Signaling for dictionary learning techniques for channel estimation

Abstract

Methods, systems, and devices for wireless communication are described. A user equipment (UE) may generate one or more channel estimates for multiple channels between the UE and a network entity using a sparse recovery technique. The one or more channel estimates may be based on one or more measurements using a set of directional beams. The UE may calculate a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The UE may send a message including an indication of the dictionary to the network entity. In some examples, the network entity may compute a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, and the network entity may send a message to the UE including an indication of the dictionary.

Description

Technical Field

[0001] The following relates to wireless communications, including signaling for dictionary learning techniques for channel estimation. Background Art

[0002] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, broadcasting, and the like. These systems may be able to 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 (such as long term evolution (LTE) systems, advanced LTE (LTE-A) systems, or LTE-A Pro systems) and fifth generation (5G) systems (which may be referred to as new radio (NR) systems). These systems may employ techniques such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations, each of which supports wireless communications for communication devices, which may be referred to as user equipment (UE).

[0003] In some wireless communication systems, a UE and a network entity or some other combination of wireless devices may perform beam selection techniques to select one or more beams to be used for communications between the devices. Techniques for performing such beam selection procedures may be improved. Summary of the invention

[0004] The described technology relates to improved methods, systems, devices and apparatuses for supporting signaling for dictionary learning techniques for channel estimation. In general, a user equipment (UE), a network entity, or both may perform a dictionary learning procedure to determine channel information. Then, the UE, the network entity, or both may use the learned dictionary to determine a channel, which may be used to select a customized beam (e.g., one or more dynamic beam directions that may be different from a predetermined beam set corresponding to a codebook) for communication between devices. For example, as the UE moves around a cell, the UE may record raw channel estimates to be used as training samples for the dictionary. In some cases, the UE may meet a threshold of training samples to determine a sparse dictionary, and when learning the dictionary, the UE may report the sparse dictionary to the network entity. In one example, the network entity may send a sparse dictionary to similar UEs (e.g., UEs with the same antenna configuration, UEs associated with the same manufacturer, UEs of the same model, UEs of the same type 115). For example, when determining one or more beams for communicating with other devices (e.g., other UEs, network nodes, etc.), the UE may use the sparse dictionary to communicate in the cell.

[0005] Additionally or alternatively, the UE or multiple similar UEs may send an original channel estimate to the network entity. The network entity may classify the original channel estimate from one UE or from multiple similar UEs and determine a sparse dictionary for each UE and / or for each group of similar UEs. In such cases, the network entity may determine a different sparse dictionary for each group of similar UEs. The network entity may send an indication of the sparse dictionary to the corresponding UE. Upon determining and / or receiving the sparse dictionary, the UE may send the original channel estimate to the network entity, where the original channel estimate may be a sparse channel representation. The UE, the network entity, or both may use the sparse dictionary and the original channel estimate to determine the original channel, and in some cases, the UE, the network entity, or both may perform beam management to select one or more best beams between the UE and the network entity based on the original channel estimate.

[0006] A method for wireless communication at a UE is described. The method may include: generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; computing a dictionary associated with a sparse channel representation of the channels between the UE and the network entity based on a learning procedure using the one or more channel estimates; and sending a message including an indication of the dictionary to the network entity.

[0007] An apparatus for wireless communication at a UE is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executed by the processor to cause the apparatus to: generate one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; calculate a dictionary associated with a sparse channel representation of the channel between the UE and the network entity based on a learning procedure using the one or more channel estimates; and send a message including an indication of the dictionary to the network entity.

[0008] Another apparatus for wireless communication at a UE is described. The apparatus may include: means for generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; means for calculating a dictionary associated with a sparse channel representation of the channels between the UE and the network entity based on a learning procedure using the one or more channel estimates; and means for sending a message including an indication of the dictionary to the network entity.

[0009] A non-transitory computer-readable medium storing code for wireless communication at a UE is described. The code may include instructions executable by a processor to: generate one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; calculate a dictionary associated with a sparse channel representation of the channel between the UE and the network entity based on a learning procedure using the one or more channel estimates; and send a message including an indication of the dictionary to the network entity.

[0010] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending a feedback message indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

[0011] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a signal indicating a configuration for sending the sparse channel representation of a certain number of dominant taps for the channel, wherein sending the feedback message can be based on the configuration.

[0012] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the feedback message may include operations, features, components, or instructions for sending an identifier of the dictionary associated with the sparse channel representation along with the feedback message.

[0013] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a configured signal indicating a threshold number of training samples to be obtained before calculating the dictionary, wherein sending the message can be based on satisfying the threshold number of training samples.

[0014] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining a certain number of training samples that at least satisfy the threshold number of training samples, wherein the UE calculates the dictionary based on the number of training samples satisfying the threshold.

[0015] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining corresponding training samples at one or more locations of the UE, one or more times of the day, or a combination thereof, wherein the one or more channel estimates may be based on the corresponding training samples.

[0016] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a signal indicating a configuration of a set of parameters for calculating the dictionary, the set of parameters including criteria for stopping the learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary can be calculated based on the set of parameters.

[0017] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for computing an updated dictionary based on changes to one or more conditions on which the dictionary may depend, wherein the indication of the dictionary includes an indication of the updated dictionary.

[0018] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0019] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, using the sparse recovery technique to generate the one or more channel estimates may include operations, features, components, or instructions for performing the following operations: generating the one or more channel estimates using an orthogonal matching pursuit (OMP) algorithm.

[0020] A method for wireless communication at a network entity is described. The method may include: receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and the network entity; performing a beam management procedure for selecting one or more directional beams based on the dictionary; and communicating with the UE using the one or more directional beams.

[0021] An apparatus for wireless communication at a network entity is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executed by the processor to cause the apparatus to: receive a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and the network entity; execute a beam management procedure for selecting one or more directional beams based on the dictionary; and communicate with the UE using the one or more directional beams.

[0022] Another apparatus for wireless communication at a network entity is described. The apparatus may include: means for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and the network entity; means for executing a beam management procedure for selecting one or more directional beams based on the dictionary; and means for communicating with the UE using the one or more directional beams.

[0023] A non-transitory computer-readable medium storing code for wireless communication at a network entity is described. The code may include instructions executable by a processor to: receive a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and the network entity; execute a beam management procedure for selecting one or more directional beams based on the dictionary; and communicate with the UE using the one or more directional beams.

[0024] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending one or more messages that each include an indication of the dictionary to one or more other UEs, the one or more other UEs having the same antenna configuration as the UE, being associated with the same manufacturer as the UE, being the same model as the UE, being the same type as the UE, or a combination thereof.

[0025] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a feedback message indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message including an index set of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

[0026] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending a signal indicating a configuration for sending the sparse channel representation of a certain number of dominant paths for the channel, wherein receiving the feedback message can be based on the configuration.

[0027] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the feedback message may include operations, features, components, or instructions for receiving an identifier of the dictionary associated with the sparse channel representation along with the feedback message.

[0028] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: using the dictionary and the sparse channel representation to estimate the channel between the UE and the network entity, wherein performing the beam management procedure can be based on estimating the channel.

[0029] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a signal indicating a configuration of a threshold number of training samples for computing the dictionary, wherein receiving the message may be based on satisfying the threshold number of training samples.

[0030] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a signal indicating a configuration of a set of parameters for computing the dictionary, the set of parameters including criteria for stopping the learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary may be based on the set of parameters.

[0031] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the indication of the dictionary includes an indication of an updated dictionary that may have been updated based on a change in one or more conditions upon which the dictionary may rely.

[0032] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0033] A method for wireless communication at a UE is described. The method may include: generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; sending a signal indicating the one or more channel estimates to the network entity; and receiving a message including an indication of a dictionary associated with a sparse channel representation of the channels between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0034] An apparatus for wireless communication at a UE is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executed by the processor to cause the apparatus to: generate one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; send a signal indicating the one or more channel estimates to the network entity; and receive a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0035] Another apparatus for wireless communication at a UE is described. The apparatus may include: means for generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; means for sending a signal indicating the one or more channel estimates to the network entity; and means for receiving a message including an indication of a dictionary associated with a sparse channel representation of the channels between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0036] A non-transitory computer-readable medium storing code for wireless communication at a UE is described. The code may include instructions executable by a processor to: generate one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams; send a signal indicating the one or more channel estimates to the network entity; and receive a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0037] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending a feedback message indicating the sparse channel representation of the channel between the UE and the network entity after receiving the dictionary, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

[0038] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a signal indicating a configuration for sending the sparse channel representation of a certain number of dominant paths for the channel, wherein sending the feedback message can be based on the configuration.

[0039] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the feedback message may include operations, features, components, or instructions for sending an identifier of the dictionary associated with the sparse channel representation along with the feedback message.

[0040] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for receiving, in the message, an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary is applicable.

[0041] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for receiving in the message an indication of a set of one or more conditions to which the dictionary is applicable, the set of one or more conditions comprising a geographic location, a time of day, a zone, or a combination thereof.

[0042] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing operations for compressing the one or more channel estimates, wherein the signal indicative of the one or more channel estimates includes the compressed one or more channel estimates.

[0043] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, components, or instructions for performing the following operations: The operations performed for compressing the one or more channel estimates may be based on an autoencoder, one or more compression schemes, or a combination thereof.

[0044] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a signal indicating a configuration for sending an indication of the one or more channel estimates for a certain number of dominant paths for the channel, wherein sending the signal can be based on the configuration.

[0045] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for receiving a second message that includes an indication of a second dictionary associated with a second channel between the UE and the network entity based on a change in one or more conditions on which the dictionary may depend.

[0046] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0047] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining corresponding training samples at one or more locations of the UE, one or more times of the day, or a combination thereof, wherein the one or more channel estimates may be based on the corresponding training samples.

[0048] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, using the sparse recovery technique to generate the one or more channel estimates may include operations, features, components, or instructions for performing the following operations: generating the one or more channel estimates using an orthogonal matching pursuit (OMP) algorithm.

[0049] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the message includes a radio resource control message.

[0050] A method for wireless communication at a network entity is described. The method may include: receiving from each UE of a set of one or more UEs a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity; computing a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates; and sending a message including an indication of the dictionary to the UE.

[0051] An apparatus for wireless communication at a network entity is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executed by the processor to cause the apparatus to: receive from each UE of a set of one or more UEs a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity; calculate a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates; and send a message including an indication of the dictionary to the UE.

[0052] Another apparatus for wireless communication at a network entity is described. The apparatus may include: means for receiving, from each UE in a set of one or more UEs, a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity; means for calculating, based on a learning procedure using the one or more channel estimates, a dictionary associated with a sparse channel representation of a channel between the UE and the network entity; and means for sending a message including an indication of the dictionary to the UE.

[0053] A non-transitory computer-readable medium storing code for wireless communication at a network entity is described. The code may include instructions executable by a processor to: receive from each UE of a set of one or more UEs a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity; calculate a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates; and send a message including an indication of the dictionary to the UE.

[0054] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: receiving a feedback message indicating the sparse channel representation of the channel between the UE and the network entity after sending the dictionary, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

[0055] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: estimating the channel between the UE and the network entity using the dictionary and the sparse channel representation; and performing a beam management procedure for selecting one or more directional beams based on estimating the channel.

[0056] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending a signal indicating a configuration for sending the sparse channel representation of a certain number of dominant paths for the channel, wherein receiving the feedback message can be based on the configuration.

[0057] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the feedback message may include operations, features, components, or instructions for receiving an identifier of the dictionary associated with the sparse channel representation along with the feedback message.

[0058] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending, in the message, an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary is applicable.

[0059] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending in the message an indication of a set of one or more conditions to which the dictionary is applicable, the set of one or more conditions comprising a geographic location, a time of day, a zone, or a combination thereof.

[0060] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: sending a signal indicating a configuration for sending the one or more channel estimates for a certain number of dominant paths for the channel, wherein the network entity receives the one or more channel estimates for the number of dominant paths.

[0061] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a second message that includes an indication of a second dictionary associated with a second channel between the UE and the network entity based on a change in one or more conditions on which the dictionary may depend.

[0062] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0063] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the corresponding signal indicative of the one or more channel estimates includes a compressed version of the one or more channel estimates.

[0064] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for performing the following operations: calculating the dictionary may be based on each UE in the set of one or more UEs having the same antenna configuration, being associated with the same manufacturer, being the same model, being the same type, or a combination thereof.

[0065] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the message includes a radio resource control message. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figures 1 to 3 An example of a wireless communication system supporting signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is illustrated.

[0067] Figure 4 and Figure 5An example of a process flow in a system that supports signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is illustrated.

[0068] Figure 6 and Figure 7 A block diagram of a device supporting signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is shown.

[0069] Figure 8 A block diagram of a communications manager supporting signaling for a dictionary learning technique for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0070] Fig. 9 A diagram of a system including a device supporting signaling for a dictionary learning technique for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0071] Fig.10 and Fig.11 A block diagram of a device supporting signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is shown.

[0072] Fig.12 A block diagram of a communications manager supporting signaling for a dictionary learning technique for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0073] Fig.13 A diagram of a system including a device supporting signaling for a dictionary learning technique for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0074] Figures 14 to 19 A flow chart illustrating a method of supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. DETAILED DESCRIPTION

[0075] Some wireless communication systems (e.g., millimeter wave (mmW) wireless communication systems) may support beam selection techniques that allow user equipment (UE) and network entities to communicate by selecting one or more optimal beams for communication between network devices. In some cases, the selection of beams may be based on a set of directional beams established by a predefined codebook. For example, the UE or network entity may perform original channel estimation (e.g., using beamformed channel measurements) to support digital beamforming. The original channel may refer to a communication channel between the network entity and the UE when beamforming is not present, and the channel information associated with the original channel may be applicable to signaling between the network entity and the UE, such as beamformed signaling using a beam pair link. The beam pair link may include a predefined transmit beam and a predefined receive beam based on a predefined codebook configured by the network. However, the predefined codebook may constrain the UE and the network entity to a relatively limited number of directional beams, which may result in inefficiency. Additionally, when performing raw channel estimation, in some cases, the channel estimation may be based on a total number of possible beamformed channel measurements, which may be based on each beam direction available at the network entity and the UE. However, measuring each possible transmit beam and receive beam combination may result in a relatively large overhead (e.g., due to the amount of measurements performed). In such cases, the overhead for channel estimation may consume a relatively large amount of resources and may result in increased inefficiency.

[0076] Techniques for enabling a UE, a network entity, or both to use dictionary learning to determine channel information (which can then be used to select a customized beam for communication) are described herein. In such cases, using dictionary learning techniques for raw channel estimation can result in identifying a relatively larger number of beam directions than using a predefined codebook. Additionally, dictionary learning techniques allow raw channel estimation to be performed without having to perform beamformed channel measurements associated with each beam direction. Dictionary learning may include reconstructing a channel by estimating information from the raw channel using a sparse dictionary derived from the raw channel data. For example, as the UE moves around a cell, the UE may record the raw channel estimate to serve as a training sample for the dictionary. In some cases, the UE may meet a threshold of training samples to determine (e.g., estimate, infer) a sparse dictionary, and when learning the sparse dictionary, the UE may report the sparse dictionary to the network entity. In one example, the network entity may send (e.g., relay) a sparse dictionary to similar UEs (e.g., UEs with the same antenna configuration, UEs with the same brand, model, or other similar capabilities or characteristics) so that these UEs may use the sparse dictionary for communication in the cell.

[0077] Alternatively, the UE or multiple similar UEs may send raw channel estimates to the network entity. The network entity may classify the raw channel estimates from one UE or from multiple similar UEs and determine (e.g., estimate, infer) a sparsification dictionary for each UE and / or for each group of similar UEs. In such cases, the network entity may determine a different sparsification dictionary for each group of similar UEs. The network entity may send an indication of the sparsification dictionary to the respective UE.

