Beam management aspects of lifecycle management

Abstract

A user equipment (UE) includes a transceiver, an antenna coupled with the transceiver, and a processor. In one or more embodiments, the processor is configured to cause the UE to receive an indication of a configuration of a first set of beams used by a network device for reference signal measurements, and measure the reference signals. A set of measurements based on the measurements is provided to a machine learning engine (internal or external to the UE), which provides, in response, a beam estimation / prediction (BEP) model. The UE can then use the BEP model to infer or otherwise determine beam predictions for the first set of beams based on measurements of a second set of beams made under the same indicated configuration of the first set of beams. A report indicating the beam predictions can then be sent to the network.

Description

Cross-reference to related applications

[0001] This Patent Cooperation Treaty patent application claims priority to U.S. Provisional Patent Application No. 63 / 547,310, filed November 3, 2023, entitled “BeamManagement Aspects of Life Cycle Management,” the contents of which are incorporated herein by reference as if fully disclosed herein. Technical Field

[0002] This application relates in general to wireless communication systems, including systems, apparatus, and methods for beam management in lifecycle management. Background Technology

[0003] Wireless mobile communication technologies use various standards and protocols to transmit data between network devices (e.g., base stations, radio heads, etc.) and wireless communication devices. Wireless communication system standards and protocols may include, for example, 3GPP Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and the IEEE 802.11 standard for Wireless Local Area Networks (WLANs) (often referred to as Wi-Fi within industry organizations). ® ).

[0004] As envisioned by 3GPP, different wireless communication system standards and protocols can use various radio access networks (RANs) for communication between RAN network equipment (sometimes collectively referred to as RAN nodes, network nodes, or simply nodes) and wireless communication equipment called UEs (User Equipment). 3GPP RANs can include, for example, Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next Generation Radio Access Network (NG-RAN).

[0005] Each RAN can use one or more Radio Access Technologies (RATs) for communication between network devices and UEs. For example, GERAN implements the GSM and / or EDGE RAT, UTRAN implements the Universal Mobile Telecommunications System (UMTS) RAT or other 3GPP RATs, E-UTRAN implements the LTE RAT (sometimes simply referred to as LTE), and NG-RAN implements the NR RAT (sometimes referred to herein as the 5G RAT, 5G NR RAT, or simply NR). In some deployments, E-UTRAN may also implement the NR RAT. In some deployments, NG-RAN may also implement the LTE RAT.

[0006] The network equipment used in a RAN can correspond to that RAN. An example of E-UTRAN network equipment is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly referred to as Evolved Node B, Enhanced Node B, eNodeB, or eNB). An example of NG-RAN network equipment is a Next Generation Node B (sometimes also called gNodeB or gNB).

[0007] The RAN provides communication services to external entities through its connection with the core network (CN). For example, E-UTRAN can utilize the evolved packet core (EPC), while NG-RAN can utilize the 5G core network (5GC). Attached Figure Description

[0008] To facilitate the identification of any particular element or action in the discussion, one or more of the most significant digits in the figure reference numerals refer to the figure number in which the element was first introduced.

[0009] Figure 1 An example wireless communication system according to the implementation described herein is shown.

[0010] Figure 2 An example signaling diagram is shown based on one or more aspects described herein.

[0011] Figure 3 An example signaling diagram is shown based on one or more aspects described herein.

[0012] Figure 4 An example method of wireless communication based on one or more aspects described herein is shown.

[0013] Figure 5 Another example method of wireless communication based on one or more aspects described herein is shown.

[0014] Figure 6 An example architecture of a wireless communication system according to the implementation scheme described herein is illustrated.

[0015] Figure 7 An example system for performing signaling between a wireless device and a network device according to the implementation described herein is illustrated. Detailed Implementation

[0016] Various implementations are described with reference to user equipment (UE). However, references to UE are provided for illustrative purposes only. The example implementations can be used with any electronic component capable of establishing a connection to a network and configured with hardware, software, and / or firmware for exchanging information and data with the network. Therefore, the UE described herein is used to represent any suitable electronic device.

[0017] Beamforming can be used in wireless communication systems to optimize wireless communication with the UE by focusing the signal at the UE, thereby improving efficiency and reliability. Beamforming performed by network devices can employ multiple antennas and advanced algorithms to create precise, focused communication links. This targeted approach improves signal strength, quality, and data rate, thus supporting multiple-input multiple-output (MIMO) configurations. By adapting the signal direction based on the UE's location and surrounding environment, beamforming overcomes obstacles to achieve faster speeds and lower latency for users in a variety of scenarios and applications. Network devices (e.g., base stations or gNBs) serving UEs in a coverage area can use a set of beams, each beam of which is associated with a specific set of antenna parameters for transmitting and / or receiving using one or more antenna arrays at the network device. Different beams can typically be associated with communication in specific vertical and horizontal directions. For example, a base station can be deployed and configured such that beams are horizontally associated with a certain number of radial degrees (e.g., radial angles of five, ten, or twenty degrees), while one or more beams may exist in the vertical direction and be associated with different vertical angles (e.g., two, three, or four beams in the vertical direction). In some cases, the beam distribution may be uniform (e.g., uniform or equal distribution vertically and / or horizontally). However, in other cases, the beams may be of irregular size and / or distributed in the spatial domain.

[0018] Additionally, network operators perform lifecycle management (LCM) to oversee different phases of network operation, including managing the beams used by the network to communicate with the UEs it serves. LCM for beams can include performance monitoring, data collection, UE-assisted monitoring, and configuration. Various aspects of LCM include planning and design, testing, deployment, installation, configuration, integration, and ongoing operation and maintenance to ensure optimal network performance. In the context of beam management, the communication beams used by network devices can be reconfigured or otherwise modified during operation, and different network devices can communicate using different beam configurations. However, network operators may be motivated or otherwise unwilling to disclose information about the beam configurations used by network devices. For example, network operators may seek to avoid disclosing proprietary or confidential information, such as beam patterns (e.g., how wide or narrow the beam) or different parameters used for beamforming.

[0019] A UE communicating with a network device uses resources to track or otherwise determine the beam configuration of the network device. The network device may utilize a relatively large number of communication beams. Therefore, the UE may expend increased resources and / or power to monitor and measure a large number of beams. To mitigate this resource and / or power consumption, the network may use a set of beams (e.g., set A) for communication and / or control in its operation, but the UE may measure a different set of beams (e.g., set B, which may be a subset of set A). The UE can then derive or otherwise determine parameters for one or more beams in set A based on the measurements of the beams in set B.

[0020] The UE may use or rely on machine learning by referencing various management and control tasks, such as channel state information (CSI), beam management, or positioning. In one or more implementations, the UE uses machine learning to determine parameters for one or more beams in set A based on set B beam measurements. Machine learning may also include artificial intelligence. A processor, system, server, or other device or component, or a group of these, that implements or performs machine learning may be referred to as a machine learning engine.

