NW-sided model measurement reporting overhead reduction for ai / ML beam management data collection

Abstract

Example embodiments of the present disclosure are directed to reduction of measurement reporting overhead. In some embodiments, a method comprises receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam configured to be used by the network as input to a classifier used for determining a set of at least one predicted beam.

Description

NW-SIDED MODEL MEASUREMENT REPORTING OVERHEAD REDUCTION FOR AI / ML BEAM MANAGEMENT DATA COLLECTIONRELATED APPLICATION

[0001] This application claims the benefit of, and priority from, US provisional Application No.: 63 / 532134 filed on August 11, 2023, which is hereby incorporated by reference in its entirety.TECHNICAL FIELD

[0002] The examples and non-limiting example embodiments relate generally to communications and, more particularly, to NW-sided model measurement reporting overhead reduction for AI / ML BM data collection.BACKGROUND

[0003] It is known to use resources, such as beam resources of a device, for transmission and reception of data in a communication network.SUMMARY

[0004] The following summary is merely intended to be illustrative. The summary is not intended to limit the scope of the claims.

[0005] In accordance with one aspect, an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receive, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determine a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0006] In accordance with one aspect, an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determine a set of atleast one measured beam, based on at least one measurement; and report, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0007] In accordance with one aspect, a method including: transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0008] In accordance with a one aspect, computer program comprising instructions which, when the program is executed by a computer, cause the computer to perform at least one of the above methods.

[0009] In accordance with one aspect, a method including: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0010] In accordance with one aspect, an apparatus including: means for transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and means for determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0011] In accordance with one aspect, an apparatus including: means for receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for determining a set of at least one measured beam, based on at least one measurement; and means for reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at leastone measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0012] a non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0013] In accordance with an aspect, a non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings.

[0015] FIG. 1 shows a gNB configuring a UE to get a measurement report only from a subset of beams while excluding the other beams from the set of measurements.

[0016] FIG. 2 shows a representation of NW training and inference for DL Tx spatial domain beam prediction.

[0017] FIG. 3 shows DL Tx-Rx beam pair prediction using a Tx beam prediction model at the gNB and Rx beam prediction at the UE.

[0018] FIG. 4 shows DL Tx-Rx beam pair prediction using an ML model at the UE.

[0019] FIG. 5 shows a flowchart of the herein described Ll-RSRP measurement filtering procedure.

[0020] FIG. 6 shows an example two-part CSI report for set B beams measurement.

[0021] FIG. 7 is a signaling diagram of the herein described framework for enabling gNB- sided TX or TX-RX beam selection.

[0022] FIG. 8 is a block diagram of one possible and non-limiting system in which the example embodiments may be practiced.

[0023] FIG. 9 is an example apparatus configured to implement the examples described herein.

[0024] FIG. 10 shows a representation of an example of non-volatile memory media used to store instructions that implement the examples described herein.

[0025] FIG. 11 is an example method, based on the examples described herein.

[0026] FIG. 12 is an example method, based on the examples described herein.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0027] Starting from Rel-15, 3GPP has standardized a set of operations for supporting beamforming transmission, including beam sweeping, beam measurements and reporting, beam maintenance and recovery. All these aspects are detailed in the standard under the broad topic of beam management procedures. Beam management has evolved in Rel-16 and successively in Rel-17 to support more advanced configurations such as multi beams reporting to enable multi-TRPs and multi-panel configurations. However, the fundamental problem of the beam management procedures is that with a larger number of beams supported by high-dimensional MIMO arrays, the CSI-RS measurements and feedback overhead radically increase to enable beam selection. In addition, the time required for gNB and UE to complete the beam sweeping and establish the best beam increases accordingly. Thus, limiting the support of low latency communication. This is mainly due to the frequency of SSB / CSLRS transmission during procedures Pl, P2, P3 that are described in 3GPP TR 38.802 and summarized as follows (1-3):

[0028] 1. Pl provides beam sweeping implemented for the gNB to scan the coverage areaperiodically transmitting SSBs with wide angular beams. Conversely, the UE scans different SSBs to identify the best beam and corresponding time / frequency resources on which requesting access.

[0029] 2. During P2, the gNB performs beam refinement transmitting CSI-RSs with narrow beams to identify a more precise direction towards the UE after establishing the wide beam in Pl.

[0030] 3. During P3, beam refinement is implemented at the UE side to scan a set of Rx narrow beams while the gNB transmits CSI-RSs using the best beam identified in P2.

[0031] The procedures Pl, P2 and P3, are executed sequentially to establish the data transmission between gNB and UE, and in case of beam failure and recovery are fully repeated. In addition, P2 and P3 are also periodically repeated for beam maintenance.

[0032] Rel-18 study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface, agreed in RANI . RP-213599 includes a use case for beam management, e.g., beam prediction in time, and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement [RANI].

[0033] The primary motivation for supporting AI / ML-based beam management in the standard is overhead savings and latency reduction. It has been shown that ML algorithms enable predicting the serving beam for different UE locations and time instances, thus avoiding measuring the actual beam quality and saving those resources to be employed for data transmission. On the other hand, beam scanning operations like those performed in Pl, P2 and P3 are time inefficient and not scalable when the size of antenna arrays increases. Therefore, ML algorithms can replace sequential beam scanning by recommending a reduced set of beams likely to contain the best beam index of the full scan.

[0034] 3GPP Rel-18 includes an AI / ML beam management sub-use case BM-Casel: spatial-domain DL beam prediction for Set A of beams based on measurement results of Set B of beams. For this sub use case, options for beam prediction include DL Tx beam prediction and beam pair prediction. 3GPP Rel-18 also specifies a BM-Case2: Temporal DL beam prediction for Set A of beams based on the historic measurement results of Set B of beams.

[0035] The use cases for AI / ML-based beam management indicated in RP-213599 are beamprediction in time and / or spatial domain and beam selection accuracy improvement. Beam prediction in time refers to the broad range of ML approaches that predict the next beam to use. Therefore, these works predict the best beam to use in successive time instances. Differently, spatial domain ML approaches infer the best beam in different spatial locations. Finally, the approaches considering improving beam selection accuracy look more to system performance aspects such as reliability and outage, targeting more specific applications.

[0036] AI / ML spatial domain beam prediction sub-use cases (NW side training and Inference). For BM-Casel, measurement results of Set B of beams may be used to predict the best beam from Set A of beams. This procedure saves resources from both UE and gNB compared to the exhaustively measuring all the beams in Set A.

[0037] Alt.1 : Set B is a subset of Set A.

[0038] Alt.2: Set A and Set B are different (e.g. Set A consists of narrow beams and Set B consists of wide beams).

