Distributed machine learning model configuration

Abstract

Methods, systems, and devices for wireless communication are described. The UE may configure a machine learning model by the core network to perform analysis, training, or inference. The UE may exchange capability information related to the machine learning model with the core network. For example, the UE may indicate to a core network entity a list of machine learning models supported at the UE, and the UE may receive an indication of the list of machine learning models supported at the core network entity. The UE or the core network may initiate the configuration. For example, the UE may request a configured 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.

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 with 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 core network entity; receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity; receiving control signaling from the core network entity indicating a configuration for a machine learning model, 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, a memory coupled to the processor, and instructions stored in the memory. The instructions are executable by the processor to cause the apparatus to: send an indication of a first set of one or more machine learning models supported at the UE to a core network entity; receive an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity; receive control signaling from the core network entity indicating a configuration for a machine learning model, 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: means for sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity; means for receiving, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity; means for receiving control signaling from the core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model; and means 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 core network entity; receive an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity; receive control signaling from the core network entity indicating a configuration for a machine learning model, 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 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, sending the request may include operations, features, components, or instructions for sending a protocol data unit session modification request message, wherein receiving the control signaling includes receiving the control signaling via a protocol data unit session modification command message.

[0010] 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.

[0011] 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 core network entity based on the control signaling indicating the configuration for the machine learning model.

[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 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.

[0013] 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 UE configuration update command indicating the configuration for the machine learning model.

[0014] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the indication of the first set of one or more machine learning models may include operations, features, components, or instructions for sending a registration request indicating the first set of one or more machine learning models supported at the UE, wherein receiving the indication of the second set of one or more machine learning models includes receiving the indication of the second set of one or more machine learning models via a registration response message.

[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 protocol data unit session modification command indicating the configuration for the machine learning model.

[0016] 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 protocol data unit session modification complete message to the core network entity based on the protocol data unit session modification command indicating the configuration for the machine learning model.

[0017] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, sending the indication of the first set of one or more machine learning models may include operations, features, components, or instructions for sending a session establishment message or a modification request message indicating the first set of one or more machine learning models supported at the UE, wherein receiving the indication of the second set of one or more machine learning models includes receiving the indication of the second set of one or more machine learning models via a session establishment response message or a modification response message.

[0018] 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, wherein performing the analysis includes: performing the analysis based on the one or more parameters.

[0019] 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 the address indicated via the control signaling.

[0020] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the core network entity may be an Access and Mobility Management Function (AMF) entity or a Session Management Function (SMF) entity.

[0021] A method for wireless communication at a first core network entity is described. The method may include obtaining an indication of a first set of one or more machine learning models supported at a UE; outputting an indication of a second set of one or more machine learning models supported at the first core network entity or a second core network entity, or both; and outputting control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0022] An apparatus for wireless communication at a first core network entity is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions are executable by the processor to cause the apparatus to: obtain an indication of a first set of one or more machine learning models supported at a UE; output an indication of a second set of one or more machine learning models supported at the first core network entity or a second core network entity, or both; and output control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0023] Another apparatus for wireless communication at a first core network entity 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 outputting an indication of a second set of one or more machine learning models supported at the first core network entity or a second core network entity, or both; and means for outputting control signaling indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0024] A non-transitory computer-readable medium storing code for wireless communication at a first core network entity 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; output an indication of a second set of one or more machine learning models supported at the first core network entity or a second core network entity, or both; and output control signaling indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0025] 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 service request message requesting the machine learning model, wherein outputting the control signaling includes outputting the control signaling via a service response message in response to the service request message.

[0026] 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 protocol data unit session modification request message requesting the machine learning model, wherein outputting the control signaling includes outputting the control signaling via a protocol data unit session modification command message in response to the protocol data unit session modification request message.

[0027] 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 UE configuration update complete message in response to the control signaling indicating the configuration for the machine learning model, wherein outputting the control signaling includes outputting the control signaling via a UE configuration update command.

[0028] 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 protocol data unit session modification complete message in response to the control signaling indicating the configuration for the machine learning model, wherein outputting the control signaling includes outputting the control signaling via a protocol data unit session modification command message.

[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 request from another core network entity for the UE to perform analysis based on the machine learning model, wherein outputting the control signaling includes outputting the control signaling in response to the request.

[0030] 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 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 analysis according to the machine learning model, an activation event for reporting the analysis, one or more parameters for performing the analysis, or any combination thereof.

[0031] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, outputting the indication of the first set of one or more machine learning models may include operations, features, components, or instructions for obtaining a registration request indicating the first set of one or more machine learning models supported at the UE, wherein outputting the indication of the second set of one or more machine learning models includes outputting the indication of the second set of one or more machine learning models via a registration response message.

[0032] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, obtaining the indication of the first set of one or more machine learning models may include operations, features, components, or instructions for obtaining a session establishment message or a modification request message indicating the first set of one or more machine learning models supported at the UE, wherein outputting the indication of the second set of one or more machine learning models includes outputting the indication of the second set of one or more machine learning models via a session establishment response message or a modification response message.

[0033] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first core network entity may be an AMF entity.

[0034] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: outputting the indication of the first set of one or more machine learning models supported at the UE to an SMF entity, wherein the second core network entity may be the SMF entity; obtaining the indication of the second set of one or more machine learning models supported at the SMF entity from the SMF entity; and obtaining the control signaling indicating the configuration for the machine learning model from the SMF entity.

[0035] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the first core network entity may be an SMF entity.

[0036] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining, from an AMF entity, the indication of the first set of one or more machine learning models supported at the UE, wherein the second core network entity may be the AMF entity; outputting, to the AMF entity, the indication of the second set of one or more machine learning models supported at the SMF entity; and outputting, to the AMF entity, the control signaling indicating the configuration of the machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 An example of a wireless communication system supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0038] Figure 2 An example of a wireless communication system supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0039] Figure 3 An example of a capability exchange procedure supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0040] Figure 4 and Figure 5 Examples of network-initiated machine learning model configuration supporting distributed machine learning model configuration according to aspects of the present disclosure are illustrated.

[0041] Figure 6 and Figure 7 An example of UE-initiated machine learning model configuration supporting distributed machine learning model configuration according to various aspects of the present disclosure is illustrated.

[0042] Figure 8 An example of a machine learning process supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0043] Figure 9 and Figure 10 A block diagram of a device supporting distributed machine learning model configuration according to aspects of the present disclosure is shown.

[0044] Figure 11 A block diagram of a communication manager supporting distributed machine learning model configuration according to aspects of the present disclosure is shown.

[0045] Figure 12 A diagram of a system including devices supporting distributed machine learning model configuration is shown in accordance with aspects of the present disclosure.

[0046] Figure 13 and Figure 14A block diagram of a device supporting distributed machine learning model configuration according to aspects of the present disclosure is shown.

[0047] Figure 15 A block diagram of a communication manager supporting distributed machine learning model configuration according to aspects of the present disclosure is shown.

[0048] Figure 16 A diagram of a system including devices supporting distributed machine learning model configuration is shown in accordance with aspects of the present disclosure.

[0049] Figures 17 to 21 A flowchart illustrating a method for supporting distributed machine learning model configuration according to aspects of the present disclosure is shown. DETAILED DESCRIPTION

[0050] The core network of a wireless communication system can train machine learning models to perform analysis, such as network optimization and inference. UEs in the wireless communication system can also support analysis based on machine learning models. For example, the core network can configure a trained machine learning model for a UE, and the UE can use the trained machine learning model to perform analysis. 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.

[0051] The present disclosure provides techniques for configuring machine learning models at a UE using a distributed architecture. A core network entity, such as an AMF entity, may manage, store, or support one or more machine learning models associated with the functionality of the core network entity. For example, an AMF entity may manage one or more AMF machine learning models, and an SMF entity may manage one or more SMF machine learning models. The AMF entity may configure the AMF machine learning model to the UE, and the UE may use the AMF machine learning model to perform analysis. In some cases, in order to support distributed architecture techniques, the UE and the core network entity may exchange capability information. For example, the UE may indicate to the AMF entity and the SMF entity a set of machine learning models supported at the UE. The AMF entity and the SMF entity may each indicate to the UE the machine learning models they support. In another example, a policy control function (PCF) entity may manage one or more PCF machine learning models, and other network entities of the core network with different functions may also manage machine learning models related to those functionalities.

[0052] Systems that do not support performing machine learning model training or analysis at the UE may be less efficient, 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 less information or less inference (e.g., only network-side inference 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 inference 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. 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 particular protocol data unit (PDU) session, the UE may determine to establish a PDU session via a different access technology based on the network load prediction. In another example, by implementing these techniques, the UE may provide the 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 an 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 forecast and may provide the list of UEs to the application function.

