Loop equivariant inference machine for channel estimation

Abstract

Methods, systems, and devices for wireless communication are described. A wireless device may receive an assignment of a set of resources associated with a channel, wherein the set of resources includes a first subset of resources allocated for data transmission and a second subset of resources allocated for reference signals. The wireless device may generate a first set of a plurality of channel estimates for each layer of the channel from the reference signal according to a minimum mean square estimation (MMSE) operation. The wireless device may generate a second set of a plurality of channel estimates for each layer of the channel from a non-linear two-dimensional interpolation of the channel, and may perform a refinement operation using the estimates to generate channel estimates associated with a plurality of layers.

Description

[0001] This application is a continuation of the application with the application number 202380064854.3, filed on September 22, 2023, and titled “RECURRENT EQUIVARIANT INFERENCE MACHINES FOR CHANNEL ESTIMATION,” which claims priority to U.S. Patent Application No. 18 / 472,083, filed on September 21, 2023, and titled “RECURRENT EQUIVARIANT INFERENCE MACHINES FOR CHANNEL ESTIMATION,” and U.S. Patent Application No. 17 / 952,203, filed on September 23, 2022, and titled “RECURRENT EQUIVARIANT INFERENCE MACHINES FOR CHANNEL ESTIMATION,” each of which is assigned to the assignee hereof and expressly incorporated by reference herein in its entirety. Cross Reference to Related Applications

[0002] This Patent Application claims priority to U.S. Patent Application No. 18 / 472,083, filed on September 21, 2023, and titled “RECURRENT EQUIVARIANT INFERENCE MACHINES FOR CHANNEL ESTIMATION,” and U.S. Patent Application No. 17 / 952,203, filed on September 23, 2022, and titled “RECURRENT EQUIVARIANT INFERENCE MACHINES FOR CHANNEL ESTIMATION,” by PRATIK, et al., each of which is assigned to the assignee hereof and expressly incorporated by reference herein in its entirety. BACKGROUND

[0003] The following relates to wireless communications, and more specifically to estimating a channel using a machine learning model.

[0004] Wireless communications systems are widely deployed to provide various types of communication content such as voice, video, packet data, messaging, broadcast, and so on. These systems can be capable of supporting communication with multiple users by sharing the 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, LTE-Advanced (LTE-A) systems, or LTE-A Pro systems, and fifth generation (5G) systems, which can be referred to as New Radio (NR) systems. These systems can employ technologies such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple-access communications system can include one or more base stations, each simultaneously supporting communication with multiple communication devices, which can be otherwise known as user equipment (UE). SUMMARY

[0005] The described techniques relate to improved methods, systems, devices, and apparatuses that support cyclic equivariant inference machines for channel estimation. For example, the described techniques allow for the use of cyclic equivariant inference machines to compute channel estimates. In some cases, a wireless communication system can place pilot symbols (e.g., demodulation reference signal (DMRS) symbols) in a transmission slot according to a known pattern, allowing a wireless device to estimate unknown resources of a channel based on known resources (e.g., DMRS symbols). For example, a wireless device can receive an assignment of a set of resources associated with a channel, where the set of resources includes a first subset of resources allocated for data transmission and a second subset of resources allocated for reference signals (e.g., DMRS). The wireless device can generate a plurality of channel estimates (e.g., single-input and single-output (SISO) channel estimates) for each layer of the channel, and utilize the estimates to perform a refinement operation to generate a channel estimate associated with the multiple layers (e.g., a multiple-input and multiple-output (MIMO) channel estimate). In some cases, the refinement operation can include a plurality of iterations. For example, each iteration can include generating a respective gradient associated with each of the per-layer channel estimates based on the per-layer channel estimates and observed resources of the channel (e.g., known DMRS resources); generating a current set of values of latent variables (e.g., inference variables based on observed variables) based on a previous set of values of the latent variables, the respective gradient, and the per-layer channel estimates; and modifying (e.g., refining, updating, improving) the channel estimate based on the current set of values of the latent variables, the per-layer channel estimates, and the respective gradient. In some cases, the refinement operation can be performed by a refinement network that includes a likelihood module, an encoder module, and a decoder module.

[0006] A method for wireless communication at a wireless communication device is described. The method can include receiving an assignment of a set of resources associated with a channel, the set of resources including a first subset of resources allocated for a data signal and a second subset of resources allocated for a reference signal, generating, from the reference signal received on the second subset of resources, a first set of channel estimates associated with respective layers of a set of layers of the channel for the set of resources according to a minimum mean square estimation (MMSE) operation, generating a second set of channel estimates and a set of values of a latent variable associated with respective layers of the set of layers of the channel for the set of resources according to a nonlinear two-dimensional interpolation of the channel, the nonlinear two-dimensional interpolation of the channel based on the first set of channel estimates, and including a refinement operation that includes one or more iterations on the second set of channel estimates, where each iteration of the one or more iterations is performed according to a same set of machine learning parameters. Performing each iteration of the one or more iterations can include generating a respective gradient associated with the second set of channel estimates based on the second set of channel estimates for the second subset of resources and a measured observation of the second subset of resources, generating a second set of values of the latent variable based on a first set of values of the set of values of the latent variable, the second set of channel estimates, the set of machine learning parameters, and the respective gradient, and modifying the second set of channel estimates associated with the set of layers based on the second set of values of the latent variable, the second set of channel estimates, the set of machine learning parameters, and the respective gradient.

[0007] An apparatus for performing wireless communication at a wireless communication device is described. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the wireless communication device to: receive an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generate, according to an MMSE operation, a first set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set from the reference signals received on the second subset of resources; generate a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with corresponding layers in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates; and perform a refinement operation comprising one or more iterations on the second set of multiple channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. To perform each of the one or more iterations, the one or more processors may be configured to cause the wireless device to: generate a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generate a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modify the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0008] Another apparatus for wireless communication is described. The apparatus may include components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generating, according to an MMSE operation, a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, from the reference signal received on the second subset of resources; generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables according to a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates; and including a refinement operation comprising one or more iterations on the second set of multiple channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. Each of the one or more iterations may include components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generating a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0009] A non-transitory computer-readable medium is described, storing code for performing wireless communication at a wireless communication device. The code may include instructions executable by one or more processors to cause the wireless communication device to: receive an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for a data signal and a second subset of resources allocated for a reference signal; generate, according to an MMSE operation, a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, from the reference signal received on the second subset of resources; generate, according to a nonlinear two-dimensional interpolation of the channel for the resource set, a second set of multiple channel estimates and a set of multiple values ​​of latent variables, the second set of multiple channel estimates and the set of multiple values ​​associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates; and perform a refinement operation comprising one or more iterations on the second set of multiple channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. The instruction for executing each of the one or more iterations can be executed by the one or more processors to cause the wireless device to: generate a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generate a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modify the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0010] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the refinement operation is a first refinement operation, and the set of machine learning parameters is a first set of machine learning parameters. Some examples of the methods, apparatuses, and nontransitory computer-readable media described herein may include operations, features, components, or instructions for performing a second refinement operation on the second set of multiple channel estimates, the second refinement operation including one or more second iterations performed based on the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a set of multiple attention computations.

[0011] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the set of multiple attention computations includes intra-Physical Resource Block (PRB) computation, inter-PRB computation, cross-multiple-input multiple-output (MIMO) computation, multilayer perceptron (MLP) computation, or any combination thereof.

[0012] Some examples of the methods, apparatus, and nontransitory computer-readable media described herein may include operations, features, components, or instructions for performing the MMSE operation based on a resource configuration mode allocated to the second subset of resources for the reference signal, the reference signal including a demodulation reference signal (DMRS).

[0013] In some examples of the methods, apparatus, and nontransitory computer-readable media described herein, generating the corresponding gradient may include operations, features, components, or instructions for: generating a corresponding set of values ​​of a residual variable based on the difference between an observation of the measurement of the second resource subset and the second set of multiple channel estimates of the second resource subset; and combining the corresponding set of values ​​of the residual variable, the second resource subset, and the number of mask bits.

[0014] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set of values ​​for generating the latent variable may include operations, features, components, or instructions for combining the second set of multiple channel estimates for the second subset of resources, the corresponding gradient, and corresponding values ​​from the first set of values ​​for the latent variable based on generating the corresponding gradient.

[0015] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set of methods for generating the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0016] In some examples of the methods, apparatus, and nontransitory computer-readable media described herein, the second set that generates the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between resources of each group in a set of multiple resource groups and other groups in the set of multiple resource groups, wherein each group in the set of multiple resource groups comprises a set of multiple resource blocks.

[0017] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set that generates the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between each layer in the set of multiple layers of the resource set.

[0018] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set of modifications to the multiple channel estimates may include operations, features, components, or instructions for combining the values ​​of the latent variable based on the set of machine learning parameters, the second set of multiple channel estimates, and the corresponding gradients.

[0019] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the nonlinear two-dimensional interpolation of the channel is based on a machine learning model.

[0020] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the first set of multiple channel estimates and the second set of multiple channel estimates are associated with a set of multiple single-input single-output (SISO) antenna pairs.

[0021] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, each iteration in the one or more iterations is performed by a refined network comprising a likelihood module, an encoder module, and a decoder module, the refined network including a machine learning model. In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, each refined network performs according to the same set of machine learning parameters.

[0022] A method for wireless communication is described. The method may include: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generating a set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set; and performing a refinement operation comprising one or more iterations on the set of multiple channel estimates, wherein each iteration of the one or more iterations may include operations, features, components, or instructions for: generating a corresponding gradient associated with the set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​of a latent variable based on a first set of values ​​of a latent variable, the set of multiple channel estimates, and the corresponding gradient; and modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0023] An apparatus for performing wireless communication at a wireless communication device is described. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the wireless communication device to: receive an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generate a set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set; and perform a refinement operation including one or more iterations on the set of multiple channel estimates, wherein the instruction for each of the one or more iterations is executable by the processor to cause the apparatus to: generate a corresponding gradient associated with the set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generate a second set of values ​​of the latent variables based on the first set of values ​​of the latent variables, the set of multiple channel estimates, and the corresponding gradients; and modify the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variables, the set of multiple channel estimates, and the corresponding gradients.

[0024] Another apparatus for wireless communication is described. The apparatus may include: means for receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; means for generating a set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set; and means for performing a refinement operation including one or more iterations on the set of multiple channel estimates, wherein each iteration of the one or more iterations may include: means for generating a corresponding gradient associated with the set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; means for generating a second set of values ​​of the latent variable based on the first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and means for modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0025] A non-transitory computer-readable medium storing code for wireless communication is described. The code may include instructions executable by one or more processors to: receive an assignment to a set of resources associated with a channel, the set of resources including a first subset allocated for data signals and a second subset allocated for reference signals; generate a set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set; and perform a refinement operation including one or more iterations on the set of multiple channel estimates, wherein the instructions in each of the one or more iterations are capable of: generating a corresponding gradient associated with the set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​of the latent variable based on the first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0026] In some examples of the methods, apparatus, and nontransitory computer-readable media described herein, generating the corresponding gradient may include operations, features, components, or instructions for: generating a corresponding set of values ​​of a residual variable based on the difference between observations of the measurement of the second resource subset and the set of multiple channel estimates of the second resource subset; and combining the corresponding set of values ​​of the residual variable, observations of the measurement of the second resource subset, and the number of mask bits.

[0027] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set of values ​​for generating the latent variable may include operations, features, components, or instructions for combining the set of multiple channel estimates for the second subset of resources, the corresponding gradient, and corresponding values ​​from the first set of values ​​for the latent variable based on generating the corresponding gradient.

[0028] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set of methods for generating the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0029] In some examples of the methods, apparatus, and nontransitory computer-readable media described herein, the second set that generates the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between resources of each group in a set of multiple resource groups and other groups in the set of multiple resource groups, wherein each group in the set of multiple resource groups comprises a set of multiple resource blocks.

[0030] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second set that generates the value of the latent variable may include operations, features, components, or instructions for modeling the correlation between each layer in the set of multiple layers of the resource set.

[0031] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, modifying the set of multiple channel estimates may include operations, features, components, or instructions for combining the values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0032] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the initial values ​​of this set of multiple channel estimates may be associated with a SISO antenna pair.

[0033] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the second subset of resources may be configured according to resource configuration patterns in a set of resource configuration patterns.

[0034] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the set of resource configuration patterns may be a set of DMRS patterns.

[0035] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, each iteration may be performed by a refined network comprising a likelihood module, an encoder module, and a decoder module, and each refined network may also include corresponding parameters associated with the machine learning operation.

[0036] In some examples of the methods, apparatuses, and nontransitory computer-readable media described herein, the resource set includes one or more resource groups, and each corresponding layer in the set of multiple layers may be associated with a corresponding antenna pair in a set of multiple SISO antenna pairs. Attached Figure Description

[0037] Figure 1 An example of a wireless communication system supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown.

[0038] Figure 2An example of a network architecture supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown.

[0039] Figures 3 to 6 An example of a network supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown.

[0040] Figure 7 and Figure 8 A block diagram of a device supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown.

[0041] Figure 9 A block diagram of a communication manager supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown.

[0042] Figure 10 A diagram is shown of a system comprising a user equipment (UE) supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure.

[0043] Figure 11 A diagram is shown of a system comprising a network entity supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure.

[0044] Figures 12 to 15 A flowchart illustrating a method for supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. Detailed Implementation

[0045] Some wireless communication systems support channel estimation. For example, wireless devices can estimate channel resources to maintain high data throughput. To achieve channel estimation, some communication systems can utilize a tracking reference signal (TRS) to calculate channel characteristics (e.g., Doppler, delay spread, signal-to-noise ratio (SNR), etc.) and estimate channel resources based on these characteristics. However, TRS can include relatively large overhead (e.g., memory, computation), and not all wireless communication systems can transmit TRS continuously (e.g., periodically or relatively regularly over time), which can affect channel estimation. Additionally, some wireless communication systems support multiple-input multiple-output (MIMO) communication, where multiple resource layers can interfere with each other, further reducing the accuracy of channel estimation. A resource layer can refer to the spatial layer of the wireless channel. For MIMO communication, multiple antennas or antenna ports of the transmitting device can each be associated with a corresponding layer that can transmit on the same time-frequency resources. To further improve TRS consistency and account for cross-MIMO interference, the channel estimation process can be updated.

[0046] Some wireless communication devices support machine learning-based channel estimation operations. The techniques described herein allow the application of least mean square estimation (MMSE) techniques used for channel estimation to machine learning-based channel estimation techniques to improve channel estimation. For example, performing a combination of machine learning-based and MMSE-based channel estimation can provide enhanced channel estimation through machine learning capabilities while maintaining the existing channel estimation and demapping hardware at the wireless device for MMSE operations, which can reduce memory consumption and computational costs, among other possibilities. MMSE operations may involve the wireless device estimating the channel by minimizing the mean square error of variables associated with the channel. The techniques described herein allow the use of cyclic equivariant inference engines to compute channel estimates, which can be machine learning models that provide relatively reliable and accurate estimates based on a given set of inputs. In some cases, wireless communication systems may place pilot symbols (e.g., demodulation reference signal (DMRS) symbols, other types of reference symbols, or any other pilot symbols) in transmission slots according to known patterns, thereby allowing the wireless device to estimate unknown resources of the channel based on known resources (e.g., DMRS symbols). For example, a wireless device may receive assignments of a first set of resources allocated within a channel for data transmission and a second set of resources allocated within the channel for reference signals (e.g., DMRS). The wireless device may perform an MMSE operation to generate a first set of multiple channel estimates for each layer of the channel (e.g., single-input single-output (SISO) channel estimates). The MMSE operation may be an estimation technique that utilizes linear equalization to estimate the channel. MMSE may be hardware-supported within the wireless device, which enables reduced complexity and processing compared to performing an initial estimate based on machine learning. The wireless device may then modify the MMSE estimates using nonlinear two-dimensional interpolation and generate a second set of multiple channel estimates for each layer of the channel. For example, the wireless device may construct the first set of multiple channel estimates using interpolation in the time and frequency domains based on a machine learning model. In some cases, nonlinear two-dimensional interpolation may leverage a machine learning model to improve the accuracy of the channel estimates generated by the MMSE operation and apply the channel estimates to both the time and frequency domains.

[0047] A wireless device may utilize a second set of multiple channel estimates to perform a refinement operation to generate channel estimates associated with multiple layers (e.g., MIMO channel estimates). That is, in one example, the wireless device may employ channel estimates generated via MMSE operations and subsequent machine learning interpolation, and the wireless device may refine the channel estimates and combine the estimates for each layer of the channel into a single MIMO channel estimate. In some cases, the refinement operation may include multiple iterations of refinement. Each refinement iteration may generate a corresponding gradient associated with each layer of the channel estimate based on the channel estimates for each layer and the observed resources of the channel (e.g., known DMRS resources). Each refinement iteration may further generate a current set of values ​​for latent variables (e.g., inferred variables based on observed variables). The current set of values ​​for latent variables may be generated based on a previous set of values ​​for latent variables, the corresponding gradients, and the channel estimates for each layer. Each refinement iteration may further modify (e.g., refine, update, improve) the channel estimates based on the current set of values ​​for latent variables, the channel estimates for each layer, and the corresponding gradients. That is, in one example, each refinement iteration may further improve the channel estimates and generate new or improved values ​​for the inferred latent variables. In some cases, the refinement operation can be performed by a refinement network, which can be a machine learning model that includes a likelihood module, an encoder module, and a decoder module.

[0048] The techniques described herein allow wireless devices to reliably and accurately estimate channels with relatively low memory consumption and processing. For example, by first utilizing MMSE operations to generate channel estimates, wireless devices can reduce memory consumption and processing compared to machine learning-based estimation or other techniques. Additionally or alternatively, by using MMSE for channel estimation, wireless devices can support reduced hardware costs and complexity compared to other machine learning-based channel estimation techniques, at least because MMSE operations can be supported by current hardware components of the wireless device.

[0049] The aspects of this disclosure are first described in the context of a wireless communication system. Then, the aspects of this disclosure are described in the context of a network. The aspects of this disclosure are further illustrated and described by means of, and with reference to, apparatus diagrams, system diagrams, and flowcharts relating to cyclic equivariant inference engines used for channel estimation.

[0050] Figure 1 An example of a wireless communication system 100 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. 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 an LTE network, an LTE-A network, an LTE-APro network, an NR network, or a network operating according to other systems and radio technologies, including future systems and radio technologies not expressly mentioned herein.