[0039] Referring to FIG. 1 and FIG. 2, for BM-Casel, a sub-set (271, 272, 273, 274) of narrow beam measurements (110, 270) may be used to predict the best narrow beam at the UE side 10 which leads to avoiding measuring all narrow beams (beams 275, 276, 277, 278, 279 are not measured). For example, in FIG. 2, gNB 70 configures (240) the UE 10 to get the measurement report (250) only from a subset of beams (beams 141, 142, 143, 144 of pattern 140, beams 151, 152, 153, 154, 155, 156, 157, 158 of pattern 150, beam 271, 272, 273, 274 of beam set or pattern 270) while excluding the other beams (unlabeled beams of patterns 140, 150, beams 275, 276, 277, 278, 279 of beam set or pattern 270) from the set of measurements (110).

[0040] For example, if the NN beam prediction model (130) is implemented at the gNB side 70, instead of transmitting a large number of reference signals like SSBs and CSI-RSs, the UE reports (250) only a few beams and ML model 130 at gNB 70 computes the parameters like CRI and RSRP to be used as input data of the ML model. In addition, assistance information (ASSTINFO) 120 from UE lOcan be added to the ML model input if available.

[0041] In this example, the gNB 70 executes the ML model prediction 260 locally and provides a list of CRI associated with K beams. The list contains both measured beams and predicted beams, which are ranked, for instance, in descending order from the most likelybest beam to the less likely best beam. Finally, the list of ranked beams and available RSRP values are added to the beam reporting message sent back to the gNB.

[0042] Thus, FIG. 2 shows a representation of NW training and inference for DL Tx spatial domain beam prediction. Also shown in FIG. 2 is the training 280 of the NW model.

[0043] DL Tx-Rx beam pair in spatial domain beam prediction. Beam pair prediction as one of the alternatives for spatial beam prediction can be operated based on relationship between Set B beams (set of measured beams to be used for ML model input) and Set A beams (set of beams which are predicted as output of ML model):

[0044] Alt.1 : Set B is a subset of Set A

[0045] Alt.2: Set A and Set B are different (e.g. Set A consists of narrow beams and Set B consists of wide beams).

[0046] FIG. 3 shows DL Tx-Rx beam pair prediction using a Tx beam prediction model at gNB 70 and Rx beam prediction at the UE 10.

[0047] As an example, referring to FIG. 3, if ML model is implemented at gNB and Set B is a subset of Set A, DL beam pair prediction between UE and gNB (known as Tx-Rx beam pair) can be done where subset of SSB / CSLRSs are predicted (310) at gNB 70 and Rx beam selection is followed based on QCL Type D with corresponding SSB resources (320). CSI- RS beam repetition (330) at the gNB 70 might be followed by Rx beam prediction (340) at the UE 10.

[0048] FIG. 4 shows DL Tx-Rx beam pair prediction using an ML model at UE 10.

[0049] As another example, referring to FIG. 4, if ML model is implemented at UE and Set B is a subset of Set A, DL beam pair prediction between UE and gNB (known as Tx-Rx beam pair) can be done where subset of SSB / CSI-RSs are measured via one SSB sweep (410) at UE 10 and Tx-Rx beam selection is performed (410, 420) to achieve the best Rx beam (430) for the beam pair (See FIG. 4).

[0050] 3GPP status. Regarding the potential specification impact on the UE measurement reporting enhancements for NW-side inference with BM-case 1 and BM-case 2, the importance of payload overhead for sharing the Ll-RSRP while running an ML model atnetwork side was proposed may be considered. In particular, there may be potential specification impact for BM-Casel and BM-Case2 with a network-side AI / ML model on the LI reporting enhancement for AI / ML inference. The UE may report the measurement results of more than 4 beams in one reporting instance, and other LI reporting enhancements can be considered. The mechanism related to the reporting and reporting overhead reduction may also be considered.

[0051] Accordingly, two main aspects in NW sided model data collection are mechanisms related to reporting and reduced overhead reporting from UE to NW. These two aspects are related to the examples described herein.

[0052] Ll-RSRP quantization granularity of legacy reporting reduces the Ll-RSRP sharing overhead while not degrading the performance significantly. In particular, at least for BM- Casel for inference of DL Tx beam with Ll-RSRPs of all beams in Set B, existing quantization granularity of Ll-RSRP (i.e., IdB for the best beam, 2dB for the difference to the best beam) causes a minor loss in beam prediction (e.g. less than 5% loss in terms of Top- 1 beam prediction accuracy. These observations indicate that ML models are capable to predicting the optimal communication beam even with limited information. However, to the best of authors knowledge, no prior has investigated the methods on reducing the reported quantized RSRP targeting at new mechanisms for measurement reporting and reducing overhead (on top of quantization) at the same time.

[0053] As Set A and Set B are gNB specific and depend on the gNB codebook, it is reasonable to have the ML model running at the gNB for DL Tx beam prediction or DL Tx- RX beam pair prediction. However, both prediction schemes require measured RSRP at the UE to be shared with the gNB, which may introduce high overhead to the network (proportional to the Set B cardinality). To reduce the overhead, quantizing the measured RSRPs is a known method at the UE as quantization helps to reduce the overhead significantly. However, most of the measured / quantized RSRPs are very low (close to the noise level). Therefore, the main question that the examples described herein address is: How the overhead of sharing the measured / quantized RSRPs with gNB can be reduced? Answering this question facilitates ML-based beam prediction at gNB with larger codebooks (larger Set B and Set A). In addition, potential solutions for feedback overhead reduction may result in reducing the size of data sets in data collection as well.

[0054] The examples described herein are directed to a new signaling format for supporting the methods and solutions to reduce further the reporting overhead of the shared measured / quantized RSRPs from UE to the NW. These enhancements not only facilitate NW sided model prediction performance, but also it provides overhead reduction via reducing the size of datasets in data collection.

[0055] Due to propagation properties in FR2, the channel between the gNB and the UE is sparse including a few strong components. Therefore, a large portion of the RSRP measurements (using the beams in Set B) are significantly lower than the highest measured RSRP beams maybe even maybe close to the noise level. As the beam prediction task is a classification problem, the selected beam from Set A does not depend strongly on the exact values of the RSRP of beams which have received low power.

[0056] Described herein is a procedure to reduce the feedback overhead from UE to NW during data collection via sharing selected and most significant RSRP values applied to both DL Tx beam prediction and DL Tx Rx beam pair. To further reducing the LI -RSRP sharing overhead (in addition to the quantization technique), the examples described herein focus on the UE being configured only to share a few / selected quantized LI -RSRP values instead of sharing all the quantized Ll-RSRP values. The main operations of the examples described herein are as follows.

[0057] UE receives from NW (e.g., via RRC) an MRS configuration of which reduced Set B measurement reporting for NW-sided model data collection is applied. NW can decide based on the selected preprocessing option in the training procedure of the NW sided ML model beam selection which configuration out of existing / applicable MRSs can be configured.

