Techniques for beam characteristic prediction using joint learning process

Abstract

Methods, systems, and devices for wireless communication are described. A first network node, such as a user equipment (UE), may receive a first model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources (CMRs). The first network node may generate first measurement information corresponding to a first number of CMRs in the set of CMRs, and may input the first measurement information into the first model. The first network node may obtain information corresponding to a first prediction of a second number of CMRs in the set of CMRs as an output of the first model, receive signals using the second number of CMRs, and generate second measurement information corresponding to the second number of CMRs. The first network node may train the first model using the second measurement information and send the trained first model to a second network node.

Description

Background Art

[0001] The following relates to wireless communications, including techniques for beam characteristic prediction using a federated learning process.

[0002] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, broadcast, etc. These systems may be able to support communication with multiple users by sharing available system resources (e.g., time, frequency, and power). Examples of such multiple access systems include fourth generation (4G) systems (such as long term evolution (LTE) systems, advanced LTE (LTE-A) systems, or LTE-A Pro systems) and fifth generation (5G) systems (which may be referred to as new radio (NR) systems). These systems may employ techniques such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations, each of which supports wireless communication of communication devices, which may be referred to as user equipment (UE). Summary of the invention

[0003] The described techniques relate to improved methods, systems, devices, and apparatuses that support techniques for beam characteristic prediction using a federated learning process. For example, the described techniques provide for implementing a federated learning model between a network and other network nodes (e.g., user equipment (UE)) to facilitate prediction of temporal and spatial characteristics of future beams or future communications. Specifically, various aspects of the present disclosure support techniques that enable a first network node (e.g., a base station, a network entity) to configure a plurality of network nodes (e.g., a UE) with a federated learning model associated with a corresponding set of channel measurement resources (CMRs). In such cases, the first network node may aggregate trained federated learning models from the corresponding network nodes, and distribute the aggregated (e.g., composite) federated learning models across the corresponding network nodes (e.g., UEs) such that the first network node and the corresponding network nodes are configured to use the same model to predict / estimate beam characteristics.

[0004] A method for wireless communication at a first network node is described. The method may include: receiving a first model configured to predict at least one of a time domain characteristic or a space domain characteristic associated with a CMR set; generating first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; inputting the first measurement information into the first model; obtaining first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted space domain parameters; and receiving a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0005] A first network node for wireless communication is described. The first network node may include a memory and at least one processor coupled to the memory. The at least one processor may be configured to: receive a first model, the first model being configured to predict at least one of a time domain characteristic or a space domain characteristic associated with a CMR set; generate first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; input the first measurement information into the first model; obtain first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted space domain parameters; and receive a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0006] An apparatus for wireless communication at a first network node is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to: receive a first model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a CMR set; generate first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; input the first measurement information into the first model; obtain first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters; and receive a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0007] Another apparatus for wireless communication at a first network node is described. The apparatus may include: a component for receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a CMR set; a component for generating first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; a component for inputting the first measurement information into the first model; a component for obtaining first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters; and a component for receiving a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0008] A non-transitory computer-readable medium storing a code for wireless communication at a first network node is described. The code may include instructions executable by a processor to perform the following operations: receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a CMR set; generating first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; inputting the first measurement information into the first model; obtaining first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters; and receiving a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0009] Some examples of the methods, devices, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: generating second measurement information corresponding to the second number of CMRs; training the first model using the second measurement information, wherein training the first model using the second measurement information includes inputting the second measurement information into the first model; and sending the trained first model to a second network node.

[0010] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: receiving from the second network node a second model based on the trained first model and a third model associated with the CMR set, wherein the second model may be configured to predict at least one of the time domain characteristics or the spatial domain characteristics of the CMR set; and obtaining second predicted information corresponding to the CMR set as an output of the second model, wherein the second predicted information includes at least one of the following: one or more time domain parameters or one or more spatial domain parameters.

[0011] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for training the first model using a set of identifiers associated with the second number of CMRs, wherein the set of identifiers corresponds to the second measurement information, and wherein training the first model using the set of identifiers includes inputting the set of identifiers into the first model.

[0012] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for receiving control information from a second network node, the control information indicating at least one of: the first number of CMRs or the second number of CMRs.

[0013] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first number of CMRs may be based on the periodicity, or the second number of CMRs may be based on the periodicity.

[0014] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first number of CMRs may be associated with a first set of time instances, the second number of CMRs may be associated with a second set of time instances different from the first set of time instances, and the one or more predicted time domain parameters include predicted measurements associated with the second number of CMRs associated with the second set of time instances.

[0015] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first number of CMRs may be associated with a first set of spatial filters at a second network node, the second number of CMRs may be associated with a second set of spatial filters at the second network node, and the one or more predicted spatial domain parameters include predicted measurements associated with the second number of CMRs sent via the second set of spatial filters at the second network node.

[0016] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: receiving a first beam set, wherein the first beam set includes the first signal set corresponding to the first number of CMRs; inputting a first beam identifier set corresponding to the first beam set into the first model, wherein the first predicted information may be based on the first beam identifier set.

[0017] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining, as an additional output of the first model, information including a second prediction of a second set of beam identifiers corresponding to a second set of beams, the second set of beam identifiers being associated with the second number of CMRs.

[0018] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first model may be associated with one or more serving cells, one or more bandwidth parts, one or more CMR sets, a channel state information reporting configuration, or any combination thereof.

[0019] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for receiving control information from a second network node, the control information indicating the one or more serving cells, the one or more bandwidth parts, the one or more CMR sets, the channel state information reporting configuration, or any combination thereof.

[0020] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first model includes a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0021] Some examples of the methods, devices, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: receiving the first model includes receiving the first model from a second network node, the first network node includes a UE, and the second network node includes a base station, a network entity, a server, or any combination thereof.

[0022] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, and the methods, apparatus, and non-transitory computer-readable media may also include operations, features, components, or instructions for: reference signal resources or synchronization signal block resources.

[0023] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, a reference signal received power, a signal-to-noise ratio, a signal-to-interference-plus-noise ratio, a channel quality indicator, a rank indicator, a precoding matrix indicator, or any combination thereof.

[0024] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the first model may include operations, features, components, or instructions for: receiving a download including the first model, and receiving the first model from a second network node via control signaling, or both.

[0025] A method for wireless communication at a first network node is described. The method may include: sending a signal within a CMR set; receiving a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; receiving a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the CMR set; generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; and sending an indication of the third model to at least one of the second network node or the third network node.

[0026] A first network node for wireless communication is described. The first network node may include a memory and at least one processor coupled to the memory. The at least one processor may be configured to: send a signal within a CMR set; receive a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; receive a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the CMR set; generate a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; and send an indication of the third model to at least one of the second network node or the third network node.

[0027] An apparatus for wireless communication at a first network node is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to: send a signal within a CMR set; receive a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; receive a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the CMR set; generate a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; and send an indication of the third model to at least one of the second network node or the third network node.

[0028] Another apparatus for wireless communication at a first network node is described. The apparatus may include: means for sending a signal within a CMR set; means for receiving a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; means for receiving a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the CMR set; means for generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; and means for sending an indication of the third model to at least one of the second network node or the third network node.

[0029] A non-transitory computer-readable medium storing code for wireless communication at a first network node is described. The code may include instructions executable by a processor to perform the following operations: send a signal within a CMR set; receive a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; receive a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the CMR set; generate a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the CMR set; and send an indication of the third model to at least one of the second network node or the third network node.

[0030] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: sending control information to the second network node, the control information indicating at least one of: a first number of CMRs in the CMR set or a second number of CMRs in the CMR set, wherein the first trained model may be trained based on a subset of the signals sent within the first number of CMRs.

[0031] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, a periodicity may be associated with the set of CMRs, and at least one of the first number of CMRs or the second number of CMRs may be based on the periodicity.

[0032] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the third model may be associated with one or more serving cells, one or more bandwidth parts, one or more CMR sets, a channel state information reporting configuration, or any combination thereof.

[0033] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending control information to at least one of the second network node or the third network node, the control information indicating one or more serving cells, one or more bandwidth parts, one or more CMR sets, a channel state information reporting configuration, or any combination thereof.

[0034] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the third model includes a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0035] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, at least one of the second network node or the third network node includes a corresponding UE, and the first network node includes a base station, a network entity, a server, or any combination thereof.

[0036] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the CMR set includes at least one of: a channel state information reference signal resource or a synchronization signal block resource.

[0037] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first portion of the set of CMRs may be the same as the second portion of the set of CMRs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 and Figure 2 An example of a wireless communication system supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0039] Figure 3 and Figure 4 An example of a model training procedure supporting techniques for beam property prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0040] Figure 5 An example of a process flow supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0041] Figure 6 and Figure 7 A block diagram of a device supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0042] Figure 8 A block diagram of a communication manager supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0043] Fig. 9 A diagram of a system including a device supporting techniques for beam characteristic prediction using a federated learning process is shown in accordance with one or more aspects of the present disclosure.

[0044] Fig.10 and Fig.11 A block diagram of a device supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0045] Fig.12A block diagram of a communication manager supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown.

[0046] Fig.13 A diagram of a system including a device supporting techniques for beam characteristic prediction using a federated learning process is shown in accordance with one or more aspects of the present disclosure.

[0047] Fig.14 and Fig.15 A flow chart illustrating a method of supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown. DETAILED DESCRIPTION

[0048] In some wireless communication systems, network nodes such as user equipment (UE) and base stations may perform beam management procedures in order to determine beam characteristics. For example, during the beam management procedure, a first network node (e.g., UE) may refine transmit (Tx) beams, receive (Rx) beams, and spatial filters that define these beams and will exhibit sufficient performance for wireless communication between the first network node and the second network node (e.g., base station). For example, a first network node (UE) may perform measurements on reference signals received from a second network node (base station) using different Rx beams, and may send a measurement report that enables the second network node to determine beam characteristics for future communications. In some wireless communication systems, network nodes (e.g., UE, base station, network entity) may be configured to determine and predict beam characteristics using machine learning models. However, the use of different models (and / or different inputs / outputs to and from the models) across different network nodes may result in differences between beam characteristics determined / predicted by the respective network nodes.

[0049] Thus, aspects of the present disclosure relate to techniques for implementing a federated learning model between network nodes (e.g., between a network and a UE) to facilitate prediction of temporal and spatial characteristics of future beams / communications. Specifically, the described techniques enable a network to configure a federated learning model to multiple UEs, aggregate trained federated learning models from respective UEs, and distribute the aggregated (e.g., composite) federated learning model across UEs such that the network and UEs are configured to use the same model to predict / estimate beam characteristics.

[0050] For example, a first network node (e.g., UE) may receive a model (e.g., a joint learning model) associated with a set of channel measurement resources (CMRs) from a second network node (e.g., base station, network entity). The first network node may perform measurements on a first subset of CMRs and input the measurements into the model. The model is configured to output time domain parameters (e.g., predicted channel measurements) and / or spatial domain parameters (e.g., predicted Tx beams of sufficient quality) for a second subset of CMRs. Additional measurements performed on the second subset of CMRs may be input into the model as "markers" for further training the model. Subsequently, the first network node may send the trained model to the second network node, where the second network node compiles multiple trained models across multiple network nodes (e.g., trained models from multiple UEs), generates an aggregated / composite model, and redistributes the aggregated / composite model to the respective network nodes for predicting future beam characteristics.

[0051] First, aspects of the disclosure are described in the context of a wireless communication system. Additional aspects of the disclosure are described in the context of an example model training procedure and an example process flow. Aspects of the disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flow diagrams related to techniques for beam characteristic prediction using a federated learning process.

[0052] Figure 1 An example of a wireless communication system 100 supporting techniques for beam characteristic prediction using a joint learning process in accordance with one or more aspects of the present 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 aspects, the wireless communication system 100 may be a long term evolution (LTE) network, an advanced LTE (LTE-A) network, an LTE-A Pro network, a new radio (NR) network, or a network operating according to other systems and radio technologies (including future systems and radio technologies not explicitly mentioned herein).

[0053] The network entities 105 may be dispersed throughout a geographic area to form the wireless communication system 100, and may include devices in different forms or with different capabilities. In various examples, the network entities 105 may be referred to as network elements, mobility elements, radio access network (RAN) nodes, or network equipment, etc. In some aspects, the network entities 105 and the UE 115 may communicate wirelessly via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, the network entity 105 may support a coverage area 110 (e.g., a geographic coverage area) within which the UE 115 and the network entity 105 may establish one or more communication links 125. The coverage area 110 may be an example of a geographic area within which the network entity 105 and the UE 115 may support signal communications according to one or more radio access technologies (RATs).

[0054] The UEs 115 may be dispersed throughout the coverage area 110 of the wireless communication system 100, and each UE 115 may be stationary or mobile, or both stationary and mobile at different times. The UEs 115 may be devices in different forms or with different capabilities. Figure 1 Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be capable of communicating with various types of devices such as Figure 1 Communicating with other UEs 115 or network entities 105 as shown.

[0055] As described herein, a node (which may be referred to as a node, a network node, a network entity, or a wireless node) may include, may be, or may be included in (e.g., as a component of) a base station (e.g., any base station described herein), a UE (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, an integrated access and backhaul (IAB) node, a distributed unit (DU), a central unit (CU), a remote unit (RU), and / or another processing entity configured to perform any of the techniques described herein. For example, the network node may be a UE. As another example, the network node may be a base station or a network entity. As another example, a first network node may be configured to communicate with a second network node or a third network node. In one aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a UE. In another aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a base station. In yet other aspects of this example, the first network node, the second network node, and the third network node may be different relative to these examples. Similarly, references to UE, base station, device, equipment, computing system, etc. may include disclosure of UE, base station, device, equipment, computing system, etc. as a network node. For example, a disclosure that a UE is 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 the present disclosure, once a specific example is expanded according to the present disclosure (e.g., a UE is 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), a broader example of a narrower example may 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 also discloses that a first network node is configured to receive information from a second network node, the first network node may refer to a first UE configured to receive information, a first base station, a first device, a first device, a first computing system, a first group of one or more components, a first processing entity, etc.; and the second network node may refer to a second UE, a second base station, a second device, a second device, a second computing system, a second group of one or more components, a second processing entity, etc.

[0056] As described herein, different terms may be used in various aspects to describe the transmission of information (e.g., any information, signal, etc.). The disclosure of one communication term includes the 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 the present disclosure, the disclosure that the first network node is configured to send information to the second network node includes the disclosure that the first network node is configured to provide, transmit, output, transmit or send information to the second network node. Similarly, in this example and consistent with the present disclosure, the disclosure that the first network node is configured to send information to the second network node includes the disclosure that the second network node is configured to receive, obtain or decode information provided, transmitted, output, communicated or sent by the first network node.

[0057] In some aspects, the network entities 105 may communicate with the core network 130, or with each other, or both. For example, the network entities 105 may communicate with the core network 130 via one or more backhaul communication links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some aspects, the network entities 105 may communicate with each other on the backhaul links 120 (e.g., according to X2, Xn, or other interface protocols) directly (e.g., directly between the network entities 105) or indirectly (e.g., via the core network 130). In some aspects, the network entities 105 may communicate with each other via midhaul communication links 162 (e.g., according to a midhaul interface protocol) or fronthaul communication links 168 (e.g., according to a fronthaul interface protocol) or any combination thereof. The backhaul communication links 120, midhaul communication links 162, or fronthaul communication links 168 may be or include one or more wired links (e.g., electrical links, optical fiber links), one or more wireless links (e.g., radio links, wireless optical links), etc. or various combinations thereof. UE 115 may communicate with core network 130 via communication link 155 .

[0058] One or more of the network entities 105 described herein may include or may be referred to as a base station 140 (e.g., a transceiver base station, a radio base station, an NR base station, an access point, a radio transceiver, a Node B, an evolved Node B (eNB), a next-generation Node B, or a gigabit Node B (any of which may be referred to as a gNB), a 5G NB, a next-generation eNB (ng-eNB), a home Node B, a home evolved Node B, or other suitable terms). In some aspects, the network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, stand-alone) base station architecture, which may be configured to utilize a protocol stack physically or logically integrated within a single network entity 105 (e.g., a single RAN node, such as a base station 140).

[0059] In some aspects, the network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that may be configured to utilize a protocol stack that is physically or logically distributed between two or more network entities 105, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, the network entity 105 may include one or more of the following: a central unit (CU) 160, a distributed unit (DU) 165, a radio unit (RU) 170, a RAN intelligent controller (RIC) 175 (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) 180 system, or any combination thereof. The RU 170 may also be referred to as a radio head, an intelligent radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmit receive point (TRP). One or more components of the network entity 105 in the decomposed RAN architecture may be co-located, or one or more components of the network entity 105 may be located in distributed locations (e.g., separate physical locations). In some aspects, one or more network entities 105 of the decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0060] The functional split between CU 160, DU 165, and RU 170 is flexible, and different functionalities may be supported 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, and RU 170. For example, a functional split of a protocol stack may be employed between CU 160 and DU 165, such that CU 160 may support one or more layers of a protocol stack, and DU 165 may support one or more different layers of a protocol stack. In some aspects, CU 160 may host higher protocol layer (e.g., layer 3 (L3), layer 2 (L2)) functionality and signaling (e.g., radio resource control (RRC), service data adaptation protocol (SDAP), packet data convergence protocol (PDCP)). The CU 160 may be connected to one or more DUs 165 or RUs 170, and the one or more DUs 165 or RUs 170 may host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160. Additionally or alternatively, a functional split of the protocol stack may be employed between the DU 165 and the RU 170, such that the DU 165 may support one or more layers of the protocol stack, and the RU 170 may support one or more different layers of the protocol stack. The DU 165 may support one or more different cells (e.g., via one or more RUs 170). In some cases, the functional split between CU 160 and DU 165 or between DU 165 and RU 170 may be within the protocol layer (e.g., some functions of the protocol layer may be performed by one of CU 160, DU 165, or RU 170, while other functions of the protocol layer are performed by different ones of CU 160, DU 165, or RU 170). CU 160 may be further functionally split into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 160 may be connected to one or more DUs 165 via midhaul communication links 162 (e.g., F1, F1-c, F1-u), and DU 165 may be connected to one or more RUs 170 via fronthaul communication links 168 (e.g., open fronthaul (FH) interface). In some aspects, the midhaul communication link 162 or the fronthaul communication link 168 may be implemented according to interfaces (eg, channels) between layers of a protocol stack supported by respective network entities 105 communicating over those communication links.