[0051] Network entity 105 may be distributed across a geographical area to form wireless communication system 100, and may include devices in different forms or with different capabilities. In various examples, network entity 105 may be referred to as a network element, mobility element, radio access network (RAN) node, or network equipment, among other names. In some examples, network entity 105 and UE 115 may wirelessly communicate via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, network entity 105 may support coverage area 110 (e.g., a geographical coverage area) within which UE 115 and network entity 105 may establish one or more communication links 125. Coverage area 110 may be an example of a geographical area within which network entity 105 and UE 115 may support signal communication according to one or more radio access technologies (RATs).

[0052] UE 115 can be distributed throughout the coverage area 110 of wireless communication system 100, and each UE 115 can be stationary or mobile, or stationary and mobile at different times. UE 115 can be devices in different forms or with different capabilities. Figure 1 Some example UE 115s are illustrated herein. The UE 115 described herein can be able to support various types of devices (such as, e.g., ...). Figure 1 The UE 115 may communicate with other UEs 115 or network entities 105 as shown. The UE 115 may include a communication manager 101 configured to send communications to and receive communications from the network entity 105. In some examples, the communication manager 101 may be configured to receive assignments to a set of resources, including resources allocated for data signals and resources allocated for reference signals. Additionally or alternatively, the communication manager 101 may be configured to generate a channel estimate based on MMSE operations, nonlinear two-dimensional interpolation of the channel, refinement operations, or any combination thereof.

[0053] As described herein, a node, which may be referred to as a node, network node, network entity, or wireless node, can be a base station (e.g., any base station described herein), a UE (e.g., any UE described herein), a network controller, apparatus, device, computing system, one or more components, and / or another suitable processing entity configured to perform any of the techniques described herein. For example, a network node can be a UE. As another example, a network node can be a base station. As yet another example, a first network node can be configured to communicate with a second or third network node. In one aspect of this example, the first network node can be a UE, the second network node can be a base station, and the third network node can be a UE. In another aspect of this example, the first network node can be a UE, the second network node can be a base station, and the third network node can be a base station. In still other aspects of this example, the first network node, the second network node, and the third network node can be different from these examples. Similarly, references to UE, base station, apparatus, device, computing system, etc., can include disclosures of UE, base station, apparatus, device, computing system, etc., as network nodes. For example, a disclosure of a UE being configured to receive information from a base station also discloses that a first network node is configured to receive information from a second network node. Consistent with this disclosure, once a particular example is extended according to this disclosure (e.g., a UE is configured to receive information from a base station, and a first network node is also disclosed to be configured to receive information from a second network node), a wider example of the narrower example can be interpreted in reverse, but in a broad, open-ended manner. In the above example where a UE is configured to receive information from a base station, and a first network node is also disclosed to be configured to receive information from a second network node, the first network node can refer to a first UE configured to receive information, a first base station, a first device, a first equipment, a first computing system, a first or more components, a first processing entity, etc.; and the second network node can refer to a second UE, a second base station, a second device, a second equipment, a second computing system, a second or more components, a second processing entity, etc.

[0054] As described herein, different terms may be used in various aspects to describe the transmission of information (e.g., any information, signal, etc.). Disclosure of one communication term includes disclosure of other communication terms. For example, a first network node may be described as being configured to send information to a second network node. In this example and consistent with this disclosure, disclosure that a first network node is configured to send information to a second network node includes disclosure that the first network node is configured to provide, transmit, output, communicate, or send information to the second network node. Similarly, in this example and consistent with this disclosure, disclosure that a first network node is configured to send information to a second network node includes disclosure that the second network node is configured to receive, obtain, or decode information provided, transmitted, output, communicate, or sent by the first network node.

[0055] In some examples, network entity 105 may communicate with core network 130, or communicate with each other, or both. For example, network entity 105 may communicate with 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, network entity 105 may communicate with each other directly (e.g., directly between network entities 105) or indirectly (e.g., via core network 130) via backhaul communication links 120 (e.g., according to X2, Xn, or other interface protocols). In some examples, network entity 105 may communicate with each other via midhaul communication link 162 (e.g., according to midhaul interface protocol) or fronthaul communication link 168 (e.g., according to fronthaul interface protocol) or any combination thereof. Backhaul communication link 120, midhaul communication link 162, or fronthaul communication link 168 may be or include one or more wired links (e.g., electrical links, fiber optic links), one or more wireless links (e.g., radio links, wireless optical links), etc., or various combinations thereof. UE 115 can communicate with core network 130 via communication link 155.

[0056] One or more network entities in network entity 105 described herein may include or be referred to as base station 140 (e.g., transceiver base station, radio base station, NR base station, access point, radio transceiver, Node B, evolved Node B (eNB), next-generation Node B or gigabit Node B (any of which may be referred to as gNB), 5G NB, next-generation eNB (ng-eNB), home Node B, home evolved Node B, or other suitable terms). In some examples, network entity 105 (e.g., base station 140) may be implemented in an aggregated (e.g., monolithic, self-contained) base station architecture that 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 base station 140). Network entity 105 may include communication manager 102 configured to send communications to and receive communications from UE 115. In some examples, the communication manager 102 may be configured to send assignments to a set of resources, including resources allocated for data signals and resources allocated for reference signals. Additionally or alternatively, the communication manager 102 may be configured to generate channel estimates based on MMSE operations, nonlinear two-dimensional interpolation of the channel, refinement operations, or any combination thereof.

[0057] In addition to being performed between UE 115 and network entity 105, or instead of between the UE and network entity, the techniques described herein can also be implemented via additional or alternative wireless devices, including IAB node 104, distributed unit (DU) 165, centralized unit (CU) 160, radio unit (RU) 170, etc. For example, in some specific implementations, the aspects described herein can be implemented in the context of a decomposed radio access network (RAN) architecture (e.g., an open RAN architecture). In a decomposed architecture, the RAN can be divided into three functional areas corresponding to CU 160, DU 165, and RU 170. The functional division between CU 160, DU 165, and RU 175 is flexible and therefore results in many different permutations of functionality depending on which functions (e.g., MAC functions, baseband functions, radio frequency functions, and any combination thereof) are performed at CU 160, DU 165, and RU 175. For example, a functional split of the protocol stack can be used between DU 165 and RU 170, so that DU 165 can support one or more layers of the protocol stack, and RU 170 can support one or more different layers of the protocol stack.

[0058] Some wireless communication systems (e.g., wireless communication system 100), infrastructure for NR access, and spectrum resources may additionally support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture. One or more network entities 105 may include CU 160, DU 165, and RU 170, and may be referred to as donor network entity 105 or IAB donor. One or more DU 165s (e.g., and / or RU 170) associated with donor network entity 105 may be partially controlled by the CU 160 associated with donor network entity 105. One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB node 104) via supported access and backhaul links. IAB node 104 may support mobile terminal (MT) functionality controlled and / or scheduled by the coupled IAB donor's DU 165. Additionally, IAB node 104 may include DU 165, which supports communication links with additional entities (e.g., IAB node 104, UE 115, etc.) within the 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 IAB node 104) may be configured to operate according to the techniques described herein.

[0059] In some examples, the wireless communication system 100 may include a core network 130 (e.g., a next-generation core network (NGC)), one or more IAB donors, IAB nodes 104, and a UE 115, wherein the IAB nodes 104 may be partially controlled by each other and / or by the IAB donors. The IAB donor nodes and IAB nodes 104 may be examples of various aspects of network entity 105. The IAB donors and one or more IAB nodes 104 may be configured as a relay chain (e.g., or communicate according to a relay chain).

[0060] For example, the access network (AN) or RAN can refer to communication between an access node (e.g., an IAB donor), IAB node 104, and one or more UEs 115. An IAB donor can facilitate a connection between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, an IAB donor can refer to a RAN node having a wired or wireless connection to the core network 130. An IAB donor can include a CU 160 and at least one DU 165 (e.g., and RU 170), where CU 160 can communicate with the core network 130 via an NG interface (e.g., some backhaul link). CU 160 can manage Layer 3 (L3) functionality and signaling (e.g., Radio Resource Control (RRC), Serving Data Adaptation Protocol (SDAP), PDCP, etc.). At least one DU 165 and / or RU 170 can manage lower layers, such as Layer 1 (L1) and Layer 2 (L2) functionalities and signaling (e.g., RLC, MAC, physical (PHY) etc.), and each can be at least partially controlled by CU 160. DU 165 can support one or more different cells. IAB donors and IAB nodes 104 can communicate via an F1 interface according to a protocol that defines the signaling messages (e.g., the F1 AP protocol). Additionally, CU 160 can communicate with the core network via an NG interface (which may be part of a backhaul link) and can communicate with other CU 160s (e.g., CU 160 associated with an alternative IAB donor) via an Xn-C interface (which may be part of a backhaul link).

[0061] IAB node 104 may refer to a RAN node that provides IAB functionality (e.g., access for UE 115, radio self-backhaul capability, etc.). IAB node 104 may include DU 165 and MT. DU 165 may act as a distributed scheduling node toward child nodes associated with IAB node 104, and MT may act as a scheduled node toward a parent node associated with IAB node 104. That is, an IAB donor may be referred to as a parent node communicating with one or more child nodes (e.g., an IAB donor may relay UE transmissions through one or more other IAB nodes 104). Additionally, depending on the AN's relay chain or configuration, IAB node 104 may also be referred to as a parent node or child node of other IAB nodes 104. Therefore, the MT entity (e.g., MT) of IAB node 104 can provide a Uu interface to the child node to receive signaling from the parent IAB node 104, and the DU interface (e.g., DU 165) can provide a Uu interface to the parent node to signal to the child IAB node 104 or UE 115.

[0062] For example, IAB node 104 can be referred to as a parent node associated with an IAB node and a child node associated with an IAB donor. An IAB donor may include a CU 160 with a wired (e.g., fiber optic) or wireless connection to the core network and may act as a parent node of IAB node 104. For example, the DU 165 of the IAB donor can relay transmissions to UE 115 via IAB node 104 and can directly signal transmissions to UE 115. The CU 160 of the IAB donor can signal to IAB node 104 via the F1 interface to notify of the establishment of a communication link, and IAB node 104 can schedule transmissions via DU 165 (e.g., transmissions relayed from the IAB donor to UE 115). That is, data can be relayed to and from IAB node 104 via signaling through the NR Uu interface of the MT to IAB node 104. Communication with IAB node 104 can be scheduled by DU 165 of the IAB donor, and communication with IAB node 104 can be scheduled by DU 165 of IAB node 104.

[0063] When the techniques described herein are applied in the context of a decomposed RAN architecture, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of IAB node 104) can be configured to support techniques for large round-trip times during random access channel procedures, as described herein. For example, some operations described as being performed by UE 115 or network entity 105 can be additionally or alternatively performed by components of the decomposed RAN architecture (e.g., IAB nodes, DUs, CUs, etc.).

[0064] In some examples, network entity 105 may be implemented in a decomposed architecture (e.g., a decomposed base station architecture, a decomposed RAN architecture) that can be configured to utilize a protocol stack physically or logically distributed between two or more network entities 105 (such as an 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, network entity 105 may include one or more of the following: CU 160, DU 165, RU 170, RAN Intelligent Controller (RIC) 175 (e.g., a near real-time RIC, a non-real-time RIC), a Service Management and Orchestration (SMO) system 180, or any combination thereof. 170 may also be referred to as a radio headend, intelligent radio headend, remote radio headend (RRH), remote radio unit (RRU), or transmit / receive point (TRP). One or more components of network entity 105 in a decomposed RAN architecture may be co-located, or one or more components of network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 in a decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0065] The functional splitting among CU 160, DU 165, and RU 170 is flexible and can support different functionalities 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 170. For example, protocol stack functional splitting can be used between CU 160 and DU 165, allowing CU 160 to support one or more layers of the protocol stack, and DU 165 to support one or more different layers of the protocol stack. In some examples, CU 160 can host higher protocol layer (e.g., Layer 3 (L3), Layer 2 (L2)) functionalities and signaling (e.g., RRC, SDAP, PDCP). CU 160 can be connected to one or more DU 165 or RU 170, and the one or more DU 165 or RU 170 can host lower protocol layers, such as Layer 1 (L1) (e.g., PHY layer) or L2 (e.g., RLC layer, Media Access Control (MAC) layer) functionality and signaling, and each can be at least partially controlled by CU 160. Additionally or alternatively, protocol stack functional splitting can be employed between DU 165 and RU 170, such that DU 165 can support one or more layers of the protocol stack, and RU 170 can support one or more different layers of the protocol stack. DU 165 can support one or more different cells (e.g., via one or more RU 170). In some cases, functional decomposition between CU 160 and DU 165, or between DU 165 and RU 170, can be performed 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 can be performed by different of CU 160, DU 165, or RU 170). CU 160 can be further functionally decomposed into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 160 can be connected to one or more DU 165s via midhaul communication link 162 (e.g., F1, F1-c, F1-u), and DU 165 can be connected to one or more RU 170s via fronthaul communication link 168 (e.g., open fronthaul (FH) interface). In some examples, the midhaul communication link 162 or the fronthaul communication link 168 may be implemented based on the interfaces (e.g., channels) between the layers of the protocol stack, which are supported by the corresponding network entities 105 that communicate via these communication links.

[0066] In some wireless communication systems (e.g., wireless communication system 100), the 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 node 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 DU 165s or one or more RU 170s may be partially controlled by one or more CU 160s associated with 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 node 104) via supported access and backhaul links (e.g., backhaul communication link 120). IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a DU 165 of a coupled IAB donor. The IAB-MT may include a separate set of antennas for relaying communication with UE 115, or may share the same antennas (e.g., those of RU 170) for access to IAB node 104 via DU 165 of IAB node 104. (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, 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 IAB node 104) may be configured to operate according to the techniques described herein.

[0067] For example, the access network (AN) or RAN may include communication between an access node (e.g., an IAB donor), IAB node 104, and one or more UEs 115. The IAB donor may facilitate connectivity between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, an IAB donor may refer to a RAN node having a wired or wireless connection to the core network 130. The IAB donor may include a CU 160 and at least one DU 165 (e.g., and RU 170), in which case the CU 160 may communicate with the core network 130 via an interface (e.g., a backhaul link). The IAB donor and IAB node 104 may communicate via an F1 interface according to a protocol defining the signaling messages (e.g., the F1 AP protocol). Additionally or alternatively, the CU160 may communicate with the core network via an interface (which may be part of a backhaul link) and may communicate with other CU 160s (e.g., CU 160 associated with an alternative IAB donor) via an Xn-C interface (which may be part of a backhaul link).

[0068] IAB node 104 may refer to a RAN node that provides IAB functions (e.g., access for UE 115, radio self-backhaul capability, etc.). DU 165 may act as a distributed scheduling node toward child nodes associated with IAB node 104, and IAB-MT may act as a scheduled node toward a parent node associated with IAB node 104. That is, an IAB donor may be referred to as a parent node communicating with one or more child nodes (e.g., an IAB donor may relay UE transmissions through one or more other IAB nodes 104). Additionally or alternatively, depending on the AN's relay chain or configuration, IAB node 104 may also be referred to as a parent node or child node of other IAB nodes 104. Therefore, the IAB-MT entity of IAB node 104 may provide a Uu interface for child IAB node 104 to receive signaling from parent IAB node 104, and the DU interface (e.g., DU 165) may provide a Uu interface for parent IAB node 104 to signal to child IAB node 104 or UE 115.

[0069] For example, IAB node 104 may be referred to as a parent node supporting communication to child IAB nodes, or as a child IAB node associated with an IAB donor, or both. An IAB donor may include a CU 160 having a wired or wireless connection to core network 130 (e.g., backhaul communication link 120) and may act as a parent node of IAB node 104. For example, the IAB donor's DU 165 may relay transmissions to UE 115 via IAB node 104, or may signal transmissions directly to UE 115, or both. The IAB donor's CU 160 may signal the establishment of a communication link to IAB node 104 via an F1 interface, and IAB node 104 may schedule transmissions via DU 165 (e.g., transmissions relayed from the IAB donor to UE 115). That is, data may be relayed to and from IAB node 104 via signaling through the NR Uu interface of the MT to IAB node 104. Communication with IAB node 104 can be scheduled by DU 165 of the IAB donor, and communication with IAB node 104 can be scheduled by DU 165 of IAB node 104.

[0070] In the context of applying the techniques described herein to a decomposed RAN architecture, one or more components of the decomposed RAN architecture can be configured to support cyclic equivariant inference engines for channel estimation as described herein. For example, some operations described as being performed by UE 115 or network entity 105 (e.g., base station 140) can additionally or alternatively be performed by one or more components of the decomposed RAN architecture (e.g., IAB node 104, DU 165, CU 160, RU 170, RIC 175, SMO 180).

[0071] UE 115 may include or be referred to as a mobile device, wireless device, remote device, handheld device, or subscriber device, or any other suitable term, wherein "device" may also be referred to as a unit, station, terminal, or client, etc. UE 115 may also include or be referred to as a personal electronic device, such as a cellular phone, personal digital assistant (PDA), tablet computer, laptop computer, or personal computer. In some examples, UE 115 may include or be referred to as a wireless local loop (WLL) station, Internet of Things (IoT) device, Internet of Everything (IoE) device, or machine-type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0072] The UE 115 described herein may be able to communicate with various types of devices, such as other UEs 115 that 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 As shown.

[0073] UE 115 and network entity 105 can wirelessly communicate with each other via one or more communication links 125 (e.g., access links) using resources associated with one or more carriers. The term "carrier" can refer to a set of RF spectrum resources having a physical layer structure defined for supporting communication link 125. For example, a carrier for communication link 125 may include a portion of the RF spectrum band (e.g., a bandwidth portion (BWP)) operating according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling coordinating carrier operation, user data, or other signaling. Wireless communication system 100 may support communication with UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, UE 115 may be configured to have multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation can be used for both frequency division duplex (FDD) and time division duplex (TDD) component carriers. Communication between network entity 105 and other devices can refer to communication between these devices and any part of network entity 105 (e.g., entity, sub-entity). For example, the terms “send,” “receive,” or “communicate” when referring to network entity 105 can refer to any part of the RAN’s network entity 105 (e.g., base station 140, CU160, DU 165, RU 170) communicating with another device (e.g., directly or via one or more other network entities 105).

[0074] The signal waveform transmitted via a carrier may include multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform extended OFDM (DFT-S-OFDM)). In a system employing MCM, a resource element may refer to a resource of one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, in which case the symbol period and 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 decoding rate of the modulation scheme, or both), such that a relatively high number of resource elements (e.g., in the transmission duration) and a relatively high-order modulation scheme can correspond to a relatively high communication rate. Wireless communication resources may refer to a combination of RF spectrum resources, temporal resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial resources can increase the data rate or data integrity used for communication with UE 115.