[0058] In an example, UE only reports RSRPs that are above a preconfigured threshold (TH) among the measured RSRPs of the beams in Set B. In this case, the feedback could be variable and depends on the measurements at the UE.

[0059] In another example, UE measures all the beams in Set B and reports only the N-best beams with highest LI -RSRPs. As N determines the number of beams to be reported, the feedback overhead size is fixed and does not depend on the UE measurements.

[0060] In another example, UE calculates the received power from all the measured Set Bbeams, i.e., P_tot. Then, UE only reports the M best beams that cover at least X% of P_tot. Therefore, the feedback overhead varies in this case.

[0061] UE receives a new (and different) UCI payload format configuration consisting of an additional CSI report segment that UE can report measurements corresponding to the configured MRS. Based on the selected MRS by the NW, the signaling overhead bits may change from one UE to another or from one measurement to another by the same UE. The new CSI reporting segment can be semi-statically configured.

[0062] In an example, an asymmetric signaling scheme, where UCI includes two CSI reporting parts can be applied (as dynamic overhead length may cause problems in decoding for the NW), where the feedback includes two parts as follows: a) a Fixed payload size part (which may also be referred to as a first part) which includes the measurement information that is common for all configured MRSs. NW configures this payload for CSI reporting as beam reporting in NR, b) a Dynamic payload size part which (which may also be referred to as a second part) includes the reporting beams with most significant Ll-RSRP. The size of second part of the payload can be decoded based on some info provided in the first part of the pay load (with fixed size) can be dependent on the following: i. configured MRS by the NW, ii. hyperparameters corresponding the configured MRS, iii. actual measurement of RSRPs at each realization.

[0063] In an alternative embodiment, a bitmap is used to indicate the set of measured beams. In this embodiment, the UE 10 uses a bit sequence with length of the size of Set B to indicate which beams are reported. For example, if Set B has 4 beams, the UE can share 4 bits for indication: 0110 means only beam #2 and beam #3 are reported, and beam #1 and beam #4 are not reported. Then, the UE 10 shares the quantized version of the corresponding Ll- RSRP of the indicated beams. The reporting of the bitmap may be used as an alternative to reporting the index and RSRP in the two-part CSI report.

[0064] UE receives from NW (e.g., via RRC) configurations of, MRS scheme and its parameters, “R”: The number of bits that UE can use to indicate how many beams are reported in each beam report.

[0065] UE measures the beams in Set B and determines the strongest beam for reporting in the fixed payload and K-l beams for reporting in dynamic payload of the CSI report based on the configured MRS from NW (e.g., via RRC).

[0066] UE reports the measured strongest beams in the fixed payload and dynamic payload of the CSI report (K-1 beams in the dynamic payload can be reported based on the determined method).

[0067] FIG. 5 shows a method to implement the herein described NW sided reduced Ll- RSRP measurement filtering procedure and reporting reduction. At 501, the gNB 70 decides on the measurement reporting scheme (MRS) and hyperparameters. At 502, the gNB 70 shares the determined MRS and hyperparameters with the UE 10. At 503, the gNB 70 transmits reference signals over the beams in gNB-Set B. At 504, the UE 10 measures the DL Tx beams in gNB-Set B or DL Tx-Rx beam pairs in gNB-UE-Set B. AT 505-1, the UE 10 filters the measured Ll-RSRP based on the received MRS. At 505-2, the UE 10 may quantize the filtered Ll-RSRP. At 506, the UE 10 shares only the filtered Ll-RSRP measurements. At 507, the gNB 70 may pre-process the received Ll-RSRP measurements. At 508, the gNB 70 feeds the pre-processed L1_RSRP measurements to the network-side ML beam prediction model. At 509, the gNB 70 shares the outcomes of beam prediction with UE 10.

[0068] FIG. 6 shows an example two-part CSI report for Set B beams measurement. In particular, FIG. 6 shows an example how the asymmetric beam report can be applied. Based on the configured MRS, the UE only keeps k beams for reporting to the NW. In the “Fixed payload” part 610, UE reports the index 612 and RSRP of the best beam 614 in Set B (the beam with highest RSRP), and additionally indicates the number of k beams to be reported beams (616) in the dynamic payload 620. Thus, all the remained k-1 beam indices (622, 623, 624, ..., 620-k) and corresponding RSRPs (632, 633, 634, ..., 630-k) are reported in the “Dynamic payload” part 620. Note that k is usually significantly smaller than the cardinality of Set B.

[0069] Detailed descrip tion / implementation:

[0070] FIG. 7 illustrates example embodiments by 5 steps. The description of these embodiments including additional embodiments in these 5 steps are as follows.

[0071] Step 1: At 701, NW 70 selects an MRS scheme and corresponding hyperparameters based on the trained model(s) capability and data collection NW decides which MRS scheme to be used with the best Set B estimation e.g., for a UE with supported functionalities. At 702, NW 70 trains an ML model with the possibility of dealing with the missing beam reportsaccording to the selected MRS. In an example, NW configures a selected MRS scheme based on a hardcoded higher-level configuration illustrated in Table 1 as follows:Table 1. an example of MRS configuration using hardcoded higher-level signaling

[0072] Step 2: At 703, NW 70 indicates and UE 10 receives (e.g., via RRC) MRS based CSI reporting configuration generating two-part CSI report and two different payload size indication as response to a trigger event, wherein the new configuration field CSIreportwithMRS- ”true” can be described as : CSI_bitsnumberofbeams - ”R” , indicating the number of bits allocated for the UE to report k. So, the UE reports an integer k using R bits, to inform the NW about how many beams are going to be reported in the beam report. Note: NW may indicate different MRS with respect to supported functionality-based or model ID based LCM indicated by the UE (e.g., NW may configure different MRS scheme for Altl and different MRS with respect to Alt 2 beam prediction introduced in section 3.2.1.2)

[0073] At 704, the gNB 70 enables a two-part beam report, and at 705, the gNB 70 transmits reference signals over the beams in gNB -Set B.

[0074] Step 3: At 706, UE measures Set B beams (either for DL Tx or DL Tx-Rx beam pair).

[0075] At 707, the UE 10 filters the measured RSRP according to the configured MRS and its hyperparameters.

[0076] Step 4: UE reports the most significant RSRP measurements based on the determined MRS scheme in Step 1. At 708, UE 10 may quantize the filtered / indicated Ll- RSRPs. At 709, UE 10 uses two-part CSI beam report considering determined fixed anddynamic payload size to report RSRP measurements to the gNB 70.