[0053] 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 a core network entity that supports the machine learning model. For example, after exchanging capability information with the AMF entity, the UE may determine that the AMF entity supports the AMF machine learning model, and the UE may send a request to the AMF entity to be configured with the AMF machine learning model. In some cases, the core network entity may receive a request, such as from a consumer or another network entity, for the UE to perform analysis using a machine learning model. The core network entity may configure the machine learning model to the UE based on the request. For example, another core network entity may request the SMF entity to obtain an SMF analysis based on the SMF machine learning model from the UE. Based on receiving the request, the SMF may identify the UE that supports the SMF machine learning model and configure the SMF machine learning model to the UE. The SMF analysis may be, for example, a request for information related to the user experience of the UE or a request for information related to the user experience of a network slice.

[0054] In some cases, the UE may obtain the machine learning model from the core network. For example, the core network entity may send control signaling to the UE to configure or instruct 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.

[0055] The UE may perform analysis based on the machine learning model. Performing the analysis may enable some optimization to be performed at the UE or at the core network. For example, the UE may request to perform analysis based on inferences determined from the 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 the 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 on a network with a low network load, thereby increasing throughput and reducing latency and network load bearing. For example, the UE may report to the AMF entity an analysis or inference determined by analyzing the load forecast of the network using a machine learning model, and the AMF entity may adjust network resources to avoid overload on the network. In another example, the UE may report to the SMF entity an analysis or inference associated with the user experience, and the SMF entity may adjust network resource allocation to improve data transmission performance.

[0056] Performing analysis at the UE or training a machine learning model at the UE can provide more information for performing network selection or network load management than performing analysis or inference solely at the network side. Additionally or alternatively, a core network entity can request that the UE perform analysis and report information obtained from performing the analysis, which can enable optimization at the core network or core network entity based on the reported information. For example, an application client can request that the UE perform analysis using a machine learning model, and the UE can report the analysis information from the machine learning model. The application client can use the reported information to, for example, perform split rendering, reduce processing power at the UE or network, or both.

[0057] 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 distributed machine learning model configurations.

[0058] Figure 1An example of a wireless communication system 100 supporting distributed machine learning model configuration according to 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).

[0059] 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, network equipment, and the like. In some examples, the network entities 105 and the UEs 115 may communicate wirelessly via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, the network entities 105 may support a coverage area 110 (e.g., a geographic coverage area) within which the UEs 115 and the network entities 105 may establish one or more communication links 125. The coverage area 110 may be an example of a geographic area within which the network entities 105 and the UEs 115 may support communication of signals according to one or more radio access technologies (RATs).

[0060] 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 that take different forms or have 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 .

[0061] As described herein, a node of the wireless communication system 100 (which may be referred to as a network node or 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, reference 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 a node. 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.

[0062] As described herein, various terms may be used to describe the communication of information (e.g., any information, signal, etc.) in various aspects. Disclosure of one communication term includes disclosure of the 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, disclosure that the first network node is configured to send information to the second network node includes disclosure that the first network node is configured to provide, transmit, output, communicate, or send information to the second network node. Similarly, in this example and consistent with the present disclosure, disclosure that the first network node is configured to send information to the second network node includes 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.

[0063] In some examples, network entities 105 can communicate with core network 130, with each other, or both. For example, network entities 105 can communicate with core network 130 via one or more backhaul links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some examples, network entities 105 can communicate with each other directly (e.g., directly between network entities 105) or indirectly (e.g., via core network 130) via backhaul communication links 120 (e.g., according to X2, Xn, or other interface protocols). In some examples, network entities 105 can communicate with each other via midhaul communication links 162 (e.g., according to a midhaul interface protocol) or fronthaul communication links 168 (e.g., according to a fronthaul interface protocol), or any combination thereof. Backhaul communication links 120, midhaul communication links 162, or fronthaul communication links 168 can be or include one or more wired links (e.g., electrical links, fiber optic links), one or more wireless links (e.g., radio links, wireless optical links), etc., or various combinations thereof. UE 115 may communicate with core network 130 via communication link 155 .

[0064] One or more of the network entities 105 described herein may include or may be referred to as a base station 140 (e.g., a transceiver base station, a radio base station, an NR base station, an access point, a radio transceiver, a Node B, an evolved Node B (eNB), a next-generation Node B, or a gigabit Node B (any of which may be referred to as a gNB), a 5G NB, a next-generation eNB (ng-eNB), a Home Node B, a Home evolved Node B, or other suitable terminology). In some examples, the network entity 105 (e.g., a base station 140) may be implemented in a converged (e.g., monolithic, standalone) base station architecture that may be configured to utilize a protocol stack that is physically or logically integrated within a single network entity 105 (e.g., a single RAN node, such as the base station 140).

[0065] In some examples, the network entity 105 can be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that can 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 can include one or more of the following: a central unit (CU) 165, a distributed unit (DU) 170, a radio unit (RU) 175, a RAN intelligent controller (RIC) 180 (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) 185 system, or any combination thereof. The RU 175 can also be referred to as a radio head, an intelligent radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmit receive point (TRP). One or more components of the network entity 105 in the disaggregated 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 disaggregated RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0066] The functional split between CU 165, DU 170, and RU 175 is flexible and can support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, and any combination thereof) are performed at CU 165, DU 170, and RU 175. For example, a functional split of the protocol stack can be employed between CU 165 and DU 170 such that CU 165 can support one or more layers of the protocol stack and DU 170 can support one or more different layers of the protocol stack. In some examples, CU 165 can 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 165 may be connected to one or more DUs 170 or RUs 175, and the one or more DUs 170 or RUs 175 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 165. Additionally or alternatively, a functional split of the protocol stack may be employed between the DU 170 and the RU 175, such that the DU 170 may support one or more layers of the protocol stack and the RU 175 may support one or more different layers of the protocol stack. The DU 170 may support one or more different cells (e.g., via one or more RUs 175). In some cases, the functional split between the CU 165 and the DU 170 or between the DU 170 and the RU 175 may be within the protocol layer (e.g., some functions of the protocol layer may be performed by one of the CU 165, DU 170, or RU 175, while other functions of the protocol layer may be performed by a different one of the CU 165, DU 170, or RU 175). The CU 165 may be further functionally split into CU control plane (CU-CP) and CU user plane (CU-UP) functions. The CU 165 may be connected to one or more DUs 170 via midhaul communication links 162 (e.g., F1, F1-c, F1-u), and the DU 170 may be connected to one or more RUs 175 via fronthaul communication links 168 (e.g., an open fronthaul (FH) interface). In some examples, midhaul communication link 162 or fronthaul communication link 168 may be implemented according to an interface (e.g., channel) between layers of a protocol stack supported by the respective network entities 105 communicating over those communication links.

[0067] In a wireless communication system (e.g., wireless communication system 100), the infrastructure and spectrum resources for radio access can support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture (e.g., to the core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB nodes 104) can be partially controlled by each other. One or more IAB nodes 104 can be referred to as a donor entity or IAB donor. One or more DUs 170 or one or more RUs 175 can be partially controlled by one or more CUs 165 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) can 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 the DU 170 of the coupled IAB donor. 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., the RU 175) for access via the DU 170 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 170 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.

[0068] For example, an access network (AN) or RAN may include an access node (e.g., an IAB donor), communications between the 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 that has a wired or wireless connection to the core network 130. The IAB donor may include a CU 165 and at least one DU 170 (e.g., and RU 175), in which case the CU 165 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 the F1 interface according to a protocol that defines signaling messages (e.g., the F1 AP protocol). Additionally or alternatively, CU 165 may communicate with the core network via an interface (which may be an example of part of a backhaul link) and may communicate with other CUs 165 (e.g., CUs 165 associated with alternative IAB donors) via an Xn-C interface (which may be an example of part of a backhaul link).

[0069] 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.). The DU 170 may act as a distributed scheduling node toward child nodes associated with the IAB node 104, and the IAB-MT may act as a scheduled node toward a parent node associated with the IAB node 104. In other words, an IAB donor may be referred to as a parent node that communicates with one or more child nodes (e.g., the IAB donor may relay transmissions to the UE through one or more other IAB nodes 104). Additionally or alternatively, depending on the relay chain or configuration of the AN, the 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 the IAB node 104 may provide a Uu interface for the child IAB node 104 to receive signaling from the parent IAB node 104 , and a DU interface (eg, DU 170 ) may provide a Uu interface for the parent IAB node 104 to signal to the child IAB node 104 or the UE 115 .

