Enhancement of transmission configuration indication state switching requirements for beam prediction and measurement

Abstract

Systems, methods, apparatuses, and computer program products for enhancement of transmission configuration indication state switching requirements. One method may include a UE predicting at least one beam associated with a TCI state; transmitting, to a network element, information indicating the at least one predicted beam; receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and determining whether the target TCI state is known based on a condition for the at least one predicted beam.

Description

TITLEENHANCEMENT OF TRANSMISSION CONFIGURATION INDICATION STATE SWITCHING REQUIREMENTS FOR BEAM PREDICTION AND MEASUREMENTTECHNICAL FIELD

[0001] Some example embodiments may generally relate to mobile or wireless telecommunication systems, such as 3rdGeneration Partnership Project (3GPP) Long Term Evolution (LTE), 5thgeneration (5G) radio access technology (RAT), new radio (NR) access technology, 6thgeneration (6G), and / or other communications systems. For example, certain example embodiments may relate to systems and / or methods for enhancement of transmission configuration indication state switching requirements.BACKGROUND

[0002] Examples of mobile or wireless telecommunication systems may include 5G RAT, the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), LTE Evolved UTRAN (E-UTRAN), LTE-Advanced (LTE-A), LTE-A Pro, NR access technology, MulteFire Alliance, and / or 6G and beyond. 5G wireless systems refer to the next generation (NG) of radio systems and network architecture. A 5G system is typically built on a 5G NR, but a 5G (or NG) network may also be built on E-UTRA radio. It is expected that NR can support service categories such as enhanced mobile broadband (eMBB), ultra-reliable low-latency- communication (URLLC), and massive machine-type communication (mMTC). NR is expected to deliver extreme broadband, ultra-robust, low-latency connectivity, and massive networking to support the Internet of Things (loT). The next generation radio access network (NG-RAN) represents the radio access network (RAN) for 5G, which may provide radio access for NR, LTE, and LTE-A. It is noted that the nodes in 5G providing radio access functionality to a user equipment (e.g., similar to the Node B in UTRAN or the Evolved Node B (eNB) in LTE) may be referred to as next-generationNode B (gNB) when built on NR radio, and may be referred to as next-generation eNB (NG-eNB) when built on E-UTRA radio.SUMMARY

[0003] In accordance with some example embodiments, a method may include predicting, by a user equipment, at least one beam associated with a TCI state. The method may further include transmitting, by the user equipment, to a network element, information regarding the at least one predicted beam. The method may further include receiving, by the user equipment, a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The method may further include determining, by the user equipment, whether the target TCI state is known based on a condition for the at least one predicted beam.

[0004] In accordance with certain example embodiments, an apparatus may include means for predicting at least one beam associated with a TCI state. The apparatus may further include means for transmitting, to a network element, information regarding the at least one predicted beam. The apparatus may further include means for receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The apparatus may further include means for determining whether the target TCI state is known based on a condition for the at least one predicted beam.

[0005] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include predicting at least one beam associated with a TCI state. The method may further include transmitting, to a network element, information regarding the at least one predicted beam. The method may further include receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The method may further include determining whether the target TCI state is known based on a condition for the at least one predicted beam.

[0006] In accordance with some example embodiments, a computer program product may perform a method. The method may include predicting at least one beam associated with a TCI state. The method may further include transmitting, to a network element, information regarding the at least one predicted beam. The method may further include receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The method may further include determining whether the target TCI state is known based on a condition for the at least one predicted beam.

[0007] In accordance with certain example embodiments, an apparatus may include 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 predict at least one beam associated with a TCI state. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, to a network element, information regarding the at least one predicted beam. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to determine whether the target TCI state is known based on a condition for the at least one predicted beam.

[0008] In accordance with various example embodiments, an apparatus may include predicting circuitry configured to predict at least one beam associated with a TCI state. The apparatus may further include transmitting circuitry configured to transmit, to a network element, information regarding the at least one predicted beam. The apparatus may further include receiving circuitry configured to receive a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams. The apparatus may further include determining circuitry configured to determine whether the target TCI state is known based on a condition for the at least one predicted beam.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] For a proper understanding of example embodiments, reference should be made to the accompanying drawings, wherein:

[0010] FIG. 1 illustrates an example of a signaling diagram according to certain example embodiments;

[0011] FIG. 2 illustrates an example of a flow diagram of a method according to various example embodiments;

[0012] FIG. 3 illustrates an example of various network devices according to some example embodiments; and

[0013] FIG. 4 illustrates an example of a 5G network and system architecture according to certain example embodiments.DETAILED DESCRIPTION

[0014] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for periodicities of beam predictions is not intended to limit the scope of certain example embodiments, but is instead representative of selected example embodiments.