[0077] Step 5: At 710 and 711, gNB 70 processes the received RSRPs in Set B and predict the optimal beam in Set A. In particular, at 710, the gNB 70 preprocesses the received beam report, which may include interpolation and padding. At 711, the gNB 70 feeds the pre- processed Ll-RSRP measurements to the network-side ML-based beam prediction model. At 712, the gNB 70 shares the outcomes of beam prediction with the UE 10.

[0078] Thus, FIG. 7 shows a flowchart of the herein described framework for enabling gNB -sided TX or TX-RX beam selection. The UE 10 shares the most useful information with gNB 70, which results in reducing the payload size.

[0079] The examples described herein may be part of Rel-18, captured in TS 38.213, TS 38.321 and TS 38.331. The examples described herein implement signaling (configuring the MRS and its hyperparameters, besides the proposed asymmetric beam report).

[0080] FIG. 8 shows a block diagram of one possible and non-limiting example of a cellular network 1 that is connected to a user equipment (UE) 10. A number of network elements are shown in the cellular network of FIG. 8: a base station 70; and a core network 90.

[0081] In FIG. 8, a user equipment (UE) 10 is in wireless communication via radio link 11 with the base station 70 of the cellular network 1. A UE 10 is a wireless communication device, such as a mobile device, that is configured to access a cellular network. The UE 10 is illustrated with one or more antennas 28. The ellipses 2 indicate there could be multiple UEs 10 in wireless communication via radio links with the base station 70. The UE 10 includes one or more processors 13, one or more memories 15, and other circuitry 16. The other circuitry 16 includes one or more receivers (Rx(s)) 17 and one or more transmitters (Tx(s)) 18. A program 12 is used to cause the UE 10 to perform the operations described herein. For a UE 10, the other circuitry 16 could include circuitry such as for user interface elements (not shown) like a display.

[0082] The base station 70, as a network element of the cellular network 1, provides the UE 10 access to cellular network 1 and to the data network 91 via the core network 90 (e.g., via a user plane function (UPF) of the core network 90). The base station 70 is illustrated as having one or more antennas 58. In general, the base station 70 is referred to as RAN node 70 herein. An example of a RAN node 70 is a gNB. There are, however, many other examplesof RAN nodes including an eNB (LTE base station) or transmission reception point (TRP). The base station 70 includes one or more processors 73, one or more memories 75, and other circuitry 76. The other circuitry 76 includes one or more receivers (Rx(s)) 77 and one or more transmitters (Tx(s)) 78. A program 72 is used to cause the base station 70 to perform the operations described herein.

[0083] It is noted that the base station 70 may instead be implemented via other wireless technologies, such as Wi-Fi (a wireless networking protocol that devices use to communicate without direct cable connections). In the case of Wi-Fi, the link 11 could be characterized as a wireless link.

[0084] Two or more base stations 70 communicate using, e.g., link(s) 79. The link(s) 79 may be wired or wireless or both and may implement, e.g., an Xn interface for fifth generation (5G), an X2 interface for LTE, or other suitable interface for other standards.

[0085] The cellular network 1 may include a core network 90, as a third illustrated element or elements, that may include core network functionality, and which provide connectivity via a link or links 81 with a data network 91, such as a telephone network and / or a data communications network (e.g., the Internet). The core network 90 includes one or more processors 93, one or more memories 95, and other circuitry 96. The other circuitry 96 includes one or more receivers (Rx(s)) 97 and one or more transmitters (Tx(s)) 98. A program 92 is used to cause the core network 90 to perform the operations described herein.

[0086] The core network 90 could be a 5GC (5G core network). The core network 90 can implement or comprise multiple network functions (NF(s)) 99, and the program 92 may comprise one or more of the NFs 99. A 5G core network may use hardware such as memory and processors and a virtualization layer. It could be a single standalone computing system, a distributed computing system, or a cloud computing system. The NFs 99, as network elements, of the core network could be containers or virtual machines running on the hardware of the computing system(s) making up the core network 90.

[0087] Core network functionality for 5G may include access and mobility management functionality that is provided by a network function 99 such as an access and mobility management function (AMF(s)), session management functionality that is provided by a network function such as a session management function (SMF). Core network functionality for access and mobility management in an LTE network may be provided by an MME(Mobility Management Entity) and / or SGW (Serving Gateway) functionality, which routes data to the data network. Many others are possible, as illustrated by the examples in FIG. 8: AMF; SMF; MME; SGW; gateway mobile location center (GMEC); location management functions (LMFs); unified data management (UDM); unified data repository (UDR); network repository function (NRF); and / or evolved serving mobile location center (E-SMLC). These are merely exemplary core network functionality that may be provided by the core network 90, and note that both 5G and LTE core network functionality might be provided by the core network 90. The radio access network (RAN) node 70 is coupled via a backhaul link 31 to the core network 90. The RAN node 70 and the core network 90 may include an NG interface for 5G, or an SI interface for LTE, or other suitable interface for other radio access technologies for communicating via the backhaul link 31.

[0088] In the data network 91, there is a computer-readable medium 94. The computer- readable medium 94 contains instructions that, when downloaded and installed into the memories 15, 75, or 95 of the corresponding UE 10, base station 70, and / or core network element(s) 90, and executed by processor(s) 13, 73, or 93, cause the respective device to perform corresponding actions described herein. The computer-readable medium 94 may be implemented in other forms, such as via a compact disc or memory stick.

[0089] The programs 12, 72, and 92 contain instructions stored by corresponding one or more memories 15, 75, or 95. These instructions, when executed by the corresponding one or more processors 13, 73, or 93, cause the corresponding apparatus 10, 70, or 90, to perform the operations described herein. The computer readable memories 15, 75, or 95 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, firmware, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The computer readable memories 15, 75, and 95 may be means for performing storage functions. The processors 13, 73, and 93, may be of any type suitable to the local technical environment, and may include one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on a multi-core processor architecture, as non-limiting examples. The processors 13, 73, and 93 may be means for causing their respective apparatus to perform functions, such as those described herein.

[0090] The receivers 17, 77, and 97, and the transmitters 18, 78, and 98 may implementwired or wireless interfaces. The receivers and transmitters may be grouped together as transceivers.

[0091] FIG. 9 is an example apparatus 900, which may be implemented in hardware, configured to implement the examples described herein. The apparatus 900 comprises at least one processor 902 (e.g. an FPGA and / or CPU), one or more memories 904 including computer program code 905, the computer program code 905 having instructions to carry out the methods described herein, wherein the at least one memory 904 and the computer program code 905 are configured to, with the at least one processor 902, cause the apparatus 900 to implement circuitry, a process, component, module, or function (implemented with control module 906) to implement the examples described herein, including NW-sided model measurement reporting overhead reduction for AI / ML BM data collection. The memory 904 may be a non-transitory memory, a transitory memory, a volatile memory (e.g. RAM), or a non-volatile memory (e.g. ROM). Configuration / reporting 930 of the control module implements the herein described aspects related to NW-sided model measurement reporting overhead reduction for AI / ML BM data collection.