[0070] For example, IAB node 104 may be referred to as a parent node that supports communications to child IAB nodes and may be referred to as a child IAB node associated with an IAB donor. The IAB donor may include a CU 165 having a wired or wireless connection to the core network 130 (e.g., backhaul communication link 120) and may serve as a parent node for IAB node 104. For example, the DU 170 of the IAB donor may relay transmissions to the UE 115 via the IAB node 104 and may directly signal transmissions to the UE 115. The CU 165 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 170. 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 170 of the IAB donor, and communications with the IAB node 104 may be scheduled by the DU 170 of the IAB node 104 .

[0071] 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 the distributed 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 170, a CU 165, a RU 175, a RIC 180, a SMO 185).

[0072] UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, where "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.

[0073] 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.

[0074] The UE 115 and the network entity 105 can wirelessly communicate with each other via one or more communication links 125 (e.g., access links) over 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 used for the communication link 125 may include a portion of an RF spectrum band (e.g., a bandwidth portion (BWP)) that operates according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling for coordinating carrier operations, user data, or other signaling. The wireless communication system 100 may support communications with the UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, the UE 115 may be configured 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 the network entity 105 (e.g., base station 140, CU 165, DU 170, RU 175) of the RAN communicating with another device (e.g., directly or via one or more other network entities 105).

[0075] 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 performed by UE 115 via the carrier, or a carrier may operate in a non-standalone mode, in which case a different carrier (e.g., of the same or different radio access technology) is used to anchor the connection.

[0076] The communication link 125 shown in the wireless communication system 100 may include downlink transmissions (e.g., forward link transmissions) from the network entity 105 to the UE 115, uplink transmissions (e.g., return link transmissions) from the UE 115 to the network entity 105, or both, as well as other transmission configurations. A carrier may carry downlink communications or uplink communications (e.g., in an FDD mode), or may be configured to carry both downlink and uplink communications (e.g., in a TDD mode).

[0077] A carrier may be associated with a particular bandwidth of the RF spectrum, and in some examples, the carrier bandwidth may be referred to as the "system bandwidth" of the carrier or wireless communication system 100. For example, the carrier bandwidth may be one of a set of bandwidths of carriers of a particular radio access technology (e.g., 1.4 megahertz (MHz), 3 MHz, 5 MHz, 10 MHz, 15 MHz, 20 MHz, 40 MHz, or 80 MHz). Devices of the wireless communication system 100 (e.g., the network entity 105, the 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 the 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 the carrier bandwidth.

[0078] The signal waveform transmitted via the carrier may be composed of multiple subcarriers (e.g., using multicarrier modulation (MCM) techniques such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system employing MCM techniques, a resource element may refer to the resource of one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be inversely related. The number of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both), such that the more resource elements a device receives and the higher the order of the modulation scheme, the higher the data rate of the device may be. Wireless communication resources may refer to a combination of RF spectrum resources, time resources, and spatial resources (e.g., spatial layers, beams), and the use of multiple spatial resources may improve the data rate or data integrity of communications with UE 115.

[0079] 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 by the UE 115 may be constrained to one or more active BWPs.

[0080] 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, T s =1 / (Δf max ·N f) seconds sampling period, where Δf max It can represent the maximum supported subcarrier spacing, and N f The maximum supported discrete Fourier transform (DFT) size may be indicated. Time intervals of communication resources may be organized according to radio frames, each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0081] Each frame may include a plurality of consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into 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 to the front of each symbol period). In some wireless communication systems 100, the time slot may be further divided into a plurality of mini-time slots containing one or more symbols. Excluding the cyclic prefix, each symbol period may contain one or more (e.g., N f The duration of a symbol period may depend on the subcarrier spacing or the operating frequency band.

[0082] A subframe, slot, mini-slot, or symbol may be the minimum scheduling unit (e.g., in the time domain) of the wireless communication system 100 and may be referred to as a Transmit Time Interval (TTI). In some examples, the TTI duration (e.g., the number of symbol periods in a TTI) may be variable. Additionally or alternatively, the minimum scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of a shortened TTI (sTTI)).

[0083] 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, for example, using one or more of time division multiplexing (TDM), frequency division multiplexing (FDM), or hybrid TDM-FDM techniques. 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 the 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 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 a control channel candidate may refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with 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 .

[0084] The network entity 105 may provide communication coverage via one or more cells (e.g., macro cells, small cells, hotspots, or other types of cells, or any combination thereof). The term "cell" may refer to a logical communication entity used to communicate with the network entity 105 (e.g., via a carrier) and may be associated with an identifier (e.g., a physical cell identifier (PCID), a virtual cell identifier (VCID), or other cell identifier) ​​used to distinguish between adjacent cells. In some examples, a cell may also refer to a coverage area 110 or a portion of a coverage area 110 (e.g., a sector) within which the logical communication entity operates. Depending on various factors such as the capabilities of the network entity 105, such cells may range from smaller areas (e.g., structures, subsets of structures) to larger areas. For example, a cell may be or may include a building, a subset of buildings, or an external space between or overlapping coverage areas 110, etc.

[0085] A macro cell typically covers a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access to UEs 115 that have a service subscription 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) than macro cells, and may operate in the same or different frequency bands (e.g., licensed, unlicensed) as the macro cells. Small cells may provide unrestricted access to UEs 115 that have a service subscription with the network provider, or may provide restricted access to UEs 115 associated with the small cell (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.

[0086] 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.

[0087] In some examples, network entities 105 (e.g., base stations 140, RUs 175) can be mobile and, therefore, provide communication coverage for mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies can overlap, but the different coverage areas 110 can be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies can be supported by different network entities 105. The wireless communication system 100 can include, for example, a heterogeneous network in which different types of network entities 105 provide coverage for various coverage areas 110 using the same or different radio access technologies.

[0088] The wireless communication system 100 may support synchronous or asynchronous operation. For synchronous operation, the network entities 105 (e.g., base stations 140) may have similar frame timing, and transmissions from different network entities 105 may be approximately aligned in time. For asynchronous operation, the network entities 105 may have different frame timing, and in some examples, transmissions from different network entities 105 may not be aligned in time. The techniques described herein may be used for either synchronous or asynchronous operation.

[0089] 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 it 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, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, queue management and tracking, remote security sensing, physical access control, and transaction-based commercial charging.

[0090] 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 UEs 115 include entering a power-saving deep sleep mode when not engaged in active communications, operating with limited bandwidth (e.g., according to narrowband communication), 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.

[0091] 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 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 functionality 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.

[0092] 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 performing D2D communication may be within a coverage area 110 of a network entity 105 (e.g., a base station 140, a RU 175), which may support aspects of such D2D communication as configured or scheduled by the network entity 105. In some examples, one or more UEs 115 in the 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 the D2D communication. In some other examples, D2D communications may be performed between UEs 115 without the involvement of network entity 105 .

[0093] 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 thereof. The vehicles can signal information related to traffic conditions, signal scheduling, weather, safety, emergency situations, or any other information relevant 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 175) using vehicle-to-network (V2N) communication, or both.

[0094] 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 generation or system, which may include at least one control plane entity (e.g., a mobility management entity (MME), an AMF entity) 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 external networks. The control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management for UEs 115 served by network entities 105 (e.g., base stations 140) associated with the core network 130. User IP packets may be delivered through the user plane entity, which may provide IP address allocation and other functions. The user plane entity may be connected to the IP services 150 of one or more network operators. IP services 150 may include access to the Internet, an intranet, an IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0095] The wireless communication system 100 can operate using one or more frequency bands that can range from 300 megahertz (MHz) to 300 gigahertz (GHz). Generally speaking, the region from 300 MHz to 3 GHz is referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range from approximately one decimeter to one meter in length. UHF waves can be blocked or redirected by buildings and environmental features (which can be referred to as clusters), but these waves can penetrate structures sufficiently for a macro cell to provide service to a UE 115 located indoors. Transmission of UHF waves can be associated with smaller antennas and a shorter range (e.g., less than 100 kilometers) than transmission using the smaller frequencies and longer wavelengths of the high frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz.

[0096] The wireless communication system 100 may also operate in the super high frequency (SHF) region using frequency bands from 3 GHz to 30 GHz (also known as centimeter bands) or in the extremely high frequency (EHF) region of the spectrum (e.g., from 30 GHz to 300 GHz) (also known as millimeter bands). In some examples, the wireless communication system 100 may support millimeter wave (mmW) communications between the UE 115 and the network entity 105 (e.g., base station 140, RU 175), and the EHF antennas of the corresponding devices may be smaller and more closely spaced than the UHF antennas. In some examples, this may facilitate the use of antenna arrays within the device. However, the propagation of EHF transmissions may be subject to even greater atmospheric attenuation and a shorter range than SHF or UHF transmissions. The techniques disclosed herein may be employed 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.