[0078] Upon determining and / or receiving the sparsification dictionary, the UE may send an original channel estimate to the network entity, where the original channel estimate may be a sparse channel representation. The UE, the network entity, or both may use the sparsification dictionary and the original channel estimate to determine the original channel (e.g., reconstruct the original channel), and in some cases, the UE, the network entity, or both may perform beam management to select one or more optimal beams between the UE and the network entity based on the original channel estimate. For example, the UE, the network entity, or both may perform a grid search on the oversampled codebook beams based on the determined original channel to find the best beam pair.

[0079] Certain aspects of the subject matter described herein may be implemented to achieve one or more advantages. The described techniques for performing raw channel estimation using dictionary learning may enable selection of custom beamforming directions that may not be included in a set of beams from a predefined codebook. The described techniques may support improved performance, increased efficiency, and reduced overhead of wireless communications. Thus, supported techniques may include improved network operation, and in some examples, increased network efficiency, etc.

[0080] Various aspects of the present disclosure are first described in the context of a wireless communication system. Various aspects of the present disclosure are illustrated by process flows and described with reference to process flows. Various aspects of the present disclosure are further illustrated by device diagrams, system diagrams, and flow diagrams related to signaling for dictionary learning techniques for channel estimation and described with reference to these diagrams.

[0081] Figure 1 An example of a wireless communication system 100 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is illustrated. The wireless communication system 100 may include one or more network entities 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, a New Radio (NR) network, or a network operating according to other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.

[0082] The network entities 105 may be dispersed throughout a geographic area to form the wireless communication system 100, and may include devices in different forms or with different capabilities. In various examples, the network entities 105 may be referred to as network elements, mobility elements, radio access network (RAN) nodes, or network equipment, among other nomenclature. In some examples, the network entities 105 and the UE 115 may communicate wirelessly via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, the network entity 105 may support a coverage area 110 (e.g., a geographic coverage area) within which the UE 115 and the network entity 105 may establish one or more communication links 125. The coverage area 110 may be an example of a geographic area within which the network entity 105 and the UE 115 may support signal communications according to one or more radio access technologies (RATs).

[0083] The UEs 115 may be dispersed throughout the coverage area 110 of the wireless communication system 100, and each UE 115 may be stationary or mobile, or both stationary and mobile at different times. The UEs 115 may be devices in different forms or with different capabilities. Figure 1 Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be able to communicate with various types of devices such as Figure 1 Other UEs 115 or network entities 105 are shown communicating.

[0084] As described herein, a node of the wireless communication system 100 (which may be referred to as a network node or a wireless node) may be a network entity 105 (e.g., any network entity described herein), a UE 115 (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, the node may be a UE 115. As another example, the node may be a network entity 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a network entity 105. In other aspects of this example, the first node, the second node, and the third node may be different relative to these examples. Similarly, references to UE 115, network entity 105, apparatus, device, computing system, etc. may include disclosure of UE 115, network entity 105, apparatus, device, computing system, etc. as nodes. For example, a disclosure that UE 115 is configured to receive information from network entity 105 also discloses that the first node is configured to receive information from a second node.

[0085] In some examples, the network entities 105 may communicate with the core network 130, or communicate with each other, or both. For example, the network entities 105 may communicate with the core network 130 via one or more backhaul communication links 120 (e.g., according to S1, N2, N3 or other interface protocols). In some examples, the network entities 105 may communicate with each other through the backhaul communication link 120 (e.g., according to X2, Xn or other interface protocols) directly (e.g., directly between each network entity 105) or indirectly (e.g., via the core network 130). In some examples, the network entities 105 may communicate with each other via the midhaul communication link 162 (e.g., according to the midhaul interface protocol) or the fronthaul communication link 168 (e.g., according to the fronthaul interface protocol) or any combination thereof. The backhaul communication link 120, the midhaul communication link 162, or the fronthaul communication link 168 may be or include one or more wired links (e.g., electrical links, optical fiber links), one or more wireless links (e.g., radio links, wireless optical links), etc. or various combinations thereof. UE 115 may communicate with core network 130 via communication link 155 .

[0086] One or more of the network entities 105 described herein may include or may be referred to as a base station 140 (e.g., a transceiver base station, a radio base station, an NR base station, an access point, a radio transceiver, a Node B, an evolved Node B (eNB), a next generation Node B, or a Gigabit Node B (any of which may be referred to as a gNB), a 5G NB, a next generation eNB (ng-eNB), a Home Node B, a Home Evolved Node B, or other suitable terminology). In some examples, the network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, stand-alone) base station architecture, which may be configured to utilize a protocol stack physically or logically integrated within a single network entity 105 (e.g., a single RAN node, such as a base station 140).

[0087] In some examples, the network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that may be configured to utilize a protocol stack that is physically or logically distributed between two or more network entities 105, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, the network entity 105 may include one or more of the following: a central unit (CU) 160, a distributed unit (DU) 165, a radio unit (RU) 170, a RAN intelligent controller (RIC) 175 (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) 180 system, or any combination thereof. The RU 170 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmit receive point (TRP). One or more components of the network entity 105 in the decomposed RAN architecture may be co-located, or one or more components of the network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 of the decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0088] The functional split between CU 160, DU 165, and RU 175 is flexible and may support different functions, depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, and any combination thereof) are performed at CU 160, DU 165, or RU 175. For example, a functional split of a protocol stack may be employed between CU 160 and DU 165 such that CU 160 may support one or more layers of a protocol stack and DU 165 may support one or more different layers of a protocol stack. In some examples, CU 160 may host higher protocol layer (e.g., layer 3 (L3), layer 2 (L2)) functions and signaling (e.g., radio resource control (RRC), service data adaptation protocol (SDAP), packet data convergence protocol (PDCP)). The CU 160 may be connected to one or more DUs 165 or RUs 170, and the one or more DUs 165 or RUs 170 may host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functions and signaling, and may each be at least partially controlled by the CU 160. Additionally or alternatively, a functional split of the protocol stack may be employed between the DUs 165 and RUs 170, such that the DUs 165 may support one or more layers of the protocol stack, and the RUs 170 may support one or more different layers of the protocol stack. The DUs 165 may support one or more different cells (e.g., via one or more RUs 170). In some cases, the functional split between CU 160 and DU 165 or between DU 165 and RU 170 can be within the protocol layer (e.g., some functions of the protocol layer can be performed by one of CU 160, DU 165, or RU 170, while other functions of the protocol layer are performed by different ones of CU 160, DU 165, or RU 170). CU 160 can be further functionally split into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 160 can be connected to one or more DUs 165 via midhaul communication links 162 (e.g., F1, F1-c, F1-u), and DU 165 can be connected to one or more RUs 170 via fronthaul communication links 168 (e.g., open fronthaul (FH) interface). In some examples, midhaul communication link 162 or fronthaul communication link 168 may be implemented based on interfaces (eg, channels) between layers of a protocol stack supported by respective network entities 105 that communicate over those communication links.

[0089] In some wireless communication systems (e.g., wireless communication system 100), infrastructure and spectrum resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture (e.g., to core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB nodes 104) may be partially controlled by each other. One or more IAB nodes 104 may be referred to as donor entities or IAB donors. One or more DUs 165 or one or more RUs 170 may be controlled in part by one or more CUs 160 associated with a donor network entity 105 (e.g., donor base station 140). One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB nodes 104) via supported access and backhaul links (e.g., backhaul communication links 120). The IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a coupled IAB donor's DU 165. The IAB-MT may include an independent set of antennas for relaying communications with the UE 115, or may share the same antennas of the IAB node 104 (e.g., of the RU 170) for access via the DU 165 of the IAB node 104 (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, the IAB node 104 may include a DU 165 that supports communication links with additional entities (e.g., IAB node 104, UE 115) within a relay chain or configuration (e.g., downstream) of the access network. In such cases, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of the IAB node 104) may be configured to operate according to the techniques described herein.

[0090] In the case where the techniques described herein are applied to the context of a decomposed RAN architecture, one or more components of the decomposed RAN architecture may be configured to support signaling for dictionary learning techniques for channel estimation as described herein. For example, some operations described as being performed by a UE 115 or a network entity 105 (e.g., a base station 140) may additionally or alternatively be performed by one or more components of the decomposed RAN architecture (e.g., an IAB node 104, a DU 165, a CU 160, a RU 170, a RIC 175, a SMO 180).

[0091] UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable term, where a "device" may also be referred to as a unit, a station, a terminal, or a client, etc. UE 115 may also include or may be referred to as a personal electronic device, such as a cellular phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some examples, UE 115 may include or may be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0092] The UE 115 described herein may be capable of communicating with various types of devices such as other UEs 115 which may sometimes act as relays, as well as network entities 105 and network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, etc. Figure 1 shown.

[0093] The UE 115 and the network entity 105 may wirelessly communicate with each other via one or more communication links 125 (e.g., access links) on one or more carriers. The term "carrier" may refer to a set of RF spectrum resources having a physical layer structure defined for supporting the communication link 125. For example, a carrier for the communication link 125 may include a portion of an RF spectrum band (e.g., a bandwidth portion (BWP)) that operates 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 for coordinating carrier operations, user data, or other signaling. The wireless communication system 100 may support communications with the UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, the UE 115 may be configured to have multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation may be used for both frequency division duplex (FDD) and time division duplex (TDD) component carriers. Communication between the network entity 105 and other devices may refer to communication between these devices and any portion (e.g., entity, sub-entity) of the network entity 105. For example, the terms "send," "receive," or "communicate" when referring to the network entity 105 may refer to any portion of a network entity 105 (e.g., base station 140, CU 160, DU 165, RU 170) of a RAN communicating with another device (e.g., directly or via one or more other network entities 105).

[0094] In some examples, such as in a carrier aggregation configuration, a carrier may also have acquisition signaling or control signaling that coordinates the operation of other carriers. A carrier may be associated with a frequency channel (e.g., an Evolved Universal Mobile Telecommunications System Terrestrial Radio Access (E-UTRA) Absolute RF Channel Number (EARFCN)) and may be located according to a channel raster for discovery by UE 115. A carrier may operate in a standalone mode, in which case initial acquisition and connection may be made by UE 115 via the carrier, or a carrier may operate in a non-standalone mode, in which case a different carrier (e.g., of the same or different radio access technology) is used to anchor the connection.

[0095] The communication link 125 shown in the wireless communication system 100 may include downlink transmissions (e.g., forward link transmissions) from the network entity 105 to the UE 115, uplink transmissions (e.g., return link transmissions) from the UE 115 to the network entity 105, or both, as well as other transmission configurations. A carrier may carry downlink communications or uplink communications (e.g., in FDD mode), or may be configured to carry downlink communications and uplink communications (e.g., in TDD mode).

[0096] A carrier may be associated with a particular bandwidth of the RF spectrum, and in some examples, the carrier bandwidth may be referred to as the "system bandwidth" of the carrier or wireless communication system 100. For example, the carrier bandwidth may be one of a set of bandwidths of carriers for a particular radio access technology (e.g., 1.4 megahertz (MHz), 3 MHz, 5 MHz, 10 MHz, 15 MHz, 20 MHz, 40 MHz, or 80 MHz). A device of the wireless communication system 100 (e.g., a network entity 105, a UE 115, or both) may have a hardware configuration that supports communication on a particular carrier bandwidth or may be configurable to support communication on one of a set of carrier bandwidths. In some examples, the wireless communication system 100 may include a network entity 105 or a UE 115 that supports concurrent communication via carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured to operate on a portion (e.g., a subband, a BWP) or all of a carrier bandwidth.

[0097] The signal waveform transmitted by the carrier may include multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system using MCM technology, a resource element may refer to a symbol period (e.g., the duration of a modulation symbol) and a resource of a subcarrier, in which case the symbol period and the subcarrier spacing may be inversely related. The number of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both), so that the more resource elements a device receives and the higher the order of the modulation scheme, the higher the data rate of the device may be. Wireless communication resources may refer to a combination of RF spectrum resources, time resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial resources may increase the data rate or data integrity used for communication with UE 115.

[0098] One or more numerologies of a carrier may be supported, where the numerologies may include subcarrier spacing (Δf) and cyclic prefixes. A carrier may be divided into one or more BWPs with the same or different numerologies. In some examples, a UE 115 may be configured with multiple BWPs. In some examples, a single BWP of a carrier may be active at a given time, and communications of a UE 115 may be constrained to one or more active BWPs.

[0099] The time interval for the network entity 105 or the UE 115 may be expressed as a multiple of a basic time unit, which may be, for example, a sampling period T s =1 / (Δf max ·N f ) seconds, where Δf max It can represent the maximum supported subcarrier spacing, and N f The maximum supported discrete Fourier transform (DFT) size may be indicated. Time intervals of communication resources may be organized according to radio frames, each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0100] 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 into subframes (e.g., in the time domain), and each subframe may be further divided into a certain number of 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 a certain number of symbol periods (e.g., depending on the length of the cyclic prefix appended in front of each symbol period). In some wireless communication systems 100, the time slot may be further divided into multiple micro-time slots containing one or more symbols. Excluding the cyclic prefix, each symbol period may contain one or more (e.g., N f The duration of a symbol period may depend on the subcarrier spacing or the operating frequency band.

[0101] A subframe, slot, mini-slot, or symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communication system 100 and may be referred to as a transmit time interval (TTI). In some examples, the TTI duration (e.g., the number of symbol periods in a TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of a shortened TTI (sTTI)).

[0102] Physical channels may be multiplexed on a carrier according to various techniques. Physical control channels and physical data channels may be multiplexed on a downlink carrier using, for example, one or more of a time division multiplexing (TDM) technique, a frequency division multiplexing (FDM) technique, or a hybrid TDM-FDM technique. A control region (e.g., a control resource set (CORESET)) of a physical control channel may be defined by a set of symbol periods and may extend across a system bandwidth of a carrier or a subset of that system bandwidth. One or more control regions (e.g., CORESETs) may be configured for a set of UEs 115. For example, one or more UEs in UE 115 may monitor or search a control region to obtain control information according to one or more search space sets, and each search space set may include one or more control channel candidates in one or more aggregation levels arranged in a cascaded manner. The aggregation level of a control channel candidate may refer to the amount 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 sets may include a common search space set configured for transmitting control information to multiple UEs 115 , and a UE-specific search space set for transmitting control information to a specific UE 115 .

[0103] The network entity 105 may provide communication coverage via one or more cells (e.g., macro cells, small cells, hot spots, or other types of cells, or any combination thereof). The term "cell" may refer to a logical communication entity used to communicate with the network entity 105 (e.g., via a carrier), and may be associated with an identifier (e.g., a physical cell identifier (PCID), a virtual cell identifier (VCID), or other cell identifier) ​​used to distinguish adjacent cells. In some examples, a cell may also refer to a coverage area 110 or a portion of a coverage area 110 (e.g., a sector) within which the logical communication entity operates. Depending on various factors such as the capabilities of the network entity 105, such cells may range from smaller areas (e.g., structures, subsets of structures) to larger areas. For example, a cell may be or may include a building, a subset of a building, or an external space between or overlapping coverage areas 110, and the like.

[0104] A macro cell generally covers a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access to UEs 115 that have service subscriptions with a network provider that supports the macro cell. Small cells may be associated with lower power network entities 105 (e.g., lower power base stations 140) compared to macro cells, and small cells may operate in the same or different (e.g., licensed, unlicensed) frequency bands as macro cells. Small cells may provide unrestricted access to UEs 115 that have service subscriptions with a network provider, or may provide restricted access to UEs 115 associated with small cells (e.g., UEs 115 in a closed subscriber group (CSG), UEs 115 associated with users in a home or office). A network entity 105 may support one or more cells, and may also use one or more component carriers to support communications on one or more cells.

[0105] In some examples, a carrier may support multiple cells, and different cells may be configured according to different protocol types (e.g., MTC, narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB)) that may provide access to different types of devices.

[0106] In some examples, the network entities 105 (e.g., base stations 140, RUs 170) may be mobile and thus provide communication coverage for mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 provide coverage for various coverage areas 110 using the same or different radio access technologies.

