / ML model.

[0056] The UE 102 then generates an inference 110 by providing the measurements of the SSBs as taken using the UE beams as input to the AI / ML model. This inference 110 identifies a predicted network narrow beam from the set of network narrow beams that is predicted to correspond to good coverage aspects (e.g.. a good signal strength and / or signal quality between the UE and the network) if used by the network 104 to communicate with the UE 102.

[0057] FIG. 3 illustrates a diagram 300 for the use of an AI / ML model 308 that is located at a UE 102 according to such embodiments. As illustrated, the AI / ML model 308 may receive, as input, one or more measurements 302 of SSBs as these SSBs were transmitted by the network 104 on corresponding SSB beams and measured by the UE 102 (e.g., as in the discussion of FIG. 2). In such circumstances, the SSB beams are understood as a set B of beams for which measurements (the measurements 302) are being used to generate one or more predictions for a set A of beams. The measurements 302 may be, for example, RSRP (e.g., Ll-RSRP) measurements.

[0058] Based on the measurements 302, the AI / ML model may generate, as output, predicted measurements 304 for each of a set of network narrow beams. In such10P69799WO1 4896-5552-6508' 1circumstances, the network narrow beams are understood as a set A of beams. The predicted measurements 304 may be, for example, RSRP (e.g., Ll-RSRP) measurements.

[0059] Based on the predicted measurements 304 of the network narrow beams, the UE 102 selects a predicted network narrow beam 306 from the set of network narrow beams. In some cases, the predicted network narrow beam 306 selected by the UE 102 is the network narrow beam for a strongest predicted measurement within the predicted measurements 304 (and thus is understood to be predicted to correspond to good coverage aspects between the UE 102 and the network 104).

[0060] Assuming that the UE 102 supports the AI / ML model 308 corresponding to the association ID indicated in the SIB1 108 and thus is capable of performing the prediction just described, the UE 102 uses the mapping of the second set of ROs to the set of network narrow beams as received in the SIB1 108 to identify an RO of the second set of ROs that corresponds to the predicted network narrow beam 306 identified through the use of the AI / ML model 308. The UE 102 then transmits a RACH transmission 112 made up of a RACH sequence using that RO.

[0061] The network 104 monitors this second set of ROs for the network narrow beams using the set of network narrow beams. As just described, the RO of this second set of ROs that corresponds to the predicted network narrow beam 306 is used by the UE 102 for the RACH transmission 112 having the RACH sequence. Accordingly, this RACH transmission 112 is received by the network 104 in the RO that is known to correspond to the predicted network narrow beam 306 selected by the UE 102. In this manner, the network is informed of the predicted network narrow beam 306 that was selected by the UE 102. Note that due to the use of the predicted network narrow beam 306 by the network 104 during this RO, signaling for the RACH transmission 112 occurs to good network coverage aspects between the UE 102 and the network 104.

[0062] FIG. 4 illustrates a diagram 400 illustrating the use and reception of the RACH transmission 112, according to such an embodiment. Suppose that the predicted network narrow beam 306 predicted by the AI / ML model 308 is understood by the UE 102 to correspond to the first UE beam 218. To identify this correspondence, the UE 102 may, for example, identify7that the use of the first UE beam 218 generated a strong measurement of an SSB transmitted on an SSB beam that is spatially congruent with the predicted network narrow beam 306. Alternatively, it may be that an AI / ML model at the UE (e.g., the AI / ML model 308, or another AI / ML model) is trained to identify11P69799WO1 4896-5552-6508' 1correspondence between the set of UE beams and the set of narrow network beams based on the measurements 302 and is used to make this correspondence.

[0063] As illustrated, the network 104 uses the first UE beam 218 to transmit the RACH transmission 112 in the RO that corresponds to the predicted network narrow beam 306. As previously discussed, a second set of network narrow beams is associated with the association ID previously sent by the UE 102 to the network 104 in the SIB1 108. Each of this second set of network narrow beams is used to monitor its corresponding RO in the second set of ROs as given in the mapping that was also provided in the SIB1 108.

[0064] Because the UE 102 sends the RACH transmission 112 in the RO for the predicted network narrow beam 306, the network 104 accordingly identifies that the predicted network narrow beam 306 the RACH transmission 112 is to be used going forward.

[0065] Again, returning to FIG. 1: in response to the RACH transmission 112, the network 104 transmits an RAR message 114. The network transmits the RAR message 114 using the predicted network narrow beam 306 identified according to the RACH transmission 112, as just described. Due to the use of the predicted network narrow beam 306 by the network 104, signaling for the RAR message 114 occurs to good network coverage aspects between the UE 102 and the network 104.

[0066] The UE 102, in response to receiving the RAR message 114 (e.g., using the same UE beam that was used to transmit the RACH transmission 112), transmits a contention resolution message 116.

[0067] The contention resolution message 116 is received by the network using the predicted network narrow' beam 306. In response to the contention resolution message 116, the network 104 transmits a contention resolution response message 118. The network transmits the contention resolution response message 118 using the predicted network narrow beam 306 identified according to the RACH transmission 112. Due to the use of the predicted netw ork narrow' beam 306 by the netw ork 104, signaling for each of the contention resolution message 116 and the contention resolution response message 118 occurs to good network coverage aspects between the UE 102 and the network 104.

[0068] The UE 102, in response to receiving the contention resolution response message 118 (e.g., using the same UE beam that was used to transmit the RACH transmission 112), transmits a Msg 5 120.12P69799WO1 4896-5552-6508' 1

[0069] The Msg 5 120 is received by the network 104 using the predicted network narrow beam 306 identified according to the RACH transmission 112. Due to the use of the predicted network narrow beam 306 by the network 104, signaling for the Msg 5 120 occurs according to good network coverage aspects between the UE 102 and the network 104.