[0015] Artificial intelligence (AI) / machine learning (ML) based beam management is an aspect of 3GPP Release (Rel)-19, including spatial domain beam prediction (z.e., beam management (BM)-Casel) and time domain beam prediction (z.e., BM-Case2). Spatial beam prediction (BM-Casel) may predict the best transmission (Tx) / receiver (Rx) beams in different spatial locations.

[0016] 3GPP includes AI / ML for NR air interfaces based on the AI / ML techniques to NR air interface. In an AI / ML general framework, signalling and protocol aspects of life cycle management (LCM), enabling functionality and model selection (if justified), activation, deactivation, switching, fallback, and identification related signalling, have been studied. Necessary signalling / mechanism(s) for LCM tofacilitate model training, inference, performance monitoring, data collection for both UE-sided and network (NW)-sided models, as well as signalling mechanisms of applicable functionalities / models, are needed.

[0017] 3GPP is also developing beam management, particularly downlink (DL) Tx beam predictions for both UE-sided and NW-sided models, encompassing spatial- domain DL Tx beam prediction for a Set A of beams based on measurement results of a Set B of beams (“BM-Casel”); temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams (“BM-Case2”); specifying necessary signalling / mechanism(s) to facilitate LCM operations specific to the beam management use cases, if any; and enabling methods to ensure consistency between training and inference regarding NW-side additional conditions for inferences at the UE (if identified). Based upon this, it would be beneficial to develop a common framework design to support both BM-Casel and BM-Case2.

[0018] Various terminologies used for AI / ML may include:

[0019] AI / ML Model: A data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.

[0020] AI / ML model delivery: A generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. An entity could mean a network node / function (e.g., gNB, LME, etc.), UE, proprietary server, etc.

[0021] AI / ML model inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0022] AI / ML model testing: A subprocess of training to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Different from AI / ML model validation, testing does not assume subsequent tuning of the model.

[0023] AI / ML model training: A process to train an AI / ML model by learning the input / output relationship in a data driven manner, and obtain the trained AI / ML model for inference.

[0024] AI / ML model transfer: Delivery of an AI / ML model over the air interface in a manner that is not transparent to 3GPP signalling, either parameters of a modelstructure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model.

[0025] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0026] Data collection: A process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference.

[0027] Federated learning / f ederated training: An ML technique that trains an AI / ML model across multiple decentralized edge nodes (e.g., UEs, gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.

[0028] Functionality identification: A process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Information regarding the AI / ML functionality may be shared during functionality identification where AI / ML functionality resides depends on the specific use cases and sub use cases.

[0029] Model activation: may enable an AI / ML model for a specific function.

[0030] Model deactivation: may disable an AI / ML model for a specific function.

[0031] Model download: model transfer from the network to a UE.

[0032] Model identification: A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. The process / method of model identification may or may not be applicable. Information regarding the AI / ML model may be shared during model identification.

[0033] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.

[0034] Model parameter update: Process of updating the model parameters of a model.

[0035] Model selection: The process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Model selection may or may not be carried out simultaneously with model activation.

[0036] Model switching: Deactivating a currently active AI / ML model, and activating a different AI / ML model for a specific function.

[0037] Model update: Process of updating the model parameters and / or model structure of a model.

[0038] Model upload: Model transfer from UE to the network.

[0039] Network-side AI / ML model: An AI / ML model whose inference is performed entirely at the network.

[0040] Offline field data: The data collected from field and used for offline training of the AI / ML model.

[0041] Offline training: An AI / ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions.

[0042] Online field data: The data collected from field and used for online training of the AI / ML model.

[0043] Online training: An AI / ML training process where the model being used for inference may be continuously trained in or near real-time with the arrival of new training samples. Near real-time vs. non real-time may be context-dependent, and may be relative to the inference time-scale. There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Fine-tuning / re-training may be done via online or offline training.

[0044] Reinforcement learning (RL): A process of training an AI / ML model from input (e.g., state) and a feedback signal (e.g., reward) resulting from the model’s output e.g., action) in an environment the model is interacting with.

[0045] Semi-supervised learning: A process of training a model with a mix of labelled data and unlabelled data.

[0046] Supervised learning: A process of training a model from input and its corresponding labels.