[0097] The wireless communication system 100 can utilize both licensed and unlicensed RF spectrum bands. For example, the wireless communication system 100 can use license assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology in an unlicensed band such as the 5 GHz industrial, scientific, and medical (ISM) band. When operating in an unlicensed RF spectrum band, devices such as the network entity 105 and the UE 115 can employ carrier sensing for conflict detection and avoidance. In some examples, operations in the unlicensed band can be combined with component carriers (e.g., LAA) operating in the licensed band based on a carrier aggregation configuration. Operations in the unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, among others.

[0098] A network entity 105 (e.g., a base station 140, a RU 175) or a UE 115 may be equipped with multiple antennas that can be used to employ techniques such as transmit diversity, receive diversity, multiple-input, multiple-output (MIMO) 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, the 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 may 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 panels may support RF beamforming for signals transmitted via the antenna ports.

[0099] The network entity 105 or the UE 115 may use MIMO communication to exploit multipath signal propagation and improve spectral efficiency by sending or receiving multiple signals via different spatial layers. Such a technique 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 techniques include single-user MIMO (SU-MIMO), in which multiple spatial layers are transmitted to the same receiving device, and multi-user MIMO (MU-MIMO), in which multiple spatial layers are transmitted to multiple devices.

[0100] Beamforming (which may also be referred to as spatial filtering, directional transmission, or directional reception) is a signal processing technique that can be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming can be achieved by combining signals communicated via antenna elements of an antenna array so that some signals propagating at a particular orientation relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to signals communicated via antenna elements can 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. The adjustments associated with each of these antenna elements can be defined by a set of beamforming weights associated with a particular orientation (e.g., relative to the antenna array of the transmitting device or the receiving device, or relative to some other orientation).

[0101] The network entity 105 or the UE 115 may use beam sweeping techniques as part of a beamforming operation. For example, the network entity 105 (e.g., base station 140, RU 175) may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with the UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted multiple times by the network entity 105 along different directions. For example, the network entity 105 may transmit signals according to different sets of beamforming weights associated with different transmit directions. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device, such as the network entity 105, or by a receiving device, such as the UE 115) the beam direction for later transmission or reception by the network entity 105.

[0102] Some signals, such as data signals associated with a particular receiving device, may be transmitted by a transmitting device (e.g., transmitting network entity 105, transmitting UE 115) along a single beam direction (e.g., a direction associated with a receiving device (e.g., receiving network entity 105 or receiving UE 115)). In some examples, a beam direction associated with transmission along a single beam direction may be determined based on signals transmitted along one or more beam directions. For example, UE 115 may receive one or more of the signals transmitted by network entity 105 along different directions and may report to network entity 105 an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.

[0103] 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 the system bandwidth or one or more subbands. Network entity 105 may transmit reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)), which may or may not be precoded. UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-faceted codebook, a linear combination codebook, a port-selective 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 175), 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).

[0104] A receiving device (e.g., UE 115) may perform reception operations according to multiple reception configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a receiving device (e.g., network entity 105). For example, the receiving device may perform reception according to multiple reception directions by receiving via different antenna subarrays, processing received signals according to different antenna subarrays, receiving according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array (e.g., different directional listening weight sets), or processing received signals according to different receive 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 reception configurations or reception directions. In some examples, the receiving device may use a single reception configuration to receive along a single beam direction (e.g., when receiving data signals). 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).

[0105] The wireless communication system 100 may be a packet-based network operating 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 for communication via 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 for the establishment, configuration, and maintenance of RRC connections between the UE 115 and the network entity 105 or the core network 130 for radio bearers supporting user plane data. At the PHY layer, transport channels may be mapped to physical channels.

[0106] UE 115 and network entity 105 may support retransmission of data to increase the likelihood of successfully receiving the data. Hybrid automatic repeat request (HARQ) feedback is a technique for increasing the likelihood of correctly receiving data over a communication link (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC)), forward error correction (FEC), and retransmission (e.g., automatic repeat request (ARQ)). HARQ may improve throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, a device may support simultaneous slot HARQ feedback, wherein the device may provide HARQ feedback in a particular time slot for data received in previous symbols in the time slot. In some other examples, the device may provide HARQ feedback in subsequent time slots or based on some other time interval.

[0107] The present disclosure provides techniques for configuring machine learning models at a UE 115 using a distributed architecture. A core network entity 160, such as an AMF entity, may manage, store, or support one or more machine learning models associated with the functionality of the core network entity 160. For example, the AMF entity may manage one or more AMF machine learning models, and the SMF entity may manage one or more SMF machine learning models. The AMF entity may configure the AMF machine learning model to the UE 115, and the UE 115 may perform analysis using the AMF machine learning model. In some cases, to support the distributed architecture techniques, the UE 115 and different core network entities may exchange capability information. For example, the UE 115 may indicate a list of machine learning models supported at the UE 115 to the AMF entity and the SMF entity. The AMF entity and the SMF entity may each indicate the respective supported machine learning models to the UE. For example, the UE 115 may transmit an identifier of the supported machine learning model to the AMF entity during a registration procedure, and the AMF entity may store the UE 115's capability to support the machine learning model associated with the machine learning model identifier as part of the UE context.

[0108] The UE 115 or the core network may initiate a procedure for configuring the machine learning model for the UE 115. In some cases, the UE 115 may initiate the procedure by sending a request for the machine learning model to a core network entity 160 that supports the machine learning model. For example, after exchanging capability information with an AMF entity, the UE 115 may determine that the AMF entity supports the AMF machine learning model, and the UE 115 may send a request to the AMF entity to be configured with the AMF machine learning model. In some cases, the core network entity 160 may receive a request for the UE 115 to perform analysis using the machine learning model, and the core network entity 160 may configure the machine learning model for the UE 115 based on the request. For example, another core network entity 160 may request an SMF entity to obtain SMF analysis based on the SMF machine learning model from the UE 115. Based on receiving the request, the SMF may identify the UE 115 that supports the SMF machine learning model and configure the SMF machine learning model for the UE 115.

[0109] In some cases, the UE 115 may obtain the machine learning model from the core network. For example, the core network entity 160 may send control signaling to the UE 115 that configures or indicates the machine learning model. The control signaling may include, for example, the address or location (e.g., URL or FQDN) of the machine learning model, and the UE 115 may obtain the machine learning model from the core network via the address or location of the machine learning model. For example, the machine learning model configuration may be a file with many data packets. In some examples, instead of the core network entity (e.g., AMF entity, SMF entity, etc.) providing the machine learning model directly to the UE 115 via signaling (e.g., because this may incur significant overhead to the core network), the core network entity may instruct the UE 115 to transmit the machine learning model configuration including the 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. Reference Figure 8 Some additional techniques for training with machine learning models are described in more detail.

[0110] In some examples, a core network entity 160, such as an AMF entity or an SMF entity, may include a communication manager 101 configured to support one or more aspects of the techniques for distributed machine learning model configuration described herein. For example, the communication manager 101 may be configured to support the core network entity 160 in obtaining (e.g., receiving from a UE 115-a) an indication of a first set of one or more machine learning models supported at a UE 115 (such as UE 115-a). In some examples, the communication manager 101 may be configured to support the core network entity 160 in outputting (e.g., to the UE 115-a) an indication of a second set of one or more machine learning models supported at the core network entity 160 or a second core network entity, or both. For example, the core network entity 160 may indicate the machine learning models supported at the core network entity 160, or the core network entity may convey the machine learning models supported at another network entity, such as the AMF entity sending NAS signaling to the UE 115-a indicating the machine learning models supported by the SMF entity. In some examples, communications manager 101 may be configured to enable core network entity 160 to output control signaling (e.g., to UE 115-a) indicating configuration of a machine learning model at UE 115-a. In some examples, the first set of one or more machine learning models may include the machine learning model indicated by the control signaling.

[0111] In some examples, UE 115-a may include a communications manager 102 configured to support one or more aspects of the techniques for distributed machine learning model configuration described herein. For example, communications manager 102 may be configured to support UE 115-a sending (e.g., to core network entity 160) an indication of a first set of one or more machine learning models supported at UE 115-a. In some examples, communications manager 102 may be configured to support UE 115-a receiving, from core network entity 160, an indication of a second set of one or more machine learning models supported at core network entity 160. In some examples, communications manager 102 may be configured to support UE 115-a receiving (e.g., from core network entity 160) control signaling indicating configuration for a machine learning model at UE 115-a, wherein the first set of one or more machine learning models includes the machine learning model. In some examples, communications manager 102 may be configured to support UE 115-a performing analysis based on the machine learning model.