[0070] Note that, relative to an alternative case where the network 104 uses a wide network beam (e.g., an SSB beam) instead of a predicted network narrow beam to receive a Msg 5 (and thus where applicable network coverage aspects are relatively less strong), the use of the predicted network narrow beam 306 for receiving the Msg 5 120 (and thus the existence of relatively stronger network coverage aspects) means that the Msg 5 120 may be sent with a relatively higher reliability and / or density (e.g., according to a relatively higher modulation and coding scheme (MCS)) than would otherwise be reasonable using the wide network beam. This means that the bottlenecking experienced due to the potentially large amount of data in the Msg 5 120 is relatively reduced as compared to the wide network beam case.

[0071] Note that in alternative cases to that just described, where a UE does not support the use of the AI / ML model 308 corresponding to the association ID indicated in the SIB1 108 and thus is not capable of performing the prediction, that UE rather sends a RACH transmission on a RACH occasion that, for example, corresponds to a strongest- measured SSB using the mapping of the set of ROs to the set of SSBs. The network receives this RACH transmission in an RO of the first set of ROs that is mapped to the SSB beams. In such circumstances, the remainder of the RACH procedure proceeds according to a use by the network of a corresponding SSB beam (instead of the use of a network narrow beam).

[0072] FIG. 5 illustrates a RACH -ConfigCommon IE 500 as may be used to configure a first mapping of a first set of ROs to SSB beams and a second mapping of a second set of ROs to a set of network narrow beams, as discussed in embodiments herein. The RACH- ConflgCommon IE 500 may be included in, for example, a SIB1 (e.g.. the SIB1 108 of FIG. 1).

[0073] As illustrated, the RACH-ConfigCommon IE 500 includes an ssb-perRACH- OcccasionAndCB-PreamblesPerSSB IE 502. The ssb-perRACH-OcccasionAndCB- PreamblesPerSSB IE 502 identifies a mapping between the first set of ROs and a set of SSB beams by identifying, based on a selection therein (e.g., a selection of “oneEighth,”13P69799WO1 4896-5552-6508' 1“oneFourth,"’ etc.), a number of SSBs (as these correspond to their SSB beams) for each of the first set of ROs when the each SSB of the set of SSBs is applied (in order) to the indicated amount of ROs from the (ordered) first set of ROs. The SSBs may be identified using an SSB index.

[0074] Further, as illustrated, the RACH -Conf igCommon IE 500 also includes setA- perRACH-OccasionAndCB-PreamblesPerSetA-beam IE 504. The setA-perRACH- OcccisionAndCB-PreamblesPerSetA-beam IE 504 identifies a mapping between the second set of ROs and a set of network narrow beams (a “Set A"’ of beams) by identifying, based on a selection therein (e.g.. a selection of “oneEighth,” “oneFourth,” etc.), a number of network narrow beams for each of the second set of ROs when the each network narrow beam of the set of network narrow beams is applied (in order) to the indicated amount of ROs from the (ordered) second set of ROs.

[0075] FIG. 6 illustrates a diagram 600 visualizing a RACH configuration of a first set of ROs that is mapped to a set of SSB beams and a second set of ROs that is mapped to a set of network narrow beams. As illustrated, according to the configuration, instances 602 of a first set of ROs mapped to a set of SSB beams and instances 604 of a second set of ROs mapped to network narrow beams may be time domain multiplexed (TDMed).

[0076] A RACH configuration sent from the network to the UE may provide for different TDM patterns for each of a first set of ROs mapped to SSB beams and a second set of ROs mapped to network narrow beams. For example, a RACH configuration may provide for alternating single instances of the first and second sets (e.g., as illustrated in FIG. 6). As another example, a RACH configuration may provide for two instances of a first set of ROs mapped to the SSB beams followed by one instance of a second set of ROs mapped to network narrow beams. Note that these examples are not given by way of limitation, and that other patterns not explicitly discussed here are possible.

[0077] Then, a UE can choose to perform a RACH transmission on an RO of the first set of ROs for the SSB beams (e.g., when the UE does not have the capability to use an AI / ML model associated with the second set of ROs for the network narrow beams and / or when signal strength / quality (e.g., Ll-RSRP) is good), or to instead perform a RACH transmission on an RO of the second set of ROs mapped to the set of network narrow beams (e.g., when the UE has the capability to use the AI / ML model associated with the second set of ROs for the network narrow beams and / or when signal strength / quality (e.g., Ll-RSRP) is poor).14P69799WO1 4896-5552-6508' 1

[0078] FIG. 7 illustrates a flow diagram 700 for a RACH procedure between a UE 702 and a network 704 according to second embodiments discussed herein. The behaviors of the network 704 may be understood to be carried out more particularly by, for example, a base station of the network 704.

[0079] Note preliminarily that corresponding to such cases, beam correspondence is assumed at both / each of the UE 702 side and the network 704 side. Accordingly, discussion with respect to such second embodiments understands that a beam of the UE 702 represents a same beamforming as used in either / both of the Tx direction and the Rx direction, and likewise that a beam of the network 704 represents a same beamforming as used in either / both of the Tx direction and the Rx direction.

[0080] First, as illustrated, the network 704 transmits SSBs 706 on a corresponding set of SSB beams, where each of the SSB beams corresponds to one of the transmitted SSBs. The transmission may occur using one or more SSB bursts of the SSBs on the SSB beams, in a beam sweeping manner (according to a Tx beam sweeping for the SSB bursts).

[0081] The UE 702 performs a measurement of each of these SSB beams using each of a plurality of UE beams. These measurements may also be performed in beam sweeping manner (e.g., according to an Rx beam sweeping, using a different UE beam corresponding to each of the SSB bursts to take measurements). Accordingly, the UE 702 generates a set of measurements of the SSBs as these are received using a plurality of UE beams. Refer to, e.g., FIG. 2 and corresponding discussion thereof herein.