[0075] The time interval for network entity 105 or UE 115 can be expressed as a multiple of a basic time unit, such as the sampling period. seconds, of which This can represent the supported subcarrier spacing, while The supported Discrete Fourier Transform (DFT) size can be represented. The time interval of the communication resource can be organized according to radio frames, each with a specified duration (e.g., 10 milliseconds (ms)). Each radio frame can be identified by a System Frame Number (SFN) (e.g., ranging from 0 to 1023).

[0076] 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 (e.g., in the time domain) be divided into subframes, and each subframe may be further divided into a 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 number of symbol periods (e.g., depending on the length of the cyclic prefix appended to each symbol period). In some wireless communication systems 100, time slots may be further divided into multiple micro-time slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., The duration of a symbol period is associated with a (number) sampling period. The duration of a symbol period can depend on the subcarrier spacing or the operating frequency band.

[0077] A subframe, time slot, micro-time slot, or symbol can be the smallest scheduling unit of the wireless communication system 100 (e.g., in the time domain) and can be referred to as a transmission time interval (TTI). In some examples, the duration of the TTI (e.g., the number of symbol periods in the TTI) can be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 can be dynamically selected (e.g., in a burst of shortened TTIs (sTTIs)).

[0078] Physical channels can be multiplexed using various techniques to enable communication using carriers. For example, one or more of Time Division Multiplexing (TDM), Frequency Division Multiplexing (FDM), or hybrid TDM-FDM techniques can be used to multiplex physical control channels and physical data channels for signaling via downlink carriers. The control region of a physical control channel (e.g., a control resource set (CORESET)) can be defined by a set of symbol periods and can extend across the system bandwidth of a carrier or a subset of that bandwidth. One or more control regions (e.g., CORESETs) can be configured for a set in UE 115. For example, one or more UEs in UE 115 can monitor or search control regions to obtain control information based on one or more search space sets, and each search space set can include one or more control channel candidates in one or more aggregation levels arranged in a concatenated manner. The aggregation level of control channel candidates can 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 set may include: a common search space set configured to transmit control information to multiple UEs 115, and a UE-specific search space set used to transmit control information to a specific UE 115.

[0079] In some examples, network entity 105 (e.g., base station 140, RU 170) may be mobile, and thus provide communication coverage to 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 use the same or different radio access technologies to provide coverage for various coverage areas 110.

[0080] Wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication, or various combinations thereof. For example, wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable, low-latency, or critical functions. Ultra-reliable communication may include private 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 prioritizing 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.

[0081] In some examples, UE 115 may be configured to support direct communication with other UE 115s via device-to-device (D2D) communication link 135 (e.g., according to peer-to-peer (P2P), D2D, or sidelink protocols). In some examples, one or more UE 115s performing D2D communication in a group may be within the coverage area 110 of network entity 105 (e.g., base station 140, RU 170), which may support aspects of such D2D communication configured (e.g., scheduled) by network entity 105. In some examples, one or more UE 115s in such a group may be outside the coverage area 110 of network entity 105, or may otherwise be unable or not configured to receive transmissions from network entity 105. In some examples, the group of UE 115s communicating via D2D communication may support a one-to-many (1:M) system, where each UE 115 transmits to each of the other UE 115s in the group. In some examples, network entity 105 may facilitate the scheduling of resources used for D2D communication. In other examples, D2D communication may be performed between UEs 115 without involving network entity 105.

[0082] Core network 130 provides user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. Core network 130 can be an evolved packet core (EPC) or a 5G core (5GC), and may include at least one control plane entity (e.g., a Mobility Management Entity (MME), 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), Packet Data Network (PDN) Gateway (P-GW), or User Plane Function (UPF)) for routing packets or interconnecting to external networks. The control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by network entity 105 (e.g., base station 140) associated with core network 130. User IP packets can be delivered through the user plane entity, which can provide IP address allocation and other functions. The user plane entity may connect to one or more network operator IP services 150. IP services 150 may include access to the Internet, intranets, IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0083] Wireless communication system 100 can operate using one or more frequency bands in the range of 300 MHz to 300 GHz. Generally, the region from 300 MHz to 3 GHz is referred to as the Ultra High Frequency (UHF) region or decimeter band because the wavelength range is approximately 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 are sufficient to penetrate structures so that macrocells can provide service to UE 115 located indoors. Compared to communication using smaller frequencies and longer wavelengths in the lower frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz, communication using UHF waves can be associated with smaller antennas and shorter ranges (e.g., less than 100 km).

[0084] Wireless communication system 100 may utilize licensed and unlicensed RF spectrum bands. For example, wireless communication system 100 may use unlicensed frequency bands (such as the 5 GHz Industrial, Scientific, and Medical (ISM) band) to employ Licensed Assisted Access (LAA), LTE Unlicensed (LTE-U) radio access technology, or NR technology. When operating using unlicensed RF spectrum bands, devices such as network entity 105 and UE 115 may employ carrier sensing for collision detection and avoidance. In some examples, operation using unlicensed frequency bands may be combined with component carriers operating using licensed frequency bands based on carrier aggregation configurations (e.g., LAA). Operations using unlicensed spectrum may include downlink transmission, uplink transmission, P2P transmission, or D2D transmission, etc.

[0085] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc., based on frequency / wavelength. In 5G NR, two initial operating bands have been designated as frequency ranges FR1 (410MHz–7.125 GHz) and FR2 (24.25 GHz–52.6 GHz). It should be understood that although a portion of FR1 is greater than 6 GHz, FR1 is generally (interchangeably) referred to as the “sub-6 GHz” band in various documents and articles. Similar naming issues sometimes occur with FR2, which is generally (interchangeably) referred to as the “millimeter wave” band in documents and articles, although this is different from the Extremely High Frequency (EHF) band (30 GHz–300 GHz) designated as a “millimeter wave” band by the International Telecommunication Union (ITU).

[0086] The frequencies between FR1 and FR2 are generally referred to as intermediate frequency (IF) bands. Recent 5G NR studies have identified the operating bands used for these IF bands as the frequency range designation FR3 (7.125 GHz – 24.25 GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, thus effectively extending the features of FR1 and / or FR2 to IF band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as the frequency range designations FR4a or FR4–1 (52.6 GHz – 71 GHz), FR4 (52.6 GHz – 114.25 GHz), and FR5 (114.25 GHz – 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0087] In light of the foregoing, unless otherwise specified, it should be understood that, as used herein, the term "below 6 GHz" and the like can broadly refer to frequencies less than 6 GHz, within FR1, or including intermediate frequency band frequencies. Furthermore, unless otherwise specified, it should be understood that, as used herein, the term "millimeter wave" and the like can broadly refer to frequencies that can include intermediate frequency band frequencies, within FR2, FR4, FR4-a or FR4-1 and / or FR5, or within the EHF band.

[0088] 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 techniques such as transmit diversity, receive diversity, MIMO communication, or beamforming. The antennas of network entity 105 or UE 115 may be located within one or more antenna arrays or antenna panels, which can support MIMO operation 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, the antennas or antenna arrays associated with network entity 105 may be located at different geographical locations. Network entity 105 may include an antenna array having a collection of multiple rows and columns of antenna ports that network entity 105 can use to support beamforming for communication with UE 115. Similarly, UE 115 may include one or more antenna arrays that can support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals transmitted via the antenna ports.

[0089] Network entity 105 or UE 115 can use MIMO communication to leverage multipath signal propagation and improve spectral efficiency by transmitting or receiving multiple signals via different spatial layers. This technique can be referred to as spatial multiplexing. The multiple signals can be transmitted, for example, by a transmitting device via different antennas or different combinations of antennas. Similarly, the multiple signals can be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals can be referred to as a separate spatial stream and can carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers can be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include: single-user MIMO (SU-MIMO), for which multiple spatial layers are transmitted to the same receiving device; and multi-user MIMO (MU-MIMO), for which multiple spatial layers are transmitted to multiple devices.

[0090] Beamforming (also known as spatial filtering, directional transmission, or directional reception) is a signal processing technique that can be used at a transmitting or receiving device (e.g., network entity 105, UE 115) to shape or guide an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting and receiving devices. Beamforming can be achieved by combining signals transmitted via antenna elements of an antenna array such that some signals propagating in a particular direction relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to the signals transmitted via the antenna elements can include the transmitting or receiving device applying amplitude shifts, phase shifts, or both to the signals carried via the antenna elements associated with the device. The adjustments associated with each of these antenna elements can be defined by a set of beamforming weights associated with a particular direction (e.g., relative to the antenna array of the transmitting or receiving device or relative to some other direction).

[0091] Network entity 105 or UE 115 may use beam scanning technology as part of beamforming operations. For example, 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 transmitted multiple times by network entity 105 in different directions. For example, network entity 105 may transmit signals according to different beamforming weight sets associated with different transmission directions. Beam directions may be identified (e.g., by a transmitting device (such as network entity 105) or by a receiving device (such as UE 115)) by transmission along different beam directions for later transmission or reception by network entity 105.

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

[0093] In some examples, transmissions performed by a device (e.g., network entity 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital pre-decoding or beamforming to generate a combined beam for transmission (e.g., from network entity 105 to UE 115). UE 115 may report feedback indicating pre-decoding weights for one or more beam directions, and this feedback may correspond to a configured beam set across the system bandwidth or one or more sub-bands. Network entity 105 may transmit reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)) that may or may not be pre-decoded. UE 115 may provide feedback for beam selection, which may be a pre-decoding 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 transmitted by network entity 105 (e.g., base station 140, RU 170) in one or more directions, UE 115 may use similar techniques to transmit signals multiple times in different directions (e.g., to identify the beam direction used by UE 115 for subsequent transmission or reception), or to transmit signals in a single direction (e.g., to transmit data to a receiving device).

[0094] A receiving device (e.g., UE 115) may perform reception operations according to multiple reception configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a transmitting device (e.g., network entity 105). For example, the receiving device may perform reception according to multiple reception directions by: receiving via different antenna subarrays; processing the received signal according to different antenna subarrays; receiving according to different sets of reception beamforming weights (e.g., different sets of directional listening weights) applied to signals received at multiple antenna elements of the antenna array; or processing the received signal according to different sets of reception beamforming weights applied to signals received at multiple antenna elements of the antenna array, any of which may refer to “listening” according to different reception configurations or reception directions. In some examples, the receiving device may use a single reception configuration to receive along a single beam direction (e.g., when a data signal is received). The single receiver configuration can be aligned along a beam direction determined by listening based on different receiver configuration directions (e.g., based on the beam direction determined to have the highest signal strength, highest SNR, or other acceptable signal quality based on listening to multiple beam directions).

[0095] The wireless communication system 100 can be a packet-based network operating according to a layered protocol stack. In the user plane, communication at the bearer or PDCP layer can be IP-based. The RLC layer performs packet segmentation and reassembly for transmission via logical channels. The MAC layer performs priority processing and multiplexing of logical channels to transport channels. The MAC layer can also implement error detection, error correction, or both to support retransmission and improve link efficiency. In the control plane, the RRC layer provides the establishment, configuration, and maintenance of RRC connections between the UE 115 and network entity 105 or core network 130 that support user plane data radio bearers. The PHY layer maps transport channels to physical channels.

[0096] In some cases, the wireless communication system 100 may support SISO communication, MIMO communication, or both. For example, SISO communication may include communication between a single transmitter and a single receiver, while MIMO communication may include communication between multiple transmitters and multiple receivers. In some cases, MIMO communication may include multiple SISO communications via transmitter and receiver pairs (e.g., transmit antenna and receive antenna pairs). For example, network entity 105 may include a first transmit antenna and a second transmit antenna, and UE 115 may include a first receive antenna and a second receive antenna. Antenna pairs may include a first transmit using the first receive antenna, a first transmit using the second receive antenna, a second transmit using the first receive antenna, and a second transmit using the second receive antenna. Each antenna pair may modify the signal to minimize interference before signal transmission using a beamforming matrix (e.g., a pre-decoding matrix, an orthogonal matrix) (e.g., a linear pre-decoder, a beamformer that creates a beam that focuses energy for each receive antenna by weighting the phase and magnitude of the transmit antennas). Because the beamforming matrix may be unknown to the receiver (e.g., UE 115, network entity 105), the receiver may estimate the pre-decoded channel.

[0097] In some examples, the wireless communication system 100 may support channel estimation. For example, channel estimation can be used in a resource grid-based (e.g., time slot-based) wireless MIMO-OFDM system. Channel estimation can be 5G NR channel estimation with varying DMRS modes, the number of resource blocks, etc. Channel estimation can be used for super-resolution or signal recovery based on sparse observations.

[0098] In MIMO communication, multiple layers of information (e.g., communications) can interfere with each other, making channel estimation more complex. In some cases, orthogonal covering codes can be used to remove interference through a despreading step. However, the despreading step may be insufficient for frequency-selective or fast-fading channels (e.g., high delay spread and high Doppler response). Additionally, narrowband MIMO communication (e.g., communication using blocks of relatively small bandwidth portions) may use different pre-decoding matrices for each resource group (e.g., physical resource groups (PRGs)) that may be unknown to the UE 115. Unknown pre-decoding matrices can add further complexity to channel estimation, causing some wireless communication systems to avoid using the correlation between discontinuous PRGs in channel estimation. For example, some estimation techniques (e.g., MMSE) may utilize a TRS or another continuous reference signal to calculate channel characteristics (e.g., Doppler, delay spread, SNR, etc.) and estimate channel resources based on these characteristics.

[0099] In some cases, estimation techniques may include least squares and linear MMSE (LMMSE). Least squares can avoid using information about channel statistics or noise variance and does not model correlations across different PRG and MIMO layers, thus making it relatively simple to implement with low computational overhead. However, the estimation accuracy may be insufficient for most use cases (e.g., practical applications). LMMSE can utilize second-order channel statistics and noise variance (e.g., bin-based strategies based on estimated channel parameters such as Doppler, delay spread, etc.). Under certain conditions, LMMSE can have high computational cost but relatively low estimation error. However, LMMSE may not model correlations across different PRG and MIMO layers.

[0100] In some cases, estimation techniques may include deep learning-based techniques. Deep learning-based techniques may not utilize explicit information from channel statistics and may employ nonlinear interpolation. Unlike LMMSE, deep learning techniques may not utilize large matrix inversion operations. Deep learning techniques may utilize separate networks for each DMRS mode. In some cases, deep learning techniques may not consider correlations across different PRGs.

[0101] The techniques described herein allow the use of cyclic equivariant inference engines to compute channel estimates, which can lead to channel estimates based on DMRS symbols utilizing the correlation between non-adjacent PRGs (e.g., unknown pre-decoders). In some cases, wireless communication system 100 (e.g., OFDM system) can deploy pilot-based channel estimation techniques to obtain CSI relatively accurately (e.g., obtaining accurate CSI can help maintain high data throughput, for example, in fast fading environments). Pilot signals may be referred to as DMRS symbols. DMRS symbols can be inserted into transmission slots according to known DMRS patterns, thereby allowing wireless devices to estimate unknown channel resources (e.g., non-DMRS locations, resources allocated for data signals) based on known resources (e.g., DMRS symbols). In some cases, DMRS patterns can be pre-configured (e.g., a fixed set of possible DMRS patterns). DMRS patterns can be used based on channel characteristics.

[0102] In some examples, the wireless device may receive an assignment to a set of resources associated with a channel, wherein the set of resources includes a first subset of resources allocated for data transmission (e.g., non-DMRS) and a second subset of resources allocated for reference signals (e.g., DMRS). The wireless device may generate multiple channel estimates (e.g., SISO channel estimates) for each layer of the channel and use the estimates to perform a refinement operation to generate channel estimates associated with the multiple layers (e.g., MIMO channel estimates). In some cases, the refinement operation may include multiple iterations. For example, each iteration may include generating a corresponding gradient associated with each of the layer-by-layer channel estimates based on the layer-by-layer channel estimates and the observed resources of the channel (e.g., known DMRS resources); generating a current set of latent variable values ​​(e.g., inference variables based on observed variables) based on a previous set of latent variable values, the corresponding gradient, and the layer-by-layer channel estimates; and modifying (e.g., refining, updating, improving) the channel estimate based on the current set of latent variable values, the layer-by-layer channel estimates, and the corresponding gradient. In some cases, this refinement operation can be performed by a refinement network that includes a likelihood module, an encoder module, and a decoder module.

[0103] In some cases, the wireless communication system 100 can be incorporated into an end-to-end (E2E) neural network for channel state feedback. Such a neural network architecture can be used to provide channel state information feedback (CSF) by offering an intermediate channel representation to the wireless communication network, and the wireless device (e.g., the receiving wireless device, network entity 105) can reconstruct the channel (e.g., a separate implementation of the proposed method on the UE and network sides), allowing this type of model architecture to have some degree of interoperability specifications.

[0104] Figure 2Examples of network architecture 300 (e.g., decomposed base station architecture, decomposed RAN architecture) supporting cyclic equivariant inference engines for channel estimation according to one or more aspects of this disclosure are illustrated. Network architecture 200 may illustrate examples for implementing one or more aspects of wireless communication system 100. Network architecture 200 may include one or more CUs 160-a that may communicate directly with core network 130-a via backhaul communication link 120-a, or indirectly with core network 130-a via one or more decomposed network entities 105 (e.g., near-RT RIC 175-b via E2 link or non-RT RIC 175-a associated with SMO 180-a (e.g., SMO framework) or both). CUs 160-a may communicate with one or more DUs 165-a via corresponding midhaul communication link 162-a (e.g., F1 interface). DUs 165-a may communicate with one or more RUs 170-a via corresponding fronthaul communication link 168-a. RU 170-a may be associated with a corresponding coverage area 110-a and may communicate with UE 115-a via one or more communication links 125-a. In some implementations, UE 115-a may be served by multiple RU 170-a simultaneously.

[0105] Each network entity in network entity 105 of network architecture 200 (e.g., CU 160-a, DU 165-a, RU170-a, non-RT RIC 175-a, near-RT RIC 175-b, SMO 180-a, Open Cloud (O-Cloud) 205, Open eNB (O-eNB) 210) may include one or more interfaces or may be coupled to one or more interfaces configured to receive or transmit signals (e.g., data, information) via wired or wireless transmission media. Each network entity 105 or an associated processor (e.g., a controller) that provides instructions to the interfaces of network entity 105 may be configured to communicate with one or more network entities in other network entities 105 via transmission media. For example, these network entities 105 may include wired interfaces configured to receive signals on wired transmission media or to transmit signals to one or more network entities in other network entities 105 via wired transmission media. Additionally or alternatively, network entity 105 may include a wireless interface that may include a receiver, transmitter, or transceiver (e.g., an RF transceiver) configured to receive signals on a wireless transmission medium or transmit signals on a wireless transmission medium to one or more other network entities 105, or both.