[0021] A machine learning engine may include and / or generate machine learning models to find patterns or make decisions from previously unseen datasets. In some examples, a machine learning model may refer to a program (algorithm, code, procedure). Additionally or alternatively, a machine learning model may refer to parameters, values, data, or other inputs provided to the machine learning engine (e.g., a program) that define or otherwise control the operation of the machine learning engine. A dataset can be used to train a machine learning model, where the program is optimized to find certain patterns or outputs from the dataset. The output of the training is the machine learning model.

[0022] In some cases, UE characteristics and capabilities may vary, and the UE may be able to handle different management settings. For example, a network entity may provide 32 beams for measurement, while the UE has the capability to measure 8 beams and derive the 32 beams from those measurements. As a second example, the UE may have the capability to measure 16 beams and derive the 32 beams from those 16 measurements. The UE may report that it is able to derive measurements for a subset of beams based on beam measurements for a subset of a set of beams, but different UEs may have different capabilities to actually derive those beams (e.g., different UEs may need to measure different numbers of beams to derive that set of beams). Furthermore, network entities (e.g., base stations) may have different beamforming configurations, capabilities, or both.

[0023] Given the foregoing, a shared understanding between the UE and the network (e.g., a network entity of the network) regarding the beam configuration of the network entity and the UE's capabilities regarding the beam configuration of the machine learning model, for example, enables the UE to use the machine learning model to perform inference of the operational beams of the network entity. As further discussed herein, the machine learning model can be trained using channel information or channel state information (CSI) as training data and can be, include, or be referred to as a beam estimation / prediction (BEP) model. In one or more embodiments, the network (e.g., via a network entity) provides the UE with a configuration indicating the beam configuration of the network entity. In one or more embodiments, to allow the network to avoid publicly reading proprietary information about the beam configuration, the indicated beam configuration can be an index in a set of indexes available for communication. The network can then configure or reconfigure the network entity based on one of the indexed beam configurations, and the UE may have an indication in the future that the beam configuration is the same as or different from the previous beam configuration. The UE can then collect data to train and deploy the BEP model based on the indicated beam configuration of the network entity (e.g., set A beams, and optionally set B beams for some cases). For example, such a BEP model can be used in conjunction with LCM. The UE can collect data for the model and then provide this data to the UE-side server that trained the model. The UE-side server can then provide the model back to the UE. In some cases, the UE hands over to the network entity so that the network entity knows that the UE has a correct (suitable, appropriate) BEP model for the current situation (e.g., for a UE served by a network entity with beam configurations of the network entity). In one or more aspects, consistency between the training phase and the configuration (e.g., inference) phase is beneficial for sets A and B. The UE can then use the BEP model to measure reference signals for beams in set B from the network entity and to infer channel state information for one or more beams in set A. The UE can provide the network with indications of measurements, predictions, orderings, or combinations thereof for one or more beams in set A, for example, in a channel state information report or beam report.

[0024] Figure 1 An example wireless communication system 100 is illustrated according to one or more aspects described herein. In one or more embodiments, the wireless communication system 100 supports one or more aspects of beam management for lifecycle management, as further described herein.

[0025] Wireless communication system 100 includes UE 102, network device 104, and machine learning engine 106. One or more UEs, including UE 102, may be served by network device 104 via communication link 120 (e.g., having a Radio Resource Control (RRC) connection established with the network device). Coverage area 110 (e.g., a cell or serving cell) is the service area of ​​an RF spectrum band utilized by network device 104. In one or more embodiments, communication link 120 may include downlink and / or uplink connections.

[0026] In one or more embodiments, network device 104 utilizes beam steering, which may be, include, or be referred to as electronic beam steering. Additionally, in one or more embodiments, UE 102 utilizes beam steering to receive signals, transmit signals, or both. As used herein, electronic beam steering refers to, but is not limited to, the ability of a device (e.g., network device 104) to perform beamforming, beam shaping, or other multi-antenna or multi-antenna element techniques that control, direct, or otherwise shape electromagnetic energy radiated from network device 104 in different directions and at different amounts or amplitudes. Electronic beam steering also refers to the ability of network device 104 to adjust antennas or antenna elements to increase or decrease the reception of electromagnetic radiation from a particular direction. Such receive beamforming may be referred to as a "receive beam" in contrast to transmit beamforming using a "transmit beam." Network device 104 uses beam steering to transmit signals to a UE (e.g., UE 102) served by network device 104. Such signals may include data signals, control signals, or both. Control signals may include reference signals, synchronization signals, or control channels, or combinations thereof.

[0027] In one or more embodiments, network device 104 utilizes beam steering to transmit reference signals on a set of beams 130. In some embodiments, the reference signals include Channel State Information Reference Signals (CSI-RS) or Synchronization Signal Blocks (SSBs) (e.g., including a Primary Synchronization Signal (PSS), a Secondary Synchronization Signal (SSS), a Physical Broadcast Channel (PBCH) carrying control information, and a Demodulation Reference Signal (DMRS) for the PBCH). As an example configuration, network device 104 may transmit reference signals (e.g., CSI-RS, SSB, or both) spatially distributed across a set of 32 transmit beams in both vertical and horizontal directions. For example, the set of beams 130 may include eight transmit beams 132 at a first vertical beam angle, eight transmit beams 134 at a second vertical beam angle, eight transmit beams 136 at a third vertical beam angle, and eight transmit beams 138 at a fourth vertical beam angle. The beams in the set of beams 130 may also be horizontally extended.

[0028] In an example of wireless communication system 100, the group of beams 130 illustrates an example of set A beams and may also be referred to as operational beams. A subset of the group of beams 130 includes eight beams (beams 140, 141, 142, 143, 144, 145, 146, and 147), which may collectively be an example of set B beams. As illustrated with reference to the group of beams 130, set B is a subset of set A in the illustration. In one or more embodiments, the group of beams 130 may each correspond to a beam transmitted by network device 104 for SSB. In some embodiments, in addition to transmitting on different spatial resources as illustrated with reference to the group of beams 130, each beam in the group of beams 130 may also transmit on a different set of time and frequency resources.

[0029] In one or more embodiments, machine learning engine 106 may be a UE-side server communicating with UE 102. Machine learning engine 106 may implement or otherwise perform one or more machine learning tasks, such as training a BEP model for UE 102 based on a set of measurements performed by UE 102 on reference signals received from network device 104 on one or more beams in the set of beams 130 (e.g., set A beams, set B beams). After training, machine learning engine 106 may then provide the BEP model back to UE 102 via communication link 122, which may be a wired or wireless connection.

[0030] The machine learning engine 106 may be or include one or more computing components, such as a processor and memory. In one or more embodiments, the machine learning engine 106 is a device external to the UE 102 but communicating with the UE 102 (e.g., directly or via a network device such as network device 104, such as a server). In other embodiments, the machine learning engine 106 is a server (e.g., a software-based server) for the machine learning engine, which is internal to the UE 102 or otherwise juxtaposed with the UE 102, such as within the same mobile device, vehicle, etc.

