Machine learning model selection in beamforming communication

Abstract

Methods, systems, and apparatus for wireless communication are described, in which a base station can develop multiple different prediction models for each of several different functions. These different functions can be used to determine various beamforming parameters for beamforming communication between a user equipment (UE) and the base station. The base station can provide these models to the UE, and the UE can then use these models to determine values ​​for one or more beamforming parameters. The same function (e.g., a beam prediction function that identifies transmit / receive beams for communication) can have multiple different models, which can be provided to the UE by the base station and can be used based on specific channel conditions or the location of the UE. The UE or the base station can select which of the multiple prediction models will be used for communication.

Description

[0001] Cross-references

[0002] This patent application claims priority to U.S. Provisional Patent Application No. 63 / 011,184, filed April 16, 2020, entitled "Machine Learning Model Selection in Beamformed Communications," and U.S. Patent Application No. 17 / 229,334, filed April 13, 2021, entitled "Machine Learning Model Selection in Beamformed Communications," each of which has been assigned to the assignee of this application. Technical Field

[0003] In general, the following description relates to wireless communication, and more specifically, the following description relates to communication for managing beamforming. Background Technology

[0004] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, broadcasting, and so on. These systems can support communication with multiple users by sharing available system resources (e.g., time, frequency, and power). Examples of such multiple access systems include fourth-generation (4G) systems (e.g., Long Term Evolution (LTE) systems, LTE-A Advanced (LTE-A) systems, or LTE-A Pro systems) and fifth-generation (5G) systems (which may be called New Radio (NR) systems). These systems can employ technologies such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiplexing (OFDMA), or Discrete Fourier Transform Extended Orthogonal Frequency Division Multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations or one or more network access nodes, each of which simultaneously supports communication from multiple communication devices (or user equipment (UE)). Summary of the Invention

[0005] A method for wireless communication at a user equipment (UE) is described. The method may include: receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station; and communicating with the base station using beamforming communication based on one or more parameters, the one or more parameters being based on a prediction model among the one or more prediction models for the first function of beamforming communication with the base station.

[0006] An apparatus for wireless communication at a UE is described. The apparatus may include a processor and a memory coupled to the processor, the processor and the memory being configured to: receive from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station; and communicate with the base station using beamforming communication based on one or more parameters, the one or more parameters being based on a prediction model among the one or more prediction models for the first function of beamforming communication with the base station.

[0007] Another apparatus for wireless communication at a UE is described. The apparatus may include: units for receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station; and units for communicating with the base station using beamforming communication based on one or more parameters, the one or more parameters being based on a prediction model among the one or more prediction models for the first function of beamforming communication with the base station.

[0008] A non-transitory computer-readable medium is described, storing code for wireless communication at a UE. The code may include instructions executable by a processor to: receive from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station; and communicate with the base station using beamforming communication based on one or more parameters, the one or more parameters being based on a prediction model among the one or more prediction models for the first function of beamforming communication with the base station.

[0009] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: measuring one or more channel conditions between the UE and the base station; in response to the measurement, sending a measurement report to the base station indicating the one or more channel conditions; receiving an indication of the prediction model from the base station; and in response to the indication from the base station, selecting the prediction model for use in the first function. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the UE receives from the base station a preferred list of prediction models for each function in a set of functions to be used at the UE for communication associated with beamforming.

[0010] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: determining whether the prediction model accurately predicts the first function; and, based on the determination, sending an indication to the base station. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement report also indicates the location information of the UE. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement may include operations, features, units, or instructions for: measuring one or more reference signals received from the base station and one or more other base stations in one or more synchronization signal blocks (SSBs).

[0011] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: sending one or more measurement reports to the base station based on measurements associated with beamforming communication that uses the prediction model for the first function; receiving from the base station an instruction for switching to a different prediction model among the one or more prediction models in response to the one or more measurement reports; determining one or more updated parameters for further beamforming communication based on the different prediction models used for the first function; and communicating with the base station using beamforming communication that can be based on the one or more updated parameters.

[0012] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving a model selection function from the base station for selecting different prediction models; and, based on the model selection function, switching to the different prediction model among the one or more prediction models for use in the first function. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: measuring one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or combinations thereof, to identify a set of multiple measurements; and providing the set of multiple measurements as input to the model selection function, wherein the switching is performed in response to an associated output of the model selection function based on the set of multiple measurements.

[0013] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: calculating a result of the first function for each of two or more prediction models to generate two or more results of the first function; determining a first result among the two or more results of the first function as the most preferred result, wherein the first result is associated with a first prediction model; and selecting the first prediction model based on the determination. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: monitoring the prediction quality from the first prediction model in a set of multiple predictions; and switching to a second prediction model for the first function based on the prediction quality from the first prediction model decreasing to below a threshold quality. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the decrease in prediction quality to below the threshold quality may be determined based on a mismatch between the result of the first prediction model and observations based on one or more measurements at the UE. In some examples of the methods, apparatuses and non-transitory computer-readable media described herein, the prediction quality may be determined to have fallen below the threshold quality based on one or more of the following: the number of consecutive incorrect predictions exceeds the threshold, the number of incorrect predictions in a set of past predictions exceeds the threshold, or any combination thereof.

[0014] A method for wireless communication at a base station is described. The method may include: sending to a first UE one or more prediction models for at least a first function associated with beamforming communication with the first UE, the one or more prediction models being based on identifying the first UE as being for beamforming communication with the base station; and communicating with the first UE using beamforming communication parameters based on one of the one or more prediction models.

[0015] An apparatus for wireless communication at a base station is described. The apparatus may include a processor and a memory coupled to the processor, the processor and the memory being configured to: transmit to a first UE one or more prediction models for at least a first function associated with beamforming communication with the first UE, the one or more prediction models being based on identifying the first UE as being for beamforming communication with the base station; and communicate with the first UE using beamforming communication parameters based on one of the prediction models.

[0016] Another apparatus for wireless communication at a base station is described. The apparatus may include: a unit for transmitting to a first UE one or more prediction models for at least a first function associated with beamforming communication with the first UE, the one or more prediction models being based on identifying the first UE as being for beamforming communication with the base station; and a unit for communicating with the first UE using beamforming communication parameters based on the prediction models in the one or more prediction models.

[0017] A non-transitory computer-readable medium is described, storing code for wireless communication at a base station. The code may include instructions executable by a processor to: send to a first UE one or more prediction models for at least a first function associated with beamforming communication with the first UE, the one or more prediction models being based on identifying the first UE as being for beamforming communication with the base station; and communicate with the first UE using beamforming communication parameters based on one of the one or more prediction models.

[0018] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving from the first UE a measurement report indicating channel conditions at one or more measurements at the first UE; selecting a prediction model from the one or more prediction models based on the measurement report for beamforming communication with the first UE; and sending an indication of the prediction model to the first UE. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, sending the indication of the prediction model may include operations, features, units, or instructions for: sending a priority list of prediction models for each of a set of multiple functions to be used at the first UE for beamforming communication.

[0019] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving from the first UE an indication of whether the prediction model accurately predicts the first function; and updating a model for determining, based on a measurement report, which of the one or more prediction models to indicate to the UE. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement report further indicates location information of the first UE, and wherein the selection is further based on the location information.

[0020] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving one or more measurement reports from the first UE, the one or more measurement reports indicating measurements associated with beamforming communications that use the prediction model for the first function; determining, based on the one or more measurement reports, that the first UE will switch to a different prediction model among two or more prediction models; and sending an instruction to the UE to switch to the different prediction model.

[0021] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include: operations, features, units, or instructions for sending a model selection function to the first UE for the UE to select a different prediction model. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include: operations, features, units, or instructions for configuring the first UE to select a prediction model from two or more prediction models based on the result of the first function for each of the two or more prediction models. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the configuration may include: operations, features, units, or instructions for configuring a threshold prediction quality at the first UE to initiate a switch between prediction models. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the threshold prediction quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in a set of past predictions exceeding the threshold, or any combination thereof.

[0022] A method for wireless communication at a UE is described. The method may include: receiving from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; selecting a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; determining one or more parameters for the beamforming communication based on the first prediction model for the first function; and communicating with the base station using beamforming communication based on the one or more determined parameters.

[0023] An apparatus for wireless communication at a UE is described. The apparatus may include a processor and a memory coupled to the processor, the processor and the memory being configured to: receive from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; select a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; determine one or more parameters for the beamforming communication based on the first prediction model for the first function; and communicate with the base station using beamforming communication based on the one or more determined parameters.

[0024] Another apparatus for wireless communication at a UE is described. The apparatus may include: units for receiving from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; units for selecting a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; units for determining one or more parameters for the beamforming communication based on the first prediction model for the first function; and units for communicating with the base station using beamforming communication based on the one or more determined parameters.

[0025] A non-transitory computer-readable medium is described, storing code for wireless communication at a UE. The code may include instructions executable by a processor to: receive from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; select a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; determine one or more parameters for the beamforming communication based on the first prediction model for the first function; and communicate with the base station using beamforming communication based on the one or more determined parameters.

[0026] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the selection may include operations, features, units, or instructions for: measuring one or more channel conditions between the UE and the base station; in response to the measurement, sending a measurement report to the base station indicating the one or more channel conditions; receiving an indication of the first prediction model from the base station; and in response to the indication from the base station, selecting the first prediction model for the first function.

[0027] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the UE receives from the base station a priority list of prediction models for each of a set of functions to be used at the UE for communication associated with beamforming. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement may include operations, features, units, or instructions for measuring one or more reference signals received from the base station and one or more other base stations in one or more synchronization signal blocks (SSBs). In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement report further indicates the location information of the UE.

[0028] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: determining whether the first prediction model accurately predicts the first function; and sending an indication to the base station based on the determination. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the selection may include operations, features, units, or instructions for: calculating a result for the first function for each prediction model in the set of prediction models to generate a set of results for the first function; determining that a first result in the set of results for the first function may be the most preferred result in the set of results, wherein the first result is associated with the first prediction model; and selecting the first prediction model based on the determination.

[0029] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: monitoring the prediction quality from the first prediction model within a set of predictions; and switching to a second prediction model for the first function based on the prediction quality from the first prediction model falling below a threshold quality. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the prediction quality falling below the threshold quality is determined based on a mismatch between the results of the first prediction model and observations based on one or more measurements at the UE. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the prediction quality falling below the threshold quality may be determined based on one or more of the following: the number of consecutive incorrect predictions exceeds a threshold, the number of incorrect predictions in a set of past predictions exceeds a threshold, or any combination thereof.

[0030] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: sending one or more measurement reports to the base station based on measurements associated with beamforming communication that uses the first prediction model for the first function; receiving from the base station an instruction for switching to a second prediction model in a set of prediction models in response to the one or more measurement reports; determining one or more updated parameters for further beamforming communication based on the second prediction model used for the first function; and communicating with the base station using beamforming communication based on the one or more updated parameters.

[0031] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving a model selection function from the base station for selecting different prediction models; and, based on the model selection function, switching from a first prediction model to a second prediction model in the set of prediction models for use in the first function. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: measuring one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or combinations thereof, to identify a set of measurements; and providing the set of measurements as input to the model selection function, wherein the switching is performed in response to an associated output of the model selection function based on the set of measurements.

[0032] A method for wireless communication at a base station is described. The method may include: identifying a set of predictive models for at least a first function associated with beamforming communication between the base station and a UE; transmitting the set of predictive models to the first UE based on identifying the first UE as being for beamforming communication with the base station; and communicating with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on the first predictive model in the set of predictive models.

[0033] An apparatus for wireless communication at a base station is described. The apparatus may include a processor and a memory coupled to the processor, the processor and the memory being configured to: identify a set of prediction models for at least a first function associated with beamforming communication between the base station and a UE; transmit the set of prediction models to a first UE based on identifying the first UE as being for beamforming communication with the base station; and communicate with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first prediction model in the set of prediction models.

[0034] Another apparatus for wireless communication at a base station is described. The apparatus may include: units for identifying a set of predictive models for at least a first function associated with beamforming communication between the base station and a UE; units for transmitting the set of predictive models to the first UE based on identifying the first UE as being for beamforming communication with the base station; and units for communicating with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first predictive model in the set of predictive models.

[0035] A non-transitory computer-readable medium is described, storing code for wireless communication at a base station. The code may include instructions executable by a processor to: identify a set of predictive models for at least a first function associated with beamforming communication between the base station and a UE; transmit the set of predictive models to the first UE based on identifying the first UE as being for beamforming communication with the base station; and communicate with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first predictive model in the set of predictive models.

[0036] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving from the first UE a measurement report indicating channel conditions at one or more measurements at the first UE; selecting, based on the measurement report, a first prediction model from a set of prediction models for beamforming communication with the first UE; and sending an indication of the first prediction model to the first UE.

[0037] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the indication to send the first prediction model may include operations, features, units, or instructions for sending a priority list of prediction models for each of a set of functions to be used at the first UE for communication associated with beamforming. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the measurement report further indicates location information of the first UE, and the selection is further based on the location information.

[0038] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving from the first UE an indication of whether the first prediction model accurately predicts the first function; and updating a model for determining, based on a measurement report, which prediction model in the set of prediction models to indicate to the UE. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: configuring the first UE to select the first prediction model from the set of prediction models based on the results for the first function for each of the prediction models.

[0039] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for configuring the threshold prediction quality at the first UE to initiate a switch between prediction models. In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the threshold prediction quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in a set of past predictions exceeding the threshold, or any combination thereof.

[0040] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: receiving one or more measurement reports from a first UE, the one or more measurement reports indicating measurements associated with beamforming communication using the first prediction model for the first function; determining, based on the one or more measurement reports, that the first UE will switch to a second prediction model in the set of prediction models; and sending an instruction to the UE to switch to the second prediction model. Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, units, or instructions for: sending a model selection function to the first UE for the UE to select a different prediction model from the set of prediction models. Attached Figure Description

[0041] Figure 1Based on various aspects of this disclosure, examples of wireless communication systems that support the selection of machine learning models in beamforming communications are shown.

[0042] Figure 2 Based on various aspects of this disclosure, an example of a wireless communication system that supports the selection of machine learning models in beamforming communications is shown.

[0043] Figure 3 Based on various aspects of this disclosure, another example is shown as part of a wireless communication system that supports the selection of machine learning models in beamforming communications.

[0044] Figure 4 and Figure 5 Based on various aspects of this disclosure, examples of the process flow for selecting machine learning models in communications that support beamforming are shown.

[0045] Figure 6 and Figure 7 Based on various aspects of this disclosure, a block diagram of a device for selecting a machine learning model in beamforming communications is shown.

[0046] Figure 8 Based on various aspects of this disclosure, a block diagram of a communication manager supporting machine learning model selection in beamforming communications is shown.

[0047] Figure 9 Based on various aspects of this disclosure, a diagram of a system including a device that supports machine learning model selection in beamforming communications is shown.

[0048] Figure 10 and Figure 11 Based on various aspects of this disclosure, a block diagram of a device for selecting a machine learning model in beamforming communications is shown.

[0049] Figure 12 Based on various aspects of this disclosure, a block diagram of a communication manager supporting machine learning model selection in beamforming communications is shown.

[0050] Figure 13 Based on various aspects of this disclosure, a diagram of a system including a device that supports machine learning model selection in beamforming communications is shown.