[0106] In some examples, the CU 160-a can host one or more higher-level control functions. Such control functions may include RRC, PDCP, SDAP, etc. Each control function may be implemented using an interface configured to signal to other control functions hosted by the CU 160-a. The CU 160-a may be configured to handle user plane functions (e.g., CU-UP), control plane functions (e.g., CU-CP), or combinations thereof. In some examples, the CU 160-a may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units may communicate bidirectionally with the CU-CP units via an interface such as an E1 interface. The CU 160-a may be implemented to communicate with the DU 165-a for network control and signaling purposes, as needed.

[0107] DU 165-a may correspond to a logic unit that includes one or more functions (e.g., base station functions, RAN functions) for controlling the operation of one or more RU 170-a. In some examples, DU 165-a may at least partially host one or more aspects of the RLC layer, MAC layer, and PHY layer (e.g., high PHY layers, such as modules for FEC encoding and decoding, scrambling, modulation and demodulation, etc.), depending at least in part on the functional partitioning, such as those defined by the 3rd Generation Partnership Project (3GPP). In some examples, DU 165-a may also host one or more low PHY layers. Each layer may be implemented using an interface configured to communicate with other layers hosted by DU 165-a or with control functions hosted by CU160-a.

[0108] In some examples, lower-layer functions may be implemented by one or more RU 170-a units. For example, an RU 170-a controlled by a DU 165-a may correspond to a logical node that hosts RF processing functions or low-PHY layer functions (e.g., performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, Physical Random Access Channel (PRACH) extraction and filtering, etc.) or both, based at least in part on function splitting (such as lower-layer function splitting). In this architecture, the RU 170-a may be implemented to handle over-the-air (OTA) communications with one or more UE 115-a units. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communications with the RU 170-a may be controlled by the corresponding DU 165-a unit. In some examples, this configuration allows the DU 165-a and CU 160-a to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0109] The SMO 180-a can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network entities 105. For non-virtualized network entities 105, the SMO 180-a can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via an operation and maintenance interface (e.g., the O1 interface). For virtualized network entities 105, the SMO 180-a can be configured to interact with a cloud computing platform (e.g., O-Cloud 205) via a cloud computing platform interface (e.g., the O2 interface) to perform network entity lifecycle management (e.g., to instantiate virtualized network entities 105). Such virtualized network entities 105 may include, but are not limited to, CU 160-a, DU 165-a, RU 170-a, and near-RT RIC 175-b. In some specific implementations, the SMO 180-a can communicate with components configured according to the 4G RAN (e.g., via the O1 interface). Additionally or alternatively, in some implementations, the SMO 180-a may communicate directly with one or more RU 170-a via the O1 interface. The SMO 180-a may also include a non-RT RIC 175-a configured to support the functionality of the SMO 180-a.

[0110] The non-RT RIC 175-a can be configured to include logical functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) or machine learning (ML) workflows (including model training and updates, or policy-based guidance of applications / features in the near-RT RIC 175-b). The non-RT RIC 175-a can be coupled to or communicate with the near-RT RIC 175-b (e.g., via the A1 interface). The near-RT RIC 175-b can be configured to include logical functions that enable near real-time control and optimization of RAN elements and resources via data collection and actions on an interface (e.g., via the E2 interface) connecting one or more CU 160-a, one or more DU 165-a, or both, and the O-eNB 210 to the near-RT RIC 175-b.

[0111] In some examples, to generate AI / ML models to be deployed in a near-RT RIC 175-b, a non-RT RIC 175-a may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 175-b and can be received from non-network data sources or network functions at the SMO 180-a or non-RT RIC 175-a. In some examples, a non-RT RIC 175-a or near-RT RIC 175-b may be configured to tune RAN behavior or performance. For example, a non-RT RIC 175-a may monitor long-term trends and patterns in performance and employ AI or ML models to perform corrective actions via the SMO 180-a (e.g., via O1 reconfiguration) or via the generation of RAN management policies such as the A1 policy.

[0112] Figure 3 An example of a network 300 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. In some examples, network 300 may be implemented by aspects of wireless communication system 100. For example, network 300 may be implemented by UE 115, network entity 105, or both, as referenced herein. Figure 1 and Figure 2 As stated above.

[0113] In some examples, a wireless device (e.g., UE 115, network entity 105) may use multiple resources (e.g., time resources, frequency resources, etc.) to transmit signals via one or more time slots (e.g., frequency and time grids). Resource elements (e.g., symbol 315, DMRS 320, a single subcarrier for a single OFDM symbol) may be grouped with multiple resource elements to form a physical resource block (PRB) (e.g., PRB 310). Each column of resources in PRB 310 (e.g., resource elements with the same time resource and different frequency resources) may be considered a single resource block (e.g., OFDM symbol). In some cases, PRB 310 may include twelve subcarrier frequencies (in the frequency domain) and fourteen OFDM symbols (in the time domain). Multiple PRBs 310 may be bundled (e.g., grouped, combined) to form a single PRG, such as PRG 305. In some cases, PRG 305 may include the number of PRBs 310 determined by a bundle size parameter (e.g., ...). bundleSize The number of consecutive PRBs stacked together in a single PRG. For example, the bundle size parameter may indicate two or four PRBs 310 (e.g., four consecutive resource blocks) for narrowband pre-decoding operations or zero PRBs 310 (e.g., no stacked PRBs) for wideband pre-decoding operations, forming part of the bandwidth portion.

[0114] In some cases, wireless communication systems (e.g., wireless communication system 100) may utilize pilot-based channel estimation techniques. Pilot symbols may be referred to as DMRS symbols (e.g., DMRS symbol 320). For example, a wireless device may transmit signals including one or more PRBs 310 via a Physical Downlink Shared Channel (PDSCH) (e.g., a channel for user data). PRBs 310 may include various symbols 315 (e.g., resource elements allocated for data signals), various DMRS symbols 320 (e.g., resource elements configured for demodulation reference signals), and in some cases, empty symbols (e.g., resource elements without allocated data).

[0115] DMRS symbols 320 may be inserted into various resource elements of the PRB 310 according to resource configuration modes (e.g., DMRS modes). For example, a wireless device may be configured with various DMRS modes and select DMRS mode 345 for the signal. In some cases, various DMRS modes may include DMRS symbols inserted in adjacent resource elements, every other resource element, a single resource block of the PRB, multiple resource blocks of the PRB, and other potential configurations.

[0116] In some examples, DMRS mode 345 may be known to the receiving wireless device. For example, the receiving wireless device may receive the signal and determine, based on DMRS mode 345, which symbols of PRG 305 include various DMRS 320. To extract (e.g., process, determine, decode, estimate) the data at symbol 315, the receiving wireless device may perform a channel estimation process. For example, according to Equation 1, the received DMRS 320 (e.g., ) can be equal to noise (e.g., interference, ) and channels (e.g., PDSCH, ) and the original data (e.g., Combinations of products between ).

[0117] Equation 1: Because DMRS 320 is a pilot symbol known to both the transmitting radio device (e.g., UE 115, network entity 105) and the receiving radio device (e.g., UE 115, network entity 105), the receiving radio device can use it based on the known pilot symbol. and (Given some noise) to estimate (For example, extracting the channel at the DMRS location). The receiving wireless device can then interpolate the estimated channel across various symbols 315 (e.g., residual resource elements) (e.g., for image inpainting) to extract (e.g., compute) the data at symbol 315. In some cases, This can include cross-MIMO interference, inter-PRG interference, and intra-PRG interference. Some channel estimation techniques may not consider (e.g., calculate) these types of interference (e.g., noise), which may lead to inaccurate channel estimation and inaccurate data estimation.

[0118] In some specific implementations, the signal may include multiple PRG 305s, where each PRG 305 can be based on a unique pre-decoding matrix ( This can be configured (e.g., pre-decoding). For example, the signal may include four PRGs 305, each pre-decoded according to a unique pre-decoding matrix. The unique pre-decoding matrix can be found by performing singular value decomposition (SVD) on the resource blocks within the PRG 305 or by using a random (e.g., orthogonal) pre-decoder. In some cases, according to Equation 2, the effective channel of the first PRG 305 (e.g., ) can be equal to the unique pre-decoding matrix of the channel and the first PRG 305 ( The product between ).

[0119] Equation 2: In some cases, the receiving wireless device may not know which pre-decoding matrix is ​​applied to which PRG 305. Therefore, the unique pre-decoding of the channel for each PRG 305 may prevent smooth interpolation of the channel between PRG 305s.

[0120] In some specific implementations, MIMO communication can introduce additional complexity into the channel estimation formula (e.g., the SISO channel estimation formula). For example, at the DMRS tone inference (e.g., extraction) step, the formula may include multiple unknown equations (e.g., multiple equations with multiple unknown variables), which can lead to solving an indeterminate inverse problem. Complexity may include determining the alignment of the channel across different PRG bundles and then utilizing the correlations across them. Additionally, these multiple layers may add additional multiplexing information (e.g., correlations across receiver and transmitter antenna pairs) that can be used to enhance channel estimation performance.

[0121] The techniques described herein allow for the computation of channel estimates using cyclic equivariant inference engines. For example, a single neural network estimator can be used for various use cases of channel estimation, including modular and interpretable model designs (e.g., channel profile estimation, various DMRS mode configurations, SNR, cross-MIMO estimation, inter-PRG estimation, intra-PRG estimation, etc.). In some specific implementations, channel estimation may include multiple stages (e.g., steps). For example, a first stage may include solving for SISO channel estimates (e.g., for each transmitter and receiver antenna pair). A second stage may include using the SISO channel estimates to solve for MIMO channel estimates (e.g., learning correlations between antenna pairs). A third stage may include solving for MIMO channel estimates within a PRG bundle (e.g., within a PRG, learning correlations between resource elements within each PRG). A fourth stage may include solving for MIMO channel estimates across PRG bundles (e.g., between PRGs, learning correlations between resource elements across PRGs).

[0122] Additionally or alternatively, in some examples as described herein, a cyclic equivariant inference engine and an MMSE operation may be used to compute the channel estimate. The MMSE operation may be an estimation technique that utilizes linear equalization to estimate the channel. MMSE may be hardware-supported within the wireless device, which enables reduced complexity and processing compared to performing the initial estimation based on machine learning. A cyclic equivariant inference engine may represent an example of a machine learning model that provides relatively reliable and accurate estimates based on a given set of inputs. For example, the first stage of channel estimation may include solving for the SISO channel estimate (e.g., for each transmitter and receiver antenna pair) based on MMSE operation 350 (e.g., which may also be referred to as the average MMSE (AMMSE) operation). A first set of multiple channel estimates for each layer of the channel may be generated based on MMSE operation 350. In this case, the remaining segments may be built upon the estimates generated by MMSE. In some cases, the individual stages of channel estimation may be performed iteratively (e.g., including multiple iterations of each stage). In some cases, one or more stages of this process may utilize an SNR estimate (e.g., a genie value). Although four stages are described, the channel estimation process utilizing the described technique may include more or fewer stages, stages that include various other steps, stages that do not include one or more of the described steps, or any combination thereof. While these stages are described as four separate stages, they can be considered as a continuous process.

[0123] In some cases, a network can perform individual stages. For example, a network can include, as referenced herein, various stages. Figure 3 The coarse network described herein and as referenced herein Figures 4 to 6The refinement network is a request network. In some cases, the network may include u-net type (e.g., u-net 525) encoder (e.g., encoder 430) and decoder (e.g., decoder 435) convolutional blocks, followed by an attention-based (e.g., attention 605) refinement network for longer-range correlations. In some examples, the coarse network 325 may provide an initial channel estimate (e.g., a coarse estimate) per daily antenna pair (e.g., transmit and receiver antenna pairs) per PRG via learned interpolation (e.g., smoothing). Additionally or alternatively, MMSE operation 350 may provide an initial channel estimate per daily antenna pair per PRG, and the coarse network 325 may modify or update the channel estimate via the learned interpolation.

[0124] Network 300 can represent the first phase. Wireless devices (e.g., as referenced herein) Figure 1 The UE 115, network entity 105, or both may receive an assignment of a set of resources associated with a channel (e.g., a PDSCH channel). This set of resources may include a first subset of resources allocated for data signals (e.g., symbol 315) and a second subset of resources allocated for reference signals (e.g., DMRS symbol 320).

[0125] In some cases, the wireless device may perform MMSE operation 350 to generate a first set 355 of multiple channel estimates (e.g., LS channel estimates at DMRS symbol 320) associated with a corresponding layer 360 of a channel for a resource set. For example, this resource set may include one or more PRGs 305, and a second subset of resources may include individual DMRS symbols 320 inserted into the corresponding resource elements based on a resource configuration pattern (e.g., pattern 345) from a set of resource configuration patterns (e.g., a set of DMRS patterns). In some examples, one or more resources in the first set, including resources not in DMRS symbol 315, may be initialized with zero entries. Each corresponding layer 360 may be associated with a corresponding antenna pair (e.g., a transmitter and receiver pair) of multiple SISO antenna pairs. In some specific implementations, the initial values ​​of the first set 355 of multiple channel estimates may be associated with SISO antenna pairs. Compared to other channel estimation techniques, MMSE operation 350 may be associated with relatively low computational cost and processing. As described herein, network 300 may utilize MMSE channel estimates as input and may build upon MMSE estimates. For example, after MMSE operation 350, there can be one or more attention-based refinement operations (e.g., machine learning-based channel estimation) for relatively long-range correlations, which reduces complexity and processing compared to other channel estimation techniques.

[0126] After performing MMSE operation 350, the wireless device can use a first set 355 of multiple channel estimates to generate a second set 335 of multiple channel estimates using network 325 (e.g., a coarse network). In some examples, network 325 may include or be based on a machine learning model for channel estimation. In some examples, network 325 may perform nonlinear two-dimensional interpolation of the channel based on the first set 335 of multiple channel estimates. For example, network 325 may interpolate the channel in both the time and frequency domains (e.g., two dimensions).

[0127] Network 325 may involve (e.g., input) a first set 355 of channel estimates generated by MMSE operation 350 based on PRG 305. Network 325 may perform various iterations 330 on the first set 355 of channel estimates. For example, network 325 may include a u-net encoder-decoder fully convolutional network, where each iteration may include gated and gated extended convolutional units. In some cases, for one or more iterations 330, network 325 may copy and concatenate the results of previous iterations 330 to one or more iterations 330. In some examples, the first set 355 of multiple channel estimates and the second set 335 of multiple channel estimates may be channel estimates for a corresponding SISO antenna pair for each PRG bundle (e.g., ,in It is channel estimation. It is a PRG index. It is a PRB index. It is the MIMO index of a given antenna pair ( ),and (This refers to the resource element index within the PRB two-dimensional grid). For example, a wireless device can receive corresponding PRG bundles per antenna pair. If MIMO communication includes two transmit antennas and two receive antennas, there can be four antenna pairs, each antenna pair having multiple PRG bundles. The wireless device can utilize MMSE operation 350 to generate a first channel estimate 355 for each antenna pair and each PRG bundle 305, and utilize network 325 to further generate a second channel estimate 335 for each antenna pair and each PRG bundle 305. In some cases, network 325 can output... Network 325 can additionally generate latent variables. For example, the latent variables can be estimates 340 (e.g., z-estimates), which may not be directly observed but inferred from parameters of other observations. The latent variables can be abstract representations of underlying channel characteristics (e.g., Doppler shift, delay spread). Network 325 (e.g., an embedding network) can be used as a feature extractor to generate initial latent values ​​(e.g., ...). This can be further used by subsequent refinement modules. In some examples, the output of network 325 can be the input of network 400 (e.g., input 415).

[0128] In some cases, the techniques described herein can lead to various advantages over other channel estimation techniques. For example, channel estimation via cyclic equivariant inference engines (e.g., networks 300, 400, 500, and 600) can offer various signal processing and deep learning advantages. For instance, signal processing can be based on DMRS (e.g., excluding dependence on TRS except SNR), excluding explicit parameter estimation (e.g., Doppler shift, delay spread, etc.), avoiding old binning strategies, utilizing relatively less memory and computational overhead (e.g., reducing parameter library maintenance), modeling additional interactions (e.g., interference, cross-MIMO, intra-PRG, inter-PRG processing gains), and abstracting the orthogonal overlay code (OCC) despreading step (as referenced herein). Figure 1 (as described herein) or any combination thereof, thereby circumventing the associated computational costs and performance losses. Deep learning techniques may include a variable number of PRG bundles, a variable number of bundle sizes (e.g., PRBs per PRG), multiple DMRS patterns (e.g., multiple input DMRS configurations, the number of additional columns, configuration types), fundamental mathematical symmetries, positive models in network design, and modular and interpretable architectures (e.g., the ability to perform ablation studies and measure component significance). By leveraging network 325 built on top of MMSE operation 350 as described herein, one or more nonlinear interpolation gains can be added to MMSE estimation. MMSE operation 350 provides a partially machine learning channel estimation solution that enables machine learning capabilities while maintaining existing channel estimation and demapping hardware at the wireless device, reducing memory consumption and computational costs, among other possibilities.

[0129] Figure 4 An example of a network 400 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. In some examples, network 400 may be implemented by aspects of wireless communication system 100. For example, network 400 may be implemented by UE 115, network entity 105, or both, as referenced herein. Figure 1 and Figure 2 As stated above.

[0130] In some cases, Network 400 can support channel estimation. For example, the channel estimation problem can be defined as solving a channel estimation problem given an observed signal (e.g., ...). ) and signals (e.g., Maximize the channel in the case of (e.g., The posterior (e.g.) In some cases, conditional probability distributions (e.g., This can be parameterized by channel characteristics (e.g., delayed Doppler distribution). See references in this document. Figure 3 The latent variables (e.g.) It can be an abstract representation of basic channel characteristics (e.g., Doppler, delay spread, etc.).

[0131] In some cases, the output of network 300 can be the input of network 400. For example, input 415 may include one or more channel estimates (e.g., channel estimate 335 per SISO antenna pair per PRG 305) and corresponding estimates 340 (e.g., corresponding latent variables per channel estimate). Input 415 may also be the input of a refinement network 405 that may include various iterations 410. For example, a wireless device (e.g., network entity 105, UE 115) may perform a refinement operation on the channel estimates (e.g., via refinement network 405). The refinement operation may include multiple iterations to generate corresponding gradients (e.g., gradient 480) based on observations of channel estimates of a subset of resources (e.g., DMRS symbols) and measurements of a subset of resources (e.g., DMRS symbol 320), as referenced herein. Figure 4 The aforementioned (e.g., module 425); generates a second set of latent variables based on channel estimation and corresponding gradients, as referenced herein. Figure 4 and Figure 5 The aforementioned (e.g., module 430); and the modification of the channel estimates associated with multiple layers based on a second set of latent variables, channel estimates, and corresponding gradients, as referenced herein. Figure 5 The aforementioned (e.g., module 435).