[0061] In some wireless communication systems (e.g., wireless communication system 100), infrastructure and spectrum resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture (e.g., to core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB nodes 104) may be partially controlled by each other. One or more IAB nodes 104 may be referred to as donor entities or IAB donors. One or more DUs 165 or one or more RUs 170 may be controlled in part by one or more CUs 160 associated with a donor network entity 105 (e.g., a donor base station 140). One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB nodes 104) via supported access and backhaul links (e.g., backhaul communication links 120). The IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a coupled IAB donor's DU 165. The IAB-MT may include an independent set of antennas for relaying communications with the UE 115, or may share the same antennas of the IAB node 104 (e.g., of the RU 170) for access via the DU 165 of the IAB node 104 (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some aspects, the IAB node 104 may include a DU 165 that supports communication links with additional entities (e.g., IAB node 104, UE 115) within a relay chain or configuration (e.g., downstream) of the access network. In such cases, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of the IAB node 104) may be configured to operate according to the techniques described herein.

[0062] For example, an access network (AN) or RAN may include an access node (e.g., an IAB donor), communications between an IAB node 104, and one or more UEs 115. An IAB donor may facilitate connectivity between a core network 130 and an 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. An 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 the IAB node 104 may communicate via an F1 interface according to a protocol that defines signaling messages (e.g., an F1 AP protocol). Additionally or alternatively, CU 160 may communicate with the core network via an interface (which may be an example of part of a backhaul link) and may communicate with other CUs 160 (e.g., CUs 160 associated with alternative IAB donors) via an Xn-C interface (which may be an example of part of a backhaul link).

[0063] An IAB node 104 may refer to a RAN node that provides IAB functionality (e.g., access for UE 115, wireless self-backhaul capabilities, 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 that communicates with one or more child nodes (e.g., an IAB donor may relay transmissions to a UE through one or more other IAB nodes 104). Additionally or alternatively, depending on the relay chain or configuration of the AN, an IAB node 104 may also be referred to as a parent node or child node of other IAB nodes 104. Thus, 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 a DU interface (eg, DU 165 ) may provide a Uu interface for parent IAB node 104 to signal to child IAB node 104 or UE 115 .

[0064] For example, the IAB node 104 may be referred to as a parent node that supports communications to a child IAB node, and may be referred to as a child IAB node associated with an IAB donor. The IAB donor may include a CU 160 having a wired or wireless connection (e.g., a backhaul communication link 120) to the core network 130, and may act as a parent node of the IAB node 104. For example, the DU 165 of the IAB donor may relay transmissions to the UE 115 through the IAB node 104, and may directly signal the UE 115 of the transmissions. The CU 160 of the IAB donor may signal the IAB node 104 of the communication link establishment via the F1 interface, and the IAB node 104 may schedule transmissions (e.g., transmissions relayed from the IAB donor to the UE 115) through the DU 165. That is, data may be relayed to and from the IAB node 104 via signaling through the NR Uu interface of the MT to the IAB node 104. Communications with the IAB node 104 may be scheduled by the DU 165 of the IAB donor, and communications with the IAB node 104 may be scheduled by the DU 165 of the IAB node 104 .

[0065] In the case where the techniques described herein are applied to the context of a decomposed RAN architecture, one or more components of the decomposed RAN architecture may be configured to support the techniques for beam characteristic prediction using a joint learning process as described herein. For example, some operations described as being performed by a UE 115 or a network entity 105 (e.g., a base station 140) may additionally or alternatively be performed by one or more components of the decomposed RAN architecture (e.g., an IAB node 104, a DU 165, a CU 160, a RU 170, a RIC 175, a SMO 180).

[0066] UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, where a "device" may also be referred to as a unit, a station, a terminal, or a client, etc. UE 115 may also include or may be referred to as a personal electronic device, such as a cellular phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some aspects, UE 115 may include or be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0067] The UE 115 described herein may be capable of communicating with various types of devices, such as other UEs 115, which may sometimes act as relays, as well as network entities 105 and network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, etc. Figure 1shown.

[0068] The UE 115 and the network entity 105 may communicate with each other wirelessly via one or more communication links 125 (e.g., access links) via one or more carriers. The term "carrier" may refer to a set of RF spectrum resources having a physical layer structure defined for supporting the communication link 125. For example, a carrier for the communication link 125 may include a portion of an RF spectrum band (e.g., a bandwidth portion (BWP)) that operates according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling for coordinating carrier operations, user data, or other signaling. The wireless communication system 100 may support communication with the UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, the UE 115 may be configured to have multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation may be used for both frequency division duplex (FDD) and time division duplex (TDD) component carriers. Communication between the network entity 105 and other devices may refer to communication between these devices and any portion (e.g., entity, sub-entity) of the network entity 105. For example, the terms "send," "receive," or "communicate" when referring to the network entity 105 may refer to any portion of the network entity 105 (e.g., base station 140, CU 160, DU 165, RU 170) of the RAN communicating with another device (e.g., directly or via one or more other network entities 105).

[0069] The signal waveform transmitted through the carrier may be composed of multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system using MCM technology, a resource element may refer to a symbol period (e.g., the duration of a modulation symbol) and a subcarrier resource, in which case the symbol period and the subcarrier spacing may be inversely related. The number of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both), so that the more resource elements a device receives and the higher the order of the modulation scheme, the higher the data rate of the device may be. Wireless communication resources may refer to a combination of RF spectrum resources, time resources, and spatial resources (e.g., spatial layers, beams), and the use of multiple spatial resources may improve the data rate or data integrity of communications with UE 115.

[0070] The time interval of the network entity 105 or the UE 115 may be expressed as a multiple of a basic time unit, which may be, for example, a sampling period T s =1 / (Δfmax ·N f ) seconds, where Δf max It can represent the maximum supported subcarrier spacing, and N f The maximum supported discrete Fourier transform (DFT) size may be indicated. Time intervals of the communication resources may be organized according to radio frames, each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0071] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some aspects, a frame may be divided into subframes (e.g., in the time domain), and each subframe may be further divided into a certain number of time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include a certain number of symbol periods (e.g., depending on the length of the cyclic prefix appended in front of each symbol period). In some wireless communication systems 100, the time slot may be further divided into a plurality of mini-time slots containing one or more symbols. Excluding the cyclic prefix, each symbol period may include one or more (e.g., N f The duration of a symbol period may depend on the subcarrier spacing or the operating frequency band.

[0072] A subframe, slot, mini-slot, or symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communication system 100 and may be referred to as a transmit time interval (TTI). In some aspects, the TTI duration (e.g., the number of symbol periods in a TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of a shortened TTI (sTTI)).

[0073] Physical channels may be multiplexed on a carrier according to various techniques. Physical control channels and physical data channels may be multiplexed on a downlink carrier using, for example, one or more of a time division multiplexing (TDM) technique, a frequency division multiplexing (FDM) technique, or a hybrid TDM-FDM technique. A control region (e.g., a control resource set (CORESET)) of a physical control channel may be defined by a set of symbol periods and may extend across a system bandwidth of a carrier or a subset of that system bandwidth. One or more control regions (e.g., CORESETs) may be configured for a set of UEs 115. For example, one or more of the UEs 115 may monitor or search a control region for control information according to one or more search space sets, and each search space set may include one or more control channel candidates in one or more aggregation levels arranged in a cascaded manner. The aggregation level of a control channel candidate may refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space sets may include a common search space set configured for transmitting control information to multiple UEs 115 , and a UE-specific search space set for transmitting control information to a specific UE 115 .

[0074] In some aspects, the network entities 105 (e.g., base stations 140, RUs 170) may be mobile and, therefore, provide communication coverage for mobile coverage areas 110. In some aspects, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 provide coverage for various coverage areas 110 using the same or different radio access technologies.

[0075] The wireless communication system 100 may support synchronous or asynchronous operation. For synchronous operation, the network entities 105 (e.g., base stations 140) may have similar frame timing, and transmissions from different network entities 105 may be approximately aligned in time. For asynchronous operation, the network entities 105 may have different frame timing, and in some aspects, transmissions from different network entities 105 may not be aligned in time. The techniques described herein may be used for synchronous or asynchronous operation.

[0076] Some UEs 115, such as MTC or IoT devices, may be low-cost or low-complexity devices and may provide automated communication between machines (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC may refer to data communication technology that allows devices to communicate with each other or with a network entity 105 (e.g., base station 140) without human intervention. In some aspects, M2M communication or MTC may include communication from devices that integrate sensors or meters to measure or capture information and relay such information to a central server or application that utilizes the information or presents the information to a person interacting with the application. Some UEs 115 may be designed to collect information or implement automated behavior of machines or other devices. Examples of applications for MTC devices include: smart metering, inventory monitoring, water level monitoring, equipment monitoring, health care monitoring, wildlife monitoring, weather and geographic event monitoring, queue management and tracking, remote security sensing, physical access control, and transaction-based commercial charging.

[0077] Some UEs 115 may be configured to employ a reduced power consumption mode of operation, such as half-duplex communication (e.g., a mode that supports one-way communication via transmission or reception but does not transmit and receive concurrently). In some aspects, half-duplex communication may be performed at a reduced peak rate. Other power saving techniques for UEs 115 include entering a power-saving deep sleep mode when not engaged in active communications, operating with limited bandwidth (e.g., according to narrowband communications), or a combination of these techniques. For example, some UEs 115 may be configured to operate using a narrowband protocol type that is associated with a defined portion or range (e.g., a subcarrier or resource block (RB) set) within a carrier, within a guard band of a carrier, or outside a carrier.

[0078] The wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication or various combinations thereof. For example, the wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable or low-latency or critical functions. Ultra-reliable communication may include private communication or group communication, and may be supported by one or more services (such as push-to-talk, video, or data). Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, and ultra-reliable low-latency may be used interchangeably herein.

[0079] In some aspects, a UE 115 may be able to communicate directly with other UEs 115 over a device-to-device (D2D) communication link 135 (e.g., according to a peer-to-peer (P2P), D2D, or sidelink protocol). In some aspects, one or more UEs 115 in a group that are performing D2D communication may be within a coverage area 110 of a network entity 105 (e.g., a base station 140, a RU 170), which may support various aspects of such D2D communication as configured or scheduled by the network entity 105. In some aspects, one or more UEs 115 in the group may be outside of the coverage area 110 of the network entity 105, or may otherwise be unable or not configured to receive transmissions from the network entity 105. In some aspects, a group of UEs 115 communicating via D2D communication may support a one-to-many (1:M) system in which each UE 115 transmits to each of the other UEs 115 in the group. In some aspects, the network entity 105 may facilitate scheduling resources for D2D communication. In some other examples, D2D communications may be performed between UEs 115 without involving network entity 105 .

[0080] In some systems, the D2D communication link 135 can be an example of a communication channel (such as a sidelink communication channel) between vehicles (e.g., UE 115). In some aspects, the vehicles can communicate using vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination of these items. The vehicles can signal information related to traffic conditions, signal scheduling, weather, safety, emergency situations, or any other information related to the V2X system. In some aspects, the vehicles in the V2X system can communicate with roadside infrastructure such as roadside units, or communicate with the network using vehicle-to-network (V2N) communication via one or more network nodes (e.g., network entity 105, base station 140, RU 170), or communicate with both.

[0081] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or a 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) for managing access and mobility and at least one user plane entity (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)) for routing packets or interconnecting to an external network. The control plane entity may manage non-access layer (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by a network entity 105 (e.g., a base station 140) associated with the core network 130. User IP packets may be delivered through the user plane entity, which may provide IP address allocation and other functions. The user plane entity may be connected to the IP service 150 of one or more network operators. IP services 150 may include access to the Internet, an intranet, an IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0082] The wireless communication system 100 may operate using one or more frequency bands that may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). Generally speaking, the region from 300 MHz to 3 GHz is referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelength ranges from about one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features (which may be referred to as clusters), but these waves may be sufficient to penetrate structures so that macro cells provide services to UEs 115 located indoors. Transmission of UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than 100 kilometers) than transmission using smaller frequencies and longer wavelengths of the high frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz.

[0083] The wireless communication system 100 may also operate in a super high frequency (SHF) region using a frequency band from 3 GHz to 30 GHz (also referred to as a centimeter band) or in an extremely high frequency (EHF) region of a spectrum (e.g., from 30 GHz to 300 GHz) (also referred to as a millimeter band). In some aspects, the wireless communication system 100 may support millimeter wave (mmW) communications between a UE 115 and a network entity 105 (e.g., a base station 140, a RU 170), and the EHF antennas of the corresponding devices may be smaller and more closely spaced than UHF antennas. In some aspects, this may facilitate the use of antenna arrays within the device. However, there may be even greater atmospheric attenuation and a shorter range for the propagation of EHF transmissions than for SHF or UHF transmissions. The technology disclosed herein may be adopted across transmissions using one or more different frequency regions, and the use of frequency bands specified across these frequency regions may differ by country or regulatory agency.

[0084] The wireless communication system 100 may utilize licensed and unlicensed RF spectrum bands. For example, the wireless communication system 100 may use license assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology in unlicensed bands such as the 5 GHz industrial, scientific, and medical (ISM) band. When operating in an unlicensed RF spectrum band, devices such as the network entity 105 and the UE 115 may employ carrier sensing for conflict detection and avoidance. In some aspects, operations in unlicensed bands may be based on a carrier aggregation configuration combined with component carriers operating in a licensed band (e.g., LAA). Operations in the unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, and the like.

[0085] The network entity 105 (e.g., base station 140, RU 170) or UE 115 may be equipped with multiple antennas that can be used to employ technologies such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of the network entity 105 or UE 115 may be located within one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly, such as an antenna tower. In some aspects, antennas or antenna arrays associated with the network entity 105 may be located at different geographical locations. The network entity 105 may have an antenna array having a collection of multiple rows and columns of antenna ports that the network entity 105 can use to support beamforming for communications with the UE 115. Similarly, the UE 115 may have one or more antenna arrays that may support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals sent via the antenna ports.

[0086] The network entity 105 or UE 115 may use MIMO communication to utilize multipath signal propagation and improve spectral efficiency by sending or receiving multiple signals via different spatial layers. Such a technology may be referred to as spatial multiplexing. The multiple signals may be sent, for example, by a transmitting device via different antennas or different combinations of antennas. Similarly, the multiple signals may be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers may be associated with different antenna ports for channel measurement and reporting. MIMO technology includes single-user MIMO (SU-MIMO), in which multiple spatial layers are sent to the same receiving device, and multi-user MIMO (MU-MIMO), in which multiple spatial layers are sent to multiple devices.

[0087] Beamforming (which may also be referred to as spatial filtering, directional transmission, or directional reception) is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or direct an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining signals conveyed via antenna elements of an antenna array so that some signals propagating in a particular direction relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to signals conveyed via antenna elements may include the transmitting device or the receiving device applying an amplitude offset, a phase offset, or both to signals carried via antenna elements associated with the device. Adjustments associated with each of these antenna elements may be defined by a set of beamforming weights associated with a particular direction (e.g., relative to the antenna array of the transmitting device or the receiving device or relative to some other direction).

[0088] The network entity 105 or UE 115 may use beam scanning techniques as part of a beamforming operation. For example, the network entity 105 (e.g., base station 140, RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be sent multiple times by the network entity 105 along different directions. For example, the network entity 105 may send signals according to different sets of beamforming weights associated with different transmission directions. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device, such as network entity 105, or by a receiving device, such as UE 115) beam directions for later transmission or reception by the network entity 105.

[0089] Some signals, such as data signals associated with a particular receiving device, may be transmitted by a transmitting device (e.g., a transmitting network entity 105, a transmitting UE 115) along a single beam direction (e.g., a direction associated with a receiving device (such as a receiving network entity 105 or a receiving UE 115)). In some aspects, a beam direction associated with transmission along a single beam direction may be determined based on signals transmitted along one or more beam directions. For example, UE 115 may receive one or more of the signals transmitted by network entity 105 along different directions and may report to network entity 105 an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.

[0090] In some aspects, transmission by a device (e.g., by a network entity 105 or a UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from the network entity 105 to the UE 115). The UE 115 may report feedback indicating precoding weights for one or more beam directions, and the feedback may correspond to a configured beam set across a system bandwidth or one or more subbands. The network entity 105 may transmit a reference signal (e.g., a cell-specific reference signal (CRS), a channel state information reference signal (CSI-RS)), which may be precoded or not precoded. The UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-faceted codebook, a linear combination codebook, a port selection codebook). Although these techniques are described with reference to signals sent along one or more directions by a network entity 105 (e.g., base station 140, RU 170), UE 115 may use similar techniques to send signals multiple times along different directions (e.g., to identify a beam direction for subsequent transmission or reception by UE 115), or to send signals along a single direction (e.g., to send data to a receiving device).

[0091] When receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a receiving device (e.g., network entity 105), the receiving device (e.g., UE 115) may perform receiving operations (e.g., directional listening) according to multiple receiving configurations. For example, the receiving device may perform reception according to multiple receiving directions by receiving via different antenna subarrays, processing the received signals according to different antenna subarrays, receiving according to different receiving beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or processing the received signals according to different receiving beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as "listening" according to different receiving configurations or receiving directions. In some aspects, the receiving device may use a single receiving configuration to receive along a single beam direction (e.g., when receiving a data signal). A single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or other acceptable signal quality based on listening according to multiple beam directions).

[0092] The wireless communication system 100 may be a packet-based network that operates according to a layered protocol stack. In the user plane, communications at the bearer or PDCP layer may be IP-based. The RLC layer may perform packet segmentation and reassembly to communicate through logical channels. The MAC layer may perform priority processing and multiplexing of logical channels into transport channels. The MAC layer may also use error detection techniques, error correction techniques, or both to support retransmission at the MAC layer to improve link efficiency. In the control plane, the RRC protocol layer may provide the establishment, configuration, and maintenance of an RRC connection that supports a radio bearer for user plane data between a UE 115 and a network entity 105 or a core network 130. At the PHY layer, transport channels may be mapped to physical channels.

[0093] UE 115 and network entity 105 may support retransmission of data to increase the possibility of successfully receiving data. Hybrid automatic repeat request (HARQ) feedback is a technique for increasing the possibility of correctly receiving data through a communication link (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC)), forward error correction (FEC), and retransmission (e.g., automatic repeat request (ARQ)). HARQ may improve the throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some aspects, a device may support simultaneous slot HARQ feedback, in which the device may provide HARQ feedback in a specific time slot for data received in a previous symbol in the time slot. In some other examples, the device may provide HARQ feedback in a subsequent time slot or according to some other time interval.