[0112] Figure 2 An example of a wireless communication system 200 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0113] The wireless communication system 200 may include a UE 115-a, which may be a Figure 1 10. The wireless communication system 200 may include one or more entities of a core network, such as an AMF entity 205, an SMF entity 210, or both. In some cases, the wireless communication system 200 may include another network entity 245, which may be an example of another entity in the core network, an AMF entity 205, an SMF entity 210, or any combination thereof. In some cases, the UE 115-a may communicate directly with the AMF entity 205 and the SMF entity 210. Additionally or alternatively, the UE 115-a may communicate with the AMF entity 205 and the SMF entity 210 by conveying NAS signaling via the network entity 105 or a base station. In some cases, the UE 115-a may communicate with the SMF entity 210 via the AMF entity 205, such as by sending or receiving SMF NAS signaling transmitted to or from the SMF entity 210 via the AMF entity 205. In some cases, the AMF entity 205 and the SMF entity 210 may communicate via a network link 215.

[0114] The core network of wireless communication system 200 may train machine learning models to perform analytics, such as network optimization and inference. UEs 115 in wireless communication system 200, such as UE 115-a, may also support using machine learning models to perform analytics. Wireless communication system 200 may implement an example configuration of a distributed architecture for provisioning UEs 115, such as UE 115-a, with machine learning models that have been trained by the core network.

[0115] For a distributed architecture or distributed configuration, the core network entity may manage, store, or support one or more machine learning models associated with the functionality of the core network entity. For example, the AMF entity 205 may manage one or more AMF machine learning models, and the SMF entity 210 may manage one or more SMF machine learning models. The AMF entity 205 may, for example, support an AMF load analysis machine learning model or a bad behavior UE detection machine learning model. The SMF entity 210 may, for example, support a service experience analysis machine learning model.

[0116] UE 115-a and different core network entities may exchange capability information. For example, UE 115-a may send an indication of capability 220 of supporting a range of machine learning models at UE 115-a. UE 115 may send an indication of capability 220 to AMF entity 205 or SMF entity 210 or both. UE 115-a may receive an indication of capability 225 from AMF entity 205 or SMF entity 210 or both. Capabilities 225 may indicate a list of machine learning models supported at AMF entity 205 or SMF entity 210 or both. Figure 3 Additional techniques and signaling for UE and network capability exchange are described in more detail.

[0117] The UE 115-a or the core network may initiate a procedure for configuring the machine learning model to the UE 115-a. In some cases, the core network entity may receive a request 240 for the UE to perform analysis using the machine learning model, and the core network entity may configure the machine learning model to the UE based on the request. For example, another core network entity 245 may transmit a request 240-a for the AMF entity 205 to obtain AMF analysis based on the AMF machine learning model from the UE 115. Based on the UE and core network capability exchange, the AMF entity 205 may identify the UE 115-a as a UE 115 that supports the AMF machine learning model. Additionally or alternatively, another core network entity 245 may transmit a request 240-b for the SMF entity 210 to obtain SMF analysis based on the SMF machine learning model from the UE 115-a, and the SMF entity 210 may identify the UE 115-a as a UE 115 that supports the SMF machine learning model. Reference Figure 4 and Figure 5 Some additional examples of network-initiated procedures are described in more detail.

[0118] Additionally or alternatively, the UE 115-a may initiate the procedure by sending a request 235 for a machine learning model to a core network entity that supports the machine learning model. In some cases, the UE 115-a may determine the machine learning model to request based on the function or operation being 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 from the AMF entity 205 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 from the SMF entity 210.

[0119] For example, after exchanging capability information with the AMF entity 205, the UE 115-a may determine that the AMF entity 205 supports the AMF machine learning model 205, and the UE 115-a may send a request 235 to the AMF entity 205 requesting to be configured with the AMF machine learning model. In another example, after exchanging capability information with the SMF entity 210, the UE 115-a may determine that the SMF entity 210 supports the SMF machine learning model. The UE 115-a may send a request 235 to the SMF entity 210 requesting to be configured with the SMF machine learning model. Figure 6 and Figure 7 Additional examples of UE-initiated procedures are described in more detail.

[0120] UE 115-a may receive control signaling from a core network entity indicating a configuration for a machine learning model at UE 115-a. For example, AMF entity 205 may send control signaling indicating a machine learning model configuration 230 for an AMF machine learning model at UE 115-a, or SMF entity 210 may send control signaling indicating a machine learning model configuration 230 for an SMF machine learning model at UE 115-a. In some cases, UE 115-a may obtain the machine learning model from the core network. For example, 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-a may obtain the machine learning model from the core network via the address or location of the machine learning model.

[0121] 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 8 Some examples and techniques for using machine learning models are described in more detail.

[0122] In some examples, UE 115-a may report analysis, training information, or inferences determined based on the 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, a network entity of 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.

[0123] Figure 3 An example of a capability exchange procedure 300 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0124] The capability exchange procedure 300 may be implemented by the UE 115, the AMF entity 305, the SMF entity 310, or any combination thereof. The UE 115, the AMF entity 305, and the SMF entity 310 may be reference Figure 2 1 and 2. The corresponding examples of the UE 115, the AMF entity 205, and the SMF entity 210 are shown. The processes and signaling of the capability exchange 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 of the signaling or procedures shown may not be performed in other examples.

[0125] The machine learning model may require certain software, hardware, a 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 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.

[0126] The UE 115 may exchange capability information with different core network entities such as the AMF entity 305 and the SMF entity 310. The UE 115 may indicate a list of machine learning models supported at the UE 115, and each core network entity may indicate a list of machine learning models supported at the core network entity. For example, the UE 115 may indicate a capability to the AMF entity 305 to indicate that the UE 115 supports or is able to receive a machine learning model configuration from the AMF entity 305. In some cases, the indication of the supported machine learning models may include an identifier of the supported machine learning model.

[0127] For example, the UE 115 may send an indication of a first set of one or more machine learning models supported at the UE 115 to the AMF entity 305 at 315. In some cases, the UE 115 may send a registration request including an indication of the UE capabilities. The AMF entity 305 may send an indication of the machine learning models supported at the AMF entity 305 to the UE 115 at 320. For example, the UE 115 may receive a second set of one or more machine learning models supported at the AMF entity 305. In some cases, the AMF entity 305 may send a registration response including an indication of the AMF capabilities.

[0128] In another example, the UE 115 may send an indication of the machine learning models supported at the UE 115 to the SMF entity 310 at 325. For example, the UE 115 may send an indication of a first set of one or more machine learning models supported at the UE 115. In some cases, the UE 115 may send a protocol data unit (PDU) session establishment message or a PDU session modification request including an indication of the UE capabilities. The SMF entity 310 may send an indication of the machine learning models supported at the SMF entity 310 to the UE 115 at 330. For example, the UE 115 may receive an indication of a set of one or more machine learning models supported at the SMF entity 310. In some cases, the SMF entity 310 may send a PDU session establishment message or a PDU session modification response message including an indication of the SMF capabilities.

[0129] Figure 4 An example of a network-initiated machine learning model configuration 400 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0130] The network-initiated machine learning model configuration 400 may be implemented by the UE 115, the AMF entity 405, and another network entity 410, or any combination thereof. The UE 115 and the AMF entity 405 may be reference Figure 2 4. The UE 115 and the AMF entity 205 are examples of the corresponding embodiments. Another network entity 410 can be an example of another core network entity such as an SMF. 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 of the signaling or procedures shown may not be performed in other examples.

[0131] The UE 115 or the core network may initiate the procedure for configuring the machine learning model to the UE 115 in order to perform analysis. Network-initiated machine learning model configuration 400 illustrates an example in which an AMF entity 405 receives a request 415 from another entity 410 to configure a machine learning model to the UE 115.

[0132] The AMF entity 405 may receive an analysis request from another network entity 410 and, in response to the analysis request, determine to configure a machine learning model to the UE 115. For example, the AMF entity 405 may determine that obtaining the requested analysis requires UE-assisted model training or analysis.

[0133] In some cases, the analysis request may include a machine learning model identifier of a machine learning model used to perform the analysis, and the AMF entity 405 may identify the UE 115 that can support the machine learning model. For example, the AMF entity 405 may identify the UE 115 based on the reference Figure 3 The UE 115 may be identified by the UE and network capability exchange procedure described above. In some examples, different analysis operations may correspond to different analysis identifiers. The analysis request 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.

[0134] The AMF entity 405 may send control signaling 420 to the UE 115 for configuring the machine learning model for the UE 115. The control signaling 420 may include machine learning model configuration information, which the UE 115 may use to obtain the machine learning model. For example, the UE 115 may receive control signaling 420 from the AMF entity 405 indicating configuration of a machine learning model for the UE 115, the machine learning model being included in a first set of one or more machine learning models supported at the UE 115. In some cases, the AMF entity 405 may include the machine learning model configuration information in a UE Configuration Update Command message. Additionally or alternatively, the AMF entity 405 may send a NAS message of dedicated NAS signaling to convey or indicate the machine learning model configuration information to the UE 115.