[0132] In some cases, the refinement network 405 may include iterative refinement performed by various refinement units. For example, each iteration 410 of the refinement network 405 may be performed by various modules (e.g., three or four unique refinement modules). For example, iteration 410 may include module 425 (e.g., a likelihood module), module 430 (e.g., an encoder module), and module 435 (e.g., a decoder module). Additionally or alternatively, iteration 410 may include components for performing... Figure 4 Various other modules for other tasks not illustrated herein. In some examples, the refinement network 405 may include a corresponding set of machine learning parameters 485 associated with machine learning operations. For example, the set of machine learning parameters 485 may be represented as follows: The set of machine learning parameters 485 can be set during machine learning simulations (e.g., pre-field operations). In some cases, the set of machine learning parameters 485 may include corresponding parameters unique for each iteration 410 (e.g., for T iterations, ...). ,in This is because the input to each iteration can vary (e.g., different from other traditional encoder and decoder machine learning implementations). In some other cases, the set of machine learning parameters 485 can be common in each iteration 410 to reduce the complexity or size of the implementation of the refinement network 405. That is, the same parameters can be used in each iteration 410 (e.g., for T iterations, ...). ).

[0133] In some cases, module 425 may output to modules 430 and 435, module 430 may output to module 435, and module 435 may output to the next iteration 410 or to the final (e.g., last, final) output (e.g., output 420) of the refinement network 405. In some examples, the output of module 435 (e.g., output 420) may include channel estimates of the second module 425, the second module 430, and the second module 435 that are output to the next iteration 410 (e.g., a set of MIMO channel estimates for each of the PRG, PRB, and antenna pairs at the respective iteration 410). For example, for iteration 410 (e.g., The set of channel estimates (e.g., ) can be equal to In some cases, the output of module 435 may include latent variables (e.g., a set of latent variables for each channel estimation) that are output to second module 425 and the next iteration 410 of second module 430. For example, for the set of latent variables of iteration 410 (e.g., ) can be equal to .

[0134] In some examples, at least a portion of input 415 may be an input to module 425. For example, as referenced herein... Figure 3 The second set 335 of the multiple channel estimates can be input to module 425. Additionally or alternatively, the observed DMRS symbols (e.g., ) and known DMRS symbols (e.g., ) can be input into module 425 (e.g., In some cases, module 425 can coordinate the descent. and And it uses cyclic inference as the gradient. For example, according to Equation 3, module 425 can be based on observations of this measurement of a resource subset (e.g., DMRS symbol 320) and a second set 335 of multiple channel estimates associated with that resource subset. The difference between ) generates the corresponding set of values ​​for the residual variable 465 (e.g., According to Equation 3, module 425 can combine the corresponding set of values ​​of residual variable 465, and known observations 470 associated with the resource subset (e.g., And the number of mask bits 475 (e.g., binary mask).

[0135] Equation 3: Therefore, module 425 can generate the corresponding gradient 480 (e.g., For example, each antenna pair may have a corresponding gradient based on the channel component associated with the respective antenna pair. In some cases, the feedback from module 425 (e.g., the feedback module) may also be sparse because the observations are sparse.

[0136] In some examples, module 430 may include various steps. For example, module 430 (e.g., an encoder module) may receive at 440 a first set of values ​​including latent variables, a channel estimate, and an input of gradient 480 (e.g., At position 445, the input fusion is performed, as referenced in this article. Figure 5 As described above; at 450, various attention calculations are performed (e.g., intra-PRG calculation at 450-a, inter-PRG calculation at 450-b, and cross-MIMO calculation at 450-c), as referenced herein. Figure 6 The process is described above; at 455, a multilayer perceptron (MLP) procedure is performed; and at 460, a second set of latent variable values ​​is output (e.g., In some cases, the output of each step can be cascaded with the output of the next step. Module 430 can generate a second set of values ​​for the latent variables according to Equation 4 via various steps: Equation 4: In some cases, module 435 may receive a second set of latent variable values ​​and modify the channel estimates associated with multiple layers based on the second set of latent variable values, the channel estimates (e.g., channel estimates from previous iterations), and the corresponding gradients. For example, the channel estimate for iteration 410 may be generated according to Equation 5: Equation 5: As referenced in this article Figure 5 As stated above.

[0137] In some examples, each iteration 410 of the refinement network 405 may utilize the same set 485 of one or more machine learning parameters. For example, the first iteration 410 may operate based on this set of machine learning parameters 485. Each module in modules 425, 430, and 435 may operate based on corresponding machine learning parameters from the set of machine learning parameters 485. The remaining iterations 410 of the refinement network 405 may utilize the same set of machine learning parameters 485 to estimate a given attention computation. The set of machine learning parameters 485 may be generated based on training the refinement network 405 according to one or more training parameter sets. If weights are shared during training operations (e.g., If shared weights are used, the same set of machine learning parameters 485 can be generated for each iteration 410. This set of machine learning parameters 485 can be stored on the refinement network 405 and can be utilized during the operation of the refinement network 405. In some examples, different refinement operations can be performed for different attention computations, and all iterations 410 of a given refinement operation can share the same set of machine learning parameters 485, where the set of machine learning parameters for different refinement operations can be different. Attention computations can include, for example, intra-PRB computation, inter-PRB computation, cross-MIMO computation, MLP computation, or any combination thereof. The size of the shared parameter set can be independent of the amount of resources and can be based on the number of machine learning model parameters used for a given attention computation.

[0138] Compared to a refinement operation using different parameters for each iteration 410, sharing the same set of machine learning parameters 485 across all iterations 410 enables a reduction in the size of the refinement network 405 and a reduction in the complexity associated with the refinement operation. This reduction in size and complexity is achieved while the reliability and accuracy of the refinement operation remain relatively unchanged. For example, the number of parameters in the parameter set for iteration 410 of the refinement network can range from 100K to 2M parameters, and therefore sharing the same parameter set across iterations 410 provides a substantial benefit in terms of storage space used for that parameter set. Thus, the number of parameters that can be generated when training the refinement network 405 is less than if different parameters were used for each iteration 410, and the refinement operation still produces reliable and accurate outputs 420 associated with the refined channel estimation and latent variables.

[0139] Figure 5 An example of a network 500 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. In some examples, network 500 may be implemented by aspects of wireless communication system 100, network 400, or both. For example, network 500 may be implemented by UE 115, network entity 105, encoder 430, decoder 435, or any combination thereof, as referenced herein. Figure 1 and4 As stated above.

[0140] In some cases, Network 500 can perform fusions associated with neural networks. For example, Network 500 can be an example of a convolutional neural network (CNN) (e.g., a neural network that uses convolutions instead of more general matrix multiplications for multiple layers). In some cases, fusions associated with CNNs can fuse (e.g., combine, compress) two or more convolutional layers (e.g., the weights associated with each layer) together.

[0141] In some examples, such as those referenced in this article Figure 4 The refinement network (e.g., refinement network 405) may utilize network 500 through one or more modules (e.g., modules 430, 435). For example, the encoder module (e.g., module 430) may perform a fusion operation (e.g., at 445). The encoder module may generate a second set of values ​​of latent variables associated with multiple channel estimates based on the corresponding values ​​of a first set of values ​​of combined (e.g., fused) channel estimates, corresponding gradients (e.g., gradient 480), and latent variables. For example, the encoder module may generate output 530 (e.g., based on equation 6) ): Equation 6: in It is a fusion operation. This represents the first set of values ​​for the latent variable (e.g., the first part of the estimate 505). This represents the channel estimation (e.g., the second part of the estimation 505), and This represents the corresponding gradient (e.g., gradient 510). For example, the encoder module can fuse gradient 510 (e.g., from likelihood module 425) into the latent state variables (e.g., a first set of latent variable values), thus modeling MIMO multiplexing (e.g., multiplexed MIMO phenomena). The fusion operation can be performed independently on each PRG of the channel (e.g., PRG 305) and incorporate gradient 510 (e.g., gradient information) into the latent state (e.g., the fusion operation is performed for each PRG of each antenna pair).

[0142] In some cases, the fusion operation may include various steps. For example, the encoder module may receive an estimate 505 (e.g., the channel estimate and latent variable values ​​from the previous iteration 410) and a gradient 510 (e.g., the gradient 480 from the same iteration 410) as input, as referenced herein. Figure 4 The encoder module can combine (e.g., fuse, cascade) estimates 505 and gradients 510 to generate a combination 520 (e.g., In some cases, the combination 520 can be input into the u-net 525 (e.g., a tiny u-net). In some examples, the u-net 525 can be an example of a CNN type utilizing upsampling operators (e.g., upsampling operators with a relatively large number of feature channels). The u-net 525 can perform various computations associated with the neural network (e.g., combination, operations) to generate the output 530 (e.g., ).

[0143] In some examples, the decoder module (e.g., module 435) may perform a fusion operation. The decoder module may modify the channel estimates (e.g., generate a third iteration of the channel estimates) based on a second set of combined (e.g., fused) latent variable values ​​(e.g., output from step 460), a second set of multiple channel estimates, and corresponding gradients (e.g., gradient 480). For example, the decoder module may generate output 530 based on Equation 7 (e.g., ): Equation 7: in It is a fusion operation. The second set represents the values ​​of the latent variable (e.g., the first part of the estimate 505). This represents the channel estimation (e.g., the second part of the estimation 505), and This represents the corresponding gradient (e.g., gradient 510). For example, the decoder module may receive estimate 505 (e.g., channel estimate and latent variable values ​​from the same iteration 410) and gradient 510 (e.g., gradient 480 from the same iteration 410) as input, as referenced herein. Figure 4 The decoder module can combine (e.g., fuse, cascade) estimates 505 and gradients 510 to generate a combination 520 (e.g., In some cases, the combination 520 can be input to the u-net 525 (e.g., a tiny u-net). The u-net 525 can perform various computations associated with the neural network (e.g., combination, operations) to generate the output 530 (e.g., The decoder module can utilize information from various sub-modules (steps 440 to 460) of the likelihood module and the encoder module to update latent variables, channel estimates, or both. The decoder module can act independently on each PRG to improve the channel estimate (e.g., make the channel estimate closer to the actual channel) by utilizing the updated latent variables (e.g., a second set of values) along with gradient information.

[0144] Figure 6An example of a network 600 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. In some examples, network 600 may be implemented by aspects of wireless communication system 100, network 400, or both. For example, network 600 may be implemented by UE 115, network entity 105, encoder 430, or any combination thereof, as referenced herein. Figure 1 and 4 As stated above.

[0145] In some cases, network 600 may perform attention operations associated with the neural network (e.g., attention 605). For example, attention 605 may include weighting portions of the input data (e.g., input 610) in a manner different from other portions of the input data (e.g., enhancing some parts of the data while reducing others). In some cases, applying attention 605 may aggregate input data (e.g., observed DMRS symbols) with known data (e.g., known DMRS symbols) (e.g., modification, alignment). In some examples, attention 605 may model interactions (e.g., correlations) within data elements 620. For example, data elements 620-a, 620-b, 620-c, and 620-d may interact with data elements 620-e, 620-f, 620-g, and 620-h, and vice versa.

[0146] In some cases, the encoder module (e.g., module 430) may perform attention 605 (e.g., self-attention) at various steps of the channel estimation process (e.g., step 450), as referenced herein. Figure 4 As described above. For example, the encoder module may (e.g., at 450-a) perform an in-PRG attention operation to model the correlation between the resources (e.g., resource elements) of each PRB (e.g., PRB 310) of the PRG (e.g., PRG 305) and other PRBs of that PRG (e.g., PRBs belonging to a single PRG bundle). The encoder module may determine a set of values ​​for latent variables (e.g., output 530) from the fusion operation, as referenced herein. Figure 5 The encoder module can flatten each subset of values ​​associated with each PRB of the PRG. For example, the set of values ​​(e.g., ) may include four subsets of values ​​(e.g., , The encoder module can flatten (e.g., combine, compress into a single frequency line) four subsets into data elements 620-a, 620-b, 620-c, and 620-d (e.g., input 610). In some cases, data elements 620-e, 620-f, 620-g, and 620-h can be copies (replicas) of data elements 620-a, 620-b, 620-c, and 620-d, respectively (e.g., , In some examples, PRG intra-attention can be used to model long-range correlations (e.g., PRBs separated across frequency axes).

[0147] In some cases, the encoder module may (e.g., at 450-b) perform an inter-PRG attention operation to model the correlations between resources (e.g., resource elements) of each PRG in MIMO communication (e.g., PRG 305). The encoder module may determine a flattened subset of values ​​associated with each PRB of each PRG (e.g., , , , ), and combine flattened subsets (e.g., embedded subsets) (e.g., concatenation, averaging, mean pull) into a single set of values ​​(e.g.: , , , Data elements 620-a, 620-b, 620-c, and 620-d are respectively used as data elements 620-a, 620-b, 620-c, and 620-d (e.g., input 610). In some cases, data elements 620-e, 620-f, 620-g, and 620-h can be derived from... , , , The encoder module can represent the corresponding output of attention 605 (e.g., output 615, residual) with a flattened subset of values ​​(e.g., the subset before averaging). , , , The combinations (e.g., addition) serve as the output of inter-PRG attention 615. In some examples, inter-PRG attention can facilitate information exchange across different PRG bundles.

[0148] In some cases, the encoder module may (e.g., at 450-c) perform cross-MIMO attention operations to model the correlations between each of the multiple layers associated with MIMO communication (e.g., interactions between antenna pairs per PRB per PRG bundle). In some cases, MIMO communication may be a collection of resources including DMRS symbol 320 and data symbol 315, as referenced herein. Figure 3 The encoder module can determine the source block (e.g., line pair) for each MIMO layer (e.g., daily line pair). For example, in a two-dimensional grid, data elements 620-a, 620-b, 620-c, and 620-d (e.g., input 610 for cross-MIMO attention operations) can be respectively derived from... , , and In some cases, data elements 620-e, 620-f, 620-g, and 620-h can be represented by... , , and The encoder module can output 615 for cross-MIMO attention. In some examples, cross-MIMO attention can model the interactions (e.g., correlations) between different transmission links per PRG per PRB (e.g., between different MIMO links in an equally variable manner). In some examples, the encoder module can utilize the same set of machine learning parameters for all iterations of a given attention computation. That is, in multiple attention computations, each individual attention computation can utilize a corresponding set of machine learning parameters, and the set of machine learning parameters can differ across attention computations.

[0149] Figure 7 A block diagram 700 illustrates a device 705 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure. Device 705 may be an example of aspects of a UE 115 or network entity 105 as described herein. Device 705 may include a receiver 710, a transmitter 715, and a communication manager 720. Device 705 or one or more components of device 705 (e.g., receiver 710, transmitter 715, and communication manager 720) may include at least one processor (or processing circuitry) that may be coupled to at least one memory (or memory circuitry) to individually or jointly support or implement the technology. Each of these components may communicate with each other (e.g., via one or more buses).

[0150] Receiver 710 may provide components for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to cyclic variable inference engines used for channel estimation). The information may be passed to other components of device 705. Receiver 710 may utilize a single antenna or a collection of antennas.

[0151] Transmitter 715 may provide components for transmitting signals generated by other components of device 705. For example, transmitter 715 may transmit information associated with various information channels, such as control channels, data channels, information channels related to cyclic variable inference engines used for channel estimation, such as packets, user data, control information, or any combination thereof. In some examples, transmitter 715 may be co-located with receiver 710 in a transceiver module. Transmitter 715 may utilize a single antenna or a collection of multiple antennas.

[0152] The communication manager 720, receiver 710, transmitter 715, or various combinations thereof, or various components thereof, may be examples of parts for performing various aspects of a cyclic equivariant inference engine for channel estimation as described herein. For example, the communication manager 720, receiver 710, transmitter 715, or various combinations thereof, or components thereof, may be able to perform one or more of the functions described herein.

[0153] In some examples, the communication manager 720, receiver 710, transmitter 715, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). This circuitry may include a processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (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. In some examples, at least one processor (or processing circuitry) and at least one memory (or memory circuitry) coupled to said at least one processor may be configured to perform one or more of the functions described herein (e.g., instructions stored in at least one memory are executed individually or jointly by one or more processors).

[0154] In another specific embodiment, the communication manager 720, receiver 710, transmitter 715, or various combinations or components thereof may be implemented in code executed by at least one processor (e.g., as communication management software or firmware). If implemented in code executed by at least one processor, the functionality of the communication manager 720, receiver 710, transmitter 715, or various combinations or components thereof may be performed by a general-purpose processor, DSP, CPU, ASIC, FPGA, microcontroller, or any combination of these or other programmable logic devices (e.g., components configured or otherwise individually or collectively to support the performance of the functions described in this disclosure).

[0155] In some examples, the communication manager 720 may be configured to use or otherwise cooperate with the receiver 710, transmitter 715, or both to perform various operations (e.g., receiving, acquiring, determining, monitoring, outputting, transmitting). For example, the communication manager 720 may receive information from the receiver 710, transmit information to the transmitter 715, or be integrated in combination with the receiver 710, transmitter 715, or both to acquire information, output information, or perform various other operations as described herein.

[0156] According to the examples disclosed herein, the communication manager 720 can support wireless communication. For example, the communication manager 720 is capable of, configured to, or operable to support components for: receiving an assignment of a resource set associated with a channel, the resource set including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The communication manager 720 is capable of, configured to, or operable to support components for: generating a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, based on the reference signal received from the second subset of resources according to MMSE operations. The communication manager 720 is capable of, configured to, or operable to support components for: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The communication manager 720 is capable of, configured to, or operable to support components for: performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, to perform each of the one or more iterations, the communication manager 720 may be configured to, or otherwise support components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0157] By including or configuring a communication manager 720 according to the examples described herein, device 705 (e.g., at least one processor that controls or is otherwise coupled to receiver 710, transmitter 715, communication manager 720, or a combination thereof) can support technologies that can support techniques for more accurate channel estimation, more efficient use of communication resources, and reduced memory and computational overhead.