[0094] In some aspects, network nodes (e.g., UE 115, network entity 105, base station) of the wireless communication system 100 may support signaling and techniques for implementing a federated learning model between network nodes (e.g., between the network and UE 115) to facilitate prediction of temporal and spatial characteristics of future beams / communications. Specifically, the described techniques enable the network to configure a federated learning model to multiple UEs 115, aggregate trained federated learning models from respective UEs 115, and distribute the aggregated (e.g., composite) federated learning model across UEs 115 such that the network and UE 115 are configured to use the same model to predict / estimate beam characteristics.

[0095] For example, a first network node (e.g., network entity 105) of the wireless communication system 100 may send a model (e.g., a joint learning model) associated with a set of CMRs to a second network node (e.g., UE 115). The second network node may perform measurements on a first subset of CMRs and input the measurements into the model. In some aspects, the model may be configured to output time domain parameters (e.g., predicted channel measurements) and / or spatial domain parameters (e.g., predicted Tx beams of sufficient quality) for a second subset of CMRs. Additional measurements performed on the second subset of CMRs may be input into the model as "markers" for further training the model. Subsequently, the second network node (UE 115) may send the trained model to the first network node (network entity 105), wherein the first network node compiles multiple trained models across multiple network nodes (e.g., trained models from multiple UEs 115), generates an aggregated / composite model, and redistributes the aggregated / composite model to the respective network nodes (UE 115) for predicting future beam characteristics.

[0096] The techniques described herein may facilitate the use of models such as federated learning models, distributed models, machine learning models, etc. to more efficiently and accurately predict beam characteristics. By enabling network nodes to more accurately predict beam characteristics for future communications, the techniques described herein may enable the network to more efficiently schedule wireless communications, and may enable corresponding network nodes to perform communications using parameters (e.g., Tx beams, Rx beams) that will exhibit adequate performance. Therefore, aspects of the present disclosure may enable more efficient and reliable wireless communications within the wireless communication system 100.

[0097] Figure 2 An example of a wireless communication system 200 supporting techniques for beam characteristic prediction using a federated learning process in accordance with one or more aspects of the present disclosure is shown. In some examples, aspects of the wireless communication system 200 may implement or be implemented by aspects of the wireless communication system 100. Specifically, the wireless communication system 200 may support signaling and techniques that enable a network node (e.g., a UE 115, a network entity 105) to predict beam characteristics for future communications using a model such as a FL model, a distributed learning model, a machine learning model, etc.

[0098] The wireless communication system 200 may include a plurality of network nodes, which may be as shown in FIG. Figure 1 Examples of network entities 105 and UEs 115 as described. For example, the wireless communication system 200 may include a first network node 105-a, which may be an example of a base station or network entity 105, and one or more additional network nodes 115-a, 115-b, and 115-d, which may be examples of UEs 115. The network nodes 105-a, 115-b, and 115-d may communicate with the first network node 105-a using communication links 205-a, 205-b, and 205-c, respectively, which may be examples of NR or LTE links between the respective network nodes 115 and the first network node 105-a. In some cases, the communication link 205 may include an example of an access link (e.g., a Uu link), which may include a bidirectional link that implements both uplink and downlink communications. For example, the second network node 115-a (e.g., UE 115-a) may use the communication link 205-a to send an uplink signal, such as an uplink control signal or an uplink data signal, to one or more components of the first network node 105-a, and one or more components of the first network node 105-a may use the communication link 205-a to send a downlink signal, such as a downlink control signal or a downlink data signal, to the second network node 115-a.

[0099] In some aspects, the wireless communication system 200 may include an additional network node 105-b. The additional network node 105-b may include a server, a network entity 105, and the like. In some aspects, the additional network node 105-b may include or be associated with the first network node 105-a. In other specific implementations, the additional network node 105-b may be separate from the network node 105-a, but may be communicatively coupled to (e.g., coupled to) corresponding devices of the wireless communication system 200 via the communication link 210. For example, the network nodes 115-a, 115-b, and 115-c may be communicatively coupled to (e.g., coupled to) the additional network node 105-b via the communication link 210.

[0100] In some aspects, the network nodes of the wireless communication system 200 may perform a beam management procedure to determine beam characteristics to be used for wireless communication between the respective network nodes. For example, during an initial access phase of the beam management procedure, when the network node 115-a (e.g., UE) receives a signal from the first network node 105-a, the network node 115-a may scan across beams or reference signals (e.g., synchronization signal block (SSB) scanning) to determine which Rx beams will be used at the network node 115-a to communicate with the first network node 105-a (e.g., SSB and RACH associations). In other words, the network node 115-a may perform SSB beam scanning and / or CSI-RS beam scanning as part of the beam management procedure. Once in connected mode, the respective network nodes may perform hierarchical beam refinement procedures (e.g., P1, P2, P3 procedures, or U1, U2, U3 procedures) in which the respective network nodes scan across narrower beams to refine which beams will be used for wireless communications. The network node 115-a may send a layer 1 (L1) report for beam refinement.

[0101] During the beam management procedure, the corresponding network node may be configured to identify and / or predict beam characteristics in the time domain and / or space domain to achieve overhead and latency reduction and beam selection accuracy improvement. In other words, the network node may be configured to predict channel conditions and corresponding beam characteristics to be used at different time points in the future, and / or predict channel conditions to be experienced using different Tx / Rx beam combinations. The beam management procedure may also achieve positioning accuracy enhancement for different scenarios, such as for severe non-line of sight (NLOS) conditions.

[0102] The beam management procedure may be used to refine transmit (Tx) beams, receive (Rx) beams, and spatial filters that define these beams and will exhibit adequate performance for wireless communications between the first network node 105-a (network entity 105) and the second network node 115-a (UE 115). For example, the second network node 115-b may perform measurements on reference signals received from the first network node 105-a (network entity 105) using different Rx beams, and may send measurement reports (e.g., CSI feedback) that enable the first network node 105-a to determine beam characteristics for future communications.

[0103] In some wireless communication systems, network nodes (e.g., UE 115, base station, network entity 105) may be configured to utilize machine learning models to determine and predict beam characteristics. However, using different models (and / or different inputs / outputs to and from the models) across different network nodes may result in differences between the beam characteristics determined / predicted by the respective network nodes.

[0104] Thus, some aspects of the present disclosure relate to using a FL model (also referred to as a distributed learning model) associated with a set of CMRs to predict beam characteristics associated with the set of CMRs. In general, the wireless communication system 200 may implement a FL model in which multiple models are trained at different network nodes (e.g., network nodes 115-a, 115-b, 115-c), aggregated into a composite model, and redistributed to the respective network nodes. In other words, the wireless communication system 200 may enable the FL model and other artificial intelligence (AI) models to be trained to predict temporal and spatial beam characteristics via computation at edge devices and servers.

[0105] For example, in the context of the wireless communication system 200, local training for the federated learning model may be triggered by an edge server, such as an additional network node 105-b. In this regard, the additional network node 105-b may send a model (e.g., an untrained model) to each of the network nodes 115-a, 115-b, 115-c for training. In other words, the network nodes 115-a, 115-b, 115-c may each download or retrieve a model from the additional network node 105-b. The network node 115 may, for example, train the received local model by performing measurements on the signal received from the first network node 105-a and inputting the measurements into the corresponding local model. Specifically, the network nodes 115 may each train the corresponding local model based on the measurements input into the local model to predict the temporal and spatial characteristics of the CMR. Therefore, each local model will be trained differently based on the channel conditions (and therefore the measurements) at each of the corresponding network nodes 115.

[0106] Continuing with the same example, the local models trained at the network nodes 115 may be aggregated (e.g., sent, uploaded) to an edge server or network node. For example, the network nodes 115-a, 115-b, 115-c may each send a trained local model to the first network node 105-a, the additional network node 105-b, or both. The parameters of the trained local models may be parameters in a recursive neural network (RNN) or used to derive gradients for the RNN. Subsequently, the first network node 105-a, the additional network node 105-b, or both may aggregate and combine the received local models to generate or update an "aggregate" or "composite" model (e.g., a global model). In some cases, the aggregation of local models received from the network nodes 115 may include simple parameter / gradient averaging (e.g., the FedAvg procedure). The updated aggregate / composite model (e.g., a global model) may then be sent or broadcast back to the edge devices (e.g., network nodes 115-a, 115-b, 115-c) so that the corresponding network nodes 115 may utilize the aggregate / composite model to predict the time / spatial domain characteristics of future CMR and future communications.

[0107] Federated learning may provide several advantages over other types of models or learning procedures. Specifically, federated learning may enable rapid access to real-time data generated at edge devices (e.g., network nodes 115-a, 115-b, 115-c) for rapid training of AI models. In addition, the federated learning procedures described herein may reduce or eliminate the consumption of large amounts of radio device resources for raw data delivery, and may achieve improved privacy because raw data associated with a federated model (e.g., data used to train the corresponding federated model) does not necessarily need to be exchanged between devices.

[0108] In the context of federated learning, different devices (e.g., network nodes 115-a, 115-b, 115-c) may be expected to train a common model with the same input / output / label definition (which may be signaled from the network or the first network node 105-a) and feed the trained model back to the network / first network node 105-a. The techniques described herein may utilize federated learning-based training (e.g., machine learning-based training) to perform beam prediction in the spatial / temporal domain by associating respective models distributed across network nodes 115-a, 115-b, 115-c with defined beam measurement processes operated by respective network nodes 115 in order to determine appropriate inputs, outputs, and labels for the models.

[0109] In other words, the local models distributed to each of the corresponding network nodes 115-a, 115-b, 115-c (and trained by the network nodes) can be associated with (e.g., corresponding to) a common CMR set, so that the corresponding network nodes 115-a, 115-b, 115-c use similar or identical inputs, outputs, and labels to train the corresponding local models, which will be aggregated to generate an aggregated / composite model for predicting the temporal / spatial characteristics of the CMR set. Therefore, the technology described herein relates to signaling and other configurations that enable the corresponding network nodes of the wireless communication system 200 (e.g., the first network node 105-a, network nodes 115-a, 115-b, 115-c, additional network nodes 105-b) to "reach a consensus" with respect to the inputs, outputs, and labels used to train the local models when using a federated learning technique to train a common machine learning model for beam prediction.

[0110] For example, in the context of periodic CSI (P-CSI) reporting with a reported number ssb-Index-RSRP associated with sixteen SSB resources, the second network node 115-a may be configured to perform L1 reference signal received power (L1-RSRP) of the SSB resources, and use the periodically measured L1-RSRP associated with a certain number of sixteen SSB resources as input to the model (where the number of SSBs used as input may be spatial / temporal downsampled). In this example, the model can be used to predict the spatial and temporal characteristics of a set of SSBs as output (e.g., outputting predicted ssb-Index-RSRP). Non-downsampled L1-RSRP measurements associated with the predicted measurements may be used as markers that are input back into the model to facilitate supervised training. In addition to downsampled and / or non-downsampled downlink measurements (e.g., downlink beam quality) used as input and output from the model, the second network node 105-b may also input the Rx beam for receiving the corresponding SSB at the model input. For example, in case of UE 115 rotation or MPE event, the Rx beam may be gradually changed, resulting in a gradual change of the corresponding Tx beam at the network entity 105. Therefore, by inputting the Rx beam into the model, the second network node 115-a may train the model to predict the Rx beam that will exhibit superior performance when receiving future SSBs.

[0111] Various aspects of the wireless communication system 200 may support signaling enhancements for supporting federated learning-based beam prediction and machine model training at the corresponding network nodes 115-a, 115-b, 115-c. Specifically, the wireless communication system 200 may support a network configuration that enables a model (e.g., a federated model) to be associated with one or more beam measurement procedures (e.g., CMR) so that the network nodes 115-a, 115-b, 115-c can appropriately identify inputs, outputs, and tags associated with the federated learning process and the corresponding model for beam prediction throughout the wireless communication system 200. In addition, various aspects of the present disclosure may also enable the corresponding network nodes 115-a, 115-b, 115-b (e.g., UE 115) to implicitly identify the Rx beam information at the corresponding network node 115 as input for further training the federated learning machine learning model.

[0112] Specifically, the wireless communication system 200 may support techniques for implementing a federated learning model between network nodes (e.g., between the network and the UE 115) to facilitate prediction of temporal and spatial characteristics of future beams / communications. The described techniques enable the first network node 105-a and / or the additional network node 105-b to configure the federated learning model to the respective network nodes 115-a, 115-b, 115-c, aggregate the trained federated learning models from the respective network nodes 115, and distribute the aggregated (e.g., composite) federated learning model across the respective network nodes 115, such that the first network node 105-a and the respective network nodes 115-a, 115-b, 115-c are configured to use the same model to predict / estimate beam characteristics.

[0113] For example, refer to Figure 2 In the illustrated wireless communication system 200, each network node 115-a, 115-b, 115-c may be configured by the network (e.g., by the first network node 105-a, the additional network node 105-b, or both) to locally train a model 220 (e.g., a machine learning model, a federated learning model, a distributed learning model) for spatial / temporal beam prediction. For example, in some cases, each network node 115 may download, retrieve, or otherwise receive a local model 220 to be trained by the corresponding network node 115.

[0114] In some aspects, the model 220 received by each network node 115 may be associated with a set of CMRs 215, where the model 220 is to be trained based on the CMRs 215 and used to predict beam characteristics associated with the CMRs 215. For example, Figure 2The illustrated CMRs 215 may include CSI-RS resources, SSB resources, or both associated with the model 220 received / downloaded at each respective network node 115. In this regard, a training procedure for the model 220 at each network node 115 may be associated with at least one set of CMRs 215 (e.g., CSI-RS resources, SSB resources) such that inputs, outputs, and / or tags (e.g., data tags) associated with the training process for jointly learning the model 220 are associated with the set of CMRs 215.

[0115] The association between the model 220 (e.g., the joint learning training process for the model 220) and the set of CMRs 215 may be indicated or determined in a variety of ways or in a variety of implementations. For example, in some cases, the model 220 may be associated with one or more serving cells (e.g., ServingCell-IDs), one or more BWPs (e.g., BWP-IDs), one or more CMR resource set identifiers (e.g., CSI-RS resource IDs, SSB resource IDs) for the joint learning process, or any combination thereof. In such cases, the association between the model 220 and the corresponding set of CMRs 215 may be signaled to the network nodes 115-a, 115-b, 115-c in a variety of implementations.

[0116] For example, the association between the model 220 and the corresponding set of CMRs 215 may be configured together with the configuration for the joint learning training process. In other cases, the association between the model 220 and the corresponding set of CMRs 215 may be configured separately from the configuration for the joint learning training process and may be indicated via RRC signaling, triggered via DCI and / or MAC-CE signaling, or both. In addition, in some cases, the association between the model 220 and the corresponding set of CMRs 215 may be configured or indicated based on an association with a corresponding CSI report configuration (e.g., CSI report setting, specific or particular CSI resource setting), so that the CMRs 215 associated with the corresponding CSI report configuration (e.g., CSI-RS / SSB resources) may be considered as CMRs 215 for the joint learning training process.

[0117] In some aspects, the input to the model 220 may include spatial / time domain downsampled channel characteristic measurements (e.g., L1-RSRP measurements, L1-SINR measurements, rank indicator (RI), precoding matrix indicator (PMI), channel quality indicator (CQI)) of a first number of CMRs in the set of CMRs 215 (e.g., a first number of CSI-RS resources / SSB resources associated with the model 220). For example, Figure 2As shown, the second network node 115-b may receive reference signals (e.g., CSI-RS, SSB) within the set of CMRs 215 and may perform measurements 225 for a first number of CMRs in the set of CMRs 215. The measurements 225 for the N1 CMRs 215 may include RSRP measurements, RI, PMI, CQI, etc. The first number of CMRs / first subset of the set of CMRs 215 measured for input to the model 220 may be downsampled in the time domain and / or the spatial domain such that the second network node 115-b does not perform measurements 225 for each CMR 215.

[0118] Continue to refer Figure 2 , measurements 225 performed on a first number of CMRs / a first subset of the set of CMRs 215 may be input into a local model 220 at the second network node 115-a. In some aspects, the model 220 may be configured to generate one or more outputs, wherein the model output may include predicted channel characteristics of a second number of CMRs / a second subset of the set of CMRs 215 (e.g., CSI-RS resources, SSB resources) associated with the model 220. In some cases, the predicted channel characteristics may or may not be spatial / time domain downsampled. In other words, the second network node 115-a may be configured to input measurements 225 associated with a first subset of the set of CMRs 215, and the model 220 may output predictions 230 associated with a second subset of the set of CMRs 215. The predictions 230 may include or indicate parameters associated with the second subset of the set of CMRs 215, including predicted time domain parameters, predicted spatial domain parameters, or both. For example, the prediction 230 may include a predicted RSRP measurement for the CMR 215 scheduled to be performed at a future measurement occurrence (e.g., a time instance) (time domain prediction), and / or a predicted RSRP measurement for the CMR 215 scheduled to be performed at the first network node 105-a using a specified Tx beam (spatial domain prediction).

[0119] In the context of supervised learning, a loss function for ML model training may be calculated based on labeled data (e.g., labels 235), where the labeled data is determined based on at least actual measured channel characteristics associated with predicted channel characteristics of a second number of CMRs in the set of CMRs 215. In other words, after generating the predictions 230 for the second subset of the set of CMRs 215, the second network node 115-a may perform actual measurements on the second subset N2, and the measurements on the second subset of CMRs may be input as labels 235 to further train and refine the model. In this regard, the labels 235 may correspond to the predictions 230 output by the model 220, where re-inputting the labels 235 into the model 220 may enable the model 220 to determine how accurately the model 220 predicted the beam characteristics of the second number of CMRs / a second subset of the CMRs, and further refine the model 220 for subsequent beam characteristic predictions.

[0120] When training the local models 220, each network node 115-a, 115-b, 115-c may feed back the trained model 220 or intermediate parameters (e.g., gradients) associated with the model training to the first network node 105-a, the additional network node 105-b, or both. In other words, the network node 115-a may send a first locally trained model 220 to the first network node 105-a, the network node 115-b may send a second locally trained model 220 to the first network node 105-a, and the network node 115-c may send a third locally trained model 220 to the first network node 105-a. In this example, the first network node 105-a may be configured to compile or aggregate the locally trained models 220 and generate an aggregated or composite model based on the respective locally trained models 220. The first network node 105-a may then return the aggregation / compound model to the network nodes 115-a, 115-b, 115-c, such that each network node within the wireless communication system 200 is configured to perform beam characteristic prediction using the same aggregation / compound model.

