Centralized machine learning model configuration

By using a centralized core network entity management machine learning model and leveraging AMF entities for signaling forwarding, the problem of low efficiency in configuring machine learning models at the UE in wireless communication systems is solved. This enables collaborative optimization between the UE and the core network, improving the efficiency of network management and device management.

CN118985143APending Publication Date: 2024-11-19QUALCOMM INC
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202280093999.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-03-31
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In existing wireless communication systems, the configuration and management of machine learning models at the user equipment (UE) are inefficient, and the collaborative optimization capabilities of the UE and the core network cannot be effectively utilized.

Method used

A centralized core network entity management machine learning model is adopted, and signaling forwarding is performed through the AMF entity to realize the configuration and analysis of machine learning models between UE and centralized core network entity, and support the execution of analysis at UE to improve network optimization efficiency.

Benefits of technology

It improves the collaborative optimization capabilities between the UE and the core network, increases the amount of information in network management and device management, achieves more efficient network selection and load management, and reduces latency and network load.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118985143A_ABST
    Figure CN118985143A_ABST
Patent Text Reader

Abstract

Methods, systems, and devices for wireless communication are described. The UE may be configured with a machine learning model by a core network to perform analysis, training, or inference. The UE may indicate capability information to a core network entity, the capability information including a list of machine learning models supported at the UE. A centralized core network entity may manage different machine learning models, and may communicate information about the machine learning models to the UE, such as by another core network entity. The UE or the core network may initiate the configuration. For example, the UE may request to be configured with a machine learning model. The core network may transmit control signaling to the UE indicating a configuration for the machine learning model. The UE may perform an analysis based on the machine learning model.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0001] The following relates to wireless communications, including machine learning model management.

[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 or one or more network access nodes, each base station or network access node simultaneously supporting communication of multiple communication devices, which may be further referred to as user equipment (UE). Summary of the invention

[0003] A method for wireless communication at a UE is described. The method may include: sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity; receiving control signaling from the first core network entity indicating configuration for a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model; and performing analysis based on the machine learning model.

[0004] An apparatus for wireless communication at a UE is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to: send an indication of a first set of one or more machine learning models supported at the UE to a first core network entity; receive control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model; and perform analysis based on the machine learning model.

[0005] Another apparatus for wireless communication at a UE is described. The apparatus may include: a component for sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity; a component for receiving control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model; and a component for performing analysis based on the machine learning model.

[0006] A non-transitory computer-readable medium storing code for wireless communication at a UE is described. The code may include instructions executable by a processor to: send an indication of a first set of one or more machine learning models supported at the UE to a first core network entity; receive control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model; and perform analysis based on the machine learning model.

[0007] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a request for the machine learning model to the first core network entity, wherein receiving the control signaling includes receiving the control signaling in response to sending the request.

[0008] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the request may include operations, features, components, or instructions for: sending a service request message, wherein receiving the control signaling includes: receiving the control signaling via a service response message.

[0009] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0010] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a completion message to the first core network entity based on the control signaling indicating the configuration of the machine learning model at the UE.

[0011] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the control signaling may include operations, features, components, or instructions for: receiving the control signaling indicating the configuration for the machine learning model, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, or any combination thereof.

[0012] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the control signaling may include operations, features, components, or instructions for: receiving one or more parameters of the machine learning model; and wherein performing the analysis includes: performing the analysis based on the one or more parameters.

[0013] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining the machine learning model from the core network based on an address indicated via the control signaling.

[0014] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for sending a non-access stratum (NAS) message to the first core network entity, the non-access stratum (NAS) message including information determined from performing the analysis based on the machine learning model.

[0015] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the control signaling may include operations, features, components, or instructions for: receiving a NAS message that can be configured according to a core network centralized entity container, the NAS message indicating the configuration for the machine learning model at the UE.

[0016] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first core network entity may be an access and mobility management function (AMF) entity.

[0017] A method for wireless communication is described. The method may include: obtaining an indication of a first set of one or more machine learning models supported at a UE; obtaining control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models at the UE; and outputting a NAS message including the control signaling configured according to the second core network entity.

[0018] An apparatus for wireless communication is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to: obtain an indication of a first set of one or more machine learning models supported at a UE; obtain control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE; and output a NAS message including the control signaling configured according to the second core network entity.

[0019] Another apparatus for wireless communication is described. The apparatus may include: means for obtaining an indication of a first set of one or more machine learning models supported at a UE; means for obtaining, from a second core network entity, control signaling configured according to the second core network entity, the control signaling indicating a configuration for a machine learning model for the first set of one or more machine learning models from the UE; and means for outputting a NAS message including the control signaling configured according to the second core network entity.

[0020] A non-transitory computer-readable medium storing code for wireless communication is described. The code may include instructions executable by a processor to: obtain an indication of a first set of one or more machine learning models supported at a UE; obtain control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE; and output a NAS message including the control signaling configured according to the second core network entity.

[0021] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining a request for the machine learning model, outputting an indication of the request for the machine learning model to the second core network entity; and wherein obtaining the control signaling includes, and obtaining the control signaling based on the indication.

[0022] Some examples of the methods, devices, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: outputting a discovery request for the second core network entity to a third core network entity, and obtaining an identifier of the second core network entity from the third core network entity based on the discovery request.

[0023] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0024] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining a request from the second core network entity for one or more UEs to perform analysis based on the machine learning model; and wherein outputting the NAS message includes: outputting the NAS message to the UE based on the request.

[0025] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for outputting to the second core network entity one or more identifiers of a group of one or more UEs associated with the first core network entity that support the machine learning model, the group of UEs including at least the UE.

[0026] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request for the one or more UEs to perform analysis includes one or more UE identifiers associated with the one or more UEs, one or more registration area lists, one or more network slice identifiers, or any combination thereof.

[0027] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for identifying the one or more UEs including at least the UE based on the request.

[0028] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, outputting the control signaling may include operations, features, components, or instructions for: outputting the NAS message including the control signaling, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a duration for performing analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

[0029] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining a completion message in response to the NAS message, and outputting the completion message to the second core network entity.

[0030] A method for wireless communication at a second core network entity is described. The method may include: identifying a UE that supports configuration of a machine learning model at the UE; and sending control signaling configured according to the second core network entity to a first core network entity, the control signaling being used to configure the machine learning model at the UE.

[0031] An apparatus for wireless communication at a second core network entity is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to: identify a UE that supports configuration of a machine learning model at the UE; and send control signaling configured according to the second core network entity to a first core network entity, the control signaling being used to indicate to the UE a configuration for the machine learning model.

[0032] Another apparatus for wireless communication at a second core network entity is described. The apparatus may include a component for identifying a UE that supports configuration of a machine learning model at the UE; and a component for sending control signaling configured according to the second core network entity to a first core network entity, the control signaling being used to indicate to the UE a configuration for the machine learning model.

[0033] A non-transitory computer-readable medium storing code for wireless communication at a second core network entity is described. The code may include instructions executable by a processor to: identify a UE that supports configuration of a machine learning model at the UE; and send control signaling configured according to the second core network entity to a first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0034] 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 first core network entity, an indication of a request from the UE to configure the machine learning model at the UE.

[0035] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, receiving the indication may include operations, features, components, or instructions for: receiving a NAS message from the UE via the first core network entity, the NAS message including the request.

[0036] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0037] 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 request from another network entity for one or more UEs to perform analysis based on the machine learning model.

[0038] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, identifying the UE may include operations, features, components, or instructions for: sending a request message to one or more network entities including at least the second core network entity for the one or more network entities to report UE identifiers of UEs that support the machine learning model; and receiving a response message from at least the second core network entity indicating a group of UEs including at least the UE.

[0039] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request message includes one or more registration area lists, one or more network slice identifiers, and an identifier of the machine learning model.

[0040] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: sending a discovery request for the one or more network entities to a third core network entity, the discovery request including one or more registration area lists or one or more network slice identifiers or both; and receiving a discovery response message from the third core network entity indicating the one or more network entities including at least the second core network entity, wherein the one or more network entities correspond to the one or more registration area lists or the one or more network slice identifiers or both.

[0041] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the request for the one or more UEs to perform the analysis includes one or more UE identifiers, UE group identifiers, or both of the one or more UEs, where the UE can be identified based on the request.

[0042] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the control signaling may include operations, features, components, or instructions for sending the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

[0043] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining a NAS message from the UE via the first core network entity, the NAS message including information determined at the UE by performing analysis based on the machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 An example of a wireless communication system supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0045] Figure 2 An example of a wireless communication system supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0046] Figure 3 An example of a capability indication procedure supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0047] Figure 4An example of network-initiated machine learning model configuration supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0048] Figure 5 An example of UE-initiated machine learning model configuration supporting centralized machine learning model configuration according to various aspects of the present disclosure is illustrated.

[0049] Figure 6 An example of a machine learning process supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0050] Figure 7 and Figure 8 A block diagram of a device supporting centralized machine learning model configuration according to various aspects of the present disclosure is shown.

[0051] Fig. 9 A block diagram of a communication manager supporting centralized machine learning model configuration according to aspects of the present disclosure is shown.

[0052] Fig.10 A diagram of a system including a device supporting centralized machine learning model configuration according to aspects of the present disclosure is shown.

[0053] Fig.11 and Fig.12 A block diagram of a device supporting centralized machine learning model configuration according to various aspects of the present disclosure is shown.

[0054] Fig.13 A block diagram of a communication manager supporting centralized machine learning model configuration according to aspects of the present disclosure is shown.

[0055] Fig.14 A diagram of a system including a device supporting centralized machine learning model configuration according to aspects of the present disclosure is shown.

[0056] Figures 15 to 19 A flowchart illustrating a method of supporting centralized machine learning model configuration according to aspects of the present disclosure is shown. DETAILED DESCRIPTION

[0057] The core network of the wireless communication system can train machine learning models to perform analysis, such as network optimization and inference. The UE in the wireless communication system can also support performing analysis based on the machine learning model. For example, the core network can configure the trained machine learning model to the UE, and the UE can perform analysis using the trained machine learning model. The UE can obtain inference results from the trained machine learning model, and these inference results can be used for local optimization at the UE or reported to the core network for core network optimization.

[0058] The present disclosure provides a technique for configuring a machine learning model at a UE using a centralized architecture with a centralized core network entity. The centralized core network entity may manage, store, or support one or more machine learning models associated with various functionalities of the core network. For example, the centralized core network entity may manage machine learning models associated with mobility management, session management, policy-related management, and the like. In one example, the centralized entity may configure the machine learning model to the UE via NAS signaling through another network entity such as an AMF entity, and the UE may use the machine learning model to perform analysis. In some cases, in order to support centralized architecture techniques, the UE may report capability information to a serving AMF entity, and the AMF entity may communicate signaling between the UE and the centralized core network entity. For example, a centralized core network entity may support and manage artificial intelligence or machine learning techniques, but there may be no direct link between the UE and the centralized core network entity because the interface between the UE and the core network may terminate at the AMF entity. Therefore, the UE may communicate with the centralized core network entity through the AMF entity, such as via NAS signaling sent to the AMF entity and then forwarded by the AMF entity. For example, the UE may transmit a NAS request to the AMF entity, and the AMF entity may transmit the request to the centralized core network entity. Similarly, the centralized core network entity may transmit configuration signaling to the AMF entity, and the AMF entity forwards the configuration signaling to the UE via a downlink NAS message.

[0059] The UE or the core network may initiate a procedure for configuring a machine learning model to the UE. In some cases, the UE may initiate the procedure by sending a request for a machine learning model to an AMF entity, which may forward the request to a centralized core network entity. The AMF entity may identify or discover a centralized core network entity that manages the requested machine learning model, and transmit the request to the centralized core network entity. The centralized core network entity may transmit control signaling for configuring the machine learning model to the UE to the AMF entity, and the AMF entity may transmit (e.g., forward a NAS message) the control signaling to the UE to configure the machine learning model to the UE, or indicate the configuration for the machine learning model to the UE. In some cases, the centralized core network entity may receive a request from another network entity or a consumer for the UE to perform analysis using a machine learning model. The centralized core network entity may identify or discover an AMF entity that serves one or more UEs that have the capability to support the requested machine learning model, and the centralized core network entity may configure the machine learning model to the identified one or more UEs via the AMF entity. A centralized core network entity may receive requests for analysis from one or more specific UEs, from a group of UEs, or for a network slice.

[0060] In some cases, the UE may obtain the machine learning model from the core network. For example, the UE may receive control signaling that configures or indicates the machine learning model. The control signaling may include, for example, an address or location (e.g., a uniform resource locator (URL) or a fully qualified domain name (FQDN)) of the machine learning model, and the UE may obtain the machine learning model from the core network via the address or location of the machine learning model.

[0061] The UE may perform analysis based on a machine learning model. Performing analysis may enable some optimization at the UE or at the core network. For example, the UE may request to perform analysis based on inferences determined from a machine learning model to achieve UE optimization. In some cases, the UE may perform network load analysis using a machine learning model, and the UE may request the network to provide a machine learning model or analysis results. The UE may perform analysis using a machine learning model, or use the analysis results to perform network selection for a network with a low network load, thereby increasing throughput and reducing latency and network load bearing. For example, performing analysis at the UE or training a machine learning model at the UE may provide more information for performing network selection or network load management compared to performing analysis or inference at the network side alone. Additionally or alternatively, a core network entity or consumer may request the UE to perform analysis and report information obtained from performing analysis, which may enable optimization at the core network or core network entity based on the reported information. For example, an application client may request the UE to perform analysis using a machine learning model, and the UE may report analysis information from the machine learning model. The application client may use the reported information to, for example, perform split rendering, reduce processing power at the UE or network, or both.