[0031] In some examples, the design for network operator control and / or configuration of network device 104 (e.g., configuration, parameter values, analog beam selection such as SSB or narrow beam resources) is part of the core implementation and is proprietary (e.g., network operator, network entity manufacturer, etc.). Such designs may take into account various network conditions, such as UE mobility (e.g., how frequently the UE's optimal transmit beam changes), UE distribution (e.g., the physical location of the target UE), hierarchical structure between SSB beams and / or narrow beams, etc. Network operators may want to provide high Quality of Service (QoS) for UEs and also want to reduce the power consumption of the network (including network entities). Therefore, network operators may expect to utilize different beam designs at different times. For example, a key performance indicator for the network might be system capacity during peak hours, but at night it might be power consumption. In other examples, additional or different key performance indicators may be required.

[0032] Information regarding the beam configuration of network entities within the network can be shared differently. In one or more embodiments, the network (e.g., via network device 104) can share data about the beam configuration with UE 102 for data collection during training and inference, and training and inference are performed on the UE side (e.g., on the radio connectivity side opposite network device 104, such as at UE 102 and / or machine learning engine 106). Providing beam design information to UE 102 allows the network (e.g., the vendor of network device 104) to benefit from machine learning (e.g., artificial intelligence) without implementing machine learning on the network side, while also making it easier for UE 102 (e.g., the vendor of UE 102's chipset or other components) to implement machine learning. In some embodiments, providing beam design information can effectively offload heavy workloads (e.g., processing time, power consumption) from network device 104 to UE 102. In other embodiments, the performance of a single BEP model across different scenarios and / or configurations may be sufficient (e.g., exceeding a threshold), allowing the network to choose to use a function-based LCM. In one or more implementations, the network operator may not expect (e.g., with UE 102) to share beam design information, and UE 102 and network device 104 may exchange signaling to identify the beam configuration of network device 104 and UE capability information for UE 102, based on signaling mechanisms that may be specific to the network including network device 104.

[0033] In one or more embodiments, the performance of a wireless communication system 100, including a network device 104 serving a UE (including UE 102), is affected by differences (e.g., mismatches) in the design of the set of beams 130 (including set A and / or set B designs). For example, when a mismatch exists in set A of the set of beams 130, machine learning inference performance may be worse than conventional methods (e.g., methods that do not use a BEP model for inference). In some examples, the mismatch in set A could be a simulated beam codebook design mismatch between training and inference. Similarly, when a mismatch exists in set B, BEP model inference performance may be worse than conventional methods, or may be degraded compared to a case without mismatch.

[0034] Figure 2 An example signaling diagram 200 is shown according to one or more aspects described herein. In one or more embodiments, signaling diagram 200 supports one or more aspects of beam management for lifecycle management, as further described herein. In one or more embodiments, one or more features or aspects of signaling diagram 200 may be implemented in or by the wireless communication system 100.

[0035] Network device 104 may send to UE 102 an indication 210 of a configuration 210 for a first set of beams 130 used by the network device to transmit a reference signal 212 for measurement. In one or more embodiments, a second set of beams (e.g., when set B is not a subset of set A) may optionally (e.g., additionally or alternatively) be used for transmitting the reference signal 212. Configuration 210 may be a measurement resource configuration, and the indication provides UE 102 with an indication of the configuration of the first set of beams 130 of network device 104. UE 102 can then use configuration 210 to collect training data. In one or more embodiments, UE 102 measures the reference signal 212 according to the configuration of the first set of beams 130 during a first duration.

[0036] UE 102 can then provide a set of training data 214 to machine learning engine 106. In one or more embodiments, this set of training data 214 is based on measurements of reference signal 212 and is used for both a first set of beams 130 and a second set of beams that are related to the first set of beams (e.g., mapped to, correspond to, or otherwise associated with the first set of beams). As further described herein, the first set of beams may be set A, and the second set of beams may be set B. In some embodiments, the second set of beams is a subset of the first set of beams 130. In other embodiments, the second set of beams is wider than the first set of beams or is otherwise different from the first set of beams. For example, the second set of beams may be one or more SSB beams, while the first set of beams is a beam (e.g., a narrower communication beam, or otherwise different from the first set of beams).

[0037] UE 102 responds by providing the set of training data 214 to obtain BEP model 218 from machine learning engine 106. Machine learning engine 106 performs BEP model training 216 based on the set of training data 214 provided by UE 102, as further described herein. Machine learning engine 106 then provides BEP model 218 to UE 102.

[0038] UE 102 receives another indication of configuration 220 for a first set of beams 130 used by network device 104 to transmit a reference signal for measurement. In one or more embodiments, network device 104 is the same network device from which UE 102 receives configuration 210. For example, UE 102 may still be within the coverage area of ​​network device 104. In some embodiments, network device 104 is a different network device from which UE 102 receives configuration 210. For example, UE 102 may have moved to another coverage area. Configuration 220 may indicate a configuration of the first set of beams 130 compatible with the BEP model. In one or more embodiments, UE 102 measures the reference signal 222 during a second duration and according to configuration 220 (e.g., or configuration 210, for example, where the indicated configuration is the same).

[0039] In one or more embodiments, using a BEP model, UE 102 performs beam determination 224 on one or more beams in the first set of beams 130 (e.g., set of beams A) based at least in part on a reference signal corresponding to the second set of beams (e.g., set B beams) (e.g., mapped to or otherwise associated with the second set of beams). In one or more embodiments, beam determination 224 includes determining a beam (e.g., an optimal beam or a set of optimal beams for UE 102).

[0040] Then, UE 102 sends a report 226 to network device 104 indicating the result of beam determination 224. In one or more embodiments, report 226 is a CSI report. In some embodiments, report 226 is a beam report.

[0041] Figure 3 An example signaling diagram 300 is shown according to one or more aspects described herein. In one or more embodiments, signaling diagram 300 supports one or more aspects of beam management for lifecycle management, as further described herein. In one or more embodiments, signaling diagram 300 may include one or more features or aspects of signaling diagram 200 or examples thereof. In some embodiments, one or more features or aspects of signaling diagram 300 may be implemented in or by the wireless communication system 100.

[0042] In one or more embodiments, different signaling occurs during different sessions, including a first session 332, a second session 334, and a third session 336. In one or more embodiments, the first session 332 and the third session 336 correspond to connected modes (e.g., RRC connected mode), and the second session 334 corresponds to an idle mode (e.g., RRC idle mode). In other embodiments, all signaling in signaling diagram 300 occurs when UE 102 is in connected mode. In still other embodiments, different combinations of connected mode and idle mode signaling are possible, such that the signaling in question can occur in a different one of the first session 332, the second session 334, or the third session 336.