[0158] Figure 8A block diagram 800 of a device 805 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure is shown. Device 805 may be an example of aspects of device 705, UE 115, or network entity 105 as described herein. Device 805 may include a receiver 810, a transmitter 815, and a communication manager 820. Device 805 or one or more components of device 805 (e.g., receiver 810, transmitter 815, and communication manager 820) may include at least one processor (or processing circuitry) that may be coupled to at least one memory (or memory circuitry) to support the technology. Each of these components may communicate with each other (e.g., via one or more buses).

[0159] Receiver 810 may provide components for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to cyclic variable inference engines used for channel estimation). The information may be passed to other components of device 805. Receiver 810 may utilize a single antenna or a collection of antennas.

[0160] Transmitter 815 may provide components for transmitting signals generated by other components of device 805. For example, transmitter 815 may transmit information associated with various information channels, such as control channels, data channels, information channels related to cyclic variable inference engines used for channel estimation, such as packets, user data, control information, or any combination thereof. In some examples, transmitter 815 may be co-located with receiver 810 in a transceiver module. Transmitter 815 may utilize a single antenna or a collection of multiple antennas.

[0161] Device 805 or its various components may be examples of parts used to perform various aspects of a cyclic equivariant inference engine for channel estimation as described herein. For example, communication manager 820 may include scheduling component 825, MMSE component 830, coarse network component 835, fine network component 840, or any combination thereof. Communication manager 820 may be examples of various aspects of communication manager 720 as described herein. In some examples, communication manager 820 or its various components may be configured to use or otherwise cooperate with receiver 810, transmitter 815, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, communication manager 820 may receive information from receiver 810, transmit information to transmitter 815, or be integrated in combination with receiver 810, transmitter 815, or both to acquire information, output information, or perform various other operations as described herein.

[0162] According to the examples disclosed herein, the communication manager 820 can support wireless communication. The scheduling component 825 is capable of, configured to, or operable to support components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The MMSE component 830 is capable of, configured to, or operable to support components for: generating, according to MMSE operations, a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, based on the reference signal received from the second subset of resources. The coarse network component 835 is capable of, configured to, or operable to support components for: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The refinement network component 840 is capable of, can be configured to, or is operable to support components for performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, in order to perform each of the one or more iterations, the likelihood component 845 may be configured or otherwise support components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of channel estimates for the second resource subset and observations of measurements of the second resource subset; the encoder component 850 may be configured or otherwise support components for: generating a second set of values ​​of the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and the decoder component 855 may be configured or otherwise support components for: modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0163] Additionally or alternatively, according to the examples disclosed herein, the communication manager 820 may support wireless communication. The scheduling component 825 may be configured or otherwise support components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The coarse network component 835 may be configured or otherwise support components for: generating a set of multiple channel estimates associated with corresponding layers in a set of multiple layers of channels for the resource set. The refinement network component 840 may be configured or otherwise support components for: performing a refinement operation on the set of multiple channel estimates, including one or more iterations. In some examples, for each of the one or more iterations, the likelihood component 845 may be configured or otherwise support components for generating a corresponding gradient associated with the set of multiple channel estimates based on the set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; the encoder component 850 may be configured or otherwise support components for generating a second set of values ​​of the latent variable based on a first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and the decoder component 855 may be configured or otherwise support components for modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0164] Figure 9 A block diagram 900 is shown of a communication manager 920 supporting a cyclic equivariant inference engine for channel estimation according to one or more aspects of this disclosure. The communication manager 920 may be an example of aspects of the communication manager 720, communication manager 820, or both as described herein. The communication manager 920 or its various components may be examples of parts for performing the various aspects of the cyclic equivariant inference engine for channel estimation as described herein. For example, the communication manager 920 may include a scheduling component 925, an MMSE component 930, a coarse network component 935, a fine network component 940, a likelihood component 945, an encoder component 950, a decoder component 955, or any combination thereof. These components, or each of their components or sub-components (e.g., one or more processors, one or more memories), may communicate directly or indirectly with each other (e.g., via one or more buses), and such communication may include communication within protocol layers of the protocol stack, communication associated with logical channels of the protocol stack (e.g., between protocol layers of the protocol stack, within devices, components, or virtualization components associated with network entity 105, between devices, components, or virtualization components associated with network entity 105), or any combination thereof.

[0165] According to the examples disclosed herein, the communication manager 920 can support wireless communication. The scheduling component 925 is capable of, configured to, or operable to support components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The MMSE component 930 is capable of, configured to, or operable to support components for: generating, according to MMSE operations, a first set of multiple channel estimates associated with corresponding layers in a set of multiple layers of the channel for the resource set, based on the reference signal received from the second subset of resources. The coarse network component 935 is capable of, configured to, or operable to support components for: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​associated with corresponding layers in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The refinement network component 940 is capable of, configured to, or operable to support components for performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, in order to perform each of the one or more iterations, the likelihood component 945 is capable of being configured to support components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; the encoder component 950 is capable of being configured to support components for: generating a second set of values ​​of the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and the decoder component 955 is capable of being configured to support components for: modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0166] In some examples, the refinement operation is a first refinement operation, and the set of machine learning parameters is a first set of machine learning parameters, and the refinement network component 940 is capable of, configured to, or operable to support components for: performing a second refinement operation on a second set of multiple channel estimates, the second refinement operation including one or more second iterations performed based on the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a set of multiple attention computations.

[0167] In some examples, the set of multiple attention computations includes PRB intra-group computation, PRB inter-group computation, cross-MIMO computation, MLP computation, or any combination thereof.

[0168] In some examples, MMSE component 930 is capable of, configured to, or operable to support components for performing the MMSE operation based on a resource configuration mode assigned to the second subset of resources for the reference signal, which includes DMRS.

[0169] In some examples, to support the generation of the corresponding gradient, the likelihood component 945 can be configured or operable to support components for: generating a corresponding set of residual variable values ​​based on the difference between the observations of the measurement for the second resource subset and a second set of multiple channel estimates for the second resource subset. In some examples, to support the generation of the corresponding gradient, the likelihood component 945 can be configured or operable to support components for: combining the corresponding set of residual variable values, the second resource subset, and the number of mask bits.

[0170] In some examples, in order to support the generation of a second set of values ​​for latent variables, encoder component 950 is capable of, configured to, or operable to support components for combining the second set of channel estimates for the second subset of resources, the corresponding gradient, and the corresponding values ​​in the first set of values ​​for the latent variables based on the generation of the corresponding gradient.

[0171] In some examples, in order to support the generation of a second set of values ​​for latent variables, encoder component 950 is capable of, configured to, or operable to support components for modeling the correlation between the resources of each resource block in a resource block group and the other resource blocks in that resource block group.

[0172] In some examples, in order to support the generation of a second set of values ​​for latent variables, encoder component 950 is capable of, configured to, or operable to support components for: modeling the correlation between resources of each group in a set of multiple resource groups of the resource set and other groups in the set of multiple resource groups, wherein each group in the set of multiple resource groups comprises a set of multiple resource blocks.

[0173] In some examples, in order to support the generation of a second set of values ​​for latent variables, encoder component 950 is able to be configured or operable to support components for modeling the correlation between each layer in the set of multiple layers for the resource set.

[0174] In some examples, in order to support modification of a second set of multiple channel estimates, encoder component 950 is capable of, configured to, or operable to support components for: combining the values ​​of the latent variable based on the set of machine learning parameters, the second set of multiple channel estimates, and the corresponding gradient.

[0175] In some examples, this nonlinear two-dimensional interpolation of the channel is based on a machine learning model.

[0176] In some examples, the first set of multiple channel estimates and the second set of multiple channel estimates are associated with a set of multiple single-input and single-output antenna pairs.

[0177] In some examples, each iteration in the one or more iterations is performed by a refinement network comprising a likelihood module, an encoder module, and a decoder module, which includes a machine learning model. In some examples, each refinement network performs based on the same set of machine learning parameters.

[0178] According to the examples disclosed herein, the communication manager 920 may support wireless communication. The scheduling component 925 may be configured or otherwise support components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The coarse network component 935 may be configured or otherwise support components for: generating a set of multiple channel estimates associated with corresponding layers in a set of multiple layers for the channel of the resource set. The refinement network component 940 may be configured or otherwise support components for: performing a refinement operation on the set of multiple channel estimates, including one or more iterations. In some examples, for each of the one or more iterations, the likelihood component 945 may be configured or otherwise support components for generating a corresponding gradient associated with the set of multiple channel estimates based on the set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; the encoder component 950 may be configured or otherwise support components for generating a second set of values ​​of the latent variable based on a first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and the decoder component 955 may be configured or otherwise support components for modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0179] In some examples, to support the generation of the corresponding gradient, the likelihood component 945 may be configured or otherwise support components for generating a corresponding set of residual variable values ​​based on the difference between the observations of the measurement for the second resource subset and a set of multiple channel estimates for the second resource subset. In some examples, to support the generation of the corresponding gradient, the likelihood component 945 may be configured or otherwise support components for combining the corresponding set of residual variable values, the observations of the measurement for the second resource subset, and the number of mask bits.

[0180] In some examples, to support the generation of a second set of values ​​for latent variables, encoder component 950 may be configured or otherwise support components for combining the set of multiple channel estimates for the second resource subset, the corresponding gradient, and the corresponding values ​​in the first set of values ​​for the latent variables based on the generation of the corresponding gradient.

[0181] In some examples, to support the generation of a second set of values ​​for latent variables, encoder component 950 may be configured or otherwise supported for the following: modeling the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0182] In some examples, to support the generation of a second set of values ​​for latent variables, encoder component 950 may be configured or otherwise support components for modeling the correlation between resources of each group in a set of multiple resource groups of the resource set and other groups in the set of multiple resource groups, wherein each group in the set of multiple resource groups comprises a set of multiple resource blocks.

[0183] In some examples, to support the generation of a second set of latent variable values, encoder component 950 may be configured or otherwise supported for components that model the correlation between each layer in the set of multiple layers for the resource set.

[0184] In some examples, to support modifications to a set of multiple channel estimates, the decoder component 955 may be configured or otherwise support components for combining the set of values ​​of the latent variable, the second set of multiple channel estimates, and the corresponding gradient.

[0185] In some examples, the initial values ​​of this set of multiple channel estimates are associated with a SISO antenna pair.

[0186] In some examples, the second subset of resources is configured according to resource configuration patterns in the resource configuration pattern set.

[0187] In some examples, this set of resource configuration patterns is a set of DMRS patterns.

[0188] In some examples, each iteration is performed by a refinement network, which includes a likelihood module, an encoder module, and a decoder module, and each refinement network also includes corresponding parameters associated with the machine learning operation.

[0189] In some examples, the resource set includes one or more resource groups, and each corresponding layer in the set of multiple layers is associated with a corresponding antenna pair in the set of multiple SISO antenna pairs.

[0190] Figure 10A diagram of a system 1000 including a device 1005 supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown. Device 1005 may be an example of device 705, device 805, or UE 115 as described herein, or may include components thereof. Device 1005 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof (e.g., wirelessly). Device 1005 may include components for bidirectional voice and data communication, including components for transmitting and receiving communications, such as a communication manager 1020, an input / output (I / O) controller 1010, a transceiver 1015, an antenna 1025, at least one memory 1030 (or memory circuitry), code 1035, and at least one processor 1040 (or processing circuitry). These components may communicate electronically or be otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1045).

[0191] I / O controller 1010 manages the input and output signals of device 1005. I / O controller 1010 can also manage peripheral devices not integrated into device 1005. In some cases, I / O controller 1010 may represent a physical connection or port to an external peripheral device. In some cases, I / O controller 1010 may utilize an operating system such as iOS. ® ANDROID ® MS-DOS ® MS-WINDOWS ® OS / 2 ® UNIX ® LINUX ® Or another known operating system. Additionally or alternatively, the I / O controller 1010 may represent or interact with a modem, keyboard, mouse, touchscreen, or similar device. In some cases, the I / O controller 1010 may be implemented as part of one or more processors (such as at least one processor 1040) (or processing circuitry). In some cases, a user may interact with the device 1005 via the I / O controller 1010 or via hardware components controlled by the I / O controller 1010.

[0192] In some cases, device 1005 may include a single antenna 1025. However, in other cases, device 1005 may have more than one antenna 1025, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. Transceiver 1015 may communicate bidirectionally via one or more antennas 1025, wired or wireless links, as described herein. For example, transceiver 1015 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Transceiver 1015 may also include a modem for: modulating packets; providing the modulated packets to one or more antennas 1025 for transmission; and demodulating packets received from one or more antennas 1025. Transceiver 1015, or transceiver 1015 and one or more antennas 1025, may be an example of transmitter 715, transmitter 815, receiver 710, receiver 810, or any combination thereof or components thereof as described herein.

[0193] At least one memory 1030 (or memory circuitry) may include random access memory (RAM) and read-only memory (ROM). At least one memory 1030 may store computer-readable, computer-executable code 1035, including instructions that, when executed by at least one processor 1040, cause device 1005 to perform the various functions described herein. Code 1035 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1035 may not be directly executable by at least one processor 1040, but may enable a computer (e.g., when compiled and executed) to perform the functions described herein. In some cases, among other things, at least one memory 1030 may also include a basic I / O system (BIOS) that controls basic hardware or software operations, such as interaction with peripheral components or devices.

[0194] At least one processor 1040 (or processing circuitry) may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, at least one processor 1040 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into at least one processor 1040. At least one processor 1040 may be configured to execute computer-readable instructions stored in memory (e.g., at least one memory 1030) to cause device 1005 to perform various functions (e.g., supporting various functions or tasks of a cyclic equivariant inference engine for channel estimation). For example, device 1005 or components thereof may include at least one processor 1040 (or processing circuitry) and at least one memory 1030 (or memory circuitry) coupled to or coupled to at least one processor 1040, the at least one processor 1040 and the at least one memory 1030 being configured to perform the various functions described herein. In some examples, at least one processor 1040 may include multiple processors, and at least one memory 1030 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, which may be configured individually or collectively to perform the various functions described herein. In some examples, at least one processor 1040 may be a component of a processing system, which may refer to a system of machines (such as a series of machines), circuitry (including, for example, one or both of processor circuitry (which may include at least one processor 1040) and memory circuitry (which may include at least one memory 1030)) or components that receive or receive input and process the input to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. Thus, at least one processor 1040 or a processing system including at least one processor 1040 may be configured, configurable, or operable to cause device 1005 to perform one or more of the functions described herein. Furthermore, as described herein, “configurable to,” “configurable to,” and “operable to” are used interchangeably and may be associated with the ability to perform one or more of the functions described herein when executing code stored in at least one memory 1030 or otherwise.

[0195] According to the examples disclosed herein, the communication manager 1020 can support wireless communication. For example, the communication manager 1020 is capable of, configured to, or operable to support components for: receiving an assignment of a resource set associated with a channel, the resource set including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The communication manager 1020 is capable of, configured to, or operable to support components for: generating a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, based on the reference signal received from the second subset of resources according to MMSE operations. The communication manager 1020 is capable of, configured to, or operable to support components for: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The communication manager 1020 is capable of, configured to, or operable to support components for: performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, to perform each of the one or more iterations, the communication manager 1020 may be configured to, or otherwise support components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0196] Additionally or alternatively, according to the examples disclosed herein, the communication manager 1020 may support wireless communication. For example, the communication manager 1020 may be configured or otherwise support components for: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The communication manager 1020 may be configured or otherwise support components for: generating a set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of channels for the resource set. The communication manager 1020 may be configured or otherwise support components for: performing a refinement operation on the set of multiple channel estimates, including one or more iterations. In some examples, for each of the one or more iterations, the communication manager 1020 may be configured or otherwise support components for: generating a corresponding gradient associated with the set of multiple channel estimates based on the set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generating a second set of values ​​of the latent variable based on a first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient.

[0197] By including or configuring the communication manager 1020 according to the examples described herein, the device 1005 can support techniques for improving communication reliability, reducing latency, improving and reducing user experience related to processing, reducing power consumption, utilizing communication resources more efficiently, providing more accurate channel estimation, and reducing memory and computational overhead.

[0198] In some examples, the communication manager 1020 may be configured to use or otherwise coordinate with the transceiver 1015, one or more antennas 1025, or any combination thereof to perform various operations (e.g., receiving, monitoring, transmitting). Although the communication manager 1020 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1020 may be supported or performed by at least one processor 1040, at least one memory 1030, code 1035, or any combination thereof. For example, code 1035 may include instructions that can be executed by at least one processor 1040 to cause the device 1005 to perform various aspects of the cyclic equivariant inference engine for channel estimation as described herein, or at least one processor 1040 and at least one memory 1030 may be otherwise configured to perform or support such operations individually or jointly.

[0199] Figure 11A diagram of a system 1100 including a device 1105 supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown. Device 1105 may be an example of device 705, device 805, or network entity 105 as described herein, or may include components thereof. Device 1105 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, and this communication may include communication via one or more wired interfaces, one or more wireless interfaces, or any combination thereof. Device 1105 may include components supporting output and acquisition of communication, such as a communication manager 1120, a transceiver 1110, an antenna 1115, at least one memory 1125 (or memory circuitry), code 1130, and at least one processor 1135 (or processing circuitry). These components may communicate electronically or be otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1140).

[0200] Transceiver 1110 may support bidirectional communication via a wired link, a wireless link, or both, as described herein. In some examples, transceiver 1110 may include a wired transceiver and be able to communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, transceiver 1110 may include a wireless transceiver and be able to communicate bidirectionally with another wireless transceiver. In some examples, device 1105 may include one or more antennas 1115 that may be capable of transmitting or receiving wireless transmissions (e.g., concurrently). Transceiver 1110 may also include a modem for: modulating a signal; providing the modulated signal for transmission (e.g., via one or more antennas 1115, via a wired transmitter); receiving the modulated signal (e.g., from one or more antennas 1115, from a wired receiver); and demodulating the signal. In some embodiments, transceiver 1110 may include one or more interfaces, such as one or more interfaces coupled to one or more antennas 1115 configured to support various receive or acquire operations, or one or more interfaces coupled to one or more antennas 1115 configured to support various transmit or output operations, or combinations thereof. In some embodiments, transceiver 1110 may include one or more processors or one or more memory components or configured to be coupled to such processors or memory components, which are operable to perform or support operations based on received or acquired information or signals, or to generate information or other signals for transmission or other output, or any combination thereof. In some embodiments, transceiver 1110, or transceiver 1110 and one or more antennas 1115, or transceiver 1110 and one or more antennas 1115 and one or more processors or one or more memory components (e.g., at least one processor 1135, at least one memory 1125, or both) may be included in a chip or chip assembly mounted in device 1105. In some examples, transceiver 1110 is operable to support communication via one or more communication links (e.g., communication link 125, backhaul communication link 120, midhaul communication link 162, and fronthaul communication link 168).