[0047] Two-sided (AI / ML) model: A paired AI / ML model over which joint inference is performed, wherein joint inference comprises AI / ML inference whose inference is performed jointly across the UE and the network. For example, the first part of inference may be performed by the UE first, and then performed by a base station, or vice versa.

[0048] UE-side (AI / ML) model: An AI / ML model whose inference is performed entirely at the UE.

[0049] Unsupervised learning: A process of training a model without labelled data.

[0050] Proprietary-format models: ML models of vendor- / device- specific proprietary format from the perspective of 3 GPP. They are not mutually recognizable across vendors and hide model design information from other vendors when shared. An example is a device- specific binary executable format.

[0051] Open-format models: ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors, and do not hide model design information from other vendors when shared.

[0052] In order to facilitate the AI / ML model inference, 3 GPP is studying enhanced or new configurations / UE reporting / UE measurement (e.g., enhanced or new beam measurement and / or beam reporting); enhanced or new signaling for measurement configuration / triggering; and signaling of assistance information (if applicable). For NW-sided models and UE-sided models, beam indication may be based on a unified Transmission Configuration Indication (TCI) state framework.

[0053] In current 5G systems, networks may use beam measurements e.g., layer 1 (LI) -reference signal received power (RSRP) measurements and reporting) to make the decisions about serving TCI state / beam switching and / or addition of the TCI states / beams into the active TCI state list. The latency of these operations on the UEside depends on the knowledge of the target / added TCI state(s) by the UE. Therefore, 3 GPP defines the conditions of the known TCI state. In particular, when the TCI state is known, the UE may be aware of corresponding beam / RSs it has measured recently, and may switch to it faster than to an unknown TCI state. Throughout this disclosure, the terms “beam” and “TCI state” are interchangeable unless otherwise specified.

[0054] In 3GPP Rel-19 AI / ML BM, the measurements of the Set B of beams are used as input to the ML model, that outputs the best N beams (z.e., beam indices and / or Ll-RSRP values) from a different or overlapping Set A of beams. For a UE-sided model, Set A and B can be provided with the CSI reporting configurations. A monitoring mechanism may verify that a prediction of beams from Set A are close to the actual measurements. Set A and Set B may overlap (z.e., a predicted beam may also be measured).

[0055] Based on the UE report for predicted and / or measured beams, the network may determine whether any changes are required in the serving or in the set of active TCI states. The network may adjust the set of active TCI states based on the predicted TCI states (e.g., to add the best predicted beams into the active TCI state list). It may be is beneficial to switch / add known TCI states to shorten the latencies.

[0056] To use a known TCI state, the network needs to confirm that the reference signal (RS) resource corresponding to the activated / indicated beams can be measured by the UE prior any beam indication occurring. As long as that is guaranteed by the network, it may not matter whether an indicated / activated TCI state is corresponding to predicted or measured RS resources. However, too frequent measurements and transmission of Set A / subset of Set A beams may be unfavorable due to a need to reduce the overhead and latency.

[0057] There can be several disadvantages in introducing reporting of predicted beams instead of directly measured beams. For example, there is no current definition of whether a prediction of the beam (or measurement prediction for the RSs corresponding to the TCI state) may be interpreted in the same way from the TCI knowledge point of view or not. It may also be beneficial to modify the definition of the known TCI state to account for AI / ML-based predicted beams, as well as toconfigure monitoring actions / measurements in an optimal way while minimizing the beam change and / or active TCI state list updates.

[0058] Certain example embodiments described herein may have various technical effects to overcome the disadvantages described above. For example, certain example embodiments may modify the definition of a known TCI state account for AI / ML- based predicted beams, and may configure monitoring actions / measurements in an optimal way while minimizing the length of the beam change and / or active TCI state list updates. Thus, certain example embodiments discussed below are directed to improvements in computer-related technology.

[0059] Certain example embodiments described herein relate to enhancements related to AI / ML for beam management, including enhancement of transmission configuration indication state switching requirements for activated / indicated known TCI states for AI / ML beam predictions and measurements.

[0060] In particular, the UE may be configured to report predicted beams to the NW, and the NW may indicate / activate a TCI state corresponding to a predicted beam. The UE may be defined with one or more criteria to determine whether the indicated / activated TCI state is known or unknown.