[0043] UE 102 may provide UE capability signaling 308 to network device 104. In one or more embodiments, UE 102 sends UE capability signaling 308, which includes an indication of the UE's ability to collect training data to train a BEP model. In some embodiments, UE 102 sends UE capability signaling 308, which includes an indication of the UE's ability to infer one or more beams from a first set of beams (e.g., set A) from a second set of beams 130 (e.g., set B). In some embodiments, a single indication may indicate support for both training data collection and model inference. UE capability signaling for collecting training data and for model inference may be provided in the same set of signaling or messages, or may be provided in separate signaling or messages.

[0044] In one or more embodiments, UE capability signaling 308 may indicate whether UE 102 can perform model inference (or inference). In some embodiments, UE capability signaling indicates the number or range of beams that UE 102 can perform inference on, for example, the number of beams in set A or set B or both.

[0045] Network device 104 may send to UE 102 an indication of configuration 310 for a first set of beams 130 used by the network device to transmit reference signals for measurement. Configuration 310 may be a measurement resource configuration, and the indication provides UE 102 with an indication of the configuration of the first set of beams 130 of network device 104.

[0046] In one or more embodiments, information for the design of the first set of beams (e.g., set A) can be carried in the measurement resource configuration or measurement resource set configuration. For example, parameters may exist. set_A_config_index For example, the indication of the configuration of the first set of beams is an index within a set of indices. In some embodiments, each index in this set of indices is used for a corresponding configuration among multiple configurations of the first set of beams (e.g., corresponding to, mapped to, or otherwise associated with a corresponding configuration). In some embodiments, the index value can be from 0 to 127. In some embodiments, the indication of the configuration of the first set of beams is in a set of reference signal measurement resources (e.g., a non-zero power channel state information reference signal resource set, such as...). NZP-CSI-RS-ResourceSet This information is received in the configuration of [the system / configuration]. In some implementations, this type of information can be used for data collection used for training, inference, and performance monitoring. In some implementations, such as when set B is a subset of set A, set_A_config_index It can be by set_A_set_B_config_index The replacement, where the latter indicates the index used for configurations of set A and set B. In some implementations, set_A_config_index It can be by set_A_config_index and set_B_config_index Replacement, the latter indicating an index used for the configuration of set A and another index used for the configuration of set B.

[0047] In one or more implementations, information regarding the design of the first set of beams 130 (e.g., set A) can be carried in the reporting configuration. In some examples, the reporting configuration is a channel state information reporting configuration. For example, parameters, as further described herein, set_A_config_index It can exist in the reporting configuration (e.g., channel state information reporting configuration, such as...) CSI-ReportConfig In some implementations, this information can be used for inference and performance monitoring. In some implementations, such as when set B is a subset of set A, set_A_config_index It can be by set_A_ set_B_config_index The replacement, where the latter indicates the index used for configurations of set A and set B. In some implementations, set_A_config_index It can be by set_A_config_index and set_B_config_index Replacement, the latter indicating an index used for the configuration of set A and another index used for the configuration of set B.

[0048] In one or more embodiments, beam information (e.g., analog beam information) for each beam in the first set of beams 130 (e.g., set A) is explicitly provided by the network (e.g., via network device 104). In some embodiments, instructions for configuration (e.g., to ensure consistency between training and inference) are provided, for example. set_A_config_index ) can be a global index (which may also be referred to as a "global variable" or "persistent variable"), making any such indicator with the same value (e.g., set_A_config_index Cross-session references to the same configuration (e.g., set A design). In some implementations, if the indication is not global, as is typical for RRC signaling, then the indication (e.g., set_A_config_ index ) will be "local variables". In some implementations, the configuration signaling, together with the indication for the configuration, includes beam information for each beam in that set of beams corresponding to the indication (e.g., for set_A_beam_information_for_ beam_0 , set_A_beam_information_for_beam_1 , set_A_beam_information_for_beam_2 Information about each of them.

[0049] In one or more embodiments, the configuration of the first set of beams includes one or more of a network vendor identifier and / or a scenario identifier and / or a configuration identifier. In some embodiments, set_A_config_index It can contain any or all of the following as subfields: network provider ID, scenario ID, or configuration ID.

[0050] In one or more embodiments, the second set of beams (e.g., set B) is a subset of the first set of beams 130 (e.g., set A). For example, the first set of beams may be 32 beams, and the second set of beams may be 8 beams. Alternatively, the designation of the second set of beams in the first set of beams 130 may be made in a different manner.

[0051] In one or more embodiments, the indication of the second set of beams for the BEP model is a bitmap or combination index selection from the first set of beams 130. For example, selecting the second set of beams (e.g., set B) from the first set of beams 130 (e.g., set A), beams [0000, 1000, ..., 0001] using a 32-bit bitmap means selecting beams 4, 5, ..., 31 for set B, and the measurement resources for the second set of beams (e.g., set B) are arranged in that order.

[0052] In one or more implementations, selecting beam set B from beam set A allows for beam reordering. In a first example, a second set of beams {4, ..., 31} is used, and the input to the BEP model (e.g., an AI model) is in the order of 4, progressing to 5, and so on down to 31. In a second example, a second set of beams {31, ..., 4} is used, and the first measurement resource is beam 31 from the first set of beams 130 (e.g., set A), such that the input to the BEP model (e.g., an AI model) is in the order of 31, progressing to 30, and so on down to 4.

[0053] UE 102 uses configuration 310 to collect training data 314. In one or more embodiments, UE 102 measures reference signal 312 according to the configuration of a first set of beams 130 during a first duration. In one or more embodiments, the first set of beams 130 is used for the transmission of reference signal 312. In some embodiments, a second set of beams (e.g., when set B is not a subset of set A) may optionally (e.g., additionally or alternatively) be used for the transmission of reference signal 312.

[0054] In one or more embodiments, the set of training data 314 includes CSI. UE 102 may then provide the set of training data 314 to machine learning engine 106, as further described herein. Machine learning engine 106 performs model training 316 based on the set of training data 314 provided by UE 102, as further described herein. UE 102 then obtains a BEP model 318 from machine learning engine 106 in response to providing the set of training data 314.

[0055] In one or more embodiments, UE 102 may provide UE capability signaling 328 to network device 104. UE capability signaling 328 may be similar to UE capability signaling 308 described herein. In some embodiments, UE 102 may provide UE capability signaling 308 during a first session 332 and UE capability signaling 328 during a third session 336.

[0056] UE 102 receives another indication of configuration 320 for a first set of beams 130 used by network device 104 to transmit reference signals for measurement. In some embodiments, the indication of configuration 320 may include aspects of or examples of the indication of configuration 310, as further described herein. In one or more embodiments, the indication of configuration 320 is used by UE 102 in BEP model 318 to perform a measurement of reference signal 322, as further described herein. In one or more embodiments, using BEP model 318, UE 102 performs beam determination 324 on one or more beams in the first set of beams (e.g., set B beams) based at least in part on the measurement of reference signal 322 corresponding to a second set of beams (e.g., set B beams) (e.g., mapped to communication resources associated with the second set of beams). In one or more embodiments, beam determination 324 includes determining CSI, which may include indication of one or more beams determined for beam determination 324.