[0201] At least one memory 1125 may include RAM, ROM, or any combination thereof. At least one memory 1125 may store computer-readable, computer-executable code 1130 including instructions that, when executed by one or more processors of at least one processor 1135, cause device 1105 to perform the various functions described herein. Code 1130 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1130 may not be directly executable by the processor of at least one processor 1135, but may cause a computer (e.g., when compiled and executed) to perform the functions described herein. In some cases, at least one memory 1125 may also include a BIOS, among other things, that controls basic hardware or software operation, such as interaction with peripheral components or devices. In some examples, at least one processor 1135 may include multiple processors, and at least one memory 1125 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, which may be configured individually or collectively to perform the various functions described herein (e.g., as part of a processing system).

[0202] At least one processor 1135 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, ASICs, CPUs, FPGAs, microcontrollers, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, at least one processor 1135 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into one or more processors of at least one processor 1135. At least one processor 1135 may be configured to execute computer-readable instructions stored in memory (e.g., one or more memories in at least one memory 1125) to cause device 1105 to perform various functions (e.g., supporting various functions or tasks of a cyclic equivariant inference engine for channel estimation). For example, device 1105 or components of device 1105 may include at least one processor 1135 (or processing circuitry) and at least one memory 1125 (or memory circuitry) coupled to or coupled to one or more processors of at least one processor 1135, the at least one processor 1135 and the at least one memory 1125 being configured to perform the various functions described herein. At least one processor 1135 may 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 example) that can host functions for performing the functions of device 1105 (e.g., by executing code 1130). At least one processor 1135 may be any one or more suitable processors capable of executing scripts or instructions of one or more software programs stored in device 1105 (such as within one or more memories of at least one memory 1125). In some examples, at least one processor 1135 may include multiple processors, and at least one memory 1125 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, which may be configured individually or collectively to perform the various functions described herein. In some examples, at least one processor 1135 may be a component of a processing system, which may refer to a system of machines (such as a series of machines), circuits (including, for example, one or both of processor circuitry (which may include at least one processor 1135) and memory circuitry (which may include at least one memory 1125)) or components that receive or receive input and process the input to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. Therefore, at least one processor 1135 or a processing system including at least one processor 1135 may be configured, configurable, or operable to cause the device 1105 to perform one or more of the functions described herein.Furthermore, as described herein, “configurable to,” “configurable to,” and “operable to” are used interchangeably and may be associated with the ability to perform one or more of the functions described herein when executing code stored in at least one memory 1125 or otherwise.

[0203] In some examples, bus 1140 may support communication at the protocol layer of the protocol stack (e.g., within a protocol layer). In some examples, bus 1140 may support communication associated with logical channels of the protocol stack (e.g., between protocol layers of the protocol stack), which may include communication performed within components of device 1105, or communication performed between different components of device 1105 that are co-addressable or may be located in different locations (e.g., where device 1105 may refer to a system in which one or more of communication manager 1120, transceiver 1110, at least one memory 1125, code 1130 and at least one processor 1135 may be located in one component of different components or partitioned between different components).

[0204] In some examples, the communication manager 1120 can manage various aspects of communication with the core network 130 (e.g., via one or more wired or wireless backhaul links). For example, the communication manager 1120 can manage the delivery of data communications by client devices such as one or more UEs 115. In some examples, the communication manager 1120 can manage communication with other network entities 105 and may include a controller or scheduler for coordinating communication with other network entities 105 to control communication with UE 115. In some examples, the communication manager 1120 may support the X2 interface within LTE / LTE-A wireless communication network technology to provide communication between network entities 105.

[0205] According to the examples disclosed herein, the communication manager 1120 may support wireless communication. For example, the communication manager 1120 is capable of, configured to, or operable to support components for: receiving an assignment of a resource set associated with a channel, the resource set including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The communication manager 1120 is capable of, configured to, or operable to support components for: generating a first set of multiple channel estimates associated with a corresponding layer in a set of multiple layers of the channel for the resource set, based on the reference signal received from the second subset of resources according to MMSE operations. The communication manager 1120 is capable of, configured to, or operable to support components for: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with a corresponding layer in the set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The communication manager 1120 is capable of, configured to, or operable to support components for: performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, to perform each of the one or more iterations, the communication manager 1120 may be configured to, or otherwise support components for: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​for the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient.

[0206] By including or configuring the communication manager 1120 according to the examples described herein, the device 1105 can support techniques for improving communication reliability, reducing latency, improving and reducing user experience associated with processing, reducing power consumption, utilizing communication resources more efficiently, providing more accurate channel estimation, and reducing memory and computational overhead.

[0207] In some examples, the communication manager 1120 may be configured to use or otherwise coordinate with the transceiver 1110, one or more antennas 1115 (e.g., where applicable), or any combination thereof to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). Although the communication manager 1120 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1120 may be supported or performed by the transceiver 1110, one or more processors in at least one processor 1135, one or more memories in at least one memory 1125, code 1130, or any combination thereof (e.g., by a processing system including at least a portion of at least one processor 1135, at least one memory 1125, code 1130, or any combination thereof). For example, code 1130 may include instructions that can be executed by one or more processors in at least one processor 1135 to cause the device 1105 to perform various aspects of the cyclic equivariant inference engine for channel estimation as described herein, or at least one processor 1135 and at least one memory 1125 may be otherwise configured to perform or support such operations individually or jointly.

[0208] Figure 12 A flowchart illustrating a method 1200 for supporting a cyclic equivariant inference engine for channel estimation according to various aspects of this disclosure is shown. Operation of method 1200 may be implemented by a UE or network entity or its components as described herein. For example, operation of method 1200 may be implemented by, as referenced... Figures 1 to 11 The UE 115 or network entity performs the described function. In some examples, the UE or network entity may execute a set of instructions to control the functional elements of the UE or network entity to perform the described function. Additionally or alternatively, the UE or network entity may use dedicated hardware to perform aspects of the described function.

[0209] At 1205, the method may include: receiving an assignment to a set of resources associated with the channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The operation of block 1205 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1205 may be provided by reference to... Figure 9 The scheduling component 925 is used to execute this.

[0210] At 1210, the method may include: generating, from the reference signal received on the second subset of resources, a first set of multiple channel estimates associated with corresponding layers in a set of multiple layers for the channel of the resource set, according to MMSE operations. The operation of block 1210 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1210 may be derived from, as referenced... Figure 9The MMSE component 930 is used to perform this.

[0211] At 1215, the method may include: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, wherein the second set of multiple channel estimates and the set of multiple values ​​are associated with a corresponding layer in a set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The operation of block 1215 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1215 may be derived from references... Figure 9 The coarse network component 935 is used to perform this.

[0212] At 1220, the method may include: performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, each of the one or more iterations may include: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generating a second set of values ​​of the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient. The operation of block 1220 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1220 may be provided by reference to [reference needed]. Figure 9 The refined network component 940 is used to perform this.

[0213] Figure 13 A flowchart illustrating a method 1300 for supporting a cyclic equivariant inference engine for channel estimation according to various aspects of this disclosure is shown. Operation of method 1300 may be implemented by a UE or network entity or its components as described herein. For example, operation of method 1300 may be implemented by, as referenced... Figures 1 to 11 The UE 115 or network entity performs the described function. In some examples, the UE or network entity may execute a set of instructions to control the functional elements of the UE or network entity to perform the described function. Additionally or alternatively, the UE or network entity may use dedicated hardware to perform aspects of the described function.

[0214] At 1305, the method may include: receiving an assignment to a set of resources associated with the channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. The operation of block 1305 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1305 may be determined by reference to... Figure 9 The scheduling component 925 is used to execute this.

[0215] At 1310, the method may include: generating a first set of multiple channel estimates associated with corresponding layers in a set of multiple layers for the channel of the second resource subset from the reference signal received on the second resource subset according to MMSE operations. The operation of block 1310 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1310 may be derived from, as referenced... Figure 9 The MMSE component 930 is used to perform this.

[0216] At 1315, the method may include: generating a second set of multiple channel estimates and a set of multiple values ​​of latent variables based on a nonlinear two-dimensional interpolation of the channel for the resource set, the second set of multiple channel estimates and the set of multiple values ​​being associated with a corresponding layer in a set of multiple layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is based on the first set of multiple channel estimates. The operation of block 1315 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1315 may be derived from references... Figure 9 The coarse network component 935 is used to perform this.

[0217] At 1320, the method may include: performing a refinement operation on the second set of multiple channel estimates comprising one or more iterations, wherein each of the one or more iterations is performed based on the same set of machine learning parameters. In some examples, each of the one or more iterations may include: generating a corresponding gradient associated with the second set of multiple channel estimates based on the second set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generating a second set of values ​​of the latent variable based on a first set of values ​​in the set of multiple values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient; and modifying the second set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the second set of multiple channel estimates, the set of machine learning parameters, and the corresponding gradient. The operation of block 1320 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1320 may be provided by reference to [reference needed]. Figure 9 The refined network component 940 is used to perform this.

[0218] At 1325, the method may include: performing a second refinement operation on the second set of multiple channel estimates, the second refinement operation including one or more second iterations performed based on the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a set of multiple attention computations. The operation at box 1325 may be performed according to examples as disclosed herein. In some examples, aspects of the operation at 1325 may be derived from references... Figure 9 The refined network component 940 is used to perform this.

[0219] Figure 14 A flowchart illustrating a method 1400 for supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown. Operation of method 1400 may be implemented by a UE or its components as described herein. For example, operation of method 1400 may be performed by, as described in reference... Figures 1 to 13 The UE 115 is used to execute this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0220] At 1405, the method may include: receiving an assignment to a set of resources associated with the channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. Receiving the assignment may include identifying the time-frequency resources on which the assignment is transmitted, demodulating the transmissions on those time-frequency resources, and decoding the demodulated transmissions to obtain bits indicating the assignment. The assignment may be received via a DCI in a downlink control channel. The operation of 1405 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1405 may be determined by reference to [reference needed]. Figure 9 The scheduling component 925 is used to execute this.

[0221] At 1410, the method may include: generating a set of multiple channel estimates associated with a corresponding layer in a set of multiple layers for channels of the resource set. Generating the set of multiple channel estimates may include performing as referenced herein. Figure 3 The various interpolation techniques described herein are used to calculate daily line-to-per-PRG estimates (e.g., SISO channel estimates). The operation of 1410 can be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1410 can be derived from references... Figure 9 The coarse network component 935 is used to perform this.

[0222] At 1415, the method may include performing a refinement operation on the set of multiple channel estimates, including one or more iterations. Performing the refinement operation may include via [reference here]. Figures 4 to 6The refinement network computation (e.g., updating, generating) of various channel estimates (e.g., MIMO channel estimates) and refinement of the estimates over various iterations of the machine learning operation. In some examples, each of the one or more iterations may include: generating a corresponding gradient associated with the set of multiple channel estimates based on the set of multiple channel estimates for the second resource subset and observations of measurements of the second resource subset; generating a second set of values ​​of the latent variable based on a first set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient; and modifying the set of multiple channel estimates associated with the set of multiple layers based on the second set of values ​​of the latent variable, the set of multiple channel estimates, and the corresponding gradient. The operation of 1415 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1415 may be derived from references to Figure 9 The refined network component 940 is used to perform this.

[0223] Figure 15 A flowchart illustrating a method 1500 for supporting a cyclic equivariant inference engine for channel estimation, according to one or more aspects of this disclosure, is shown. Operation of method 1500 may be implemented by a UE or its components as described herein. For example, operation of method 1500 may be performed by, as described in reference... Figures 1 to 14 The UE 115 described herein is used to perform this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0224] At 1505, the method may include: receiving an assignment to a set of resources associated with the channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals. Receiving the assignment may include identifying the time-frequency resources on which the assignment is transmitted, demodulating the transmissions on those time-frequency resources, and decoding the demodulated transmissions to obtain bits indicating the assignment. The assignment may be received via a DCI in a downlink control channel. The operation of 1505 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1505 may be determined by reference to [reference / ... Figure 9 The scheduling component 925 is used to execute this.

[0225] At 1510, the method may include: generating a set of multiple channel estimates associated with a corresponding layer in a set of multiple layers for channels of the resource set. Generating the set of multiple channel estimates may include performing as referenced herein. Figure 3 The various interpolation techniques described herein are used to calculate daily line-to-per-PRG estimates (e.g., SISO channel estimates). The operation of the 1510 can be performed according to examples as disclosed herein. In some examples, aspects of the operation of the 1510 can be derived from references...Figure 9 The coarse network component 935 is used to perform this.

[0226] At 1515, the method may include performing a refinement operation on the set of multiple channel estimates comprising one or more iterations. Performing the refinement operation may include via means as referenced herein. Figures 3 to 5 The refinement network computation (e.g., updating, generating) of various channel estimates (e.g., MIMO channel estimates) and refinement of the estimates over various iterations of the machine learning operation. In some examples, each of the one or more iterations may include: generating a corresponding gradient associated with the set of multiple channel estimates based on observations of measurements of the second resource subset and a set of multiple channel estimates for the second resource subset; generating a second set of latent variable values ​​(e.g., based at least in part on a first set of latent variable values, the multiple channel estimates, the corresponding gradients, and modeling correlations between resources in each of the multiple resource groups of the resource set and other groups in the multiple resource groups). The set of multiple resource groups includes multiple resource blocks; and the set of multiple channel estimates associated with the set of multiple layers is modified based on the second set of the latent variable values, the set of multiple channel estimates, and the corresponding gradient. The operation of 1515 can be performed according to examples disclosed herein. In some examples, aspects of the operation of 1515 can be performed by a likelihood module (e.g., module 425), an encoder module (e.g., module 430), or a decoder module (e.g., module 435). In some examples, aspects of the operation of 1515 can be performed by, as referenced... Figure 9 The refined network component 940 is used to perform this.

[0227] The following provides an overview of the various aspects of this disclosure: Aspect 1: An apparatus for performing wireless communication at a wireless communication device, the apparatus comprising: one or more memories; and one or more processors coupled to the one or more memories, the one or more memories being configured to execute code causing the wireless communication device to: receive an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generate, according to MMSE operations, a first plurality of channel estimates associated with corresponding layers of a plurality of layers of the channel for the resource set from the reference signals received on the second subset of resources; and generate, according to a nonlinear two-dimensional interpolation of the channel for the resource set, a second plurality of channel estimates and a plurality of values ​​of latent variables, the second plurality of channel estimates and the plurality of values ​​being associated with corresponding layers of the plurality of layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is at least The process involves, in part, the first plurality of channel estimates; and performing a refinement operation comprising one or more iterations on the second plurality of channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters, and wherein, in order to perform each of the one or more iterations, the one or more processors are configured to cause the wireless communication device to: generate a corresponding gradient associated with the second plurality of channel estimates based at least in part on the second plurality of channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generate a second set of values ​​of the latent variables based at least in part on a first set of values ​​of the plurality of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients; and modify the second plurality of channel estimates associated with the plurality of layers based at least in part on the second set of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients.

[0228] Aspect 2: The apparatus according to aspect 14, wherein the refinement operation is a first refinement operation, and the set of machine learning parameters is a first set of machine learning parameters, and wherein the one or more processors are configured to cause the wireless communication device to: perform a second refinement operation on the second plurality of channel estimates, the second refinement operation comprising one or more second iterations performed according to the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention calculations in a plurality of attention calculations.

[0229] Aspect 3: The apparatus according to aspect 15, wherein the plurality of attention calculations includes intra-PRB calculation, inter-PRB calculation, cross-MIMO calculation, MLP calculation, or any combination thereof.

[0230] Aspect 4: An apparatus according to any one of Aspects 14 to 16, wherein the one or more processors are configured to cause the wireless communication device to perform the MMSE operation based on a resource configuration mode allocated for the second subset of resources of the reference signal, the reference signal including DMRS.

[0231] Aspect 5: An apparatus according to any one of Aspects 14 to 17, wherein, in order to generate the corresponding gradient, the one or more processors are configured to cause the wireless communication device to: generate a corresponding set of values ​​of residual variables based at least in part on the difference between observations of the measurements of the second resource subset and the second plurality of channel estimates for the second resource subset; and combine the corresponding set of values ​​of the residual variables, the second resource subset, and the number of mask bits.

[0232] Aspect 6: The apparatus according to any one of Aspects 14 to 18, wherein, in order to generate the second set of values ​​of the latent variables, the one or more processors are configured to cause the wireless communication device to: combine, at least in part, the second plurality of channel estimates for the second subset of resources, the corresponding gradients, and corresponding values ​​in the first set of values ​​of the latent variables based on the generation of the corresponding gradients.

[0233] Aspect 7: The apparatus according to any one of Aspects 14 to 19, wherein, in order to generate the second set of values ​​of the latent variables, the one or more processors are configured to cause the wireless communication device to: model the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0234] Aspect 8: The apparatus according to any one of Aspects 14 to 19, wherein, in order to generate the second set of values ​​of the latent variable, the one or more processors are configured to cause the wireless communication device to: model the correlation between resources of each of a plurality of resource groups of the resource set and other groups of the plurality of resource groups, wherein each of the plurality of resource groups comprises a plurality of resource blocks.

[0235] Aspect 9: The apparatus according to any one of Aspects 14 to 19, wherein, in order to generate the second set of values ​​of the latent variables, the one or more processors are configured to cause the wireless communication device to: model the correlation between each of the plurality of layers of the resource set.

[0236] Aspect 10: The apparatus according to any one of Aspects 14 to 22, wherein, in order to modify the second plurality of channel estimates, the one or more processors are configured to cause the wireless communication device to: combine the second set of values ​​of the latent variables, the second plurality of channel estimates, and the corresponding gradients, at least in part, based on the set of machine learning parameters.

[0237] Aspect 11: The apparatus according to any one of aspects 14 to 23, wherein the nonlinear two-dimensional interpolation of the channel is based at least in part on a machine learning model.

[0238] Aspect 12: The apparatus according to any one of aspects 14 to 24, wherein the first plurality of channel estimates and the second plurality of channel estimates are associated with a plurality of SISO antenna pairs.

[0239] Aspect 13: The apparatus according to any one of Aspects 14 to 25, wherein each of the one or more iterations is performed by a refinement network comprising a likelihood module, an encoder module and a decoder module, the refinement network comprising a machine learning model; and each refinement network is performed according to the same set of machine learning parameters.