[0107] The wireless communication system 100 may support synchronous or asynchronous operation. For synchronous operation, the network entities 105 (e.g., base stations 140) may have similar frame timing, and transmissions from different network entities 105 may be approximately aligned in time. For asynchronous operation, the network entities 105 may have different frame timing, and in some examples, transmissions from different network entities 105 may not be aligned in time. The techniques described herein may be used for either synchronous operation or asynchronous operation.

[0108] The wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication or various combinations thereof. For example, the wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable or low-latency or critical functions. Ultra-reliable communication may include private communication or group communication, and may be supported by one or more services (such as push-to-talk, video, or data). Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, and ultra-reliable low-latency may be used interchangeably herein.

[0109] In some examples, a UE 115 may be able to communicate directly with other UEs 115 over a device-to-device (D2D) communication link 135 (e.g., according to a peer-to-peer (P2P), D2D, or sidelink protocol). In some examples, one or more UEs 115 in a group that are performing D2D communication may be within a coverage area 110 of a network entity 105 (e.g., a base station 140, a RU 170), which may support aspects of such D2D communication configured or scheduled by the network entity 105. In some examples, one or more UEs 115 in such a group may be outside of the coverage area 110 of the network entity 105, or may otherwise be unable or not configured to receive transmissions from the network entity 105. In some examples, a group of UEs 115 communicating via D2D communication may support a one-to-many (1:M) system, in which each UE 115 transmits to each of the other UEs 115 in the group. In some examples, the network entity 105 may facilitate scheduling of resources for D2D communication. In some other examples, D2D communications may be performed between UEs 115 without involving network entity 105 .

[0110] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or a 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) for managing access and mobility and at least one user plane entity (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)) for routing packets or interconnecting to an external network. The control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management of UE 115 served by a network entity 105 (e.g., a base station 140) associated with the core network 130. User IP packets may be delivered through the user plane entity, which may provide IP address allocation and other functions. The user plane entity may be connected to the IP service 150 of one or more network operators. IP services 150 may include access to the Internet, an intranet, an IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0111] The wireless communication system 100 may operate using one or more frequency bands that may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). Generally speaking, the region from 300 MHz to 3 GHz is referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelength ranges from about one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features (which may be referred to as clusters), but these waves may be sufficient to penetrate structures so that macro cells provide services to UEs 115 located indoors. Transmission of UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than 100 kilometers) compared to transmission using smaller frequencies and longer wavelengths of the high frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz.

[0112] The wireless communication system 100 can utilize both licensed RF spectrum bands and unlicensed RF spectrum bands. For example, the wireless communication system 100 can use license assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology in an unlicensed band (such as the 5 GHz industrial, scientific, and medical (ISM) band). When operating in an unlicensed RF spectrum band, devices such as network entity 105 and UE 115 can use carrier sensing for conflict detection and avoidance. In some examples, operations in an unlicensed band can be based on a carrier aggregation configuration (e.g., LAA) in combination with component carriers operating in a licensed band. Operations in an unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, and the like.

[0113] The network entity 105 (e.g., base station 140, RU 170) or UE 115 may be equipped with multiple antennas that can be used to employ technologies such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of the network entity 105 or UE 115 may be located in one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly, such as an antenna tower. In some examples, antennas or antenna arrays associated with the network entity 105 may be located at different geographical locations. The network entity 105 may have an antenna array having a collection of multiple rows and columns of antenna ports that the network entity 105 can use to support beamforming for communications with the UE 115. Similarly, the UE 115 may have one or more antenna arrays that may support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals sent via the antenna ports.

[0114] The network entity 105 or UE 115 may use MIMO communication to utilize multipath signal propagation and improve spectral efficiency by sending or receiving multiple signals via different spatial layers. Such a technology may be referred to as spatial multiplexing. The multiple signals may be sent, for example, by a transmitting device via different antennas or different combinations of antennas. Similarly, the multiple signals may be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers may be associated with different antenna ports for channel measurement and reporting. MIMO technology includes single-user MIMO (SU-MIMO) and multi-user MIMO (MU-MIMO), in which multiple spatial layers are sent to the same receiving device and in which multiple spatial layers are sent to multiple devices.

[0115] Beamforming (which may also be referred to as spatial filtering, directional transmission, or directional reception) is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or direct an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining signals conveyed via antenna elements of an antenna array so that some signals propagating in a particular direction relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to signals conveyed via antenna elements may include the transmitting device or the receiving device applying an amplitude offset, a phase offset, or both to signals carried via antenna elements associated with the device. Adjustments associated with each of these antenna elements may be defined by a set of beamforming weights associated with a particular direction (e.g., relative to the antenna array of the transmitting device or the receiving device or relative to some other direction).

[0116] The network entity 105 or UE 115 may use beam scanning techniques as part of a beamforming operation. For example, the network entity 105 (e.g., base station 140, RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be sent multiple times by the network entity 105 along different directions. For example, the network entity 105 may send signals according to different sets of beamforming weights associated with different transmission directions. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device (such as network entity 105), or by a receiving device (such as UE 115)) beam directions for later transmission or reception by the network entity 105.

[0117] Some signals, such as data signals associated with a particular receiving device, may be sent by a transmitting device (e.g., transmitting network entity 105, transmitting UE 115) along a single beam direction (e.g., a direction associated with a receiving device (such as receiving network entity 105 or receiving UE 115)). In some examples, the beam direction associated with the transmission along the single beam direction may be determined based on signals sent along one or more beam directions. For example, UE 115 may receive one or more of the signals sent by network entity 105 along different directions, and may report to network entity 105 an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.

[0118] In some examples, transmission by a device (e.g., by network entity 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from network entity 105 to UE 115). UE 115 may report feedback indicating precoding weights for one or more beam directions, and the feedback may correspond to a configured set of beams across a system bandwidth or one or more subbands. Network entity 105 may send reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)), which may or may not be precoded. UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., multi-panel codebook, linear combination codebook, port selection codebook). Although these techniques are described with reference to signals sent along one or more directions by a network entity 105 (e.g., base station 140, RU 170), UE 115 may use similar techniques to send signals multiple times along different directions (e.g., to identify a beam direction for subsequent transmission or reception by UE 115), or to send signals along a single direction (e.g., to send data to a receiving device).

[0119] A receiving device (e.g., UE 115) may perform receiving operations according to multiple receiving configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a receiving device (e.g., network entity 105). For example, the receiving device may perform reception according to 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) applied to signals received at multiple antenna elements of an antenna array, or processing the received signals according to different receiving beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as "listening" according to different receiving configurations or receiving directions. In some examples, the receiving device may use a single receiving configuration to receive along a single beam direction (e.g., when receiving a data signal). A single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or other acceptable signal quality based on listening according to multiple beam directions).

[0120] The wireless communication system 100 can be a packet-based network that operates according to a layered protocol stack. In the user plane, the communication at the bearer or PDCP layer can be IP-based. The RLC layer can perform packet segmentation and reorganization to communicate through logical channels. The MAC layer can perform priority processing and multiplexing of logical channels into transport channels. The MAC layer can also use error detection technology, error correction technology, or both to support retransmission at the MAC layer to improve link efficiency. In the control plane, the RRC protocol layer can provide the establishment, configuration and maintenance of the RRC connection of the radio bearer that supports user plane data between the UE 115 and the network entity 105 or the core network 130. At the PHY layer, the transport channel can be mapped to the physical channel.

[0121] UE 115 and network entity 105 may support retransmission of data to increase the likelihood of data being successfully received. Hybrid automatic repeat request (HARQ) feedback is a technique for increasing the likelihood of correctly receiving data through a communication link (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC)), forward error correction (FEC), and retransmission (e.g., automatic repeat request (ARQ)). HARQ can improve throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, a device may support simultaneous slot HARQ feedback, wherein the device may provide HARQ feedback in a specific time slot for data received in a previous symbol in the time slot. In some other examples, the device may provide HARQ feedback in a subsequent time slot or according to some other time interval.

[0122] In some examples, wireless communication between devices (such as between network entity 105 and UE 115) can be performed using multiple beam directions, and the devices can use analog beamforming or digital beamforming to select the best beam for communication. In analog beamforming, the beam is controlled by adjusting the analog phase shifter along the radio frequency path. Therefore, there may be a phase shifter and a common analog-digital-analog converter (ADC) for each antenna element. In digital beamforming, the phase and amplitude are digitally controlled, and an ADC may exist for each antenna element. In some examples, UE 115 may estimate the channel using beamformed channel measurements (e.g., determined during a beam management procedure). For example, UE 115 or network entity 105 may perform original channel estimation to support digital beamforming. The original channel may refer to the communication channel between network entity 105 and UE 115 when beamforming is not present. In raw channel estimation, the device may estimate the channel based on a total number of possible beamformed channel measurements, which may be based on a total number of beams available at the network entity 105 and the UE 115 (e.g., which may also be based on a total number of available antenna ports at the network entity 105 and the UE 115).

[0123] In some cases, the channel matrix may have two dimensions, where a first dimension may correspond to the number of beams available at the network entity 105 and a second dimension may correspond to the number of beams available at the UE 115. For example, the first dimension of the channel matrix may be equal to the total number of antenna ports at the network entity 105 and the second dimension of the channel matrix may be equal to the total number of antenna ports at the UE 115 (e.g., if the UE 115 has 8 antenna ports and the network entity has 64 antenna ports, the channel matrix may be 8×64 and may include 512 elements (e.g., the total number of possible beamformed channel measurements)). Thus, when performing raw channel estimation, in some cases, the channel estimation may be based on the total number of possible beamformed channel measurements, which may be based on each beam direction available at the network entity 105 and the UE 115. However, measuring every possible transmit beam and receive beam combination may result in a relatively large overhead (e.g., due to the amount of measurements performed). In such cases, the overhead for channel estimation may consume a relatively large amount of resources and may result in increased inefficiency.

[0124] The wireless communication system 100 may support techniques for performing raw channel estimation (e.g., estimating a base raw channel, or a channel independent of which specific beams are used for communication) using a relatively small number of beamformed measurements, for example, based on the sparsity of the mmW channel. The raw channel estimation may include estimating a channel matrix corresponding to the original channel, wherein a compressed representation (e.g., a sparse representation) of the channel matrix may also be derived from the original channel. The device may utilize a sparse recovery algorithm (e.g., orthogonal matching pursuit (OMP) or any other compressed sensing technique) to determine the sparse representation and reconstruct the base raw channel. For example, the channel between the UE 115 and the network entity 105 may be sparse in the angular domain, so that there may be several dominant paths between the UE 115 and the network entity 105. Therefore, the sparsity of the channel may be utilized to perform channel estimation. The OMP algorithm may be associated with an iterative algorithm for determining an optimal beam direction based on a quantized set of significant paths. Dictionary learning may include reconstructing the channel by estimating information from the original channel using a sparse dictionary derived from the original channel data. The sparse dictionary may consist of atoms that are elements indicating channel information. In some examples, when determining the sparse representation, the device may generate a quantized sparse channel representation to determine a significant path (eg, a dominant path) in the channel. The dominant path may be associated with a significant beam index for channel estimation.

[0125] In some examples, the device may generate a quantized sparse channel representation by dividing the angular space at the UE 115 and the network entity 105 into an angular grid, wherein each angular grid is associated with a certain number of antenna ports and with an angular range (e.g., beam direction). In some cases, the UE 115 may determine the angular space to use the OMP algorithm. The angular range may be a range of azimuth angles, a range of elevation angles, or any combination thereof, and may correspond to an antenna port of the device, wherein two or more beams associated with the device may have directions within the indicated angular range. For example, the grid size may be based on the product of the number of azimuth angles at the UE 115, the number of elevation angles at the UE 115, the number of azimuth angles at the network entity 105, and the number of elevation angles at the network entity 105. Based on the angular grid, the device may determine the dominant path corresponding to a significant (e.g., best) beam in the channel, and the device may use the dominant path to estimate (e.g., reconstruct) the original channel through the OMP algorithm. The OMP algorithm may be an iterative algorithm that may select the best beam direction based on the number of dominant paths from the corresponding angular grid, so that the algorithm iterates for each dominant path. The device may use (e.g., run) an OMP algorithm, which may include iterating per dominant path and determining the best azimuth and elevation angles per dominant path until a criterion (e.g., a threshold) is met or until the device has run the OMP algorithm a certain number of times. However, in some examples, the device running the OMP algorithm may consume a relatively large amount of resources and may suffer from reduced efficiency due to multiple iterations.

[0126] Additionally or alternatively, the original channel estimation may also support separate selection (e.g., separate optimization) of transmit beams and receive beams (e.g., which may enhance analog or digital beamforming) compared to other techniques that may be limited to using a default codebook of beams (e.g., a codebook based on a discrete Fourier transform (DFT)). In some cases, the selection of the best beam may be based on a set of directional beams established by a predefined codebook. For example, channel information associated with the original channel may be applied to signaling between the network entity 105 and the UE 115, such as beamformed signaling using a beam pair link. The beam pair link may include a predefined transmit beam and a predefined receive beam based on a predefined codebook configured by the wireless network. However, the predefined codebook may constrain the UE 115 and the network entity 105 to a relatively limited number of directional beams, which may lead to further inefficiencies.

[0127] In some cases, the sparse recovery algorithm may utilize a predefined sparsification dictionary by partitioning the angular space into a two-dimensional (2D) grid, where the predefined sparsification dictionary may be based on a transmitter element response matrix (e.g., network entity 105 responses calculated at the 2D angular grid points) and a receiver element response matrix (e.g., UE 115 responses calculated at the 2D angular grid points). However, to reduce the complexity of the sparse recovery algorithm, the network device may be configured to perform dictionary learning to learn the sparsification dictionary directly from training data rather than relying on a predefined dictionary.

[0128] Because the sparsification dictionary is learned from training data, the network device may not recognize the correspondence between the sparsification basis and the angular domain. For example, dictionary learning may not be used to extract explicit angular information. Therefore, in order to implement a sparsification dictionary learned by dictionary, the oversampled codebook index may be predicted by non-oversampled codebook measurements. For example, the network device may be configured to use dictionary learning to estimate the underlying original channel from the beamformed measurement, and use the original channel estimate to identify the UE 115 and / or network entity 105 beam from the oversampled codebook.

[0129] For example, a network device (e.g., UE 115, network entity 105, or both) may identify the top numbered beam pair measurements and utilize dictionary learning to estimate the original channel between the network device and another network device. The network device may then perform a grid search on the sampled codebook beams to identify the best beam pair. The network device may then communicate with another network device using the identified best beam pair. In some cases, in order to perform such a procedure, it may be assumed that UE 115 knows the antenna element responses of network entity 105 and that UE 115 knows the oversampled network entity codebook. Additionally or alternatively, it may be assumed that UE 115 estimates the underlying original channel and infers the best beam pair from the oversampled codebook without actually measuring the oversampled codebook, thereby reducing overhead and reducing power consumption. Additionally or alternatively, it may be assumed that the mapping from the original channel estimate to the index of the best beam in the oversampled codebook may be accomplished using a trained neural network, machine learning, or the like.

[0130] To learn the sparse dictionary for the original channel, the network device may use information from the original channel between the network devices. However, since the device may not know the original channel in the air deployment (e.g., the "true" original channel), the network device may instead rely on an estimated original channel from a sparse recovery technique (such as OMP with a predefined dictionary).

[0131] The wireless communication system 100 may support techniques for using dictionary learning for the UE 115, the network entity 105, or both to determine channel information (which may then be used to select a customized beam for communication). In such cases, using dictionary learning techniques for raw channel estimation may allow a relatively larger number of beam directions to be identified compared to using a predefined codebook. Additionally, the dictionary learning techniques allow raw channel estimation to be performed without having to perform beamformed channel measurements associated with each beam direction. For example, as the UE 115 moves around a cell, the UE 115 may record raw channel estimates to serve as training samples for the dictionary. The UE 115 may meet a threshold of training samples to determine (e.g., estimate, infer) a sparse dictionary, and the UE 115 may report the learned sparse dictionary to the network entity 105. In one example, the network entity 105 may send the learned sparsified dictionary to similar UEs 115 (e.g., UEs 115 having the same antenna configuration, having the same brand, model, or other capabilities or characteristics that are the same between UEs 115) so that the UEs 115 can use the sparsified dictionary to communicate.