[0062] Systems that perform machine learning model training or analysis at the UE do not support performing local device management or network management (e.g., network load management, split rendering for virtual reality, extended reality, or augmented reality technologies, etc.) based on information or inferences obtained at the network (e.g., network-side inferences and analysis). However, by implementing the techniques described herein, the UE or the network entity, or both, may perform local device management or network management based on inferences or analysis performed at both the UE and the network entity, which may provide the UE or the network entity, or both, with more information to perform more optimized device or network management.

[0063] For example, the UE may use network load analysis to predict network load for different radio access technologies (RATs) (e.g., 4G or 5G), and register with the RAT based on the network load prediction. In another example, for a specific protocol data unit (PDU) session, the UE may determine to establish a PDU session via different access technologies based on the network load prediction. In another example, by implementing these techniques, the UE may provide network load prediction analysis to a UE application client, and the application client may determine whether to initiate high-bitrate data transmission. The network may provide a list of UEs to the entity, node, or consumer based on a request from the requesting entity, node, or consumer. For example, an application function may request a list of UEs within a specific location, and the network may request that the UE provide a network load prediction and may provide the list of UEs to the application function. The UE may select a network or RAT with a lower load based on the network load prediction, which may provide the UE with higher quality communications or lower latency communications.

[0064] Various aspects of the present disclosure are first described in the context of a wireless communication system. Various aspects of the present disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flow diagrams related to centralized machine learning model configurations.

[0065] Figure 1 An example of a wireless communication system 100 supporting distributed machine learning model configuration according to various aspects of the present disclosure is illustrated. The wireless communication system 100 may include one or more network entities 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a long term evolution (LTE) network, an advanced LTE (LTE-A) network, an LTE-A Pro network, a new radio (NR) network, or a network operating according to other systems and radio technologies (including future systems and radio technologies not explicitly mentioned herein).

[0066] 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 examples, the network entities 105 and the UE 115 may communicate wirelessly via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, the network entity 105 may support a coverage area 110 (e.g., a geographic coverage area), and the UE 115 and the network entity 105 may establish one or more communication links 125 over the coverage area. The coverage area 110 may be an example of a geographic area in which the network entity 105 and the UE 115 may support signal communications according to one or more RATs.

[0067] 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 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. Figure 1 As shown, the UE 115 described herein may be capable of communicating with various types of devices, such as other UEs 115 or network entities 105 .

[0068] As described herein, a node of the wireless communication system 100 (which may be referred to as a network node or a wireless node) may be a network entity 105 (e.g., any network entity described herein), a UE 115 (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, the node may be a UE 115. As another example, the node may be a network entity 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a network entity 105. In yet other aspects of this example, the first node, the second node, and the third node may be different relative to these examples. Similarly, references to UE 115, network entity 105, apparatus, device, computing system, etc. may include disclosure of UE 115, network entity 105, apparatus, device, computing system, etc. as nodes. For example, a disclosure that UE 115 is configured to receive information from network entity 105 also discloses that the first node is configured to receive information from a second node.

[0069] As described herein, different terms may be used in various aspects to describe the communication 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, communicate, 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.

[0070] In some examples, 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 links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some examples, the network entities 105 may communicate with each other on the backhaul communication link 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 examples, the network entities 105 may communicate with each other via the midhaul communication link 162 (e.g., according to the midhaul interface protocol) or the fronthaul communication link 168 (e.g., according to the fronthaul interface protocol) or any combination thereof. The backhaul communication link 120, the midhaul communication link 162, or the fronthaul communication link 168 may be or include one or more wired links (e.g., electrical links, optical fiber links), one or more wireless links (e.g., radio links, wireless optical links), and other examples or various combinations thereof. UE 115 may communicate with core network 130 via communication link 155 .

[0071] 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 examples, the network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, standalone) 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).

[0072] In some examples, the network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that may be configured to utilize a protocol stack that is physically or logically distributed between two or more network entities 105, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, the network entity 105 may include one or more of the following: a central unit (CU) 170, a distributed unit (DU) 175, a radio unit (RU) 180, a RAN intelligent controller (RIC) 185 (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) 190 system, or any combination thereof. The RU 180 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmit receive point (TRP). One or more components of the network entity 105 in the decomposed RAN architecture may be co-located, or one or more components of the network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 of the decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0073] The functional split between CU 170, DU 175, and RU 185 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 170, DU 175, and RU 185. For example, a functional split of a protocol stack may be employed between CU 170 and DU 175, such that CU 170 may support one or more layers of a protocol stack, and DU 175 may support one or more different layers of a protocol stack. In some examples, CU 170 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 170 may be connected to one or more DUs 175 or RUs 180, and the one or more DUs 175 or RUs 180 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 170. Additionally or alternatively, a functional split of the protocol stack may be employed between the DUs 175 and RUs 180, such that the DUs 175 may support one or more layers of the protocol stack, and the RUs 180 may support one or more different layers of the protocol stack. The DUs 175 may support one or more different cells (e.g., via one or more RUs 180). In some cases, the functional split between CU 170 and DU 175 or between DU 175 and RU 180 may be within the protocol layer (e.g., some functions of the protocol layer may be performed by one of CU 170, DU 175, or RU 180, while other functions of the protocol layer are performed by different ones of CU 170, DU 175, or RU 180). CU 170 may be further functionally split into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 170 may be connected to one or more DUs 175 via midhaul communication links 162 (e.g., F1, F1-c, F1-u), and DU 175 may be connected to one or more RUs 180 via fronthaul communication links 168 (e.g., open fronthaul (FH) interface). In some examples, midhaul communication link 162 or fronthaul communication link 168 may be implemented according to an interface (eg, channel) between layers of a protocol stack supported by the respective network entities 105 communicating over those communication links.

[0074] In a wireless communication system (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 a 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 175 or one or more RUs 180 may be controlled in part by one or more CUs 170 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 175. 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 180) for access via the DU 175 of the IAB node 104 (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, the IAB node 104 may include a DU 175 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.

[0075] 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. The IAB donor may facilitate connectivity between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, the IAB donor may refer to a RAN node having a wired or wireless connection to the core network 130. The IAB donor may include a CU 170 and at least one DU 175 (e.g., and RU 180), in which case the CU 170 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 170 may communicate with the core network via an interface (which may be an example of a portion of a backhaul link) and may communicate with other CUs 170 (e.g., CU 170 associated with an alternative IAB donor) via an Xn-C interface (which may be an example of a portion of a backhaul link).

[0076] 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 175 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 175 ) may provide a Uu interface for parent IAB node 104 to signal to child IAB node 104 or UE 115 .

[0077] 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 170 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 175 of the IAB donor may relay transmissions to the UE 115 through the IAB node 104, and may directly signal the transmissions to the UE 115. The CU 170 of the IAB donor may signal the establishment of a communication link to the IAB node 104 via the F1 interface, and the IAB node 104 may schedule transmissions (e.g., transmissions relayed from the IAB donor to the UE 115) via the DU 175. That is, data may be relayed to and from the IAB node 104 via signaling via the NR Uu interface of the MT to the IAB node 104. Communications with the IAB node 104 may be scheduled by the DU 175 of the IAB donor, and communications with the IAB node 104 may be scheduled by the DU 175 of the IAB node 104 .

[0078] Where the techniques described herein are applied in the context of a disaggregated RAN architecture, one or more components of the disaggregated RAN architecture may be configured to support a centralized machine learning model configuration 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 disaggregated RAN architecture (e.g., an IAB node 104, a DU 175, a CU 170, a RU 180, a RIC 185, a SMO 190).

[0079] UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable term, where a "device" may also be referred to as a unit, a station, a terminal, or a client, etc. UE 115 may also include or may be referred to as a personal electronic device, such as a cellular phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some examples, UE 115 may include or may be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0080] The UE 115 described herein may be capable of communicating with various types of devices, such as other UEs 115, which may sometimes act as relays, as well as network entities 105 and network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, etc. Figure 1 shown.

[0081] 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 RAT (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 with multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation may be used for both frequency division duplex (FDD) component carriers and time division duplex (TDD) component carriers. Communication between the network entity 105 and other devices may refer to communication between a device and any portion (e.g., entity, sub-entity) of the network entity 105. For example, the terms "send," "receive," or "communicate" when referring to the network entity 105 may refer to any portion of a network entity 105 (e.g., base station 140, CU 170, DU 175, RU 180) of the RAN communicating with another device (e.g., directly or via one or more other network entities 105).

[0082] In some examples, such as in a carrier aggregation configuration, a carrier may also have acquisition signaling or control signaling that coordinates the operation of other carriers. A carrier may be associated with a frequency channel (e.g., an Evolved Universal Mobile Telecommunications System Terrestrial Radio Access (E-UTRA) Absolute RF Channel Number (EARFCN)) and may be located according to a channel raster for discovery by UE 115. A carrier may operate in a standalone mode, in which case initial acquisition and connection may be made by UE 115 via the carrier, or a carrier may operate in a non-standalone mode, in which case a different carrier (e.g., of the same or different RAT) is used to anchor the connection.

[0083] The communication link 125 shown in the wireless communication system 100 may include downlink transmissions (e.g., forward link transmissions) from the network entity 105 to the UE 115, uplink transmissions (e.g., return link transmissions) from the UE 115 to the network entity 105, or both, as well as other transmission configurations. A carrier may carry either downlink communications or uplink communications (e.g., in an FDD mode), or may be configured to carry both downlink communications and uplink communications (e.g., in a TDD mode).

[0084] A carrier may be associated with a particular bandwidth of the RF spectrum, and in some examples, the carrier bandwidth may be referred to as the "system bandwidth" of the carrier or wireless communication system 100. For example, the carrier bandwidth may be one of a set of bandwidths for a carrier for a particular RAT (e.g., 1.4 megahertz (MHz), 3 MHz, 5 MHz, 10 MHz, 15 MHz, 20 MHz, 40 MHz, or 80 MHz). A device of the wireless communication system 100 (e.g., a network entity 105, a UE 115, or both) may have a hardware configuration that supports communication over a particular carrier bandwidth, or may be configurable to support communication over one of a set of carrier bandwidths. In some examples, the wireless communication system 100 may include a network entity 105 or a UE 115 that supports concurrent communication via carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured to operate over a portion (e.g., a subband, a BWP) or all of a carrier bandwidth.

[0085] 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 UE115.

[0086] One or more parameter sets for a carrier may be supported, where the parameter set may include subcarrier spacing (Δf) and cyclic prefix. A carrier may be divided into one or more BWPs with the same or different parameter sets. In some examples, a UE 115 may be configured with multiple BWPs. In some examples, a single BWP for a carrier may be active at a given time, and communications of a UE 115 may be constrained to one or more active BWPs.

[0087] 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 / (Δf max ·N f ) seconds, where Δfmax 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).

[0088] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, the frame may be divided into subframes (e.g., in the time domain), and each subframe may be further divided into a certain number of time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include a certain number of symbol periods (e.g., depending on the length of the cyclic prefix appended in front of each symbol period). In some wireless communication systems 100, the time slot may be further divided into multiple micro-time slots containing one or more symbols. Excluding the cyclic prefix, each symbol period may 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.

[0089] A subframe, a time slot, a mini-time slot, or a 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 transmission time interval (TTI). In some examples, the TTI duration (e.g., the number of symbol periods in a TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of a shortened TTI (sTTI)).

[0090] 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 the system bandwidth. One or more control regions (e.g., CORESETs) may be configured for a group of UEs 115. For example, one or more of the UEs 115 may monitor or search the 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 the control channel candidates may refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with the coded information of 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 configured for transmitting control information to a specific UE 115 .

[0091] The network entity 105 may provide communication coverage via one or more cells (e.g., macro cells, small cells, hot spots, or other types of cells, or any combination thereof). The term "cell" may refer to a logical communication entity used to communicate with the network entity 105 (e.g., via a carrier), and may be associated with an identifier used to distinguish adjacent cells (e.g., a physical cell identifier (PCID), a virtual cell identifier (VCID), or other cell identifier). In some examples, a cell may also refer to a coverage area 110 or a portion of a coverage area 110 (e.g., a sector) within which the logical communication entity operates. Depending on various factors such as the capabilities of the network entity 105, such cells may range from smaller areas (e.g., structures, subsets of structures) to larger areas. For example, a cell may be or may include a building, a subset of a building, or an external space between or overlapping coverage areas 110, and the like.

[0092] A macro cell generally covers a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access to UEs 115 that have service subscriptions with a network provider that supports the macro cell. Small cells may be associated with lower power network entities 105 (e.g., lower power base stations 140) compared to macro cells, and small cells may operate in the same or different (e.g., licensed, unlicensed) frequency bands as macro cells. Small cells may provide unrestricted access to UEs 115 that have service subscriptions with a network provider, or may provide restricted access to UEs 115 associated with small cells (e.g., UEs 115 in a closed subscriber group (CSG), UEs 115 associated with users in a home or office). A network entity 105 may support one or more cells, and may also use one or more component carriers to support communications on one or more cells.

[0093] In some examples, a carrier may support multiple cells, and different cells may be configured according to different protocol types (e.g., MTC, narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB)) that may provide access to different types of devices.

[0094] In some examples, the network entities 105 (e.g., base stations 140, RUs 180) may be mobile and thus provide communication coverage for mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 provide coverage for various coverage areas 110 using the same or different RATs.

[0095] The wireless communication system 100 may support synchronous or asynchronous operation. For synchronous operation, the network entities 105 (e.g., base stations 140) may have similar frame timing, and transmissions from different network entities 105 may be approximately aligned in time. For asynchronous operation, the network entities 105 may have different frame timing, and in some examples, transmissions from different network entities 105 may not be aligned in time. The techniques described herein may be used for synchronous or asynchronous operation.