[0240] Aspect 14: A method for performing wireless communication at a wireless communication device, the method comprising: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generating, according to an MMSE operation, a first plurality of channel estimates associated with corresponding layers of a plurality of layers of the channel for the resource set from the reference signals received on the second subset of resources; generating, according to a nonlinear two-dimensional interpolation of the channel for the resource set, a second plurality of channel estimates and a plurality of values ​​of latent variables associated with corresponding layers of the plurality of layers of the channel for the resource set, wherein the nonlinear two-dimensional interpolation of the channel is at least partially based on the first plurality of channel estimates; and generating, according to the second plurality of... The channel estimation execution includes one or more iterations of refinement operations, each of which is performed based on the same set of machine learning parameters, and each of which includes: generating a corresponding gradient associated with the second plurality of channel estimates based at least in part on the second plurality of channel estimates for the second subset of resources and observations of measurements on the second subset of resources; generating a second set of values ​​of the latent variables based at least in part on a first set of values ​​of the plurality of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients; and modifying the second plurality of channel estimates associated with the plurality of layers based at least in part on the second set of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients.

[0241] Aspect 15: The method according to aspect 14, wherein the refinement operation is a first refinement operation and the set of machine learning parameters is a first set of machine learning parameters, the method further comprising: performing a second refinement operation on the second plurality of channel estimates, the second refinement operation including one or more second iterations performed according to the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a plurality of attention computations.

[0242] Aspect 16: According to the method of aspect 15, the plurality of attention computations include intra-PRB computation, inter-PRB computation, cross-MIMO computation, MLP computation, or any combination thereof.

[0243] Aspect 17: The method according to any one of Aspects 14 to 16, the method further comprising: performing the MMSE operation based on a resource configuration mode allocated for the second subset of resources of the reference signal, the reference signal including DMRS.

[0244] Aspect 18: The method according to any one of Aspects 14 to 17, wherein generating the corresponding gradient comprises: generating a corresponding set of values ​​of residual variables based at least in part on the difference between observations of the measurements of the second resource subset and the second plurality of channel estimates for the second resource subset; and combining the corresponding set of values ​​of the residual variables, the second resource subset, and the number of mask bits.

[0245] Aspect 19: The method according to any one of Aspects 14 to 18, wherein generating the second set of values ​​of the latent variables comprises: combining, at least in part, the second plurality of channel estimates for the second subset of resources, the corresponding gradients, and corresponding values ​​of the first set of values ​​of the latent variables based on generating the corresponding gradients.

[0246] Aspect 20: The method according to any one of Aspects 14 to 19, wherein the second set of values ​​for generating the latent variables comprises: modeling the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0247] Aspect 21: The method according to any one of Aspects 14 to 19, wherein the second set of generating the values ​​of the latent variables comprises: modeling the correlation between resources of each of a plurality of resource groups in the resource set and other groups in the plurality of resource groups, wherein each of the plurality of resource groups comprises a plurality of resource blocks.

[0248] Aspect 22: The method according to any one of aspects 14 to 19, wherein generating the second set of values ​​of the latent variables comprises: modeling the correlation between each of the plurality of layers of the resource set.

[0249] Aspect 23: The method according to any one of Aspects 14 to 22, wherein modifying the second plurality of channel estimates comprises: combining the second set of values ​​of the latent variables, the second plurality of channel estimates, and the corresponding gradients, at least in part based on the set of machine learning parameters.

[0250] Aspect 24: The method according to any one of aspects 14 to 23, wherein the nonlinear two-dimensional interpolation of the channel is based at least in part on a machine learning model.

[0251] Aspect 25: The method according to any one of Aspects 14 to 24, wherein the first plurality of channel estimates and the second plurality of channel estimates are associated with a plurality of SISO antenna pairs.

[0252] Aspect 26: The method according to any one of Aspects 14 to 25, wherein each of the one or more iterations is performed by a refinement network comprising a likelihood module, an encoder module and a decoder module, the refinement network comprising a machine learning model; and each refinement network is performed according to the same set of machine learning parameters.

[0253] Aspect 27: An apparatus for performing wireless communication at a wireless communication device, the apparatus comprising at least one component for performing the method according to any one of aspects 14 to 26.

[0254] Aspect 28: A non-transitory computer-readable medium storing code for wireless communication at a wireless communication device, said code including instructions executable by one or more processors to cause the wireless communication device to perform a method according to any one of aspects 14 to 26.

[0255] Aspect 29: A method for wireless communication, the method comprising: receiving an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; generating a plurality of channel estimates associated with corresponding layers of a plurality of layers of the channel for the set of resources; and performing a refinement operation comprising one or more iterations on the plurality of channel estimates, wherein each of the one or more iterations comprises: generating a corresponding gradient associated with the plurality of channel estimates based at least in part on the plurality of channel estimates for the second subset of resources and observations of measurements of the second subset of resources; generating a second set of values ​​of the latent variables based at least in part on a first set of values ​​of latent variables, the plurality of channel estimates and the corresponding gradients; and modifying the plurality of channel estimates associated with the plurality of layers based at least in part on the second set of values ​​of the latent variables, the plurality of channel estimates and the corresponding gradients.

[0256] Aspect 30: The method according to aspect 14, wherein generating the corresponding gradient comprises: generating a corresponding set of values ​​of residual variables based at least in part on the difference between observations of the measurements of the second resource subset and the plurality of channel estimates for the second resource subset; and combining the corresponding set of values ​​of the residual variables, observations of the measurements of the second resource subset, and the number of mask bits.

[0257] Aspect 31: The method according to any one of aspects 14 to 15, wherein generating the second set of values ​​of the latent variables comprises: combining, at least in part, the plurality of channel estimates for the second resource subset, the corresponding gradients, and corresponding values ​​of the latent variables in the first set based on generating the corresponding gradients.

[0258] Aspect 32: The method according to any one of Aspects 14 to 16, wherein generating the second set of values ​​of the latent variables comprises: modeling the correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group.

[0259] Aspect 33: The method according to any one of Aspects 14 to 17, wherein the second set of generating the values ​​of the latent variables comprises: modeling the correlation between resources of each of a plurality of resource groups in the resource set and other groups in the plurality of resource groups, wherein each of the plurality of resource groups comprises a plurality of resource blocks.

[0260] Aspect 34: The method according to any one of aspects 14 to 18, wherein generating the second set of values ​​of the latent variables comprises: modeling the correlation between each of the plurality of layers of the resource set.

[0261] Aspect 35: The method according to any one of Aspects 14 to 19, wherein modifying the plurality of channel estimates comprises: combining the second set of values ​​of the latent variables, the plurality of channel estimates, and the corresponding gradients.

[0262] Aspect 36: The method according to any one of Aspects 14 to 20, wherein the initial values ​​of the plurality of channel estimates are associated with a SISO antenna pair.

[0263] Aspect 37: The method according to any one of Aspects 14 to 21, wherein the second resource subset is configured according to a resource configuration pattern in a set of resource configuration patterns.

[0264] Aspect 38: According to the method of aspect 22, the set of resource configuration modes is a set of demodulation reference signal modes.

[0265] Aspect 39: The method according to any one of Aspects 14 to 23, wherein each iteration is performed by a refinement network, the refinement network comprising a likelihood module, an encoder module and a decoder module, and each refinement network further comprising corresponding parameters associated with a machine learning operation.

[0266] Aspect 40: The method according to any one of Aspects 14 to 24, wherein the resource set comprises one or more resource groups, and each corresponding layer of the plurality of layers is associated with a corresponding antenna pair of the plurality of SISO antenna pairs.

[0267] Aspect 41: An apparatus for wireless communication, the apparatus comprising: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories and capable of operating individually or jointly to execute the code, so that the apparatus performs a method according to any one of aspects 14 to 25.

[0268] Aspect 42: An apparatus for wireless communication, the apparatus comprising at least one component for performing the method according to any one of aspects 14 to 25.

[0269] Aspect 43: A non-transitory computer-readable medium storing code for wireless communication, the code including instructions executable by a processor to perform a method according to any one of aspects 14 to 25.

[0270] It should be noted that the methods described herein describe possible specific implementations, and the operations and steps can be rearranged or otherwise modified, and other specific implementations are also possible. Furthermore, aspects from two or more methods can be combined.

[0271] While aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for illustrative purposes, and the terms LTE, LTE-A, LTE-A Pro, or NR may be used in most of the description, the techniques described herein are also applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described can be applied to a variety of other wireless communication systems, such as Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0272] The information and signals described herein can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout this specification can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0273] The various exemplary blocks and components described herein can be implemented or performed using at least one general-purpose processor (or processing circuitry), DSP, ASIC, CPU, 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. The general-purpose processor may be a microprocessor, but in alternative embodiments, 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, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration). Any function or operation described herein that can be performed by a processor may be performed by multiple processors capable of performing the described function or operation individually or jointly.

[0274] The functions described herein can be implemented using hardware, software executed by a processor, processing circuitry, firmware, or any combination thereof. If implemented using software executed by a processor, these functions can be stored as one or more instructions or code on a computer-readable medium, or transmitted using one or more instructions or code on a computer-readable medium. Other examples and specific implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein can be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination of these. Features implementing the functions can also be physically located in different locations, including portions distributed such that the functions are implemented in different physical locations.

[0275] Computer-readable media include both non-transitory computer storage media and communication media, with the latter including any medium that facilitates the transfer of a computer program from one location to another. Non-transitory storage media can be any available medium accessible by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compressed optical disc (CD) ROM or other optical disc storage devices, magnetic disk storage devices or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code components in the form of instructions or data structures, and that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Furthermore, any connection is appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included within the definition of computer-readable media. As used herein, disks and optical discs include CDs, laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs. Disks can magnetically reproduce data, and optical discs can optically reproduce data using lasers. Combinations of the above are also included within the scope of computer-readable media. Any function or operation described herein that can be performed by memory can be performed by memory circuitry and / or multiple memories capable of performing said function or operation individually or jointly.

[0276] As used herein (including in the claims), the word "or" in an enumeration of items (e.g., an enumeration of items accompanied by phrases such as "at least one of" or "one or more of") indicates an inclusive enumeration, such that an enumeration of at least one of, for example, 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). Additionally, as used herein, the phrase "based on" should not be construed as a reference to a closed set of conditions. For example, an example step described as "based on condition A" could be based on both condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "at least partially based on".

[0277] As used herein, including in claims, the article “a” preceding a noun is open-ended and is understood to refer to “at least one” or “one or more” of those nouns. Therefore, the terms “a”, “at least one,” “one or more,” and “at least one of one or more” are interchangeable. For example, where a claim enumerates “components” performing one or more functions, each of the individual functions may be performed by a single component or by any combination of multiple components. Therefore, the term “component” having a characteristic or performing a function may refer to “at least one of one or more components” having a particular characteristic or performing a particular function. Subsequent references to a component introduced with the article “a” using the terms “the” or “said” may refer to any or all of the one or more components. For example, a component introduced with the article “a” may be understood to mean “one or more components,” and subsequent reference to “the component” in a claim may be understood to be equivalent to referring to “at least one of the one or more components.” Similarly, subsequent references to a component introduced by the terms "the" or "said" as "one or more components" can refer to any or all of the components mentioned in the one or more claims. For example, a subsequent reference to "the one or more components" in a claim can be understood as equivalent to a reference to "at least one of the one or more components." As used herein, including in the claims, the terms "set" or "subset" can be understood as referring to one or more items. For example, a reference to "a set of objects" or "a subset of objects" can be understood as equivalent to referring to one or more objects.

[0278] The term "determine" encompasses a variety of actions, and therefore, "determine" can include calculation, computation, processing, derivation, investigation, lookup (such as by searching in a table, database, or other data structure), identification, and similar actions. Furthermore, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data stored in memory), etc. Additionally, "determine" can include parsing, acquiring, selecting, choosing, creating, and other similar actions.

[0279] In the accompanying drawings, similar components or features may have the same reference numerals. Furthermore, various components of the same type can be distinguished by adding a dash after the reference numerals and a second numeral for differentiation between similar components. If only the first reference numeral is used in the description, the description can be applied to any of the similar components having the same first reference numeral, regardless of the second or other subsequent reference numerals.

[0280] This document describes example configurations in conjunction with the accompanying drawings and does not represent all implementable or within the scope of the claims. The term "example" as used herein means "used as an example, instance, or illustration," not "preferred" or "advantageous over other examples." Detailed descriptions include specific details to provide an understanding of the described techniques. However, these techniques can be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concept of the described examples.

[0281] The description herein is provided to enable those skilled in the art to implement or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of this disclosure. Therefore, this 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. An apparatus for performing wireless communication at a wireless communication device, the apparatus comprising: One or more memory units; and One or more processors, said one or more processors coupled to said one or more memories and configured to enable the wireless communication device to: Receive an assignment to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; Based on the least mean square estimation operation, a first plurality of channel estimates are generated from the reference signals received on the second subset of resources and associated with corresponding layers among the plurality of layers of the channels for the resource set. A second plurality of channel estimates and a plurality of latent variable values ​​are generated based on the nonlinear two-dimensional interpolation of the channels for the resource set, the second plurality of channel estimates and the plurality of values ​​being associated with a corresponding layer among the plurality of layers of the channels for the resource set, wherein the nonlinear two-dimensional interpolation of the channels is at least partially based on the first plurality of channel estimates; as well as A refinement operation comprising one or more iterations is performed on the second plurality of channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters, and wherein, in order to perform each of the one or more iterations, the one or more processors are configured to cause the wireless communication device to: The corresponding gradient associated with the second plurality of channel estimates is generated at least in part based on the second plurality of channel estimates for the second resource subset and observations of measurements of the second resource subset; A second set of values ​​for the latent variables is generated, at least in part, based on a first set of values ​​from the plurality of values ​​of the latent variables, a second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients; and The second plurality of channel estimates associated with the plurality of layers are modified at least in part based on the second set of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients.

2. The apparatus of claim 1, wherein the refinement operation is a first refinement operation, and the machine learning parameter set is a first set of machine learning parameters, and the one or more processors are configured to cause the wireless communication device to: A second refinement operation is performed on the second plurality of channel estimates, the second refinement operation comprising one or more second iterations performed based on the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a plurality of attention computations.

3. The apparatus of claim 2, wherein the plurality of attention computations includes intra-physical resource block computation, inter-physical resource block computation, cross-multiple-input multiple-output computation, multilayer perceptron computation, or any combination thereof.

4. A wireless communication device for wireless communication, the wireless communication device comprising: Components for receiving assignments to a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; A component for generating a first plurality of channel estimates associated with a corresponding layer among a plurality of layers of the channels for the resource set, based on the reference signal received on the second subset of resources according to a least mean square estimation operation; Components for generating a second plurality of channel estimates and a plurality of values ​​of latent variables based on nonlinear two-dimensional interpolation of the channels for the resource set, the second plurality of channel estimates and the plurality of values ​​being associated with a corresponding layer among a plurality of layers of the channels for the resource set, wherein the nonlinear two-dimensional interpolation of the channels is at least partially based on the first plurality of channel estimates; as well as A component for performing a refinement operation comprising one or more iterations on the second plurality of channel estimates, wherein each of the one or more iterations is performed based on the same set of machine learning parameters, and wherein the component for performing each of the one or more iterations comprises: A component for generating a corresponding gradient associated with the second plurality of channel estimates based at least in part on the second plurality of channel estimates for the second subset of resources and observations of measurements of the second subset of resources; Components for generating a second set of values ​​for the latent variables based at least in part on a first set of values ​​of the plurality of values ​​of the latent variables, a second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients; and A component for modifying the second plurality of channel estimates associated with the plurality of layers, at least in part based on the second set of values ​​of the latent variables, the second plurality of channel estimates, the set of machine learning parameters, and the corresponding gradients.

5. The wireless communication device according to claim 4, wherein the refinement operation is a first refinement operation, and the machine learning parameter set is a first set of machine learning parameters, the wireless communication device further comprising: Components for performing a second refinement operation on the second plurality of channel estimates, the second refinement operation including one or more second iterations performed based on the same second set of machine learning parameters, wherein the first refinement operation and the second refinement operation are associated with corresponding attention computations in a plurality of attention computations.

6. An apparatus for performing wireless communication at a wireless communication device, the apparatus comprising: processor; Memory coupled to the processor; as well as Instructions stored in the memory, executable by the processor, cause the device to: Receive the assignment of a set of resources associated with the channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; Generate multiple channel estimates associated with corresponding layers among multiple layers of the channels for the resource set; as well as The device performs a refinement operation comprising one or more iterations on the plurality of channel estimates, wherein the instructions for each of the one or more iterations are executable by the processor to cause the device to: The corresponding gradients associated with the multiple channel estimates are generated at least in part based on the multiple channel estimates for the second resource subset and the measured observations of the second resource subset; A second set of latent variable values ​​is generated, at least in part, based on a first set of latent variable values, the plurality of channel estimates, and the corresponding gradients; and The multiple channel estimates associated with the multiple layers are modified, at least in part, based on the second set of values ​​of the latent variables, the multiple channel estimates, and the corresponding gradients.

7. The apparatus according to claim 6, wherein, The instructions for generating the corresponding gradient are executable by the processor to enable the device to: The corresponding set of values ​​for the residual variables is generated at least in part based on the difference between the measured observations of the second resource subset and the plurality of channel estimates for the second resource subset; as well as The corresponding set of values ​​of the residual variable, the measured observations of the second resource subset, and a certain number of mask bits are combined.

8. The apparatus according to claim 6, wherein, The instructions for generating the second set of values ​​of the latent variables are executable by the processor to enable the device to: The correlation between the resources of each resource block in the resource block group and the other resource blocks in the resource block group is modeled.

9. An apparatus for conducting wireless communication, the apparatus comprising: A unit for receiving an assignment of a set of resources associated with a channel, the set of resources including a first subset of resources allocated for data signals and a second subset of resources allocated for reference signals; A unit for generating multiple channel estimates associated with a corresponding layer among multiple layers of the channels for the resource set; as well as A unit for performing a refinement operation including one or more iterations on the plurality of channel estimates, wherein the unit for each of the one or more iterations comprises: A unit for generating a corresponding gradient associated with the plurality of channel estimates based at least in part on the plurality of channel estimates for the second resource subset and the measured observations of the second resource subset; A unit for generating a second set of latent variable values ​​based at least in part on a first set of latent variable values, the plurality of channel estimates, and the corresponding gradients; and A unit for modifying the plurality of channel estimates associated with the plurality of layers based at least in part on the second set of values ​​of the latent variables, the plurality of channel estimates, and the corresponding gradients.

10. The apparatus according to claim 6, wherein, The unit for generating the values ​​of the latent variables in the second set includes: A unit for modeling the correlation between resources in each of a plurality of resource groups in the resource set and other groups in the plurality of resource block groups, wherein each of the plurality of resource groups includes a plurality of resource blocks.

Images