[0121] In some respects, Figure 2 The illustrated model 220 training process may be used to predict time domain parameters of a set of CMRs 215 (eg, time domain measurement predictions), predict space domain parameters of a set of CMRs 215 (eg, space domain measurement predictions), or both. Figure 3 Further details on time domain beam prediction are given in this paper. Figure 4 Spatial domain beam prediction is described in further detail.

[0122] Although much of the description of the wireless communication system 200 is described in the context of the network nodes 115-a, 115-b, and 115-c locally training the models 220 and the first network node 105-a redistributing the aggregate / composite model based on the locally trained models 220, this should not be considered a limitation of the present disclosure unless otherwise noted herein. Specifically, in some cases, the network nodes 115-a, 115-b, 115-c may simply receive, download, or otherwise obtain the trained models 220 from the network (e.g., via the first network node 105-a and / or the additional network node 105-b) such that the network nodes 115-a, 115-b, and 115-c do not perform any training, but instead use the trained models 220 to predict future time-domain and spatial-domain characteristics of the set of CMRs 215 (e.g., specifically to predict future time-domain and spatial-domain characteristics of the set of CMRs 215). In such cases, network node 115 may thereby ignore or otherwise avoid inputting labels 235 into model 220 due to the fact that network node 115 does not perform any training.

[0123] In the event that the network nodes 115-a, 115-b, and 115-c receive, download, or otherwise obtain the trained model 220, the input measurements 225 and the predictions 230 (e.g., outputs) of the trained model 220 may be configured together when the respective network nodes 115 receive, download, or otherwise obtain the trained model 220. Additionally or alternatively, the input measurements 225 and the predictions 230 of the trained model 220 may be configured separately from when the respective network nodes 115 receive or download the trained model 220. In such cases, the input measurements 225 and the predictions 230 of the trained model 220 may be configured by the first network node 105-a via RRC signaling, activated or triggered via DCI and / or MAC-CE, or both. In additional or alternative embodiments, the input measurements 225 and predictions 230 of the trained model 220 may be configured based on an association with a corresponding CSI reporting configuration (e.g., CSI reporting setting, CSI resource setting) such that a set of CMRs 215 associated with the corresponding CSI reporting configuration (e.g., a set of CSI-RS / SSB resources) may be considered as CMRs 215 for the trained model 220 inference / prediction process for predicting time domain and spatial domain parameters, as described herein.

[0124] Figure 3 An example of a model training procedure 300 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. In some examples, aspects of the model training procedure 300 can implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, or both. Specifically, the model training procedure 300 illustrates using a model 305 to perform time domain beam prediction, as described in reference Figure 1 – Figure 2 The above, and other aspects.

[0125] Figure 3 The illustrated model training procedure 300 includes a first network node 115-d and a second network node 105-c, which may be examples of other network nodes described herein. Figure 3 The illustrated first network entity 115 - d may include Figure 2 Examples of UE 115 and / or network entity 115-a are shown. Similarly, Figure 3 The illustrated second network node 105 - c may include Figure 2 An example of a network entity 105, a base station and / or a first network node 105-a is illustrated.

[0126] As previously described herein, the first network node 115-d may be configured with, retrieve, download, or otherwise receive the model 305 (e.g., a federated learning model, a distributed learning model, a machine learning model). In some cases, the first network node 115-d may receive the model 305 from the second network node 105-c, an additional network node (e.g., a server), or both. The model 305 may be useful for predicting at least the time domain characteristics associated with the set of CMRs 310. In this regard, the model 305 may be used to predict the time domain characteristics associated with the set of CMRs 310. Figure 3 The illustrated set of CMRs 310 is associated. The set of CMRs 310 may include CSI-RS resources, SSB resources, or both.

[0127] For example, Figure 3 As shown, a CMR 310 set (eg, a CSI-RS / SSB resource set) may be periodic or semi-persistent and may include K number of CMRs 310 . Figure 3 The illustrated CMRs 310 are illustrated as having a periodicity of 20 ms. However, a set of CMRs 310 may be associated with any periodicity or no periodicity (eg, aperiodic).

[0128] In this example, the first network node 115-d may be configured to receive a first number of CMRs or reference signals (e.g., CSI-RS, SSB) within a first subset of the K number of CMRs 310, perform measurements (e.g., RSRP measurements, RI, PMI, CQI) on the first number of CMRs 310, and use the measurements as input 315 to the model 305. For example, Figure 3As shown, the first network node 115-d may perform measurements for the first CMR 310-a and may use the measurements as input 315-a, which is input into the model 305-a (e.g., into the first version of the model 305-a). In this example, the model 305-a may be configured to generate an output 325-a, wherein the output 325-a includes predicted time domain parameters for the set of CMRs 310. For example, the output 325-a may include predicted RSRP measurements for the second CMR 310-b, the third CMR 310-c, and the fourth CMR 310-d.

[0129] In some aspects, the time-domain downsampled channel characteristic measurements of a first number of CMRs in the set of CMRs 310 may be determined based on a periodicity P of the set of CMRs 310, an integer factor N1, or both. In other words, the periodicity may determine which subset of the set of CMRs 310 is to be measured for input 315 to the model 305 and which subset of the set of CMRs 310 is to be predicted via an output 325 of the model 305. For example, the first network node 115-d may determine a periodicity P of the set of CMRs 310 (e.g., a periodicity of a periodic or semi-persistent CSI-RS or SSB resource) and an integer factor N1 of a network configuration such that channel characteristics of a first number of CMRs / first subset of the set of CMRs 310 are identified at timings relative to each or at least some N1×P instances / measurements of the set of CMRs 310 (e.g., time-domain downsampled by a factor N1 relative to a periodic / semi-persistent CSI-RS / SSB resource set). In other words, the first network node 115 - c may determine which subset of the CMRs 310 to measure as input 315 to the model 305 based on the periodicity P (eg, 20 ms) and the integer factor N1 (which may be indicated by the second network node 105 - c ).

[0130] The first number of CMRs 310 (a first subset of CMRs 310) to be measured as input 315 to the model 305 may be equal to or less than K, where K represents the number of CMRs 310. If the first number of CMRs 310 or the first subset of CMRs 310 measured is less than K, the model 305 trained by machine learning via federated learning training may also be run or implemented at the second network node 105-c (based on L1-RSRP feedback). Additionally or alternatively, the first number of CMRs / first subset of the set of CMRs 310 to be measured as input 315 may be determined based on the best channel quality measured (e.g., strongest L1-RSRP or L1-SINR, highest CQI, maximum RI). In such cases, the input 315 of the model 305 may include an identifier (e.g., an identifier, an index, or other information indicating the identity of the CMR) of the corresponding CMR 310 measured (e.g., an identifier of a CMR 310 included in a first number of CMRs 310 / a first subset of CMRs 310 measured for the input 315). For example, the input 315-a may include an identifier associated with a first CMR 310-a measured for input to the model 305 (e.g., an identifier associated with the first CMR 310-a, an index associated with the first CMR 310-a, or other information indicating the identity of the first CMR 310-a).

[0131] Continuing with the same example, output 325-a may indicate predicted measurements for at least a portion of a second number of CMRs (e.g., a second subset) in the set of CMRs 310. For example, output 325-a may include a first predicted RSRP measurement for a second CMR 310-b, a second predicted RSRP measurement for a third CMR 310-c, and a third predicted RSRP measurement for a fourth CMR 310-d. In some cases, the first network node 115-d, the second network node 105-c, or both may utilize output 325-a (e.g., predicted time domain measurements) to select or modify parameters for performing wireless communication between respective devices.

[0132] In some aspects, the predicted channel characteristics of the second number of CMRs 310 (eg, predicted time domain characteristics of output 325 - a ) may be based on multiple factors or parameters. Specifically, which CMRs 310 are predicted via output 325 - a may be based on multiple factors or parameters.

[0133] In some cases, the predicted channel characteristics of the second number of CMRs 310 may be based on a periodicity P associated with the set of CMRs 310 (e.g., periodic or semi-persistent CSI-RS / SSB resources) and an integer factor N2 of the network configuration. In such cases, the predicted channel characteristics of the second number of CMRs 310 (e.g., output 325-a) may be identified by a timing at which a consecutive number of N2×P instances / measurements occurred relative to the set of CMRs 310, where a first predicted CMR 310 instance / timing is just after a last timing identified from a channel characteristic measurement associated with the first number of CMRs 310. For example, in some cases, the second network node 105-c may indicate the integer value N2 to the first network node 115-d, and where the integer value N2 and the periodicity P determine which CMRs 310 are to be predicted for the output 325-a via the model 305-a.

[0134] In some aspects, the second number of CMRs 310 estimated via output 325 may be equal to or less than K, where K represents the number of CMRs 310. That is, the model 305 may be configured to predict measurements for each CMR 310 or only a subset of the remaining CMRs 310. In the event that the second number of CMRs 310 predicted by the model 305 is less than K, the machine learning model 305 trained via federated learning may be run or executed at the first network node 115-d to report the predicted channel characteristics with reduced model complexity and / or reporting overhead. For example, if the model 305-a is specifically (e.g., only) configured to predict measurements for the third CMR 310-c (rather than predicting measurements for each of the CMRs 310-b, 310-c, 310-d), the model 305-a may be executed at the first network node 115-d with less power consumption and processing resources.

[0135] In addition, in some cases, the second number of CMRs 310 estimated via output 325 may be determined based on the predicted channel quality (e.g., strongest L1-RSRP, strongest L1-SINR, highest CQI, maximum RI) of the corresponding CMRs 310. In such cases, output 325 of model 305 may include an identifier of the CMR 310 reported via output 325 (e.g., an identifier associated with CMR 310, an index associated with CMR 310, or other information indicating the identity of CMR 310). For example, where model 305-a receives input 315-a, model 305-a may predict that the fourth CMR 310-d will have the best channel quality (e.g., strongest signal strength), and may therefore include a predicted measurement and identifier associated with the fourth CMR 310-d.

[0136] In some cases, the first network node 115-d may be configured to perform measurements (e.g., RSRP, RI, PMI, CQI) on the second number of CMRs 310 / a second subset of the CMRs 310, and use the measurements performed on the second number of CMRs 310 as tags 320, which are input back into the model 305 to facilitate training. For example, the first network node 115-d may measure signals received via the second CMR 310-b, and input the measurements as tags 320-a into the model 305-a. Similarly, the first network node 115-d may measure signals received via the third CMR 310-c and the fourth CMR 310-c, and input the measurements as tags 320-b and 320-c, respectively, into the model 305-a. The tags 320-a, 320-b, 320-c may include identifiers (e.g., identifiers, indices, or other information indicating the CMR identification) associated with the corresponding CMRs 310-b, 310-c, 310-d. By inputting the tags 320 into the model 305, the model 305 may be configured to compare the predicted measurements for the CMRs 310-b, 310-c, 310-d with the measurements actually performed (e.g., the tags 320-a, 320-b, 320-c) to further train and refine the model 305 to predict the time domain parameters of the CMR 310 set. For example, the tag 320-a may be compared with the predicted measurements for the CMR 310-b within the output 325-a. Similarly, the tags 320-b and 320-c may be compared with the predicted measurements for the CMRs 310-c and 310-d within the output 325-a, respectively.

[0137] In some aspects, the actual measured channel characteristics (e.g., data tags 320) associated with the predicted channel characteristics for the second number of CMRs 310 predicted via the output 325 (e.g., the predicted characteristics within the output 325) may be based on the same integer factor N2 and the channel characteristic instances, occasions, or occurrences predicted via the output 325. That is, if the model 305 is configured to predict channel characteristics for CMRs 310-b and 310-d, the first network node 115-d may be configured to input tags 320-a and 320-c corresponding to the CMRs 310-b and 310-d.

[0138] In addition, in the event that the second number of CMRs 310 predicted via output 325 is less than K, as previously discussed herein, the measured best channel quality associated with the second number of CMRs 310 (e.g., a label 320 corresponding to the strongest L1-RSRP, the strongest L1-SINR, the highest CQI, the largest RI) may be utilized to identify the actual measured channel characteristics (e.g., the label 320), wherein the label 320 may include an identifier (e.g., an identifier, an index, or other information indicating the CMR identification) corresponding to the second number of CMRs 310. That is, if the model 305 is configured to generate an output 325 that predicts the characteristics of the CMRs 310 having the two highest predicted channel qualities, the first network node 115-d may input the labels 320 corresponding to the two CMRs 310 having the two highest predicted channel qualities together with the identifiers corresponding to the respective CMRs 310.

[0139] This process of measuring signals received via CMR 310, providing the measurements as input 315 to model 305, using model 305 to generate output 325, and providing labels 320 to model 305 may be performed iteratively. Figure 3 As shown, the first network node 115-d may measure the signal received via the CMR 310-e and provide the measurement as an input 315-c to a "second version" or "trained version" of the model 305-b. In this regard, after inputting the labels 320-a, 320-b, 320-c to further train the model 305-a, the model 305-b may be considered to be an updated or trained version of the model 305-a. In addition, the measurements performed on the first CMR 310-a may additionally be provided to the model 305-b as input 315-b. In the same manner, the model 305-b may generate an output 325-b including predicted time domain measurements, which may include predicted measurements for the CMRs 310-f, 310-g, 310-h included in the second number of CMRs 310 or a second subset of the CMRs 310. Furthermore, actual measurements for the CMRs 310 - f to 310 - h may be input to the model 305 - b as labels 320 - d , 320 - e , 320 - f to further train and refine the model 305 - b .

[0140] In some implementations, the Rx beam information used by the first network node 115-d to receive signals within the corresponding CMR 310 may be additionally used for the input 315 and the label 320, and predicted via the output 325. In other words, the Rx beam information at the first network node 115-d may be used to Figure 3Model inputs, outputs, and data labels of the illustrated joint learning training process. Specifically, the Rx beams used to measure the corresponding CMRs 310 for the first number of CMRs 310 may be indicated via input 315. In addition, the output 325 of the model 305 may include predicted Rx beam information associated with the predicted channel characteristics of the second number of CMRs 310 predicted via the output 325.

[0141] For example, the first network node 115-a may receive a reference signal (e.g., CSI-RS, SSB) via a first CMR 310-a via a first Rx beam, and may indicate the first Rx beam via a first input 315-a. Similarly, the first network node 115-a may receive a reference signal (e.g., CSI-RS, SSB) via a fifth CMR 310-e via a second Rx beam, and may indicate the second Rx beam via a second input 315-b. In this example, the first output 325-a may include predicted Rx beams for CMRs 310-b, 310-c, and / or 310-d, and the second output 325-b may include predicted Rx beams for CMRs 310-f, 310-g, and / or 310-h. In some aspects, the predicted Rx beam information indicated via the output 325 may include Rx beams at the first network node 115 - d that are predicted to exhibit the best or sufficient quality to receive signals via the corresponding predicted CMRs 310 .

[0142] In addition, in the context of supervised learning, a loss function for machine learning model training may be calculated based on at least labeled data based on actually used Rx beams for receiving and measuring the second number of CMRs 310. In other words, the first network node 115-d may receive and measure signals received via CMRs 310-b to 310-d, CMRs 310-f to 310-h using the corresponding Rx beams, and may include identifiers associated with the Rx beams, which are used as inputs to the model 305 within the labels 320-a to 320-f to further train the model to accurately predict which Rx beams should be used to receive signals via the set of CMRs 310. For example, the output 325-a may predict the first Rx beam that should be used for the second CMR 310-b. Subsequently, the first network node 115-d may receive a signal via the second CMR 310-b using the second Rx beam, and may include an identifier of the second Rx beam within the label 320-a. In this regard, the model 305 - a may be configured to compare the predicted first Rx beam with the actually used second Rx beam to further train the model 305 to perform time-domain beam prediction.

[0143] In some aspects, the Rx beam information used as input / output / flag to the model 305 may be determined or indicated via implicit Rx beam information. In other words, the Rx beam information used for the input 315, output 325, and / or flag 320 may be implicitly identified based on the third number of CMRs 310 (e.g., a third number of CSI-RS / SSB resources), the SRS resource set, or both. In some aspects, the second network node 105-c may indicate the third number of CMRs 310 to be used for implicit determination of the Rx beam information.

[0144] For example, in some cases, an Rx beam for receiving a signal via a CMR 310 may be based on the corresponding CMR 310. That is, an Rx beam associated with a CMR 310 may be determined based on one or more CMRs 310 within the third number of CMRs 310, such as a CMR 310 that maximizes the L1-RSRP of the Rx beam among the third number of CMRs 310. In such a case, an input 315, an output 325, and a flag 320 of the Rx beam information may be identified based on the associated CMR 310.

[0145] By way of another example, in other cases, an Rx beam for receiving a signal via a CMR 310 may be based on SRS information in combination with the corresponding CMR 310. That is, an Rx beam associated with a CMR 310 may be determined based on one or more SRS resources associated with an SRS resource set, wherein a Tx spatial filter (at the second network node 105-c) for a corresponding SRS resource within the SRS resource set is determined by a corresponding CMR 310 in the third number of CMRs 310. In such a case, an input 315, an output 325, and a tag 320 of the Rx beam information may be identified based on the associated SRS resource.

[0146] Additionally or alternatively, the Rx beam information used as an input / output / label to the model 305 may be determined or indicated via explicit Rx beam information. In other words, the Rx beam included in the input 315, the output 325, and / or the label 320 may be explicitly identified (e.g., by the second network node 105-c) based on: Rx beamforming pre-decoder information (e.g., phase / amplitude coefficients associated with a corresponding RF chain or phase shifter), an antenna panel identifier associated with the Rx beamforming pre-decoder, an orientation of an antenna panel associated with the Rx beamforming, a target angle of arrival (AoA) and / or a zenith angle of arrival (ZoA) associated with the Rx beamforming, or any combination thereof.

[0147] As previously described herein, in some aspects, the first network node 115-d may send the trained model 305-b to the second network node 105-c. Specifically, the second network node 105-c may compile multiple trained models 305 for time-domain beam prediction from multiple network nodes, and may generate an aggregated or composite model based on the compiled locally trained models 305. In such cases, the second network node 105-c may send the aggregated / composite model to the first network node 115-d (and other network nodes) so that each network node within the wireless communication system may utilize the same trained model to predict time-domain characteristics associated with the set of CMRs 310.