[0061] For example, in various example embodiments, a first condition (Condition 1) may include an additional requirement defined to relax the timeline on “TCI state switch command is received within 1280 ms upon the last transmission of the RS resource for beam reporting or measurement,” where the predicated beam corresponding to a Set A / subset of set A may be measured with a periodicity longer than the 1280 ms. The predicted beam(s) in Set A, but outside Set B, may not have been measured, and may become unknown TCI states. The predicted beam may be measured at some point (e.g., with time longer than 1280 ms).

[0062] In some example embodiments, a TCI state switch command may be received within D ms upon the last transmission of the RS resource for beam reporting or measurement. In various example embodiments, the new periodicity / delay requirements may be increased. For example, D may be a multiple of 1280, i.e., L times current TCI switch command e.g., 10 times 1280 ms), in order to avoid thenetwork updating activated / indicated TCI states too frequently. Additionally, the UE may transmit at least one measured or predicted Ll-RSRP report for the target TCI state before the TCI state switch command.

[0063] Additionally or alternatively, a second condition (Condition 2) may include defining a requirement relating to the beam prediction outcome at the UE. For example, if the RS resource of a TCI state is corresponding to a predicted beam among reported Top-K beams in last X ms duration (e.g., 100 ms), such TCI state may meet known TCI state criterion. Thus, a TCI state corresponding to a RS resource indicator in latest predicted beam reports may be considered as a known TCI state.

[0064] In certain example embodiments, the downlink TCI state may be known if certain conditions are met. For example, during the period from the last transmission of the RS resource used for the Ll-RSRP measurement reporting for the target downlink TCI state to the completion of active downlink TCI state switch, where the RS resource for Ll-RSRP measurement may be the RS in target downlink TCI state or quasi co-located (QCLed) to the target downlink TCI state, a downlink TCI state switch command (z.e., gNB commanding the UE to switch) may be received within 1280 ms upon the last transmission of the RS resource for beam reporting or measurement. For a UE that supports beam prediction, for condition 1 , a TCI state switch command indicating a predicted beam may be received within D ms upon the last transmission of the corresponding RS resource for beam reporting or measurement, where D > 1280. This means that the last measurement or beam reporting of the RS resource corresponding to the TCI state corresponding to a predicted beam may happen in a period longer than 1280 ms e.g., L*1280 ms) prior receiving the downlink TCI state switch command.

[0065] For condition 2, the RS resource e.g., SSB or CSI-RS) associated with the target downlink TCI state corresponding to a predicted beam should be among the reported Top-K beams in the last X ms duration (e.g., 100 ms). The UE may have sent at least 1 measured or predicted Ll-RSRP report for target downlink TCI state before downlink TCI state switch command. The target downlink TCI state may remain detectable during the downlink TCI state switching period. The SSBassociated with the downlink TCI state may remain detectable during the downlink TCI switching period (e.g., SNR of the downlink TCI state > -3dB). The SSB may be associated with either the serving cell PCI or a PCI different from serving cell PCI. Otherwise, the downlink TCI state may be unknown.

[0066] New TCI requirements may enable Set A / subset of set A to be measured, and / or UE-sided inferences with TCI states indication corresponding to new TCI states requirements. Condition 1 and condition 2 may be used in combination for the predicted beams to correspond to known TCI states. For condition 1, if predicted beams are not in a set of measured beams (z.e., Set B), after a period of time e.g., longer than 1280ms), the predicted beams may not fulfill the condition of known TCI states. In certain example embodiments, after the UE receives the downlink TCI state switch command, the UE may check whether the activated / indicated beam is a predicted beam or a directly measured beam. If it is a predicted beam, the UE may use the condition 1 and / or condition 2 to determine whether the corresponding TCI state is known; otherwise, the UE may use the condition in legacy.

[0067] The time period for enabling at least subset of Set A to be measured may be expanded for TCI state in AI / ML BM. For BM-Case 1 (z.e., spatial domain beam prediction) and BM-Case 2 (i.e., temporal domain beam prediction), the predicted CRI (Peri) in SetA / subset of Set A may be measured with a time longer than 1280 ms, for example, L*1280 ms, where L is an integer larger than 1. For example, L may be 10 when the UE performs predictions. The TCI state switch command may be received within L*1280 ms upon the last transmission of the RS resource for subset of Set A beams reporting. The UE may transmit at least 1 measured or predicted Ll- RSRP report for the target TCI state before the TCI state switch command. The TCI state may remain detectable during the TCI state switching period. The synchronization signal block (SSB) / CSI-RS associated with the TCI state may also remain detectable during the TCI switching period e.g., signal-to-noise ratio (SNR) of TCI state > -3 dB).