[0082] As further shown in FIG. 1, the network 704 also transmits a SIB1 708 (e.g., in a beam sweeping manner) that is received at the UE 702. The SIB1 708 carries an association ID. This association ID represents a mapping of a set of SSB beams to a set of network narrow beams. Using this association ID, the UE 702 identifies an AI / ML model that may be used to identify a predicted network narrow beam from the set of network narrow beams using the measurements of the set of SSB beams. In some cases, the set of network narrow beams may correspond to a CSI-RS resource set that is known to the network 704 and / or to the UE 702 (this CSI-RS resource set may also be indicated in the SIB1 708).

[0083] The SIB1 708 further carries a mapping of a set of ROs to the set of SSB beams used by the SSBs 706 (e.g., in an ssb-perRACH-OcccasionAndCB-PrecimblesPerSSB IE of a RACPI-ConfigCommon IE).15P69799WO1 4896-5552-6508' 1

[0084] The flow diagram 700 of FIG. 7, as compared to the flow diagram 100 of FIG. 1, reflects the principle that effective RACH procedure coverage aspects are (effectively / as applied) Apically relatively better than (effective / applied) coverage aspects specific to the communication of Msg 5 720. This is because, for example, a RACH transmission 710 carries a relatively small amount (e.g., one bit) of substantive information, while a Msg 5 720 carries more than this. Thus, the most relevant message of the flow diagram 700 (that is in large part responsible for the consequences of bottlenecking) is / will be the Msg 5 720.

[0085] Accordingly, the flow diagram 700 begins the use of a predicted network narrow beam later than in the case of an embodiment for the flow diagram 100 of FIG. 1 (as shown in FIG. 7, starting with the contention resolution response message 718, as will be discussed). Under such a mechanism, there is no immediate need (at the time of the RACH transmission 710) use an RO of the RACH procedure to indicate / identify a particular network narrow beam.

[0086] Accordingly, alternatively to the SIB1 108 of FIG. 1, the SIB1 708 of FIG. 7 does not carry a mapping between any set of ROs and the set of network narrow beams. The RACH transmission 710 is transmitted in an RO corresponding to an SSB beam of the network (e.g., for which a strongest measurement of a corresponding SSB across all the SSB measurements was taken, as identified using the mapping of the set of ROs to the set of SSB beams received in the SIB1 708).

[0087] Further, a RACH partitioning mechanism may be used with the RACH transmission 710 in order to identify to the network 704 that the UE 702 can use the AI / ML model corresponding to the association ID that was indicated in the SIB1 708. With respect to this RACH partitioning, it may be that, in some cases, a separate RACH root sequence (RACH preamble) may be reserved for use by UEs that are capable of using the AI / ML model corresponding to the association ID, while other RACH root sequences are used by UEs that are not capable of using the AI / ML model. In some cases, certain time resources for sending the RACH transmission 710 may be reserved for use by UEs that are capable of using the AI / ML model corresponding to the association ID, while other time resources for sending the RACH transmission 710 may be used by UEs that are not capable of using the AI / ML model. In some cases, certain frequency resources for sending the RACH transmission 710 may be reserved for use by UEs that are capable of using the AI / ML model corresponding to the association ID.16P69799WO1 4896-5552-6508' 1while other frequency resources for sending the RACH transmission 710 may be used by UEs that are not capable of using the AI / ML model.

[0088] The flow diagram 700 assumes the case that the UE 702 is capable of using the AI / ML model corresponding to the association ID indicated in the SIB1 708. Accordingly, the RACH transmission 710 is sent according to a dedicated RACH root sequence, a dedicated time resource, and / or a dedicated frequency resource to indicate this capability to the network 704.

[0089] Upon receiving the RACH transmission 710 in this manner, the network 704 correspondingly identifies the UE 702 as a UE that can use the AI / ML model identified by the association ID that was indicated in the SIB1 708. Accordingly, in response to the RACH transmission 710, the network 704 transmits an RAR message 712 that includes an indication that the UE 702 is to use the AI / ML model to generate a predicted network narrow beam for the network 704 to use during subsequent communications and to identify that predicted network narrow beam to the network 704.

[0090] In some embodiments, this indication is made using a channel state information (CSI) request bit of the RAR message 712. FIG. 8 illustrates a table 802 for RAR message content field sizes, according to some embodiments. Among other things, the table 802 illustrates that an RAR message (e.g., the RAR message 712) may include a CSI request field 804 having a size of one bit.

[0091] Note that in various existing wireless communication systems, a CSI request field bit of an RAR message of a RACH procedure that is being used for initial access is reserved (is not used to make any substantive indications), at least because there is no expectation of CSI feedback to be provided in the contention resolution message 716 in such initial access cases. It is accordingly recognized that, for embodiments discussed herein corresponding to the use of the flow diagram 700, such a CSI request bit can be substantively used to instruct the UE to identify and report a predicted network narrow beam (e.g., instead of for representing a CSI request).

[0092] For example, it may be that a CSI request bit value of ‘ 1 ’ instructs the UE to identify and report a predicted network narrow beam, while a CSI request bit value of ‘0’ instructs the UE not to perform these actions (or vice-versa).

[0093] Returning to FIG. 7: in response to receiving the RAR message 712 having the indication to identify and report a predicted network narrow beam, the UE 702 generates an inference 714 by providing the measurements of the SSBs 706 as taken using the UE17P69799WO1 4896-5552-6508' 1beams as input to the AI / ML model. This inference identifies a predicted network narrow beam from the set of network narrow beams that is predicted to correspond to good coverage aspects (e.g., a good signal strength and / or signal quality between the UE 702 and the network 704) if used by the network 704 to communicate with the UE 702. Refer to, e.g., FIG. 3 and corresponding discussion thereof herein.