[0057] Then, UE 102 sends a beam report 326 indicating CSI to network device 104. In one or more embodiments, beam report 326 is a CSI report.

[0058] Figure 4 An example method 400 for wireless communication performed by a UE is illustrated. In one or more embodiments, method 400 supports one or more aspects of beam management in lifecycle management, as further described herein. In some cases, the UE may be UE 102, wireless device 702, or one of the other UEs described herein. Method 400 may be performed using a processor, transceiver (or main radio component), or other components of the UE.

[0059] At 402, method 400 includes receiving an indication of the configuration of a first set of beams used by the network device to transmit reference signals for measurement, and an optional second set of beams (in some cases, e.g., for set B). In one or more embodiments, the indication of the configuration is for the first set of beams. In some embodiments, the indication of the configuration is for both the first set of beams and the second set of beams.

[0060] At 404, method 400 includes measuring a reference signal during a first duration according to a configuration for a first set of beams and, in some cases, an optional second set of beams. In one or more embodiments, method 400 includes measuring the reference signal during the first duration according to a configuration for the first set of beams. In some embodiments, method 400 includes measuring the reference signal during the first duration according to a configuration for both the first set of beams and the second set of beams.

[0061] At 406, method 400 includes obtaining a BEP model to be used to determine the CSI for a second set of beams, the second set of beams having a relationship with the first set of beams, and the BEP model being based at least in part on measurements of a reference signal during a first duration.

[0062] At 408, method 400 includes measuring the reference signal during the second duration and, depending on the configuration.

[0063] At 410, method 400 includes determining beam predictions for one or more beams in the first group of beams based at least in part on measurements of the reference signal during the second duration using a BEP model. In one or more embodiments, beam prediction may be or include beam ranking. Under certain conditions, the UE may perform measurements on one or more predicted or ranked beams in the first group of beams.

[0064] At 412, method 400 includes sending a report (e.g., a CSI report or a beam report) to a network device based at least in part on beam prediction. In one or more embodiments, beam prediction is beam information or includes beam information that may include the ordering of one or more beams in set A, or the predicted strength of one or more beams in set A, or both.

[0065] In one or more embodiments, method 400 further includes providing a set of training data to a machine learning engine, at least in part based on measurements of a reference signal, for both the first and second beam sets. Method 400 may also include obtaining a BEP model from the machine learning engine in response to providing the set of training data.

[0066] In one or more embodiments, method 400 further includes transmitting UE capability signaling that includes a first indication of the UE's ability to collect training data to train a BEP model. In some embodiments, method 400 further includes transmitting UE capability signaling that includes a second indication of the UE's ability to determine (e.g., infer) one or more beams in a first set of beams from a second set of beams using the BEP model. In some embodiments, method 400 further includes transmitting UE capability signaling that includes both the first and second indications. In one or more embodiments, an indication of configuration is received in response to the UE capability signaling.

[0067] In one or more embodiments, the indication of the configuration of the first group of beams is an index in a set of indices, each index in the set of indices corresponding to a corresponding configuration in a plurality of configurations of the first group of beams.

[0068] In one or more embodiments, the indication of the configuration of the first set of beams is received in the configuration of the reference signal measurement resource set. In some embodiments, the configuration of the reference signal measurement resource set includes a non-zero power channel state information reference signal resource set.

[0069] In one or more embodiments, the indication of the configuration of the first set of beams is received in the reporting configuration. In some embodiments, the reporting configuration includes a channel state information reporting configuration.

[0070] In one or more embodiments, the second set of beams is a subset of the first set of beams. In one or more embodiments, the second set of beams has at least one beam that is different from the first set of beams. In some embodiments, each beam in the second set of beams is different from each beam in the first set of beams.

[0071] In one or more embodiments, the indication of the configuration of the first group of beams includes beam information for each beam in the first group of beams.

[0072] In one or more embodiments, the configuration of the first set of beams may also include one or more of a network vendor identifier and / or a scenario identifier and / or a configuration identifier.

[0073] In one or more embodiments, the indication of the second set of beams for the BEP model includes a bitmap or combination index selection from the first set of beams (e.g., [1100 1100 1100 1100] to select 8 set B beams from 16 set A beams). In some embodiments, the indication of the second set of beams for the BEP model is a reordered subset of the first set of beams.

[0074] In one or more embodiments, a first duration is used for a first radio resource control (RRC) connection session, and a second duration is used for a second RRC connection session. In some embodiments, one or more of 402 to 414 occur during the first session (e.g., during RRC active mode), and one or more of 402 to 414 occur during the second session (e.g., during RRC active mode). In some embodiments, one or more of 402 to 414 occur during the UE's RRC idle mode or RRC inactive mode.

[0075] In one or more embodiments, the configuration indication is for both the first set of beams and the second set of beams, and the UE measures the reference signal received via the transceiver according to the configuration of the first set of beams and the second set of beams during a first duration.

[0076] Method 400 may be embodied, extended or modified in various ways, as described in the following paragraphs and elsewhere in this description.

[0077] Figure 5 An example method 500 for wireless communication performed by a network device is illustrated. In one or more embodiments, method 500 supports one or more aspects of beam management in lifecycle management, as further described herein. In some cases, the network device may be one of network device 104, network device 720, or other network devices described herein. Method 500 may be performed using a processor, transceiver (or main radio component), or other components of the network device.

[0078] At 502, method 500 includes using a first set of beams to transmit a reference signal. In some embodiments (e.g., when set B is not a subset of set A), at 502, method 500 may optionally (e.g., additionally or alternatively) include using a second set of beams to transmit the reference signal.

[0079] At 504, method 500 includes receiving UE capability signaling from the UE, the UE capability signaling including an indication of the UE's ability to train a BEP model (e.g., collect training data for the BEP model) or an inference using the BEP model to determine beam predictions of the first set of beams by means of measurements of the second set of beams.

[0080] At 506, method 500 includes sending an indication of the configuration of a first set of beams in response to UE capability signaling. Additionally or alternatively, in some embodiments, at 506, method 500 includes sending an indication of the configuration for a second set of beams.

[0081] At 508, method 500 includes receiving a report (e.g., a channel state information report or a beam report) indicating beam prediction from the UE.

[0082] In one or more embodiments, the indication of the configuration of the first group of beams is an index within a set of indices, each index corresponding to a corresponding configuration among a plurality of configurations for the first group of beams. In some embodiments, the indication of the configuration of the first group of beams is sent in a configuration of a reference signal measurement resource set. In some embodiments, the indication of the configuration of the first group of beams is sent in a channel state information reporting configuration. In some embodiments, the indication of the configuration of the first group of beams includes beam information for each beam in the first group of beams.