[0092] The apparatus 900 includes a display and / or RO interface 908, which includes user interface (UI) circuitry and elements, that may be used to display aspects or a status of the methods described herein (e.g., as one of the methods is being performed or at a subsequent time), or to receive input from a user such as with using a keypad, camera, touchscreen, touch area, microphone, biometric recognition, one or more sensors, etc. The apparatus 900 includes one or more communication e.g. network (N / W) interfaces (I / F(s)) 910. The communication I / F(s) 910 may be wired and / or wireless and communicate over the Internet / other network(s) via any communication technique including via one or more links 924. The link(s) 924 may be the link(s) 11 and / or 79 and / or 31 and / or 81 from FIG. 8. The link(s) 11 and / or 79 and / or 31 and / or 81 from FIG. 8 may also be implemented using transceiver(s) 916 and corresponding wireless link(s) 926. The communication I / F(s) 910 may comprise one or more transmitters or one or more receivers.

[0093] The transceiver 916 comprises one or more transmitters 918 and one or more receivers 920. The transceiver 916 and / or communication I / F(s) 910 may comprise standard well-known components such as an amplifier, filter, frequency-converter, (de)modulator, and encoder / decoder circuitries and one or more antennas, such as antennas 914 used for communication over wireless link 926.

[0094] The control module 906 of the apparatus 900 comprises one of or both parts 906-1 and / or 906-2, which may be implemented in a number of ways. The control module 906 may be implemented in hardware as control module 906-1, such as being implemented as part of the one or more processors 902. The control module 906-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the control module 906 may be implemented as control module 906-2, which is implemented as computer program code (having corresponding instructions) 905 and is executed by the one or more processors 902. For instance, the one or more memories 904 store instructions that, when executed by the one or more processors 902, cause the apparatus 900 to perform one or more of the operations as described herein. Furthermore, the one or more processors 902, the one or more memories 904, and example algorithms (e.g., as flowcharts and / or signaling diagrams), encoded as instructions, programs, or code, are means for causing performance of the operations described herein.

[0095] The apparatus 900 to implement the functionality of control 906 may be UE 10, base station 70 (e.g. gNB 70), or core network 90 including any of the network functions 99 such as LMF 99, which network functions 99 may be implemented with a network entity. Thus, processor 902 may correspond to processor(s) 13, processor(s) 73 and / or processor(s) 93, memory 904 may correspond to one or more memories 15, one or more memories 75 and / or one or more memories 95, computer program code 905 may correspond to program 12, program 72, or program 92, communication I / F(s) 910 and / or transceiver 916 may correspond to other circuitry 16, other circuitry 76, or other circuitry 96, and antennas 914 may correspond to antennas 28 or antennas 58.

[0096] Alternatively, apparatus 900 and its elements may not correspond to either of UE 10, base station 70, or core network and their respective elements, as apparatus 900 may be part of a self-organizing / optimizing network (SON) node or other node, such as a node in a cloud.

[0097] The apparatus 900 may also be distributed throughout the network (e.g. 91) including within and between apparatus 900 and any network element (such as core network 90 and / or the base station 70 and / or the UE 10).

[0098] Interface 912 enables data communication and signaling between the various items of apparatus 900, as shown in FIG. 9. For example, the interface 912 may be one or morebuses such as address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. Computer program code (e.g. instructions) 905, including control 906 may comprise object-oriented software configured to pass data or messages between objects within computer program code 905. The apparatus 900 need not comprise each of the features mentioned, or may comprise other features as well. The various components of apparatus 900 may at least partially reside in a common housing 928, or a subset of the various components of apparatus 900 may at least partially be located in different housings, which different housings may include housing 928.

[0099] FIG. 10 shows a schematic representation of non-volatile memory media 1000a (e.g. computer / compact disc (CD) or digital versatile disc (DVD)) and 1000b (e.g. universal serial bus (USB) memory stick) and 1000c (e.g. cloud storage for downloading instructions and / or parameters 1002 or receiving emailed instructions and / or parameters 1002) storing instructions and / or parameters 1002 which when executed by a processor allows the processor to perform one or more of the steps of the methods described herein.

[0100] FIG. 11 is an example method 1100, based on the example embodiments described herein. At 1110, the method includes transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme. At 1120, the method includes receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme. At 1130, the method includes determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment. Method 1100 may be performed by network node 70, a network entity implementing a network function 99 of the core network 90, or apparatus 900.

[0101] FIG. 12 is an example method 1200, based on the example embodiments described herein. At 1210, the method includes receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme. At 1220, the method includes determining a set of at least one measured beam, based on at least one measurement. At 1230, the method includes reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme. At 1240, the method includes wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam. Method 1200may be performed by user equipment 10 or apparatus 900.

[0102] The following examples are provided and described herein.

[0103] Example 1. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receive, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determine a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0104] Example 2. The apparatus of example 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the user equipment, an indication to transmit a beam report comprising the set of at least one measured beam; receive, from the user equipment, the beam report; wherein the beam report comprises a first part and a second part; wherein the first part comprises at least one or more of: an index of a best beam of the set of at least one measured beam having the highest reference signal received power, the reference signal received power of the best beam, and a number of at least one beam reported in the second part; wherein the second part comprises an index and a reference signal received power of at least one other beam of the set of at least one measured beam; and determine the set of at least one predicted beam, using information from the beam report as input to the classifier.

[0105] Example 3. The apparatus of any of examples 1 to 2, wherein the set of at least one measured beam comprises a downlink transmission beam, or a downlink transmissionreception beam pair.

[0106] Example 4. The apparatus of any of examples 1 to 3, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, at least one reference signal received power that is above a threshold; wherein the measurement reporting scheme comprises an indication to the user equipment to report the at least one reference signal received power in response to the at least one reference signal received power being above the threshold; wherein the at least one parameter associated with the measurement reporting scheme comprises the threshold.

[0107] Example 5. The apparatus of example 4, wherein: wherein the at least one reference signal received power received from the user equipment comprises at least one reference signal received power of at least one downlink transmission beam; and the set of at least one measured beam received from the user equipment comprises the at least one downlink transmission beam.

[0108] Example 6. The apparatus of any of examples 1 to 5, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a number of at least one best beam having a highest reference signal received power among beams measured by the user equipment; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one best beam having a highest reference signal received power among beams measured by the user equipment; wherein the at least one parameter associated with the measurement reporting scheme comprises a number of at least one best beam having a highest reference signal received power among beams measured by the user equipment that are to be reported.

[0109] Example 7. The apparatus of example 6, wherein: the at least one best beam comprises at least one downlink transmission-reception beam pair; and the set of at least one measured beam received from the user equipment comprises the at least one downlink transmission-reception beam pair.