[0135] The machine learning model configuration information may include various information about the machine learning model. For example, the machine learning model may include a machine learning model file address, a machine learning model training request, a machine learning model inference request, machine learning model information, an activation event, or any combination thereof. The machine learning model information may include, for example, a model identifier, a location of the machine learning model, a version of the machine learning model, an effective time for performing analysis based on the machine learning model, or any combination thereof.

[0136] The machine learning model file address may be, for example, a URL or FQDN that UE 115 may 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 UE 115 how to use the machine learning model. For example, the machine learning model configuration information may request that UE 115 perform additional training on the machine learning model or that UE 115 perform inference based on the machine learning model.

[0137] The activation event may indicate an event trigger for activating and using the machine learning model (such as by performing training, analysis, or inference). For example, the activation event may configure the UE 115 to use the machine learning model within a certain time period or duration of receiving the machine learning model configuration information, to use the machine learning model while in a certain location or geographic area, to use the machine learning model immediately after obtaining or downloading the machine learning model, or any combination thereof.

[0138] In some cases, the machine learning model configuration information may be configured to determine an analysis identifier for an 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 a stored address of the machine learning model file, a validity period, a machine learning model identifier for identifying the machine learning model, and a corresponding analysis identifier for 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.

[0139] In some cases, the UE 115 may send a response message 425 to the AMF entity 405. For example, the UE 115 may send the response message 425 based on receiving the machine learning model configuration information or based on obtaining the machine learning model. In some cases, the UE 115 may send a UE Configuration Update Complete NAS message to the AMF entity 405. In some other examples, the UE 115 may send the response message 425 using dedicated NAS signaling associated with the machine learning configuration.

[0140] At 430, 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 transmit a report of the analysis to the core network, such as by sending a report 435 to AMF entity 405. In some cases, AMF entity 405 may transmit the report to another network entity 410. In some cases, the core network may perform core network optimization based on the report.

[0141] Figure 5 An example of a network-initiated machine learning model configuration 500 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0142] The network-initiated machine learning model configuration 500 may be implemented by the UE 115, the SMF entity 505, and another core network entity 510, or any combination thereof. The UE 115 and the SMF entity 505 may be reference Figure 2 UE 115 and SMF entity 210 are corresponding examples. Another core network entity 510 can be an example of another core network entity such as an AMF entity. The process and signaling of network-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 of the signaling or procedures shown may not be performed in other examples.

[0143] The UE 115 or the core network may initiate the procedure for configuring the machine learning model to the UE 115 for performing analysis. Network-initiated machine learning model configuration 500 illustrates an example where an SMF entity 505 receives a request 515 from another core network entity 510 to configure a machine learning model to the UE 115.

[0144] The SMF entity 505 may receive an analysis request from another core network entity 510 and, in response to the analysis request, determine to configure a machine learning model to the UE 115. For example, the SMF entity 505 may determine that obtaining the requested analysis requires UE-assisted model training or analysis.

[0145] In some cases, the analysis request may include a machine learning model identifier of a machine learning model used to perform the analysis, and the SMF entity 505 may identify a UE 115 that can support the machine learning model. For example, the SMF entity 505 may identify a UE 115 that can support the machine learning model based on the reference Figure 3 The UE 115 is identified by the UE and network capability exchange procedure described above.

[0146] The SMF entity 505 may send control signaling 520 to the UE 115 to configure the machine learning model for the UE 115. In some cases, the control signaling 520 may be sent as a NAS message via the AMF entity. The control signaling 520 may include machine learning model configuration information, which the UE 115 may use to obtain the machine learning model. For example, the UE 115 may receive control signaling 520 from the SMF entity 505 indicating the configuration of a machine learning model for the UE 115, the machine learning model being included in a first set of one or more machine learning models supported at the UE 115. In some cases, the SMF entity 505 may include the machine learning model configuration information in a PDU Session Modification Command message. Additionally or alternatively, the SMF entity 505 may send a NAS message of dedicated NAS signaling to convey or indicate the machine learning model configuration information to the UE 115.

[0147] The machine learning model configuration information may include various information about the machine learning model. For example, the machine learning model may include a machine learning model file address, a machine learning model training request, a machine learning model inference request, machine learning model information, an activation event, or any combination thereof. The machine learning model information may include, for example, a model identifier, a location of the machine learning model, a version of the machine learning model, an effective time for performing analysis based on the machine learning model, or any combination thereof.

[0148] The machine learning model file address may be, for example, a URL or FQDN that UE 115 may 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 UE 115 how to use the machine learning model. For example, the machine learning model configuration information may request that UE 115 perform additional training on the machine learning model or that UE 115 perform inference based on the machine learning model.

[0149] The activation event may indicate an event trigger for activating and using the machine learning model (such as by performing training, analysis, or inference). For example, the activation event may configure the UE 115 to use the machine learning model within a certain time period or duration of receiving the machine learning model configuration information, to use the machine learning model while in a certain location or geographic area, to use the machine learning model immediately after obtaining or downloading the machine learning model, or any combination thereof.

[0150] In some cases, the machine learning model configuration information may configure an analysis identifier for determining an 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. 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 UE 115 may send a response message 525 to the SMF entity 505. For example, the UE 115 may send the response message 525 based on receiving the machine learning model configuration information or based on obtaining the machine learning model. In some cases, the UE 115 may send a PDU session modification complete message to the SMF entity 505. In some other examples, the UE 115 may send the response message using dedicated NAS signaling associated with the machine learning configuration.

[0152] At 530, 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 transmit a report of the analysis to the core network, such as by sending a report 535 to SMF entity 505. In some cases, SMF entity 505 may transmit the report to another core network entity 510. In some cases, the core network may perform core network optimization based on the report.

[0153] Figure 6 An example of UE-initiated machine learning model configuration 600 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0154] The UE-initiated machine learning model configuration 600 may be implemented by the UE 115 and the AMF entity 605. The UE 115 and the AMF entity 605 may be reference Figure 2 1 and corresponding examples of the UE 115 and the AMF entity 205. The process and signaling of the UE-initiated machine learning model configuration 600 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 of the signaling or procedures shown may not be performed in other examples.

[0155] The UE 115 or the core network may initiate a procedure for configuring the machine learning model to the UE 115 for performing analysis. The UE-initiated machine learning model configuration 600 illustrates an example of the UE 115 sending a request 610 to the AMF entity 605 requesting a configured machine learning model for the UE 115 to use to perform analysis using the machine learning model. The UE may include an identifier of the machine learning model with the request 610. In one example, the UE 115 may send a service request to the AMF entity 605 requesting the machine learning model. The UE 115 may send a service request to the AMF entity 605 requesting the machine learning model. The UE 115 may send a service request to the AMF entity 605 requesting the machine learning model. Figure 3 The UE and network capability exchange procedure is used to determine whether the AMF entity 605 supports the machine learning model.

[0156] The AMF entity 605 may send control signaling 615 to the UE 115 for configuring the machine learning model for the UE 115. The control signaling 615 may include machine learning model configuration information, which the UE 115 may use to obtain the machine learning model. For example, the UE 115 may receive control signaling 615 from the AMF entity 605 indicating configuration of a machine learning model for the UE 115, the machine learning model being included in a first set of one or more machine learning models supported at the UE 115. In some cases, the AMF entity 605 may include the machine learning model configuration information in a service request message. Additionally or alternatively, the AMF entity 605 may send a NAS message of dedicated NAS signaling to convey or indicate the machine learning model configuration information to the UE 115.

[0157] The machine learning model configuration information may include the requested machine learning model information. In some cases, the machine learning model configuration information may include a machine learning model file address or an event filter or both. The machine learning model file address may be, for example, a URL or FQDN that the UE 115 may use to obtain or download the machine learning model from the core network. The event filter may, for example, include one or more filters for a trigger-based or event-based reporting scheme. Additionally or alternatively, the machine learning model configuration information may include, for example, a reference to the machine learning model configuration information or a reference to the event filter. Figure 4 and Figure 5 Any information described in the configuration of the network-initiated machine learning model.

[0158] At 620, 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 transmit a report of the analysis to the core network. In some cases, UE 115 may perform UE-side optimization based on the analysis.

[0159] Figure 7 An example of UE-initiated machine learning model configuration 700 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated.

[0160] UE-initiated machine learning model configuration 700 may be implemented by UE 115 and SMF entity 705. UE 115 and SMF entity 705 may be reference Figure 2 UE 115 and SMF entity 210 are shown in Figure 7. The process and signaling of UE-initiated machine learning model configuration 700 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 of the signaling or procedures shown may not be performed in other examples.