[0068] Beam prediction may be less effective if the network is delayed when switching from unknown to known TCI state. To avoid the network experiencingsignificant delays, condition 2 may require that the predicted beams (e.g., when UE predicts Top-2 beams) should be within reported Top-K beams to be known. If the predicted beam is not in Top-K beams, then it may be considered an unknown TCI state.

[0069] With condition 2, for BM-Casel / 2, when the UE reports the Top-N beams (Peri) or predicted Ll-RSRP corresponding to Peri to the network, the network may update the active TCI states, and indicate the beam(s) corresponding to the predicted Top-N beam(s) that is within the reported Top-K beams. N may be less than or equal to K. The activated / indicated beam may be among the reported Top-K beams during the last X ms duration e.g., 100 ms).

[0070] For a target TCI state to be known, a corresponding TCI state switch command may be received within or longer than 1280 ms, where the target TCI state may be within predicted Top-N and within reported Top-K beams e.g., N < K) in last X ms (e.g., 100 ms) duration. The UE may send at least 1 measured or predicted Ll-RSRP report of Top-N Prci for the target TCI state before the TCI state switch command. The TCI state may remain detectable during the TCI state switching period. The SSB / CSI-RS associated with the TCI state may remain detectable during the TCI switching period (e.g., SNR of TCI state > -3 dB).

[0071] FIG. 1 illustrates an example of a signaling diagram 100 depicting periodicities for AI / ML beam predictions. NE 130 and UE 120 may be similar to NE 310 and UE 320, as illustrated in FIG. 3, according to certain example embodiments.

[0072] At operation 101, NE 130 may transmit to UE 120 an RRC configuration to configure UE 120 to perform AI / ML beam predictions. This may include a configuration of TCI states PDCCH / PDSCH-config, tci-StatesToAddModList) and measurement configuration (e.g., nzp-CSI-RS-ResourceAddModList).

[0073] At operation 102, UE 120 may be in a CONNECTED state with NE 130.

[0074] At operation 103, NE 130 may transmit to UE 120 a PDCCH / PDSCH TCI state indication for beam measurements (e.g., SSB and CSI-RS beams).

[0075] At operation 104, UE 120 may perform inferences for AI / ML BM Casel / 2.

[0076] At operation 105, UE 120 may report to NE 130 at least one of (i) Peri and cri (predicted Top-N beams and measured Top-K beams) or (ii) predicted Ll-RSRP corresponding predicted cri and RSRP of measured Top-K beams.

[0077] Operations 106-107 may relate to condition 2 described above. For example, at operation 106, NE 130 may transmit a TCI state activation to UE 120. At operation107, UE 120 may determine, for the target TCI state indicated in the TCI state activation, RSs corresponding to known TCI states that should be among Peri (predicted Top-N beams and reported Top-K beams, N <K ) in the last x ms.

[0078] Operations 108-110 may relate to condition 1 described above. At operation108, UE 120 may determine a time period between last transmission of the RS resource for beam reporting or measurement and TCI state switch command to be longer thanl280 ms. At operation 109, NE 130 may transmit to UE 120 a TCI state activation. At operation 110, UE 110 may determine whether the target TCI state indicated in the TCI state activation is known based on a condition for the at least one predicted beam.

[0079] FIG. 2 illustrates an example of a flow diagram of a method 200 that may be performed by a UE, such as UE 320 illustrated in FIG. 3, according to various example embodiments.

[0080] At step 201, the method may include predicting at least one beam associated with a TCI state.

[0081] At step 202, the method may further include transmitting, to a network element, such as NE 310 illustrated in FIG. 3, information regarding the at least one predicted beam. For example, the information regarding the at least one predicted beam may be at least one of a CSI-RS resource indicator or RSRP.

[0082] At step 203, the method may further include receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams.

[0083] At step 204, the method may further include determining whether the target TCI state is known based on a condition for the at least one predicted beam. For example, the condition may be satisfied when the TCI state switch command isreceived within a first time period larger than a predetermined period of time upon the last transmission of a RS resource for beam reporting or measurement for the target TCI state, where the predetermined period of time may be 1280 ms. As another example, the condition may be satisfied if the target TCI state corresponds to a predicted beam that is among top K beams reported to the network element within a second time period, where the second time period may be smaller than 1280 ms.

[0084] In certain example embodiments, the method may further include measuring a plurality of beams; determining top K beams from the plurality of measured beams; and reporting information regarding the top K beams to the network element.