[0051] Figures 14 to 21 Based on various aspects of this disclosure, flowcharts depicting methods for selecting machine learning models in communications that support beamforming are shown. Detailed Implementation

[0052] In some deployments, wireless communication systems can operate in the millimeter-wave (mmW) frequency range (e.g., 24 GHz, 26 GHz, 28 GHz, 39 GHz, 52.6–71 GHz, etc.). Wireless communication at these frequencies may be associated with increased signal attenuation (e.g., path loss, penetration loss, blocking loss), which can be affected by various factors such as diffraction, propagation environment, blocking density, material properties, and so on. Therefore, signal processing techniques such as beamforming can be used to coherently combine energy and overcome path loss at these frequencies. Due to the increased path, penetration, and blocking losses in mmW communication systems, beamforming can be applied to transmissions between wireless devices (e.g., from base stations and / or user equipment (UEs)). Furthermore, receiving devices can use beamforming techniques to configure antennas and / or antenna arrays and / or antenna array modules to receive transmissions in a directional manner.

[0053] To identify suitable beamforming parameters, the UE and base station can perform a beam training process to identify suitable beams and associated beamforming parameters for communication. For example, the base station can transmit multiple beams during beam scanning, and the UE can measure the received signal to identify the preferred beam, and the base station and UE can then establish a beampup link. Furthermore, when using beamforming for communication, various other parameters (e.g., channel attribute parameters including delay spread, connectivity parameters for identifying when to switch UEs between base stations, etc.) can be identified and used for communication.

[0054] Based on the various techniques discussed herein, a base station can develop multiple different prediction models for each of several different functions that can be used to determine various beamforming parameters. For example, multiple neural network (NN), artificial intelligence (AI), or machine learning (ML) models can be generated for each of the multiple different functions. The base station can provide these models to the UE, which can then use them to determine values ​​(e.g., initial values) for one or more beamforming parameters. Furthermore, in some cases, multiple different models can be available for the same function (e.g., a beam prediction function for identifying transmit / receive beams used for communication), and the base station can provide these models to the UE. These different models for the same function can be used based on specific channel conditions or the location of the UE. For example, a first model predicting delay spread channel properties might provide a good fit and prediction when the UE is relatively close to the base station, while a second model might provide a better fit and prediction when the UE is relatively far from the base station. For example, some functions could be beam prediction functions (e.g., transmit / receive beams used for communication at the UE and base station), channel property predictions (e.g., predicted delay spread values), connectivity predictions (e.g., when to perform a handover between different base stations, and which base station to select for a given channel condition and / or location), and so on. In some cases, multiple different models can be provided for each function, and a model can be selected and used for communication based on various techniques such as those discussed herein. Furthermore, when the UE is in a changing channel environment (e.g., due to UE movement), the UE can update its model to appropriately match the current channel environment based on techniques such as those discussed herein.

[0055] In some cases, a base station can provide multiple different models for each of several different functions and can assist the UE in model selection. For example, the UE can measure the channel between itself and the serving base station or cell (and optionally, one or more other base stations or cells from which the UE can receive signals) and use the channel measurement for model selection. Such measurements can be based on periodic synchronization signal blocks (SSBs) transmitted by the base station, and the UE can measure any detected SSBs from the serving base station or other base stations. Furthermore, in some cases, the UE can measure its location (e.g., based on Global Positioning System (GPS) measurements, indoor positioning measurements, or a combination thereof), which can be provided as input to one or more models or used to assist in model selection. In some cases, the UE can send one or more measurement reports to the serving base station, which can provide measured channel conditions, location information, or a combination thereof. In response to the measurement reports, the serving base station can provide the UE with a priority list of predictive models for each function (e.g., based on which models provide better results for the UE function based on the UE measurement reports). In some cases, the UE can provide feedback to the base station related to the accuracy of the predictions of the model indicated by the base station, and the base station can use this feedback to update the recommendation for which model to select for future indication.

[0056] In some cases, the UE can receive multiple models for multiple functions, and the UE can determine which model to select for communication. In other cases, the UE can determine the outcome of each model, and based on the initial results, the UE can select the best model to use. Furthermore, the UE can monitor the prediction quality of the selected model and switch to a different model if the prediction quality drops below a threshold. For example, if the prediction model indicates that a different base station will provide a better link, the UE can request other base stations to send synchronization signals to find a beam pair. If this action does not result in a better prediction (e.g., no suitable beam pair with other base stations is identified), the prediction is incorrect; otherwise, the prediction is good. In some cases, if the current prediction model gives a consecutive number of bad predictions exceeding a threshold, or if n bad predictions are observed in the past m predictions, the UE can switch to a different prediction model.

[0057] Furthermore, in some cases, the UE can update its prediction model based on the current channel environment observed at the UE. In this case, the UE can measure the channel characteristics between itself and its serving base station and send the corresponding measurement report to the base station. Based on the measurement report, the base station can send an update to the UE to use a different prediction model, which the UE can use to update its model and any associated parameters. Alternatively, in some cases, the base station can provide a model selection function that can be used at the UE to update its model. In this case, the UE can measure the channel or its internal state provided to the model selection function (e.g., gyroscope measurements that may indicate switching antenna panels). The model selection function can then output an update to be applied to the UE's prediction model.

[0058] Such a technique can be used to instruct the UE on a predictive model, which can be used to determine one or more beamforming parameters for communication between the UE and the base station. This predictive model allows for more efficient determination of communication parameters with fewer iterations, leading to better selection of appropriate parameters and improved communication efficiency. Therefore, providing a predictive model and model instructions for use at the UE can provide enhanced efficiency and reliability.

[0059] The various aspects of this disclosure are initially described in the context of wireless communication systems. These aspects are further depicted and described by way of process flows, apparatus diagrams, system diagrams, and flowcharts relating to the selection of machine learning models in beamforming communications.

[0060] Figure 1 According to various aspects of this disclosure, examples of a wireless communication system 100 supporting machine learning model selection in beamforming communications are shown. The wireless communication system 100 may include one or more base stations 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a Long Term Evolution (LTE) network, an Advanced LTE (LTE-A) network, an LTE-A Pro network, or a New Radio (NR) network. In some examples, the wireless communication system 100 may support enhanced broadband communications, ultra-reliable (e.g., mission-critical) communications, low-latency communications, communications with low-cost and low-complexity devices, or any combination thereof.

[0061] Base stations 105 can be distributed throughout a geographical area to form a wireless communication system 100, and can be devices of different forms or with different capabilities. Base stations 105 and UE 115 can communicate wirelessly via one or more communication links 125. Each base station 105 can provide a coverage area 110, and UE 115 and base station 105 can establish one or more communication links 125 on the coverage area 110. The coverage area 110 can be an example of a coverage area where base station 105 and UE 115 are able to support signal transmission according to one or more radio access technologies.

[0062] UE 115 can be distributed throughout the entire coverage area 110 of the wireless communication system 100, and each UE 115 can be stationary, mobile, or both at different times. UE 115 can be devices of different forms or with different capabilities. Figure 1 Some example UE 115s are shown in the document. The UE 115 described herein is capable of communicating with various types of devices, such as other UE 115s, base station 105, or network devices (e.g., core network nodes, relay devices, repeater devices, customer premises equipment (CPE), integrated access and backhaul (IAB) nodes, router devices, or other network devices). Figure 1 As shown in the image.

[0063] Base station 105 can communicate with core network 130, communicate with each other, or both. For example, base station 105 can connect to core network 130 via one or more backhaul links 120 (e.g., via S1, N2, N3, or other interfaces). Base station 105 can communicate directly (e.g., directly between base stations 105) or indirectly (e.g., via core network 130) or both via backhaul links 120 (e.g., via X2, Xn, or other interfaces). In some examples, backhaul link 120 can be or include one or more radio links. In some examples, one or more base stations 105 can provide a backhaul connection between another base station 105 and core network 130 via backhaul link 160, while acting as an IAB node.

[0064] One or more of the base stations 105 described herein may include, or be referred to by those skilled in the art as: base station transceiver, radio base station, access point, radio transceiver, node B, eNodeB (eNB), next-generation node B or giga node B (any of which may be referred to as gNB), home node B, home eNodeB or other suitable terms.

[0065] UE 115 may include or be referred to as a mobile device, wireless device, remote device, handheld device, or user equipment, or some other suitable term, wherein "device" may also refer to a unit, station, terminal, or client, etc. UE 115 may also include or be referred to as a personal electronic device, such as a cellular phone, personal digital assistant (PDA), tablet computer, laptop computer, or personal computer. In some examples, UE 115 may include or be referred to as a wireless local loop (WLL) station, Internet of Things (IoT) device, Internet of Things (IoE) device, or machine-type communication (MTC) device, etc., which may be implemented in various items such as home appliances, vehicles, meters, etc.

[0066] The UE 115 described herein can communicate with various types of devices, such as other UE 115s that sometimes act as relays, routers, or CPEs, as well as base stations 105 and network devices including macro eNBs or gNBs, small cell eNBs or gNBs, IAB nodes, or relay base stations, and other examples, such as... Figure 1 As shown in the image.

[0067] UE 115 and base station 105 can communicate wirelessly with each other via one or more communication links 125 using one or more carriers. The term "carrier" can refer to a set of radio spectrum resources having a defined physical layer structure to support communication link 125. For example, a carrier for communication link 125 may include a portion of the radio spectrum band (e.g., a bandwidth portion (BWP)) operating according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling coordinating the operation of the carrier, user data, or other signaling. Wireless communication system 100 can use carrier aggregation or multi-carrier operation to support communication with UE 115. Depending on the carrier aggregation configuration, UE 115 may be configured with multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation can be used with frequency division duplex (FDD) and time division duplex (TDD) component carriers.

[0068] The communication link 125 shown in the wireless communication system 100 may include uplink transmission from UE 115 to base station 105, or downlink transmission from base station 105 to UE 115. The carrier may carry downlink or uplink communication (e.g., in FDD mode) or may be configured to carry both downlink and uplink communication (e.g., in TDD mode).

[0069] A carrier can be associated with a specific bandwidth of the radio spectrum, and in some examples, the carrier bandwidth can be referred to as the carrier or the “system bandwidth” of the wireless communication system 100. For example, the carrier bandwidth can be one of several defined bandwidths of a carrier for a particular radio access technology (e.g., 1.4, 3, 5, 10, 15, 20, 40, or 80 MHz). Devices of the wireless communication system 100 (e.g., base station 105, UE 115, or both) can have a hardware configuration that supports communication over a specific carrier bandwidth, or can be configured to support communication over one of a set of carrier bandwidths. In some examples, the wireless communication system 100 may include a base station 105 or UE 115 that supports simultaneous communication via carriers associated with multiple carrier bandwidths. In some examples, each servicing UE 115 can be configured to operate on a portion (e.g., a subband, BWP) or all of the carrier bandwidth.

[0070] The signal waveform transmitted via a carrier can consist of multiple subcarriers (e.g., using multicarrier modulation (MCM) techniques such as Orthogonal Frequency Division Multiplexing (OFDM) or Discrete Fourier Transform Extended OFDM (DFT-s-OFDM). In a system employing MCM, a resource element can consist of one symbol period (e.g., the duration of a modulation symbol) and one subcarrier, where the symbol period and subcarrier spacing are inversely proportional. The number of bits carried by each resource element can depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both). Therefore, the more resource elements received by UE 115 and the higher the order of the modulation scheme, the higher the data rate that can be used for UE 115. Wireless communication resources can refer to radio spectrum resources, temporal resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial layers can further increase the data rate or data integrity used for communication with UE 115.

[0071] The time interval used for base station 105 or UE 115 can be expressed as a multiple of the basic time unit (e.g., it can refer to T). s =1 / (Δf) max ·N f (sampling period of ) seconds), where Δf max This can represent the maximum supported subcarrier spacing, while N... f This can represent the maximum supported Discrete Fourier Transform (DFT) size. Communication resources can be organized into time intervals based on radio frames, where each radio frame has a specified duration (e.g., 10 milliseconds (ms)). Each radio frame can be identified by a System Frame Number (SFN) (e.g., a range from 0 to 1023).

[0072] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into multiple time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include multiple symbol periods (e.g., depending on the length of the cyclic prefix appended to each symbol period). In some wireless communication systems 100, the time slots may be further divided into multiple micro-time slots containing one or more symbols. In addition to the cyclic prefix, each symbol period may contain one or more (e.g., N) symbols. f ( ) sampling periods. The duration of a symbol period can depend on the subcarrier spacing or the operating frequency band.

[0073] A subframe, time slot, micro-time slot, or symbol can be the smallest scheduling unit of the wireless communication system 100 (e.g., in the time domain), and it can be referred to as a transmission time interval (TTI). In some examples, the duration of the TTI (e.g., the number of symbol periods in the TTI) can be variable. Alternatively or additionally, the smallest scheduling unit of the wireless communication system 100 can be dynamically selected (e.g., in bursts of shortened TTIs (sTTIs)).

[0074] Physical channels can be multiplexed onto a carrier using various techniques. For example, one or more of Time Division Multiplexing (TDM), Frequency Division Multiplexing (FDM), or hybrid TDM-FDM techniques can be used to multiplex physical control channels and physical data channels onto a downlink carrier. A control region (e.g., a control resource set (CORESET)) for physical control channels can be defined over multiple symbol periods and can extend over a subset of the system bandwidth or the system bandwidth of the carrier. One or more control regions (e.g., CORESETs) can be configured for a set of UEs 115. For example, one or more UEs 115 can monitor or search for control regions to obtain control information based on one or more search space sets, and each search space set can include one or more control channel candidates arranged in a cascaded manner with one or more aggregation levels. The aggregation level for control channel candidates can refer to the number of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space set may include a common search space set configured to send control information to multiple UEs 115 and a UE-specific search space set used to send control information to a specific UE 115.

[0075] In some examples, base station 105 may be mobile, and thus provide communication coverage for mobile geographic coverage areas 110. In some examples, different geographic coverage areas 110 associated with different technologies may overlap, but the different geographic coverage areas 110 may be supported by the same base station 105. In other examples, overlapping geographic coverage areas 110 associated with different technologies may be supported by different base stations 105. For example, wireless communication system 100 may include a heterogeneous network in which different types of base stations 105 use the same or different radio access technologies to provide coverage for various geographic coverage areas 110.

[0076] Some UEs 115, such as MTC or IoT devices, can be low-cost or low-complexity devices that can provide automated machine-to-machine communication (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC can refer to data communication technologies that allow devices to communicate with each other or with base station 105 without human intervention. In some examples, M2M communication or MTC may include communication from devices with integrated sensors or meters that measure or capture information and relay that information to a central server or application, which may then utilize or present the information to personnel interacting with the application. Some UEs 115 can be designed to collect information or automate the behavior of machines or other devices. Examples of applications for MTC devices include: smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based billing.

[0077] Wireless communication system 100 can be configured to support ultra-reliable communication or low-latency communication, or various combinations thereof. For example, wireless communication system 100 can be configured to support ultra-reliable low-latency communication (URLLC) or mission-critical communication. UE 115 can be designed to support ultra-reliable, low-latency, or mission-critical functions (e.g., mission-critical functions). Ultra-reliable communication can include private or group communication and can be supported through one or more mission-critical services (e.g., mission-critical push-to-talk (MCPTT), mission-critical video (MCVideo), or mission-critical data (MCData)). Support for mission-critical functions can include prioritizing services, which can be used for public safety or general business applications. The terms ultra-reliable, low-latency, mission-critical, and ultra-reliable low-latency are used interchangeably herein.