[0083] The embodiments contemplated herein include one or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform one or more elements of method 400 or 500. In the context of method 400, the non-transitory computer-readable medium may be, for example, the memory of a UE (such as memory 706 of a wireless device 702 as a UE, as described herein). In the context of method 500, the non-transitory computer-readable medium may be, for example, the memory of a network device (such as memory 724 of a network device 720, as described herein).

[0084] The embodiments contemplated herein include an apparatus having logic components, modules, or circuitry for performing one or more elements of method 400 or 500. In the context of method 400, the apparatus may be, for example, an apparatus of a UE (such as wireless device 702 as a UE). In the context of method 500, the apparatus may be, for example, an apparatus of a network device (such as network device 720, as described herein).

[0085] The embodiments contemplated herein include an apparatus having one or more processors and one or more computer-readable media that use or store instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of method 400 or 500. In the context of method 400, the apparatus may be, for example, an apparatus of a UE (such as wireless device 702 as a UE, as described herein). In the context of method 500, the apparatus may be, for example, an apparatus of a network device (such as network device 720, as described herein).

[0086] The implementation scheme envisioned herein includes a signal as described in or associated with one or more elements of method 400 or 500.

[0087] The embodiments contemplated herein include a computer program or computer program product having instructions, wherein execution of the program by a processor causes the processor to perform one or more elements of method 400 or 500. In the context of method 400, the processor may be a processor of a UE (such as processor 704 of wireless device 702 as a UE, as described herein), and the instructions may be located, for example, in the processor and / or in the memory of the UE (such as memory 706 of wireless device 702 as a UE, as described herein). In the context of method 500, the processor may be a processor of a network device (such as processor 722 of network device 720, as described herein), and the instructions may be located, for example, in the processor and / or in the memory of the network device (such as memory 724 of network device 720, as described herein).

[0088] Figure 6 An example architecture of a wireless communication system according to the implementation scheme described herein is illustrated. The following description is for an example wireless communication system 600 operating in conjunction with LTE system standards or specifications provided by 3GPP technical specifications and / or 5G or NR system standards or specifications.

[0089] like Figure 6 As shown, the wireless communication system 600 includes UE 602 and UE 604 (but any number of UEs may be used). In this example, UE 602 and UE 604 are exemplified as smartphones (e.g., handheld touchscreen mobile computing devices capable of connecting to one or more cellular networks), but may also include any mobile or non-mobile computing device configured for wireless communication.

[0090] UE 602 and UE 604 can be configured to communicatively couple with RAN 606. In some embodiments, RAN 606 may be NG-RAN, E-UTRAN, etc. UE 602 and UE 604 utilize connections (or channels) with RAN 606 (shown as connection 608 and connection 610, respectively), where each connection includes a physical communication interface. RAN 606 may include one or more network devices (such as base station 612 and base station 614) implementing connection 608 and connection 610.

[0091] In this example, Connection 608 and Connection 610 are air interfaces that enable this type of communication coupling and can conform to the RAT used by RAN606, such as LTE and / or NR, for example.

[0092] In some implementations, UE 602 and UE 604 may also exchange communication data directly via sidelink interface 616. UE 604 is shown configured to access an access point (shown as AP 618) via connection 620. By way of example, connection 620 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, wherein AP 618 may include Wi-Fi. ® Router. In this example, AP 618 can connect to another network (e.g., the Internet) without going through the core network (CN) 624.

[0093] In some implementations, UE 602 and UE 604 may be configured to communicate with each other or with base station 612 and / or base station 614 on a multi-carrier communication channel using orthogonal frequency division multiplexing (OFDM) communication signals according to various communication technologies, such as, but not limited to, orthogonal frequency division multiple access (OFDMA) communication technology (e.g., for downlink communication) or single-carrier frequency division multiple access (SC-FDMA) communication technology (e.g., for uplink and ProSe or sidelink communication), but the scope of the implementation is not limited in this respect. The OFDM signal may include multiple orthogonal subcarriers.

[0094] In some implementations, all or some of the base stations in base station 612 or base station 614 may be implemented as one or more software entities running on a server computer as part of a virtual network. Furthermore, or in other implementations, base station 612 or base station 614 may be configured to communicate with each other via interface 622. In implementations where the wireless communication system 600 is an LTE system (e.g., when CN 624 is an EPC), interface 622 may be an X2 interface. This X2 interface may be defined between two or more network devices (e.g., two or more eNBs, etc.) connected to the EPC and / or between two eNBs connected to the EPC. In implementations where the wireless communication system 600 is an NR system (e.g., when CN 624 is a 5GC), interface 622 may be an Xn interface. This Xn interface is defined between two or more network devices (e.g., two or more gNBs, etc.) connected to the 5GC, between base station 612 (e.g., gNB) and eNB connected to the 5GC, and / or between two eNBs connected to the 5GC (e.g., CN 624).

[0095] RAN 606 is shown communicatively coupled to CN 624 via interface 628. CN 624 may include one or more network elements 626 configured to provide various data and telecommunications services to customers / subscribers (e.g., users of UE 602 and UE 604) connected to CN 624 via RAN 606. Components of CN 624 may be implemented in a single physical device or a separate physical device, including components for reading and executing instructions from machine-readable or computer-readable media (e.g., non-transitory machine-readable storage media).

[0096] In some implementations, CN 624 may be an EPC, and RAN 606 may be connected to CN 624 via S1 interface 628. In some implementations, S1 interface 628 may be divided into two parts: an S1 user plane (S1-U) interface carrying service data between base station 612 or base station 614 and the serving gateway (S-GW), and an S1-MME interface serving as the signaling interface between base station 612 or base station 614 and the mobility management entity (MME).

[0097] In some implementations, CN 624 may be a 5GC, and RAN 606 may be connected to CN 624 via NG interface 628. In some implementations, NG interface 628 may be divided into two parts: an NG user plane (NG-U) interface carrying service data between base station 612 or base station 614 and user plane function (UPF), and an S1 control plane (NG-C) interface serving as the signaling interface between base station 612 or base station 614 and access and mobility management function (AMF).

[0098] Generally, application server 630 may be an element that provides Internet Protocol (IP) bearer resources (e.g., packet-switched data services) for use with CN 624. Application server 630 may also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for UE 602 and UE 604 via CN 624. Application server 630 can communicate with CN 624 via IP communication interface 632.

[0099] Figure 7 An example system 700 for performing signaling 738 between a wireless device 702 and a network device 720 according to an embodiment described herein is illustrated. System 700 may be part of a wireless communication system as described herein. Wireless device 702 may be, for example, a UE of a wireless communication system. Network device 720 may be, for example, a base station (e.g., an eNB or gNB) or a radio headend of a wireless communication system.