[0085] In some example embodiments, the method may further include receiving a configuration for configuring the user equipment to perform beam prediction based on an AI / ML model.

[0086] FIG. 3 illustrates an example of a system according to certain example embodiments. In one example embodiment, a system may include multiple devices, such as, for example, NE 310 and / or UE 320.

[0087] NE 310 may be one or more of a base station (e.g., 3G UMTS NodeB, 4G LTE Evolved NodeB, or 5G NR Next Generation NodeB), a serving gateway, a server, and / or any other access node or combination thereof.

[0088] NE 310 may further include at least one gNB -centralized unit (CU), which may be associated with at least one gNB -distributed unit (DU). The at least one gNB-CU and the at least one gNB -DU may be in communication via at least one Fl interface, at least one Xn-C interface, and / or at least one NG interface via a 5thgeneration core (5GC).

[0089] UE 320 may include one or more of a mobile device, such as a mobile phone, smart phone, personal digital assistant (PDA), tablet, or portable media player, digital camera, pocket video camera, video game console, navigation unit, such as a global positioning system (GPS) device, desktop or laptop computer, single-location device, such as a sensor or smart meter, or any combination thereof. Furthermore, NE 310 and / or UE 320 may be one or more of a citizens broadband radio service device (CBSD).

[0090] NE 310 and / or UE 320 may include at least one processor, respectively indicated as 311 and 321. Processors 311 and 321 may be embodied by any computational or data processing device, such as a central processing unit (CPU), application specific integrated circuit (ASIC), or comparable device. The processors may be implemented as a single controller, or a plurality of controllers or processors.

[0091] At least one memory may be provided in one or more of the devices, as indicated at 312 and 322. The memory may be fixed or removable. The memory may include computer program instructions or computer code contained therein. Memories 312 and 322 may independently be any suitable storage device, such as a non-transitory computer-readable medium. The term “non-transitory,” as used herein, may correspond to a limitation of the medium itself (z.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., random access memory (RAM) vs. read-only memory (ROM)). A hard disk drive (HDD), random access memory (RAM), flash memory, or other suitable memory may be used. The memories may be combined on a single integrated circuit as the processor, or may be separate from the one or more processors. Furthermore, the computer program instructions stored in the memory, and which may be processed by the processors, may be any suitable form of computer program code, for example, a compiled or interpreted computer program written in any suitable programming language.

[0092] Processors 311 and 321 , memories 312 and 322, and any subset thereof, may be configured to provide means corresponding to the various blocks of FIGs. 1-2. Although not shown, the devices may also include positioning hardware, such as GPS or micro electrical mechanical system (MEMS) hardware, which may be used to determine a location of the device. Other sensors are also permitted, and may be configured to determine location, elevation, velocity, orientation, and so forth, such as barometers, compasses, and the like.

[0093] As shown in FIG. 3, transceivers 313 and 323 may be provided, and one or more devices may also include at least one antenna, respectively illustrated as 314 and 324. The device may have many antennas, such as an array of antennas configured for multiple input multiple output (MIMO) communications, or multiple antennas formultiple RATs. Other configurations of these devices, for example, may be provided. Transceivers 313 and 323 may be a transmitter, a receiver, both a transmitter and a receiver, or a unit or device that may be configured both for transmission and reception.

[0094] The memory and the computer program instructions may be configured, with the processor for the particular device, to cause a hardware apparatus, such as UE, to perform any of the processes described above (z.e., FIGs. 1-2). Therefore, in certain example embodiments, a non-transitory computer-readable medium may be encoded with computer instructions that, when executed in hardware, perform a process such as one of the processes described herein. Alternatively, certain example embodiments may be performed entirely in hardware.

[0095] In certain example embodiments, an apparatus may include circuitry configured to perform any of the processes or functions illustrated in FIGs. 1-2. As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry), (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions), and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0096] FIG. 4 illustrates an example of a 5G network and system architecture according to certain example embodiments. Shown are multiple network functions that may be implemented as software operating as part of a network device or dedicated hardware, as a network device itself or dedicated hardware, or as a virtual function operating as a network device or dedicated hardware. The NE and UE illustrated in FIG. 4 may be similar to NE 310 and UE 320, respectively. The user plane function (UPF) may provide services such as intra-RAT and inter-RAT mobility, routing and forwarding of data packets, inspection of packets, user plane quality of service (QoS) processing, buffering of downlink packets, and / or triggering of downlink data notifications. The application function (AF) may primarily interface with the core network to facilitate application usage of traffic routing and interact with the policy framework.