[0148] Figure 4 An example of a model training procedure 400 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. In some examples, aspects of the model training procedure 400 can implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, the model training procedure 300, or any combination thereof. Specifically, the model training procedure 400 illustrates using a model 405 to perform spatial domain beam prediction, as described in reference Figure 1 – Figure 2 The above, and other aspects.

[0149] Although described in the context of time-domain beam prediction Figure 3 The illustrated model 305 is described in the context of spatial domain beam prediction. Figure 4 The illustrated model 405, but in some specific implementations, these models can be the same. In other words, in some cases, the network node (e.g., UE 115) can be configured to train a single model according to both model training procedures 300 and 400 so that the model can be used for both time domain beam prediction and space domain beam prediction.

[0150] Figure 4 The illustrated model training procedure 400 includes a first network node 115-e and a second network node 105-d, which may be examples of other network nodes described herein. Figure 4 The illustrated first network entity 115 - e may include Figure 2 Examples of UE 115 and / or network entity 115-a are shown. Similarly, Figure 4 The illustrated second network node 105 - d may include Figure 2 An example of a network entity 105, a base station and / or a first network node 105-a is illustrated.

[0151] As previously described herein, the first network node 115-e may be configured with, retrieve, download, or otherwise receive the model 405 (e.g., a federated learning model, a distributed learning model, a machine learning model). In some cases, the first network node 115-e may receive the model 405 from the second network node 105-d, an additional network node (e.g., a server), or both. The model 405 may be useful for predicting at least the time domain characteristics associated with the set of CMRs 410. In this regard, the model 405 may be used to predict the time domain characteristics associated with the set of CMRs 410. Figure 4 The illustrated set of CMRs 410 is associated. The set of CMRs 410 may include CSI-RS resources, SSB resources, or both.

[0152] For example, Figure 4 As shown, a CMR 410 set (eg, a CSI-RS / SSB resource set) may include K number of CMRs 410 with different spatial filters. In other words, Figure 4 The illustrated CMRs 410 may be separated in the spatial domain and may be associated with different spatial filters or Tx beams at the second network node 105 - d .

[0153] In this example, the first network node 115-e may be configured to receive a first number of CMRs or reference signals (e.g., CSI-RS, SSB) within a first subset of the K number of CMRs 410, perform measurements (e.g., RSRP measurements, RI, PMI, CQI) on the first number of CMRs 410, and use the measurements as input 415 to the model 405. For example, Figure 4 As shown, the first network node 115-e may perform measurements for CMRs 410 having CMR identifiers (e.g., CMR indices) 0, 4, 8, and 12. For example, the first network node 105-e may perform measurements on reference signals (e.g., CSI-RS, SSB) sent according to CMR #0, CMR #4, CMR #8, and CMR #12, and may include these measurements in the input 415 provided to the model 405.

[0154] In this example, the model 405 can be configured to generate an output 425, where the output 425 includes predicted spatial domain parameters of the CMR 410 set. For example, the output 425 can include predicted RSRP measurements for at least a portion of the CMR 410 that is not measured for the input 415. For example, the output 425 can include predicted RSRP measurements for the CMR 410 having identifiers (e.g., indices) 1–3, 5–7, 9–11, and 13–15. In this regard, the first quantity of CMR 410 associated with the input 415 can include CMR#0, 4, 8, and 12, and the second quantity of CMR 410 predicted via the output 425 can include CMR#1–3, 5–7, 9–11, and 13–15.

[0155] In some aspects, the spatial domain downsampled channel characteristic measurements of the first quantity of CMRs in the CMR 410 set that are measured for the input 415 can be determined based on an integer factor N1, where N1 < K, and K represents the number of CMR 410. Specifically, the channel characteristics of the first quantity of CMR 410 measured for the input 415 to the model 405 can include the number of instances / occurrences of the CMR 410. In other words, the CMR 410 measured for the input 415 can be spatially domain downsampled by a factor N1 with respect to the Figure 4 illustrated CMR 410 set. In this regard, in some cases, the integer factor N1 can indicate how many CMR 410 are to be measured for the input 415 (e.g., how many CMR 410 are included in the first quantity of CMR 410). In some aspects, the second network node 105-d can indicate or signal the integer factor N1 used to determine which CMR 410 are to be measured for the input 415.

[0156] Furthermore, which CMR 410 (e.g., CSI-RS resources and / or SSB resources) are included in the first quantity of CMR 410 measured for the input 415 can be further configured by the network (e.g., by the second network node 105-d). For example, in the context of a CSI-RS resource set (e.g., CMR 410 set) having CSI-RS resources 0 to 15 (e.g., K = 16) (CMR 410 having identifiers (e.g., indices) 0 to 15) and an integer factor N1 = 4 (e.g., four CMR 410 to be measured for the input 415, or the first quantity of CMR 410 equals four), the network can configure the first quantity of CMR 410 to be measured for the input 415 as CSI-RS resources 0, 4, 8, and 12 (e.g., configure the first network node 115-e to measure CMR#0, 4, 8, and 12).

[0157] Continuing with the same example, output 425 may indicate predicted measurements for at least a portion of a second number of CMRs (e.g., a second subset) in the set of CMRs 410. For example, output 425 may include a first predicted RSRP measurement for CMR 1, a second predicted RSRP measurement for CMR 2, a third predicted RSRP measurement for CMR 3, etc. In some cases, the first network node 115-e, the second network node 105-d, or both may utilize output 425 (e.g., predicted time domain measurements) to select or modify parameters for performing wireless communications between respective devices.

[0158] In some aspects, the predicted channel characteristics of the second number of CMRs 410 (eg, the predicted time domain characteristics of output 425) may be based on multiple factors or parameters. Specifically, which CMRs 410 are predicted via output 425 may be based on multiple factors or parameters.

[0159] In some cases, the second number of CMRs 410 predicted via the output 425 may include each CMR 410 in the complete set of CMRs 410, except for those CMRs included in the first number of CMRs 410 and measured for the input 415. In other words, in some cases, the output 425 may predict spatial domain parameters / characteristics of each CMR in the CMRs 410 that were not measured for the input 415, and may therefore predict spatial domain parameters for CMRs #1-3, 5-7, 9-11, and 13-15.

[0160] In additional or alternative implementations, output 425 may predict spatial domain parameters for only a portion of CMRs 410 that were not measured for input 415. In other words, the second number of CMRs 410 predicted via output 425 may include a subset of CMRs 1-3, 5-7, 9-11, and 13-15. In some aspects, which CMRs 410 are predicted via output 425 may be based on an integer factor N2 of a network configuration. Specifically, the second number of CMRs 410 predicted via output 425 may include instances / occurrences (e.g., predicting only In such a case, the integer factor N2 may be signaled by the second network node 105 - d.

[0161] Additionally or alternatively, the second number of CMRs 410 estimated via output 425 may be determined based on predicted channel qualities (e.g., strongest L1-RSRP, strongest L1-SINR, highest CQI, maximum RI) of the corresponding CMRs 410. In such cases, output 325 of model 405 may include identifiers of CMRs 410 reported via output 425 (e.g., an identifier associated with CMR 410, an index associated with CMR 410, or other information indicating the identity of CMR 410). For example, where model 405-a receives input 415, model 405 may predict that the fourth CMR 410 (CMR 3) will have the best channel quality, and may therefore include a predicted measurement and identifier associated with CMR #3. For example, in the context of a CSI-RS resource set (e.g., a set of CMRs 410) having CSI-RS resources 1 to 16 (i.e., K=16), N1=4 (e.g., four CMRs 410 to be measured for input 415, or a first number of CMRs is four), and N2=4 (e.g., four CMRs 410 predicted via output 425, or a second number of CMRs is four), the second network node 105-d may configure the first number of CSI-RS resources measured for input to include CSI-RS resources #1, 5, 9, and 13 (e.g., CMRs #1, 5, 9, and 13 are measured for input 415), and the second number of CSI-RS resources to be the four CRI-RS resources that have the strongest predicted L1-RSRP among CSI-RS resources #2–4, 6–8, 10–12, 14–16.

[0162] In some cases, the first network node 115-e may be configured to perform measurements (e.g., RSRP, RI, PMI, CQI) on a second number of CMRs 410 / a second subset of the CMRs 410, and use the measurements performed on the second number of CMRs 410 as tags 420 that are input back into the model 405 to facilitate training. For example, the first network node 115-e may measure signals received via a second CMR 410 (e.g., CMR #1), and input the measurements into the model 405 as tags 420. Similarly, the first network node 115-e may measure signals received via a third and fourth CMR 410 (e.g., CMR #2 and #3), and input the measurements into the model 405 as tags 420. The tags 420 may include identifiers associated with the respective CMRs 410 (e.g., the tags 420 for CMR #1 may include identifiers associating the tags 420 with CMR #1). As described herein, the identifier may be an index or other information indicating an association between a tag and a CMR. By inputting the tag 420 into the model 405, the model 405 may be configured to compare the predicted measurements for the CMR 410 with the measurements actually performed (e.g., the tag 420) to further train and refine the model 405 to predict the spatial domain parameters of the set of CMRs 410. For example, the tag 420 for CMR #1 is compared with the predicted measurements for CMR #1 within the output 425.

[0163] In some aspects, the actual measured channel characteristics (e.g., data tags 420) associated with the predicted channel characteristics for the second number of CMRs 410 predicted via output 425 (e.g., the predicted characteristics within output 425) may be based on the same integer factor N2 and the channel characteristic instances / opportunities predicted via output 412. That is, if model 405 is configured to predict channel characteristics for CMRs #1-3 and 9-11, first network node 115-e may be configured to input tags 420 corresponding to CMRs #1-3 and 9-11.

[0164] In addition, in the event that the second number of CMRs 410 predicted via output 425 is less than K, as previously discussed herein, the measured best channel quality associated with the second number of CMRs 410 (e.g., a label 420 corresponding to the strongest L1-RSRP, the strongest L1-SINR, the highest CQI, the largest RI) may be utilized to identify the actual measured channel characteristics (e.g., label 320), where the label 420 may include identifiers of the second number of CMRs 410. That is, if the model 405 is configured to generate an output 425 that predicts characteristics of the CMRs 410 having the two highest predicted channel qualities, the first network node 115-e may input the labels 420 corresponding to the two CMRs 410 having the two highest predicted channel qualities together with the identifiers corresponding to the respective CMRs 410.

[0165] In some implementations, the Rx beam information used by the first network node 115-e to receive the signal within the corresponding CMR 410 may be additionally used for the input 415 and the label 420, and predicted via the output 425. In other words, the Rx beam information at the first network node 115-e may be used to Figure 4 Model inputs, outputs, and data labels of the illustrated joint learning training process. Specifically, the Rx beams used to measure the corresponding CMRs 410 for the first number of CMRs 410 may be indicated via input 415. In addition, the output 425 of the model 405 may include predicted Rx beam information associated with the predicted channel characteristics of the second number of CMRs 410 predicted via output 425.

[0166] For example, the first network node 115-a may receive a reference signal (e.g., CSI-RS, SSB) via CMR#6 via a first Rx beam, and may indicate the first Rx beam via the first input 415. In this example, the output 425 may include a predicted Rx beam for CMR#6 (e.g., a predicted Rx beam predicted to exhibit the best or sufficient quality to receive a signal via CMR#6).

[0167] Furthermore, in the context of supervised learning, a loss function for machine learning model training may be calculated based on at least labeled data based on actually used Rx beams for receiving and measuring the second number of CMRs 410. In other words, the first network node 115-e may receive and measure signals received via the second number of CMRs 410 (e.g., CMR #1-3, 5-7, 9-11, and 13-15) using corresponding Rx beams, and may include identifiers associated with the Rx beams that are used as inputs to the model 405 within the label 420 to further train the model to accurately predict which Rx beams should be used to receive signals via the set of CMRs 410. In this regard, the model 405-a may be configured to compare the predicted Rx beams within the output 425 with the actually used Rx beams within the label 420 to further train the model 405 to perform spatial domain beam prediction.

[0168] In some aspects, the Rx beam information used as an input / output / indicator to the model 405 may be determined or indicated via implicit Rx beam information, explicit Rx beam information, or both, as shown in FIG. Figure 3 In this regard, the model training procedure 300 is described in detail. Figure 3 Any description associated with the use of the input, output, and labeled Rx beam information in the may additionally be understood to apply to Figure 4 , unless otherwise described herein.

[0169] As previously described herein, in some aspects, the first network node 115-e may send the trained model 405 to the second network node 105-d. Specifically, the second network node 105-d may compile multiple trained models 405 for time-domain beam prediction from multiple network nodes, and may generate an aggregated or composite model based on the compiled locally trained models 405. In such cases, the second network node 105-d may send the aggregated / composite model to the first network node 115-e (and other network nodes) so that each network node within the wireless communication system may utilize the same trained model to predict time-domain characteristics associated with the set of CMRs 410.

[0170] Figure 5An example of a process flow 500 supporting techniques for beam characteristic prediction using a joint learning process in accordance with one or more aspects of the present disclosure is shown. In some examples, aspects of the process flow 500 may implement or be implemented by aspects of the wireless communication system 100, the wireless communication system 200, the model training procedure 300, the model training procedure 400, or any combination thereof. Specifically, the process flow 500 illustrates a joint learning training process for training a model associated with a CMR set to predict time domain and / or spatial domain parameters of the CMR set, as described in reference Figure 1 – Figure 4 The above, and other aspects.

[0171] The process flow 500 may include a first network node 505-a (e.g., UE 115), a second network node 505-b (e.g., network entity 105, base station), and a third network node 505-c (e.g., server), which may be as described in reference Figure 1 – Figure 4 Examples of UE 115, network entity 105 and server are described.

[0172] In some examples, the operations illustrated by process flow 500 may be performed by hardware (e.g., including circuits, processing blocks, logic components, and other components), code executed by a processor (e.g., software), or any combination thereof. The following alternative examples may be implemented in which some of the steps are performed in an order different from the order described or not performed at all. In some cases, the steps may include additional features not mentioned below, or other steps may be added.

[0173] At 510, the first network node 505-a may receive a model for predicting temporal and / or spatial characteristics associated with a set of CMRs. In other words, the first network node 505-a may receive a model (e.g., a federated learning model, a distributed learning model, a machine learning model) corresponding to the set of CMRs, wherein the model may be used to predict temporal and / or spatial characteristics associated with the set of CMRs. The set of CMRs may include a set of CSI-RS resources, SSB resources, or both.

[0174] The first network node 505-a may receive, download, or otherwise obtain the model from the second network node 505-b, the third network node 505-c, or both. In some aspects, the model may be untrained, such that the first network node 505-a is configured to train a local model. Additionally or alternatively, the first network node 505-a may receive a trained model, such that the first network node 505-a is able to perform time domain / spatial domain prediction without any training at the first network node 505-a.

[0175] In some aspects, a model may be associated with one or more serving cells, one or more BWPs, one or more CSI resource sets, CSI reporting configurations, or any combination thereof. In some cases, the second network node 505-b, the third network node 505-c, or both may indicate (e.g., via control signaling) a serving cell, BWP, CSI resource set, and / or CSI reporting configuration associated with the model. The association between the model and the CSI reporting configuration may be configured together with the model, or signaled to the first network node 505-a separately from the model (e.g., via RRC, DCI, MAC-CE). Additionally or alternatively, the model may be configured together with a CSI reporting configuration (e.g., CSI reporting settings, CSI resource settings).

[0176] At 515, the first network node 505-a may receive a control message indicating respective numbers of CMRs or respective subsets of CMRs to be measured as inputs to the model and / or predicted as outputs of the model from the second network node 505-b, the third network node 505-c, or both. The first network node 505-a may receive the control message at 515 based on receiving the model at 510.

[0177] For example, the control message may indicate a first number of CMRs (eg, a first subset of CMRs) to be measured as input to the model. Figure 3 The illustrated first CMR 310-a and fifth CMR 310-e are to be measured for time domain prediction, or may indicate Figure 4 The illustrated CMRs #0, 4, 8, and 12 are to be measured for spatial domain prediction. Similarly, the control message may indicate a second number (eg, a second subset) of outputs to be predicted for the model. For example, the control message may indicate Figure 3 Which of the illustrated CMRs 310-b to 310-d and / or CMRs 310-f to 310-h are to be predicted as output of the model or Figure 4 Which CMRs among the illustrated CMRs #1-3, 5-7, 9-11, and 13-15 are to be predicted as the output of the model.

[0178] In some cases, the first number of CMRs / a first subset of CMRs, the second number of CMRs / a second subset of CMRs, or both may be determined based on a periodicity associated with the CMR set, an integer factor (e.g., N1, N2) indicated by the second network node 505-b, or both. For example, the first network node 505-a may determine a periodicity P of the CMR set (e.g., a periodicity of a periodic or semi-persistent CSI-RS or SSB resource) and an integer factor N1 indicated by the second network node 505-b such that channel characteristics of the first number of CMRs / a first subset of the CMR set are identified at the timing of each N1×P measurement occurrence (e.g., instance) relative to the CMR set (e.g., time domain down-sampled by a factor N1 relative to the periodic / semi-persistent CSI-RS / SSB resource set). By way of another example, in some cases, the second network node 505-b may indicate an integer value N2 to the first network node 505-b, and wherein the integer value N2 and the periodicity P determine which CMRs are to be predicted as outputs of the model.

[0179] At 520, the first network node 505-a may receive a first set of reference signals (e.g., CSI-RS, SSB) from the second network node 505-b via the first number of CMRs. The first network node 505-a may receive the first set of reference signals at 520 based on receiving the model at 510, receiving the control message at 515, or both. For example, where the control message at 515 indicates a first number of CMRs to be measured for input to the model, the first network node 505-a may receive the first set of reference signals at 520 based on the control message.

[0180] In some aspects, the first network node 505-a may receive a first set of reference signals via a first number of CMRs using a first set of Rx beams at the first network node 505-a. The first set of Rx beams used to receive the reference signals at 520 may be determined or indicated implicitly or explicitly, as previously described herein with respect to Figure 2 Furthermore, as will be described in further detail herein, the model may be configured to receive Rx beam information as input and predict Rx beam information as output.

[0181] At 525, the first network node 505-a may perform measurements on a first set of signals received at 520 via a first number of CMRs (e.g., a first subset of CMRs). In other words, the first network node 505-a may obtain first measurement information. In this regard, the first network node 505-a may perform measurements at 525 based on receiving a model at 510, receiving a control message at 515, receiving a reference signal at 520, or any combination thereof. The measurements may include RSRP measurements, SNR measurements, SINR measurements, CQI, RI, PMI, or any combination thereof.