[0094] The UE 702 then reports this predicted network narrow beam to the network 704 in the contention resolution message 716. Note that the partitioning used corresponding to the identification of the UE 702 as capable of using the AI / ML model according to the RACH transmission 710 also acts to inform the network that a contention resolution message 716 that is sized to include information about the predicted network narrow beam will ultimately be sent by the UE 702. Accordingly, the network 704 expects the contention resolution message 716 to include the indication of the predicted network narrow beam. The indication may be made using, for example, a beam index for the predicted network narrow beam. This may, in some cases, use six bits within the contention resolution message 716.

[0095] In some embodiments, the contention resolution message 716 may further include (again, as expected by the network per the partitioning) a predicted signal strength (e.g., Ll -RSRP) of the predicted network narrow beam as predicted by the AI / ML model (in addition to the beam index for the predicted network narrow beam). The indication of the predicted signal strength may, in some cases, use seven bits within the contention resolution message 716.

[0096] In response to the contention resolution message 716, the network 704 transmits a contention resolution response message 718. The network transmits the contention resolution response message 718 using the predicted network narrow beam identified according to the contention resolution message 716. Due to the use of the predicted network narrow beam by the network 704, signaling for the contention resolution response message 118 occurs to good network coverage aspects between the UE 702 and the network 704.

[0097] The UE 702, in response to receiving the contention resolution response message 718 (e.g., using the same UE beam that was used to transmit the RACH transmission 710), transmits a Msg 5 720.

[0098] The Msg 5 720 is received by the network 704 using the predicted network narrow beam identified according to the contention resolution message 716. Due to the18P69799WO1 4896-5552-650811use of the predicted network narrow beam by the network 704, signaling for the Msg 5 720 occurs according to good network coverage aspects between the UE 702 and the network 704.

[0099] Note that, relative to an alternative case where the network 704 uses a wide network beam (e.g.. an SSB beam) instead of the predicted network narrow beam to receive a Msg 5 (and thus where applicable network coverage aspects are relatively less strong), the use of the predicted network narrow beam for receiving the Msg 5 720 (and thus the existence of relatively stronger network coverage aspects) means that the Msg 5 720 may be sent with a relatively higher reliability and / or density (e.g., according to a relatively higher MCS) than would otherwise be reasonable using the wide network beam. This means that the bottlenecking experienced due to the potentially large amount of data in the Msg 5 720 is relatively reduced as compared to the wide network beam case.

[0100] FIG. 9 illustrates a method 900 of a UE, according to embodiments discussed herein. The method 900 includes receiving 902, from a base station, a system information message comprising a first mapping of a first set of ROs to a set of network narrow beams and an association ID identifying an AI / ML model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted SSBs transmitted on a set of network SSB beams. The method 900 further includes generating 904 the measurements of the transmitted SSBs as transmitted by the base station using a plurality of UE beams. The method 900 further includes providing 906 the measurements as input to the AI / ML model to identify, using the AI / ML model, the predicted network narrow beam. The method 900 further includes identifying 908, based on the first mapping, a selected RO of the first set of ROs corresponding to the predicted network narrow beam. The method 900 further includes sending 910. to the base station, on the selected RO, a RACH transmission.

[0101] In some embodiments of the method 900, the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

[0102] In some embodiments of the method 900, the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

[0103] In some embodiments of the method 900, the system information message further comprises a second mapping of a second set of ROs to the transmitted SSBs.19P69799WO1 4896-5552-6508' 1

[0104] FIG. 10 illustrates a method 1000 of a base station, according to embodiments discussed herein. The method 1000 includes sending 1002, to a UE. a system information message comprising a first mapping of a first set of ROs to a set of network narrow beams and an association ID identifying an AI / ML model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted SSBs transmitted on a set of network SSB beams. The method 1000 further includes transmitting 1004 the transmitted SSBs on the set of network SSB beams. The method 1000 further includes receiving 1006, from the UE, a RACH transmission on a selected RO of the first set of ROs that was selected by the UE and that corresponds to a predicted network narrow beam predicted by the UE. The method 1000 further includes sending 1008, to the UE, an RAR message on the predicted network narrow beam.

[0105] In some embodiments of the method 1000, the RACH transmission is received using the predicted network narrow beam.

[0106] In some embodiments of the method 1000, the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

[0107] In some embodiments of the method 1000, the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

[0108] In some embodiments of the method 1000, the system information message further comprises a second mapping of a second set of ROs to the transmitted SSBs.

[0109] FIG. 11 illustrates a method 1100 of a UE. according to embodiments discussed herein. The method 1100 includes receiving 1102, from a base station, a system information message comprising an association ID identifying an AI / ML model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted SSBs that are transmitted on a set of network SSB beams. The method 1100 further includes generating 1104 the measurements of the transmitted SSBs as transmitted by the base station using a plurality of UE beams. The method 1100 further includes sending 1106, to the base station, a RACH transmission on a selected RO. The method 1100 further includes receiving 1108, from the base station, in response to the RACH transmission, an RAR message that schedules a contention resolution message and that indicates that the UE is to identify the predicted network narrow beam to the base station. The method 1100 further includes providing 1110 the measurements as inputs to the AI / ML model to identify', using the AI / ML model, the predicted network20P69799WO1 4896-5552-6508' 1narrow beam. The method 1100 further includes sending 1112, to the base station, the contention resolution message as scheduled by the RAR. wherein the contention resolution identifies the predicted network narrow beam.

[0110] In some embodiments of the method 1100, the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

[0111] In some embodiments of the method 1100, the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

[0112] In some embodiments of the method 1100, the selected RO uses a frequency resource that indicates, to the base station, that the UE can use the AI / ML model.

[0113] In some embodiments of the method 1100, the system information message further identifies the set of network narrow beams.