[0097] According to certain example embodiments, processors 311 and 321, and memories 312 and 322, may be included in or may form a part of processing circuitry or control circuitry. In addition, in some example embodiments, transceivers 313 and 323 may be included in or may form a part of transceiving circuitry.

[0098] In some example embodiments, an apparatus (e.g., NE 310 and / or UE 320) may include means for performing a method, a process, or any of the variants discussed herein. Examples of the means may include one or more processors, memory, controllers, transmitters, receivers, and / or computer program code for causing the performance of the operations.

[0099] In various example embodiments, apparatus 320 may be controlled by memory 322 and processor 321 to predict at least one beam associated with a TCI state; transmit, to a network element, information regarding the at least one predicted beam; receive a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and determine whether the target TCI state is known based on a condition for the at least one predicted beam.

[0100] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for predicting at least one beam associated with a TCI state; means for transmitting, to a network element, information regarding the at least one predictedbeam; means for receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and means for determining whether the target TCI state is known based on a condition for the at least one predicted beam.

[0101] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable manner in one or more example embodiments. For example, the usage of the phrases “various embodiments,” “certain embodiments,” “some embodiments,” or other similar language throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an example embodiment may be included in at least one example embodiment. Thus, appearances of the phrases “in various embodiments,” “in certain embodiments,” “in some embodiments,” or other similar language throughout this specification does not necessarily all refer to the same group of example embodiments, and the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments.

[0102] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or,” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0103] Additionally, if desired, the different functions or procedures discussed above may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the described functions or procedures may be optional or may be combined. As such, the description above should be considered as illustrative of the principles and teachings of certain example embodiments, and not in limitation thereof.

[0104] One having ordinary skill in the art will readily understand that the example embodiments discussed above may be practiced with procedures in a different order, and / or with hardware elements in configurations which are different than those which are disclosed. Therefore, although some embodiments have been described based upon these example embodiments, it would be apparent to those of skill in the art that certainmodifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of the example embodiments.

[0105] Partial Glossary

[0106] 3GPP 3rdGeneration Partnership Project

[0107] 5G 5thGeneration

[0108] 5GC 5thGeneration Core

[0109] 6G 6thGeneration

[0110] AF Application Function

[0111] Al Artificial Intelligence

[0112] ASIC Application Specific Integrated Circuit

[0113] BM Beam Management

[0114] BS Base Station

[0115] CBSD Citizens Broadband Radio Service Device

[0116] CN Core Network

[0117] CPU Central Processing Unit

[0118] CU Centralized Unit

[0119] DL Downlink

[0120] DU Distributed Unit

[0121] eMBB Enhanced Mobile Broadband

[0122] eNB Evolved Node B

[0123] gNB Next Generation Node B

[0124] GPS Global Positioning System

[0125] HDD Hard Disk Drive

[0126] loT Internet of Things

[0127] LI Layer 1

[0128] L2 Layer 2

[0129] LCM Life Cycle Management

[0130] LTE Long-Term Evolution

[0131] LTE-A Long-Term Evolution Advanced

[0132] MEMS Micro Electrical Mechanical System

[0133] ML Machine Learning

[0134] MIMO Multiple Input Multiple Output

[0135] mMTC Massive Machine Type Communication

[0136] NE Network Entity

[0137] NG Next Generation

[0138] NG-eNB Next Generation Evolved Node B

[0139] NG- RAN Next Generation Radio Access Network

[0140] NR New Radio

[0141] NW Network

[0142] GAM Operations, Administration and Maintenance

[0143] PDA Personal Digital Assistance

[0144] PDCCH Physical Downlink Control Channel

[0145] PDSCH Physical Downlink Shared Channel

[0146] QoS Quality of Service

[0147] RAM Random Access Memory

[0148] RAN Radio Access Network

[0149] RAT Radio Access Technology

[0150] RF Radio Frequency

[0151] RL Refinement Learning

[0152] ROM Read-Only Memory

[0153] RRC Radio Resource Control

[0154] RSRP Reference Signal Received Power

[0155] Rx Receiver

[0156] SNR Signal-to-Noise Ratio

[0157] SSB Synchronization Signal Block

[0158] TCI Transmission Configuration Indication

[0159] Tx Transmission

[0160] UE User Equipment

[0161] UL Uplink

[0162] UMTS Universal Mobile Telecommunications System

[0163] UPF User Plane Function

[0164] URLLC Ultra-Reliable and Low-Latency Communication

[0165] UTRAN Universal Mobile Telecommunications System TerrestrialRadio Access Network

[0166] WLAN Wireless Local Area Network

Claims

WE CLAIM:

1. A method, comprising: predicting, by a user equipment, at least one beam associated with a transmission configuration indication (TCI) state; transmitting, by the user equipment, to a network element, information regarding the at least one predicted beam; receiving, by the user equipment, a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and determining, by the user equipment, whether the target TCI state is known based on a condition for the at least one predicted beam.