[0096] 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 examples, 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.

[0097] 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 examples, half-duplex communication may be performed at a reduced peak rate. Other power saving techniques for UE 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.

[0098] 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). The 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.

[0099] In some examples, a UE 115 may be able to communicate directly with other UEs 115 via a device-to-device (D2D) communication link 135 (e.g., according to a peer-to-peer (P2P), D2D, or sidelink protocol). In some examples, one or more UEs 115 in a group that are performing D2D communication may be within a coverage area 110 of a network entity 105 (e.g., a base station 140, a RU 180), which may support aspects of such D2D communication configured or scheduled by the network entity 105. In some examples, one or more UEs 115 in this group may be outside the coverage area 110 of the network entity 105, or may otherwise be unable or not configured to receive transmissions from the network entity 105. In some examples, a group of UEs 115 communicating via D2D communication may support a one-to-many (1:M) system, in which each UE 115 transmits to each other UE 115 in the group. In some examples, the network entity 105 may facilitate scheduling of resources for D2D communication. In some other examples, D2D communications may be performed between UEs 115 without the involvement of network entity 105 .

[0100] 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 examples, 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 examples, vehicles in the V2X system can communicate with roadside infrastructure (such as roadside units), or communicate with the network via one or more network nodes (e.g., network entity 105, base station 140, RU 180) using vehicle-to-network (V2N) communication, or both.

[0101] 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) or other generations or systems, which may include at least one control plane entity (e.g., a mobility management entity (MME), an AMF entity 165) that manages 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)) that routes packets or interconnections to an external network. The control plane entity may manage 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 transferred through the user plane entity, which may provide IP address allocation and other functions. The user plane entity may be connected to IP services 150 of one or more network operators. The IP service 150 may include access to the Internet, an intranet, an IP multimedia subsystem (IMS), or a packet-switched streaming service.

[0102] 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). In general, the region from 300 MHz to 3 GHz is referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range 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.

[0103] 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 known as a centimeter band) or in an extremely high frequency (EHF) region of the spectrum (e.g., from 30 GHz to 300 GHz) (also known as a millimeter band). In some examples, the wireless communication system 100 may support millimeter wave (mmW) communications between UE 115 and network entity 105 (e.g., base station 140, RU 180), and the EHF antenna of the corresponding device may be smaller and closer than the UHF antenna. In some examples, 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 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 vary by country or regulatory agency.

[0104] The wireless communication system 100 may utilize both 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 examples, operations in an unlicensed band may be based on a carrier aggregation configuration in conjunction with a component carrier (e.g., LAA) operating in a licensed band. Operations in an unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, and the like.

[0105] The network entity 105 (e.g., base station 140, RU 180) 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 examples, antennas or antenna arrays associated with the network entity 105 may be located in different geographic locations. The network entity 105 may have an antenna array having a set of 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.

[0106] 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.

[0107] 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).

[0108] 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 180) 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 beamforming weight sets 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.

[0109] Some signals, such as data signals associated with a particular receiving device, may be sent by a transmitting device (e.g., transmitting network entity 105, transmitting UE 115) along a single beam direction (e.g., a direction associated with a receiving device (such as receiving network entity 105 or receiving UE 115)). In some examples, the beam direction associated with the transmission along the single beam direction may be determined based on signals sent along one or more beam directions. For example, UE 115 may receive one or more of the signals sent by network entity 105 along different directions, and may report to network entity 105 an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.

[0110] In some examples, transmission by a device (e.g., by network entity 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from network entity 105 to UE 115). UE 115 may report feedback indicating precoding weights for one or more beam directions, and the feedback may correspond to a set of configured beams across a system bandwidth or one or more subbands. Network entity 105 may send 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. 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 180), 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).

[0111] A receiving device (e.g., UE 115) may perform receiving operations according to multiple receiving configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a receiving device (e.g., network entity 105). For example, the receiving device may perform reception according to multiple receiving directions by receiving via different antenna subarrays, processing 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 received signals according to different receiving beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as "listening" according to different receiving configurations or receiving directions. In some examples, the receiving device may use a single receiving configuration to receive along a single beam direction (e.g., when receiving a data signal). A single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or other acceptable signal quality based on listening according to multiple beam directions).

[0112] 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.

[0113] 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 technology 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 cyclic redundancy check (CRC)), forward error correction (FEC) and retransmission (e.g., automatic repeat request (ARQ)). HARQ can improve the throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, the device may support simultaneous slot HARQ feedback, wherein the device may provide HARQ feedback in a specific time slot for data received in a previous symbol in the time slot. In some other examples, the device may provide HARQ feedback in a subsequent time slot or according to some other time interval.

[0114] The present disclosure provides techniques for configuring machine learning models at UE 115 using a centralized architecture with a centralized core network entity 160. The centralized core network entity 160 may manage, store, or support one or more machine learning models associated with various functionalities of the core network 130. In some cases, a 5G network data analysis function may be an example of a centralized core network entity 160. The centralized core network entity 160 may coordinate or use artificial intelligence or machine learning operations in the wireless communication system 100, such as for the core network 130, the RAN, the UE 115, or any combination thereof. In some examples, the centralized core network entity 160 may be an example of or provide a core network interface for artificial intelligence operations, machine learning operations, or both. In some cases, the centralized core network entity 160 may be a network entity dedicated to machine learning model configuration and management.

[0115] For example, the centralized core network entity 160 may manage machine learning models associated with mobility management, session management, etc. The centralized core network entity 160 may configure the machine learning model to the UE 115 via NAS signaling through another network entity such as the AMF entity 165, and the UE 115 may perform analysis using the machine learning model. In some cases, in order to support centralized architecture technology, the UE 115 may report capability information to the serving AMF entity 165, and the AMF entity 165 may communicate signaling between the UE 115 and the centralized core network entity 160.

[0116] In some examples, the AMF entity 165 may not support artificial intelligence or machine learning techniques, but there may not be a direct link for machine learning between the UE and the centralized core network entity because the interface between the UE and the core network may terminate at the AMF entity. Therefore, the UE may communicate with the centralized core network entity through the AMF entity, such as via NAS signaling sent to the AMF entity and then forwarded by the AMF entity. For example, the UE may transmit a NAS request to the AMF entity, and the AMF entity may transmit the request to the centralized core network entity. Similarly, the centralized core network entity may transmit configuration signaling to the AMF entity, and the AMF entity forwards the configuration signaling to the UE via a downlink NAS message.

[0117] The UE 115 or the core network 130 may initiate a procedure for configuring the machine learning model to the UE 115. In some cases, the UE 115 may initiate the procedure by sending a request for the machine learning model to the AMF entity 165. The AMF entity 165 may identify or discover the centralized core network entity 160 that manages the requested machine learning model and transmit the request to the centralized core network entity 160. The centralized core network entity 160 may transmit control signaling for configuring the machine learning model to the UE 115 to the AMF entity 165, and the AMF entity 165 may transmit (e.g., forward a NAS message) the control signaling to the UE 115 to configure the machine learning model to the UE 115. In some cases, the centralized core network entity 160 may receive a request from another network entity or a consumer for the UE 115 to perform analysis using the machine learning model.

[0118] The centralized core network entity 160 may identify or discover an AMF entity 165 serving one or more UEs 115 that have the capability to support the requested machine learning model. For example, the UE 115 may transmit an identifier of the supported machine learning model to the AMF entity 165 during a registration procedure, and the AMF entity 165 may store the capability of the UE 115 to support the machine learning model associated with the machine learning model identifier as part of the UE context. The centralized core network entity 160 may select a UE 115 that supports the ML model based on a request for one or more UEs 115 to perform analysis or inference using the machine learning model, and the centralized core network entity 160 may transmit the request to the AMF entity 160 with the machine learning model identifier. The AMF entity 160 may respond to the centralized core network entity 160, indicating which UEs 115 support the identified machine model based on the stored UE context. The centralized core network entity 160 may configure the machine learning model to the identified one or more UEs 115 via the AMF entity 165, such as via NAS signaling, which is sent to the one or more UEs 115 via the AMF entity 165. The centralized core network entity 160 may receive a request to obtain analysis from one or more specific UEs 115, from a group of UEs 115, or for a network slice.

[0119] In some cases, UE 115 may obtain the machine learning model from core network 130. For example, UE 115 may receive control signaling that configures or indicates the machine learning model. The control signaling may include, for example, an address or location (e.g., a URL or FQDN) of the machine learning model, and UE 115 may obtain the machine learning model from core network 130 via the address or location of the machine learning model. For example, the machine learning may be a file with many data packets. In some examples, instead of the centralized core network entity 160 providing the machine learning model directly to UE 115 via signaling (e.g., because this may incur significant overhead to the core network), the centralized core network entity 160 may instruct UE 115 to transmit a machine learning model configuration including a machine learning model file download address. The UE may download the machine learning model via the user plane using the machine learning model file download address.

[0120] In some examples, UE 115-a may include a communications manager 101 configured to support one or more aspects of the techniques for centralized machine learning model configuration described herein. For example, communications manager 101 may be configured to support UE 115-a sending an indication of a first set of one or more machine learning models supported at UE 115-a to a first core network entity such as AMF entity 165. In some examples, communications manager 102 may be configured to support UE 115-a receiving control signaling from AMF entity 165 indicating configuration for a machine learning model at UE 115-a. The first set of one or more machine learning models may include the machine learning model. In some examples, communications manager 101 may be configured to support UE 115-a to perform analysis based on the machine learning model.

[0121] In some examples, the AMF entity 165 may include a communications manager 102 configured to support one or more aspects of the techniques for centralized machine learning model configuration described herein. For example, the communications manager 102 may be configured to support the AMF entity 165 in obtaining an indication of a first set of one or more machine learning models supported at the UE 115. In some examples, the indication may be obtained or received from a UE 115 such as a UE 115-a. In some examples, the communications manager 102 may be configured to support the AMF entity 165 in obtaining control signaling configured according to the second core network entity from a second core network entity such as a centralized core network entity 160, the control signaling indicating the configuration of a machine learning model from the first set of one or more machine learning models. In some examples, the communications manager 102 may be configured to support the AMF entity 165 in outputting a NAS message including control signaling configured according to the second core network entity.

[0122] In some examples, the centralized core network entity 160 may include a communication manager 103 configured to support one or more aspects of the techniques for centralized machine learning model configuration described herein. For example, the communication manager 103 may be configured to support the centralized core network entity 160 in identifying a UE 115, such as UE 115-a, that supports configuration of a machine learning model at the UE 115. In some examples, the communication manager 103 may be configured to support the centralized core network entity 160 in outputting control signaling configured according to the centralized core network entity 160 to a first core network entity (e.g., AMF entity 165), the control signaling being used to indicate to the UE 115 the configuration for the machine learning model.

[0123] Figure 2 An example of a wireless communication system 200 supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0124] The wireless communication system 200 may include a UE 115-a, which may be as described with reference to Figure 1 An example of a UE 115 described. The wireless communication system 200 may include one or more entities of a core network, such as an AMF entity 205, a centralized core network entity 210, or both. In some cases, the wireless communication system 200 may include another network entity 225, which may be an example of another network entity, an AMF entity 205, a session management function (SMF) entity, a consumer in the wireless communication system 200, or any combination thereof. In some cases, the UE 115-a may communicate directly with the AMF entity 205 and the centralized core network entity 210. Additionally or alternatively, the UE 115-a may communicate with the AMF entity 205 and the centralized core network entity 210 by conveying NAS signaling via the network entity 105. In some cases, the UE 115-a may communicate with the centralized core network entity 210 via the AMF entity 205, such as by sending or receiving NAS signaling configured according to the centralized core network entity 210, which is conveyed to or from the centralized core network entity 210 via the AMF entity 205. In some cases, the AMF entity 205 and the centralized core network entity 210 may communicate via a network link 215.

[0125] The core network of the wireless communication system 200 may train machine learning models to perform analysis, such as network optimization and inference. The UE 115 such as UE 115-a in the wireless communication system 200 may also support the use of machine learning models to perform analysis. The wireless communication system 200 may implement an example configuration of a centralized architecture for configuring machine learning models to UEs 115 such as UE 115-a.

[0126] For a centralized architecture or centralized configuration, the centralized core network entity 210 may manage, store, or support one or more machine learning models associated with the functionality of the core network entity. For example, the centralized core network entity 210 may manage machine learning models associated with mobility management, session management, and the like. For example, the centralized core network entity 210 may have functionality for supporting machine learning model training, data collection and artificial intelligence inference, and artificial intelligence analysis data exposure. The centralized core network entity 210 may send a machine learning model configuration 230 indicating a machine learning model to a UE 115 such as UE 115-a. The machine learning configuration 230 may be sent via NAS signaling 250 by another network entity such as an AMF entity 205, and the UE 115-a may perform analysis using the machine learning model.

[0127] In some cases, to support centralized architecture techniques, the UE 115-a may report capability information to a serving AMF entity such as the AMF entity 205. For example, the UE 115-a may transmit a capability message 220 to the AMF entity 205 indicating an identifier of a machine learning model supported by the UE 115-a. Figure 3 Examples of UE and network capability exchange are described in more detail.