[0078] In some examples, UE 115 can also communicate directly with other UE 115 via device-to-device (D2D) communication link 135 (e.g., using peer-to-peer (P2P) or D2D protocols). One or more UE 115s using D2D communication may be located within the geographic coverage area 110 of base station 105. Other UE 115s in the group may be located outside the geographic coverage area 110 of base station 105 or may not be able to receive transmissions from base station 105. In some examples, the group of UE 115s communicating via D2D communication may utilize a one-to-many (1:M) system, in which each UE 115 sends signals to every other UE 115 in the group. In some examples, base station 105 facilitates the scheduling of resources for D2D communication. In other cases, D2D communication is performed between UE 115s without involving base station 105.

[0079] In some systems, the D2D communication link 135 may be an example of a communication channel (e.g., a lateral link communication channel) between vehicles (e.g., UE 115). In some examples, vehicles may communicate using vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination thereof. Vehicles may signal information related to traffic conditions, signal control, weather, safety, emergencies, or any other information related to the V2X system. In some examples, vehicles in a V2X system may communicate with roadside infrastructure such as roadside units, or use vehicle-to-network (V2N) communication to communicate with the network via one or more network nodes (e.g., base station 105), or both.

[0080] Core network 130 can provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. Core network 130 can be an evolved packet core (EPC) or a 5G core (5GC), the latter including at least one control plane entity (e.g., a Mobility Management Entity (MME), Access and Mobility Management Function (AMF)) managing access and mobility, and at least one user plane entity (e.g., a Serving Gateway (S-GW), Packet Data Network (PDN) Gateway (P-GW), or User Plane Function (UPF)) routing packets or interconnecting to external networks. Control plane entities can manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management for UE 115 served by base station 105 associated with core network 130. User IP packets can be transmitted through user plane entities, which can provide IP address allocation and other functions. User plane entities can connect to network operator IP services 150. These operator IP services 150 can include access to the Internet, intranets, IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0081] Some of the network devices (e.g., base station 105) may include sub-components such as access network entities 140, which may be examples of access node controllers (ANCs). Each access network entity 140 may communicate with the UE 115 through one or more other access network transport entities 145 (which may be referred to as a radio headend, smart radio headend, or transmit / receive point (TRP)). Each access network transport entity 145 may include one or more antenna panels. In some configurations, the various functions of each access network entity 140 or base station 105 may be distributed across various network devices (e.g., radio headends and ANCs) or combined into a single network device (e.g., base station 105).

[0082] Wireless communication system 100 can operate using one or more frequency bands (typically in the range of 300 MHz to 300 GHz). The region from 300 MHz to 3 GHz is generally referred to as the Very High Frequency (UHF) region or decimeter band, due to its wavelength range of approximately one decimeter to one meter in length. UHF waves may be blocked or deflected by buildings and environmental features; however, these waves can penetrate structures sufficiently to allow macrocells to provide service to UE 115 located indoors. Compared to transmissions using smaller frequencies and longer wavelengths in the lower frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz, UHF wave transmission can be associated with smaller antennas and shorter distances (e.g., less than 100 km).

[0083] The wireless communication system 100 can also operate in the ultra-high frequency (SHF) region using a frequency band from 3 GHz to 30 GHz (also known as the centimeter-wave band), or in the extremely high frequency (EHF) region of the spectrum (e.g., from 30 GHz to 300 GHz) (also known as the millimeter-wave band). In some examples, the wireless communication system 100 can support millimeter-wave (mmW) communication between the UE 115 and the base station 105, with the corresponding device's EHF antenna potentially being even smaller and more compact than a UHF antenna. In some examples, this can be advantageous for using antenna arrays within the device. However, compared to SHF or UHF transmissions, EHF transmissions may suffer from greater atmospheric attenuation and shorter transmission distances. In transmissions using one or more different frequency regions, the techniques disclosed herein can be employed, and the designated use of frequency bands across these frequency regions may vary due to national or regulatory factors.

[0084] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc., based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range names FR1 (410MHz-7.125GHz) and FR2 (24.25GHz-52.6GHz). It should be understood that although a portion of FR1 is greater than 6GHz, in various documents and articles, FR1 is generally (interchangeably) referred to as the "below 6GHz" band. A similar naming issue sometimes arises with FR2, although it differs from the Extremely High Frequency (EHF) band (30GHz-300GHz) defined as a "millimeter wave" band by the International Telecommunication Union (ITU), it is generally (interchangeably) referred to as the "millimeter wave" band in various documents and articles.

[0085] The frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR studies have identified the operating frequency bands of these mid-band frequencies as the frequency range name FR3 (7.125GHz-24.25GHz). Frequency bands falling within FR3 can inherit FR1 and / or FR2 characteristics, thus effectively extending the characteristics of FR1 and / or FR2 to mid-band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation above 52.6GHz. For example, three higher operating frequency bands have been identified as the frequency range names FR4a or FR4-1 (52.6GHz-71 GHz), FR4 (52.6GHz-114.25GHz), and FR5 (114.25GHz-300 GHz). Each of these higher frequency bands falls within the EHF band.

[0086] In light of the foregoing, unless otherwise explicitly stated, it should be understood that the terms "below 6 GHz" etc. (if used herein) can broadly refer to frequencies below 6 GHz, which may be within FR1 or include intermediate frequency band frequencies. Furthermore, unless otherwise explicitly stated, it should be understood that the terms "millimeter wave" etc. (if used herein) can broadly refer to frequencies including intermediate frequency band frequencies, which may be within FR2, FR4, FR4-a or FR4-1 and / or FR5, or may be within the EHF band.

[0087] Wireless communication system 100 can utilize licensed and unlicensed radio spectrum bands. For example, wireless communication system 100 can employ licensed assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology in unlicensed bands such as the 5 GHz Industrial, Scientific, and Medical (ISM) band. When operating in unlicensed radio spectrum bands, devices such as base station 105 and UE 115 can employ carrier sensing for collision detection and avoidance. In some examples, operation in unlicensed bands can be based on carrier aggregation configurations that combine component carriers operating in licensed bands (e.g., LAA). Operation in unlicensed spectrum can include other examples such as downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions.

[0088] Base station 105 or UE 115 may be equipped with multiple antennas that can be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communication, or beamforming. The antennas based on 105 or UE 115 may be located in one or more antenna arrays or antenna panels, and they can support MIMO operation or transmit beamforming or receive beamforming. For example, one or more base station antennas or antenna arrays may be located at the same antenna assembly (e.g., an antenna tower). In some examples, the antennas or antenna arrays associated with base station 105 may be located in different geographical locations. Base station 105 may have an antenna array with multiple rows and columns of antenna ports, which base station 105 can use to support beamforming for communication with UE 115. Similarly, UE 115 may have one or more antenna arrays that can support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support radio frequency beamforming for signals transmitted via the antenna ports.

[0089] Base station 105 or UE 115 can use MIMO communication to employ multipath signal propagation, increasing spectral efficiency by transmitting or receiving multiple signals via different spatial layers. These techniques can be termed spatial multiplexing. For example, transmitting devices can transmit the multiple signals via different antennas or different combinations of antennas. Similarly, receiving devices can receive the multiple signals via different antennas or different combinations of antennas. Each of the multiple signals can be referred to as a separate spatial stream, carrying bits associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers can be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include single-user MIMO (SU-MIMO) and multi-user MIMO (MU-MIMO), where in SU-MIMO, multiple spatial layers are transmitted to the same receiving device, and in MU-MIMO, multiple spatial layers are transmitted to multiple devices.

[0090] Beamforming (also known as spatial filtering, directional transmission, or directional reception) is a signal processing technique that can be used at a transmitting or receiving device (e.g., base station 105, UE 115) to shape or control antenna beams (e.g., transmit beams, receive beams) along a spatial path between the transmitting and receiving devices. Beamforming can be achieved by combining signals transmitted via antenna elements of an antenna array, such that some signals propagating in a specific orientation relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to signals transmitted via antenna elements can include applying amplitude offset, phase offset, or both to the signals carried by the antenna elements associated with the transmitting or receiving device. The adjustments associated with each antenna element can be specified by a beamforming weight set associated with a specific orientation (e.g., the antenna array of the transmitting or receiving device, or another orientation).

[0091] Base station 105 or UE 115 may use beam scanning technology as part of beamforming operations. For example, base station 105 may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Base station 105 may transmit several signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) multiple times in different directions. For example, base station 105 may transmit signals based on different beamforming weight sets associated with different transmission directions. Transmissions in different beam directions can be used to identify (e.g., by a transmitting device such as base station 105 or a receiving device such as UE 115) the beam direction that base station 105 will later transmit or receive.

[0092] Base station 105 may transmit signals (e.g., data signals associated with a specific receiving device) in a single beam direction (e.g., a direction associated with a receiving device such as UE 115). In some examples, the beam direction associated with transmission along a single beam direction may be determined based on signals transmitted in one or more beam directions. For example, UE 115 may receive one or more signals transmitted by base station 105 in different directions and may report to base station 105 an indication that UE 115 received signals with the highest signal quality or other acceptable signal quality.

[0093] In some examples, multiple beam directions can be used to perform transmissions by a device (e.g., base station 105 or UE 115), and the device can use a combination of digital precoding or radio frequency beamforming to generate a combined beam for transmission (e.g., from base station 105 to UE 115). UE 115 can report feedback indicating precoding weights for one or more beam directions, and this feedback can correspond to a configured number of beams across the system bandwidth or one or more subbands. Base station 105 can transmit reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)), which can be precoded or unprecoded. UE 115 can provide feedback for beam selection, which can be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., multi-panel type codebook, linear combination type codebook, port selection type codebook). Although these techniques are described with reference to signals transmitted in one or more directions by reference to base station 105, UE 115 may employ similar techniques to transmit signals multiple times in different directions (e.g., to identify beam directions for subsequent transmission or reception by UE 115) or to transmit signals in a single direction (e.g., to transmit data to a receiving device).

[0094] When receiving various signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) from base station 105, the receiving device (e.g., UE 115) can attempt multiple receiving configurations (e.g., directional listening). For example, the receiving device can attempt multiple receiving directions by: receiving via different antenna subarrays, processing the received signals according to different antenna subarrays, receiving according to different receiving beamforming weight sets (e.g., different directional listening weight sets) (where these weight sets are applied to signals received at multiple antenna elements of the antenna array), or processing the received signals according to different receiving beamforming weight sets (where these weight sets are applied to signals received at multiple antenna elements of the antenna array). Any of these methods can be referred to as "listening" according to different receiving configurations or receiving directions. In some examples, the receiving device can use a single receiving configuration to receive along a single beam direction (e.g., when receiving data signals). A single receiver configuration can be aligned based on a beam direction determined by listening in different receiver configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or otherwise acceptable signal quality based on listening in multiple beam directions).

[0095] In some aspects of this disclosure, UE 115 can use beamforming in mmW communication via one or more uplink beams and one or more downlink beams. UE communication manager 101 can receive multiple prediction models from base station 105 and can select one of these prediction models to determine one or more communication parameters for beamforming communication. In some cases, UE communication manager 101 can select a prediction model based on instructions from base station 105. In other cases, UE communication manager 101 can determine the output of each prediction model and select the model with the best or most suitable output. UE communication manager 101 can be... Figure 9 Example of the Communication Manager 910.

[0096] One or more of base stations 105 may include a base station communication manager 102. The base station communication manager 102 may identify multiple prediction models for multiple functions used for beamforming communication with the UE 115. The base station communication manager 102 may provide the multiple prediction models to the UE 115 to determine one or more beamforming parameters for beamforming communication. In some cases, the base station communication manager 102 may receive one or more measurement reports from the UE 115 to select one of the prediction models for a given function and provide the UE 115 with an indication of the selected model. The base station communication manager 102 may be... Figure 13 Example of a communication manager 1310.

[0097] Figure 2 Based on various aspects of this disclosure, examples of a portion of a wireless communication system 200 supporting machine learning model selection in beamforming communications are shown. In some examples, the wireless communication system 200 may implement aspects of the wireless communication system 100. In some examples, the wireless communication system 200 may include a UE 115-a and a base station 105-a, which may be reference... Figure 1 An example of UE 115 and base station 105 is described. UE 115-a and base station 105-a can communicate using beamforming communication, wherein UE 115-a sends uplink communication 205 to base station 105-a, and base station 105-a sends downlink communication 210 to UE 115-a.

[0098] In some cases, UE 115-a and base station 105-a can establish a connection, wherein uplink communication 205 uses an uplink beam and downlink communication 210 uses a downlink beam. A beam training process can be used to establish the uplink and downlink beams, wherein different base station beams 225 and different UE beams 230 can be tested and measured to identify the preferred beams for communication. In some cases, one or more functions associated with beamforming communication can be predicted using a predictive model to predict one or more parameters of the communication. In some cases, base station 105-a can generate multiple different predictive models 220 based on historical parameters identified to provide reliable communication, and provide some or all of the predictive models 220 to UE 115-a (e.g., in RRC signaling). For example, base station 105-a can use NN, AI or ML to generate prediction model 220, and when UE 115-a enters the coverage area of ​​base station 105-a, prediction model 220 can be provided to UE 115-a to improve the efficiency of determining appropriate parameters for communication.

[0099] In some cases, UE 115-a may perform measurements on one or more reference signals (e.g., in one or more SSBs) transmitted by base station 105-a, and UE 115-a may send a measurement report 215 to base station 105-a. In some cases, based on the measurement report, base station 105-a may choose which prediction models 220 to provide to UE 115-a, which prediction model should be used at UE 115-a, or any combination thereof. For example, a first prediction model may be more suitable when UE 115-a is located relatively close to base station 105-a, while a second prediction model may be more suitable when UE 115-a is located far from base station 105-a. Figure 3 An example of this situation is shown.

[0100] Figure 3 Based on various aspects of this disclosure, examples of a wireless communication system 300 supporting machine learning model selection in beamforming communications are shown. In some examples, the wireless communication system 300 may implement aspects of wireless communication systems 100 or 200. In some examples, the wireless communication system 300 may include a first UE 115-b, a second UE 115-a, and a base station 105-b, which may be reference... Figure 1 and Figure 2 Examples of UE 115 and base station 105 described.

[0101] In this example, the first UE 115-b and base station 105-b can communicate using beamforming communication 305 via associated uplink and downlink beams. The uplink and downlink beams can be established using a beam training process, where different base station beams 310 and different UE beams 315 can be tested and measured to identify the preferred beams for communication. Similarly, the second UE 115-c and base station 105-b can communicate using beamforming communication 320 via associated uplink and downlink beams, which are also established using a beam training process, where different base station beams 310 and different UE beams 325 can be tested and measured to identify the preferred beams for communication.

[0102] As discussed in this paper, one or more functions associated with beamforming communication can use predictive models to predict one or more parameters used for communication. In some cases, a particular function may have multiple predictive models, some of which may be better suited to certain channel conditions. Figure 3 In the example, the first UE 115-b can be at a first position 330, where a first prediction model for the first function is preferred, while the second UE 115-c can be at a second position 335, where a second prediction model for the first function is preferred. In this case, the base station 105-b can provide information that the UE 115 can use to select an appropriate prediction model.