[0110] Example 8. The apparatus of any of examples 1 to 7, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the at least one parameter associated with the measurement reporting scheme comprises the given percentage.

[0111] Example 9. The apparatus of example 8, wherein: the at least one beam received from the user equipment comprises at least one downlink transmission beam; and the set of at least one measured beam comprises the at least one downlink transmission beam.

[0112] Example 10. The apparatus of any of examples 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the user equipment, the set of at least one predicted beam.

[0113] Example 11. The apparatus of any of examples 1 to 10, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a set of measured beams for training; train the classifier using the set of measured beams for training, wherein a number of beams in the set of measured beams for training is greater than a number of beams is the set of at least one measured beam used as input to the classifier to determine the set of at least one predicted beam.

[0114] Example 12. The apparatus of any of examples 1 to 11, wherein the classifier comprises a machine learning model.

[0115] Example 13. The apparatus of any of examples 1 to 12, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: preprocess at least one measurement associated with the set of at least one measured beam received from the user equipment; wherein the input to the classifier used to determine the set of at least one predicted beam comprises the preprocessed at least one measurement associated with the set of at least one measured beam received from the user equipment; wherein the preprocessed at least one measurement comprises a padded or interpolated at least one measurementA

[0116] Example 14. The apparatus of any of examples 1 to 13, wherein the set of at least one measured beam used as input to the classifier is a subset of the set of at least one predicted beam.

[0117] Example 15. The apparatus of any of examples 1 to 14, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

[0118] Example 16. The apparatus of any of examples 1 to 15, wherein there are no beams in both the set of at least one measured beam used as input to the classifier and the set of at least one predicted beam.

[0119] Example 17. The apparatus of example 16, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at leastone predicted beam comprises at least one narrow beam.

[0120] Example 18. The apparatus of any of examples 1 to 17, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a bitmap comprising a bit sequence having a length that corresponds to a size of the set of at least one measured beam; wherein the bit sequence indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement; and receive, from the user equipment, a quantized version of a reference signal received power measurement of the at least one beam having a respective reported measurement indicated in the bit sequence.

[0121] Example 19. The apparatus of example 18, wherein the reference signal received power measurement of the at least one beam indicated in the bit sequence as having a respective reported measurement comprises a layer 1 reference signal received power measurement.

[0122] Example 20. The apparatus of any of examples 18 to 19, wherein the measurement reporting scheme transmitted to the user equipment comprises an indication to report the bitmap comprising the bit sequence that indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement.

[0123] Example 21. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determine a set of at least one measured beam, based on at least one measurement; and report, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0124] Example 22. The apparatus of example 21, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the network, an indication to transmit a beam report comprising the set of at least one measured beam; and transmit, to the network, the beam report; wherein the beam report comprises a first part anda second part; wherein the first part comprises at least one or more of: an index of a best beam of the set of at least one measured beam having the highest reference signal received power, the reference signal received power of the best beam, and a number of at least one beam reported in the second part; wherein the second part comprises an index and a reference signal received power of at least one other beam of the set of at least one measured beam.

[0125] Example 23. The apparatus of any of examples 21 to 22, wherein the set of at least one measured beam comprises a downlink transmission beam, or a downlink transmissionreception beam pair.

[0126] Example 24. The apparatus of any of examples 21 to 23, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, at least one reference signal received power that is above a threshold; wherein the measurement reporting scheme comprises an indication to the apparatus to report the at least one reference signal received power in response to the at least one reference signal received power being above the threshold; wherein the at least one parameter associated with the measurement reporting scheme comprises the threshold.

[0127] Example 25. The apparatus of example 24, wherein: the at least one reference signal received power reported to the network comprises at least one reference signal received power of at least one downlink transmission beam; and the set of at least one measured beam reported to the network comprises the at least one downlink transmission beam.

[0128] Example 26. The apparatus of any of examples 21 to 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, a number of at least one best beam having a highest reference signal received power among beams measured by the apparatus; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one best beam having a highest reference signal received power among beams measured by the apparatus; wherein the at least one parameter associated with the measurement reporting scheme comprises a number of at least one best beam having a highest reference signal received power among beams measured by the apparatus that are to be reported.

[0129] Example 27. The apparatus of example 26, wherein: the at least one best beam comprises at least one downlink transmission-reception beam pair; and the set of at least one measured beam reported to the network comprises the at least one downlink transmission-reception beam pair.

[0130] Example 28. The apparatus of any of examples 21 to 27, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, a number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the measurement reporting scheme comprises an indication to the apparatus to report the number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the at least one parameter associated with the measurement reporting scheme comprises the given percentage.

[0131] Example 29. The apparatus of example 28, wherein: the at least one beam reported to the network comprises at least one downlink transmission beam; and the set of at least one measured beam comprises the at least one downlink transmission beam.

[0132] Example 30. The apparatus of any of examples 21 to 29, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the network, the set of at least one predicted beam.

[0133] Example 31. The apparatus of any of examples 21 to 30, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the network, a set of measured beams for training the classifier; wherein a number of beams in the set of measured beams for training is greater than a number of beams is the set of at least one measured beam used as input to the classifier to determine the set of at least one predicted beam.

[0134] Example 32. The apparatus of any of examples 21 to 31, wherein the classifier comprises a machine learning model.

[0135] Example 33. The apparatus of any of examples 21 to 32, wherein the input to the classifier used to determine the set of at least one predicted beam comprises a preprocessed at least one measurement associated with the set of at least one measured beam reported to the network; wherein the preprocessed at least one measurement comprises a padded or interpolated at least one measurement.

[0136] Example 34. The apparatus of any of examples 21 to 33, wherein the set of at least one measured beam used as input to the classifier is a subset of the set of at least one predicted beam.

[0137] Example 35. The apparatus of any of examples 21 to 34, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

[0138] Example 36. The apparatus of any of examples 21 to 35, wherein there are no beams in both the set of at least one measured beam used as input to the classifier and the set of at least one predicted beam.

[0139] Example 37. The apparatus of example 36, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

[0140] Example 38. The apparatus of any of examples 21 to 37, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the network, a bitmap comprising a bit sequence having a length that corresponds to a size of the set of at least one measured beam; wherein the bit sequence indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement; and transmit, to the network, a quantized version of a reference signal received power measurement of the at least one beam having a respective reported measurement indicated in the bit sequence.

[0141] Example 39. The apparatus of example 38, wherein the reference signal received power measurement of the at least one beam indicated in the bit sequence as having a respective reported measurement comprises a layer 1 reference signal received power measurement.

[0142] Example 40. The apparatus of any of examples 38 to 39, wherein the measurement reporting scheme received from the network comprises an indication to report the bitmap comprising the bit sequence that indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement.