[0182] At 530, the first network node 505-a may input the measurements performed at 525 into the model. For example, where the first network node 505-a performs RSRP measurements at 525 and determines the PMI of the first number of CMRs, the first network node 505-a may input the RSRP measurements and the PMI into the model.

[0183] Furthermore, in some implementations, the first network node 505-a may be configured to input Rx beam information into the model. In other words, the network node 505-a may input a first set of beam identifiers corresponding to a first set of beams into the model, wherein the first set of beams includes a first set of signals. For example, the first network node 505-a may input an identifier associated with a first set of Rx beams for receiving a reference signal via a first number of CMRs at 520. For example, the reference Figure 3 , the first network node 505-a may input the Rx beam for receiving the first CMR 310-a into the model 305-a. In such a case, the first network node 505-a may include an identifier indicating which Rx beams correspond to which measurements / which CMRs. Thus, the first network node 505-a may input the measurement and / or Rx beam information into the model at 530 based on receiving the model at 510, receiving the control message at 515, receiving the reference signal at 520, performing the measurement at 525, or any combination thereof.

[0184] At 535, the first network node 505-a may determine a set of parameters associated with the second number of CMRs as an output of the model. Specifically, the model may be configured to perform time domain prediction and spatial domain prediction for the second number of CMRs (e.g., a second subset of the CMRs) based on the input to the model at 530 (e.g., measurements, Rx beams). In this regard, the set of parameters associated with the second number of CMRs output from the model may include one or more predicted time domain parameters, one or more predicted spatial domain parameters, or both. In the context of predicted time domain parameters, the first number of CMRs and the second number of CMRs include CMRs associated with a first measurement occurrence (e.g., time instance) set and a second measurement occurrence (e.g., time instance) set, respectively, and the predicted time domain parameters include predicted measurements associated with the second number of CMRs within the second measurement occurrence (e.g., time instance) set. Similarly, in the context of predicted spatial domain parameters, the first number of CMRs and the second number of CMRs include CMRs associated with the first spatial filter set and the second spatial filter set at the second network node 505-b, respectively, and the predicted time domain parameters include predicted measurements associated with the second number of CMRs within the second spatial filter set.

[0185] For example, refer to Figure 3 , model 305 - a may predict measurements (eg, time domain parameters) associated with CMR 310 - b, CMR 310 - c, CMR 310 - c, or any combination thereof. Similarly, referring to Figure 4 , model 405 may predict measurements (e.g., spatial domain parameters) associated with CMR #1-3, 5-7, 9-11, and 13-15, or any combination thereof. In other words, an additional output of the model may be information including predictions of a second set of beam identifiers (e.g., spatial domain parameters) corresponding to a second set of beams (e.g., at least partially different from the first set of beams), and the second set of beams may be associated with a second number of CMRs. Furthermore, in these examples, outputs from the model may include predicted measurements associated with the second number of CMRs, including RSRP measurements, predicted RIs, predicted CQIs, predicted SNR / SINR measurements, predicted RIs, or any combination thereof.

[0186] In some aspects, the output from the model at 535 may additionally or alternatively include predicted Rx beam information associated with the second number of CMRs. For example, where the first network node 505-a inputs an Rx beam for receiving a reference signal via a first number of CMRs, the output at 535 may include a predicted Rx beam associated with the second number of CMRs (e.g., an Rx beam predicted to have the highest or sufficient quality for receiving a signal via the second number of CMRs).

[0187] At 540, the first network node 505-a may receive an additional set of reference signals (e.g., CSI-RS, SSB) from the second network node 505-b via the second number of CMRs. In other words, the first network node 505-a may receive reference signals via a second set of CMRs, which is predicted via the output at 535. The first network node 505-a may receive the additional set of reference signals at 540 based on (e.g., according to) a set of parameters indicated in the output at 535 (e.g., time domain / spatial domain prediction).

[0188] For example, refer to Figure 3 , the first network node 505-a may receive a second set of reference signals via a second set of CMRs including CMRs 310-b, 310-c, 310-c, or any combination thereof, the second set being predicted via the output at 535. Similarly, the reference Figure 4 , the first network node 505 - a may receive a second set of reference signals via a second set of CMRs including CMRs # 1–3, 5–7, 9–11, 13–15, or any combination thereof, the second set being predicted via the output at 535 .

[0189] The first network node 505-a may receive an additional set of reference signals at 540 based on receiving a model at 510, receiving a control message at 515, receiving a reference signal at 520, performing measurements at 525, providing input to the model at 530, determining a model output at 535, or any combination thereof. For example, where the output of the model at 535 includes a predicted Rx beam for the second number of CMRs, the first network node 505-a may receive the additional set of reference signals via the second number of CMRs using the predicted Rx beam. Additionally or alternatively, the first network node 505-a may use an Rx beam different from the predicted Rx beam for receiving the additional reference signal at 540.

[0190] At 545, the first network node 505-a may perform additional measurements (e.g., obtain additional measurement information) on an additional set of signals received via a second number of CMRs (e.g., a second subset of CMRs) at 540. In other words, the first network node 505-a may perform measurements on a second set of CMRs that are predicted for time / space domain parameters via the output of the model at 535. In this regard, the first network node 505-a may perform measurements at 545 based on receiving the model at 510, receiving a control message at 515, receiving a reference signal at 520, performing measurements at 525, providing input to the model at 530, determining model output at 535, receiving an additional set of reference signals at 540, or any combination thereof. Or any combination thereof. The measurements may include RSRP measurements, SNR measurements, SINR measurements, CQI, RI, PMI, or any combination thereof.

[0191] At 550, the first network node 505-a may input the additional measurements performed at 545 into the model. Specifically, the first network node 505-a may input the additional measurements into the model to further train the model. In some aspects, the first network node 505-a may input a set of identifiers associated with the additional set of measurements and the corresponding second number of channel measurement resources into the model so that the model can determine which measurements correspond to which CMRs.

[0192] For example, refer to Figure 3 , the first network node 505-a may perform additional measurements of a second number of CMRs (e.g., CMRs 310-a, 310-b, 310-c) and input the additional measurements into the model as labels 320 to further train the model to perform time domain prediction for the set of CMRs. Figure 4 , the first network node 505-a may perform additional measurements of a second number of CMRs (e.g., CMR #1-3, 5-7, 9-11, 13-15) and input the additional measurements into the model as labels 420 to further train the model to perform spatial domain prediction for the set of CMRs.

[0193] Furthermore, in some implementations, the first network node 505-a may be configured to input Rx beam information into the model. For example, the first network node 505-a may input an identifier associated with an additional Rx beam set for receiving an additional reference signal set via the second number of CMRs at 540. For example, the reference Figure 3, the first network node 505-a may input Rx beams for receiving signals via the second number of CMRs 310-b, 310-c, 310-d into the model 305-a. In such a case, the first network node 505-a may include identifiers indicating which Rx beams correspond to which measurements / which CMRs.

[0194] At 555, the first network node 505-a may send the trained model (e.g., a locally trained model) to the second network node 505-b, the third network node 505-c, or both. Specifically, the first network node 505-a may send the trained model at 555 based on performing model training at steps 545 to 550. Thus, if the first network node 505-a receives, downloads, or otherwise obtains the trained model, the first network node 505-a may avoid performing model training at 545 to 550.

[0195] At 560, the second network node 505-b, the third network node 505-c, or both may generate an aggregate / composite model based on the trained model received from the first network node 505-a at 555. Specifically, the second network node 505-b and / or the third network node 505-c may aggregate trained models from multiple network nodes 505 including the first network node 505-a, and may generate an aggregate / composite model based on the received locally trained models. Thus, the terms "aggregate model," "composite model," and the like may refer to a model based on two or more locally trained models.

[0196] At 565, the first network node 505-a may receive the aggregated / composite model generated at 560. Thus, the first network node 505-a may receive the aggregated / composite model at 565 based on (e.g., in response to) sending the locally trained model at 555. In addition, the second network node 505-b, the third network node 505-c, or both may distribute the aggregated / composite model to multiple network nodes 505 (e.g., multiple UEs 115), such as to each network node 505 that provides a locally trained model.

[0197] At 570, the first network node 505-a may use the aggregate / compound model to predict time domain characteristics, spatial domain characteristics, or both associated with the CMR set. In other words, the first network node 505-a may perform measurements associated with a first subset of the CMR set, input these measurements (and / or corresponding Rx beams) into the aggregate / compound model, and use the aggregate / compound model to predict time domain / spatial domain parameters associated with a second subset of the CMR set, as previously described herein.

[0198] Figure 6A block diagram 600 of a device 605 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 605 may be an example of aspects of a UE 115 as described herein. The device 605 may include a receiver 610, a transmitter 615, and a communication manager 620. The device 605 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0199] The receiver 610 may provide means 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 techniques for beam characteristic prediction using a joint learning process). The information may be communicated to other components of the device 605. The receiver 610 may utilize a single antenna or a collection of multiple antennas.

[0200] The transmitter 615 may provide means for transmitting signals generated by other components of the device 605. For example, the transmitter 615 may transmit information (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 techniques for beam characteristic prediction using a joint learning process). In some examples, the transmitter 615 may be co-located with the receiver 610 in a transceiver module. The transmitter 615 may utilize a single antenna or a collection of multiple antennas.

[0201] The communication manager 620, the receiver 610, the transmitter 615, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 620, the receiver 610, the transmitter 615, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0202] In some examples, the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a digital signal processor (DSP), a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured to or otherwise supports means for performing the functions described herein. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0203] Additionally or alternatively, in some examples, the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functionality of the communication manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting means for performing the functionality described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0204] In some examples, communication manager 620 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with receiver 610, transmitter 615, or both. For example, communication manager 620 may receive information from receiver 610, transmit information to transmitter 615, or be integrated in conjunction with receiver 610, transmitter 615, or both to obtain information, output information, or perform various other operations as described herein.

[0205] According to the examples disclosed herein, the communication manager 620 may support wireless communication at the first network node. For example, the communication manager 620 may be configured to or otherwise support a component for receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a channel measurement resource set. The communication manager 620 may be configured to or otherwise support a component for generating a first measurement information corresponding to a first number of channel measurement resources in the channel measurement resource set, wherein the first number of channel measurement resources corresponds to a first signal set. The communication manager 620 may be configured to or otherwise support a component for inputting the first measurement information into the first model. The communication manager 620 may be configured to or otherwise support a component for obtaining a first predicted information corresponding to a second number of channel measurement resources in the channel measurement resource set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters. The communication manager 620 may be configured to or otherwise support a component for receiving a second signal set, wherein the second number of channel measurement resources corresponds to a second signal set.

[0206] By including or configuring a communication manager 620 according to examples as described herein, a device 605 (e.g., a processor controlling a receiver 610, a transmitter 615, a communication manager 620, or a combination thereof or otherwise coupled thereto) may support techniques for reduced processing, reduced power consumption, and more efficient utilization of communication resources.

[0207] Figure 7 A block diagram 700 of a device 705 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 705 may be an example of aspects of the device 605 or UE 115 as described herein. The device 705 may include a receiver 710, a transmitter 715, and a communication manager 720. The device 705 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0208] The receiver 710 may provide means 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 techniques for beam characteristic prediction using a joint learning process). The information may be communicated to other components of the device 705. The receiver 710 may utilize a single antenna or a collection of multiple antennas.

[0209] The transmitter 715 may provide means for transmitting signals generated by other components of the device 705. For example, the transmitter 715 may transmit information (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 techniques for beam characteristic prediction using a joint learning process). In some examples, the transmitter 715 may be co-located with the receiver 710 in a transceiver module. The transmitter 715 may utilize a single antenna or a collection of multiple antennas.

[0210] The device 705 or its various components may be examples of components for performing various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 720 may include a modeling component 725, a channel measurement component 730, a signal receiving component 735, or any combination thereof. The communication manager 720 may be an example of various aspects of the communication manager 620 as described herein. In some examples, the communication manager 720 or its various components may be configured to use or otherwise cooperate with the receiver 710, the transmitter 715, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, the communication manager 720 may receive information from the receiver 710, transmit information to the transmitter 715, or be integrated with the receiver 710, the transmitter 715, or both to obtain information, output information, or perform various other operations as described herein.

[0211] According to an example as disclosed herein, the communication manager 720 may support wireless communication at a first network node. The modeling component 725 may be configured to or otherwise support a component for receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources. The channel measurement component 730 may be configured to or otherwise support a component for generating a first measurement information corresponding to a first number of channel measurement resources in the set of channel measurement resources, wherein the first number of channel measurement resources corresponds to a first signal set. The modeling component 725 may be configured to or otherwise support a component for inputting the first measurement information into the first model. The modeling component 725 may be configured to or otherwise support a component for obtaining a first predicted information corresponding to a second number of channel measurement resources in the set of channel measurement resources as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters. The signal receiving component 735 may be configured to or otherwise support a component for receiving a second signal set, wherein the second number of channel measurement resources corresponds to a second signal set.

[0212] Figure 8 A block diagram 800 of a communication manager 820 supporting techniques for beam characteristic prediction using a joint learning process in accordance with one or more aspects of the present disclosure is shown. The communication manager 820 may be an example of aspects of the communication manager 620, the communication manager 720, or both as described herein. The communication manager 820 or its various components may be examples of means for performing various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 820 may include a modeling component 825, a channel measurement component 830, a signal receiving component 835, a model sending component 840, a control information component 845, a directional beam component 850, or any combination thereof. Each of these components may communicate directly or indirectly with each other (e.g., via one or more buses).

[0213] According to examples as disclosed herein, the communication manager 820 may support wireless communication at a first network node. The modeling component 825 may be configured to or otherwise support a component for receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources. The channel measurement component 830 may be configured to or otherwise support a component for generating a first measurement information corresponding to a first number of channel measurement resources in a set of channel measurement resources, wherein the first number of channel measurement resources corresponds to a first signal set. In some examples, the modeling component 825 may be configured to or otherwise support a component for inputting the first measurement information into the first model. In some examples, the modeling component 825 may be configured to or otherwise support a component for obtaining a first predicted information corresponding to a second number of channel measurement resources in a set of channel measurement resources as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters. The signal receiving component 835 may be configured to or otherwise support a component for receiving a second signal set, wherein the second number of channel measurement resources corresponds to a second signal set.

[0214] In some examples, the channel measurement component 830 can be configured to or otherwise support means for generating second measurement information corresponding to the second number of channel measurement resources. In some examples, the modeling component 825 can be configured to or otherwise support means for training the first model using the second measurement information, wherein training the first model using the second measurement information includes inputting the second measurement information into the first model. In some examples, the model sending component 840 can be configured to or otherwise support means for sending the trained first model to the second network node.

[0215] In some examples, the modeling component 825 may be configured as or otherwise support means for receiving from the second network node a second model based on the trained first model and a third model associated with the channel measurement resource set, wherein the second model is configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the channel measurement resource set. In some examples, the modeling component 825 may be configured as or otherwise support means for obtaining second predicted information corresponding to the channel measurement resource set as an output of the second model, wherein the second predicted information includes at least one of the following: one or more time domain parameters or one or more spatial domain parameters.

[0216] In some examples, modeling component 825 may be configured to or otherwise support components for training the first model using a set of identifiers associated with a second number of channel measurement resources, wherein the set of identifiers corresponds to second measurement information, and wherein training the first model using the set of identifiers includes inputting the set of identifiers into the first model.

[0217] In some examples, control information component 845 may be configured to or otherwise support means for receiving control information from a second network node, the control information indicating at least one of: a first number of channel measurement resources or a second number of channel measurement resources.

[0218] In some examples, the first number of channel measurement resources is based on a periodicity, or the second number of channel measurement resources is based on a periodicity.

[0219] In some examples, a first number of channel measurement resources is associated with a first set of time instances. In some examples, a second number of channel measurement resources is associated with a second set of time instances different from the first set of time instances. In some examples, the one or more predicted time domain parameters include predicted measurements associated with the second number of channel measurement resources associated with the second set of time instances.

[0220] In some examples, the first number of channel measurement resources is associated with a first set of spatial filters at the second network node. In some examples, the second number of channel measurement resources is associated with a second set of spatial filters at the second network node. In some examples, the one or more predicted spatial domain parameters include predicted measurements associated with the second number of channel measurement resources sent via the second set of spatial filters at the second network node.

[0221] In some examples, the directional beam component 850 can be configured or otherwise support means for receiving a first set of beams, wherein the first set of beams includes a first set of signals corresponding to a first number of channel measurement resources. In some examples, the modeling component 825 can be configured or otherwise support means for inputting a first set of beam identifiers corresponding to the first set of beams into a first model, wherein the first predicted information is based on the first set of beam identifiers.

[0222] In some examples, the modeling component 825 can be configured to or otherwise support means for obtaining information including a second prediction of a second set of beam identifiers corresponding to a second set of beams as an additional output of the first model, the second set of beam identifiers being associated with a second number of channel measurement resources.

[0223] In some examples, the first model is associated with one or more serving cells, one or more bandwidth portions, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

[0224] In some examples, the control information component 845 may be configured as or otherwise support a component for receiving control information from a second network node, the control information indicating one or more serving cells, one or more bandwidth portions, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

[0225] In some examples, the first model includes a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0226] In some examples, receiving the first model includes receiving the first model from a second network node. In some examples, the first network node includes a UE. In some examples, the second network node includes a base station, a network entity, a server, or any combination thereof.

[0227] In some examples, the channel measurement resource set includes at least one of a channel state information reference signal resource or a synchronization signal block resource.

[0228] In some examples, reference signal received power, signal-to-noise ratio, signal-to-interference-plus-noise ratio, channel quality indicator, rank indicator, precoding matrix indicator, or any combination thereof.

[0229] In some examples, to support receiving the first model, modeling component 825 can be configured or otherwise support means for receiving a download including the first model. In some examples, to support receiving the first model, modeling component 825 can be configured or otherwise support means for receiving the first model from the second network node via control signaling, or both.

[0230] Fig. 9A diagram of a system 900 including a device 905 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 905 may be an example of a device 605, a device 705, or a UE 115 as described herein, or include components thereof. The device 905 may communicate (e.g., wirelessly) with one or more network entities 105, one or more UEs 115, or any combination thereof. The device 905 may include components for two-way voice and data communications, including components for sending and receiving communications, such as a communication manager 920, an input / output (I / O) controller 910, a transceiver 915, an antenna 925, a memory 930, a code 935, and a processor 940. These components may be electronically communicated or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 945).