[0100] Wireless device 702 may include one or more processors 704. Processor 704 is executable instructions that cause various operations of wireless device 702 to be performed as described herein. Processor 704 may include one or more baseband processors, which are implemented using, for example, a central processing unit (CPU), digital signal processor (DSP), application-specific integrated circuit (ASIC), controller, field-programmable gate array (FPGA) device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein.

[0101] Wireless device 702 may include memory 706. Memory 706 may be a non-transitory computer-readable storage medium that stores instructions 708, which may include instructions executable, for example, by processor 704. Instructions 708 may also be referred to as program code or computer program. Memory 706 may also store data used by processor 704 and results calculated by the processor.

[0102] Wireless device 702 may include one or more transceivers 710 (also collectively referred to as transceiver 710), which may include radio frequency (RF) transmitter and / or receiver circuitry that uses antenna 712 of wireless device 702 to facilitate signaling to and / or from wireless device 702 and other devices (e.g., network device 720) according to a corresponding RAT (e.g., signaling 738). Wireless device 702 may also include or communicate with a machine learning engine 718. As further discussed herein (e.g., referring to UE 102), in some embodiments, machine learning engine 718 may be part of or a portion of wireless device 702. In some embodiments, machine learning engine 718 may be external to wireless device 702 and communicate with wireless devices via wired or wireless communication (e.g., wirelessly communicating with beam manager 716 via transceiver 710). In one or more embodiments, machine learning engine 718 is part of beam manager 716.

[0103] Wireless device 702 may include one or more antennas 712 (e.g., one, two, four, eight, or more). In embodiments with multiple antennas 712, wireless device 702 may fully utilize the spatial diversity of such multiple antennas 712 to transmit and / or receive multiple different data streams on the same time and frequency resources. This behavior may be referred to as, for example, MIMO behavior (referring to multiple antennas used at each of the transmitting and receiving devices to implement this aspect). MIMO transmission by wireless device 702 may be achieved according to pre-decoding (or digital beamforming) applied at wireless device 702, which multiplexes data streams across antennas 712 based on known or assumed channel characteristics, such that each data stream is received with appropriate signal strength relative to the others and at a desired location in the spatial domain (e.g., the location of the receiver associated with that data stream). Some embodiments may use a single-user MIMO (SU-MIMO) method (where all data streams are directed to a single receiver) and / or a multi-user MIMO (MU-MIMO) method (where individual data streams may be directed to individual (different) receivers at different locations in the spatial domain).

[0104] In some implementations with multiple antennas, the wireless device 702 may implement analog beamforming technology, whereby the phase of the signal transmitted by the antenna 712 is relatively adjusted so that the (joint) transmission of the antenna 712 can be directed (this is sometimes referred to as beam steering).

[0105] Wireless device 702 may include one or more interfaces 714. Interfaces 714 can be used to provide input to or output to wireless device 702. For example, wireless device 702 as a UE may include interfaces 714, such as microphones, speakers, touchscreens, and buttons, to allow users of the UE to input to and / or output to the UE. Other interfaces of such UEs may consist of transmitters, receivers, and other circuitry that allow communication between the UE and other devices (e.g., in addition to the transceiver 710 / antenna 712 described), and may be compatible with known protocols (e.g., Wi-Fi). ® ,Bluetooth ® (etc.) to perform the operation.

[0106] Wireless device 702 may include beam manager 716. Beam manager 716 may be implemented via hardware, software, or a combination thereof. For example, beam manager 716 may be implemented as a processor, circuitry, and / or instructions 708 stored in memory 706 and executed by processor 704. In some examples, beam manager 716 may be integrated within processor 704 and / or transceiver 710. For example, beam manager 716 may be implemented via a combination of software components (e.g., executed by a DSP or general-purpose processor) and hardware components (e.g., logic gates and circuitry) within processor 704 or transceiver 710.

[0107] From the perspective of a wireless device or UE, the beam manager 716 can be used in various aspects of this disclosure, for example, Figures 1 to 7 The beam manager 716 can be configured, for example, to: receive via a transceiver an indication of the configuration of a first set of beams used by the network device to transmit reference signals for measurement; measure the reference signals received via the transceiver according to the configuration of the first set of beams during a first duration; obtain a beam estimation / prediction (BEP) model to be used to determine beam predictions for a second set of beams, which are related to the first set of beams, and the BEP model is based at least in part on the measurement of the reference signals during the first duration; measure the reference signals received via the transceiver during the second duration and according to the configuration; determine beam predictions for one or more beams in the second set of beams using the CSI BEP model based at least in part on the measurement of the reference signals during the second duration; and transmit a report via the transceiver to the network device based at least in part on the beam predictions.

[0108] Network device 720 may include one or more processors 722. Processor 722 is executable instructions that cause various operations of network device 720 to be performed as described herein. Processor 722 may include one or more baseband processors, which are implemented using, for example, a CPU, DSP, ASIC, controller, FPGA device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein.

[0109] Network device 720 may include memory 724. Memory 724 may be a non-transitory computer-readable storage medium that stores instructions 726, which may include, for example, instructions executed by processor 722. Instructions 726 may also be referred to as program code or a computer program. Memory 724 may also store data used by processor 722 and results calculated by the processor.

[0110] Network device 720 may include one or more transceivers 728 (also collectively referred to as transceiver 728), which may include RF transmitter and / or receiver circuitry that uses antenna 730 of network device 720 to facilitate to-and / or signaling from network device 720 to other devices (e.g., wireless device 702) and / or from network device 720 (e.g., signaling 738) in accordance with the corresponding RAT.

[0111] Network device 720 may include one or more antennas 730 (e.g., one, two, four or more). In embodiments having multiple antennas 730, network device 720 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as described.

[0112] Network device 720 may include one or more interfaces 732. Interface 732 can be used to provide input to or output to network device 720. For example, RAN network device 720 (e.g., base station, radio head, etc.) may include interfaces 732 consisting of transmitters, receivers, and other circuitry (e.g., in addition to the transceiver 728 / antenna 730 already described), which enable network device 720 to communicate with other equipment in the network and / or enable network device 720 to communicate with external networks, computers, databases, etc., for the purpose of operating, managing, and maintaining network device 720 or other equipment operatively connected to it.

[0113] Network device 720 may include at least one beam manager 736. Beam manager 736 may be implemented via hardware, software, or a combination thereof. For example, beam manager 736 may be implemented as a processor, circuitry, and / or instructions 726 stored in memory 724 and executed by processor 722. In some examples, beam manager 736 may be integrated within processor 722 and / or transceiver 728. For example, beam manager 736 may be implemented via a combination of software components (e.g., executed by a DSP or general-purpose processor) and hardware components (e.g., logic gates and circuitry) within processor 722 or transceiver 728.