[0161] The UE 115 or the core network may initiate a procedure for configuring the machine learning model to the UE 115 for performing analysis. The UE-initiated machine learning model configuration 700 illustrates an example of the UE 115 sending a request 710 to the SMF entity 705 requesting a configured machine learning model for the UE 115 to use to perform analysis using the machine learning model. The UE 115 may include an identifier of the machine learning model with the request 710. In one example, the UE 115 may send a PDU session modification request to the SMF entity 705 requesting the machine learning model. The UE 115 may perform the following steps based on the referenced example: Figure 3 The UE and network capability exchange procedure is used to determine whether the SMF entity 705 supports the machine learning model.

[0162] The SMF entity 705 may send control signaling 715 to the UE 115 for configuring the machine learning model for the UE 115. The control signaling 715 may include machine learning model configuration information, which the UE 115 may use to obtain the machine learning model. For example, the UE 115 may receive control signaling 715 from the SMF entity 705 indicating configuration of a machine learning model for the UE 115, the machine learning model being included in a first set of one or more machine learning models supported at the UE 115. In some cases, the SMF entity 705 may include the machine learning model configuration information in a PDU session modification command message. Additionally or alternatively, the SMF entity 705 may send a NAS message of dedicated NAS signaling to convey or indicate the machine learning model configuration information to the UE 115.

[0163] The machine learning model configuration information may include the requested machine learning model information. In some cases, the machine learning model configuration information may include a machine learning model file address or an event filter or both. The machine learning model file address may be, for example, a URL or FQDN that the UE 115 may use to obtain or download the machine learning model from the core network. The event filter may, for example, include one or more filters for a trigger-based or event-based reporting scheme. Additionally or alternatively, the machine learning model configuration information may include, for example, a reference to the machine learning model configuration information or a reference to the event filter. Figure 4 and Figure 5 Any information described in the configuration of the network-initiated machine learning model.

[0164] The UE 115 may send a response message 720 to the SMF entity 705. For example, the UE 115 may send a PDU session modification complete message to the SMF entity 705.

[0165] At 725, 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 transmit a report of the analysis to the core network. In some cases, UE 115 may perform UE-side optimization based on the analysis.

[0166] Figure 8 An example of a machine learning process 800 supporting distributed machine learning model configuration according to aspects of the present disclosure is illustrated. The machine learning process 800 may be implemented at a device 850, which may be a device such as a reference device. Figures 1 to 7 800 to perform analysis, inference, or training based on a machine learning model. In some examples, the machine learning model can be configured to the UE 115 according to the techniques described herein via a separate or distributed core network entity that can manage one or more machine learning models associated with the functions of the core network entity.

[0167] The machine learning process 800 may include a machine learning algorithm 810. The machine learning algorithm 810 may be implemented by the device 850. As illustrated, the machine learning algorithm 810 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 be supported. For example, the machine learning algorithm 810 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 800 may involve supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or any combination thereof.

[0168] The machine learning algorithm 810 may include an input layer 815, one or more hidden layers 820, and an output layer 825. In a fully connected neural network with one hidden layer 820, each hidden layer node 835 may receive a value as input from each input layer node 830, 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 810. Similarly, each output layer node 840 may receive a value as input from each hidden layer node 835, where the inputs are 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 810 based on output feedback. Training the machine learning algorithm 810 may support the calculation of weights (e.g., connecting input layer nodes 830 to hidden layer nodes 835 and connecting hidden layer nodes 835 to output layer nodes 840) to map input patterns to desired output results. The training may generate a device-specific machine learning algorithm 810 based on historical application data and data transfer for a particular network entity 105 or UE 115 .

[0169] In some examples, the input values ​​805 may be transmitted to the machine learning algorithm 810 for processing. In some examples, the input values ​​805 may be pre-processed according to a sequence of operations so that the input values ​​805 may be in a format compatible with the machine learning algorithm 810. The input values ​​805 may be converted into a set of k input layer nodes 830 at the input layer 815. In some cases, different measurements may be input at different input layer nodes 830 of the input layer 815. If the number of input layer nodes 830 exceeds the number of inputs corresponding to the input values ​​805, some input layer nodes 830 may be assigned a default value (e.g., a value of 0). As illustrated, the input layer 815 may include three input layer nodes 830-a, 830-b, and 830-c. However, it should be understood that the input layer 815 may include any number of input layer nodes 830 (e.g., 20 input nodes).

[0170] The machine learning algorithm 810 can convert the input layer 815 into a hidden layer 820 based on the number of input-to-hidden weights between the k input layer nodes 830 and the n hidden layer nodes 835. The machine learning algorithm 810 can include any number of hidden layers 820 as an intermediate step between the input layer 815 and the output layer 825. Additionally, each hidden layer 820 can include any number of nodes. For example, as illustrated in the figure, the hidden layer 820 can include four hidden layer nodes 835-a, 835-b, 835-c, and 835-d. However, it should be understood that the hidden layer 820 can include any number of hidden layer nodes 835 (e.g., 10 input nodes). In a fully connected neural network, each node in a layer can be based on each node in the previous layer. For example, the value of the hidden layer node 835-a can be based on the values ​​of the input layer nodes 830-a, 830-b, and 830-c (e.g., different weights are applied to each node value).

[0171] The machine learning algorithm 810 may determine the value of an output layer node 840 of an output layer 825 following one or more hidden layers 820. For example, the machine learning algorithm 810 may convert a hidden layer 820 into an output layer 825 based on the number of hidden-to-output weights between n hidden layer nodes 835 and m output layer nodes 840. In some cases, n=m. Each output layer node 840 may correspond to a different output value 845 of the machine learning algorithm 810. As illustrated, the machine learning algorithm 810 may include three output layer nodes 840-a, 840-b, and 840-c, each supporting three different thresholds. However, it should be understood that the output layer 825 may include any number of output layer nodes 840. In some examples, post-processing may be performed on the output value 845 according to a sequence of operations so that the output value 845 is in a format compatible with reporting the output value 845.

[0172] Figure 9 A block diagram 900 of a device 905 supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 905 can be an example of aspects of the UE 115 as described herein. The device 905 can include a receiver 910, a transmitter 915, and a communication manager 920. The device 905 can also include a processor. Each of these components can communicate with each other (e.g., via one or more buses).

[0173] Receiver 910 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 distributed machine learning model configurations). The information may be passed to other components of device 905. Receiver 910 may utilize a single antenna or a set of multiple antennas.

[0174] The transmitter 915 may provide means for transmitting signals generated by other components of the device 905. For example, the transmitter 915 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 distributed machine learning model configurations). In some examples, the transmitter 915 may be co-located with the receiver 910 in a transceiver module. The transmitter 915 may utilize a single antenna or a set of multiple antennas.

[0175] The communication manager 920, receiver 910, transmitter 915, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of the distributed machine learning model configuration as described herein. For example, the communication manager 920, receiver 910, transmitter 915, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0176] In some examples, the communication manager 920, the receiver 910, the transmitter 915, 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 as 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).

[0177] Additionally or alternatively, in some examples, the communication manager 920, receiver 910, transmitter 915, 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 920, receiver 910, transmitter 915, 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 herein), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0178] In some examples, the communication manager 920 can be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the receiver 910, the transmitter 915, or both. For example, the communication manager 920 can receive information from the receiver 910, transmit information to the transmitter 915, or be integrated with the receiver 910, the transmitter 915, or both to obtain information, output information, or perform various other operations as described herein.

[0179] According to the examples disclosed herein, the communication manager 920 may support wireless communications at a UE. For example, the communication manager 920 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 core network entity. For example, the communication manager 920 may be configured to or otherwise support components for receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity. The communication manager 920 may be configured to or otherwise support components for receiving control signaling from the core network entity indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The communication manager 920 may be configured to or otherwise support components for performing analysis based on the machine learning model.

[0180] By including or configuring the communication manager 920 according to examples as described herein, the device 905 (e.g., a processor controlling the receiver 910, the transmitter 915, the communication manager 920, or a combination thereof or otherwise coupled thereto) may support techniques for reducing power consumption by identifying optimizations at the device 905 based on performing inferences using a machine learning model.

[0181] Figure 10 A block diagram 1000 of a device 1005 supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1005 can be an example of aspects of the device 905 or UE 115 as described herein. The device 1005 can include a receiver 1010, a transmitter 1015, and a communication manager 1020. The device 1005 can also include a processor. Each of these components can communicate with each other (e.g., via one or more buses).

[0182] Receiver 1010 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 distributed machine learning model configurations). The information may be passed to other components of device 1005. Receiver 1010 may utilize a single antenna or a set of multiple antennas.