[0231] I / O controller 910 can manage input and output signals of device 905. I / O controller 910 can also manage peripheral devices that are not integrated into device 905. In some cases, I / O controller 910 can represent a physical connection or port to an external peripheral device. In some cases, I / O controller 910 can utilize an operating system such as or another operating system. Additionally or alternatively, I / O controller 910 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, I / O controller 910 may be implemented as part of a processor such as processor 940. In some cases, a user may interact with device 905 via I / O controller 910 or via hardware components controlled by I / O controller 910.

[0232] In some cases, the device 905 may include a single antenna 925. However, in some other cases, the device 905 may have more than one antenna 925, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 915 may communicate bidirectionally via one or more antennas 925, a wired or wireless link, as described herein. For example, the transceiver 915 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 915 may also include a modem for modulating packets, providing the modulated packets to one or more antennas 925 for transmission, and for demodulating packets received from one or more antennas 925. The transceiver 915 or the transceiver 915 and one or more antennas 925 may be examples of transmitters 615, transmitters 715, receivers 610, receivers 710, or any combination thereof or components thereof as described herein.

[0233] The memory 930 may include random access memory (RAM) and read-only memory (ROM). The memory 930 may store computer-readable, computer-executable code 935 including instructions that, when executed by the processor 940, cause the device 905 to perform various functions described herein. The code 935 may be stored in a non-transitory computer-readable medium such as a system memory or another type of memory. In some cases, the code 935 may not be directly executable by the processor 940, but may (for example, when compiled and executed) cause the computer to perform the functions described herein. In some cases, the memory 930 may also include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0234] The processor 940 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 940 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 940. The processor 940 may be configured to execute computer-readable instructions stored in a memory (e.g., a memory 930) to cause the device 905 to perform various functions (e.g., functions or tasks that support techniques for beam characteristic prediction using a joint learning process). For example, the device 905 or a component of the device 905 may include a processor 940 and a memory 930 coupled to or coupled to the processor 940, and the processor 940 and the memory 930 are configured to perform the various functions described herein.

[0235] According to the examples disclosed herein, the communication manager 920 may support wireless communication at the first network node. For example, the communication manager 920 may be configured to or otherwise support a component for receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a channel measurement resource set. The communication manager 920 may be configured to or otherwise support a component for generating a first measurement information corresponding to a first number of channel measurement resources in the channel measurement resource set, wherein the first number of channel measurement resources corresponds to a first signal set. The communication manager 920 may be configured to or otherwise support a component for inputting the first measurement information into the first model. The communication manager 920 may be configured to or otherwise support a component for obtaining a first predicted information corresponding to a second number of channel measurement resources in the channel measurement resource set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters. The communication manager 920 may be configured to or otherwise support a component for receiving a second signal set, wherein the second number of channel measurement resources corresponds to a second signal set.

[0236] By including or configuring a communications manager 920 according to examples as described herein, the device 905 may support techniques for improved communications reliability, reduced latency, an improved user experience associated with reduced processing, reduced power consumption, more efficient utilization of communications resources, improved coordination between devices, extended battery life, and improved utilization of processing power.

[0237] In some examples, the communication manager 920 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 915, one or more antennas 925, or any combination thereof. Although the communication manager 920 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 920 may be supported or performed by the processor 940, the memory 930, the code 935, or any combination thereof. For example, the code 935 may include instructions that are executable by the processor 940 to cause the device 905 to perform various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein, or the processor 940 and the memory 930 may be otherwise configured to perform or support such operations.

[0238] Fig.10A block diagram 1000 of a device 1005 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 1005 may be an example of aspects of the network entity 105 as described herein. The device 1005 may include a receiver 1010, a transmitter 1015, and a communication manager 1020. The device 1005 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0239] Receiver 1010 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be communicated to other components of device 1005. In some examples, receiver 1010 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1010 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof.

[0240] The transmitter 1015 may provide means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1005. For example, the transmitter 1015 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) (such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units)). In some examples, the transmitter 1015 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1015 may support outputting information by sending signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1015 and the receiver 1010 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0241] The communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations thereof, or various components thereof may be examples of means for performing various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations thereof, or components thereof may support methods for performing one or more of the functions described herein.

[0242] In some examples, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microprocessor, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured to or otherwise supports means for performing the functions described herein. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0243] Additionally or alternatively, in some examples, the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functions of the communication manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting means for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0244] In some examples, communication manager 1020 may be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with receiver 1010, transmitter 1015, or both. For example, communication manager 1020 may receive information from receiver 1010, transmit information to transmitter 1015, or be integrated in conjunction with receiver 1010, transmitter 1015, or both to obtain information, output information, or perform various other operations as described herein.

[0245] According to an example as disclosed herein, the communication manager 1020 may support wireless communication at a first network node. For example, the communication manager 1020 may be configured to or otherwise support a component for sending a signal within a channel measurement resource set. The communication manager 1020 may be configured to or otherwise support a component for receiving a first trained model associated with at least a first portion of a channel measurement resource set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The communication manager 1020 may be configured to or otherwise support a component for receiving a second trained model associated with at least a second portion of a channel measurement resource set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the channel measurement resource set. The communication manager 1020 may be configured to or otherwise support a component for generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The communications manager 1020 may be configured or otherwise support means for sending an indication of the third model to at least one of the second network node or the third network node.

[0246] By including or configuring a communications manager 1020 according to examples as described herein, a device 1005 (e.g., a processor controlling a receiver 1010, a transmitter 1015, a communications manager 1020, or a combination thereof or otherwise coupled thereto) may support techniques for reduced processing, reduced power consumption, and more efficient utilization of communications resources.

[0247] Fig.11 A block diagram 1100 of a device 1105 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 1105 may be an example of aspects of the device 1005 or network entity 105 as described herein. The device 1105 may include a receiver 1110, a transmitter 1115, and a communication manager 1120. The device 1105 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0248] Receiver 1110 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be communicated to other components of device 1105. In some examples, receiver 1110 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1110 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof.

[0249] The transmitter 1115 may provide means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1105. For example, the transmitter 1115 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) (such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units)). In some examples, the transmitter 1115 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1115 may support outputting information by sending signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1115 and the receiver 1110 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0250] The device 1105 or its various components may be examples of components for performing various aspects of the technology for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 1120 may include a signal transmission component 1125, a modeling component 1130, or any combination thereof. The communication manager 1120 may be an example of various aspects of the communication manager 1020 as described herein. In some examples, the communication manager 1120 or its various components may be configured to use or otherwise cooperate with the receiver 1110, the transmitter 1115, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, the communication manager 1120 may receive information from the receiver 1110, transmit information to the transmitter 1115, or be integrated with the receiver 1110, the transmitter 1115, or both to obtain information, output information, or perform various other operations as described herein.

[0251] According to an example as disclosed herein, the communication manager 1120 may support wireless communication at a first network node. The signal transmission component 1125 may be configured to or otherwise support a component for transmitting a signal within a channel measurement resource set. The modeling component 1130 may be configured to or otherwise support a component for receiving a first trained model associated with at least a first portion of a channel measurement resource set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The modeling component 1130 may be configured to or otherwise support a component for receiving a second trained model associated with at least a second portion of a channel measurement resource set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the channel measurement resource set. The modeling component 1130 may be configured to or otherwise support a component for generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The modeling component 1130 may be configured to or otherwise support means for sending an indication of the third model to at least one of the second network node or the third network node.

[0252] Fig.12 A block diagram 1200 of a communication manager 1220 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The communication manager 1220 may be an example of aspects of the communication manager 1020, the communication manager 1120, or both as described herein. The communication manager 1220 or its various components may be examples of means for performing various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein. For example, the communication manager 1220 may include a signaling component 1225, a modeling component 1230, a control information component 1235, or any combination thereof. Each of these components may communicate with each other directly or indirectly (e.g., via one or more buses), which may include communication within a protocol layer of a protocol stack, communication associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with the network entity 105, between devices, components, or virtualized components associated with the network entity 105), or any combination thereof.

[0253] According to examples as disclosed herein, the communication manager 1220 may support wireless communication at a first network node. The signal transmission component 1225 may be configured to or otherwise support a component for transmitting a signal within a channel measurement resource set. The modeling component 1230 may be configured to or otherwise support a component for receiving a first trained model associated with at least a first portion of a channel measurement resource set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. In some examples, the modeling component 1230 may be configured to or otherwise support a component for receiving a second trained model associated with at least a second portion of a channel measurement resource set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the channel measurement resource set. In some examples, the modeling component 1230 may be configured to or otherwise support a component for generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. In some examples, modeling component 1230 can be configured or otherwise support means for sending an indication of the third model to at least one of the second network node or the third network node.

[0254] In some examples, control information component 1235 may be configured as or otherwise support a component for sending control information to a second network node, the control information indicating at least one of: a first number of channel measurement resources in a set of channel measurement resources or a second number of channel measurement resources in a set of channel measurement resources, wherein the first trained model is trained based on a subset of signals sent within the first number of channel measurement resources.

[0255] In some examples, a periodicity is associated with the set of channel measurement resources. In some examples, at least one of the first number of channel measurement resources or the second number of channel measurement resources is based on the periodicity.

[0256] In some examples, the third model is associated with one or more serving cells, one or more bandwidth parts, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

[0257] In some examples, control information component 1235 may be configured as or otherwise support a component for sending control information to at least one of the second network node or the third network node, the control information indicating one or more serving cells, one or more bandwidth portions, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

[0258] In some examples, the third model includes a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0259] In some examples, at least one of the second network node or the third network node includes a corresponding UE. In some examples, the first network node includes a base station, a network entity, a server, or any combination thereof.

[0260] In some examples, the channel measurement resource set includes at least one of a channel state information reference signal resource or a synchronization signal block resource.

[0261] In some examples, the first portion of the channel measurement resource set is the same as the second portion of the channel measurement resource set.

[0262] Fig.13 A diagram of a system 1300 including a device 1305 supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The device 1305 may be an example of a device 1005, a device 1105, or a network entity 105 as described herein, or include components thereof. The device 1305 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, which communication may include communication through one or more wired interfaces, through one or more wireless interfaces, or any combination thereof. The device 1305 may include components that support output and acquisition of communications, such as a communication manager 1320, a transceiver 1310, an antenna 1315, a memory 1325, a code 1330, and a processor 1335. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1340).

[0263] The transceiver 1310 may support bidirectional communication via a wired link, a wireless link, or both, as described herein. In some examples, the transceiver 1310 may include a wired transceiver and may communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, the transceiver 1310 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1305 may include one or more antennas 1315 that may be capable of (e.g., concurrently) sending or receiving wireless transmissions. The transceiver 1310 may also include a modem for modulating a signal, for providing a modulated signal for transmission (e.g., by one or more antennas 1315, by a wired transmitter), for receiving a modulated signal (e.g., from one or more antennas 1315, from a wired receiver), and for demodulating a signal. The transceiver 1310 or the transceiver 1310 and one or more antennas 1315 or a wired interface (where applicable) may be an example of a transmitter 1015, a transmitter 1115, a receiver 1010, a receiver 1110, or any combination thereof or any component thereof as described herein. In some examples, the transceiver may be operable to support communication via one or more communication links (e.g., communication link 125, backhaul communication link 120, midhaul communication link 162, fronthaul communication link 168).

[0264] Memory 1325 may include RAM and ROM. Memory 1325 may store computer-readable, computer-executable code 1330 including instructions that, when executed by processor 1335, cause device 1305 to perform various functions described herein. Code 1330 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1330 may not be directly executable by processor 1335, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, memory 1325 may also contain, among other things, a BIOS that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0265] The processor 1335 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA, a microcontroller, a programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof). In some cases, the processor 1335 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1335. The processor 1335 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1325) to cause the device 1305 to perform various functions (e.g., functions or tasks that support techniques for beam characteristic prediction using a joint learning process). For example, the device 1305 or a component of the device 1305 may include a processor 1335 and a memory 1325 coupled to the processor 1335, and the processor 1335 and the memory 1325 are configured to perform the various functions described herein. Processor 1335 can be an example of a cloud computing platform (e.g., one or more physical nodes and supporting software such as an operating system, virtual machine, or container instance) that can host functionality for performing functions of device 1305 (e.g., by executing code 1330).

[0266] In some examples, bus 1340 may support communications of a protocol layer (e.g., within a protocol layer) of a protocol stack. In some examples, bus 1340 may support communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within a component of device 1305 or communications performed between different components of device 1305 that may be co-located or located in different locations (e.g., where device 1305 may refer to a system in which one or more of communication manager 1320, transceiver 1310, memory 1325, code 1330, and processor 1335 may be located in one of the different components or divided between the different components).

[0267] In some examples, network communications manager 1320 may manage aspects of communications with core network 130 (e.g., via one or more wired or wireless backhaul links). For example, communications manager 1320 may manage delivery of data communications for client devices such as one or more UEs 115. In some examples, communications manager 1320 may manage communications with other network entities 105 and may include a controller or scheduler for controlling communications with UE 115 in coordination with other network entities 105. In some examples, communications manager 1320 may support an X2 interface within an LTE / LTE-A wireless communications network technology to provide communications between network entities 105.

[0268] According to an example as disclosed herein, the communication manager 1320 may support wireless communication at a first network node. For example, the communication manager 1320 may be configured to or otherwise support a component for sending a signal within a channel measurement resource set. The communication manager 1320 may be configured to or otherwise support a component for receiving a first trained model associated with at least a first portion of a channel measurement resource set from a second network node, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The communication manager 1320 may be configured to or otherwise support a component for receiving a second trained model associated with at least a second portion of a channel measurement resource set from a third network node, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the channel measurement resource set. The communication manager 1320 may be configured to or otherwise support a component for generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The communications manager 1320 may be configured or otherwise support means for sending an indication of the third model to at least one of the second network node or the third network node.

[0269] By including or configuring a communications manager 1320 according to examples as described herein, the device 1305 may support techniques for improved communications reliability, reduced latency, an improved user experience associated with reduced processing, reduced power consumption, more efficient utilization of communications resources, improved coordination between devices, extended battery life, and improved utilization of processing power.

[0270] In some examples, the communication manager 1320 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the transceiver 1310, one or more antennas 1315 (e.g., where applicable), or any combination thereof. Although the communication manager 1320 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1320 may be supported or performed by the processor 1335, the memory 1325, the code 1330, the transceiver 1310, or any combination thereof. For example, the code 1330 may include instructions that are executable by the processor 1335 to cause the device 1305 to perform various aspects of the techniques for beam characteristic prediction using a joint learning process as described herein, or the processor 1335 and the memory 1325 may be otherwise configured to perform or support such operations.

[0271] Fig.14A flowchart illustrating a method 1400 for supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The operations of the method 1400 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1400 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 9 The UE 115 described herein may be executed. In some examples, the UE may execute a set of instructions to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0272] At 1405, the method may include: receiving a first model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources. The operations of 1405 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1405 may be performed as described in reference Figure 8 The modeling component 825 is used to perform the above.

[0273] At 1410, the method may include generating first measurement information corresponding to a first number of channel measurement resources in a set of channel measurement resources, wherein the first number of channel measurement resources corresponds to a first signal set. The operations of 1410 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1410 may be performed as described in reference to Figure 8 The channel measurement component 830 is used to perform.

[0274] At 1415, the method may include: inputting the first measurement information into the first model. The operations of 1415 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1415 may be performed as described in reference Figure 8 The modeling component 825 is used to perform the above.

[0275] At 1420, the method may include: obtaining first predicted information corresponding to a second number of channel measurement resources in the channel measurement resource set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted space domain parameters. The operation of 1420 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1420 may be performed as described in reference Figure 8 The modeling component 825 is used to perform the above.

[0276] At 1425, the method may include: receiving a second signal set, wherein the second number of channel measurement resources corresponds to the second signal set. The operations of 1425 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1425 may be performed as described in reference Figure 8The signal receiving component 835 is used to execute.

[0277] Fig.15 A flow chart illustrating a method 1500 for supporting techniques for beam characteristic prediction using a joint learning process according to one or more aspects of the present disclosure is shown. The operations of the method 1500 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1500 may be implemented by a network entity or a component thereof as described herein. Figures 1 to 5 as well as Figures 10 to 13 In some examples, the network entity may execute an instruction set to control the functional elements of the network entity to perform the described functions. Additionally or alternatively, the network entity may use dedicated hardware to perform various aspects of the described functions.

[0278] At 1505, the method may include: sending a signal within a channel measurement resource set. The operations of 1505 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1505 may be performed as described in reference Fig.12 The signal sending component 1225 is used to execute.

[0279] At 1510, the method may include: receiving from a second network node a first trained model associated with at least a first portion of a set of channel measurement resources, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the set of channel measurement resources. The operations of 1510 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1510 may be performed as described in reference Fig.12 The modeling component 1230 is used to perform.

[0280] At 1515, the method may include: receiving from a third network node a second trained model associated with at least a second portion of the set of channel measurement resources, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the set of channel measurement resources. The operations of 1515 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1515 may be performed as described in reference Fig.12 The modeling component 1230 is used to perform.

[0281] At 1520, the method may include: generating a third model based on the first trained model and the second trained model, the third model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the channel measurement resource set. The operations of 1520 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1520 may be performed as described in reference Fig.12 The modeling component 1230 is used to perform.

[0282] At 1525, the method may include sending an indication of the third model to at least one of the second network node or the third network node. The operations of 1525 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1525 may be performed as described in reference to Fig.12 The modeling component 1230 is used to perform.

[0283] The following provides an overview of various aspects of the disclosure:

[0284] Aspect 1: A method for performing wireless communication at a first network node, comprising: receiving a first model, the first model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a CMR set; generating first measurement information corresponding to a first number of CMRs in the CMR set, wherein the first number of CMRs corresponds to a first signal set; inputting the first measurement information into the first model; obtaining first predicted information corresponding to a second number of CMRs in the CMR set as an output of the first model, wherein the first predicted information includes at least one of the following: one or more predicted time domain parameters or one or more predicted spatial domain parameters; and receiving a second signal set, wherein the second number of CMRs corresponds to the second signal set.

[0285] Aspect 2: The method according to Aspect 1 also includes: generating second measurement information corresponding to the second number of CMRs; using the second measurement information to train the first model, wherein training the first model using the second measurement information includes inputting the second measurement information into the first model; and sending the trained first model to a second network node.