[0143] Example 41. A method including: transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0144] Example 42. A method including: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0145] Example 43. An apparatus including: means for transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and means for determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0146] Example 44. An apparatus including: means for receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for determining a set of at least one measured beam, based on at least one measurement; and means for reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0147] Example 45. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based onthe measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

[0148] Example 46. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations including: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

[0149] References to a ‘computer’, ‘processor’, etc. should be understood to encompass not only computers having different architectures such as single / multi-processor architectures and sequential or parallel architectures but also specialized circuits such as field- programmable gate arrays (FPGAs), application specific circuits (ASICs), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

[0150] The memories as described herein may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The memories may comprise a database for storing data.

[0151] As used herein, the term ‘circuitry’ may refer to the following: (a) hardware circuit implementations, such as implementations in analog and / or digital circuitry, and (b) combinations of circuits and software (and / or firmware), such as (as applicable): (i) a combination of processor(s) or (ii) portions of processor(s) / software including digital signal processor(s), software, and memories that work together to cause an apparatus to perform various functions, and (c) circuits, such as a microprocessor(s) or a portion of amicroprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present. As a further example, as used herein, the term ‘circuitry’ would also cover an implementation of merely a processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ would also cover, for example and if applicable to the particular element, a baseband integrated circuit or applications processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, or another network device.

[0152] It should be understood that the foregoing description is only illustrative. Various alternatives and modifications may be devised by those skilled in the art. For example, features recited in the various dependent claims could be combined with each other in any suitable combination(s). In addition, features from different example embodiments described above could be selectively combined into a new example embodiment. Accordingly, this description is intended to embrace all such alternatives, modifications and variances which fall within the scope of the appended claims.

[0153] The following acronyms and abbreviations that may be found in the specification and / or the drawing figures are given as follows (the abbreviations and acronyms may be appended with each other or with other characters using e.g. a dash, hyphen, slash, or number, and may be case insensitive):3GPP third generation partnership project4G fourth generation5G fifth generation5GC 5G core networkAl artificial intelligenceAMF access and mobility management functionASIC application- specific integrated circuitASSTINFO assistance informationBM beam managementBP beam predictionCD compact / computer discCPU central processing unitCRI CSI-RS resource indicatorCSI channel state informationCSI-RS channel state information reference signalDL downlinkDSP digital signal processorDVD digital versatile disc eNB evolved Node B (e.g., an LTE base station)EPC evolved packet coreE-SMLC evolved serving mobile location centerFPGA field-programmable gate arrayFR frequency rangeGMLC gateway mobile location center gNB next generation node B, base station for 5G / NR, i.e., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCID identifier or identityI / F interfaceI / O input / outputLI layer 1LCM life cycle managementLMF location management functionLTE long term evolution (4G)MIMO multiple input multiple outputML machine learningMME mobility management entityMRS measurement reporting schemeNF network functionNG new generationNG-RAN new generation radio access networkNN neural networkNR new radioNRF network repository functionN / W networkNW networkP procedureP_tot all the measured Set B beamsQCE quasi co-locationRAM random access memoryRAN radio access networkRAN 1 radio layer 1Rel releaseROM read-only memoryRP RAN plenaryRRC radio resource controlRSRP reference signal received powerRx receiver or receptionSI interface connecting the eNB to the EPCSGW serving gatewaySMF session management functionSON self-organizing / optimizing networkSSB synchronization signal block, or synchronization signal and physical broadcast channel blockTCI transmission configuration indication or indicatorTH thresholdTR technical reportTRP transmission reception pointTS technical specificationTx transmitter or transmissionUCI uplink control informationUDM unified data managementUDR unified data repositoryUE user equipment (e.g., a wireless, typically mobile device)UI user interfaceUPF user plane functionUSB universal serial busWi-Fi wireless networking protocol that devices use to communicate without direct cable connectionsX2 network interface between RAN nodes and between RAN and the core networkXn network interface between NG-RAN nodes

Claims

CLAIMSWhat is claimed is:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receive, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determine a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

2. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the user equipment, an indication to transmit a beam report comprising the set of at least one measured beam; receive, from the user equipment, the beam report; wherein the beam report comprises a first part and a second part; wherein the first part comprises at least one or more of: an index of a best beam of the set of at least one measured beam having the highest reference signal received power, the reference signal received power of the best beam, and a number of at least one beam reported in the second part; wherein the second part comprises an index and a reference signal received power of at least one other beam of the set of at least one measured beam; anddetermine the set of at least one predicted beam, using information from the beam report as input to the classifier.

3. The apparatus of any of claims 1 to 2, wherein the set of at least one measured beam comprises a downlink transmission beam, or a downlink transmission-reception beam pair.

4. The apparatus of any of claims 1 to 3, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, at least one reference signal received power that is above a threshold; wherein the measurement reporting scheme comprises an indication to the user equipment to report the at least one reference signal received power in response to the at least one reference signal received power being above the threshold; wherein the at least one parameter associated with the measurement reporting scheme comprises the threshold.

5. The apparatus of claim 4, wherein: wherein the at least one reference signal received power received from the user equipment comprises at least one reference signal received power of at least one downlink transmission beam; and the set of at least one measured beam received from the user equipment comprises the at least one downlink transmission beam.

6. The apparatus of any of claims 1 to 5, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a number of at least one best beam having a highest reference signal received power among beams measured by the user equipment; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one best beam having a highest referencesignal received power among beams measured by the user equipment; wherein the at least one parameter associated with the measurement reporting scheme comprises a number of at least one best beam having a highest reference signal received power among beams measured by the user equipment that are to be reported.

7. The apparatus of claim 6, wherein: the at least one best beam comprises at least one downlink transmissionreception beam pair; and the set of at least one measured beam received from the user equipment comprises the at least one downlink transmission-reception beam pair.

8. The apparatus of any of claims 1 to 7, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the at least one parameter associated with the measurement reporting scheme comprises the given percentage.

9. The apparatus of claim 8, wherein: the at least one beam received from the user equipment comprises at least one downlink transmission beam; and the set of at least one measured beam comprises the at least one downlinktransmission beam.

10. The apparatus of any of claims 1 to 9, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the user equipment, the set of at least one predicted beam.

11. The apparatus of any of claims 1 to 10, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a set of measured beams for training; train the classifier using the set of measured beams for training, wherein a number of beams in the set of measured beams for training is greater than a number of beams is the set of at least one measured beam used as input to the classifier to determine the set of at least one predicted beam.

12. The apparatus of any of claims 1 to 11, wherein the classifier comprises a machine learning model.

13. The apparatus of any of claims 1 to 12, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: preprocess at least one measurement associated with the set of at least one measured beam received from the user equipment; wherein the input to the classifier used to determine the set of at least one predicted beam comprises the preprocessed at least one measurement associated with the set of at least one measured beam received from the user equipment; wherein the preprocessed at least one measurement comprises a padded or interpolated at least one measurement.