[0132] Additionally or alternatively, the UE 115 or a plurality of similar UEs 115 may send raw channel estimates to the network entity 105. The network entity 105 may classify the raw channel estimates from the similar UEs 115 and determine (e.g., estimate, infer) sparsified dictionaries for different groups of similar UEs 115. The network entity 105 may send the sparsified dictionaries to the respective UEs 115. In some cases, upon receiving the dictionary, the UE 115 may send the raw channel estimates, such as sparse channel representations, to the network entity 105. The UE 115, the network entity 105, or both may use the dictionary and the raw channel estimates to determine the raw channel, and in some cases, the UE 115, the network entity 105, or both may perform beam management to select one or more best beams between the UE 115 and the network entity 105. Thus, performing raw channel estimation using dictionary learning may enable selection of customized beamforming directions that may not be included in a set of beams from a predefined codebook, which may provide improved performance, increased efficiency, and reduced overhead for wireless communications.

[0133] Figure 2 An example of a wireless communication system 200 that supports signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is illustrated. In some examples, the wireless communication system 200 may implement aspects of the wireless communication system 100. For example, the wireless communication system 200 may include UE 115-a, UE 115-b, and network entity 105-a, which may be as described in reference Figure 1Described examples of UE 115 and network entity 105. In some examples, network entity 105-a, UE 115-a, and UE 115-b may be located in coverage area 110-a, which may be served by network entity 105-a or some other network device.

[0134] In some examples, network devices (e.g., network entity 105, UE 115, node) may communicate with each other via directional beams (e.g., channels, communication links such as uplink communication links, downlink communication links, and sidelink communication links). For example, network entity 105-a may communicate with UE 115-a via an uplink communication link and a downlink communication link. Similarly, network entity 105-a may communicate with UE 115-b via an uplink communication link and a downlink communication link. In some cases, UE 115-a and UE 115-b may communicate with each other via a sidelink communication link. In one example, UE 115-a may send information (e.g., data signal, control signal) to network entity 105-a via uplink communication link 210, and network entity 105-a may send information to UE 115-b (e.g., similar UE) via downlink communication link 205.

[0135] In some examples, network devices such as network entity 105-a and UE 115-a may undergo a beam management procedure to identify an optimal beam for communication between network entity 105-a and UE 115-a. Figure 1 As described, the UE 115-a, the network entity 105-a, or both may use dictionary learning to determine channel information, which may then be used to select a custom beam for communication, such as during a beam management procedure. For example, as the UE 115-a moves around a cell (e.g., the coverage area 110-a), the UE 115-a may record (e.g., obtain, store) raw channel estimates to use as training samples (e.g., raw channel estimates, raw channel realizations) for learning the dictionary 215 (e.g., the sparse dictionary 215). Thus, the UE 115-a may accumulate training samples over time, where each training sample may be a function of the time when the training sample was obtained and the location of the UE 115 (e.g., within the geographic coverage area 110-a). For example, channel information corresponding to the wireless communication system 200 may change over time (e.g., day versus night) or during different scenarios (e.g., relatively high traffic congestion, relatively low traffic congestion), and thus UE 115-a may record different training samples at different times (e.g., day or night), in different scenarios, at different locations, etc. to obtain a representative sample (e.g., a full sample) of the channel between UE 115-a and the network entity 105-a.

[0136] In some cases, the UE 115-a may be configured to determine the dictionary 215 using one or more of the training samples. In some examples, the UE 115-a may be configured with a threshold number of training samples to be obtained (e.g., stored) by the UE 115-a prior to learning the sparsified dictionary 215. In some cases, the UE 115-a may be pre-configured with the threshold number, receive an indication of the threshold number, or autonomously determine the threshold number of training samples. In some cases, the threshold number may be configured by the network entity 105-a, and the network entity 105-a may send an indication of the threshold number of training samples to the UE 115-a (e.g., via RRC signaling, MAC-CE signaling, downlink control information (DCI) signaling). Thus, the UE 115-a may meet the threshold number of training samples and use the training samples to learn the sparsified dictionary 215 (e.g., via one or more trained neural networks, via machine learning).

[0137] Additionally or alternatively, the UE 115-a may be configured with a set of parameters associated with computing the dictionary 215 (e.g., being pre-configured with the set of parameters, receiving an indication of the set of parameters, or autonomously determining the set of parameters). For example, the network entity 105-a may send a signal indicating the configuration of a set of one or more parameters for computing the dictionary 215. The set of parameters may include a stopping criterion, a number of atoms (e.g., information elements) to be included in the dictionary 215, an indication of a neural network, etc. The stopping criterion may indicate the end of a dictionary learning phase performed by the UE 115-a. For example, the stopping criterion may be a mean square error (MSE) between a training set and a validation set, where an MSE threshold may be configured by the network entity 105-a.

[0138] Thus, when the training sample threshold is met, the UE 115-a may use the training samples to generate an original channel estimate using a sparse recovery technique (e.g., an OMP algorithm), and the UE 115-a may calculate (e.g., learn) a dictionary 215, wherein the UE 115-a may stop the learning procedure when a stopping criterion is met. The UE 115-a may report the dictionary 215-a to the network entity 105-a via the uplink communication link 210, and in some cases, may report the dictionary 215 to one or more other UEs 115 (such as UE 115-b). In some examples, the learned sparse dictionary 215 may be applicable to devices of the same type (e.g., similar devices). Similar devices may refer to devices that share the same antenna configuration, devices of the same brand, model, etc. Thus, in the case where the UE 115-b is a device similar to the UE 115-a, the network entity 105-a and / or the UE 115-a may send the dictionary 215-b to the UE 115-b via the downlink communication link 205. Thus, in some cases, only one device may need to perform dictionary learning to obtain a learned sparsified dictionary 215 that can be shared across a collection of similar devices.

[0139] The network entity 105-a and the UE 115-a may use the learned sparsification dictionary 215 to determine the best beam pair between the network entity 105-a and the UE 115-a (e.g., by utilizing the original channel estimate derived using compressed sensing and / or a machine learning algorithm). Similarly, the network entity 105-a and the UE 115-b may use the learned sparsification dictionary 215 to determine the best beam pair between the network entity 105-a and the UE 115-b. For example, during the inference phase, the UE 115-a may use the learned dictionary 215 to estimate the underlying original channel. In some examples, the network entity 105-a may send a signal indicating the configuration of the sparse channel representation of the dominant path in the UE 115-a transmission channel. Thus, the UE 115-a may send the index of the non-zero elements in the sparse channel representation together with the quantized version of the non-zero elements, which greatly reduces overhead. Feedback of the sparse representation by UE 115 - a improves the overhead of the original channel feedback since UE 115 - a is sending few non-zero elements instead of a large number of original channel estimates.

[0140] Therefore, UE 115-a may report the sparse channel representation to network entity 105-a via uplink communication link 210 according to the configuration. Since network entity 105-a has sparsified dictionary 215, network entity 105-a may use dictionary 215 and the sparse channel representation from UE 115-a to reconstruct the estimated original channel. Network entity 105-a may use the estimated original channel in a number of ways, including beam management.

[0141] In some cases, the sparsification dictionary 215 may be associated with an identifier. For example, the UE 115-a may determine the identifier and send the identifier along with the learned sparsification dictionary 215. In some cases, the network entity 105-a may determine that the identifier corresponds to the sparsification dictionary 215 from the UE 115-a. In such cases, the network entity 105-a may send an indication of the identifier to the UE 115-a. In either case, the UE 115-a may include the identifier in a report including the sparse channel representation so that the network entity 105-a may identify which sparsification dictionary 215 was used to reconstruct the original channel.

[0142] In some implementations, if there is a change (e.g., a significant change) in the environment (e.g., based on the time of day, such as day versus night, or if the UE 115 moves to a new zone or coverage area 110), the dictionary 215 may need to be relearned because the original channel structure may be different. In some cases, the UE 115-a may autonomously determine to relearn the dictionary 215, and / or the UE 115-a may receive an indication to relearn the dictionary 215, such as via a signal from the network entity 105-a. Thus, upon learning the updated sparsified dictionary 215, the UE 115-a may send the updated dictionary 215 to the network entity 105-a.

[0143] Figure 3 An example of a wireless communication system 300 that supports signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is illustrated. In some examples, the wireless communication system 300 may implement aspects of the wireless communication system 100 and the wireless communication system 200. For example, the wireless communication system 300 may include UE 115-c, UE 115-d, and network entity 105-b, which may be as described in reference Figure 1 and Figure 2 Described examples of UE 115 and network entity 105. In some examples, UE 115-c, UE 115-d, and network entity 105-b may be located in coverage area 110-b, which may be served by network entity 105-b or some other network device.

[0144] In some examples, and as referenced Figure 2As described, network entity 105-b and UE 115-c may determine an optimal directional beam for communicating with each other. In one example, UE 115-c may send information (e.g., control information, data) to network entity 105-b via uplink communication link 305 (e.g., channel, beam), and network entity 105-b may send information (e.g., control information, data) to UE 115-c via downlink communication link 315-a and to UE 115-d (e.g., similar to UE 115) via downlink communication link 315-b.

[0145] In some examples, the network entity 105-b and the UE 115-c may undergo a beam management procedure to identify an optimal beam for communication between the network devices. In some examples, the wireless communication system 300 may perform beamformed channel measurements during the beam management procedure or during different operations for determining channel information (e.g., estimating a base original channel). As used herein, an original channel may refer to a communication channel between the network entity 105-b and the UE 115-c when beamforming is not present. Thus, the original channel (and associated channel state information) may be applicable to any signaling between the network entity 105-b and the UE 115-c, including beamformed signaling using any beam pair link (e.g., whether the beam pair link includes a codebook-based predefined transmit beam and a predefined receive beam, or whether the beam pair link includes one or more customized (e.g., non-codebook-based) beams).

[0146] As described herein, UE 115-c, UE 115-d, network entity 105-b, or a combination thereof may use dictionary learning to determine channel information, which may then be used to select a customized beam for communication between the devices. For example, as UE 115 moves around a cell (e.g., coverage area 110-b), UE 115-c and / or UE 115-d may be configured to record raw channel estimates for use as training samples for learning dictionary 310 (e.g., sparse dictionary 310). As described in reference Figure 2 As described, UE 115 may be configured with a training sample threshold. For example, each UE 115 may be pre-configured with a threshold number, receive an indication of the threshold number (e.g., via RRC signaling, via MAC control element (MAC-CE) signaling, via DCI signaling), or autonomously determine a threshold number of training samples, wherein each UE 115 may be configured with the same threshold, or configured with different thresholds. Thus, UE 115-c and UE 115-d collect training samples until each UE 115 meets the threshold number of training samples. Each training sample may be a function of the time and location of the corresponding UE 115 that obtained the training sample.

[0147] In some cases, the network entity 105-b may be configured to determine the dictionary 310 based on training samples obtained by one or more UEs 115, such as one or more UEs 115 in a zone (e.g., a subset of the coverage area 110-b), one or more UEs of the same type (e.g., similar devices sharing the same antenna configuration, devices with the same or similar brand, model, configuration, components, capabilities, etc.), one or more UEs in the coverage area 110-b, etc. In such cases, the UE 115 may be configured to send an indication of the training samples to the network entity 105-b. In some cases, each UE 115 may be configured to use a sparse recovery algorithm (e.g., OMP or other type of algorithm) to estimate the underlying original channel using the obtained training samples. In some cases, the UE 115 may be configured to feed back the original channel estimate to the network entity 105-b for learning the dictionary 310. In some examples, the network entity 105-b may configure the UE 115 to send the original channel estimate for a given number of dominant paths. In some implementations, each UE 115 may be configured to compress the raw channel estimates. For example, each UE 115 may be pre-configured to compress the estimates, receive an indication to compress the estimates (e.g., via RRC signaling, via MAC-CE signaling, via DCI signaling), or autonomously determine to compress the estimates, such as if the estimates exceed a threshold size. Each UE 115 may be configured to compress the estimates to a certain size. The UE 115 may perform compression via a trained autoencoder or other compression scheme, where the UE 115 may be pre-configured with a compression technique, receive an indication of a compression technique, or autonomously determine a compression technique.

[0148] When compressing the channel estimates, each UE 115 may send a compressed version of the original channel estimate (e.g., channel estimate 320) to the network entity 105-b. For example, one or both of UE 115-c and UE 115-d may send channel estimate 320 to the network entity 105-b. Thus, the network entity 105-b may receive the original channel estimates from one or more different UEs in a cell (e.g., zone and / or coverage area 110-b) over a time range. The network entity 105-b may use the compressed channel estimates from one or more of the UEs 115 to learn one or more sparsified dictionaries 310.

[0149] In some cases, the network entity 105-b may classify the raw channel estimates received from similar UEs 115 and determine a sparsified dictionary for a group of similar UEs 115 (e.g., dictionary 310-a for UE 115-c and dictionary 310-b for UE 115-d). In such cases, the network entity 105-b may learn a sparsified dictionary 310 for a group of similar UEs 115 based on channel estimates received from one or more of the UEs 115 in the group. The raw channel estimates used to calculate the learned dictionary 310 may be relatively more diverse due to the fact that multiple similar UEs 115 record raw channel data. Similarly, the network entity 105-b may calculate different dictionaries for different groups of UEs 115. For example, in some deployment scenarios, there may be multiple UEs 115 (e.g., 120 UEs), the network entity 105-b may learn a sparsified dictionary based on channel estimates for many of the UEs 115 (e.g., 100 UEs), and the network entity 105-b may test and validate the sparsified dictionary using the remaining UEs 115 (e.g., 20 UEs). The network entity 105-b may compute the learned sparsified dictionary 310 using one or more neural networks, machine learning, etc.

[0150] The network entity 105-b may send the dictionary 310 to the corresponding UE 115, such as via RRC signaling, MAC-CE signaling, and / or DCI signaling. For example, UE 115-c and UE 115-d may be similar UEs 115, so the network entity 105-b may send the learned dictionary 310 to one or both of UE 115-c and UE 115-d. In this example, the network entity 105-b may send the dictionary 310-a to UE 115-c via a downlink communication link 315-a, and the network entity 105-b may send the dictionary 310-b to UE 115-d via a downlink communication link 315-b, where the dictionary 310-a and the dictionary 310-b may be the same dictionary. In another example, UE 115-c and UE 115-d may not be similar UEs 115. Thus, network entity 105-b may compute dictionary 310-a for UE 115-c based on channel estimates from UE 115-c (or some other device similar to UE 115-c), and network entity 105-b may send dictionary 310-a to UE 115-c. Similarly, network entity 105-b may compute dictionary 310-b for UE 115-d based on channel estimates from UE 115-d (or some other device similar to UE 115-d), and network entity 105-b may send dictionary 310-b to UE 115-d, where dictionary 310-a and dictionary 310-b may be different.

[0151] In some examples, the network entity 105-b may send an indication of a zone, region, location, or any combination thereof (e.g., an applicable zone) corresponding to each dictionary 310. For example, the dictionary may be applicable to a specific location in the coverage area 110-b, applicable to a specific time, applicable to a specific condition, etc. Thus, the network entity 105-b may indicate to the UE 115 the conditions under which the dictionary 310 is applicable. In some implementations, the network entity 105-b may send a signal indicating which UEs 115 (e.g., which type of UE 115) the learned dictionary 310 is applicable to. In some cases, the signaling including the learned dictionary 310 may also include characteristics of the UE 115 to which the dictionary is applicable.

[0152] For example, the UE 115-c may move to another zone (e.g., another coverage area 110, or another zone within the coverage area 110-b), and / or network conditions may change and the learned dictionary 310-b may not be relevant in the new zone (and / or under the new conditions). In this example, the network entity 105-b or some other device may signal the dictionary 310 corresponding to the zone to the UE 115-c, and / or the network entity 105-b may configure the UE 115-c to send (retransmit) the original channel estimate associated with the new zone so that the network entity 105-b can calculate the learned dictionary 310 for the new zone. For example, the UE 115-c may move from an indoor deployment to an urban micro (Umi) deployment, and the UE 115-c may be configured with a new dictionary 310 for the Umi deployment via RRC signaling or some other control signaling.