2. The method of claim 1 , wherein the information regarding the at least one predicted beam is at least one of a channel state information reference signal resource indicator or reference signal received power.

3. The method of claim 1 or 2, further comprising: measuring, by the user equipment, a plurality of beams; determining, by the user equipment, top K beams from the plurality of measured beams; and reporting, by the user equipment, information regarding the top K beams to the network element.

4. The method of any of claims 1 to 3, wherein the condition is satisfied when the TCI state switch command is received within a first time period larger than a predetermined period of time upon the last transmission of a reference signal resource for beam reporting or measurement for the target TCI state.

5. The method of claim 4, wherein the predetermined period of time is 1280 milliseconds.

6. The method of any of claims 1 to 5, wherein the condition is satisfied if the target TCI state corresponds to a predicted beam that is among top K beams reported to the network element within a second time period.

7. The method of claim 6, wherein the second time period is smaller than 1280 milliseconds.

8. The method of any of claims 1 to 7, further comprising: receiving, by the user equipment, a configuration for configuring the user equipment to perform beam prediction based on an artificial intelligence / machine learning model.

9. 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: predict at least one beam associated with a transmission configuration indication (TCI) state; transmit, to a network element, information regarding the at least one predicted beam; receive, a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and determine whether the target TCI state is known based on a condition for the at least one predicted beam.

10. The apparatus of claim 9, wherein the information regarding the at least one predicted beam is at least one of channel state information reference signal resource indicator or reference signal received power.

11. The apparatus of claim 9 or 10, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: measure a plurality of beams; determine top K beams from the plurality of measured beams; and report information regarding the top K beams to the network element.

12. The apparatus of any of claims 9 to 11, wherein the condition is satisfied when the TCI state switch command is received within a first time period larger than a predetermined period of time upon the last transmission of a reference signal resource for beam reporting or measurement for the target TCI state.

13. The apparatus of claim 12, wherein the predetermined period of time is 1280 milliseconds.

14. The apparatus of any of claims 9 to 13, wherein the condition is satisfied if the target TCI state corresponds to a predicted beam that is among top K beams reported to the network element within a second time period.

15. The apparatus of claim 14, wherein the second time period is smaller than 1280 milliseconds.

16. The apparatus of any of claims 9 to 15, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive a configuration for configuring the user equipment to perform beam prediction based on an artificial intelligence / machine learning model.

17. An apparatus, comprising: means for predicting at least one beam associated with a transmission configuration indication (TCI) state;means for transmitting, to a network element, information regarding the at least one predicted beam; means for receiving a TCI state switch command indicating a target TCI state corresponding to one of the at least one predicted beams; and means for determining whether the target TCI state is known based on a condition for the at least one predicted beam.

18. The apparatus of claim 17, wherein the information regarding the at least one predicted beam is at least one of channel state information reference signal resource indicator or reference signal received power.

19. The apparatus of claim 17 or 18, further comprising: means for measuring a plurality of beams; means for determining top K beams from the plurality of measured beams; and means for reporting information regarding the top K beams to the network element.

20. The apparatus of any of claims 17 to 19, wherein the condition is satisfied when the TCI state switch command is received within a first time period larger than a predetermined period of time upon the last transmission of a reference signal resource for beam reporting or measurement for the target TCI state.

21. The apparatus of claim 20, wherein the predetermined period of time is 1280 milliseconds.

22. The apparatus of any of claims 17 to 21, wherein the condition is satisfied if the target TCI state corresponds to a predicted beam that is among top K beams reported to the network element within a second time period.

23. The apparatus of claim 22, wherein the second time period is smaller than1280 milliseconds.

24. The apparatus of any of claims 17 to 23, further comprising: means for receiving a configuration for configuring the user equipment to perform beam prediction based on an artificial intelligence / machine learning model.

25. A non-transitory computer readable medium comprising program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method according to any of claims 1-8.

26. A computer program comprising instructions, which, when executed by an apparatus, cause the apparatus to perform the method of any of claims 1-8.

Images