[0114] In some embodiments of the method 1100. the system information message further comprises a mapping of a set of ROs to the transmitted SSBs; and further comprising identifying, based on the mapping, one RO of the set of ROs that corresponds to a strongest measurement of the measurements of the transmitted SSBs as the selected RO.

[0115] In some embodiments of the method 1100, the RAR message indicates that the UE is to identify the predicted network narrow beam to the base station using a CSI request field.

[0116] In some embodiments of the method 1100, the contention resolution message further comprises a predicted Ll-RSRP for the predicted network narrow beam, and wherein the AI / ML model generates the predicted Ll-RSRP for the predicted network narrow beam based on the measurements of the transmitted SSBs.

[0117] FIG. 12 illustrates a method 1200 of a base station, according to embodiments discussed herein. The method 1200 includes sending 1202, to a UE. a system information message comprising an association ID identifying an AI / ML model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted SSBs that are transmitted on a set of network SSB beams. The method 1200 further includes transmitting 1204 the transmitted SSBs on the set of network SSB beams. The method 1200 further includes receiving 1206s, from the UE, a RACH transmission on a selected RO selected by the UE. The method 1200 further includes21P69799WO1 4896-5552-6508' 1sending 1208, to the UE, in response to the RACH transmission, an RAR message that schedules a contention resolution message and that indicates that the UE is to identify the predicted network narrow beam to the base station. The method 1200 further includes receiving 1210, from the UE, the contention resolution message as scheduled by the RAR, wherein the contention resolution identifies the predicted network narrow7beam. The method 1200 further includes sending 1212, to the UE, in response to the contention resolution message, a contention resolution response message using the predicted network narrow beam.

[0118] In some embodiments of the method 1200. the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

[0119] In some embodiments of the method 1200. the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

[0120] In some embodiments of the method 1200, the selected RO uses a frequency resource that indicates, to the base station, that the UE can use the AI / ML model.

[0121] In some embodiments of the method 1200, the system information message further identifies the set of network narrow beams.

[0122] In some embodiments of the method 1200, the system information message further comprises a mapping of a set of ROs to the transmitted SSBs.

[0123] In some embodiments of the method 1200. the RAR message indicates that the UE is to identify the predicted network narrow beam to the base station using a CSI request field.

[0124] In some embodiments of the method 1200. the contention resolution message further comprises a predicted LI -RSRP for the predicted network narrow beam.

[0125] FIG. 13 illustrates an example architecture of a wireless communication system 1300, according to embodiments disclosed herein. The following description is provided for an example wireless communication system 1300 that operates in conjunction with the LTE system standards and / or 5G or NR system standards as provided by 3GPP technical specifications.

[0126] As shown by FIG. 13, the wireless communication system 1300 includes UE 1302 and UE 1304 (although any number of UEs may be used). In this example, the UE 1302 and the UE 1304 are illustrated as smartphones (e.g., handheld touchscreen mobile22P69799WO1 4896-5552-6508' 1computing devices connectable to one or more cellular networks), but may also comprise any mobile or non-mobile computing device configured for wireless communication.

[0127] The UE 1302 and UE 1304 may be configured to communicatively couple with a RAN 1306. In embodiments, the RAN 1306 may be NG-RAN, E-UTRAN, etc. The UE 1302 and UE 1304 utilize connections (or channels) (shown as connection 1308 and connection 1310, respectively) with the RAN 1306, each of which comprises a physical communications interface. The RAN 1306 can include one or more base stations (such as base station 1312 and base station 1314) that enable the connection 1308 and connection 1310.

[0128] In this example, the connection 1308 and connection 1310 are air interfaces to enable such communicative coupling, and may be consistent with RAT(s) used by the RAN 1306, such as. for example, an LTE and / or NR.

[0129] In some embodiments, the UE 1302 and UE 1304 may also directly exchange communication data via a sidelink interface 1316. The UE 1304 is shown to be configured to access an access point (shown as AP 1318) via connection 1320. By way of example, the connection 1320 can comprise a local wireless connection, such as a connection consistent with any IEEE 802.11 protocol, wherein the AP 1318 may comprise a Wi-Fi® router. In this example, the AP 1318 may be connected to another network (for example, the Internet) without going through a CN 1324.

[0130] In embodiments, the UE 1302 and UE 1304 can be configured to communicate using orthogonal frequency division multiplexing (OFDM) communication signals with each other or with the base station 1312 and / or the base station 1314 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.

[0131] In some embodiments, all or parts of the base station 1312 or base station 1314 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 1312 or base station 1314 may be configured to communicate with one another via interface23P69799WO1 4896-5552-6508' 11322. In embodiments where the wireless communication system 1300 is an LTE system (e.g.. when the CN 1324 is an EPC), the interface 1322 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 1300 is an NR system (e.g., when CN 1324 is a 5GC), the interface 1322 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 1312 (e.g., a gNB) connecting to 5GC and an eNB, and / or between two eNBs connecting to 5GC (e.g., CN 1324).

[0132] The RAN 1306 is shown to be communicatively coupled to the CN 1324. The CN 1324 may comprise one or more network elements 1326, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UE 1302 and UE 1304) who are connected to the CN 1324 via the RAN 1306. The components of the CN 1324 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).

[0133] In embodiments, the CN 1324 may be an EPC, and the RAN 1306 may be connected with the CN 1324 via an SI interface 1328. In embodiments, the SI interface 1328 may be split into two parts, an SI user plane (Sl-U) interface, which carries traffic data between the base station 1312 or base station 1314 and a serving gateway (S-GW), and the SI -MME interface, which is a signaling interface between the base station 1312 or base station 1314 and mobility management entities (MMEs).

[0134] In embodiments, the CN 1324 may be a 5GC, and the RAN 1306 may be connected with the CN 1324 via an NG interface 1328. In embodiments, the NG interface 1328 may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the base station 1312 or base station 1314 and a user plane function (UPF), and the SI control plane (NG-C) interface, which is a signaling interface between the base station 1312 or base station 1314 and access and mobility management functions (AMFs).