[0153] The network entity 105-b and the UE 115 may then use the learned sparsification dictionary 310-b to determine the best beam pair between the network entity 105-b and each UE 115-c. Similarly, the network entity 105-b and the UE 115-d may use the learned sparsification dictionary 310-a to determine the best beam pair between the network entity 105-b and the UE 115-d. For example, during the inference phase, the UE 115-c may use the learned dictionary 310 to estimate the underlying original channel. In some examples, the network entity 105-b may send a signal indicating the configuration of the sparse channel representation of the dominant path in the UE 115-c transmission channel. Thus, the UE 115-c may send the index of the non-zero elements in the sparse channel representation together with the quantized version of the non-zero elements, which greatly reduces the overhead. Feedback of the sparse representation by the UE 115-c improves the overhead of the original channel feedback because the UE 115-c is sending a few non-zero elements instead of a large number of original channel estimates.

[0154] Therefore, UE 115-c may report the sparse channel representation to network entity 105-b via uplink communication link 305 according to the configuration. Since network entity 105-b has sparsified dictionary 310-a, network entity 105-b may use dictionary 310-a and sparse channel representation from UE 115-c to reconstruct the estimated original channel. Network entity 105-b may use the estimated original channel in a number of ways, including beam management.

[0155] Figure 4 An example of a process flow 400 in a system supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is illustrated. In some examples, the process flow 400 may implement or be implemented by aspects of the wireless communication system 100 and the wireless communication system 200. For example, the process flow 400 may be implemented by the network entity 105-c and the UE 115-e, which may be as described in reference Figure 1 and Figure 2 Examples of network entities 105 and UE 115 described. The following alternative examples may be implemented in which some of the steps are performed in a different order than described or not performed at all. In some cases, the steps may include additional features not mentioned below, or other steps may be added.

[0156] At 405, in some examples, the network entity 105-c may send a signal indicating a configuration for sending a sparse channel representation for a certain number of dominant paths. In some examples, the network entity 105-c may send a signal indicating a configuration for a threshold number of training samples to be obtained before computing a dictionary. In some cases, the network entity 105-c may send a signal indicating a configuration for a set of parameters for computing the dictionary. The set of parameters may include a criterion for stopping the learning procedure, a number of atoms to be included in the dictionary, or both.

[0157] At 410, UE 115-e may obtain a number of training samples. In some examples, UE 115-e may obtain the number of training samples that satisfies a threshold number of training samples. In some examples, UE 115-e may obtain corresponding training samples at one or more locations of UE 115-e, one or more times of day, or a combination thereof, where one or more channel estimates may be based on the corresponding training samples.

[0158] At 415, UE 115-e may use sparse recovery techniques to generate channel estimates for multiple channels between UE 115-e and network entity 105-c, wherein the one or more channel estimates may be based on one or more measurements using a set of directional beams. In some examples, UE 115-e may use sparse recovery techniques to generate the one or more estimates by using an OMP algorithm to generate the one or more channel estimates.

[0159] At 420, the UE 115-e may calculate a dictionary associated with a sparse channel representation of a channel between the UE 115-e and the network entity 105-c based on a learning procedure using one or more channel estimates. In some examples, the UE 115-e may calculate the dictionary based on the number of training samples satisfying a threshold number of training samples. In some examples, the UE 115-e may calculate the dictionary based on a set of parameters for configuring the dictionary. In some examples, the UE 115-e may calculate an updated dictionary based on a change in one or more conditions on which the dictionary depends, wherein the indication of the dictionary may include an indication of the updated dictionary. The one or more conditions may include a location of the UE 115-e relative to the network entity 105-c, a time of day, or both.

[0160] At 425, the UE 115-e may send a message including an indication of the dictionary to the network entity 105-c. In some examples, sending the message may be based on satisfying a threshold number of training samples.

[0161] At 430, UE 115-e may send a feedback message to network entity 105-c indicating a sparse channel representation between UE 115-e and network entity 105-c. The feedback message may include a set of indices of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation. In some examples, UE 115-e may send the feedback message based on a configuration for sending sparse channel representations for a certain number of dominant paths. In some examples, UE 115-e may send an identifier of a dictionary associated with the sparse channel representation with the feedback message.

[0162] At 435 , the network entity 105 - c may use the dictionary and the sparse channel representation to estimate a channel between the UE 115 - e and the network entity 105 - c .

[0163] At 440, the network entity 105-c may perform a beam management procedure for selecting one or more directional beams based on the dictionary. The beam management procedure may be based on estimating the channel. The network entity 105-c may communicate with the UE 115-e using the one or more directional beams.

[0164] Figure 5An example of a process flow 500 in a system supporting signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is illustrated. In some examples, the process flow 500 may implement or be implemented by aspects of the wireless communication system 100 and the wireless communication system 300. For example, the process flow 500 may be implemented by the network entity 105-d and the UE 115-f, which may be as described in reference to Figure 1 and Figure 3 Examples of network entities 105 and UE 115 described. The following alternative examples may be implemented in which some of the steps are performed in a different order than described or not performed at all. In some cases, the steps may include additional features not mentioned below, or other steps may be added.

[0165] At 505, in some examples, the network entity 105-d may send a signal indicating a configuration for sending a sparse channel representation for a certain number of dominant paths. In some examples, the network entity 105-d may send a signal indicating a configuration for a threshold number of training samples to be obtained before computing a dictionary. In some cases, the network entity 105-d may send a signal indicating a configuration for a set of parameters for computing the dictionary. The set of parameters may include a criterion for stopping the learning procedure, a number of atoms to be included in the dictionary, or both.

[0166] At 510, UE 115-f may obtain a number of training samples. In some examples, UE 115-f may obtain the number of training samples that satisfies a threshold number of training samples. In some examples, UE 115-e may obtain corresponding training samples at one or more locations of UE 115-f, one or more times of day, or a combination thereof, where one or more channel estimates may be based on the corresponding training samples.

[0167] At 515, UE 115-f may generate one or more channel estimates for multiple channels between UE 115-f and network entity 105-d using sparse recovery techniques, where the one or more channel estimates may be based on one or more measurements using a set of directional beams. In some examples, UE 115-f may generate the one or more estimates using sparse recovery techniques by generating the one or more channel estimates using an OMP algorithm. In some examples, UE 115-f may perform operations for compressing the one or more channel estimates. The operations for compressing the one or more channel estimates may be based on an autoencoder, one or more compression schemes, or both.

[0168] At 520, UE 115-f may send a signal indicating one or more channel estimates to network entity 105-d. In some examples, the signal indicating one or more channel estimates may include the compressed one or more channel estimates. In some examples, the signal indicating one or more channel estimates may include a compressed version of the one or more channel estimates.

[0169] At 525 , the network entity 105 - d may compute a dictionary associated with a sparse channel representation of a channel between the UE 115 - f and the network entity 105 - d based on a learning procedure using one or more channel estimates.

[0170] At 530, network entity 105-d may send one or more messages each including an indication of a dictionary to one or more other UEs 115 and UE 115-f. The dictionary may be based on one or more channel estimates. One or more UEs 115 may be associated with the same antenna configuration as UE 115-f, the same manufacturer as UE 115-f, the same model as UE 115-f, or the same type as UE 115-f. In some examples, one or more UEs 115 may receive an indication of a set of one or more conditions to which the dictionary is applicable in a message. The set of one or more conditions may include one or more of a geographic location, a time of day, or a zone. In some examples, network entity 105-d may send a second message including an indication of a second dictionary associated with a second channel between UE 115-f and network entity 105-d based at least in part on a change in one or more conditions on which the dictionary may depend. In some examples, the message may include an RRC message.

[0171] At 535, UE 115-f may send a feedback message indicating a sparse channel representation of a channel between UE 115-f and network entity 105-d. The feedback message may include a set of indices of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation. In some examples, UE 115-f may send the feedback message based on a configuration for sending sparse channel representations for a certain number of dominant paths. In some examples, UE 115-f may send an identifier of a dictionary associated with the sparse channel representation along with the feedback message.

[0172] At 540 , the network entity 105 - d may use the dictionary and the sparse channel representation to estimate a channel between the UE 115 - f and the network entity 105 - d .

[0173] At 545, the network entity 105-d may perform a beam management procedure for selecting one or more directional beams based on the dictionary. The beam management procedure may be based on estimating the channel. The network entity 105-d may communicate with the UE 115-f using the one or more directional beams.

[0174] Figure 6 A block diagram 600 of a device 605 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 605 may be an example of aspects of a UE 115 as described herein. The device 605 may include a receiver 610, a transmitter 615, and a communication manager 620. The device 605 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0175] Receiver 610 may provide means for receiving information associated with various information channels (e.g., control channels, data channels, information channels related to signaling for dictionary learning techniques for channel estimation), such as packets, user data, control information, or any combination thereof. The information may be communicated to other components of device 605. Receiver 610 may utilize a single antenna or a collection of multiple antennas.

[0176] The transmitter 615 may provide means for transmitting signals generated by other components of the device 605. For example, the transmitter 615 may transmit information associated with various information channels (e.g., control channels, data channels, information channels related to signaling for dictionary learning techniques for channel estimation), such as packets, user data, control information, or any combination thereof. In some examples, the transmitter 615 may be co-located with the receiver 610 in a transceiver module. The transmitter 615 may utilize a single antenna or a collection of multiple antennas.

[0177] The communication manager 620, the receiver 610, the transmitter 615, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of signaling for dictionary learning techniques for channel estimation as described herein. For example, the communication manager 620, the receiver 610, the transmitter 615, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0178] In some examples, the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a digital signal processor (DSP), a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured to or otherwise supports components for performing the functions described in the present disclosure. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0179] Additionally or alternatively, in some examples, the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functionality of the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0180] In some examples, communication manager 620 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with receiver 610, transmitter 615, or both. For example, communication manager 620 may receive information from receiver 610, transmit information to transmitter 615, or integrate with receiver 610, transmitter 615, or both in combination to obtain information, output information, or perform various other operations as described herein.

[0181] According to examples as disclosed herein, the communication manager 620 may support wireless communications at the UE. For example, the communication manager 620 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The communication manager 620 may be configured to or otherwise support components for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The communication manager 620 may be configured to or otherwise support components for sending a message including an indication of the dictionary to the network entity.

[0182] Additionally or alternatively, according to examples as disclosed herein, the communication manager 620 may support wireless communications at the UE. For example, the communication manager 620 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The communication manager 620 may be configured to or otherwise support components for sending a signal indicating the one or more channel estimates to the network entity. The communication manager 620 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0183] By including or configuring a communication manager 620 according to examples as described herein, a device 605 (e.g., a processor controlling or otherwise coupled to a receiver 610, a transmitter 615, a communication manager 620, or a combination thereof) may support techniques for reducing processing and reducing power consumption.

[0184] Figure 7 A block diagram 700 of a device 705 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 705 may be an example of aspects of the device 605 or UE 115 as described herein. The device 705 may include a receiver 710, a transmitter 715, and a communication manager 720. The device 705 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0185] The receiver 710 may provide means for receiving information associated with various information channels (e.g., control channels, data channels, information channels related to signaling for dictionary learning techniques for channel estimation), such as packets, user data, control information, or any combination thereof. The information may be communicated to other components of the device 705. The receiver 710 may utilize a single antenna or a collection of multiple antennas.

[0186] The transmitter 715 may provide means for transmitting signals generated by other components of the device 705. For example, the transmitter 715 may transmit information associated with various information channels (e.g., control channels, data channels, information channels related to signaling for dictionary learning techniques for channel estimation), such as packets, user data, control information, or any combination thereof. In some examples, the transmitter 715 may be co-located with the receiver 710 in a transceiver module. The transmitter 715 may utilize a single antenna or a collection of multiple antennas.

[0187] The device 705 or its various components may be examples of components for performing various aspects of signaling for dictionary learning techniques for channel estimation as described herein. For example, the communication manager 720 may include a channel estimate generation component 725, a dictionary calculation component 730, a dictionary indication component 735, a channel estimate transmission component 740, or any combination thereof. The communication manager 720 may be an example of various aspects of the communication manager 620 as described herein. In some examples, the communication manager 720 or its various components may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the receiver 710, the transmitter 715, or both. For example, the communication manager 720 may receive information from the receiver 710, transmit the information to the transmitter 715, or integrate with the receiver 710, the transmitter 715, or both in combination to obtain information, output information, or perform various other operations as described herein.

[0188] According to examples as disclosed herein, the communication manager 720 may support wireless communications at the UE. The channel estimate generation component 725 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The dictionary calculation component 730 may be configured to or otherwise support components for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The dictionary indication component 735 may be configured to or otherwise support components for sending a message including an indication of the dictionary to the network entity.

[0189] Additionally or alternatively, according to examples as disclosed herein, the communication manager 720 may support wireless communications at the UE. The channel estimate generation component 725 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The channel estimate transmission component 740 may be configured to or otherwise support components for sending a signal indicating the one or more channel estimates to the network entity. The dictionary indication component 735 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0190] Figure 8A block diagram 800 of a communication manager 820 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The communication manager 820 may be an example of aspects of the communication manager 620, the communication manager 720, or both as described herein. The communication manager 820 or its various components may be examples of components for performing various aspects of signaling for a dictionary learning technique for channel estimation as described herein. For example, the communication manager 820 may include a channel estimate generation component 825, a dictionary calculation component 830, a dictionary indication component 835, a channel estimate transmission component 840, a feedback transmission component 845, a configuration message reception component 850, a training sample component 855, a dictionary calculation component 860, or any combination thereof. Each of these components may communicate with each other directly or indirectly (e.g., via one or more buses).

[0191] According to examples as disclosed herein, the communication manager 820 may support wireless communications at the UE. The channel estimate generation component 825 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The dictionary calculation component 830 may be configured to or otherwise support components for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The dictionary indication component 835 may be configured to or otherwise support components for sending a message including an indication of the dictionary to the network entity.

[0192] In some examples, the feedback sending component 845 may be configured to or otherwise support components for sending a feedback message indicating a sparse channel representation of a channel between the UE and a network entity, the feedback message comprising an indexed set of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation.

[0193] In some examples, configuration message receiving component 850 may be configured or otherwise support means for receiving a signal indicating a configuration for transmitting a sparse channel representation for a certain number of dominant paths of a channel, wherein transmitting the feedback message is based on the configuration.

[0194] In some examples, to support sending the feedback message, feedback sending component 845 can be configured or otherwise support means for sending an identifier of a dictionary associated with the sparse channel representation along with the feedback message.

[0195] In some examples, configuration message receiving component 850 may be configured or otherwise support means for receiving a signal indicating a configuration of a threshold number of training samples to be obtained prior to computing a dictionary, wherein sending the message is based on satisfying the threshold number of training samples.

[0196] In some examples, training sample component 855 may be configured or otherwise support components for obtaining a certain number of training samples that at least meets a threshold number of training samples, where the UE calculates the dictionary based on the number of training samples meeting the threshold.

[0197] In some examples, training sample component 855 may be configured or otherwise support components for obtaining corresponding training samples at one or more locations of the UE, one or more times of day, or a combination thereof, where one or more channel estimates are based on the corresponding training samples.

[0198] In some examples, the configuration message receiving component 850 may be configured as or otherwise support a component for receiving a signal indicating a configuration of a set of parameters for computing a dictionary, the set of parameters including criteria for stopping a learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is computed based on the set of parameters.

[0199] In some examples, dictionary computation component 860 can be configured or otherwise support means for computing an updated dictionary based on changes to one or more conditions upon which the dictionary depends, wherein the indication of the dictionary includes an indication of the updated dictionary.

[0200] In some examples, the one or more conditions include the location of the UE relative to the network entity, the time of day, or a combination thereof.

[0201] In some examples, to support generating one or more channel estimates using sparse recovery techniques, channel estimate generation component 825 may be configured or otherwise support means for generating one or more channel estimates using an orthogonal matching pursuit (OMP) algorithm.