14. The apparatus of any of claims 1 to 13, wherein the set of at least one measured beam used as input to the classifier is a subset of the set of at least one predicted beam.

15. The apparatus of any of claims 1 to 14, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of atleast one predicted beam comprises at least one narrow beam.

16. The apparatus of any of claims 1 to 15, wherein there are no beams in both the set of at least one measured beam used as input to the classifier and the set of at least one predicted beam.

17. The apparatus of claim 16, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

18. The apparatus of any of claims 1 to 17, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the user equipment, a bitmap comprising a bit sequence having a length that corresponds to a size of the set of at least one measured beam; wherein the bit sequence indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement; and receive, from the user equipment, a quantized version of a reference signal received power measurement of the at least one beam having a respective reported measurement indicated in the bit sequence.

19. The apparatus of claim 18, wherein the reference signal received power measurement of the at least one beam indicated in the bit sequence as having a respective reported measurement comprises a layer 1 reference signal received power measurement.

20. The apparatus of any of claims 18 to 19, wherein the measurement reporting scheme transmitted to the user equipment comprises an indication to report the bitmap comprising the bit sequence that indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement.

21. An apparatus comprising:at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determine a set of at least one measured beam, based on at least one measurement; and report, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

22. The apparatus of claim 21, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the network, an indication to transmit a beam report comprising the set of at least one measured beam; and transmit, to the network, the beam report; wherein the beam report comprises a first part and a second part; wherein the first part comprises at least one or more of: an index of a best beam of the set of at least one measured beam having the highest reference signal received power, the reference signal received power of the best beam, and a number of at least one beam reported in the second part; wherein the second part comprises an index and a reference signal received power of at least one other beam of the set of at least one measured beam.

23. The apparatus of any of claims 21 to 22, wherein the set of at least one measured beam comprises a downlink transmission beam, or a downlink transmission-reception beam pair.

24. The apparatus of any of claims 21 to 23, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, at least one reference signal received power that is above a threshold; wherein the measurement reporting scheme comprises an indication to the apparatus to report the at least one reference signal received power in response to the at least one reference signal received power being above the threshold; wherein the at least one parameter associated with the measurement reporting scheme comprises the threshold.

25. The apparatus of claim 24, wherein: the at least one reference signal received power reported to the network comprises at least one reference signal received power of at least one downlink transmission beam; and the set of at least one measured beam reported to the network comprises the at least one downlink transmission beam.

26. The apparatus of any of claims 21 to 25, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, a number of at least one best beam having a highest reference signal received power among beams measured by the apparatus; wherein the measurement reporting scheme comprises an indication to the user equipment to report the number of at least one best beam having a highest reference signal received power among beams measured by the apparatus; wherein the at least one parameter associated with the measurement reporting scheme comprises a number of at least one best beam having a highest reference signal received power among beams measured by the apparatus that are to be reported.

27. The apparatus of claim 26, wherein:the at least one best beam comprises at least one downlink transmissionreception beam pair; and the set of at least one measured beam reported to the network comprises the at least one downlink transmission-reception beam pair.

28. The apparatus of any of claims 21 to 27, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: report, to the network, a number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the measurement reporting scheme comprises an indication to the apparatus to report the number of at least one beam having a higher reference signal received power than at least one other beam, wherein the number of the at least one beam is a given percentage of a number of at least one beam of the set of at least one measured beam; wherein the at least one parameter associated with the measurement reporting scheme comprises the given percentage.

29. The apparatus of claim 28, wherein: the at least one beam reported to the network comprises at least one downlink transmission beam; and the set of at least one measured beam comprises the at least one downlink transmission beam.

30. The apparatus of any of claims 21 to 29, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from the network, the set of at least one predicted beam.

31. The apparatus of any of claims 21 to 30, wherein the instructions, when executedby the at least one processor, cause the apparatus at least to: transmit, to the network, a set of measured beams for training the classifier; wherein a number of beams in the set of measured beams for training is greater than a number of beams is the set of at least one measured beam used as input to the classifier to determine the set of at least one predicted beam.

32. The apparatus of any of claims 21 to 31, wherein the classifier comprises a machine learning model.

33. The apparatus of any of claims 21 to 32, wherein the input to the classifier used to determine the set of at least one predicted beam comprises a preprocessed at least one measurement associated with the set of at least one measured beam reported to the network; wherein the preprocessed at least one measurement comprises a padded or interpolated at least one measurement.

34. The apparatus of any of claims 21 to 33, wherein the set of at least one measured beam used as input to the classifier is a subset of the set of at least one predicted beam.

35. The apparatus of any of claims 21 to 34, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

36. The apparatus of any of claims 21 to 35, wherein there are no beams in both the set of at least one measured beam used as input to the classifier and the set of at least one predicted beam.

37. The apparatus of claim 36, wherein the set of at least one measured beam used as input to the classifier comprises at least one wide beam, and the set of at least one predicted beam comprises at least one narrow beam.

38. The apparatus of any of claims 21 to 37, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to the network, a bitmap comprising a bit sequence having a length that corresponds to a size of the set of at least one measured beam;wherein the bit sequence indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement; and transmit, to the network, a quantized version of a reference signal received power measurement of the at least one beam having a respective reported measurement indicated in the bit sequence.

39. The apparatus of claim 38, wherein the reference signal received power measurement of the at least one beam indicated in the bit sequence as having a respective reported measurement comprises a layer 1 reference signal received power measurement.

40. The apparatus of any of claims 38 to 39, wherein the measurement reporting scheme received from the network comprises an indication to report the bitmap comprising the bit sequence that indicates which at least one beam of the set of at least one beam has a respective reported measurement, and which at least one beam of the set of at least one beam does not have a respective reported measurement.

41. A method comprising: transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

42. A method comprising: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least onemeasurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

43. An apparatus comprising: means for transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and means for determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

44. An apparatus comprising: means for receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; means for determining a set of at least one measured beam, based on at least one measurement; and means for reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

45. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising:transmitting, to a user equipment, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; receiving, from the user equipment, a set of at least one measured beam, based on the measurement reporting scheme; and determining a set of at least one predicted beam using a classifier, wherein an input to the classifier comprises the set of at least one measured beam received from the user equipment.

46. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, the operations comprising: receiving, from a network, a measurement reporting scheme and at least one parameter associated with the measurement reporting scheme; determining a set of at least one measured beam, based on at least one measurement; and reporting, to the network, the set of at least one measured beam, based on the measurement reporting scheme; wherein the set of at least one measured beam is configured to be used by the network as input to a classifier used to determine a set of at least one predicted beam.

Images