[0103] In some cases, base station 105-b may provide each UE 115 with multiple prediction models for a first function, and then provide each UE 115 with an indication of which model to select (e.g., based on measurement reports from UE 115). For example, a first UE 115-b may measure a relatively high Reference Signal Received Power (RSRP), which may indicate that UE 115-b is relatively close to base station 105-b. Based on its proximity to base station 105-b, a first prediction model for the first function may be selected, such as a first prediction model based on the delay spread function of relative proximity to base station 105-b. Furthermore, in this case, a second UE 115-c may measure a relatively low RSRP, which may indicate that the second UE 115-c is relatively far from the base station, where a second prediction model for the delay function may provide better modeling for determining the delay spread parameters at the second UE 115-c. In some cases, base station 105-b can directly indicate model selection via model identifiers (e.g., index values ​​of models provided to UE 115 in RRC signaling, downlink control information (DCI), media access control (MAC) control elements (CE), or combinations thereof). In other cases, base station 105-b can provide each UE 115 with a preferred list of models, which can be used to select the appropriate model.

[0104] In other cases, each UE 115 can determine which predictive model to select by generating a functional output for each model and identifying which model provides the best output (where the model that provides the best output selected at UE 115). Alternatively, base station 105-b can provide a model selection function to UE 115, which UE 115 can use to select an appropriate model or switch between models based on changing UE 115 conditions (e.g., changed channel conditions due to mobility, changed location determined by positioning functions at UE 115, changed UE 115 orientation determined by a gyroscope (e.g., this may indicate that a different antenna panel is more suitable for communication), or any combination thereof).

[0105] Figure 4Based on various aspects of this disclosure, examples of a process flow 400 for selecting a machine learning model in beamforming communications are shown. In some examples, process flow 400 may implement aspects of wireless communication systems 100, 200, or 300. Process flow 400 may be implemented by a UE 115-d and a base station 105-c as described herein. In the following description of process flow 400, communication between UE 115-d and base station 105-c may be transmitted in a different order than the example order shown, or operations performed by UE 115-d and base station 105-c may be performed in a different order or at different times. Some operations may also be omitted from process flow 400, and other operations may be added to process flow 400.

[0106] At 405, base station 105-c can identify multiple different predictive models for various functions used in communication with the UE. In some cases, base station 105-c can collect data from communications with multiple UEs to generate predictive models for multiple functions using NN, AI, ML, or combinations thereof. For example, base station 105-a can generate predictive models about when the UE should be switched to a different base station and, in this case, which base station. In some cases, base station 105-c can generate multiple different predictive models for a specific function (e.g., base station 105-c can generate different predictive models for delay spread based on the UE's RSRP and location information). In some cases, predictive models can be generated for many different functions such as: beam prediction (e.g., transmit / receive beams for communication), channel attribute prediction (e.g., what the delay spread of communication is), connectivity prediction (e.g., when to switch between base stations, which base station to receive the switch, etc.).

[0107] At 410, base station 105-c can send a prediction model to UE 115-d. In some cases, the prediction model can be sent to UE 115-c in RRC signaling. Alternatively or concurrently, the prediction model can be sent to UE 115-d in one or more broadcast or unicast communications. At 415, base station 105-c can send one or more reference signal transmissions (e.g., in one or more SSBs) that UE 115-d can use to perform channel measurements. At 420, UE 115-d can perform reference signal measurements on the reference signals sent by base station 105-c, and in some cases, can measure reference signals from one or more other base stations that may be close to UE 115-d. At 425, UE 115-d can send a measurement report to base station 105-c, which includes the values ​​of various reference signal measurements performed at UE 115-d. In this example, UE 115-d can rely on base station 105-c for model selection and indication.

[0108] At 430, base station 105-c can select a model for communication with UE 115-d. This selection can be based on one or more measurement reports received from UE 115-d. At 435, base station 105-c can send an indication of the selected model to UE 115-d. In some cases, the prediction models provided to UE 115-d may each have an associated identifier (e.g., an index value provided when the prediction model is transmitted to UE 115-d), and the indication of the selected model can provide an identifier associated with the selected model. In other cases, the indication of the selected model can be provided through a priority list of prediction models, which UE 115-d can use to determine which model to use.

[0109] At 440, UE 115-d can determine one or more beam parameters based on a selected prediction model. In some cases, the selected prediction model can be used to determine the values ​​(e.g., initial values) for one or more beamforming parameters. Furthermore, in some cases, multiple different models can be used for the same function (e.g., beam prediction function identifying transmit / receive beams for communication), and these models can be provided to UE 115-d by base station 105-c. These different models for the same function can be used based on the specific channel conditions or location of UE 115-d. At 445, UE 115-d and base station 105-c can perform uplink and downlink communication based on the beamforming parameters provided by the one or more models.

[0110] Optionally, at 450, UE 115-d may perform further reference signal measurements on the reference signal transmitted by base station 105-c (e.g., a reference signal provided via downlink communication or transmitted in the SSB, etc.). At 455, UE 115-d may optionally send additional measurement reports to base station 105-c. In some cases, base station 105-c may use measurement reports with further data points from NN / AI / ML technologies to adjust the prediction model. Furthermore, at 460, base station 105-c may optionally use the further measurement reports to select an updated model for UE communication. For example, if the further measurement report indicates that the location of UE 115-d has changed, base station 105-c may determine that a different model for delay extension is more suitable. At 465, base station 105-c may send an indication of the selected model to UE 115-d, which UE 115-d may use for subsequent communication.

[0111] Figure 5 Based on various aspects of this disclosure, examples of a process flow 500 for selecting a machine learning model in beamforming communications are shown. In some examples, process flow 500 may implement aspects of wireless communication systems 100, 200, or 300. Process flow 500 may be implemented by a UE 115-e and a base station 105-d as described herein. In the following description of process flow 500, communication between UE 115-e and base station 105-d may be transmitted in a different order than the example order shown, or operations performed by UE 115-e and base station 105-d may be performed in a different order or at different times. Some operations may also be omitted from process flow 500, and other operations may be added to process flow 500.

[0112] At point 505, base station 105-d can identify multiple different prediction models for multiple different functions used in communication with the UE, based on techniques such as those discussed herein. At point 510, base station 105-d can transmit the prediction models to UE 115-e. In some cases, the prediction models can be transmitted to UE 115-e in RRC signaling. Alternatively or separately, the prediction models can be transmitted to UE 115-e in one or more broadcast or unicast communications. At point 515, base station 105-d can transmit one or more reference signal transmissions (e.g., in one or more SSBs) that UE 115-e can use for channel measurements.

[0113] In this example, UE 115-e can choose which model to use, and at 520, it can compute an output function for each predictive model provided by base station 105-e. At 525, UE 115-e can select the model for communication based on which model yields the best or most suitable result when computing the output function. In some cases, predictive models and a priority list that can be used when selecting the model to use can be provided to UE 115-e.

[0114] At 530, UE 115-e can determine one or more beam parameters based on a selected prediction model. In some cases, the selected prediction model can be used to determine the values ​​(e.g., initial values) for one or more beamforming parameters. Furthermore, in some cases, multiple different models can be used for the same function (e.g., beam prediction function identifying transmit / receive beams for communication), and these models can be provided to UE 115-e by base station 105-d. These different models for the same function can be used based on the specific channel conditions or location of UE 115-e. At 535, UE 115-e and base station 105-d can perform uplink and downlink communication based on the beamforming parameters provided by the one or more models.

[0115] Optionally, at 540, base station 105-d can identify a model selection function for switching between different prediction models. At 545, base station 105-d can send the model selection function to UE 115-e. Although the operations at 540 and 545 are shown as occurring after uplink and downlink communication, in some cases, such a model selection function can be provided together with the prediction model provided by base station 105-d to UE 115-e. At 550, UE 115-e can select a new model based on the model selection function, and then use the new model for subsequent communication. In some cases, UE 115-e can provide one or more measurements as input to the model selection function, which can output an updated model for UE communication. For example, if measurements indicate that the location of UE 115-e has changed, the model selection function can determine that a different model is more suitable for delay extension and can output an indication for UE 115-e to switch to the associated model. Such a technique can update the UE's model to appropriately match the current channel environment, thereby allowing the UE 115-e to take into account changing channel environments (e.g., due to the movement of the UE 115-e).

[0116] Figure 6According to various aspects of this disclosure, a block diagram 600 of a device 605 supporting machine learning model selection in beamforming communications is shown. Device 605 may be an example of some aspects of a UE 115 as described herein. Device 605 may include a receiver 610, a communications manager 615, and a transmitter 620. Device 605 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0117] Receiver 610 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, and information related to the selection of machine learning models in beamforming communications). The information can be transmitted to other components of the device 605. Receiver 610 can be a reference... Figure 9 Examples of some aspects of the transceiver 920 described. The receiver 610 may utilize a single antenna or a collection of antennas.

[0118] The communication manager 615 may support wireless communication at the UE according to examples disclosed herein. For example, the communication manager 615 may be configured or otherwise support: a unit for receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station. The communication manager 615 may also be configured or otherwise support: a unit for communicating with the base station using beamforming communication based on one or more parameters, said one or more parameters being based on a prediction model in the one or more prediction models for the first function of beamforming communication with the base station.

[0119] Communication manager 615 can receive from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; select a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; determine one or more parameters for beamforming communication based on the first prediction model for the first function; and communicate with the base station using beamforming communication based on the one or more determined parameters. Communication manager 615 may be an example of some aspects of communication manager 910 described herein.

[0120] As described herein, the communication manager 615 can be implemented to achieve one or more potential aspects. Compared to the use of multiple iterations of beamforming parameters to tune various parameters, one implementation allows device 605 to determine beamforming parameters more efficiently and accurately, which allows for efficient identification of parameters and communications. Furthermore, the implementation can provide device 605 with lower latency and power consumption associated with operations such as identifying appropriate beamforming parameters and performing beamforming communications.

[0121] The communication manager 615 or its sub-components may be implemented in hardware, in code executed by a processor (e.g., software or firmware), or in any combination thereof. When implemented in code executed by a processor, a general-purpose processor, DSP, application-specific integrated circuit (ASIC), FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any combination thereof designed to perform the functions described in this disclosure may perform the functions of the communication manager 615 or its sub-components.

[0122] The communication manager 615 or its sub-components may be physically distributed in multiple locations, including as part of a distribution that performs functions at different physical locations via one or more physical components. In some examples, the communication manager 615 or its sub-components may be separate and distinct components, according to various aspects of this disclosure. In some examples, the communication manager 615 or its sub-components may be combined with one or more other hardware components, including but not limited to: input / output (I / O) components, transceivers, network servers, another computing device, one or more other components or combinations thereof described in this disclosure.

[0123] Transmitter 620 can transmit signals generated by other components of device 605. In some examples, transmitter 620 can be co-located with receiver 610 in a transceiver module. For example, transmitter 620 can be a reference... Figure 9 Examples of some aspects of the described transceiver 920. The transmitter 620 may utilize a single antenna or a collection of antennas.

[0124] Figure 7 According to various aspects of this disclosure, a block diagram 700 of a device 705 supporting machine learning model selection in beamforming communications is shown. Device 705 may be an example of some aspects of device 605 or UE 115 as described herein. Device 705 may include a receiver 710, a communications manager 715, and a transmitter 740. Device 705 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0125] Receiver 710 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, and information related to the selection of machine learning models in beamforming communications). The information can be transmitted to other components of the device 705. Receiver 710 can be a reference... Figure 9Examples of some aspects of the transceiver 920 described. The receiver 710 may utilize a single antenna or a collection of antennas.

[0126] Communication manager 715 may be an example of some aspects of communication manager 615 as described herein. Communication manager 715 may include model recognition manager 720, model selection manager 725, beamforming manager 730, and beamforming communication manager 735. Communication manager 715 may be an example of some aspects of communication manager 910 as described herein.

[0127] Communication manager 715 may support wireless communication at the UE according to examples disclosed herein. For example, model identification manager 720 may be configured or otherwise supported as a unit for receiving from a base station one or more predictive models for at least a first function associated with beamforming communication with the base station. Beamforming communication manager 735 may be configured or otherwise supported as a unit for communicating with the base station using beamforming communication based on one or more parameters, said one or more parameters being based on a predictive model in the one or more predictive models for the first function of beamforming communication with the base station.

[0128] The model recognition manager 720 can receive from the base station a set of predictive models for at least a first function associated with beamforming communication with the base station.

[0129] The model selection manager 725 can select a first prediction model from the set of prediction models for the first function of beamforming communication with the base station.

[0130] The beamforming manager 730 can determine one or more parameters for communication used in beamforming based on a first prediction model used for the first function.

[0131] The beamforming communication manager 735 can communicate with the base station using beamforming communication based on one or more of the determined parameters.

[0132] Transmitter 740 can transmit signals generated by other components of device 705. In some examples, transmitter 740 can be co-located with receiver 710 in a transceiver module. For example, transmitter 740 can be a reference... Figure 9 Examples of some aspects of the described transceiver 920. The transmitter 740 may utilize a single antenna or a collection of antennas.

[0133] Figure 8According to various aspects of this disclosure, a block diagram 800 of a communication manager 805 supporting machine learning model selection in beamforming communication is shown. The communication manager 805 may be an example of aspects of the communication manager 615, communication manager 715, or communication manager 910 described herein. The communication manager 805 may include a model identification manager 810, a model selection manager 815, a beamforming manager 820, a beamforming communication manager 825, a measurement manager 830, and a measurement report manager 835. Each of these modules may communicate directly or indirectly with each other (e.g., via one or more buses).

[0134] Communication manager 805 may support wireless communication at the UE according to examples disclosed herein. For example, model identification manager 810 may be configured or otherwise supported as a unit for receiving from a base station one or more predictive models for at least a first function associated with beamforming communication with the base station. Beamforming communication manager 825 may be configured or otherwise supported as a unit for communicating with the base station using beamforming communication based on one or more parameters, said one or more parameters being based on a predictive model in the one or more predictive models for the first function of beamforming communication with the base station.

[0135] The model identification manager 810 can receive from the base station a set of predictive models for at least a first function associated with beamforming communication with the base station. In some cases, the UE receives from the base station a priority list of predictive models for each function in the set of functions to be used at the UE for beamforming communication.

[0136] The model selection manager 815 can select a first prediction model from a set of prediction models for a first function of beamforming communication with a base station. In some examples, the model selection manager 815 can receive an indication of the first prediction model from the base station. In some examples, the model selection manager 815 can select the first prediction model for the first function in response to an indication from the base station.

[0137] In some examples, the model selection manager 815 can determine whether the first predictive model accurately predicts the first function. In some examples, the model selection manager 815 can send an instruction to the base station based on this determination.

[0138] In some examples, the model selection manager 815 may compute the results of the first function for each predictive model in the set of predictive models to generate a set of results for the first function. In some examples, the model selection manager 815 may determine that the first result in the set of results for the first function is the optimal result in the set of results, wherein the first result is associated with the first predictive model. In some examples, the model selection manager 815 may select the first predictive model based on this determination.

[0139] In some examples, the model selection manager 815 can monitor the prediction quality from the first prediction model within the set of predictions. In some examples, the model selection manager 815 can switch to a second prediction model for the first function based on the prediction quality from the first prediction model dropping below a threshold quality.