[0202] Additionally or alternatively, according to examples as disclosed herein, the communication manager 820 may support wireless communications at the UE. In some examples, the channel estimate generation component 825 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The channel estimate transmission component 840 may be configured to or otherwise support components for sending a signal indicating one or more channel estimates to the network entity. In some examples, the dictionary indication component 835 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0203] In some examples, the feedback sending component 845 may be configured to or otherwise support components for sending a feedback message indicating a sparse channel representation of a channel between the UE and a network entity after receiving the dictionary, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation.

[0204] In some examples, configuration message receiving component 850 may be configured or otherwise support means for receiving a signal indicating a configuration for transmitting a sparse channel representation for a certain number of dominant paths of a channel, wherein transmitting the feedback message is based on the configuration.

[0205] In some examples, to support sending the feedback message, feedback sending component 845 can be configured or otherwise support means for sending an identifier of a dictionary associated with the sparse channel representation along with the feedback message.

[0206] In some examples, dictionary indication component 835 may be configured or otherwise support means for receiving, in a message, an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies.

[0207] In some examples, dictionary indication component 835 may be configured or otherwise support components for receiving in a message an indication of a set of one or more conditions applicable to a dictionary, the set of one or more conditions comprising a geographic location, a time of day, a zone, or a combination thereof.

[0208] In some examples, channel estimate generation component 825 may be configured or otherwise support means for performing operations for compressing one or more channel estimates, wherein a signal indicative of the one or more channel estimates includes the compressed one or more channel estimates.

[0209] In some examples, operations performed to compress one or more channel estimates are based on an autoencoder, one or more compression schemes, or a combination thereof.

[0210] In some examples, configuration message receiving component 850 may be configured or otherwise support means for receiving a signal indicating a configuration for sending an indication of one or more channel estimates for a certain number of dominant paths for a channel, wherein the transmitted signal is based on the configuration.

[0211] In some examples, dictionary indication component 835 may be configured to or otherwise support components for receiving a second message that includes an indication of a second dictionary associated with a second channel between the UE and the network entity based on a change in one or more conditions on which the dictionary depends.

[0212] In some examples, the one or more conditions include the location of the UE relative to the network entity, the time of day, or a combination thereof.

[0213] In some examples, training sample component 855 may be configured or otherwise support components for obtaining corresponding training samples at one or more locations of the UE, one or more times of day, or a combination thereof, where one or more channel estimates are based on the corresponding training samples.

[0214] In some examples, to support generating one or more channel estimates using sparse recovery techniques, channel estimate generation component 825 may be configured or otherwise support means for generating one or more channel estimates using an orthogonal matching pursuit (OMP) algorithm.

[0215] In some examples, the message includes a radio resource control message.

[0216] Fig. 9 A diagram of a system 900 including a device 905 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 905 may be an example of a device 605, a device 705, or a UE 115 as described herein, or include components thereof. The device 905 may communicate (e.g., wirelessly) with one or more network entities 105, one or more UEs 115, or any combination thereof. The device 905 may include components for two-way voice and data communications, including components for sending and receiving communications, such as a communication manager 920, an input / output (I / O) controller 910, a transceiver 915, an antenna 925, a memory 930, a code 935, and a processor 940. These components may be electronically communicated or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 945).

[0217] I / O controller 910 may manage input and output signals for device 905. I / O controller 910 may also manage peripheral devices that are not integrated into device 905. In some cases, I / O controller 910 may represent a physical connection or port to an external peripheral device. In some cases, I / O controller 910 may utilize an operating system, such as or another known operating system. Additionally or alternatively, I / O controller 910 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, I / O controller 910 may be implemented as part of a processor, such as processor 940. In some cases, a user may interact with device 905 via I / O controller 910 or via hardware components controlled by I / O controller 910.

[0218] In some cases, the device 905 may include a single antenna 925. However, in some other cases, the device 905 may have more than one antenna 925, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 915 may communicate bidirectionally via one or more antennas 925, a wired or wireless link, as described herein. For example, the transceiver 915 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 915 may also include a modem to modulate a packet, provide the modulated packet to one or more antennas 925 for transmission, and demodulate the packet received from the one or more antennas 925. The transceiver 915 or the transceiver 915 and the one or more antennas 925 may be examples of transmitters 615, transmitters 715, receivers 610, receivers 710, or any combination thereof or components thereof as described herein.

[0219] The memory 930 may include random access memory (RAM) and read-only memory (ROM). The memory 930 may store computer-readable, computer-executable code 935 including instructions that, when executed by the processor 940, cause the device 905 to perform various functions described herein. The code 935 may be stored in a non-transitory computer-readable medium (such as system memory) or another type of memory. In some cases, the code 935 may not be directly executable by the processor 940, but may (for example, when compiled and executed) cause the computer to perform the functions described herein. In some cases, the memory 930 may include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0220] The processor 940 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 940 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 940. The processor 940 may be configured to execute computer-readable instructions stored in a memory (e.g., a memory 930) to enable the device 905 to perform various functions (e.g., various functions or tasks supporting signaling for a dictionary learning technique for channel estimation). For example, the device 905 or a component of the device 905 may include a processor 940 and a memory 930 coupled to or coupled to the processor 940, and the processor 940 and the memory 930 are configured to perform the various functions described herein.

[0221] According to examples as disclosed herein, the communication manager 920 may support wireless communications at the UE. For example, the communication manager 920 may be configured to or otherwise support components for generating one or more channel estimates for a set of multiple channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The communication manager 920 may be configured to or otherwise support components for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The communication manager 920 may be configured to or otherwise support components for sending a message including an indication of the dictionary to the network entity.

[0222] Additionally or alternatively, according to examples as disclosed herein, the communication manager 920 may support wireless communications at the UE. For example, the communication manager 920 may be configured to or otherwise support a component for generating one or more channel estimates for a set of multiple channels between the UE and the network entity using a sparse recovery technique, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The communication manager 920 may be configured to or otherwise support a component for sending a signal indicating the one or more channel estimates to the network entity. The communication manager 920 may be configured to or otherwise support a component for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based on the one or more channel estimates.

[0223] By including or configuring a communication manager 920 according to examples as described herein, the device 905 can support techniques for reducing latency and reducing power consumption.

[0224] In some examples, the communication manager 920 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 915, one or more antennas 925, or any combination thereof. Although the communication manager 920 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 920 may be supported or performed by the processor 940, the memory 930, the code 935, or any combination thereof. For example, the code 935 may include instructions that may be executed by the processor 940 to cause the device 905 to perform various aspects of signaling for dictionary learning techniques for channel estimation as described herein, or the processor 940 and the memory 930 may be otherwise configured to perform or support such operations.

[0225] Fig.10 A block diagram 1000 of a device 1005 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 1005 may be an example of aspects of a network entity 105 as described herein. The device 1005 may include a receiver 1010, a transmitter 1015, and a communication manager 1020. The device 1005 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0226] Receiver 1010 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be communicated to other components of device 1005. In some examples, receiver 1010 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1010 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof.

[0227] The transmitter 1015 may provide a means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1005. For example, the transmitter 1015 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, the transmitter 1015 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1015 may support outputting information by sending signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1015 and the receiver 1010 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0228] The communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of signaling for dictionary learning techniques for channel estimation as described herein. For example, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0229] In some examples, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured as or otherwise supports components for performing the functions described in the present disclosure. In some examples, a processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0230] Additionally or alternatively, in some examples, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functionality of the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0231] In some examples, communication manager 1020 can be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with receiver 1010, transmitter 1015, or both. For example, communication manager 1020 can receive information from receiver 1010, transmit information to transmitter 1015, or integrate with receiver 1010, transmitter 1015, or both in combination to obtain information, output information, or perform various other operations as described herein.

[0232] According to examples as disclosed herein, the communication manager 1020 may support wireless communications at a network entity. For example, the communication manager 1020 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and a network entity. The communication manager 1020 may be configured to or otherwise support components for executing a beam management procedure for selecting one or more directional beams based on the dictionary. The communication manager 1020 may be configured to or otherwise support components for communicating with the UE using one or more directional beams.

[0233] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1020 may support wireless communications at a network entity. For example, the communication manager 1020 may be configured to or otherwise support a component for receiving, from each UE in a set of one or more UEs, a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity. The communication manager 1020 may be configured to or otherwise support a component for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The communication manager 1020 may be configured to or otherwise support a component for sending a message including an indication of the dictionary to the UE.

[0234] By including or configuring a communication manager 1020 according to examples as described herein, a device 1005 (e.g., a processor controlling or otherwise coupled to a receiver 1010, a transmitter 1015, a communication manager 1020, or a combination thereof) may support techniques for reducing processing and reducing power consumption.

[0235] Fig.11A block diagram 1100 of a device 1105 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 1105 may be an example of aspects of the device 1005 or network entity 105 as described herein. The device 1105 may include a receiver 1110, a transmitter 1115, and a communication manager 1120. The device 1105 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0236] Receiver 1110 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be communicated to other components of device 1105. In some examples, receiver 1110 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1110 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof.

[0237] The transmitter 1115 may provide a means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1105. For example, the transmitter 1115 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, the transmitter 1115 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1115 may support outputting information by sending signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1115 and the receiver 1110 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0238] The device 1105 or its various components may be examples of components for performing various aspects of signaling for dictionary learning techniques for channel estimation as described herein. For example, the communication manager 1120 may include a dictionary reception manager 1125, a beam management manager 1130, a beamforming manager 1135, a channel estimation reception manager 1140, a dictionary calculation manager 1145, a dictionary indication manager 1150, or any combination thereof. The communication manager 1120 may be an example of various aspects of the communication manager 1020 as described herein. In some examples, the communication manager 1120 or its various components may be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with the receiver 1110, the transmitter 1115, or both. For example, the communication manager 1120 may receive information from the receiver 1110, transmit information to the transmitter 1115, or integrate with the receiver 1110, the transmitter 1115, or both in combination to obtain information, output information, or perform various other operations as described herein.

[0239] According to examples as disclosed herein, the communication manager 1120 may support wireless communications at a network entity. The dictionary reception manager 1125 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and a network entity. The beam management manager 1130 may be configured to or otherwise support components for executing a beam management procedure for selecting one or more directional beams based on the dictionary. The beamforming manager 1135 may be configured to or otherwise support components for communicating with the UE using one or more directional beams.

[0240] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1120 may support wireless communications at a network entity. The channel estimate reception manager 1140 may be configured to or otherwise support components for receiving, from each UE in a set of one or more UEs, a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity. The dictionary computation manager 1145 may be configured to or otherwise support components for computing a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The dictionary indication manager 1150 may be configured to or otherwise support components for sending a message including an indication of a dictionary to the UE.

[0241] Fig.12A block diagram 1200 of a communication manager 1220 supporting signaling for a dictionary learning technique for channel estimation in accordance with one or more aspects of the present disclosure is shown. The communication manager 1220 may be an example of aspects of the communication manager 1020, the communication manager 1120, or both as described herein. The communication manager 1220 or its various components may be examples of components for performing various aspects of signaling for a dictionary learning technique for channel estimation as described herein. For example, the communication manager 1220 may include a dictionary reception manager 1225, a beam management manager 1230, a beamforming manager 1235, a channel estimation reception manager 1240, a dictionary calculation manager 1245, a dictionary indication manager 1250, a dictionary transmission manager 1255, a feedback reception manager 1260, a configuration message transmission manager 1265, a channel estimation manager 1270, or any combination thereof. Each of these components may communicate directly or indirectly with each other (e.g., via one or more buses), which communication may include communication within a protocol layer of a protocol stack, communication associated with a logical channel of the protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with the network entity 105, between devices, components, or virtualized components associated with the network entity 105), or any combination thereof.

[0242] According to examples as disclosed herein, the communication manager 1220 may support wireless communications at a network entity. The dictionary reception manager 1225 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and a network entity. The beam management manager 1230 may be configured to or otherwise support components for executing a beam management procedure for selecting one or more directional beams based on the dictionary. The beamforming manager 1235 may be configured to or otherwise support components for communicating with the UE using one or more directional beams.

[0243] In some examples, the dictionary transmission manager 1255 may be configured as or otherwise support components for sending one or more messages that each include an indication of a dictionary to one or more other UEs, the one or more other UEs having the same antenna configuration as the UE, being associated with the same manufacturer as the UE, being the same model as the UE, being the same type as the UE, or a combination thereof.

[0244] In some examples, feedback reception manager 1260 may be configured to or otherwise support components for receiving a feedback message indicating a sparse channel representation of a channel between a UE and a network entity, the feedback message comprising an indexed set of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation.

[0245] In some examples, configuration message sending manager 1265 may be configured or otherwise support means for sending a signal indicating a configuration for sending a sparse channel representation for a certain number of dominant paths of a channel, wherein receiving the feedback message is based on the configuration.

[0246] In some examples, to support receiving feedback messages, feedback reception manager 1260 may be configured or otherwise support components for receiving an identifier of a dictionary associated with a sparse channel representation along with the feedback message.

[0247] In some examples, channel estimation manager 1270 may be configured or otherwise support components for estimating a channel between a UE and a network entity using a dictionary and a sparse channel representation, wherein performing beam management procedures is based on the estimated channel.

[0248] In some examples, configuration message sending manager 1265 may be configured or otherwise support means for sending a signal indicating a configuration of a threshold number of training samples for computing a dictionary, where receiving the message is based on satisfying the threshold number of training samples.

[0249] In some examples, the configuration messaging manager 1265 may be configured to or otherwise support components for sending a signal indicating a configuration of a set of parameters for computing a dictionary, the set of parameters including criteria for stopping a learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is based on the set of parameters.

[0250] In some examples, the indication of the dictionary includes an indication of an updated dictionary that has been updated based on a change in one or more conditions on which the dictionary depends.

[0251] In some examples, the one or more conditions include the location of the UE relative to the network entity, the time of day, or a combination thereof.

[0252] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1220 may support wireless communications at a network entity. The channel estimate reception manager 1240 may be configured to or otherwise support components for receiving, from each UE in a set of one or more UEs, respective signals indicating one or more channel estimates for a set of multiple channels between each UE and the network entity. The dictionary computation manager 1245 may be configured to or otherwise support components for computing a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The dictionary indication manager 1250 may be configured to or otherwise support components for sending a message including an indication of a dictionary to the UE.

[0253] In some examples, the feedback reception manager 1260 may be configured to or otherwise support components for receiving a feedback message indicating a sparse channel representation of a channel between the UE and a network entity after sending the dictionary, the feedback message comprising an indexed set of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation.

[0254] In some examples, channel estimation manager 1270 may be configured or otherwise support components for estimating a channel between a UE and a network entity using a dictionary and a sparse channel representation. In some examples, beam management manager 1230 may be configured or otherwise support components for executing a beam management procedure for selecting one or more directional beams based on the estimated channel.

[0255] In some examples, configuration message sending manager 1265 may be configured or otherwise support means for sending a signal indicating a configuration for sending a sparse channel representation for a certain number of dominant paths of a channel, wherein receiving the feedback message is based on the configuration.

[0256] In some examples, to support sending feedback messages, feedback reception manager 1260 may be configured or otherwise support components for receiving an identifier of a dictionary associated with a sparse channel representation along with the feedback message.

[0257] In some examples, dictionary indication manager 1250 may be configured or otherwise support components for sending, in a message, an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies.

[0258] In some examples, dictionary indication manager 1250 may be configured or otherwise support components for sending in a message an indication of a set of one or more conditions applicable to a dictionary, the set of one or more conditions including geographic location, time of day, zone, or a combination thereof.

[0259] In some examples, configuration messaging manager 1265 may be configured to or otherwise support components for sending a signal indicating a configuration for sending one or more channel estimates for a certain number of dominant paths for a channel, where a network entity receives the one or more channel estimates for the number of dominant paths.

[0260] In some examples, dictionary indication manager 1250 may be configured to or otherwise support components for sending a second message that includes an indication of a second dictionary associated with a second channel between the UE and the network entity based on a change in one or more conditions on which the dictionary depends.