[0135] Generally, an application server 1330 may be an element offering applications that use internet protocol (IP) bearer resources with the CN 1324 (e.g., packet switched data services). The application server 1330 can also be configured to support one or24P69799WO1 4896-5552-6508' 1more communication services (e.g., VoIP sessions, group communication sessions, etc.) for the UE 1302 and UE 1304 via the CN 1324. The application server 1330 may communicate with the CN 1324 through an IP communications interface 1332.

[0136] FIG. 14 illustrates a system 1400 for performing signaling 1434 between a wireless device 1402 and a network device 1418, according to embodiments disclosed herein. The system 1400 may be a portion of a wireless communications system as herein described. The wireless device 1402 may be, for example, a UE of a wireless communication system. The network device 1418 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.

[0137] The wireless device 1402 may include one or more processor(s) 1404. The processor(s) 1404 may execute instructions such that various operations of the wireless device 1402 are performed, as described herein. The processor(s) 1404 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 hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0138] The wireless device 1402 may include a memory 1406. The memory' 1406 may be a non-transitory computer-readable storage medium that stores instructions 1408 (which may include, for example, the instructions being executed by the processor(s) 1404). The instructions 1408 may also be referred to as program code or a computer program. The memory' 1406 may also store data used by, and results computed by, the processor(s) 1404.

[0139] The wireless device 1402 may include one or more transceiver(s) 1410 that may include radio frequency (RF) transmitter circuitry' and / or receiver circuitry' that use the antenna(s) 1412 of the wireless device 1402 to facilitate signaling (e.g.. the signaling 1434) to and / or from the wireless device 1402 with other devices (e.g., the network device 1418) according to corresponding RATs.

[0140] The wireless device 1402 may include one or more antenna(s) 1412 (e.g., one, two, four, or more). For embodiments with multiple antenna(s) 1412, the wireless device 1402 may leverage the spatial diversity of such multiple antenna(s) 1412 to send and / or receive multiple different data streams on the same time and frequency resources. This behavior may be referred to as, for example, multiple input multiple output (MIMO)25P69799WO1 4896-5552-6508' 1behavior (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 1402 may be accomplished according to precoding (or digital beamforming) that is applied at the wireless device 1402 that multiplexes the data streams across the antenna(s) 1412 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).

[0141] In certain embodiments having multiple antennas, the wireless device 1402 may implement analog beamforming techniques, whereby phases of the signals sent by the antenna(s) 1412 are relatively adjusted such that the (joint) transmission of the antenna(s) 1412 can be directed (this is sometimes referred to as beam steering).

[0142] The wireless device 1402 may include one or more interface(s) 1414. The interface(s) 1414 may be used to provide input to or output from the wireless device 1402. For example, a wireless device 1402 that is a UE may include interface(s) 1414 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) 1410 / antenna(s) 1412 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).

[0143] The wireless device 1402 may include an AI / ML-based RACH procedure beam management module 1416. The AI / ML-based RACH procedure beam management module 1416 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML-based RACH procedure beam management module 1416 may be implemented as a processor, circuit, and / or instructions 1408 stored in the memory 1406 and executed by the processor(s) 1404. In some examples, the AI / ML-based RACH procedure beam management module 1416 may be integrated within the processor(s) 1404 and / or the transceiver(s) 1410. For example, the AI / ML-based RACH procedure beam management module 1416 may be implemented by a combination of software26P69799WO1 4896-5552-6508' 1components (e.g., executed by a DSP or a general processor) and hardware components (e.g.. logic gates and circuitry) within the processor(s) 1404 or the transceiver(s) 1410.

[0144] The AI / ML-based RACH procedure beam management module 1416 may be used for various aspects of the present disclosure, for example, aspects of FIG. 9 and / or FIG. 11. In some embodiments, the AI / ML-based RACH procedure beam management module 1416 may configure the wireless device 1402 to receive, from a network device 1418, a system information message comprising a first mapping of a first set of ROs to a set of network narrow beams and an association ID identifying an AI / ML model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted SSBs transmitted on a set of network SSB beams; generate the measurements of the transmitted SSBs as transmitted by the network device 1418 using a plurality of UE beams; provide the measurements as input to the AI / ML model to identify, using the AI / ML model, the predicted network narrow beam; identify, based on the first mapping, a selected RO of the first set of ROs corresponding to the predicted network narrow beam; and / or send, to the network device 1418, on the selected RO, a RACH transmission, as discussed herein. In some embodiments, the AI / ML-based RACH procedure beam management module 1416 may configure the wireless device 1402 to receive, from a network device 1418, a system information message comprising an association ID identifying an AI / ML model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted SSBs that are transmitted on a set of network SSB beams; generate the measurements of the transmitted SSBs as transmitted by the network device 1418 using a plurality of UE beams; send, to network device 1418, a RACH transmission on a selected RO; receive, from the network device 1418, in response to the RACH transmission, a RAR message that schedules a contention resolution message and that indicates that the wireless device 1402 is to identify the predicted network narrow beam to the network device 1418; provide the measurements as inputs to the AI / ML model to identify, using the AI / ML model, the predicted network narrow beam; and / or send, to the network device 1418, the contention resolution message as scheduled by the RAR, wherein the contention resolution identifies the predicted network narrow beam, as discussed herein.

[0145] The network device 1418 may include one or more processor(s) 1420. The processor(s) 1420 may execute instructions such that various operations of the network device 1418 are performed, as described herein. The processor(s) 1420 may include one27P69799WO1 4896-5552-6508' 1or 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.