[0140] In some examples, the model selection manager 815 may receive from the base station an instruction to switch to a second prediction model in the set of prediction models in response to the one or more measurement reports. In some examples, the model selection manager 815 may receive from the base station a model selection function for selecting a different prediction model. In some examples, the model selection manager 815 may switch from a first prediction model to a second prediction model in the set of prediction models for use in a first function, based on the model selection function. In some cases, the prediction quality is determined to have fallen below a threshold quality because the results based on the first prediction model do not match the observations based on one or more measurements at the UE. In some cases, the prediction quality is determined to have fallen below a threshold quality based on one or more of the following: the number of consecutive incorrect predictions exceeds a threshold, the number of incorrect predictions in the set of past predictions exceeds a threshold, or any combination thereof.

[0141] The beamforming manager 820 can determine one or more parameters for beamforming communication based on a first prediction model used for the first function. In some examples, the beamforming manager 820 can determine one or more updated parameters for further beamforming communication based on a second prediction model used for the first function.

[0142] The beamforming communication manager 825 can communicate with the base station using beamforming communication based on one or more determined parameters. In some examples, the beamforming communication manager 825 can communicate with the base station using beamforming communication based on one or more updated parameters.

[0143] Measurement manager 830 can measure one or more channel conditions between the UE and the base station. In some examples, measurement manager 830 can measure one or more reference signals received from the base station and one or more other base stations in one or more synchronization signal blocks (SSBs). In some examples, measurement manager 830 can measure one or more channel conditions associated with beamforming communication, one or more internal states of the UE, or a combination thereof, to identify a set of measurement values. In some examples, measurement manager 830 can provide this set of measurement values ​​as input to a model selection function, and wherein a handover is performed in response to the associated output of the model selection function based on the set of measurement values.

[0144] The measurement report manager 835 can send a measurement report indicating one or more channel conditions to the base station in response to a measurement. In some examples, the measurement report manager 835 can send one or more measurement reports to the base station based on measurements associated with beamforming that uses a first prediction model for a first function. In some cases, the measurement report further indicates the location information of the UE.

[0145] Figure 9 According to various aspects of this disclosure, a diagram of a system 900 including device 905 is shown, wherein device 905 supports machine learning model selection in beamforming communications. Device 905 may be an example of device 605, device 705, or UE 115 as described herein, or a component including device 605, device 705, or UE 115. Device 905 may include components for bidirectional voice and data communications, including components for transmitting communications and components for receiving communications, including a communication manager 910, an I / O controller 915, a transceiver 920, an antenna 925, a memory 930, and a processor 940. These components may communicate electrically via one or more buses (e.g., bus 945).

[0146] The communication manager 910 may support wireless communication at the UE according to examples disclosed herein. For example, the communication manager 910 may be configured or otherwise support: a unit for receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station. The communication manager 910 may be configured or otherwise support: a unit for communicating with the base station using beamforming communication based on one or more parameters, said one or more parameters being based on a prediction model in the one or more prediction models for the first function of beamforming communication with the base station.

[0147] The communication manager 910 can receive from the base station a set of prediction models for at least a first function associated with beamforming communication with the base station, select a first prediction model from the set of prediction models for the first function of beamforming communication with the base station, determine one or more parameters for beamforming communication based on the first prediction model for the first function, and communicate with the base station using beamforming communication based on the one or more determined parameters.

[0148] As described herein, the communication manager 910 can be implemented to achieve one or more potential aspects. Compared to the use of multiple iterations of beamforming parameters to tune various parameters, one implementation allows device 905 to determine beamforming parameters more efficiently and accurately, which allows for efficient identification of parameters and communications. Furthermore, the implementation can provide device 905 with lower latency and power consumption associated with operations such as identifying appropriate beamforming parameters and performing beamforming communications.

[0149] The I / O controller 915 can manage input and output signals for device 905. The I / O controller 915 can also manage peripheral devices not integrated into device 905. In some cases, the I / O controller 915 can represent a physical connection or port to an external peripheral device. In some cases, the I / O controller 915 can utilize, for example... This can be an operating system such as a modem, keyboard, mouse, touchscreen, or similar device, or an interaction with such a device. In some cases, the I / O controller 915 may be implemented as part of the processor. In some cases, the user may interact with the device 905 via the I / O controller 915 or via hardware components controlled by the I / O controller 915.

[0150] Transceiver 920 can communicate bidirectionally via one or more antennas, a wired link, or a wireless link, as described above. For example, transceiver 920 can represent a wireless transceiver capable of bidirectional communication with another wireless transceiver. Transceiver 920 may also include a modem for modulating packets, providing modulated packets to the antenna for transmission, and demodulating packets received from the antenna.

[0151] In some cases, the wireless device may include a single antenna 925. However, in other cases, the device may have more than one antenna 925, which are capable of transmitting or receiving multiple wireless transmissions simultaneously.

[0152] Memory 930 may include RAM and ROM. Memory 930 may store computer-readable, computer-executable code 935 containing instructions that, when executed, cause processor 910 to perform the various functions described herein. In some cases, specifically, memory 930 may contain a BIOS, which controls basic hardware or software operations (e.g., interaction with peripheral components or devices).

[0153] Processor 940 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic units, discrete hardware units, or any combination thereof). In some cases, processor 940 may be configured to use a memory controller to operate a memory array. In other cases, the memory controller may be integrated into processor 940. Processor 940 may be configured to execute computer-readable instructions stored in memory (e.g., memory 930) to cause device 905 to perform various functions (e.g., functions or tasks supporting machine learning model selection in beamforming communications).

[0154] Code 935 may include instructions for implementing various aspects of this disclosure, including instructions for supporting wireless communication. Code 935 may be stored in a non-transitory computer-readable medium such as system memory or other types of memory. In some cases, code 935 may not be executed directly by processor 940, but may instead cause a computer (e.g., when compiled and executed) to perform the functions described herein.

[0155] Figure 10 According to various aspects of this disclosure, a block diagram 1000 of a device 1005 supporting machine learning model selection in beamforming communications is shown. Device 1005 may be an example of some aspects of a base station 105 as described herein. Device 1005 may include a receiver 1010, a communication manager 1015, and a transmitter 1020. Device 1005 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0156] Receiver 1010 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, and information related to the selection of machine learning models in beamforming communications). The information can be transmitted to other components of the device 1005. Receiver 1010 can be a reference... Figure 13 Examples of some aspects of the transceiver 1320 described. The receiver 1010 may utilize a single antenna or a collection of antennas.

[0157] The communication manager 1015 may support wireless communication at a base station according to examples disclosed herein. For example, the communication manager 1015 may be configured or otherwise support: a unit for transmitting to a first UE one or more predictive models for at least a first function associated with beamforming communication with the first UE, the one or more predictive models being based on identifying the first UE as being for beamforming communication with the base station. The communication manager 1015 may also be configured or otherwise support: a unit for communicating with the first UE using beamforming communication parameters based on the one or more predictive models.

[0158] The communication manager 1015 can identify a set of prediction models for at least a first function associated with beamforming communication between a base station and a UE. Based on identifying a first UE as being used for beamforming communication with the base station, the communication manager 1015 sends the set of prediction models to the first UE and communicates with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first prediction model in the set of prediction models. The communication manager 1015 may be an example of some aspects of the communication manager 1310 described herein.

[0159] The communication manager 1015 or its sub-components may be implemented in hardware, in processor-executable code (e.g., software or firmware), or in any combination thereof. When implemented in processor-executable code, a general-purpose processor, DSP, application-specific integrated circuit (ASIC), FPGA, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any combination thereof designed to perform the functions described in this disclosure may perform the functions of the communication manager 1015 or its sub-components.

[0160] The communication manager 1015 or its sub-components may be physically distributed in multiple locations, including as part of a distribution that performs functions at different physical locations via one or more physical components. In some examples, the communication manager 1015 or its sub-components may be separate and distinct components, according to various aspects of this disclosure. In some examples, the communication manager 1015 or its sub-components may be combined with one or more other hardware components, including but not limited to: input / output (I / O) components, transceivers, network servers, another computing device, one or more other components or combinations thereof described in this disclosure.

[0161] Transmitter 1020 can transmit signals generated by other components of device 1005. In some examples, transmitter 1020 can be co-located with receiver 1010 in a transceiver module. For example, transmitter 1020 can be a reference... Figure 13 Examples of some aspects of the transceiver 1320 described. The transmitter 1020 may utilize a single antenna or a collection of antennas.

[0162] Figure 11 According to various aspects of this disclosure, a block diagram 1100 of a device 1105 supporting machine learning model selection in beamforming communications is shown. Device 1105 may be an example of aspects of device 1005 as described herein or base station 105. Device 1105 may include receiver 1110, communication manager 1115, and transmitter 1135. Device 1105 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0163] Receiver 1110 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, and information related to the selection of machine learning models in beamforming communications). The information can be transmitted to other components of device 1105. Receiver 1110 can be a reference... Figure 13 Examples of some aspects of the transceiver 1320 described. The receiver 1110 may utilize a single antenna or a collection of antennas.

[0164] Communication manager 1115 may be an example of some aspects of communication manager 1015 as described herein. Communication manager 1115 may include model selection manager 1120, model identification manager 1125, and beamforming communication manager 1130. Communication manager 1115 may be an example of some aspects of communication manager 1310 as described herein.

[0165] Communication manager 1115 may support wireless communication at a base station according to examples disclosed herein. For example, model identification manager 1125 may be configured or otherwise supported as follows: a unit for sending to a first UE one or more predictive models for at least a first function associated with beamforming communication with the first UE, the one or more predictive models being based on identifying the first UE as being for beamforming communication with the base station. Beamforming communication manager 1130 may be configured or otherwise supported as follows: a unit for communicating with the first UE using beamforming communication parameters based on the one or more predictive models.

[0166] The model selection manager 1120 can identify a set of predictive models for at least a first function associated with beamforming communication between the base station and the UE.

[0167] The model identification manager 1125 can send a set of predictive models to the first UE based on identifying the first UE as a communication for beamforming with the base station.

[0168] The beamforming communication manager 1130 can communicate with the first UE using beamforming communication based on one or more parameters of a first function, wherein one or more parameters of the first function are determined based on a first prediction model in a set of prediction models.

[0169] Transmitter 1135 can transmit signals generated by other components of device 1105. In some examples, transmitter 1135 can be co-located with receiver 1110 in a transceiver module. For example, transmitter 1135 can be a reference... Figure 13 Examples of some aspects of the transceiver 1320 described. The transmitter 1135 may utilize a single antenna or a collection of antennas.

[0170] Figure 12 According to various aspects of this disclosure, a block diagram 1200 of a communication manager 1205 supporting machine learning model selection in beamforming communication is shown. The communication manager 1205 may be an example of aspects of the communication manager 1015, communication manager 1115, or communication manager 1310 described herein. The communication manager 1205 may include a model selection manager 1210, a model identification manager 1215, a beamforming communication manager 1220, and a measurement report manager 1225. Each of these modules may communicate directly or indirectly with each other (e.g., via one or more buses).

[0171] Communication manager 1205 may support wireless communication at a base station according to examples disclosed herein. Model identification manager 1215 may be configured or otherwise supported as a unit for sending to a first UE one or more predictive models for at least a first function associated with beamforming communication with the first UE, the one or more predictive models being based on identifying the first UE as being for beamforming communication with the base station. Beamforming communication manager 1220 may be configured or otherwise supported as a unit for communicating with the first UE using beamforming communication parameters based on the one or more predictive models.

[0172] Model selection manager 1210 can identify a set of predictive models for at least a first function associated with beamforming communication between a base station and a UE. In some examples, model selection manager 1210 can select a predictive model from the set of predictive models for beamforming communication with the first UE based on a measurement report. In some examples, model selection manager 1210 can send an instruction for a first predictive model to the first UE.

[0173] In some examples, the model selection manager 1210 may select a first predictive model from the set of predictive models based on the results of each predictive model in the set of predictive models used for the first function. In some examples, the model selection manager 1210 may configure a threshold prediction quality at the first UE to initiate a switch between predictive models. In some examples, the model selection manager 1210 may determine, based on one or more measurement reports, that the first UE will switch to a second predictive model in the set of predictive models. In some examples, the model selection manager 1210 may send an instruction to the UE to switch to the second predictive model.

[0174] In some examples, the model selection manager 1210 can send a model selection function to the first UE for the UE to select different prediction models from a set of prediction models. In some cases, the threshold quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in the set of past predictions exceeding a threshold, or any combination thereof.

[0175] Model identification manager 1215 may send to the first UE a set of predictive models based on which the first UE is identified as being used for beamforming communication with the base station. In some examples, model identification manager 1215 may send a priority list of predictive models for each function in a set of functions associated with beamforming communication at the first UE.

[0176] In some examples, the model identification manager 1215 may receive an indication from the first UE regarding whether the first predictive model accurately predicts the first function. In some examples, the model identification manager 1215 may update the model used to determine, based on measurement reports, which predictive model in the set to instruct the UE.

[0177] The beamforming communication manager 1220 can communicate with the first UE using beamforming communication based on one or more parameters of a first function, wherein one or more parameters of the first function are determined based on a first prediction model in a set of prediction models.

[0178] Measurement report manager 1225 can receive measurement reports from the first UE, which indicate channel conditions for one or more measurements at the first UE. In some examples, measurement report manager 1225 can receive one or more measurement reports from the first UE, which indicate measurements associated with beamforming communication using a first prediction model for a first function. In some cases, the measurement report further indicates location information of the first UE, wherein the selection is further based on that location information.

[0179] Figure 13 According to various aspects of this disclosure, a diagram of a system 1300 including device 1305 is shown, wherein device 1305 supports machine learning model selection in beamforming communications. Device 1305 may be an example of device 1005, device 1105, or base station 105 as described herein, or a component including device 1005, device 1105, or base station 105. Device 1305 may include components for bidirectional voice and data communications, including components for transmitting communications and components for receiving communications, including a communication manager 1310, a network communication manager 1315, a transceiver 1320, an antenna 1325, a memory 1330, a processor 1340, and an inter-station communication manager 1345. These components may communicate electrically via one or more buses (e.g., bus 1350).

[0180] Communication manager 1310 may support wireless communication at a base station according to examples disclosed herein. For example, communication manager 1310 may be configured or otherwise support: a unit for transmitting to a first UE one or more predictive models for at least a first function associated with beamforming communication with the first UE, the one or more predictive models being based on identifying the first UE as being for beamforming communication with the base station. Communication manager 1310 may be configured or otherwise support: a unit for communicating with the first UE using beamforming communication parameters based on the one or more predictive models.

[0181] The communication manager 1310 can identify a set of prediction models for at least a first function associated with beamforming communication between a base station and a UE, send the set of prediction models to the first UE based on identifying the first UE as being for beamforming communication with the base station, and communicate with the first UE using beamforming communication based on one or more parameters of the first function, wherein one or more parameters of the first function are determined based on the first prediction model in the set of prediction models.

[0182] The network communication manager 1315 can manage communication with the core network (e.g., via one or more wired backhaul links). For example, the network communication manager 1315 can manage the transmission of data communication for client devices (e.g., one or more UEs 115).

[0183] Transceiver 1320 can communicate bidirectionally via one or more antennas, a wired link, or a wireless link, as described above. For example, transceiver 1320 can represent a wireless transceiver capable of bidirectional communication with another wireless transceiver. Transceiver 1320 may also include a modem for modulating packets, providing modulated packets to the antenna for transmission, and demodulating packets received from the antenna.