[0128] UE 115-a or the core network may initiate a procedure for configuring the machine learning model to UE 115-a. In some cases, the centralized core network entity 210 may receive a request 235 from another network entity or a consumer for UE 115 to perform analysis using the machine learning model. The consumer may be, for example, another network entity that may transmit analysis requests for different purposes, such as an AMF entity 205, an SMF entity, a policy and charging rules function (PCF) entity, an operation, administration, and maintenance (OAM) entity, or an application function entity. The centralized core network entity 210 may identify or discover an AMF entity such as AMF entity 205 that serves one or more UEs 115 such as UE 115-a that have the ability to support the requested machine learning model. The centralized core network entity 210 may configure the machine learning model to the identified one or more UEs 115 via the AMF entity 205. The centralized core network entity 210 may receive a request 235 to obtain analytics from one or more specific UEs 115, from a group 245 of UEs 115, or for a network slice. The group 245 of UEs 115 may, for example, correspond to UEs 115 having a common group identifier, in a common network slice, in a common registration area, having common capabilities, or any combination thereof. In some examples, the group 245 of UEs 115 may be identified based on the group identifier, and the centralized core network entity 210 may identify the UEs 115 in the group 245 or a subscriber permanent identifier (SUPI) for the group 245. In some cases, in order to discover UEs 115 having the capability to support the requested machine learning model, the centralized core network entity 210 may transmit a discovery request message to a network repository function (NRF) entity. The NRF entity may transmit a discovery response message to the centralized core network entity 210, the discovery response message indicating or identifying one or more AMF entities serving the UEs 115 that support the requested machine learning model. About Figure 4 An example of core network initiated machine learning model configuration is described in more detail.

[0129] In some cases, the UE 115-a may initiate the procedure by sending a request 240 for a machine learning model to the AMF entity 205. In some cases, the UE 115-a may determine the machine learning model to request based on the function or operation performed at the UE 115-a. For example, if the UE 115-a is to perform network selection, the UE 115-a may request a machine learning model for network load to obtain network load analysis. If the UE 115-a is performing an operation related to service experience, the UE 115-a may request a machine learning model for service experience.

[0130] The AMF entity 205 may identify or discover a centralized core network entity such as the centralized core network entity 210 that manages the requested machine learning model, and the AMF entity 205 may transmit a request 240 to the centralized core network entity 210. The centralized core network entity 210 may transmit a machine learning model configuration 230 for configuring the machine learning model for the UE 115-a to the AMF entity 205, and the AMF entity 205 may transmit (e.g., by forwarding a NAS message via NAS signaling 250) the machine learning model configuration 230 to the UE 115-a to configure the machine learning model for the UE 115-a. In some cases, in order to discover the centralized core network entity 210, the AMF entity 205 may transmit a discovery request message to the NRF entity, and the NRF entity may transmit a discovery response message indicating or identifying the centralized core network entity 210 to the AMF entity 205. Figure 5 An example of UE-initiated machine learning model configuration is described in more detail.

[0131] In some cases, UE 115-a may obtain the machine learning model from the core network. For example, UE 115-a may receive a machine learning model configuration 230 that may indicate the machine learning model. The machine learning model configuration 230 may include, for example, an address or location (e.g., a URL or FQDN) of the machine learning model, and UE 115-a may obtain the machine learning model from the core network via the address or location of the machine learning model. In some cases, the machine learning model configuration 230 may not provide the machine learning model directly to UE 115-a, but may provide a stored machine learning model file address. UE 115-a may download the machine learning model from the indicated address (e.g., via a user plane).

[0132] UE 115-a may perform analysis based on the machine learning model. Performing the analysis may enable some optimization to be performed at UE 115-a or at the core network. For example, UE 115-a may request that analysis be performed based on inferences determined from the machine learning model to achieve UE optimization. Additionally or alternatively, the core network entity may request that UE 115-a perform analysis and report information obtained from performing the analysis, which may enable optimization to be performed at the core network or core network entity based on the reported information. Figure 6 Some examples and techniques for using machine learning models are described in more detail.

[0133] In some examples, UE 115-a may report analysis, training information, or inferences determined based on a machine learning model. For example, UE 115-a may send a report indicating information to one or more of the core network entities. In some cases, the core network may use the reported information to perform optimization at the core network. Additionally or alternatively, the core network may update the machine learning model based on training performed by UE 115-a. For example, the core network may request that UE 115-a transmit analysis results or a trained machine learning model to the core network, and the core network may use the analysis results or the trained machine learning model to optimize core network operations.

[0134] Figure 3 An example of a capability indication procedure 300 supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0135] The capability indication procedure 300 may be implemented by the UE 115 or the AMF entity 305 or both. The UE 115 and the AMF entity 305 may be as described in reference Figure 2 The corresponding examples of the UE 115 and the AMF entity 205 are described. The process and signaling of the capability indication procedure 300 are exemplary and may occur in a different order in other examples. In some cases, some additional signaling or procedures not shown may be performed, or some signaling or procedures shown may not be performed in other examples.

[0136] The machine learning model may require certain software, hardware, machine learning data training platform, or any combination thereof to support the operation of the machine learning model at the UE 115. If the UE 115 supports the machine learning model, the UE 115 may have the associated software or hardware or both. In some cases, to support the application layer machine learning model, the UE 115 may have a configuration authorization from the application to the application client of the UE 115. Different UEs 115 may have different capabilities to support different machine learning models.

[0137] UE 115 may indicate machine learning capability information that supports centralized machine learning model configuration to AMF entity 305. For example, UE 115 may send an indication of a first set of machine learning models supported at UE 115 to AMF entity 305 at 310. UE 115 may transmit the capability to AMF entity 305 to indicate support or capability of UE 115 to receive machine learning model configuration from a centralized core network entity that can manage machine learning and artificial intelligence operations in the core network. In some cases, the indication of supported machine learning models may include identifiers of supported machine learning models. For example, UE 115 may send an indication of supported machine learning models at UE 115 to AMF entity 305 at 315. In some cases, UE 115 may send a registration request including an indication of UE capabilities. In response, AMF entity 305 may send a registration response to UE 115 at 320.

[0138] In some cases, the AMF entity 305 may manage or store which UEs 115 support certain machine learning models. For example, the AMF entity 305 may be requested to identify one or more UEs 115 that support a certain machine learning model. In some cases, the AMF entity 305 may indicate to another core network entity such as the NRF described herein or a centralized core network entity which machine learning models the UE 115 supports. The NRF may be, for example, a network entity for storing and managing network profiles. The network profile may include network support functions, service location areas, service slice information, or any combination thereof of network entities of the network.

[0139] Figure 4 An example of a network-initiated machine learning model configuration 400 supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated.

[0140] The network-initiated machine learning model configuration 400 may be implemented by the UE 115, the AMF entity 405, the centralized core network entity 410, the NRF entity 415, another network entity 420, or any combination thereof. The UE 115, the AMF entity 405, and the centralized core network entity 410 may be as described in reference Figure 2 The UE 115, AMF entity 205, centralized core network entity 210 and NRF entity are described. Another network entity 420 can be an example of another network entity such as SMF, consumer, etc. The process and signaling of the network-initiated machine learning model configuration 400 are exemplary and may occur in a different order in other examples. In some cases, some additional signaling or procedures not shown may be performed, or some signaling or procedures shown may not be performed in other examples.

[0141] The UE 115 or the core network may initiate a procedure for configuring the machine learning model to the UE 115 in order to perform analysis. The network-initiated machine learning model configuration 400 shows an example in which a centralized core network entity 410 receives an analysis request 425 from another network entity 420 to obtain analysis based on a machine learning model. The other network entities 420 may be, for example, an AMF entity 405, an SMF entity, a PCF entity, an OAM entity, or an application function entity that may transmit analysis requests 425 for different purposes. For example, the AMF entity 405 may request to know the access UE 115 in a specific registration area or a specific network slice so that the AMF entity 405 can adjust the network resource allocation for these registration areas or slices. In another example, the SMF entity may request information about the service experience of the UE 115 in a specific registration area or a specific network slice so that the SMF entity can adjust the resource allocation for data transmission.

[0142] In some cases, the analysis request 425 may include an event filter that specifies how to obtain analysis based on a machine learning model. The analysis request 425 may request analysis for one or more specific registration area lists, one or more specific network slices, or both. Additionally or alternatively, the analysis request 425 may indicate one or more specific UEs 115, groups of UEs 115, or both. In some cases, the analysis request 425 may include the SUPI of one or more UEs 115 or groups of UEs 115. In some examples, different analysis operations may correspond to different analysis identifiers. The analysis request 425 may include analysis identifiers corresponding to the analysis requested to be performed by one or more UEs 115, such as analysis identifiers corresponding to different service exchange operations or network load analysis operations.

[0143] In some cases, the centralized core network entity 410 may identify the UE 115 to perform analysis based on the machine learning model. The centralized core network entity 410 may determine to activate the machine learning model in one or more UEs 115 to obtain the analysis. In some cases, the centralized core network entity 410 may identify the UE 115 based on a specific UE identifier or UE group identifier included in the analysis request 425. Additionally or alternatively, the centralized core network entity 410 may identify the AMF entity in the list of network slices or registration areas identified by the analysis request 425, and the centralized core network entity 410 may request the AMF entity 405 to indicate the UE 115 that supports the requested machine learning model.

[0144] For example, the centralized core network entity 410 may identify one or more AMF entities serving the UE 115 that supports the requested machine learning model by communicating with the NRF entity 415. The centralized core network entity 410 may transmit a discovery request 430, such as Nnrf_AMFDiscover_Request, to the NRF entity 415. The discovery request 430 may indicate one or more registration area lists or one or more network slice identifiers based on the event filter received in the analysis request 425. In some cases, the centralized core network entity 410 may include a ratio or number of AMF entities in the discovery request 430. In some examples, the centralized core network entity 410 may identify the served AMF entity 405 from a unified data management (UDM) entity. If the analysis request 425 includes a group identifier, the centralized core network entity 410 may determine the SUPI of the one or more UEs 115 from the UDM entity.

[0145] The NRF entity 415 may identify an AMF entity based on the discovery request 430. In some cases, the NRF entity 415 may identify an AMF entity that serves the UE 115 that supports the requested machine learning model, or the NRF entity 415 may identify an AMF entity associated with the indicated network slice or registration area list, or both. The NRF entity 415 may send a discovery response 435 indicating the identified AMF entity including at least the AMF entity 405 to the centralized core network entity 410. The discovery response 435 may include an AMF identifier that serves the requested registration area list, network slice, or both. If the discovery request 430 includes a ratio or number of AMF entities, the discovery response 435 may include the number or portion of the AMF entities.

[0146] In some cases, the centralized core network entity 410 may transmit a subscriber request 440 to one or more AMF entities including the AMF entity 405. The subscriber request 440 may include a network slice identifier, a registration area list, a machine learning model identifier of the requested machine learning model, or any combination thereof. The centralized core network entity 410 may select a list of UEs based on criteria, such as UEs 115 that support a certain machine learning model (e.g., for providing the requested type of analysis or inference) or UEs 115 within a certain geographic area, registration area, or network slice. For example, the criteria may be that the UE 115 is registered in a specified registration area list, a specific slice is activated, and that the UE supports the requested ML model.

[0147] In some cases, the subscriber request 440 may request the AMF entity 405 to report the UE identifiers of the UEs 115 that support the requested machine learning model. The AMF entity 405 may send a subscriber notification 445 in response to the subscriber request 440. The subscriber notification 445 may include the UE identifiers of one or more UEs 115 that support the requested machine learning model. In some cases, if the centralized core network entity 410 requests or provides partial UE information, the AMF entity 405 may select the UE 115 to be indicated in the subscriber notification 445. In some cases, Nafm_EventExposure_Subscribe may be an example of a subscriber request 440, and Namf_EventExposure_Notify may be an example of a subscriber notification 445.

[0148] The centralized core network entity 410 may transmit control signaling 450 to configure the machine learning model at the one or more UEs 115 identified including the UE 115. The centralized core network entity 410 may send a NAS message or a message with a container configured according to the centralized core network entity 410 to the UE 115. The control signaling 450 may include a machine learning model identifier of the requested machine learning model, a machine learning model file address, a version of the machine learning model, a time or duration for performing analysis according to the machine learning model, an event filter, a machine learning model training request, a machine learning model inference request, or any combination thereof.

[0149] The event filters may indicate when to activate the machine learning model (such as activating the machine learning model after downloading the machine learning model, activating the machine learning model within an indicated time interval), the machine learning model expiration time, or any combination thereof, as well as other event filters. The machine learning model file address may be, for example, a URL or FQDN that the UE 115 can use to obtain or download the machine learning model from the core network. The machine learning model training request and the machine learning model inference request may indicate to the UE 115 how to use the machine learning model. For example, the machine learning model configuration information may request that the UE 115 perform additional training on the machine learning model or that the UE 115 perform inference based on the machine learning model.

[0150] In some cases, the machine learning model configuration information may indicate an analysis identifier of the associated model. For example, the machine learning model configuration information may request that the UE 115 perform a certain type of analysis, provide a certain type of information, inference or analysis, or use the model to perform a certain type of training, or any combination thereof. The analysis identifier may be associated with the analysis request, wherein the machine learning model configuration includes the stored address of the machine learning model file, the validity time, the machine learning model identifier for identifying the machine learning model, and the corresponding analysis identifier of the machine learning model. In some cases, the machine learning model configuration information may include a set of parameters for using the machine learning model. For example, the UE 115 may use the machine learning model based on the included set of parameters to perform analysis, inference, or training based on the set of parameters.