[0286] Aspect 3: The method according to Aspect 2 further includes: receiving a second model based on the trained first model and a third model associated with the CMR set from the second network node, wherein the second model is configured to predict at least one of the time domain characteristics or the spatial domain characteristics of the CMR set; and obtaining second predicted information corresponding to the CMR set as an output of the second model, wherein the second predicted information includes at least one of the following: one or more time domain parameters or one or more spatial domain parameters.

[0287] Aspect 4: The method according to any one of Aspects 2 to 3 further includes: training the first model using a set of identifiers associated with the second number of CMRs, wherein the set of identifiers corresponds to the second measurement information, and wherein training the first model using the set of identifiers includes inputting the set of identifiers into the first model.

[0288] Aspect 5: The method according to any one of aspects 1 to 4, further comprising: receiving control information from a second network node, the control information indicating at least one of: the first number of CMRs or the second number of CMRs.

[0289] Aspect 6: The method according to any one of aspects 1 to 5, wherein a periodicity is associated with the set of CMRs, and wherein at least one of the following: the first number of CMRs is based on the periodicity, or the second number of CMRs is based on the periodicity.

[0290] Aspect 7: A method according to any one of Aspects 1 to 6, wherein the first number of CMRs is associated with a first set of time instances, and the second number of CMRs is associated with a second set of time instances different from the first set of time instances, and the one or more predicted time domain parameters include predicted measurements associated with the second number of CMRs associated with the second set of time instances.

[0291] Aspect 8: A method according to any one of Aspects 1 to 7, wherein the first number of CMRs is associated with a first spatial filter set at a second network node, and the second number of CMRs is associated with a second spatial filter set at the second network node, and the one or more predicted spatial domain parameters include predicted measurements associated with the second number of CMRs sent via the second spatial filter set at the second network node.

[0292] Aspect 9: The method according to any one of Aspects 1 to 8 further includes: receiving a first beam set, wherein the first beam set includes the first signal set corresponding to the first number of CMRs; and inputting a first beam identifier set corresponding to the first beam set into the first model, wherein the first predicted information is based on the first beam identifier set.

[0293] Aspect 10: The method according to Aspect 9 further includes: obtaining second predicted information including a second set of beam identifiers corresponding to a second set of beams as an additional output of the first model, wherein the second set of beam identifiers is associated with the second number of CMRs.

[0294] Aspect 11: A method according to any one of Aspects 1 to 10, wherein the first model is associated with one or more serving cells, one or more bandwidth parts, one or more CMR sets, a channel state information reporting configuration, or any combination thereof.

[0295] Aspect 12: The method according to Aspect 11 further includes: receiving control information from a second network node, the control information indicating the one or more serving cells, the one or more bandwidth parts, the one or more CMR sets, the channel state information reporting configuration, or any combination thereof.

[0296] Aspect 13: The method according to any one of Aspects 1 to 12, wherein the first model comprises a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0297] Aspect 14: A method according to any one of Aspects 1 to 13, wherein receiving the first model comprises receiving the first model from a second network node, the first network node comprises a UE, and the second network node comprises a base station, a network entity, a server, or any combination thereof.

[0298] Aspect 15: The method according to any one of aspects 1 to 14, wherein the CMR set includes at least one of the following: a channel state information reference signal resource or a synchronization signal block resource.

[0299] Aspect 16: A method according to any one of Aspects 1 to 15, wherein at least one of the first measurement information, the one or more time domain parameters of the first predicted information, and the one or more predicted spatial domain parameters of the first predicted information includes a reference signal received power, a signal-to-noise ratio, a signal-to-interference-plus-noise ratio, a channel quality indicator, a rank indicator, a pre-decoding matrix indicator, or any combination thereof.

[0300] Aspect 17: A method according to any one of Aspects 1 to 16, wherein the first model comprises a trained model, and wherein receiving the first model comprises: receiving a download comprising the first model; or receiving the first model from a second network node via control signaling, or both.

[0301] Aspect 18: A method for wireless communication at a first network node, comprising: sending a signal within a CMR set; receiving a first trained model associated with at least a first portion of the CMR set from a second network node, the first trained model being configured to predict at least one of time domain characteristics or spatial domain characteristics associated with the CMR set; receiving a second trained model associated with at least a second portion of the CMR set from a third network node, the second trained model being configured to predict at least one of time domain characteristics or spatial domain characteristics of the CMR set; generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of time domain characteristics or spatial domain characteristics associated with the CMR set; and sending an indication of the third model to at least one of the second network node or the third network node.

[0302] Aspect 19: The method according to Aspect 18 further includes: sending control information to the second network node, the control information indicating at least one of the following: a first number of CMRs in the CMR set or a second number of CMRs in the CMR set, wherein the first trained model is trained at least in part based on a subset of the signals sent within the first number of CMRs.

[0303] Aspect 20: The method according to aspect 19, wherein a periodicity is associated with the set of CMRs, and at least one of the first number of CMRs or the second number of CMRs is based on the periodicity.

[0304] Aspect 21: A method according to any one of aspects 18 to 20, wherein the third model is associated with one or more serving cells, one or more bandwidth parts, one or more CMR sets, a channel state information reporting configuration, or any combination thereof.

[0305] Aspect 22: The method according to Aspect 21 also includes: sending control information to at least one of the second network node or the third network node, the control information indicating the one or more service cells, the one or more bandwidth parts, the one or more CMR sets, the channel state information reporting configuration, or any combination thereof.

[0306] Aspect 23: The method according to any one of Aspects 18 to 22, wherein the third model comprises a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

[0307] Aspect 24: The method according to any one of aspects 18 to 23, wherein at least one of the second network node or the third network node comprises a corresponding UE, and the first network node comprises a base station, a network entity, a server, or any combination thereof.

[0308] Aspect 25: The method according to any one of aspects 18 to 24, wherein the CMR set includes at least one of the following: a channel state information reference signal resource or a synchronization signal block resource.

[0309] Aspect 26: The method according to any one of aspects 18 to 25, wherein the first part of the CMR set is the same as the second part of the CMR set.

[0310] Aspect 27: A first network node for wireless communication, comprising: a memory; and at least one processor coupled to the memory, the at least one processor being configured to perform the method according to any one of aspects 1 to 17.

[0311] Aspect 28: An apparatus for wireless communication at a first network node, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 1 to 17.

[0312] Aspect 29: An apparatus for wireless communication at a first network node, comprising at least one means for performing a method according to any one of aspects 1 to 17.

[0313] Aspect 30: A non-transitory computer-readable medium storing code for wireless communication at a first network node, the code comprising instructions executable by a processor to perform the method according to any one of aspects 1 to 17.

[0314] Aspect 31: A first network node for wireless communication, comprising: a memory; and at least one processor coupled to the memory, the at least one processor being configured to perform the method according to any one of aspects 18 to 26.

[0315] Aspect 32: An apparatus for wireless communication at a first network node, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to any one of Aspects 18 to 26.

[0316] Aspect 33: An apparatus for wireless communication at a first network node, comprising at least one means for performing a method according to any one of aspects 18 to 26.

[0317] Aspect 34: A non-transitory computer-readable medium storing code for wireless communication at a first network node, the code comprising instructions executable by a processor to perform the method according to any one of aspects 18 to 26.

[0318] The above methods describe possible implementations, and the operations and steps may be rearranged or otherwise modified, and other implementations are possible. In addition, aspects from two or more methods may be combined.

[0319] Although aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for example purposes, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used in much of the description, the techniques described herein may also be applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the described techniques may be applicable to various other wireless communication systems, such as Ultra Mobile Broadband (UMB), Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0320] The information and signals described herein may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the specification may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0321] The various illustrative blocks and components described in conjunction with the disclosure herein may be implemented or performed with a general purpose processor, 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. A general purpose processor may be a microprocessor, but in an alternative, the processor may be any processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in combination with a DSP core, or any other such configuration).

[0322] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions may be stored on or sent via a computer-readable medium as one or more instructions or codes. Other examples and specific implementations are within the scope of the present disclosure and claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these items. Features that implement the functions may also be physically located at different locations, including being distributed so that the functions are implemented at different physical locations.

[0323] Computer-readable medium includes both non-transient computer storage medium and communication medium, and it includes any medium that facilitates the transfer of computer program from one place to another place.Non-transient storage medium can be any available medium that can be accessed by general or special-purpose computer.By way of example and not limitation, non-transient computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage device, disk storage device or other magnetic storage device, or can be used for carrying or storing the desired program code member in the form of instruction or data structure and can be accessed by general or special-purpose computer or general or special-purpose processor Any other non-transient medium.In addition, any connection is appropriately referred to as computer-readable medium.For example, if software is sent from website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology such as infrared, radio and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL or wireless technology such as infrared, radio and microwave are included in the definition of computer-readable medium. As used herein, disk and disc include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.

[0324] As used herein (including in the claims), "or" used in a list of items (e.g., a list of items preceded by a phrase such as "at least one of" or "one or more of") indicates an inclusive list, so that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). In addition, as used herein, the phrase "based on" should not be interpreted as referring to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, a condition, a factor, etc.) should be interpreted as "based on at least A" unless specifically stated differently.

[0325] The term "determining" encompasses a wide variety of actions, and thus, "determining" may include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, database or other data structure), ascertaining, etc. Additionally, "determining" may include receiving (such as receiving information), accessing (such as accessing data in a memory), etc. Additionally, "determining" may include resolving, obtaining, selecting, choosing, establishing, and other such similar actions.

[0326] In the drawings, similar components or features may have the same reference label. In addition, various components of the same type may be distinguished by following the reference label with a dash and a second label to distinguish between the similar components. If only the first reference label is used in the specification, the description may apply to any of the similar components having the same first reference label, regardless of the second or other subsequent reference labels.

[0327] The description set forth herein describes example configurations in conjunction with the accompanying drawings and does not represent all examples that may be implemented or within the scope of the claims. The terms "aspect" or "example" used herein mean "serving as an aspect, example, instance, or illustration," rather than "preferred" or "having advantages over other aspects." The specific implementation includes specific details for providing an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some instances, structures and devices are shown in block diagram form to avoid obscuring the concepts of the examples.

[0328] The description herein is provided to enable one of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to one of ordinary skill in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A first network node for wireless communication, comprising: Memory; and at least one processor coupled to the memory, wherein the at least one processor is configured to: receiving a first model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources; generating first measurement information corresponding to a first number of channel measurement resources in the channel measurement resource set, wherein the first number of channel measurement resources corresponds to a first signal set; inputting the first measurement information into the first model; Obtaining first predicted information corresponding to a second number of channel measurement resources in the set of channel measurement resources as an output of the first model, wherein the first predicted information comprises at least one of the following: one or more predicted time domain parameters or one or more predicted space domain parameters; as well as A second signal set is received, wherein the second number of channel measurement resources corresponds to the second signal set.

2. The first network node according to claim 1, wherein the at least one processor is further configured to: generating second measurement information corresponding to the second number of channel measurement resources; training the first model using the second measurement information, wherein in order to train the first model using the second measurement information, the at least one processor is configured to input the second measurement information into the first model; and The trained first model is sent to a second network node.

3. The first network node of claim 2, wherein the at least one processor is further configured to: receiving, from the second network node, a second model based on the trained first model and a third model associated with the set of channel measurement resources, wherein the second model is configured to predict at least one of a time domain characteristic or a space domain characteristic of the set of channel measurement resources; and Second predicted information corresponding to the channel measurement resource set is obtained as an output of the second model, wherein the second predicted information includes at least one of the following: one or more time domain parameters or one or more space domain parameters.

4. The first network node of claim 2, wherein the at least one processor is further configured to: The first model is trained using a set of identifiers associated with the second number of channel measurement resources, wherein the set of identifiers corresponds to the second measurement information, and wherein in order to train the first model using the set of identifiers, the at least one processor is configured to input the set of identifiers into the first model.

5. The first network node of claim 1 , wherein the at least one processor is further configured to: Control information is received from a second network node, the control information indicating at least one of: the first number of channel measurement resources or the second number of channel measurement resources.

6. The first network node of claim 1 , wherein periodicity is associated with the set of channel measurement resources, and wherein at least one of the following: The first number of channel measurement resources is based on the periodicity, or the second number of channel measurement resources is based on the periodicity.

7. The first network node according to claim 1, wherein: The first number of channel measurement resources is associated with a first set of time instances, and wherein the second number of channel measurement resources is associated with a second set of time instances different from the first set of time instances; and The one or more predicted time domain parameters include predicted measurements associated with the second number of channel measurement resources associated with the second set of time instances.

8. The first network node according to claim 1, wherein: The first number of channel measurement resources is associated with a first set of spatial filters at a second network node, and wherein the second number of channel measurement resources is associated with a second set of spatial filters at the second network node, and The one or more predicted spatial domain parameters include predicted measurements associated with the second number of channel measurement resources sent via the second set of spatial filters at the second network node.

9. The first network node of claim 1 , wherein the at least one processor is further configured to: receiving a first beam set, wherein the first beam set includes the first signal set corresponding to the first number of channel measurement resources; and A first set of beam identifiers corresponding to the first set of beams is input into the first model, wherein information for the first prediction is based on the first set of beam identifiers.

10. The first network node of claim 9, wherein the at least one processor is further configured to: Information including a second prediction of a second set of beam identifiers corresponding to a second set of beam identifiers associated with the second number of channel measurement resources is obtained as an additional output of the first model.

11. The first network node of claim 1, wherein the first model is associated with one or more serving cells, one or more bandwidth parts, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

12. The first network node of claim 11, wherein the at least one processor is further configured to: Control information is received from a second network node, the control information indicating the one or more serving cells, the one or more bandwidth parts, the one or more channel measurement resource sets, the channel state information reporting configuration, or any combination thereof.

13. The first network node of claim 1, wherein the first model comprises a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

14. The first network node of claim 1, wherein to receive the first model, the at least one processor is configured to receive the first model from a second network node, wherein the first network node comprises a user equipment (UE), and wherein the second network node comprises a base station, a network entity, a server, or any combination thereof.

15. The first network node according to claim 1, wherein the set of channel measurement resources comprises at least one of the following: channel state information reference signal resources or synchronization signal block resources.

16. The first network node according to claim 1, wherein at least one of the first measurement information, the one or more time domain parameters of the first predicted information, and the one or more predicted space domain parameters of the first predicted information comprises: Reference signal received power, signal-to-noise ratio, signal-to-interference-plus-noise ratio, channel quality indicator, rank indicator, precoding matrix indicator, or any combination thereof.

17. The first network node of claim 1, wherein the first model comprises a trained model, and wherein to receive the first model, the at least one processor is configured to: receiving a download comprising said first model; or The first model is received from a second network node via control signaling, or both.

18. A first network node for wireless communication, comprising: Memory; and at least one processor coupled to the memory, wherein the at least one processor is configured to: Sending a signal within a channel measurement resource set; receiving, from a second network node, a first trained model associated with at least a first portion of the set of channel measurement resources, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the set of channel measurement resources; receiving, from a third network node, a second trained model associated with at least a second portion of the set of channel measurement resources, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the set of channel measurement resources; generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the set of channel measurement resources; as well as An indication of the third model is sent to at least one of the second network node or the third network node.

19. The first network node of claim 18, wherein the at least one processor is further configured to: Control information is sent to the second network node, the control information indicating at least one of: a first number of channel measurement resources in the channel measurement resource set or a second number of channel measurement resources in the channel measurement resource set, wherein the first trained model is trained based on a subset of the signals sent within the first number of channel measurement resources.

20. The first network node of claim 19, wherein a periodicity is associated with the set of channel measurement resources, and wherein at least one of the first number of channel measurement resources or the second number of channel measurement resources is based on the periodicity.

21. The first network node of claim 18, wherein the third model is associated with one or more serving cells, one or more bandwidth parts, one or more channel measurement resource sets, a channel state information reporting configuration, or any combination thereof.

22. The first network node of claim 21, wherein the at least one processor is further configured to: Sending control information to at least one of the second network node or the third network node, the control information indicating the one or more serving cells, the one or more bandwidth parts, the one or more channel measurement resource sets, the channel state information reporting configuration, or any combination thereof.

23. The first network node of claim 18, wherein the third model comprises a federated learning model, a distributed learning model, a machine learning model, or any combination thereof.

24. The first network node of claim 18, wherein at least one of the second network node or the third network node comprises a respective user equipment (UE), and wherein the first network node comprises a base station, a network entity, a server, or any combination thereof.

25. The first network node according to claim 18, wherein the set of channel measurement resources comprises at least one of the following: channel state information reference signal resources or synchronization signal block resources.

26. The first network node of claim 18, wherein the first portion of the set of channel measurement resources is the same as the second portion of the set of channel measurement resources.

27. A method for wireless communication at a first network node, comprising: receiving a first model configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with a set of channel measurement resources; generating first measurement information corresponding to a first number of channel measurement resources in the channel measurement resource set, wherein the first number of channel measurement resources corresponds to a first signal set; inputting the first measurement information into the first model; Obtaining first predicted information corresponding to a second number of channel measurement resources in the set of channel measurement resources as an output of the first model, wherein the first predicted information comprises at least one of the following: one or more predicted time domain parameters or one or more predicted space domain parameters; as well as A second signal set is received, wherein the second number of channel measurement resources corresponds to the second signal set.

28. The method according to claim 27, further comprising: generating second measurement information corresponding to the second number of channel measurement resources; Using the second measurement information to train the first model, wherein using the second measurement information to train the first model comprises inputting the second measurement information into the first model; as well as The trained first model is sent to a second network node.

29. A method for wireless communication at a first network node, comprising: Sending a signal within a channel measurement resource set; receiving, from a second network node, a first trained model associated with at least a first portion of the set of channel measurement resources, the first trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the set of channel measurement resources; receiving, from a third network node, a second trained model associated with at least a second portion of the set of channel measurement resources, the second trained model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic of the set of channel measurement resources; generating a third model based on the first trained model and the second trained model, the third model being configured to predict at least one of a time domain characteristic or a spatial domain characteristic associated with the set of channel measurement resources; as well as An indication of the third model is sent to at least one of the second network node or the third network node.

30. The method of claim 29, further comprising: Control information is sent to the second network node, the control information indicating at least one of: a first number of channel measurement resources in the channel measurement resource set or a second number of channel measurement resources in the channel measurement resource set, wherein the first trained model is trained based on a subset of the signals sent within the first number of channel measurement resources.

Images