[0184] In some cases, the wireless device may include a single antenna 1325. However, in other cases, the device may have more than one antenna 1325, which are capable of transmitting or receiving multiple wireless transmissions simultaneously.

[0185] Memory 1330 may include RAM, ROM, or a combination thereof. Memory 1330 may store computer-readable code 1335 including instructions that, when executed by a processor (e.g., processor 1340), cause the device to perform the various functions described herein. In some cases, specifically, memory 1330 may contain a BIOS, which controls basic hardware or software operations (e.g., interaction with peripheral components or devices).

[0186] Processor 1340 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic units, discrete hardware units, or any combination thereof). In some cases, processor 1340 may be configured to operate a memory array using a memory controller. In some cases, the memory controller may be integrated into processor 1340. Processor 1340 may be configured to execute computer-readable instructions stored in memory (e.g., memory 1330) to cause device 1305 to perform various functions (e.g., functions or tasks supporting machine learning model selection in beamforming communications).

[0187] Inter-site communication manager 1345 can manage communication with other base stations 105 and may include a controller or scheduler for cooperating with other base stations 105 to control communication with UE 115. For example, inter-site communication manager 1345 can coordinate the scheduling of transmissions to UE 115 to implement various interference mitigation techniques such as beamforming or joint transmission. In some examples, inter-site communication manager 1345 may provide an X2 interface in LTE / LTE-A wireless communication network technology to facilitate communication between base stations 105.

[0188] Code 1335 may include instructions for implementing various aspects of this disclosure, including instructions for supporting wireless communication. Code 1335 may be stored in a non-transitory computer-readable medium such as system memory or other types of memory. In some cases, code 1335 may not be executed directly by processor 1340, but may instead cause a computer (e.g., when compiled and executed) to perform the functions described herein.

[0189] Figure 14 Based on various aspects of this disclosure, a flowchart depicting a method 1400 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1400 can be implemented by a UE or its components as described herein. For example, the operation of method 1400 can be implemented by, as referenced... Figures 6 to 9 The UE 115 described herein is used to perform this function. In some examples, the UE may execute a set of instructions to control the functional units of the UE to perform the described function. Alternatively or concurrently, the UE may use special purpose hardware to perform aspects of the described function.

[0190] At 1405, the method may include: receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station. The operation at 1405 may be performed according to examples disclosed herein. In some examples, aspects of the operation at 1405 may be derived from, as referenced... Figures 6 to 9 The described model recognition manager is used to perform this.

[0191] At 1410, the method may include: communicating with a base station using beamforming communication based on one or more parameters, said one or more parameters being based on a prediction model in one or more prediction models for a first function of beamforming communication with the base station. The operation of 1410 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1410 may be as described in reference... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0192] Figure 15According to various aspects of this disclosure, a flowchart depicting a method 1500 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1500 can be implemented by a UE 115 or its components as described herein. For example, the operation of method 1500 can be implemented by, as referenced... Figures 6 to 9 The communication manager described herein is used for execution. In some examples, the UE can execute a set of instructions to control the UE's functional units to perform the functions described below. Alternatively or concurrently, the UE can use special-purpose hardware to perform aspects of the functions described below.

[0193] At point 1505, the UE can receive from the base station a set of prediction models for at least a first function associated with beamforming communication with the base station. The operation at point 1505 can be performed according to the method described herein. In some examples, aspects of the operation at point 1505 can be derived from, as referenced... Figures 6 to 9 The described model recognition manager is used to perform this.

[0194] At point 1510, the UE can select a first prediction model from the set of prediction models for a first function of beamforming communication with the base station. The operation at 1510 can be performed according to the method described herein. In some examples, aspects of the operation at 1510 can be determined by reference to... Figures 6 to 9 The model selection manager described is used to perform this.

[0195] At point 1515, the UE can determine one or more parameters for beamforming communication based on a first prediction model used for the first function. The operation at point 1515 can be performed according to the method described herein. In some examples, aspects of the operation at point 1515 can be determined by reference to... Figures 6 to 9 The described beamforming manager is used to perform this.

[0196] At point 1520, the UE can communicate with the base station using beamforming communication based on one or more defined parameters. The operation at point 1520 can be performed according to the method described herein. In some examples, aspects of the operation at point 1520 can be determined as described in reference... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0197] Optionally, at 1525, the UE may send one or more measurement reports to the base station based on measurements associated with beamforming communication that uses the first prediction model for the first function. The operation at 1525 can be performed according to the methods described herein. In some examples, aspects of the operation at 1525 may be determined by reference to... Figures 6 to 9 The described measurement report manager is used to perform this.

[0198] Optionally, at 1530, the UE can receive from the base station an indication for switching to a second prediction model from a set of prediction models in response to one or more measurement reports. The operation at 1530 can be performed according to the method described herein. In some examples, aspects of the operation at 1530 can be determined by referring to... Figures 6 to 9 The model selection manager described is used to perform this.

[0199] Optionally, at 1535, the UE may determine one or more updated parameters for further beamforming communication based on a second prediction model used for the first function. The operation at 1535 can be performed according to the method described herein. In some examples, aspects of the operation at 1535 may be determined by reference to... Figures 6 to 9 The described beamforming manager is used to perform this.

[0200] Optionally, at 1540, the UE can communicate with the base station using beamforming communication based on one or more updated parameters. The operation at 1540 can be performed according to the methods described herein. In some examples, aspects of the operation at 1540 can be determined by reference to... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0201] Figure 16 Based on various aspects of this disclosure, a flowchart depicting a method 1600 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1600 can be implemented by a UE 115 or its components as described herein. For example, the operation of method 1600 can be implemented by, as referenced... Figures 6 to 9 The communication manager described herein is used for execution. In some examples, the UE can execute a set of instructions to control the UE's functional units to perform the functions described below. Alternatively or concurrently, the UE can use special-purpose hardware to perform aspects of the functions described below.

[0202] At point 1605, the UE can measure one or more channel conditions between the UE and the base station. The operation at point 1605 can be performed according to the method described herein. In some examples, aspects of the operation at point 1605 can be described as referenced... Figures 6 to 9 The described measurement manager is used to perform this.

[0203] At 1610, the UE may, in response to a measurement, send a measurement report to the base station indicating the one or more channel conditions. The operation of 1610 can be performed according to the method described herein. In some examples, aspects of the operation of 1610 may be as described in reference... Figures 6 to 9 The described measurement report manager is used to perform this.

[0204] At point 1615, the UE can receive from the base station a set of prediction models for at least a first function associated with beamforming communication with the base station. The operation at 1615 can be performed according to the method described herein. In some examples, aspects of the operation at 1615 can be derived from, as referenced... Figures 6 to 9 The described model recognition manager is used to perform this.

[0205] At point 1620, the UE can receive an indication of the first prediction model from the base station. The operation at point 1620 can be performed according to the method described herein. In some examples, aspects of the operation at point 1620 can be derived as described in reference... Figures 6 to 9 The model selection manager described is used to perform this.

[0206] At point 1625, the UE may, in response to an instruction from the base station, select a first prediction model for a first function. The operation at point 1625 can be performed according to the method described herein. In some examples, aspects of the operation at point 1625 may be determined by reference to... Figures 6 to 9 The model selection manager described is used to perform this.

[0207] At 1630, the UE can determine one or more parameters for beamforming communication based on a first prediction model used for the first function. The operation at 1630 can be performed according to the method described herein. In some examples, aspects of the operation at 1630 can be determined as described in reference... Figures 6 to 9 The described beamforming manager is used to perform this.

[0208] At point 1635, the UE can communicate with the base station using beamforming communication based on one or more defined parameters. The operation at point 1635 can be performed according to the method described herein. In some examples, aspects of the operation at point 1635 can be determined by reference to... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0209] Figure 17 Based on various aspects of this disclosure, a flowchart depicting a method 1700 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1700 can be implemented by a UE 115 or its components as described herein. For example, the operation of method 1700 can be implemented by, as referenced... Figures 6 to 9 The communication manager described herein is used for execution. In some examples, the UE can execute a set of instructions to control the UE's functional units to perform the functions described below. Alternatively or concurrently, the UE can use special-purpose hardware to perform aspects of the functions described below.

[0210] At 1705, the UE can receive from the base station a set of prediction models for at least a first function associated with beamforming communication with the base station. The operation at 1705 can be performed according to the method described herein. In some examples, aspects of the operation at 1705 can be derived from, as referenced... Figures 6 to 9 The described model recognition manager is used to perform this.

[0211] At 1710, the UE can compute the result of the first function for each prediction model in the set of prediction models to generate a set of results for the first function. The operation at 1710 can be performed according to the method described herein. In some examples, aspects of the operation at 1710 can be derived as described in reference... Figures 6 to 9 The model selection manager described is used to perform this.

[0212] At point 1715, the UE can determine that the first result in the set of results for the first function is the optimal result in the set of results, wherein the first result is associated with the first prediction model. The operation at point 1715 can be performed according to the method described herein. In some examples, aspects of the operation at point 1715 can be determined by referring to... Figures 6 to 9 The model selection manager described is used to perform this.

[0213] At point 1720, the UE can select a first prediction model based on this determination. The operation at point 1720 can be performed according to the method described herein. In some examples, aspects of the operation at point 1720 can be determined as described in reference... Figures 6 to 9 The model selection manager described is used to perform this.

[0214] At 1725, the UE can determine one or more parameters for beamforming communication based on a first prediction model used for the first function. The operation at 1725 can be performed according to the method described herein. In some examples, aspects of the operation at 1725 can be determined by, as referenced... Figures 6 to 9 The described beamforming manager is used to perform this.

[0215] At 1730, the UE can communicate with the base station using beamforming communication based on one or more defined parameters. The operation at 1730 can be performed according to the method described herein. In some examples, aspects of the operation at 1730 can be determined by reference to... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0216] Figure 18Based on various aspects of this disclosure, a flowchart depicting a method 1800 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1800 can be implemented by a UE 115 or its components as described herein. For example, the operation of method 1800 can be implemented by, as referenced... Figures 6 to 9 The communication manager described herein is used for execution. In some examples, the UE can execute a set of instructions to control the UE's functional units to perform the functions described below. Alternatively or concurrently, the UE can use special-purpose hardware to perform aspects of the functions described below.

[0217] At 1805, the UE can receive from the base station a set of prediction models for at least a first function associated with beamforming communication with the base station. The operation at 1805 can be performed according to the method described herein. In some examples, aspects of the operation at 1805 can be derived from, as referenced... Figures 6 to 9 The described model recognition manager is used to perform this.

[0218] At 1810, the UE can select a first prediction model from the set of prediction models for a first function, for beamforming communication with the base station. The operation at 1810 can be performed according to the method described herein. In some examples, aspects of the operation at 1810 can be defined as described in reference... Figures 6 to 9 The model selection manager described is used to perform this.

[0219] At point 1815, the UE can determine one or more parameters for beamforming communication based on a first prediction model used for the first function. The operation at point 1815 can be performed according to the method described herein. In some examples, aspects of the operation at point 1815 can be determined by, as referenced... Figures 6 to 9 The described beamforming manager is used to perform this.

[0220] At point 1820, the UE can communicate with the base station using beamforming communication based on one or more defined parameters. The operation at point 1820 can be performed according to the method described herein. In some examples, aspects of the operation at point 1820 can be determined by reference to... Figures 6 to 9 The described beamforming communication manager is used to perform this.

[0221] At point 1825, the UE can receive a model selection function from the base station for selecting different prediction models. The operation at point 1825 can be performed according to the method described herein. In some examples, aspects of the operation at point 1825 can be derived from, as referenced... Figures 6 to 9 The model selection manager described is used to perform this.

[0222] At 1830, the UE can measure one or more channel conditions associated with beamforming communication, one or more internal states of the UE, or a combination thereof, to identify a set of measured values. The operation at 1830 can be performed according to the methods described herein. In some examples, aspects of the operation at 1830 can be determined by reference to... Figures 6 to 9 The described measurement manager is used to perform this.

[0223] At point 1835, the UE can provide the set of measurements as input to the model selection function, and a switch is performed in response to the associated output of the model selection function based on the set of measurements. The operation at point 1835 can be performed according to the method described herein. In some examples, aspects of the operation at point 1835 can be described as referenced... Figures 6 to 9 The described measurement manager is used to perform this.

[0224] At point 1840, the UE can switch from a first prediction model to a second prediction model from the set of prediction models for use with the first function, based on the model selection feature. The operation at point 1840 can be performed according to the method described herein. In some examples, aspects of the operation at point 1840 can be defined as described in reference... Figures 6 to 9 The model selection manager described is used to perform this.

[0225] Figure 19 According to various aspects of this disclosure, a flowchart depicting a method 1900 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 1900 can be implemented by a base station or its components as described herein. For example, the operation of method 1900 can be implemented by, as referred to... Figures 10 to 13 The described base station 105 performs this function. In some examples, the base station may execute a set of instructions to control the functional units of the base station to perform the described function. Alternatively, the base station may use special-purpose hardware to perform aspects of the described function.

[0226] At 1905, the method may include: sending to a first UE one or more predictive models for at least a first function associated with beamforming communication with the first UE, said one or more predictive models being based on identifying the first UE as being for beamforming communication with a base station. The operation at 1905 can be performed according to examples as disclosed herein. In some examples, aspects of the operation at 1905 may be as described in reference... Figures 10 to 13 The described model recognition manager is used to perform this.

[0227] At 1910, the method may include: communicating with a first UE using communication parameters of beamforming based on one or more prediction models. The operation at 1910 can be performed according to examples as disclosed herein. In some examples, aspects of the operation at 1910 may be as described in reference... Figures 10 to 13 The described beamforming communication manager is used to perform this.

[0228] Figure 20 According to various aspects of this disclosure, a flowchart depicting a method 2000 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 2000 can be implemented by a base station 105 or its components as described herein. For example, the operation of method 2000 can be implemented by, as referred to... Figures 10 to 13 The communication manager described herein is used for execution. In some examples, the base station may execute a set of instructions to control the functional units of the base station to perform the functions described below. Alternatively or concurrently, the base station may use special-purpose hardware to perform aspects of the functions described below.

[0229] At 2005, the base station can identify a set of predictive models for at least a first function associated with beamforming communication between the base station and the UE. Operation 2005 can be performed according to the method described herein. In some examples, aspects of operation 2005 can be determined by reference to... Figures 10 to 13 The model selection manager described is used to perform this.

[0230] At point 2010, the base station can send a set of prediction models to the first UE based on identifying the first UE as being for beamforming communication with the base station. The operation of 2010 can be performed according to the method described herein. In some examples, aspects of the operation of 2010 can be derived from, as referenced... Figures 10 to 13 The described model recognition manager is used to perform this.

[0231] At point 2015, the base station can receive a measurement report from the first UE indicating one or more measured channel conditions at the first UE. Operation 2015 can be performed according to the method described herein. In some examples, aspects of operation 2015 can be determined by referring to... Figures 10 to 13 The described measurement report manager is used to perform this.

[0232] At 2020, the base station can select a first prediction model from a set of prediction models for beamforming communication with the first UE, based on a measurement report. The operation at 2020 can be performed according to the method described herein. In some examples, aspects of the operation at 2020 can be determined by referring to... Figures 10 to 13 The model selection manager described is used to perform this.