[0151] In some cases, the centralized core network entity 410 may transmit a container or a message with a container to the AMF entity 405. By transmitting the machine learning model configuration in the message with the container, the machine learning model configuration may be transparent to the AMF entity 405. The AMF entity 405 may send or forward the container to the UE 115 via a NAS message. Based on the machine learning model configuration being transmitted via a NAS message, the AMF entity 405 may forward the machine learning model configuration to the UE 115 without knowing the information included in the NAS signaling. In some cases, the centralized core network entity 410 may send control signaling 450 to the UE 115 via the AMF entity 405. For example, the centralized core network entity 410 may transmit the control signaling 450 to the AMF entity 405 in a container or a message with a container, and the AMF may forward the control signaling 450 to the UE 115 via a NAS message. The control signaling 450 may be, for example, NAS signaling including the machine learning model configuration. NAS signaling may be forwarded from the AMF entity 405 to the UE 115, wherein the machine learning model configuration may be transparent to the AMF entity 405. The centralized core network entity 410 may transmit control signaling 450 to one or more UEs 115 identified by the analysis request 425, identified by the AMF entity 405, or identified by the centralized core network entity 410 based on the UE information provided by the AMF entity 405. In some cases, Namf_Communication_N1N2MessageSubscribe may be an example of a container or a message having a container. In some examples, the AMF entity 405 may transmit a UE configuration update message including the control signaling 450 to the UE 115.

[0152] UE 115 may receive control signaling 450 indicating configuration of a machine learning model at UE 115, the machine learning model included in a set of one or more machine learning models supported at UE 115. Control signaling 450 may include machine learning model information. In some cases, UE 115 may obtain the machine learning model based on the machine learning model information. For example, UE 115 may download the machine learning model from the core network based on an address or location included in the machine learning model configuration information. In some cases, UE 115 may transmit a completion message or message notification 455 to AMF entity 405. In some cases, the completion message may be a NAS message, and the AMF entity may transmit the completion message to the centralized core network entity 410. In some examples, Namf_Communication_N1N2Message_Notif may be an example of a message notification 455. Additionally or alternatively, UE 115 may transmit a UE configuration update completion message including a message notification 455 to AMF entity 405. In some examples, the AMF entity 405 may transparently forward the message notification 455 to the centralized core network entity 410.

[0153] At 460, UE 115 may perform analysis based on the machine learning model. For example, UE 115 may perform inference based on the machine learning model, train the machine learning model, or analyze network conditions based on the machine learning model. In some examples, UE 115 may send a report of the analysis to the core network, such as by transmitting a report 465 to AMF entity 405. In some cases, AMF entity 405 may transmit the report to centralized core network entity 410 or another network entity 420 or both. In some cases, the core network may perform core network optimization based on the report.

[0154] Figure 5 An example of UE-initiated machine learning model configuration 500 supporting centralized machine learning model configuration according to various aspects of the present disclosure is illustrated.

[0155] The UE-initiated machine learning model configuration 500 may be implemented by the UE 115, the AMF entity 505, the centralized core network entity 510, the NRF entity 515, or any combination thereof. The UE 115, the AMF entity 505, and the centralized core network entity 510 may be as described in reference Figure 2 The corresponding examples of the UE 115, AMF entity 205, centralized core network entity 210 and NRF entity are described. The process and signaling of the UE-initiated machine learning model configuration 500 are exemplary and may occur in a different order in other examples. In some cases, some additional signaling or procedures not shown may be performed, or some signaling or procedures shown may not be performed in other examples.

[0156] The UE 115 or the core network may initiate a procedure for configuring the machine learning model to the UE 115 in order to perform analysis. UE-initiated machine learning model configuration 500 shows an example of a UE 115 sending a request for the core network to provide information about the machine learning model. The UE 115 may send a request 520 to the AMF entity 505. The request 520 may be an NAS message. A service request message or a registration request message may be an example of the request 520. The request 520 may include an identifier for requesting the machine learning model. In some cases, the UE 115 may include a network slice identifier in the request 520.

[0157] The AMF entity 505 may identify a centralized core network entity, such as the centralized core network entity 510, that supports the requested machine learning model based on receiving the request 520. In some cases, the AMF entity 505 may identify the centralized core network entity 510 via the NRF entity 515. The AMF entity 505 may send a discovery request 525 identifying the centralized core network entity 510 to the NRF entity 515. The discovery request 525 may include a machine learning model identifier, a registration area, a network slice identifier, or any combination thereof. In response, the NRF entity 515 may transmit a discovery response 530 to the AMF entity 505. The discovery response 530 may include an identifier of the centralized core network entity 510.

[0158] The AMF entity 505 may forward the request 520 to the centralized core network entity 510 identified by the discovery response 530. For example, the AMF entity 505 may transmit a model request 535 to the centralized core network entity 510. The model request 535 may include a machine learning model identifier, a registration area identifier, a network slice identifier, or any combination thereof. In some cases, Nnf_EventExposure_Subscribe may be an example of a model request 535.

[0159] The centralized core network entity 510 may transmit control signaling 540 including information about the machine learning model to the UE 115. The control signaling 540 may include a machine learning model identifier, a valid time of the machine learning model, a version of the machine learning model, a file address or location of the machine learning model, an event filter, or any combination thereof. In some cases, the centralized core network entity 510 may transmit the machine learning model information to the AMF entity 505, and the AMF may forward the machine learning model information to the UE 115 via a NAS message. In some cases, the AMF entity 505 may send a service acceptance message to the UE 115. In some cases, the service acceptance message may include the control signaling 540 or the NAS message or both, or an example thereof.

[0160] UE 115 may receive control signaling 540 indicating a configuration for a machine learning model at UE 115, the machine learning model included in a set of one or more machine learning models supported at UE 115. Control signaling 540 may include machine learning model information. In some cases, UE 115 may obtain the machine learning model based on the machine learning model information. For example, UE 115 may download the machine learning model from the core network based on an address or location included in the machine learning model configuration information.

[0161] At 545, UE 115 may perform analysis based on the machine learning model. For example, UE 115 may perform inference based on the machine learning model, train the machine learning model, or analyze network conditions based on the machine learning model. In some cases, UE 115 may perform UE-side optimization based on the analysis.

[0162] Figure 6 An example of a machine learning process 600 supporting centralized machine learning model configuration according to aspects of the present disclosure is illustrated. The machine learning process 600 may be implemented at a device 650, which may be a device such as the one described in reference Figures 1 to 5 Examples of the core network entity or UE 115 or both described herein. In some examples, UE 115 can perform techniques of machine learning process 600 to perform analysis, inference, or training based on a machine learning model. In some examples, the machine learning model can be configured to UE 115 according to the techniques described herein via a centralized core network entity that can manage machine learning model functions within the core network.

[0163] The machine learning process 600 may include a machine learning algorithm 610. The machine learning algorithm 610 may be implemented by the device 650. As illustrated, the machine learning algorithm 610 may be an example of a neural network, such as a feedforward (FF) or deep feedforward (DFF) neural network, a recurrent neural network (RNN), a long / short term memory (LSTM) neural network, or any other type of neural network. However, any other machine learning algorithm may also be supported. For example, the machine learning algorithm 610 may implement a nearest neighbor algorithm, a linear regression algorithm, a naive Bayes algorithm, a random forest algorithm, or any other machine learning algorithm. In addition, the machine learning process 600 may involve supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or any combination thereof.

[0164] The machine learning algorithm 610 may include an input layer 615, one or more hidden layers 620, and an output layer 625. In a fully connected neural network with one hidden layer 620, each hidden layer node 635 may receive a value as an input from each input layer node 630, where each input may be weighted. These neural network weights may be based on a cost function modified during training of the machine learning algorithm 610. Similarly, each output layer node 640 may receive a value as an input from each hidden layer node 635, where the input is weighted. If post-deployment training (e.g., online training) is supported, memory may be allocated to store errors and / or gradients of inverse matrix multiplications. These errors and / or gradients may support updating the machine learning algorithm 610 based on output feedback. Training the machine learning algorithm 610 may support the calculation of weights (e.g., connecting the input layer node 630 to the hidden layer node 635 and connecting the hidden layer node 635 to the output layer node 640) to map the input pattern to the desired output result. The training may generate a device-specific machine learning algorithm 610 based on historical application data and data transfer for a particular network entity 105 or UE 115 .

[0165] In some examples, the input value 605 may be transmitted to the machine learning algorithm 610 for processing. In some examples, the input value 605 may be pre-processed according to the sequence of operations so that the input value 605 may be in a format compatible with the machine learning algorithm 610. The input value 605 may be converted into a set of k input layer nodes 630 at the input layer 615. In some cases, different measurements may be input at different input layer nodes 630 of the input layer 615. If the number of input layer nodes 630 exceeds the number of inputs corresponding to the input value 605, some input layer nodes 630 may be assigned default values ​​(e.g., value 0). As illustrated, the input layer 615 may include three input layer nodes 630-a, 630-b, and 630-c. However, it should be understood that the input layer 615 may include any number of input layer nodes 630 (e.g., 20 input nodes).

[0166] The machine learning algorithm 610 may convert the input layer 615 into a hidden layer 620 based on the number of input-to-hidden weights between the k input layer nodes 630 and the n hidden layer nodes 635. The machine learning algorithm 610 may include any number of hidden layers 620 as an intermediate step between the input layer 615 and the output layer 625. Additionally, each hidden layer 620 may include any number of nodes. For example, as illustrated in the figure, the hidden layer 620 may include four hidden layer nodes 635-a, 635-b, 635-c, and 635-d. However, it should be understood that the hidden layer 620 may include any number of hidden layer nodes 635 (e.g., 10 input nodes). In a fully connected neural network, each node in a layer may be based on each node in a previous layer. For example, the value of a hidden layer node 635-a may be based on the value of input layer nodes 630-a, 630-b, and 630-c (e.g., where different weights are applied to each node value).

[0167] The machine learning algorithm 610 may determine the value of an output layer node 640 of an output layer 625 following one or more hidden layers 620. For example, the machine learning algorithm 610 may convert a hidden layer 620 into an output layer 625 based on the number of hidden-to-output weights between n hidden layer nodes 635 and m output layer nodes 640. In some cases, n=m. Each output layer node 640 may correspond to a different output value 645 of the machine learning algorithm 610. As illustrated, the machine learning algorithm 610 may include three output layer nodes 640-a, 640-b, and 640-c, which support three different thresholds. However, it should be understood that the output layer 625 may include any number of output layer nodes 640. In some examples, post-processing may be performed on the output value 645 according to the sequence of operations so that the output value 645 may be in a format compatible with the report output value 645.

[0168] Figure 7 A block diagram 700 of a device 705 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 705 can be an example of aspects of the 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).

[0169] 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 centralized machine learning model configurations). The information may be communicated to other components of device 705. Receiver 710 may utilize a single antenna or a set of multiple antennas.

[0170] 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 centralized machine learning model configuration). 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 set of multiple antennas.

[0171] The communication manager 720, the receiver 710, the transmitter 715, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the centralized machine learning model configuration as described herein. For example, the communication manager 720, the receiver 710, the transmitter 715, or various combinations thereof or components thereof may support methods for performing one or more of the functions described herein.

[0172] In some examples, the communication manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a digital signal processor (DSP), a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured to or otherwise supports components for performing the functions described 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).

[0173] Additionally or alternatively, in some examples, the communication manager 720, the receiver 710, the transmitter 715, 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 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the 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 elements.

[0174] In some examples, the communication manager 720 can be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with the receiver 710, the transmitter 715, or both. For example, the communication manager 720 can 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.

[0175] According to examples as disclosed herein, the communication manager 720 may support wireless communications at a UE. For example, the communication manager 720 may be configured to or otherwise support components for sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity. The communication manager 720 may be configured to or otherwise support components for receiving control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The communication manager 720 may be configured to or otherwise support components for performing analysis based on the machine learning model.

[0176] By including or configuring the communication manager 720 according to the examples described herein, the device 705 (e.g., a processor controlling the receiver 710, the transmitter 715, the communication manager 720, or a combination thereof or otherwise coupled thereto) may support techniques for reducing power consumption by identifying optimizations at the device 705 based on performing inference using a machine learning model.

[0177] Figure 8 A block diagram 800 of a device 805 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 805 can be an example of aspects of the device 705 or UE 115 as described herein. The device 805 may include a receiver 810, a transmitter 815, and a communication manager 820. The device 805 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0178] The receiver 810 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 centralized machine learning model configurations). The information may be communicated to other components of the device 805. The receiver 810 may utilize a single antenna or a set of multiple antennas.

[0179] The transmitter 815 may provide means for transmitting signals generated by other components of the device 805. For example, the transmitter 815 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 centralized machine learning model configuration). In some examples, the transmitter 815 may be co-located with the receiver 810 in a transceiver module. The transmitter 815 may utilize a single antenna or a set of multiple antennas.

[0180] Device 805 or its various components may be examples of components for performing various aspects of centralized machine learning model configuration as described herein. For example, communication manager 820 may include machine learning model capability component 825, model configuration component 830, analysis component 835, or any combination thereof. Communication manager 820 may be an example of various aspects of communication manager 720 as described herein. In some examples, communication manager 820 or its various components may be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise in conjunction with receiver 810, transmitter 815, or both. For example, communication manager 820 may receive information from receiver 810, transmit information to transmitter 815, or be integrated with receiver 810, transmitter 815, or both to obtain information, output information, or perform various other operations as described herein.

[0181] According to examples as disclosed herein, the communication manager 820 may support wireless communications at a UE. The machine learning model capability component 825 may be configured as or otherwise support components for sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity. The model configuration component 830 may be configured as or otherwise support components for receiving control signaling from the first core network entity indicating configuration for a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The analysis component 835 may be configured as or otherwise support components for performing analysis based on the machine learning model.

[0182] Fig. 9A block diagram 900 of a communication manager 920 supporting centralized machine learning model configuration in accordance with one or more aspects of the present disclosure is shown. The communication manager 920 may be an example of aspects of the communication manager 720, the communication manager 820, or both as described herein. The communication manager 920 or its various components may be examples of components for performing various aspects of centralized machine learning model configuration as described herein. For example, the communication manager 920 may include a machine learning model capability component 925, a model configuration component 930, an analysis component 935, a request component 940, a completion message component 945, a model acquisition component 950, or any combination thereof. Each of these components may communicate with each other directly or indirectly (e.g., via one or more buses).