[0146] The network device 1418 may include a memory' 1422. The memory 1422 may be a non-transitory computer-readable storage medium that stores instructions 1424 (which may include, for example, the instructions being executed by the processor(s) 1420). The instructions 1424 may also be referred to as program code or a computer program. The memory' 1422 may also store data used by, and results computed by, the processor(s) 1420.

[0147] The network device 1418 may include one or more transceiver(s) 1426 that may include RF transmitter circuitry' and / or receiver circuitry that use the antenna(s) 1428 of the network device 1418 to facilitate signaling (e.g., the signaling 1434) to and / or from the network device 1418 with other devices (e.g., the wireless device 1402) according to corresponding RATs.

[0148] The network device 1418 may include one or more antenna(s) 1428 (e.g., one, two, four, or more). In embodiments having multiple antenna(s) 1428, the network device 1418 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as has been described.

[0149] The network device 1418 may include one or more interface(s) 1430. The interface(s) 1430 may be used to provide input to or output from the network device 1418. For example, a network device 1418 that is a base station may include interface(s) 1430 made up of transmitters, receivers, and other circuitry (e g., other than the transceiver(s) 1426 / antenna(s) 1428 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.

[0150] The network device 1418 may include an AI / ML-based RACH procedure beam management module 1432. The AI / ML-based RACH procedure beam management module 1432 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML-based RACH procedure beam management module 1432 may be implemented as a processor, circuit, and / or instructions 1424 stored in the memory' 1422 and executed by the processor(s) 1420. In some examples, the AI / ML-based RACH28P69799WO1 4896-5552-6508' 1procedure beam management module 1432 may be integrated within the processor(s) 1420 and / or the transceiver(s) 1426. For example, the AI / ML-based RACH procedure beam management module 1432 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) 1420 or the transceiver(s) 1426.

[0151] The AI / ML-based RACH procedure beam management module 1432 may be used for various aspects of the present disclosure, for example, aspects of FIG. 10 and / or FIG. 12. In some embodiments, the AI / ML-based RACH procedure beam management module 1432 may configure the network device 1418 to send, to the wireless device 1402, a system information message comprising a first mapping of a first set of ROs to a set of network narrow beams and an association ID identifying an AI / ML model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted SSBs transmitted on a set of network SSB beams; transmit the transmitted SSBs on the set of network SSB beams; receive, from the wireless device 1402, a RACH transmission on a selected RO of the first set of ROs that was selected by the wireless device 1402 and that corresponds to a predicted network narrow beam predicted by the wireless device 1402; and / or send, to the wireless device 1402, a RAR message on the predicted network narrow beam, as discussed herein. In some embodiments, the AI / ML-based RACH procedure beam management module 1432 may configure the network device 1418 to send, to the wireless device 1402, a system information message comprising an association ID identifying an AI / ML model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted SSBs that are transmitted on a set of network SSB beams; transmit the transmitted SSBs on the set of network SSB beams; receive, from the wireless device 1402, a RACH transmission on a selected RO selected by the wireless device 1402; send, to the wireless device 1402, in response to the RACH transmission, a RAR message that schedules a contention resolution message and that indicates that the wireless device 1402 is to identify the predicted network narrow beam to the base station; receive, from the wireless device 1402, the contention resolution message as scheduled by the RAR, wherein the contention resolution identifies the predicted network narrow beam; and / or send, to the wireless device 1402, in response to the contention resolution message, a contention resolution response message using the predicted network narrow beam, as discussed herein.29P69799WO1 4896-5552-6508' 1

[0152] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the method 900 and / or the method 1100. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1402 that is a UE, as described herein).

[0153] 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 900 and / or the method 1100. This non-transitory computer-readable media may be, for example, a memory of a UE (such as a memory 1406 of a wireless device 1402 that is a UE, as described herein).

[0154] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any of the method 900 and / or the method 1100. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1402 that is a UE, as described herein).

[0155] 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 900 and / or the method 1100. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1402 that is a UE, as described herein).

[0156] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the method 900 and / or the method 1100.

[0157] 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 900 and / or the method 1100. The processor may be a processor of a UE (such as a processor(s) 1404 of a wireless device 1402 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' 1406 of a wireless device 1402 that is a UE, as described herein).

[0158] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the method 1000 and / or the method 1200. This apparatus may be, for example, an apparatus of a base station (such as a network device 1418 that is a base station, as described herein).30P69799WO1 4896-5552-6508' 1

[0159] 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 / or the method 1200. This non-transitory computer-readable media may be, for example, a memory7of a base station (such as a memory71422 of a network device 1418 that is a base station, as described herein).

[0160] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of any of the method 1000 and / or the method 1200. This apparatus may be, for example, an apparatus of a base station (such as a network device 1418 that is a base station, as described herein).

[0161] 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 1000 and / or the method 1200. This apparatus may be, for example, an apparatus of a base station (such as a network device 1418 that is a base station, as described herein).

[0162] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the method 1000 and / or the method 1200.

[0163] 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 1000 and / or the method 1200. The processor may be a processor of a base station (such as a processor(s) 1420 of a network device 1418 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 memory71422 of a network device 1418 that is a base station, as described herein).

[0164] 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, network31P69799WO1 4896-5552-6508' 1element, 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.

[0165] 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.

[0166] Embodiments and implementations of the systems 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.

[0167] 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.

[0168] 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.

[0169] 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 without32P69799WO1 4896-5552-6508' 1departing 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.33P69799WO1 4896-5552-6508' 1

Claims

CLAIMS1. A method of a user equipment (UE), comprising: receiving, from a base station, a system information message comprising: a first mapping of a first set of random access channel (RACH) occasions (ROs) to a set of network narrow beams: and an association identifier (ID) identifying an artificial intelligence (Al)Zmachine learning (ML) model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted synchronization signal blocks (SSBs) transmitted on a set of network SSB beams; generating the measurements of the transmitted SSBs as transmitted by the base station using a plurality of UE beams; providing the measurements as input to the AI / ML model to identify, using the AI / ML model, the predicted network narrow beam; identifying, based on the first mapping, a selected RO of the first set of ROs corresponding to the predicted network narrow beam; and sending, to the base station, on the selected RO, a RACH transmission.