[0233] At point 2025, the base station can send an indication of the first prediction model to the first UE. The operation at point 2025 can be performed according to the method described herein. In some examples, aspects of the operation at point 2025 can be determined by referring to... Figures 10 to 13 The model selection manager described is used to perform this.

[0234] At point 2030, the base station can communicate with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first prediction model in a set of prediction models. Operation 2030 can be performed according to the method described herein. In some examples, aspects of operation 2030 can be determined by reference to... Figures 10 to 13 The described beamforming communication manager is used to perform this.

[0235] Figure 21 Based on various aspects of this disclosure, a flowchart depicting a method 2100 for selecting a machine learning model in communications supporting beamforming is shown. The operation of method 2100 can be implemented by a base station 105 or its components as described herein. For example, the operation of method 2100 can be implemented by, as described in reference... Figures 10 to 13 The communication manager described herein is used for execution. In some examples, the base station may execute a set of instructions to control the functional units of the base station to perform the functions described below. Alternatively or concurrently, the base station may use special-purpose hardware to perform aspects of the functions described below.

[0236] At 2105, the base station can identify a set of predictive models for at least a first function associated with beamforming communication between the base station and the UE. The operation at 2105 can be performed according to the method described herein. In some examples, aspects of the operation at 2105 can be derived from, as referenced... Figures 10 to 13 The model selection manager described is used to perform this.

[0237] At 2110, the base station can send a set of prediction models to the first UE based on identifying the first UE as being for beamforming communication with the base station. The operation at 2110 can be performed according to the method described herein. In some examples, aspects of the operation at 2110 can be derived from, as referenced... Figures 10 to 13 The described model recognition manager is used to perform this.

[0238] At point 2115, the base station can receive a measurement report from the first UE indicating one or more measured channel conditions at the first UE. The operation of 2115 can be performed according to the method described herein. In some examples, aspects of the operation of 2115 can be described as referenced... Figures 10 to 13 The described measurement report manager is used to perform this.

[0239] At 2120, the base station can select a first prediction model from the set of prediction models for beamforming communication with the first UE, based on the measurement report. The operation at 2120 can be performed according to the method described herein. In some examples, aspects of the operation at 2120 can be described as referenced... Figures 10 to 13 The model selection manager described is used to perform this.

[0240] At point 2125, the base station may send an indication of the first prediction model to the first UE. The operation at 2125 can be performed according to the method described herein. In some examples, aspects of the operation at 2125 may be derived from, as referenced... Figures 10 to 13 The model selection manager described is used to perform this.

[0241] At 2130, the base station can communicate with the first UE using beamforming communication based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first prediction model in a set of prediction models. The operation at 2130 can be performed according to the method described herein. In some examples, aspects of the operation at 2130 can be determined by referring to... Figures 10 to 13 The described beamforming communication manager is used to perform this.

[0242] At point 2135, the base station can receive an indication from the first UE regarding whether the first prediction model accurately predicted the first function. The operation at 2135 can be performed according to the method described herein. In some examples, aspects of the operation at 2135 can be determined by referring to... Figures 10 to 13 The described model recognition manager is used to perform this.

[0243] At 2140, the base station can update the model used to determine, based on the measurement report, which prediction model from the set of prediction models to indicate to the UE. The operation at 2140 can be performed according to the method described herein. In some examples, aspects of the operation at 2140 can be as described in reference... Figures 10 to 13 The described model recognition manager is used to perform this.

[0244] It should be noted that the methods described in this paper describe possible implementations, and these operations and steps can be rearranged or modified; other implementations are also possible. Furthermore, two or more aspects from these methods can be combined.

[0245] The following provides an overview of various aspects of this disclosure:

[0246] Aspect 1: A method for wireless communication at a UE, comprising: receiving from a base station one or more prediction models for at least a first function associated with beamforming communication with the base station; and communicating with the base station using beamforming communication at least in part based on one or more parameters, the one or more parameters being at least in part based on a prediction model among the one or more prediction models for the first function of beamforming communication with the base station.

[0247] Aspect 2: The method according to aspect 1 further includes: measuring one or more channel conditions between the UE and the base station; in response to the measurement, sending a measurement report indicating the one or more channel conditions to the base station; receiving an indication of the prediction model from the base station; and in response to the indication from the base station, selecting the prediction model for use in the first function.

[0248] Aspect 3: According to the method of aspect 2, wherein the UE receives from the base station a priority list of prediction models for each of a plurality of functions to be used at the UE for communication associated with beamforming.

[0249] Aspect 4: The method according to any one of Aspects 2 to 3 further includes: determining whether the prediction model accurately predicts the first function; and sending an indication to the base station based on the determination.

[0250] Aspect 5: The method according to any one of Aspects 2 to 4, wherein the measurement report further indicates the location information of the UE.

[0251] Aspect 6: The method according to any one of Aspects 2 to 5, wherein the measurement includes: measuring one or more reference signals received from the base station and one or more other base stations in one or more synchronization signal blocks (SSBs).

[0252] Aspect 7: The method according to any one of Aspects 1 to 6 further comprises: sending one or more measurement reports to the base station based on measurements associated with beamforming communication that uses the prediction model for the first function; receiving from the base station an indication in response to the one or more measurement reports for switching to a different prediction model among the one or more prediction models; determining one or more updated parameters for further beamforming communication based at least in part on the different prediction model used for the first function; and communicating with the base station using beamforming communication based at least in part on the one or more updated parameters.

[0253] Aspect 8: The method according to any one of Aspects 1 to 7 further comprises: receiving from the base station a model selection function for selecting different prediction models; and switching to the different prediction models among the one or more prediction models for use with the first function, at least in part based on the model selection function.

[0254] Aspect 9: The method according to aspect 8 further includes: measuring one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or a combination thereof, to identify a plurality of measurements; and providing the plurality of measurements as input to the model selection function, wherein the switching is performed in response to an associated output of the model selection function based on the plurality of measurements.

[0255] Aspect 10: The method according to any one of aspects 1 to 9 further comprises: for each of two or more prediction models, calculating a result of the first function to generate two or more results of the first function; determining a first result among the two or more results of the first function as the most preferred result, wherein the first result is associated with the first prediction model; and selecting the first prediction model based at least in part on the determination.

[0256] Aspect 11: The method according to aspect 10 further includes: monitoring the prediction quality from the first prediction model among multiple predictions; and switching to a second prediction model for the first function based at least in part on the prediction quality from the first prediction model falling below a threshold quality.

[0257] Aspect 12: According to the method of aspect 11, wherein the prediction quality is determined to have fallen below the threshold quality based at least in part on the mismatch between the results of the first prediction model and observations based on one or more measurements at the UE.

[0258] Aspect 13: The method according to any one of Aspects 11 to 12, wherein the prediction quality is determined to be below the threshold quality based at least in part on one or more of the following: the number of consecutive incorrect predictions exceeds the threshold, the number of incorrect predictions in a set of past predictions exceeds the threshold, or any combination thereof.

[0259] Aspect 14: A method for wireless communication at a base station, comprising: transmitting to a first UE one or more prediction models for at least a first function associated with beamforming communication with the first UE, the one or more prediction models being at least partially based on identifying the first UE as being for beamforming communication with the base station; and communicating with the first UE using beamforming communication parameters at least partially based on the prediction models in the one or more prediction models.

[0260] Aspect 15: The method according to aspect 14 further includes: receiving from the first UE a measurement report indicating one or more measurements of channel conditions at the first UE; selecting a prediction model from the one or more prediction models for beamforming communication with the first UE, based at least in part on the measurement report; and sending an indication of the prediction model to the first UE.

[0261] Aspect 16: According to the method of aspect 15, wherein sending the instruction of the prediction model includes: sending a priority list of prediction models for each of a plurality of functions to be used at the first UE for communication associated with the beamforming.

[0262] Aspect 17: The method according to any one of Aspects 15 to 16 further comprises: receiving from the first UE an indication of whether the prediction model accurately predicts the first function; and updating the model for determining, based on a measurement report, which of the one or more prediction models to indicate to the UE.

[0263] Aspect 18: The method according to any one of Aspects 15 to 17, wherein the measurement report further indicates the location information of the first UE, and wherein the selection is further based on the location information.

[0264] Aspect 19: The method according to any one of Aspects 14 to 18 further comprises: receiving from the first UE one or more measurement reports, the one or more measurement reports indicating measurements associated with beamforming communications that use the prediction model for the first function; determining, at least in part based on the one or more measurement reports, that the first UE will switch to a different prediction model among two or more prediction models; and sending an instruction to the UE to switch to the different prediction model.

[0265] Aspect 20: The method according to any one of aspects 14 to 19 further includes: sending a model selection function to the first UE for the UE to select a different prediction model.

[0266] Aspect 21: The method according to any one of aspects 14 to 20 further comprises: configuring the first UE to select the prediction model from the two or more prediction models based on the result of the first function for each of the two or more prediction models.

[0267] Aspect 22: According to the method of aspect 21, wherein the configuration further includes: configuring the threshold prediction quality at the first UE to initiate a switch between prediction models.

[0268] Aspect 23: According to the method of aspect 22, wherein the threshold prediction quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in the set of past predictions exceeding the threshold, or any combination thereof.

[0269] Aspect 24: An apparatus for wireless communication at a base station, comprising a processor; a memory coupled to the processor; the processor and the memory being configured to perform the method described in any one of aspects 1 to 13.

[0270] Aspect 25: An apparatus for wireless communication at a UE, comprising at least one unit for performing the method described in any one of aspects 1 to 13.

[0271] Aspect 26: A non-transitory computer-readable medium storing code for wireless communication at a UE, said code including instructions executable by a processor to perform the methods described in any one of aspects 1 to 13.

[0272] Aspect 27: An apparatus for wireless communication at a base station, comprising a processor; a memory coupled to the processor; the processor and the memory being configured to perform the method described in any one of aspects 14 to 23.

[0273] Aspect 28: An apparatus for wireless communication at a base station, comprising at least one unit for performing the method described in any one of aspects 14 to 23.

[0274] Aspect 29: A non-transitory computer-readable medium storing code for wireless communication at a base station, the code including instructions executable by a processor to perform the methods described in any one of aspects 14 to 23.

[0275] Aspect 30: A method for wireless communication at a user equipment (UE), comprising: receiving from a base station a set of prediction models for at least a first function associated with beamforming communication with the base station; selecting a first prediction model from the set of prediction models for the first function of beamforming communication with the base station; determining one or more parameters for the beamforming communication based at least in part on the first prediction model for the first function; and communicating with the base station using beamforming communication based at least in part on the one or more determined parameters.

[0276] Aspect 31: According to the method of aspect 30, wherein the selection includes: measuring one or more channel conditions between the UE and the base station; in response to the measurement, sending a measurement report indicating the one or more channel conditions to the base station; receiving an indication of the first prediction model from the base station; and in response to the indication from the base station, selecting the first prediction model for the first function.

[0277] Aspect 32: The method according to any one of Aspects 30 or 31, wherein the UE receives from the base station a priority list of prediction models for each of a plurality of functions to be used at the UE for communication associated with beamforming.

[0278] Aspect 33: The method according to any one of aspects 30 to 32, wherein the measurement includes: measuring one or more reference signals received from the base station and one or more other base stations in one or more synchronization signal blocks (SSBs).

[0279] Aspect 34: The method according to any one of aspects 31 to 33, wherein the measurement report further indicates the location information of the UE.

[0280] Aspect 35: The method according to any one of aspects 30 to 34 further includes: determining whether the first prediction model accurately predicts the first function; and based on the determination, sending an indication to the base station.

[0281] Aspect 36: The method according to any one of Aspects 30 to 35, wherein the selection comprises: for each of the set of prediction models, calculating a result of the first function to generate a plurality of results of the first function; determining a first result among the plurality of results of the first function as the most preferred result among the plurality of results, wherein the first result is associated with the first prediction model; and selecting the first prediction model based on the determination.

[0282] Aspect 37: The method according to any one of aspects 30 to 36 further includes: monitoring the prediction quality from the first prediction model among multiple predictions; and switching to a second prediction model for the first function based on the prediction quality from the first prediction model falling below a threshold quality.

[0283] Aspect 38: According to the method of aspect 37, wherein the prediction quality is determined to have fallen below the threshold quality based at least in part on the mismatch between the results of the first prediction model and observations based on one or more measurements at the UE.

[0284] Aspect 39: The method according to any one of Aspects 37 to 38, wherein the prediction quality is determined to be below the threshold quality based at least in part on one or more of the following: the number of consecutive incorrect predictions exceeds the threshold, the number of incorrect predictions in a set of past predictions exceeds the threshold, or any combination thereof.

[0285] Aspect 40: The method according to any one of Aspects 30 to 39 further comprises: sending one or more measurement reports to the base station based on measurements associated with beamforming communication that uses the first prediction model for the first function; receiving from the base station an indication for switching to a second prediction model among the plurality of prediction models in response to the one or more measurement reports; determining one or more updated parameters for further beamforming communication based at least in part on the second prediction model used for the first function; and communicating with the base station using beamforming communication based at least in part on the one or more updated parameters.

[0286] Aspect 41: The method according to any one of aspects 30 to 40 further includes: receiving from the base station a model selection function for selecting different prediction models; and switching from the first prediction model to a second prediction model in the set of prediction models for use with the first function, based at least in part on the model selection function.

[0287] Aspect 42: The method according to aspect 41 further includes: measuring one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or a combination thereof, to identify a plurality of measurements; and using the plurality of measurements as input to the model selection function, wherein the handover is performed in response to an associated output of the model selection function based on the plurality of measurements.

[0288] Aspect 43: An apparatus for wireless communication, comprising at least one unit for performing the method described in any one of aspects 30 to 42.

[0289] Aspect 44: An apparatus for wireless communication, comprising a processor; a memory coupled to the processor; wherein the processor and the memory are configured to perform the method described in any one of aspects 30 to 42.

[0290] Aspect 45: A non-transitory computer-readable medium storing code for wireless communication, comprising a processor, a memory in electrical communication with the processor, and instructions stored in the memory and executable by the processor to cause the device to perform any of the methods described in aspects 30 to 42.

[0291] Aspect 46: A method for wireless communication at a base station, comprising: identifying a plurality of prediction models for at least a first function associated with beamforming communication between the base station and a UE; transmitting the plurality of prediction models to the first UE at least in part based on identifying the first UE as being for beamforming communication with the base station; and communicating with the first UE using beamforming communication at least in part based on one or more parameters of the first function, wherein the one or more parameters of the first function are determined based on a first prediction model among the plurality of prediction models.

[0292] Aspect 47: The method according to aspect 46 further includes: receiving from the first UE a measurement report indicating one or more measurements of channel conditions at the first UE; selecting, at least in part based on the measurement report, the first prediction model of the plurality of prediction models for beamforming communication with the first UE; and sending an indication of the first prediction model to the first UE.

[0293] Aspect 48: The method according to any one of Aspects 46 to 47, wherein sending the instruction to the first prediction model comprises: sending a priority list of prediction models for each of a plurality of functions to be used at the first UE for communication associated with beamforming.

[0294] Aspect 49: The method according to any one of aspects 46 to 48, wherein the measurement report further indicates the location information of the first UE, and wherein the selection is further based on the location information.

[0295] Aspect 50: The method according to any one of aspects 46 to 49 further includes: receiving from the first UE an indication of whether the first prediction model accurately predicts the first function; and updating the model for determining, based on a measurement report, which of the plurality of prediction models to indicate to the UE.