[0183] According to examples as disclosed herein, the communication manager 920 may support wireless communications at a UE. The machine learning model capability component 925 may be configured as or otherwise support components for sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity. The model configuration component 930 may be configured as or otherwise support components for receiving control signaling from the first core network entity indicating configuration for a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The analysis component 935 may be configured as or otherwise support components for performing analysis based on the machine learning model.

[0184] In some examples, request component 940 may be configured or otherwise support components for sending a request for a machine learning model to a first core network entity. In some examples, model configuration component 930 may be configured or otherwise support components for receiving control signaling in response to the request.

[0185] In some examples, to support sending the request, request component 940 can be configured or otherwise support components for sending a service request message. In some examples, to support sending the request, model configuration component 930 can be configured or otherwise support components for receiving control signaling via a service response message. In some examples, the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0186] In some examples, completion message component 945 may be configured as or otherwise support components for sending a completion message to the first core network entity based on control signaling indicating configuration of a machine learning model at the UE.

[0187] In some examples, to support receiving control signaling, the model configuration component 930 may be configured as or otherwise support a component for receiving control signaling indicating a configuration for a machine learning model, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing analysis, an activation event for reporting analysis, or any combination thereof.

[0188] In some examples, to support receiving control signaling, model configuration component 930 can be configured or otherwise support components for receiving one or more parameters of a machine learning model. In some examples, to support receiving control signaling, analysis component 935 can be configured or otherwise support components for performing analysis based on one or more parameters.

[0189] In some examples, model acquisition component 950 may be configured or otherwise support components for obtaining a machine learning model from a core network based on an address indicated via control signaling. In some examples, analysis component 935 may be configured or otherwise support components for sending a NAS message to a first core network entity, the NAS message including information determined from performing analysis based on the machine learning model.

[0190] In some examples, to support receiving control signaling, the model configuration component 930 may be configured as or otherwise support components for receiving a NAS message configured according to a core network centralized entity container, the NAS message indicating a configuration for a machine learning model at the UE. In some examples, the first core network entity is an AMF entity.

[0191] Fig.10 A diagram of a system 1000 including a device 1005 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1005 may be an example of a device 705, a device 805, or a UE 115 as described herein, or include components thereof. The device 1005 may communicate (e.g., wirelessly) with one or more network entities 105, one or more UEs 115, or any combination thereof. The device 1005 may include components for two-way voice and data communications, including components for sending and receiving communications, such as a communication manager 1020, an input / output (I / O) controller 1010, a transceiver 1015, an antenna 1025, a memory 1030, a code 1035, and a processor 1040. 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 1045).

[0192] I / O controller 1010 can manage input and output signals for device 1005. I / O controller 1010 can also manage peripheral devices that are not integrated into device 1005. In some cases, I / O controller 1010 can represent a physical connection or port to an external peripheral device. In some cases, I / O controller 1010 can utilize an operating system such as or another known operating system. Additionally or alternatively, I / O controller 1010 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, I / O controller 1010 may be implemented as part of a processor such as processor 1040. In some cases, a user may interact with device 1005 via I / O controller 1010 or via hardware components controlled by I / O controller 1010.

[0193] In some cases, the device 1005 may include a single antenna 1025. However, in some other cases, the device 1005 may have more than one antenna 1025, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 1015 may communicate bidirectionally via one or more antennas 1025, a wired or wireless link, as described herein. For example, the transceiver 1015 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1015 may also include a modem for: modulating packets; providing the modulated packets to one or more antennas 1025 for transmission; and demodulating packets received from one or more antennas 1025. The transceiver 1015 or the transceiver 1015 and one or more antennas 1025 may be examples of transmitters 715, transmitters 815, receivers 710, receivers 810, or any combination thereof or any components thereof as described herein.

[0194] The memory 1030 may include random access memory (RAM) and read-only memory (ROM). The memory 1030 may store computer-readable, computer-executable code 1035 including instructions that, when executed by the processor 1040, cause the device 1005 to perform various functions described herein. The code 1035 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 1035 may not be directly executable by the processor 1040, but may (for example, when compiled and executed) cause the computer to perform the functions described herein. In some cases, among other things, the memory 1030 may include a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0195] Processor 1040 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, processor 1040 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into processor 1040. Processor 1040 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1030) to cause device 1005 to perform various functions (e.g., functions or tasks that support centralized machine learning model configuration). For example, device 1005 or a component of device 1005 may include processor 1040 and memory 1030 coupled to or coupled to processor 1040, and processor 1040 and memory 1030 are configured to perform the various functions described herein.

[0196] According to examples as disclosed herein, the communication manager 1020 may support wireless communications at a UE. For example, the communication manager 1020 may be configured to or otherwise support components for sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity. The communication manager 1020 may be configured to or otherwise support components for receiving control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The communication manager 1020 may be configured to or otherwise support components for performing analysis based on the machine learning model.

[0197] By including or configuring the communications manager 1020 according to examples as described herein, the device 1005 may support techniques for improving coordination between devices by identifying optimizations at the UE 115 or the core network, or both, based on the UE 115 using machine learning models to perform inferences and analysis.

[0198] In some examples, the communication manager 1020 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 1015, one or more antennas 1025, or any combination thereof. Although the communication manager 1020 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1020 may be supported or performed by the processor 1040, the memory 1030, the code 1035, or any combination thereof. For example, the code 1035 may include instructions executable by the processor 1040 to cause the device 1005 to perform various aspects of the centralized machine learning model configuration as described herein, or the processor 1040 and the memory 1030 may be otherwise configured to perform or support such operations.

[0199] Fig.11 A block diagram 1100 of a device 1105 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1105 can be an example of aspects of the 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).

[0200] 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.

[0201] 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.

[0202] The communication manager 1120, the receiver 1110, the transmitter 1115, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the centralized machine learning model configuration as described herein. For example, the communication manager 1120, the receiver 1110, the transmitter 1115, or various combinations thereof or components thereof may support methods for performing one or more of the functions described herein.

[0203] In some examples, the communication manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof that is configured as or otherwise supports components for performing the functions described herein. In some examples, a processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0204] Additionally or alternatively, in some examples, the communication manager 1120, the receiver 1110, the transmitter 1115, 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 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic elements.

[0205] In some examples, communication manager 1120 may be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with receiver 1110, transmitter 1115, or both. For example, communication manager 1120 may receive information from receiver 1110, transmit information to transmitter 1115, or be integrated in conjunction with receiver 1110, transmitter 1115, or both to obtain information, output information, or perform various other operations as described herein.

[0206] According to examples as disclosed herein, the communication manager 1120 may support wireless communications. For example, the communication manager 1120 may be configured to or otherwise support components for obtaining an indication of a first set of one or more machine learning models supported at the UE. The communication manager 1120 may be configured to or otherwise support components for obtaining control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE. The communication manager 1120 may be configured to or otherwise support components for outputting a NAS message including control signaling configured according to the second core network entity.

[0207] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1120 may support wireless communication at the second core network entity. For example, the communication manager 1120 may be configured to or otherwise support a component for identifying a UE that supports configuration of a machine learning model at the UE. The communication manager 1120 may be configured to or otherwise support a component for outputting control signaling configured according to the second core network entity to the first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0208] By including or configuring the communication manager 1120 according to the examples described herein, the device 1105 (e.g., a processor controlling the receiver 1110, the transmitter 1115, the communication manager 1120, or a combination thereof or otherwise coupled thereto) may support techniques for reducing processing and more efficiently utilizing communication resources based on inferences determined based on machine learning models reported from the UE 115.

[0209] Fig.12 A block diagram 1200 of a device 1205 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1205 can be an example of aspects of the device 1105 or network entity 105 as described herein. The device 1205 may include a receiver 1210, a transmitter 1215, and a communication manager 1220. The device 1205 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0210] Receiver 1210 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 1205. In some examples, receiver 1210 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1210 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof.

[0211] The transmitter 1215 may provide means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1205. For example, the transmitter 1215 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 1215 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1215 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 1215 and the receiver 1210 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0212] Device 1205 or its various components may be examples of components for performing various aspects of centralized machine learning model configuration as described herein. For example, communication manager 1220 may include machine learning model capability component 1225, model configuration component 1230, control signaling component 1235, UE identification component 1240, configuration model component 1245, or any combination thereof. Communication manager 1220 may be an example of various aspects of communication manager 1120 as described herein. In some examples, communication manager 1220 or its various components may be configured to use or otherwise cooperate with receiver 1210, transmitter 1215, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, communication manager 1220 may receive information from receiver 1210, transmit information to transmitter 1215, or be integrated with receiver 1210, transmitter 1215, or both to obtain information, output information, or perform various other operations as described herein.

[0213] According to examples as disclosed herein, the communication manager 1220 may support wireless communications. The machine learning model capability component 1225 may be configured to or otherwise support components for obtaining an indication of a first set of one or more machine learning models supported at the UE. The model configuration component 1230 may be configured to or otherwise support components for obtaining control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE. The control signaling component 1235 may be configured to or otherwise support components for outputting a NAS message including control signaling configured according to the second core network entity.

[0214] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1220 may support wireless communication at the second core network entity. The UE identification component 1240 may be configured to or otherwise support components for identifying a UE that supports configuration of a machine learning model at the UE. The configuration model component 1245 may be configured to or otherwise support components for outputting control signaling configured according to the second core network entity to the first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0215] Fig.13 A block diagram 1300 of a communication manager 1320 supporting centralized machine learning model configuration in accordance with one or more aspects of the present disclosure is shown. The communication manager 1320 can be an example of aspects of the communication manager 1120, the communication manager 1220, or both as described herein. The communication manager 1320 or its various components can be examples of components for performing various aspects of centralized machine learning model configuration as described herein. For example, the communication manager 1320 can include a machine learning model capability component 1325, a model configuration component 1330, a control signaling component 1335, a UE identification component 1340, a configuration model component 1345, a model request component 1350, an analysis request component 1355, a completion message component 1360, an analysis report component 1365, and a discovery component 1370, or any combination thereof. Each of these components may communicate directly or indirectly with each other (e.g., via one or more buses), which communication may include communication within a protocol layer of a protocol stack, communication associated with a logical channel of 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.

[0216] According to examples as disclosed herein, the communication manager 1320 may support wireless communications. The machine learning model capability component 1325 may be configured to or otherwise support components for obtaining an indication of a first set of one or more machine learning models supported at the UE. The model configuration component 1330 may be configured to or otherwise support components for obtaining control signaling configured according to the second core network entity from the second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE. The control signaling component 1335 may be configured to or otherwise support components for outputting a NAS message including control signaling configured according to the second core network entity.

[0217] In some examples, model request component 1350 can be configured or otherwise support components for obtaining a request for a machine learning model. In some examples, model request component 1350 can be configured or otherwise support components for outputting an indication of a request for a machine learning model to a second core network entity. In some examples, model configuration component 1330 can be configured or otherwise support components for obtaining control signaling based on the indication.

[0218] In some examples, discovery component 1370 may be configured to or otherwise support components for outputting a discovery request for the second core network entity to the third core network entity. In some examples, discovery component 1370 may be configured to or otherwise support components for obtaining an identifier of the second core network entity from the third core network entity based on the discovery request. In some examples, the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0219] In some examples, analysis request component 1355 may be configured or otherwise support components for obtaining a request from a second core network entity for one or more UEs to perform analysis based on a machine learning model. In some examples, analysis request component 1355 may be configured or otherwise support components for outputting a NAS message to a UE based on the request.

[0220] In some examples, the analysis request component 1355 can be configured to or otherwise support a component for outputting to the second core network entity one or more identifiers of a group of one or more UEs associated with the first core network entity that support the machine learning model, the group of UEs including at least the UE. In some examples, the request for the one or more UEs to perform analysis includes one or more UE identifiers associated with the one or more UEs, one or more registration area lists, one or more network slice identifiers, or any combination thereof.

[0221] In some examples, analysis request component 1355 may be configured or otherwise support components for identifying one or more UEs including at least the UE based on the request.

[0222] In some examples, to support output control signaling, model configuration component 1330 may be configured as or otherwise support components for outputting a NAS message including control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing analysis, an activation event for reporting analysis, one or more parameters of the machine learning model, or any combination thereof.

[0223] In some examples, completion message component 1360 may be configured or otherwise support components for obtaining a completion message in response to a NAS message. In some examples, completion message component 1360 may be configured or otherwise support components for outputting a completion message to a second core network entity.

[0224] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1320 may support wireless communication at the second core network entity. The UE identification component 1340 may be configured to or otherwise support components for identifying a UE that supports configuration of a machine learning model at the UE. The configuration model component 1345 may be configured to or otherwise support components for outputting control signaling configured according to the second core network entity to the first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0225] In some examples, model request component 1350 may be configured or otherwise support components for obtaining an indication of a request for a machine learning model from the UE from the first core network entity. In some examples, UE identification component 1340 may be configured or otherwise support components for identifying the UE based on the indication of the request. In some examples, to support obtaining the indication, model request component 1350 may be configured or otherwise support components for obtaining a NAS message via the first core network entity, the NAS message including the request.