[0261] In some examples, the one or more conditions include the location of the UE relative to the network entity, the time of day, or a combination thereof.

[0262] In some examples, the corresponding signal indicative of one or more channel estimates includes a compressed version of the one or more channel estimates.

[0263] In some examples, computing the dictionary is based on each UE in the set of one or more UEs having the same antenna configuration, being associated with the same manufacturer, being the same model, being the same type, or a combination thereof.

[0264] In some examples, the message includes a radio resource control message.

[0265] Fig.13 A diagram of a system 1300 including a device 1305 supporting signaling for a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The device 1305 may be an example of a device 1005, a device 1105, or a network entity 105 as described herein, or include components thereof. The device 1305 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, which may include communication through one or more wired interfaces, through one or more wireless interfaces, or any combination thereof. The device 1305 may include components that support output and obtain communications, such as a communication manager 1320, a transceiver 1310, an antenna 1315, a memory 1325, a code 1330, and a processor 1335. These components may be electronically communicated or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1340).

[0266] The transceiver 1310 may support bidirectional communication via a wired link, a wireless link, or both as described herein. In some examples, the transceiver 1310 may include a wired transceiver and may communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, the transceiver 1310 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1305 may include one or more antennas 1315, which may be capable of (e.g., concurrently) sending or receiving wireless transmissions. The transceiver 1310 may also include a modem to modulate a signal, provide the modulated signal for transmission (e.g., via one or more antennas 1315, via a wired transmitter), receive the modulated signal (e.g., from one or more antennas 1315, from a wired receiver), and demodulate the signal. The transceiver 1310 or the transceiver 1310 and one or more antennas 1315 or a wired interface (where applicable) may be an example of a transmitter 1015, a transmitter 1115, a receiver 1010, a receiver 1110, or any combination thereof or components thereof as described herein. In some examples, the transceiver may be operable to support communication via one or more communication links (e.g., communication link 125, backhaul communication link 120, midhaul communication link 162, fronthaul communication link 168).

[0267] Memory 1325 may include RAM and ROM. Memory 1325 may store computer-readable, computer-executable code 1330 including instructions that, when executed by processor 1335, cause device 1305 to perform various functions described herein. Code 1330 may be stored in a non-transitory computer-readable medium (such as system memory) or another type of memory. In some cases, code 1330 may not be directly executable by processor 1335, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, memory 1325 may include, among other things, a BIOS that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0268] The processor 1335 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA, a microcontroller, a programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination thereof). In some cases, the processor 1335 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1335. The processor 1335 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1325) to enable the device 1305 to perform various functions (e.g., various functions or tasks supporting signaling for a dictionary learning technique for channel estimation). For example, the device 1305 or a component of the device 1305 may include a processor 1335 and a memory 1325 coupled to the processor 1335, and the processor 1335 and the memory 1325 are configured to perform the various functions described herein. Processor 1335 can be an example of a cloud computing platform (e.g., one or more physical nodes and supporting software, such as an operating system, virtual machine, or container instance) that can host functionality (e.g., by executing code 1330) to perform the functions of device 1305.

[0269] In some examples, bus 1340 may support communications of protocol layers (e.g., within a protocol layer) of a protocol stack. In some examples, bus 1340 may support communications associated with logical channels of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within components of device 1305 or between different components of device 1305 that may be co-located or may be located in different locations (e.g., where device 1305 may refer to a system in which one or more of communication manager 1320, transceiver 1310, memory 1325, code 1330, and processor 1335 may be located in one of the different components or divided between the different components).

[0270] In some examples, communication manager 1320 may manage aspects of communications with core network 130 (e.g., via one or more wired or wireless backhaul links). For example, communication manager 1320 may manage delivery of data communications for client devices, such as one or more UEs 115. In some examples, communication manager 1320 may manage communications with other network entities 105 and may include a controller or scheduler for controlling communications with UE 115 in coordination with other network entities 105. In some examples, communication manager 1320 may support an X2 interface within an LTE / LTE-A wireless communication network technology to provide communications between network entities 105.

[0271] According to examples as disclosed herein, the communication manager 1320 may support wireless communications at a network entity. For example, the communication manager 1320 may be configured to or otherwise support components for receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and a network entity. The communication manager 1320 may be configured to or otherwise support components for executing a beam management procedure for selecting one or more directional beams based on the dictionary. The communication manager 1320 may be configured to or otherwise support components for communicating with the UE using one or more directional beams.

[0272] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1320 may support wireless communications at a network entity. For example, the communication manager 1320 may be configured to or otherwise support a component for receiving, from each UE in a set of one or more UEs, a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and the network entity. The communication manager 1320 may be configured to or otherwise support a component for calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using the one or more channel estimates. The communication manager 1320 may be configured to or otherwise support a component for sending a message including an indication of the dictionary to the UE.

[0273] By including or configuring a communication manager 1320 according to examples as described herein, the device 1305 can support techniques for reducing latency and reducing power consumption.

[0274] In some examples, the communication manager 1320 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the transceiver 1310, one or more antennas 1315 (e.g., where applicable), or any combination thereof. Although the communication manager 1320 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1320 may be supported or performed by the processor 1335, the memory 1325, the code 1330, the transceiver 1310, or any combination thereof. For example, the code 1330 may include instructions that are executable by the processor 1335 to cause the device 1305 to perform various aspects of signaling for dictionary learning techniques for channel estimation as described herein, or the processor 1335 and the memory 1325 may be otherwise configured to perform or support such operations.

[0275] Fig.14A flowchart illustrating a method 1400 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1400 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1400 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 9 The described UE 115 performs. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0276] At 1405, the method may include using a sparse recovery technique to generate one or more channel estimates for a set of multiple channels between the UE and the network entity, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The operations of 1405 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1405 may be performed as described in reference to Figure 8 The channel estimate generation component 825 is described as performing.

[0277] At 1410, the method may include calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using one or more channel estimates. The operations of 1410 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1410 may be performed as described in reference to Figure 8 The described dictionary calculation component 830 performs.

[0278] At 1415, the method may include sending a message including an indication of the dictionary to a network entity. The operations of 1415 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1415 may be performed as described in reference to Figure 8 The described dictionary directive component 835 executes.

[0279] Fig.15 A flowchart illustrating a method 1500 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1500 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1500 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 9 The described UE 115 performs. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0280] At 1505, the method may include using a sparse recovery technique to generate one or more channel estimates for a set of multiple channels between the UE and the network entity, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The operations of 1505 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1505 may be performed as described in reference to Figure 8 The channel estimate generation component 825 is described as performing.

[0281] At 1510, the method may include calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using one or more channel estimates. The operations of 1510 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1510 may be performed as described in reference to Figure 8 The described dictionary calculation component 830 performs.

[0282] At 1515, the method may include sending a message including an indication of the dictionary to a network entity. The operations of 1515 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1515 may be performed as described in reference to Figure 8 The described dictionary directive component 835 executes.

[0283] At 1520, the method may include sending a feedback message indicating a sparse channel representation of a channel between the UE and the network entity, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation. The operations of 1520 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1520 may be performed as described in reference to Figure 8 The described feedback sending component 845 performs.

[0284] Fig.16 A flow chart illustrating a method 1600 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1600 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1600 may be implemented by a network entity or a component thereof as described in reference to Figures 1 to 5 as well as Figures 10 to 13 The described network entity performs. In some examples, the network entity may execute an instruction set to control the functional elements of the network entity to perform the described functions. Additionally or alternatively, the network entity may use dedicated hardware to perform various aspects of the described functions.

[0285] At 1605, the method may include receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity. The operations of 1605 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1605 may be performed as described in reference to Fig.12 The described dictionary receive manager 1225 executes.

[0286] At 1610, the method may include executing a beam management procedure for selecting one or more directional beams based on the dictionary. The operations of 1610 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1610 may be performed as described in reference to Fig.12 The beam management manager 1230 described performs.

[0287] At 1615, the method may include communicating with the UE using one or more directional beams. The operations of 1615 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1615 may be performed as described in reference Fig.12 The beamforming manager 1235 described herein performs.

[0288] Fig.17 A flow chart illustrating a method 1700 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1700 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1700 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 9 The described UE 115 performs. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0289] At 1705, the method may include using a sparse recovery technique to generate one or more channel estimates for a set of multiple channels between the UE and the network entity, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The operations of 1705 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1705 may be performed as described in reference to Figure 8 The channel estimate generation component 825 is described as performing.

[0290] At 1710, the method may include sending a signal indicating one or more channel estimates to a network entity. The operations of 1710 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed as described in reference to Figure 8 The channel estimate sending component 840 is described to perform.

[0291] At 1715, the method may include receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary based on one or more channel estimates. The operations of 1715 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1715 may be performed as described in reference to Figure 8 The described dictionary directive component 835 executes.

[0292] Fig.18 A flowchart illustrating a method 1800 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1800 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1800 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 9 The described UE 115 performs. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0293] At 1805, the method may include using a sparse recovery technique to generate one or more channel estimates for a set of multiple channels between the UE and the network entity, wherein the one or more channel estimates are based on one or more measurements using a set of directional beams. The operations of 1805 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed as described in reference to Figure 8 The channel estimate generation component 825 is described as performing.

[0294] At 1810, the method may include sending a signal indicating one or more channel estimates to a network entity. The operations of 1810 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed as described in reference to Figure 8 The channel estimate sending component 840 is described to perform.

[0295] At 1815, the method may include receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary based on one or more channel estimates. The operations of 1815 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1815 may be performed as described in reference to Figure 8 The described dictionary directive component 835 executes.

[0296] At 1820, the method may include sending a feedback message indicating a sparse channel representation of a channel between the UE and the network entity after receiving the dictionary, the feedback message including a set of indices of non-zero elements in the sparse channel representation and a quantized set of non-zero elements in the sparse channel representation. The operations of 1820 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1820 may be performed as described in reference to Figure 8 The described feedback sending component 845 performs.

[0297] Fig.19 A flow chart illustrating a method 1900 for signaling supporting a dictionary learning technique for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1900 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1900 may be implemented by a network entity or a component thereof as described in reference to Figures 1 to 5 as well as Figures 10 to 13 The described network entity performs. In some examples, the network entity may execute an instruction set to control the functional elements of the network entity to perform the described functions. Additionally or alternatively, the network entity may use dedicated hardware to perform various aspects of the described functions.

[0298] At 1905, the method may include receiving, from each UE in a set of one or more UEs, a respective signal indicating one or more channel estimates for a set of multiple channels between each UE and a network entity. The operations of 1905 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed as described in reference to Fig.12 The described channel estimation reception manager 1240 performs.

[0299] At 1910, the method may include calculating a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based on a learning procedure using one or more channel estimates. The operations of 1910 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1910 may be performed as described in reference to Fig.12 The described dictionary calculation manager 1245 performs.

[0300] At 1915, the method may include sending a message including an indication of the dictionary to the UE. The operations of 1915 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1915 may be performed as described in reference to Fig.12 The described dictionary directive manager 1250 performs.

[0301] The following provides an overview of various aspects of the disclosure:

[0302] Aspect 1: A method for wireless communication at a UE, comprising: using a sparse recovery technique to generate one or more channel estimates for multiple channels between the UE and a network entity, wherein the one or more channel estimates are based at least in part on one or more measurements using a set of directional beams; calculating a dictionary associated with a sparse channel representation of the channel between the UE and the network entity based at least in part on a learning procedure using the one or more channel estimates; and sending a message to the network entity including an indication of the dictionary.

[0303] Aspect 2: The method according to Aspect 1 also includes: sending a feedback message indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message including an index set of non-zero elements in the sparse channel representation and a quantization set of the non-zero elements in the sparse channel representation.

[0304] Aspect 3: The method according to aspect 2 further comprises: receiving a signal indicating a configuration for sending the sparse channel representation for a certain number of dominant paths of the channel, wherein sending the feedback message is based at least in part on the configuration.

[0305] Aspect 4: The method according to any one of aspects 2 to 3, wherein sending the feedback message further comprises: sending an identifier of the dictionary associated with the sparse channel representation together with the feedback message.

[0306] Aspect 5: The method according to any one of Aspects 1 to 4 further includes: receiving a signal indicating a configuration of a threshold number of training samples to be obtained before calculating the dictionary, wherein sending the message is at least partially based on satisfying the threshold number of training samples.

[0307] Aspect 6: The method according to aspect 5 further includes: obtaining a certain number of training samples that at least meet a threshold number of the training samples, wherein the UE calculates the dictionary at least in part based on the number of training samples meeting the threshold.

[0308] Aspect 7: The method according to any one of Aspects 1 to 6 further includes: obtaining corresponding training samples at one or more locations of the UE, one or more times of the day, or a combination thereof, wherein the one or more channel estimates are at least partially based on the corresponding training samples.

[0309] Aspect 8: The method according to any one of Aspects 1 to 7 further includes: receiving a signal indicating a configuration of a parameter set for calculating the dictionary, the parameter set including criteria for stopping the learning procedure, the number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is calculated based on the parameter set.

[0310] Aspect 9: The method according to any one of aspects 1 to 8 further includes: calculating an updated dictionary based at least in part on changes in one or more conditions on which the dictionary depends, wherein the indication of the dictionary includes an indication of the updated dictionary.

[0311] Aspect 10: The method according to aspect 9, wherein the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0312] Aspect 11: The method according to any one of Aspects 1 to 10, wherein using the sparse recovery technique to generate the one or more channel estimates further comprises: using an orthogonal matching pursuit (OMP) algorithm to generate the one or more channel estimates.

[0313] Aspect 12: A method for wireless communication at a network entity, comprising: receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a UE and the network entity; executing a beam management procedure for selecting one or more directional beams based at least in part on the dictionary; and using the one or more directional beams to communicate with the UE.

[0314] Aspect 13: The method according to Aspect 12 also includes: sending one or more messages each including an indication of the dictionary to one or more other UEs, wherein the one or more other UEs have the same antenna configuration as the UE, are associated with the same manufacturer as the UE, are the same model as the UE, are the same type as the UE, or a combination thereof.

[0315] Aspect 14: The method according to any one of Aspects 12 to 13 further includes: receiving a feedback message indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message including an index set of non-zero elements in the sparse channel representation and a quantization set of the non-zero elements in the sparse channel representation.

[0316] Aspect 15: The method according to aspect 14 further comprises: sending a signal indicating a configuration for sending the sparse channel representation for a certain number of dominant paths of the channel, wherein receiving the feedback message is based at least in part on the configuration.

[0317] Aspect 16: The method according to any one of Aspects 14 to 15, wherein receiving the feedback message further comprises: receiving an identifier of the dictionary associated with the sparse channel representation together with the feedback message.

[0318] Aspect 17: A method according to any one of Aspects 14 to 16, wherein the method further comprises: estimating the channel between the UE and the network entity using the dictionary and the sparse channel representation, wherein performing the beam management procedure is at least partially based on estimating the channel.

[0319] Aspect 18: The method according to any one of aspects 12 to 17 further comprises: sending a signal indicating a configuration of a threshold number of training samples for calculating the dictionary, wherein receiving the message is at least partially based on satisfying the threshold number of training samples.

[0320] Aspect 19: The method according to any one of Aspects 12 to 18 further includes: sending a signal indicating the configuration of a parameter set for calculating the dictionary, the parameter set including criteria for stopping the learning procedure, the number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is at least partially based on the parameter set.

[0321] Aspect 20: The method according to any one of aspects 12 to 19, wherein the indication of the dictionary comprises an indication of an updated dictionary that has been updated based at least in part on a change in one or more conditions on which the dictionary depends.

[0322] Aspect 21: The method according to aspect 20, wherein the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0323] Aspect 22: A method for performing wireless communications at a UE, comprising: using a sparse recovery technique to generate one or more channel estimates for multiple channels between the UE and a network entity, wherein the one or more channel estimates are based at least in part on one or more measurements using a set of directional beams; sending a signal indicating the one or more channel estimates to the network entity; and receiving a message including an indication of a dictionary associated with a sparse channel representation of the channels between the UE and the network entity, wherein the dictionary is based at least in part on the one or more channel estimates.