[0296] Aspect 51: The method according to any one of aspects 46 to 50 further comprises: configuring the first UE to select the first prediction model from the plurality of prediction models based on the result of the first function for each of the plurality of prediction models.

[0297] Aspect 52: The method according to any one of aspects 46 to 51, wherein the configuration further includes: configuring the threshold prediction quality at the first UE to initiate a switch between prediction models.

[0298] Aspect 53: The method according to aspect 52, wherein the threshold quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in a set of past predictions exceeding the threshold, or any combination thereof.

[0299] Aspect 54: The method according to any one of aspects 46 to 53 further comprises: receiving from the first UE one or more measurement reports, the one or more measurement reports indicating measurements associated with beamforming communication using the first prediction model for the first function; determining, at least in part based on the one or more measurement reports, that the first UE will switch to a second prediction model among the plurality of prediction models; and sending an instruction to the UE to switch to the second prediction model.

[0300] Aspect 55: The method according to any one of aspects 46 to 54 further includes: sending a model selection function to the first UE for the UE to select a different prediction model among the plurality of prediction models.

[0301] Aspect 56: An apparatus for wireless communication, comprising at least one unit for performing the method described in any one of aspects 46 to 55.

[0302] Aspect 57: An apparatus for wireless communication, comprising a processor; a memory coupled to the processor; the processor and the memory being configured such that the apparatus performs the method described in any one of aspects 46 to 55.

[0303] Aspect 58: A non-transitory computer-readable medium storing code for wireless communication, comprising a processor, a memory in electrical communication with the processor, and instructions stored in the memory and executable by the processor to cause the device to perform any of the methods described in aspects 46 to 55.

[0304] While aspects of LTE, LTE-A, LTE-A Pro, or NR systems have been described for illustrative purposes, and the terms LTE, LTE-A, LTE-A Pro, or NR are used extensively in the description, the technologies described herein are also applicable beyond LTE, LTE-A, LTE-A Pro, or NR networks. For example, the described technologies can be applied to a variety of other wireless communication systems, such as Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0305] The information and signals described herein can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the description herein can be represented using voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0306] A general-purpose processor, DSP, ASIC, CPU, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any combination thereof, designed to perform the functions described herein, may be used to implement or perform the various exemplary blocks and components described in connection with the disclosure herein. The general-purpose processor may be a microprocessor, or it may be any processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, several microprocessors, a combination of a microprocessor and a DSP core, or any other such architecture).

[0307] The functions described herein can be implemented in hardware, processor-executed software, firmware, or any combination thereof. When implemented in processor-executed software, these functions can be stored on a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Other examples and implementations also fall within the scope of this disclosure and its appended claims. For example, due to the nature of software, the functions described herein can be implemented using processor-executed software, hardware, firmware, hardware wiring, or any combination thereof. Features used to implement the functions can be physically distributed in multiple locations, including portions distributed in different physical locations to implement the functions.

[0308] Computer-readable media include non-transitory computer storage media and communication media, wherein communication media includes any medium that facilitates the transfer of a computer program from one place to another. Non-transitory storage media can be any available medium accessible to a general-purpose or special-purpose computer. For example, but not limitingly, non-transitory computer-readable media can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory, compressed optical disc (CD) ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other non-transitory medium capable of carrying or storing desired units of program code in the form of instructions or data structures and accessible by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, any connection may be appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, wireless, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, wireless, and microwave are included in the definition of computer-readable media. As used herein, disks and optical discs include CDs, laser discs, optical discs, digital versatile optical discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically. The combination of these should also be included within the scope of protection for computer-readable media.

[0309] As used herein (including in the claims), the word "or" as used in a list item (e.g., a list item ending with a phrase such as "at least one of" or "one or more of") indicates an inclusive list, such that a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Furthermore, as used herein, the phrase "based on" should not be construed as referring to a closed set of conditions. For example, an exemplary step described as "based on condition A" could be based on conditions A and B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "at least partially based on".

[0310] In the accompanying drawings, similar parts or features have the same reference numerals. Furthermore, parts of the same type can be distinguished by adding a dashed line after the reference numeral and a second reference numeral to differentiate similar parts. If only the first reference numeral is used in the description, the description applies to any similar part having the same first reference numeral, regardless of any subsequent reference numerals.

[0311] This document describes exemplary configurations in conjunction with the accompanying drawings, but these do not represent all possible examples or all examples falling within the scope of the claims. As used herein, the term "exemplary" means "serving as an example, instance, or illustration," but does not imply "more preferred" or "more advantageous" than other examples. The detailed embodiments include specific details to provide a thorough understanding of the described techniques. However, these techniques can be implemented without using these specific details. In some instances, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0312] The present disclosure has been described above to enable any person skilled in the art to implement or use it. Various modifications to the present disclosure will be apparent to those skilled in the art, and the general principles defined herein can be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the broadest scope of the principles and novel features disclosed herein.

Claims

1. A method for wireless communication at a user equipment (UE), comprising: Receive two or more prediction models from a network node for at least a first function associated with beamforming communication with the network node; Receive an indication of a prediction model among the two or more prediction models from the network node, wherein the prediction model is selected at least in part based on a measurement report indicating the location information of the UE; as well as Communicating with the network node using beamforming communication based at least in part on one or more parameters, the one or more parameters being at least in part based on the prediction model of the first function for beamforming communication with the network node.

2. The method according to claim 1, further comprising: Measure one or more channel conditions between the UE and the network node; as well as In response to the measurement, a measurement report further indicating the conditions of the one or more channels is sent to the network node.

3. The method according to claim 1, wherein, The UE receives from the network node a priority list of prediction models for each of a plurality of functions to be used at the UE for communication associated with beamforming.

4. The method according to claim 1, further comprising: Determine whether the prediction model accurately predicted the first function; as well as Based on the determination, an instruction is sent to the network node.

5. The method according to claim 2, wherein, The measurements include: Measurements are performed on one or more reference signals received from the network node and one or more other network nodes in one or more synchronization signal blocks (SSBs).

6. The method according to claim 1, further comprising: Based on measurements associated with the beamforming communication that uses the prediction model for the first function, one or more measurement reports are sent to the network node; Receive from the network node an instruction for switching to a different prediction model among the two or more prediction models in response to the one or more measurement reports; One or more updated parameters for further beamforming communication are determined, at least in part, based on the different prediction models used for the first function. as well as The network nodes are communicated using beamforming communication that is at least partially based on the one or more updated parameters.

7. The method according to claim 1, further comprising: Measure one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or a combination thereof, to identify multiple measurement values; as well as The plurality of measurements are provided as input to the model selection function, and a switching is performed in response to the associated output of the model selection function based on the plurality of measurements.

8. The method according to claim 1, further comprising: For each of the two or more prediction models, the result of the first function is calculated to generate two or more results for the first function; The first result among the two or more results of the first function is determined to be the preferred result, wherein the first result is associated with the first prediction model; as well as The first prediction model is selected based at least in part on the determination made therein.

9. The method according to claim 8, further comprising: Monitor the prediction quality from the first prediction model across multiple predictions; as well as At least in part, based on the prediction quality from the first prediction model falling below a threshold quality, the system switches to a second prediction model for the first function.

10. The method according to claim 9, wherein, The prediction quality is determined to have fallen below the threshold quality, at least in part, based on the mismatch between the results of the first prediction model and observations based on one or more measurements at the UE.

11. The method according to claim 9, wherein, The prediction quality is determined to have fallen below the threshold quality based at least in part on one or more of the following: the number of consecutive incorrect predictions exceeds the threshold, the number of incorrect predictions in a set of past predictions exceeds the threshold, or any combination thereof.

12. A method for wireless communication at a network node, comprising: Send to a first UE two or more prediction models for at least a first function associated with beamforming communication with the first UE, the two or more prediction models being at least partially based on identifying the first UE as being for beamforming communication with the network node; Sending an indication to the first UE of a prediction model among the two or more prediction models, wherein the prediction model is selected at least in part based on a measurement report indicating the location information of the first UE; and The first UE is communicated using communication parameters based at least in part on beamforming, which are based on the prediction model.

13. The method of claim 12, further comprising: Receive the measurement report from the first UE, which further indicates the channel conditions of one or more measurements at the first UE; and The prediction model is further selected based on the channel conditions measured at the first UE (one or more).

14. The method according to claim 12, wherein, The instruction to send the prediction model includes: Send a priority list of prediction models for each of the multiple functions associated with the beamforming communication at the first UE.

15. The method of claim 12, further comprising: Receive an indication from the first UE as to whether the prediction model accurately predicts the first function; as well as The model is updated to determine, based on the measurement report, which of the two or more prediction models to indicate to the UE.

16. The method of claim 12, further comprising: Receive one or more measurement reports from the first UE, the one or more measurement reports indicating measurements associated with the beamforming communication that uses the prediction model for the first function; Based at least in part on the one or more measurement reports, it is determined that the first UE will switch to a different prediction model among the two or more prediction models; as well as Send an instruction to the first UE to switch to the different prediction model.

17. The method of claim 12, further comprising: The first UE is configured to select the prediction model from the two or more prediction models based on the result of the first function for each of the two or more prediction models.

18. The method according to claim 17, wherein, The configuration further includes: Configure the threshold prediction quality at the first UE to initiate the switching between prediction models.

19. The method according to claim 18, wherein, The threshold prediction quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in the set of past predictions exceeding the threshold, or any combination thereof.

20. An apparatus for wireless communication at a user equipment (UE), comprising: One or more memory units; as well as One or more processors coupled to the one or more memories are configured to cause the UE to perform the following operations: Receive two or more prediction models from a network node for at least a first function associated with beamforming communication with the network node; Receive an indication of a prediction model among the two or more prediction models from the network node, wherein the prediction model is selected at least in part based on a measurement report indicating the location information of the UE; as well as Communicating with the network node using beamforming communication based at least in part on one or more parameters, the one or more parameters being at least in part based on the prediction model of the first function for beamforming communication with the network node.

21. The apparatus of claim 20, further comprising: An antenna coupled to the one or more processors, wherein the one or more processors are further configured to: Measure one or more channel conditions between the UE and the network node; and In response to the measurement, a measurement report further indicating the conditions of the one or more channels is sent to the network node via the antenna.

22. The apparatus according to claim 20, wherein, The one or more processors are further configured to: Receive from the network node a priority list of prediction models for each of a plurality of functions to be used at the UE for communication associated with beamforming.

23. The apparatus according to claim 20, wherein, The one or more processors are further configured to: Determine whether the prediction model accurately predicted the first function; and Based on the determination, an instruction is sent to the network node.

24. The apparatus according to claim 21, wherein, For measurement purposes, the one or more processors are configured to: Measurements are performed on one or more reference signals received from the network node and one or more other network nodes in one or more synchronization signal blocks (SSBs).

25. The apparatus according to claim 20, wherein, The one or more processors are further configured to: Based on measurements associated with the beamforming communication that uses the prediction model for the first function, one or more measurement reports are sent to the network node; Receive from the network node an instruction for switching to a different prediction model among the two or more prediction models in response to the one or more measurement reports; One or more updated parameters for further beamforming communication are determined, at least in part, based on the different prediction models used for the first function. as well as The network nodes are communicated using beamforming communication that is at least partially based on the one or more updated parameters.

26. The apparatus according to claim 20, wherein, The one or more processors are further configured to: Measure one or more channel conditions associated with the beamforming communication, one or more internal states of the UE, or a combination thereof, to identify multiple measurement values; as well as The plurality of measurements are provided as input to the model selection function, and a switching is performed in response to the associated output of the model selection function based on the plurality of measurements.

27. The apparatus according to claim 20, wherein, The one or more processors are further configured to: For each of the two or more prediction models, the result of the first function is calculated to generate two or more results for the first function; The first result among the two or more results of the first function is determined to be the preferred result, wherein the first result is associated with the first prediction model; as well as The first prediction model is selected based at least in part on the determination made therein.

28. The apparatus according to claim 27, wherein, The one or more processors are further configured to: Monitor the prediction quality from the first prediction model across multiple predictions; and At least in part, based on the prediction quality from the first prediction model falling below a threshold quality, the system switches to a second prediction model for the first function.

29. The apparatus according to claim 28, wherein, The prediction quality is determined to have fallen below the threshold quality, at least in part, based on the mismatch between the results of the first prediction model and observations based on one or more measurements at the UE.

30. The apparatus according to claim 28, wherein, The prediction quality is determined to have fallen below the threshold quality based at least in part on one or more of the following: the number of consecutive incorrect predictions exceeds the threshold, the number of incorrect predictions in a set of past predictions exceeds the threshold, or any combination thereof.

31. An apparatus for wireless communication at a network node, comprising: One or more memory units; as well as One or more processors coupled to the one or more memories are configured to cause the network node to perform the following operations: Send to a first UE two or more prediction models for at least a first function associated with beamforming communication with the first UE, the two or more prediction models being at least partially based on identifying the first UE as being for beamforming communication with the network node; Sending an indication to the first UE of a prediction model among the two or more prediction models, wherein the prediction model is selected at least in part based on a measurement report indicating the location information of the first UE; and The first UE is communicated using communication parameters based at least in part on beamforming, which are based on the prediction model.

32. The apparatus of claim 31, further comprising: An antenna coupled to the one or more processors, wherein the one or more processors are further configured to: Receive, via the antenna, the measurement report from the first UE, further indicating the channel conditions of one or more measurements at the first UE; and The prediction model is further selected based on the channel conditions measured at the first UE (one or more).

33. The apparatus according to claim 31, wherein, The one or more processors are further configured to: Send a priority list of prediction models for each of the multiple functions associated with the beamforming communication at the first UE.

34. The apparatus according to claim 31, wherein, The one or more processors are further configured to: Receive from the first UE an indication of whether the prediction model accurately predicts the first function; and The model is updated to determine, based on the measurement report, which of the two or more prediction models to indicate to the UE.

35. The apparatus according to claim 31, wherein, The one or more processors are further configured to: Receive one or more measurement reports from the first UE, the one or more measurement reports indicating measurements associated with the beamforming communication that uses the prediction model for the first function; Based at least in part on the one or more measurement reports, it is determined that the first UE will switch to a different prediction model among the two or more prediction models; as well as Send an instruction to the first UE to switch to the different prediction model.

36. The apparatus according to claim 31, wherein, The one or more processors are further configured to: The first UE is configured to select the prediction model from the two or more prediction models based on the result of the first function for each of the two or more prediction models.

37. The apparatus according to claim 36, wherein, For configuration purposes, the one or more processors are configured as follows: Configure the threshold prediction quality at the first UE to initiate the switching between prediction models.

38. The apparatus according to claim 37, wherein, The threshold prediction quality corresponds to: a threshold for the number of consecutive incorrect predictions, the number of incorrect predictions in the set of past predictions exceeding the threshold, or any combination thereof.

39. A non-transitory computer-readable medium storing code for wireless communication at a user equipment (UE), the code comprising instructions executable by a processor to perform the method according to any one of claims 1-11.

40. A non-transitory computer-readable medium storing code for wireless communication at a network node, the code comprising instructions executable by a processor to perform the method according to any one of claims 12-19.

41. An apparatus for wireless communication at a user equipment (UE), comprising a unit for performing the method according to any one of claims 1-11.

42. An apparatus for wireless communication at a network node, comprising a unit for performing the method according to any one of claims 12-19.

Images