[0226] In some examples, the analysis request component 1355 may be configured as or otherwise support a component for obtaining a request from another network entity for one or more UEs to perform analysis based on a machine learning model. In some examples, to support identifying the UE, the discovery component 1370 may be configured as or otherwise support a component for outputting a request message to one or more network entities including at least a second core network entity for the one or more network entities to report a UE identifier of a UE that supports the machine learning model. In some examples, to support identifying the UE, the discovery component 1370 may be configured as or otherwise support a component for obtaining a response message from at least a second core network entity indicating a group of UEs including at least the UE. In some examples, the request message includes one or more registration area lists, one or more network slice identifiers, and an identifier of the machine learning model.

[0227] In some examples, discovery component 1370 may be configured to or otherwise support a component for outputting a discovery request for one or more network entities to a third core network entity, the discovery request including one or more registration area lists or one or more network slice identifiers or both. In some examples, discovery component 1370 may be configured to or otherwise support a component for obtaining, from the third core network entity, a discovery response message indicating one or more network entities including at least the second core network entity, wherein the one or more network entities correspond to one or more registration area lists or one or more network slice identifiers or both.

[0228] In some examples, a request for one or more UEs to perform analysis includes one or more UE identifiers, UE group identifiers, or both, of the one or more UEs, where the UEs are identified based on the request.

[0229] In some examples, to support output control signaling, configuration model component 1345 may be configured as or otherwise support components for output control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing analysis, an activation event for reporting analysis, one or more parameters of the machine learning model, or any combination thereof.

[0230] In some examples, analysis reporting component 1365 may be configured to or otherwise support components for obtaining, via the first core network entity, a NAS message that includes information determined at the UE by performing analysis based on a machine learning model.

[0231] Fig.14 A diagram of a system 1400 including a device 1405 supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1405 may be an example of a device 1105, a device 1205, or a network entity 105 as described herein, or include components thereof. The device 1405 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 1405 may include components that support output and acquisition of communications, such as a communication manager 1420, a transceiver 1410, an antenna 1415, a memory 1425, a code 1430, and a processor 1435. 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 1440).

[0232] The transceiver 1410 may support bidirectional communication via a wired link, a wireless link, or both as described herein. In some examples, the transceiver 1410 may include a wired transceiver and may communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, the transceiver 1410 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1405 may include one or more antennas 1415, which may be capable of sending or receiving wireless transmissions (e.g., concurrently). The transceiver 1410 may also include a modem for: modulating a signal; providing the modulated signal for transmission (e.g., by one or more antennas 1415, by a wired transmitter); receiving the modulated signal (e.g., from one or more antennas 1415, from a wired receiver); and demodulating the signal. Where applicable, transceiver 1410 or transceiver 1410 and one or more antennas 1415 or wired interfaces may be examples of transmitter 1115, transmitter 1215, receiver 1110, receiver 1210, or any combination thereof or any components thereof as described herein. In some examples, the transceiver may be operable to support communication via one or more communication links (e.g., communication link 125, backhaul communication link 120, midhaul communication link 162, fronthaul communication link 168).

[0233] Memory 1425 may include RAM and ROM. Memory 1425 may store computer-readable, computer-executable code 1430 including instructions that, when executed by processor 1435, cause device 1405 to perform various functions described herein. Code 1430 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1430 may not be directly executable by processor 1435, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, among other things, memory 1425 may also include BIOS, which may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0234] Processor 1435 may include an intelligent hardware device (e.g., a general-purpose processor, DSP, ASIC, CPU, FPGA, microcontroller, programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof). In some cases, processor 1435 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into processor 1435. Processor 1435 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1425) to cause device 1405 to perform various functions (e.g., functions or tasks supporting centralized machine learning model configuration). For example, device 1405 or a component of device 1405 may include processor 1435 and memory 1425 coupled to processor 1435, and processor 1435 and memory 1425 are configured to perform various functions described herein. Processor 1435 may be an example of a cloud computing platform (e.g., one or more physical nodes and supporting software such as an operating system, a virtual machine, or a container instance), which may host functions for performing functions of device 1405 (e.g., by executing code 1430).

[0235] In some examples, bus 1440 may support communications of protocol layers (e.g., within a protocol layer) of a protocol stack. In some examples, bus 1440 may support communications associated with logical channels of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within a component of device 1405 or between different components of device 1405 that may be co-located or located in different locations (e.g., where device 1405 may refer to a system in which one or more of communication manager 1420, transceiver 1410, memory 1425, code 1430, and processor 1435 may be located in one of these different components or divided between different components).

[0236] In some examples, communication manager 1420 may manage aspects of communications with core network 130 (e.g., via one or more wired or wireless backhaul links). For example, communication manager 1420 may manage the transfer of data communications for client devices such as one or more UEs 115. In some examples, communication manager 1420 may manage communications with other network entities 105 and may include a controller or scheduler for controlling communications with UE 115 in coordination with other network entities 105. In some examples, communication manager 1420 may support an X2 interface within an LTE / LTE-A wireless communication network technology to provide communications between network entities 105.

[0237] According to examples as disclosed herein, the communication manager 1420 may support wireless communications. For example, the communication manager 1420 may be configured to or otherwise support components for obtaining an indication of a first set of one or more machine learning models supported at the UE. The communication manager 1420 may be configured to or otherwise support components for obtaining control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first set of one or more machine learning models from the UE. The communication manager 1420 may be configured to or otherwise support components for outputting a NAS message including control signaling configured according to the second core network entity.

[0238] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1420 may support wireless communication at the second core network entity. For example, the communication manager 1420 may be configured to or otherwise support a component for identifying a UE that supports configuration of a machine learning model at the UE. The communication manager 1420 may be configured to or otherwise support a component for outputting control signaling configured according to the second core network entity to the first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0239] By including or configuring the communications manager 1420 according to examples as described herein, the device 1405 may support techniques for improving coordination between devices by identifying optimizations at the UE 115 or the core network, or both, based on the UE 115 using a machine learning model to perform inference or analysis.

[0240] In some examples, the communication manager 1420 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the transceiver 1410, one or more antennas 1415 (e.g., where applicable), or any combination thereof. Although the communication manager 1420 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1420 may be supported or performed by the processor 1435, the memory 1425, the code 1430, the transceiver 1410, or any combination thereof. For example, the code 1430 may include instructions executable by the processor 1435 to cause the device 1405 to perform various aspects of the centralized machine learning model configuration as described herein, or the processor 1435 and the memory 1425 may be otherwise configured to perform or support such operations.

[0241] Fig.15A flowchart illustrating a method 1500 for supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 1500 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1500 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 10 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.

[0242] At 1505, the method may include: sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity. The operations of 1505 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1505 may be performed as described in reference to Fig. 9 The machine learning model capability component 925 is used to execute.

[0243] At 1510, the method may include: receiving control signaling from a first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The operations of 1510 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1510 may be performed as described in reference to Fig. 9 The model configuration component 930 is executed.

[0244] At 1515, the method may include: performing analysis based on the machine learning model. The operations of 1515 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1515 may be performed as described in reference Fig. 9 The analysis component 935 is used to perform the above.

[0245] Fig.16 A flowchart illustrating a method 1600 for supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 1600 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1600 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 10 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.

[0246] At 1605, the method may include: sending an indication of a first set of one or more machine learning models supported at the UE to the first core network entity. The operations of 1605 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1605 may be performed as described in reference to Fig. 9The machine learning model capability component 925 is used to execute.

[0247] At 1610, the method may include: sending a request for a machine learning model to a first core network entity. The operations of 1610 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1610 may be described by reference to Fig. 9 The request component 940 is used for execution.

[0248] At 1615, the method may include: receiving control signaling in response to the sending request. The operations of 1615 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1615 may be performed as described in reference Fig. 9 The model configuration component 930 is executed.

[0249] At 1620, the method may include: receiving control signaling from a first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The operations of 1620 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1620 may be performed as described in reference to Fig. 9 The model configuration component 930 is executed.

[0250] At 1625, the method may include: performing analysis based on the machine learning model. The operations of 1625 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1625 may be performed as described in reference Fig. 9 The analysis component 935 is used to perform the above.

[0251] Fig.17 A flowchart illustrating a method 1700 for supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 1700 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1700 may be implemented by a UE or a component thereof as described in reference to Figures 1 to 10 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.

[0252] At 1705, the method may include: sending an indication of a first set of one or more machine learning models supported at the UE to the first core network entity. The operations of 1705 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1705 may be performed as described in reference to Fig. 9 The machine learning model capability component 925 is used to execute.

[0253] At 1710, the method may include: receiving control signaling from a first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model. The operations of 1710 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed as described in reference to Fig. 9 The model configuration component 930 is executed.

[0254] At 1715, the method may include obtaining a machine learning model from a core network based on an address indicated via control signaling. The operations of 1715 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1715 may be performed as described in reference to Fig. 9 The model is obtained by component 950 for execution.

[0255] At 1720, the method may include: performing analysis based on the machine learning model. The operations of 1720 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1720 may be performed as described in reference Fig. 9 The analysis component 935 is used to perform the above.

[0256] Fig.18 A flowchart illustrating a method 1800 for supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 1800 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1800 may be implemented by a network entity or a component thereof as described in reference to Figures 1 to 6 as well as Figures 11 to 14 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.

[0257] At 1805, the method may include obtaining an indication of a first set of one or more machine learning models supported at the UE. The operations of 1805 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed as described in reference to Fig.13 The machine learning model capability component 1325 is used to execute.

[0258] At 1810, the method may include: obtaining control signaling configured according to the second core network entity from the second core network entity, the control signaling indicating a configuration for a machine learning model of a first set of one or more machine learning models from the UE. The operations of 1810 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed as described in reference to Fig.13 The model configuration component 1330 is executed.

[0259] At 1815, the method may include: outputting a non-access layer message including control signaling configured according to the second core network entity. The operations of 1815 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1815 may be performed as described in reference to Fig.13 The control signaling component 1335 is used to execute.

[0260] Fig.19 A flowchart illustrating a method 1900 for supporting centralized machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 1900 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1900 may be implemented by a network entity or a component thereof as described in reference to Figures 1 to 6 as well as Figures 11 to 14 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.

[0261] At 1905, the method may include: identifying a UE that supports configuration of a machine learning model at the UE. The operations of 1905 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed as described in reference to Fig.13 The UE identification component 1340 is used to perform.

[0262] At 1910, the method may include: outputting control signaling configured according to the second core network entity to the first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model. The operations of 1910 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 1910 may be performed as described in reference to Fig.13 The configuration model component 1345 is executed.

[0263] The following provides an overview of various aspects of the disclosure:

[0264] Aspect 1: A method for wireless communication at a UE, the method comprising: sending an indication of a first set of one or more machine learning models supported at the UE to a first core network entity; receiving control signaling from the first core network entity indicating the configuration of a machine learning model at the UE, the first set of one or more machine learning models including the machine learning model; and performing analysis based at least in part on the machine learning model.

[0265] Aspect 2: According to the method described in Aspect 1, the method also includes: sending a request for the machine learning model to the first core network entity, wherein receiving the control signaling includes: receiving the control signaling in response to sending the request.

[0266] Aspect 3: The method according to aspect 2, wherein sending the request comprises: sending a service request message, and wherein receiving the control signaling comprises: receiving the control signaling via a service response message.

[0267] Aspect 4: A method according to any one of Aspects 2 to 3, wherein the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0268] Aspect 5: According to the method described in any one of Aspects 1 to 4, the method also includes: sending a completion message to the first core network entity based at least in part on the control signaling indicating the configuration of the machine learning model at the UE.

[0269] Aspect 6: A method according to any one of Aspects 1 to 5, wherein receiving the control signaling includes: receiving the control signaling indicating the configuration for the machine learning model, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, or any combination thereof.

[0270] Aspect 7: A method according to any one of Aspects 1 to 6, wherein receiving the control signaling includes: receiving one or more parameters of the machine learning model; and wherein performing the analysis includes: performing the analysis based at least in part on the one or more parameters.

[0271] Aspect 8: According to the method described in any one of Aspects 1 to 7, the method also includes: obtaining the machine learning model from the core network at least in part based on the address indicated via the control signaling.

[0272] Aspect 9: According to the method described in any one of Aspects 1 to 8, the method further includes: sending a non-access stratum message to the first core network entity, wherein the non-access stratum message includes information determined from performing the analysis based at least in part on the machine learning model.

[0273] Aspect 10: A method according to any one of Aspects 1 to 9, wherein receiving the control signaling includes: receiving a non-access stratum message configured according to a core network centralized entity container, the non-access stratum message indicating the configuration of the machine learning model at the UE.

[0274] Aspect 11: The method according to any one of Aspects 1 to 10, wherein the first core network entity is an Access and Mobility Management Function (AMF) entity.

[0275] Aspect 12: A method for wireless communication, the method comprising: obtaining an indication of a first group of one or more machine learning models supported at a UE; obtaining control signaling configured according to the second core network entity from a second core network entity, the control signaling indicating a configuration of a machine learning model for the first group of one or more machine learning models from the UE; and outputting a non-access stratum message including the control signaling configured according to the second core network entity.

[0276] Aspect 13: According to the method described in Aspect 12, the method also includes: obtaining a request for the machine learning model; outputting an indication of the request for the machine learning model to the second core network entity; and wherein obtaining the control signaling includes: obtaining the control signaling based at least in part on the indication.

[0277] Aspect 14: According to the method according to Aspect 13, the method also includes: outputting a discovery request for the second core network entity to a third core network entity; and obtaining an identifier of the second core network entity from the third core network entity at least partially based on the discovery request.

[0278] Aspect 15: A method according to any one of Aspects 13 to 14, wherein the request includes an identifier of the machine learning model, a network slice identifier, or both.

[0279] Aspect 16: According to the method described in any one of Aspects 12 to 15, the method also includes: obtaining a request from the second core network entity for one or more UEs to perform analysis based at least in part on the machine learning model; and wherein outputting the non-access stratum message includes: outputting the non-access stratum message based at least in part on the request.