[0114] From a network device perspective, the beam manager 736 can be used in various aspects of this disclosure, for example, Figures 1 to 7The beam manager 736 can be configured, for example, to: transmit reference signals using a first set of beams via a transceiver; receive UE capability signaling from a user equipment (UE), the UE capability signaling including an indication of the UE's ability to determine beam prediction for the first set of beams using measurements of a second set of beams by training a beam estimation / prediction (BEP) model or using a BEP model; transmit an indication of the configuration of the first set of beams in response to the UE capability signaling; and receive a report from the UE indicating beam prediction.

[0115] For one or more embodiments, at least one of the components illustrated in one or more of the foregoing figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a baseband processor (or processor) as described herein in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples presented herein. Similarly, circuitry associated with a UE, network device, network element, etc., as described above in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples presented herein.

[0116] Unless otherwise expressly stated, any of the embodiments described above may be combined with any other embodiment (or combination of embodiments). The foregoing description of one or more specific embodiments provides illustrative and descriptive purposes, but is not intended to be exhaustive or to limit the scope of the embodiments to the precise form described. In light of the teachings above, modifications and variations are possible, or modifications and variations may be derived from the practice of various embodiments.

[0117] Implementations and specific embodiments of the systems and methods described herein may include various operations embodied in machine-executable instructions to be executed by a computer system. The computer system may include one or more general-purpose or special-purpose computers (or other electronic devices). The computer system may include hardware components, including specific logical parts for performing the operations; or may include a combination of hardware, software, and / or firmware.

[0118] The systems described herein relate to specific implementations but are provided as examples. These implementations may be combined into a single system, partially integrated into other systems, divided into multiple systems, or otherwise partitioned or combined. Furthermore, it is contemplated that parameters, attributes, aspects, etc., of any implementation may be used in another implementation. For clarity, these parameters, attributes, aspects, etc., are described only in one or more implementations, and it should be understood that, unless expressly stated herein, these parameters, attributes, aspects, etc., may be combined with or substituted for parameters, attributes, aspects, etc., of another implementation.

[0119] Although the foregoing has been described in considerable detail for clarity, it will be apparent that changes and modifications can be made without departing from the principles of the invention. It should be noted that many alternative ways exist to implement both the processes and apparatus described herein. Therefore, embodiments of the invention should be considered illustrative rather than restrictive, and this description is not limited to the details given herein, but can be modified within the scope and equivalents of the appended claims.

Claims

1. A user equipment (UE), the UE comprising: transceiver; as well as Processor, the processor being configured to cause the UE to: The transceiver receives instructions on the configuration of the first set of beams used by the network device to transmit reference signals for measurement. The reference signal received via the transceiver is measured according to the configuration of the first set of beams during the first duration. Obtain a beam estimation / prediction (BEP) model for determining beam predictions for a second set of beams, which are related to the first set of beams, and the BEP model is based at least in part on the measurements of the reference signal during the first duration. During the second duration and according to the configuration, the reference signal received via the transceiver is measured; The beam prediction for one or more beams in the second set of beams is determined using the BEP model based at least in part on the measurement of the reference signal during the second duration. as well as Reports are sent to the network device via the transceiver, at least in part, based on the beam prediction.

2. The UE of claim 1, wherein the processor configured to obtain the BEP model is further configured to: A set of training data is provided to the machine learning engine, at least in part, based on the measurements of the reference signal, the set of training data being used for both the first set of beams and the second set of beams; and In response to providing the set of training data to obtain the BEP model from the machine learning engine.

3. The UE of claim 1, wherein the processor is further configured to cause the UE to: Send UE capability signaling, the UE capability signaling including a first indication of the UE's ability to train the BEP model, a second indication of the UE's ability to use the BEP model to determine the beam prediction, or both, wherein the indication of the configuration is received in response to the UE capability signaling.

4. The UE of claim 1, wherein the indication of the configuration of the first group of beams is an index in a set of indexes, each index in the set of indexes corresponding to a corresponding configuration in a plurality of configurations of the first group of beams.

5. The UE of claim 1, wherein the indication of the configuration of the first set of beams is received in the configuration of the reference signal measurement resource set.

6. The UE of claim 5, wherein the configuration of the reference signal measurement resource set includes a non-zero power CSI reference signal resource set.

7. The UE of claim 1, wherein the indication of the configuration of the first group of beams is received in a reporting configuration.

8. The UE of claim 7, wherein the reporting configuration includes a CSI reporting configuration.

9. The UE according to claim 1, wherein the second set of beams is a subset of the first set of beams.

10. The UE of claim 1, wherein the indication of the configuration of the first group of beams includes beam information for each of the first group of beams.

11. The UE of claim 1, wherein the configuration of the first group of beams further includes one or more of a network vendor identifier, a scenario identifier, or a configuration identifier.

12. The UE of claim 1, wherein the indication of the second set of beams for the BEP model includes a bitmap or combination index selection from the first set of beams.

13. The UE of claim 1, wherein the indication of the second set of beams for the BEP model is a subset of the reordered first set of beams.

14. The UE of claim 1, wherein the first duration is used for a first radio resource control connection session, and the second duration is used for a second radio resource control connection session.

15. The UE according to claim 1, wherein: The instructions regarding the configuration are for both the first group of beams and the second group of beams; as well as The processor is configured to measure the reference signal, including that the processor is configured to cause the UE to measure the reference signal received via the transceiver during the first duration, according to the configuration of the first set of beams and the second set of beams.

16. A network device, the network device comprising: transceiver; as well as Processor, the processor being configured to cause the network device to: The reference signal is transmitted via the transceiver using the first set of beams; Receive UE capability signaling from User Equipment (UE), the UE capability signaling including an indication of the UE’s ability to train a beam estimation / prediction (BEP) model or to use the BEP model to determine beam prediction for a first set of beams using measurements of a second set of beams; In response to the UE capability signaling, an indication of the configuration of the first set of beams is sent; as well as The UE receives a report indicating the beam prediction.

17. The network device of claim 16, wherein the indication of the configuration of the first set of beams is an index in a set of indexes, each index in the set of indexes corresponding to a corresponding configuration in a plurality of configurations of the first set of beams.

18. The network device of claim 16, wherein the indication of the configuration of the first set of beams is sent in the configuration of the reference signal measurement resource set or in the CSI report configuration.

19. The network device of claim 16, wherein the indication of the configuration of the first group of beams includes beam information for each of the first group of beams.

20. A method for wireless communication at a user equipment (UE), the method comprising: Receive instructions on the configuration of the first set of beams used by the network device to transmit reference signals for measurement; The reference signal is measured according to the configuration of the first set of beams during the first duration; Obtain a beam estimation / prediction (BEP) model for determining beam predictions for a second set of beams, which are related to the first set of beams, and the BEP model is based at least in part on the measurements of the reference signal during the first duration. The reference signal is measured during the second duration and according to the configuration. The beam prediction for one or more beams in the second set of beams is determined using the BEP model based at least in part on the measurement of the reference signal during the second duration. as well as Reports are sent to the network devices based at least in part on the beam prediction.

Images