[0324] Aspect 23: The method according to Aspect 22 also includes: after receiving the dictionary, sending a feedback message indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message including an index set of non-zero elements in the sparse channel representation and a quantization set of the non-zero elements in the sparse channel representation.

[0325] Aspect 24: The method according to aspect 23 further comprises: receiving a signal indicating a configuration for sending the sparse channel representation for a certain number of dominant paths of the channel, wherein sending the feedback message is based at least in part on the configuration.

[0326] Aspect 25: The method according to any one of Aspects 23 to 24, wherein sending the feedback message further comprises: sending an identifier of the dictionary associated with the sparse channel representation together with the feedback message.

[0327] Aspect 26: The method according to any one of aspects 22 to 25 further includes: receiving in the message an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies.

[0328] Aspect 27: The method according to any one of Aspects 22 to 26 also includes: receiving an indication of a set of one or more conditions applicable to the dictionary in the message, the set of one or more conditions including a geographic location, a time of day, a zone, or a combination thereof.

[0329] Aspect 28: The method according to any one of Aspects 22 to 27 further includes: performing an operation for compressing the one or more channel estimates, wherein the signal indicating the one or more channel estimates includes the compressed one or more channel estimates.

[0330] Aspect 29: The method according to aspect 28, wherein performing the operation for compressing the one or more channel estimates is based at least in part on an autoencoder, one or more compression schemes, or a combination thereof.

[0331] Aspect 30: The method according to any one of Aspects 22 to 29 further includes: receiving a signal indicating a configuration for sending an indication of the one or more channel estimates for a certain number of dominant paths for the channel, wherein sending the signal is at least partially based on the configuration.

[0332] Aspect 31: The method according to any one of Aspects 22 to 30 further includes: receiving a second message, the second message comprising an indication of a second dictionary associated with a second channel between the UE and the network entity based at least in part on a change of one or more conditions on which the dictionary depends.

[0333] Aspect 32: The method according to aspect 31, wherein the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0334] Aspect 33: The method according to any one of Aspects 22 to 32 further includes: obtaining corresponding training samples at one or more locations of the UE, one or more times of the day, or a combination thereof, wherein the one or more channel estimates are at least partially based on the corresponding training samples.

[0335] Aspect 34: The method according to any one of Aspects 22 to 33, wherein using the sparse recovery technique to generate the one or more channel estimates further comprises: using an orthogonal matching pursuit (OMP) algorithm to generate the one or more channel estimates.

[0336] Aspect 35: A method according to any one of aspects 22 to 34, wherein the message comprises a radio resource control message.

[0337] Aspect 36: A method for wireless communication at a network entity, comprising: receiving a corresponding signal indicating one or more channel estimates for multiple channels between each UE and the network entity from each UE in a set of one or more UEs; calculating a dictionary associated with a sparse channel representation of the channel between the UE and the network entity based at least in part on a learning procedure using the one or more channel estimates; and sending a message to the UE including an indication of the dictionary.

[0338] Aspect 37: The method according to Aspect 36 also includes: receiving a feedback message indicating the sparse channel representation of the channel between the UE and the network entity after sending the dictionary, the feedback message including an index set of non-zero elements in the sparse channel representation and a quantization set of the non-zero elements in the sparse channel representation.

[0339] Aspect 38: The method according to Aspect 37 also includes: using the dictionary and the sparse channel representation to estimate the channel between the UE and the network entity; and performing a beam management procedure for selecting one or more directional beams based at least in part on estimating the channel.

[0340] Aspect 39: The method according to any one of Aspects 37 to 38 further includes: sending a signal indicating a configuration for sending the sparse channel representation for a certain number of dominant paths for the channel, wherein receiving the feedback message is at least partially based on the configuration.

[0341] Aspect 40: The method according to any one of aspects 37 to 39, wherein sending the feedback message further comprises: receiving an identifier of the dictionary associated with the sparse channel representation together with the feedback message.

[0342] Aspect 41: The method according to any one of aspects 36 to 40 further comprises: sending in the message an indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies.

[0343] Aspect 42: The method according to any one of Aspects 36 to 41 further includes: sending an indication of a set of one or more conditions applicable to the dictionary in the message, the set of one or more conditions including a geographic location, a time of day, a zone, or a combination thereof.

[0344] Aspect 43: The method according to any one of Aspects 36 to 42 further includes: sending a signal indicating a configuration for sending the one or more channel estimates for a certain number of dominant paths of the channel, wherein the network entity receives the one or more channel estimates for the said number of dominant paths.

[0345] Aspect 44: The method according to any one of Aspects 36 to 43 further includes: sending a second message, the second message including an indication of a second dictionary associated with a second channel between the UE and the network entity based at least in part on a change of one or more conditions on which the dictionary depends.

[0346] Aspect 45: The method according to aspect 44, wherein the one or more conditions include a location of the UE relative to the network entity, a time of day, or a combination thereof.

[0347] Aspect 46: A method according to any one of aspects 36 to 45, wherein the corresponding signal indicative of the one or more channel estimates comprises a compressed version of the one or more channel estimates.

[0348] Aspect 47: A method according to any one of Aspects 36 to 46, wherein calculating the dictionary is based at least in part on each UE in the set of one or more UEs having the same antenna configuration, being associated with the same manufacturer, being the same model, being the same type, or a combination thereof.

[0349] Aspect 48: A method according to any one of aspects 36 to 47, wherein the message comprises a radio resource control message.

[0350] Aspect 49: An apparatus for performing wireless communications at a UE, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 1 to 11.

[0351] Aspect 50: An apparatus for wireless communication at a UE, comprising at least one component for performing a method according to any one of aspects 1 to 11.

[0352] Aspect 51: A non-transitory computer-readable medium storing a code for wireless communication at a UE, the code comprising instructions executable by a processor to perform a method according to any one of aspects 1 to 11.

[0353] Aspect 52: An apparatus for wireless communication at a network entity, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 12 to 21.

[0354] Aspect 53: An apparatus for wireless communication at a network entity, comprising at least one component for performing a method according to any one of aspects 12 to 21.

[0355] Aspect 54: A non-transitory computer-readable medium storing code for wireless communication at a network entity, the code comprising instructions executable by a processor to perform the method according to any one of aspects 12 to 21.

[0356] Aspect 55: An apparatus for performing wireless communications at a UE, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 22 to 35.

[0357] Aspect 56: An apparatus for wireless communication at a UE, comprising at least one component for performing a method according to any one of aspects 22 to 35.

[0358] Aspect 57: A non-transitory computer-readable medium storing a code for wireless communication at a UE, the code comprising instructions executable by a processor to perform a method according to any one of aspects 22 to 35.

[0359] Aspect 58: An apparatus for wireless communication at a network entity, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 36 to 48.

[0360] Aspect 59: An apparatus for wireless communication at a network entity, comprising at least one component for performing a method according to any one of aspects 36 to 48.

[0361] Aspect 60: A non-transitory computer-readable medium storing code for wireless communication at a network entity, the code comprising instructions executable by a processor to perform the method according to any one of aspects 36 to 48.

[0362] It should be noted that the methods described herein describe possible implementations, and that the operations and steps may be rearranged or otherwise modified and other implementations are possible. In addition, aspects from two or more methods may be combined.

[0363] Although aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for example purposes, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used in much of the description, the techniques described herein may also be applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described may be applicable to various other wireless communication systems, such as Ultra Mobile Broadband (UMB), Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0364] The information and signals described herein may 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 specification may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0365] The various illustrative blocks and components described in conjunction with the disclosure herein may be implemented or performed with a general purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in an alternative, the processor 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, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration).

[0366] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium, or sent via a computer-readable medium. Other examples and specific implementations are within the scope of the present disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these items. Features that implement the functions may also be physically located at different locations, including being distributed so that various parts of the functions are implemented at different physical locations.

[0367] Computer-readable medium includes both non-transient computer storage medium and communication medium, and it includes any medium that facilitates computer program to be transmitted from one place to another place.Non-transient storage medium can be any available medium that can be accessed by general or special-purpose computer.By way of example and not limitation, non-transient computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage device, disk storage device or other magnetic storage device, or can be used for carrying or storing desired program code parts and any other non-transient medium that can be accessed by general or special-purpose computer or general or special-purpose processor in the form of instruction or data structure.In addition, any connection is appropriately referred to as computer-readable medium.For example, if software is sent from website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology such as infrared, radio and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL or wireless technology such as infrared, radio and microwave are included in the definition of computer-readable medium. As used herein, disk and disc include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.

[0368] As used herein (including in the claims), "or" used in a list of items (e.g., a list of items with a phrase such as "at least one of" or "one or more of") indicates an inclusive list, so that, for example, 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). In addition, as used herein, the phrase "based on" should not be interpreted as a reference to a closed set of conditions. For example, an example step described as "based on condition A" can be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "based at least in part on."

[0369] The term "determining" encompasses a variety of actions, and thus, "determining" may include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, database or other data structure), ascertaining, and the like. Additionally, "determining" may include receiving (such as receiving information), accessing (such as accessing data in a memory), etc. Additionally, "determining" may include resolving, obtaining, selecting, choosing, establishing, and other such similar actions.

[0370] In the drawings, similar components or features may have the same reference label. In addition, various components of the same type may be distinguished by following the reference label with a dash and a second label to distinguish between the similar components. If only the first reference label is used in the specification, the description may apply to any of the similar components having the same first reference label, regardless of the second reference label or other subsequent reference labels.

[0371] The descriptions set forth herein in conjunction with the accompanying drawings describe example configurations and do not represent all examples that may be implemented or within the scope of the claims. The term "example" as used herein means "used as an example, instance, or illustration," rather than "preferred" or "advantageous over other examples." The specific implementation includes specific details to provide an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0372] The description herein is provided to enable one of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to one of ordinary skill in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for wireless communication at a user equipment (UE), comprising: generating one or more channel estimates for a plurality of channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based at least in part on one or more measurements using a set of directional beams; computing a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based at least in part on a learning procedure using the one or more channel estimates; as well as A message including an indication of the dictionary is sent to the network entity.

2. The method according to claim 1, further comprising: A feedback message is sent indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message comprising a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

3. The method according to claim 2, further comprising: A signal is received indicating a configuration for transmitting the sparse channel representation for a number of dominant paths of the channel, wherein transmitting the feedback message is based at least in part on the configuration.

4. The method according to claim 2, wherein sending the feedback message further comprises: An identifier of the dictionary associated with the sparse channel representation is sent with the feedback message.

5. The method according to claim 1, further comprising: A signal is received indicating a configuration of a threshold number of training samples to be obtained prior to computing the dictionary, wherein sending the message is based at least in part on satisfying the threshold number of training samples.

6. The method according to claim 5, further comprising: A number of training samples that at least meets a threshold number of training samples is obtained, wherein the UE calculates the dictionary based at least in part on the number of training samples meeting the threshold.

7. The method according to claim 1, further comprising: Respective training samples are obtained at one or more locations of the UE, one or more times of day, or a combination thereof, wherein the one or more channel estimates are based at least in part on the respective training samples.

8. The method according to claim 1, further comprising: A signal is received indicating a configuration of a set of parameters for computing the dictionary, the set of parameters comprising criteria for stopping the learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is computed according to the set of parameters.

9. The method according to claim 1, further comprising: An updated dictionary is computed based at least in part on a change in one or more conditions upon which the dictionary depends, wherein the indication of the dictionary comprises an indication of the updated dictionary.

10. A method for wireless communication at a network entity, comprising: receiving a message including an indication of a dictionary associated with a sparse channel representation of a channel between a user equipment (UE) and the network entity; executing a beam management procedure for selecting one or more directional beams based at least in part on the dictionary; as well as The one or more directional beams are used to communicate with the UE.

11. The method according to claim 10, further comprising: One or more messages, each including an indication of the dictionary, are sent to one or more other UEs, wherein the one or more other UEs have the same antenna configuration as the UE, are associated with the same manufacturer as the UE, are the same model as the UE, are the same type as the UE, or a combination thereof.

12. The method according to claim 10, further comprising: A feedback message is received indicating the sparse channel representation of the channel between the UE and the network entity, the feedback message comprising a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

13. The method according to claim 10, further comprising: A signal is sent indicating a configuration of a threshold number of training samples for computing the dictionary, wherein receiving the message is based at least in part on satisfying the threshold number of training samples.

14. The method according to claim 10, further comprising: A signal is sent indicating a configuration of a set of parameters for computing the dictionary, the set of parameters including criteria for stopping a learning procedure, a number of atoms to be included in the dictionary, or a combination thereof, wherein the dictionary is based at least in part on the set of parameters.

15. A method for wireless communication at a user equipment (UE), comprising: generating one or more channel estimates for a plurality of channels between the UE and a network entity using a sparse recovery technique, wherein the one or more channel estimates are based at least in part on one or more measurements using a set of directional beams; sending a signal indicative of the one or more channel estimates to the network entity; as well as A message is received including an indication of a dictionary associated with a sparse channel representation of a channel between the UE and the network entity, the dictionary being based at least in part on the one or more channel estimates.

16. The method according to claim 15, further comprising: A feedback message indicating the sparse channel representation of the channel between the UE and the network entity is sent after receiving the dictionary, the feedback message comprising a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

17. The method according to claim 16, further comprising: A signal is received indicating a configuration for transmitting the sparse channel representation for a number of dominant paths of the channel, wherein transmitting the feedback message is based at least in part on the configuration.

18. The method according to claim 16, wherein sending the feedback message further comprises: An identifier of the dictionary associated with the sparse channel representation is sent with the feedback message.

19. The method according to claim 15, further comprising: An indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies is received in the message.

20. The method of claim 15, further comprising: An indication of a set of one or more conditions to which the dictionary applies is received in the message, the set of one or more conditions comprising a geographic location, a time of day, a zone, or a combination thereof.

21. The method of claim 15, further comprising: An operation is performed for compressing the one or more channel estimates, wherein the signal indicative of the one or more channel estimates comprises the compressed one or more channel estimates.

22. The method of claim 15, further comprising: A signal is received indicating a configuration for sending the indication of the one or more channel estimates for a number of dominant paths for the channel, wherein sending the signal is based at least in part on the configuration.

23. The method of claim 15, further comprising: A second message is received, the second message including an indication of a second dictionary associated with a second channel between the UE and the network entity based at least in part on a change in one or more conditions upon which the dictionary depends.

24. The method of claim 15, further comprising: Respective training samples are obtained at one or more locations of the UE, one or more times of day, or a combination thereof, wherein the one or more channel estimates are based at least in part on the respective training samples.

25. A method for wireless communication at a network entity, comprising: receiving, from each of a set of one or more user equipment (UEs), a respective signal indicating one or more channel estimates for a plurality of channels between each UE and the network entity; computing a dictionary associated with a sparse channel representation of a channel between the UE and the network entity based at least in part on a learning procedure using the one or more channel estimates; as well as A message including an indication of the dictionary is sent to the UE.

26. The method according to claim 25, further comprising: A feedback message indicating the sparse channel representation of the channel between the UE and the network entity is received after sending the dictionary, the feedback message comprising a set of indices of non-zero elements in the sparse channel representation and a quantized set of the non-zero elements in the sparse channel representation.

27. The method of claim 25, further comprising: An indication of a set of one or more characteristics associated with a set of UEs to which the dictionary applies is sent in the message.

28. The method of claim 25, further comprising: An indication of a set of one or more conditions to which the dictionary applies is sent in the message, the set of one or more conditions comprising geographic location, time of day, zone, or a combination thereof.

29. The method of claim 25, further comprising: A signal is transmitted indicating a configuration for transmitting the one or more channel estimates for a number of dominant paths of the channel, wherein the network entity receives the one or more channel estimates for the number of dominant paths.

30. The method of claim 25, further comprising: A second message is sent, the second message including an indication of a second dictionary associated with a second channel between the UE and the network entity based at least in part on a change in one or more conditions on which the dictionary depends.

Images