[0280] Aspect 17: According to the method described in Aspect 16, the method also includes: outputting one or more identifiers of a group of one or more UEs associated with the first core network entity and supporting the machine learning model to the second core network entity, the group of UEs including at least the UE.

[0281] Aspect 18: A method according to any one of Aspects 16 to 17, wherein the request for the one or more UEs to perform analysis includes one or more UE identifiers associated with the one or more UEs, one or more registration area lists, one or more network slice identifiers, or any combination thereof.

[0282] Aspect 19: The method according to any one of aspects 16 to 18, the method further comprising: identifying the one or more UEs including at least the UE based at least in part on the request.

[0283] Aspect 20: A method according to any one of Aspects 12 to 19, wherein outputting the control signaling includes: outputting the non-access layer message including the control signaling, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

[0284] Aspect 21: The method according to any one of aspects 12 to 20, further comprising: obtaining a completion message in response to the non-access stratum message; and outputting the completion message to the second core network entity.

[0285] Aspect 22: A method for performing wireless communications at a second core network entity, the method comprising: identifying a UE that supports configuration of a machine learning model at the UE; and outputting control signaling configured according to the second core network entity to a first core network entity, the control signaling being used to indicate to the UE the configuration for the machine learning model.

[0286] Aspect 23: According to the method according to Aspect 22, the method also includes: obtaining an indication of a request for the machine learning model from the UE from the first core network entity, wherein the UE is identified at least in part based on the indication of the request.

[0287] Aspect 24: The method according to aspect 23, wherein obtaining the indication comprises: obtaining a non-access stratum message via the first core network entity, the non-access stratum message comprising the request.

[0288] Aspect 25: According to the method of any one of Aspects 22 to 24, the method also includes: obtaining a request from another network entity for one or more UEs to perform analysis based at least in part on the machine learning model.

[0289] Aspect 26: A method according to Aspect 25, wherein identifying the UE includes: outputting a request message to one or more network entities including at least the second core network entity, asking the one or more network entities to report the UE identifier of the UE that supports the machine learning model; and obtaining a response message from at least the second core network entity indicating a group of UEs including at least the UE.

[0290] Aspect 27: A method according to Aspect 26, wherein the request message includes one or more registration area lists, one or more network slice identifiers, and an identifier of the machine learning model.

[0291] Aspect 28: According to the method described in any one of Aspects 26 to 27, the method further includes: outputting a discovery request for the one or more network entities to a third core network entity, the discovery request including one or more registration area lists or one or more network slice identifiers or both; and obtaining a discovery response message from the third core network entity indicating the one or more network entities including at least the second core network entity, wherein the one or more network entities correspond to the one or more registration area lists or the one or more network slice identifiers or both.

[0292] Aspect 29: A method according to any one of Aspects 25 to 28, wherein the request for the one or more UEs to perform the analysis includes one or more UE identifiers, UE group identifiers, or both of the one or more UEs, wherein the UE is identified at least in part based on the request.

[0293] Aspect 30: A method according to any one of Aspects 22 to 29, wherein outputting the control signaling includes: outputting the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

[0294] Aspect 31: According to the method described in any one of Aspects 22 to 30, the method also includes: obtaining a non-access stratum message via the first core network entity, the non-access stratum message including information determined at the UE by performing analysis based at least in part on the machine learning model.

[0295] Aspect 32: An apparatus for performing wireless communication at a UE, the apparatus comprising: a processor; and a memory, the memory coupled to the processor, the processor being configured to execute the method according to any one of aspects 1 to 11.

[0296] Aspect 33: An apparatus for wireless communication at a UE, the apparatus comprising: at least one component for performing a method according to any one of aspects 1 to 11.

[0297] Aspect 34: A non-transitory computer-readable medium storing code for wireless communication at a UE, the code comprising instructions executable by a processor to perform the method according to any one of aspects 1 to 11.

[0298] Aspect 35: An apparatus for wireless communication, the apparatus comprising: a processor; and a memory, the memory coupled to the processor, the processor being configured to perform the method according to any one of aspects 12 to 21.

[0299] Aspect 36: An apparatus for wireless communication, the apparatus comprising: at least one component for performing the method according to any one of aspects 12 to 21.

[0300] Aspect 37: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method according to any one of aspects 12 to 21.

[0301] Aspect 38: An apparatus for wireless communication at a second core network entity, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to execute a method according to any one of Aspects 22 to 31.

[0302] Aspect 39: An apparatus for wireless communication at a second core network entity, the apparatus comprising: at least one component for performing a method according to any one of aspects 22 to 31.

[0303] Aspect 40: A non-transitory computer-readable medium storing code for wireless communication at a second core network entity, the code comprising instructions executable by a processor to perform the method according to any one of aspects 22 to 31.

[0304] It should be noted that the methods described herein describe possible implementations, and that the operations and steps may be rearranged or otherwise modified and that other implementations are possible. Furthermore, aspects from two or more methods may be combined.

[0305] 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.

[0306] 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.

[0307] 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 conjunction with a DSP core, or any other such configuration).

[0308] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium, or sent via a computer-readable medium. Other examples and specific implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these items. Features that implement the functions may also be physically located at different locations, including being distributed so that the various parts of the functions are implemented at different physical locations.

[0309] Computer-readable medium includes both non-transient computer storage medium and communication medium, and it includes any medium that promotes computer program to be transferred from one place to another place.Non-transient storage medium can be any available medium that can be accessed by general or special-purpose computer.By way of example and not limitation, non-transient computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage device, disk storage device or other magnetic storage device, or can be used for carrying or storing desired program code parts and can be accessed by general or special-purpose computer or general or special-purpose processor in the form of instruction or data structure Any other non-transient medium.Moreover, 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.

[0310] As used herein (including in the claims), "or" used in a list of items (e.g., a list of items followed 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 a reference to a closed set of conditions. For example, an example step described as "based on condition A" may be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "based at least in part on."

[0311] The terms "determine" or "determine" encompass a wide variety of actions, and thus, "determine" may include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, database or other data structure), ascertaining, and the like. Additionally, "determine" may include receiving (such as receiving information), accessing (such as accessing data in a memory), etc. Additionally, "determine" may include resolving, selecting, choosing, establishing, and other such similar actions.

[0312] In the drawings, similar components or features may have the same reference number. In addition, various components of the same type may be distinguished by following the reference number with a dash and a second reference number to distinguish between similar components. If only the first reference number is used in the specification, the description may apply to any of the similar components having the same first reference number, regardless of the second or other subsequent reference numbers.

[0313] The descriptions set forth herein in conjunction with the accompanying drawings describe example configurations and do not represent all examples that may be implemented or within the scope of the claims. The term "example" as used herein means "used as an example, instance, or illustration," rather than "preferred" or "having advantages over other examples." The specific embodiments include specific details to provide an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0314] 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. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: processor; and a memory coupled to the processor, the processor being configured to: sending, to a first core network entity, an indication of a first set of one or more machine learning models supported at the UE; receiving control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models comprising the machine learning model; and Analysis is performed based at least in part on the machine learning model.

2. The apparatus of claim 1, wherein the processor is further configured to: sending a request for the machine learning model to the first core network entity; and wherein, In order to receive the control signaling, the processor is configured to: The control signaling is received in response to the request.

3. The device according to claim 2, wherein: To send the request, the processor is configured to: sending a service request message; and wherein, in order to receive the control signaling, the processor is configured to: The control signaling is received via a service response message.

4. The apparatus of claim 2, wherein the request comprises an identifier of the machine learning model, a network slice identifier, or both.

5. The apparatus of claim 1, wherein the processor is further configured to: Sending a completion message to the first core network entity based at least in part on the control signaling indicating the configuration of the machine learning model at the UE.

6. The device according to claim 1, wherein: In order to receive the control signaling, the processor is configured to: Receive the control signaling indicating the configuration for the machine learning model, the control signaling indicating a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, or any combination thereof.

7. The device according to claim 1, wherein: In order to receive the control signaling, the processor is configured to: receiving one or more parameters of the machine learning model; and wherein, to perform the analysis, the processor is configured to: The analyzing is performed based at least in part on the one or more parameters.

8. The apparatus of claim 1, wherein the processor is further configured to: The machine learning model is obtained from a core network based at least in part on an address indicated via the control signaling.

9. The apparatus of claim 1, wherein the processor is further configured to: Sending a non-access stratum message to the first core network entity, the non-access stratum message including information determined from performing the analysis based at least in part on the machine learning model.

10. The device according to claim 1, wherein: In order to receive the control signaling, the processor is configured to: Receive a non-access stratum message configured according to a core network centralized entity container, the non-access stratum message indicating the configuration of the machine learning model at the UE.

11. The apparatus of claim 1, wherein the first core network entity is an Access and Mobility Management Function (AMF) entity.

12. An apparatus for wireless communication, the apparatus comprising: processor; and a memory coupled to the processor, the processor being configured to: obtaining an indication of a first set of one or more machine learning models supported at a user equipment (UE); obtaining, from a second core network entity, control signaling configured according to the second core network entity, the control signaling indicating a configuration for a machine learning model from the first set of one or more machine learning models; as well as Outputting a non-access stratum message including the control signaling configured according to the second core network entity.

13. The apparatus of claim 12, wherein the processor is further configured to: obtaining a request for the machine learning model; and outputting an indication of the request for the machine learning model to the second core network entity; and wherein, In order to obtain the control signaling, the processor is further configured to: The control signaling is obtained based at least in part on the indication.

14. The apparatus of claim 13, wherein the processor is further configured to: outputting a discovery request for the second core network entity to a third core network entity; and An identifier of the second core network entity is obtained from the third core network entity based at least in part on the discovery request.

15. The apparatus of claim 13, wherein the request comprises an identifier of the machine learning model, a network slice identifier, or both.

16. The apparatus of claim 12, wherein the processor is further configured to: obtaining, from the second core network entity, a request for one or more UEs to perform analysis based at least in part on the machine learning model; and wherein, In order to output the non-access stratum message, the processor is further configured to: The non-access stratum message is output based at least in part on the request.

17. The apparatus of claim 16, wherein the processor is further configured to: Output one or more identifiers of a group of one or more UEs supporting the machine learning model to the second core network entity, the group of one or more UEs including at least the UE.

18. The apparatus of claim 16, wherein the request for the one or more UEs to perform analysis comprises one or more UE identifiers associated with the one or more UEs, one or more registration area lists, one or more network slice identifiers, or any combination thereof.

19. The apparatus of claim 16, wherein the processor is further configured to: The one or more UEs including at least the UE are identified based at least in part on the request.

20. The device according to claim 12, wherein: In order to output the control signaling, the processor is configured to: The output includes the non-access stratum message of the control signaling, wherein the control signaling indicates a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

21. The apparatus of claim 12, wherein the processor is further configured to: obtaining a completion message in response to the non-access stratum message; and The completion message is output to the second core network entity.

22. An apparatus for wireless communication at a second core network entity, the apparatus comprising: processor; and a memory coupled to the processor, the processor being configured to: identifying a user equipment (UE) that supports configuration of a machine learning model at the UE; as well as Output control signaling configured according to the second core network entity to the first core network entity, wherein the control signaling is used to indicate the configuration for the machine learning model to the UE.

23. The apparatus of claim 22, wherein the processor is further configured to: obtaining, from the first core network entity, an indication of a request from the UE to configure the machine learning model at the UE; and wherein, To identify the UE, the processor is further configured to: The UE is identified based at least in part on the indication of the request.

24. The device according to claim 23, wherein: In order to obtain the indication, the processor is configured to: A non-access stratum message is obtained from the UE via the first core network entity, the non-access stratum message including the request.

25. The apparatus of claim 22, wherein the processor is further configured to: A request is obtained from another network entity for one or more UEs to perform analysis based at least in part on the machine learning model.

26. The device according to claim 25, wherein To identify the UE, the processor is configured to: Outputting a request message to one or more network entities including at least the second core network entity for the one or more network entities to report UE identifiers of UEs supporting the machine learning model; as well as A response message indicating a group of UEs including at least the UE is obtained from at least the second core network entity.

27. The apparatus of claim 26, wherein the processor is further configured to: outputting a discovery request for the one or more network entities to a third core network entity, the discovery request comprising one or more registration area lists or one or more network slice identifiers or both; and Obtaining from the third core network entity a discovery response message indicating the one or more network entities including at least the second core network entity, wherein the one or more network entities correspond to the one or more registration area lists or the one or more network slice identifiers or both.

28. The device according to claim 22, wherein: In order to output the control signaling, the processor is configured to: The output indicates the control signaling of a machine learning model file address, a machine learning model training request, a machine learning model inference request, a machine learning model identifier, a machine learning model location, a machine learning model version, a time duration for performing the analysis, an activation event for reporting the analysis, one or more parameters of the machine learning model, or any combination thereof.

29. The apparatus of claim 22, wherein the processor is further configured to: A non-access stratum message is obtained from the UE via the first core network entity, the non-access stratum message comprising information determined at the UE by performing analysis based at least in part on the machine learning model.

30. A method for wireless communication at a user equipment (UE), the method comprising: sending, to a first core network entity, an indication of a first set of one or more machine learning models supported at the UE; receiving control signaling from the first core network entity indicating configuration of a machine learning model at the UE, the first set of one or more machine learning models comprising the machine learning model; and Analysis is performed based at least in part on the machine learning model.

Citation Information

Cited By

  • User equipment machine learning service continuity

    US12647861B2

  • User equipment machine learning service continuity

    US20230422117A1

  • System and method for enabling early inference in in-network learning within heterarchical intelligent collaboration sessions

    WO2026199333A1