2. The method of claim 1, wherein the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

3. The method of claim 1, wherein the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

4. The method of claim 1, wherein the system information message further comprises a second mapping of a second set of ROs to the transmitted SSBs.

5. A method of a base station, comprising: sending, to a user equipment (UE), a system information message comprising: a first mapping of a first set of random access channel (RACH) occasions (ROs) to a set of network narrow beams; and an association identifier (ID) identify ing an artificial intelligence (Al)Zmachine learning (ML) model for identifying a predicted network narrow beam from the set of network narrow beams using measurements of transmitted synchronization signal blocks (SSBs) transmitted on a set of network SSB beams; transmitting the transmitted SSBs on the set of network SSB beams;34P69799WO1 4896-5552-6508Mreceiving, from the UE, a RACH transmission on a selected RO of the first set of ROs that was selected by the UE and that corresponds to a predicted network narrow beam predicted by the UE; and sending, to the UE, a random access response (RAR) message on the predicted network narrow beam.

6. The method of claim 5, wherein the RACH transmission is received using the predicted network narrow beam.

7. The method of claim 5, wherein the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

8. The method of claim 5, wherein the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

9. The method of claim 5, wherein the system information message further comprises a second mapping of a second set of ROs to the transmitted SSBs.

10. A method of a user equipment (UE), comprising: receiving, from a base station, a system information message comprising an association identifier (ID) identifying an artificial intelligence (Al)Zmachine learning (ML) model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted synchronization signal blocks (SSBs) that are transmitted on a set of network SSB beams; generating the measurements of the transmitted SSBs as transmitted by the base station using a plurality of UE beams; sending, to the base station, a random access channel (RACH) transmission on a selected RACH occasion (RO); receiving, from the base station, in response to the RACH transmission, a random access response (RAR) message that schedules a contention resolution message and that indicates that the UE is to identify the predicted network narrow beam to the base station; providing the measurements as inputs to the AI / ML model to identify, using the AI / ML model, the predicted network narrow beam; and35P69799WO1 4896-5552-6508' 1sending, to the base station, the contention resolution message as scheduled by the RAR, wherein the contention resolution identifies the predicted network narrow beam.

11. The method of claim 10, wherein the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

12. The method of claim 10, wherein the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.

13. The method of claim 10, wherein the selected RO uses a frequency resource that indicates, to the base station, that the UE can use the AI / ML model.

14. The method of claim 10, wherein the system information message further identifies the set of network narrow beams.

15. The method of claim 10, wherein the system information message further comprises a mapping of a set of ROs to the transmitted SSBs; and further comprising identifying, based on the mapping, one RO of the set of ROs that corresponds to a strongest measurement of the measurements of the transmitted SSBs as the selected RO.

16. The method of claim 10, wherein the RAR message indicates that the UE is to identify the predicted network narrow beam to the base station using a channel state information (CSI) request field.

17. The method of claim 10, wherein the contention resolution message further comprises a predicted layer 1 reference signal received power (Ll-RSRP) for the predicted network narrow beam, and wherein the AI / ML model generates the predicted Ll-RSRP for the predicted network narrow beam based on the measurements of the transmitted SSBs.

18. A method of a base station, comprising: sending, to a user equipment (UE), a system information message comprising an association identifier (ID) identifying an artificial intelligence (AI) / machine learning (ML) model for identifying a predicted network narrow beam from a set of network narrow beams using measurements of transmitted synchronization signal blocks (SSBs) that are transmitted on a set of network SSB beams;36P69799WO1 4896-5552-6508' 1transmiting the transmitted SSBs on the set of network SSB beams; receiving, from the UE, a random access channel (RACH) transmission on a selected RACH occasion (RO) selected by the UE; sending, to the UE, in response to the RACH transmission, a random access response (RAR) message that schedules a contention resolution message and that indicates that the UE is to identify the predicted network narrow beam to the base station; receiving, from the UE, the contention resolution message as scheduled by the RAR, wherein the contention resolution identifies the predicted network narrow beam; and sending, to the UE, in response to the contention resolution message, a contention resolution response message using the predicted network narrow beam.

19. The method of claim 18, wherein the RACH transmission uses a RACH preamble that indicates, to the base station, that the UE can use the AI / ML model.

20. The method of claim 18, wherein the selected RO uses a time resource that indicates, to the base station, that the UE can use the AI / ML model.21 . The method of claim 18, wherein the selected RO uses a frequency resource that indicates, to the base station, that the UE can use the AI / ML model.

22. The method of claim 18, wherein the system information message further identifies the set of network narrow beams.

23. The method of claim 18, wherein the system information message further comprises a mapping of a set of ROs to the transmitted SSBs.

24. The method of claim 18, wherein the RAR message indicates that the UE is to identify the predicted network narrow beam to the base station using a channel state information (CSI) request field.

25. The method of claim 18, wherein the contention resolution message further comprises a predicted layer 1 reference signal received power (Ll-RSRP) for the predicted network narrow beam.

26. An apparatus comprising means to perform the method of any of claim 1 to claim 25.37P69799WO1 4896-5552-6508' 127. 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 25.

28. An apparatus comprising logic, modules, or circuitry to perform the method of any of claim 1 to claim 25.

29. A baseband processor for a user equipment (UE) that is configured to cause the UE to perform one or more elements of any one of claim 1 to claim 4 and claim 10 to claim 17.

30. A baseband processor for a base station that is configured to cause the base station to perform one or more elements of any one of claim 5 to claim 9 and claim 18 to claim 25.38P69799WO1 4896-5552-6508' 1

Images