[0183] Transmitter 1015 may provide means for transmitting signals generated by other components of device 1005. For example, transmitter 1015 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 distributed machine learning model configuration). In some examples, transmitter 1015 may be co-located with receiver 1010 in a transceiver module. Transmitter 1015 may utilize a single antenna or a set of multiple antennas.

[0184] Device 1005 or its various components can be examples of components for performing various aspects of distributed machine learning model configuration as described herein. For example, communication manager 1020 can include UE capability component 1025, network capability component 1030, machine learning model configuration component 1035, analysis component 1040, or any combination thereof. Communication manager 1020 can be an example of various aspects of communication manager 920 as described herein. In some examples, communication manager 1020 or its various components can be configured to use or otherwise cooperate with receiver 1010, transmitter 1015, or both to perform various operations (e.g., receive, obtain, monitor, output, transmit). For example, communication manager 1020 can receive information from receiver 1010, transmit information to transmitter 1015, or be integrated with receiver 1010, transmitter 1015, or both to obtain information, output information, or perform various other operations as described herein.

[0185] According to examples as disclosed herein, the communications manager 1020 may support wireless communications at a UE. The UE capabilities component 1025 may be configured to or otherwise support means for sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity. The network capabilities component 1030 may be configured to or otherwise support means for receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity. The machine learning model configuration component 1035 may be configured to or otherwise support means for receiving control signaling from the core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The analysis component 1040 may be configured to or otherwise support means for performing analysis based on the machine learning model.

[0186] Figure 11A block diagram 1100 of a communication manager 1120 supporting distributed machine learning model configuration in accordance with one or more aspects of the present disclosure is shown. The communication manager 1120 can be an example of aspects of the communication manager 920, the communication manager 1020, or both, as described herein. The communication manager 1120 or its various components can be examples of means for performing various aspects of the distributed machine learning model configuration as described herein. For example, the communication manager 1120 can include a UE capability component 1125, a network capability component 1130, a machine learning model configuration component 1135, an analysis component 1140, a request component 1145, a completion message component 1150, a machine learning model acquisition component 1155, or any combination thereof. Each of these components can communicate with each other directly or indirectly (e.g., via one or more buses).

[0187] According to examples as disclosed herein, the communication manager 1120 may support wireless communications at a UE. The UE capability component 1125 may be configured to or otherwise support means for sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity. The network capability component 1130 may be configured to or otherwise support means for receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity. The machine learning model configuration component 1135 may be configured to or otherwise support means for receiving control signaling from the core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The analysis component 1140 may be configured to or otherwise support means for performing analysis based on the machine learning model.

[0188] In some examples, request component 1145 can be configured or otherwise support means for sending a request for a machine learning model to a core network entity. In some examples, machine learning model configuration component 1135 can be configured or otherwise support means for receiving control signaling in response to sending the request.

[0189] In some examples, to support sending requests, request component 1145 can be configured or otherwise support means for sending service request messages. In some examples, to support sending requests, machine learning model configuration component 1135 can be configured or otherwise support means for receiving control signaling via service response messages.

[0190] In some examples, to support sending the request, request component 1145 can be configured or otherwise support means for sending a protocol data unit session modification request message. In some examples, to support sending the request, machine learning model configuration component 1135 can be configured or otherwise support means for receiving control signaling via a protocol data unit session modification command message. In some examples, the request includes an identifier of the machine learning model.

[0191] In some examples, completion message component 1150 may be configured as or otherwise support components for sending a completion message to a core network entity based on control signaling indicating configuration for a machine learning model.

[0192] In some examples, to support receiving control signaling, the machine learning model configuration component 1135 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.

[0193] In some examples, to support receiving control signaling, the machine learning model configuration component 1135 may be configured as or otherwise support components for receiving a UE configuration update command indicating a configuration for a machine learning model.

[0194] In some examples, to support sending an indication of the first set of one or more machine learning models, UE capability component 1125 can be configured or otherwise support means for sending a registration request indicating the first set of one or more machine learning models supported at the UE. In some examples, to support sending an indication of the first set of one or more machine learning models, network capability component 1130 can be configured or otherwise support means for receiving an indication of the second set of one or more machine learning models via a registration response message.

[0195] In some examples, to support receiving control signaling, machine learning model configuration component 1135 may be configured as or otherwise support components for receiving protocol data unit session modification commands indicating configuration for the machine learning model.

[0196] In some examples, completion message component 1150 may be configured as or otherwise support components for sending a protocol data unit session modification completion message to a core network entity based on a protocol data unit session modification command indicating configuration for a machine learning model.

[0197] In some examples, to support sending an indication of the first set of one or more machine learning models, UE capability component 1125 can be configured or otherwise support means for sending a session establishment message or a modification request message indicating the first set of one or more machine learning models supported at the UE. In some examples, to support sending an indication of the first set of one or more machine learning models, network capability component 1130 can be configured or otherwise support means for receiving an indication of the second set of one or more machine learning models via a session establishment response message or a modification response message.

[0198] In some examples, to support receiving control signaling, machine learning model configuration component 1135 can be configured or otherwise support means for receiving one or more parameters of a machine learning model. In some examples, to support receiving control signaling, analysis component 1140 can be configured or otherwise support means for performing analysis based on the one or more parameters.

[0199] In some examples, the machine learning model obtaining component 1155 may be configured to or otherwise support components for obtaining a machine learning model from the core network based on an address indicated via control signaling. In some examples, the core network entity is an AMF entity or an SMF entity.

[0200] Figure 12 A diagram of a system 1200 including a device 1205 that supports distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. Device 1205 can be an example of device 905, device 1005, or UE 115 as described herein, or include components thereof. Device 1205 can communicate (e.g., wirelessly) with one or more network entities 105, one or more UEs 115, or any combination thereof. Device 1205 may include components for two-way voice and data communication, including components for sending and receiving communications, such as a communication manager 1220, an input / output (I / O) controller 1210, a transceiver 1215, an antenna 1225, a memory 1230, code 1235, and a processor 1240. These components can be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1245).

[0201] I / O controller 1210 can manage input and output signals for device 1205. I / O controller 1210 can also manage peripheral devices that are not integrated into device 1205. In some cases, I / O controller 1210 can represent a physical connection or port to an external peripheral device. In some cases, I / O controller 1210 can utilize an operating system such as or another known operating system. Additionally or alternatively, I / O controller 1210 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, I / O controller 1210 may be implemented as part of a processor, such as processor 1240. In some cases, a user may interact with device 1205 via I / O controller 1210 or via hardware components controlled by I / O controller 1210.

[0202] In some cases, device 1205 may include a single antenna 1225. However, in some other cases, device 1205 may have more than one antenna 1225, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. Transceiver 1215 may communicate bidirectionally via one or more antennas 1225, wired, or wireless links, as described herein. For example, transceiver 1215 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Transceiver 1215 may also include a modem for modulating packets; providing the modulated packets to one or more antennas 1225 for transmission; and demodulating packets received from one or more antennas 1225. Transceiver 1215, or transceiver 1215 and one or more antennas 1225, may be examples of transmitter 915, transmitter 1015, receiver 910, receiver 1010, or any combination thereof, or any component thereof, as described herein.

[0203] Memory 1230 may include random access memory (RAM) and read-only memory (ROM). Memory 1230 may store computer-readable, computer-executable code 1235 including instructions that, when executed by processor 1240, cause device 1205 to perform the various functions described herein. Code 1235 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1235 may not be directly executed by processor 1240, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, memory 1230 may include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0204] The processor 1240 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, the processor 1240 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1240. The processor 1240 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1230) to cause the device 1205 to perform various functions (e.g., functions or tasks supporting distributed machine learning model configuration). For example, the device 1205 or a component of the device 1205 may include a processor 1240 and a memory 1230 coupled to or coupled to the processor 1240, the processor 1240 and the memory 1230 being configured to perform the various functions described herein.

[0205] According to examples as disclosed herein, the communications manager 1220 may support wireless communications at a UE. For example, the communications manager 1220 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 core network entity. For example, the communications manager 1220 may be configured to or otherwise support components for receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity. The communications manager 1220 may be configured to or otherwise support components for receiving control signaling from the core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The communications manager 1220 may be configured to or otherwise support components for performing analysis based on the machine learning model.

[0206] By including or configuring the communication manager 1220 according to examples as described herein, the device 1205 may support techniques for improving coordination between devices by identifying optimizations at the UE 115, the core network, or both based on the UE 115 using a machine learning model to perform inferences. For example, the UE 115 may use a machine learning model to perform network load analysis to select a network with a low load, thereby reducing latency and network load carrying.

[0207] In some examples, the communication manager 1220 can be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise coordinating with the transceiver 1215, one or more antennas 1225, or any combination thereof. Although the communication manager 1220 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1220 can be supported or performed by the processor 1240, the memory 1230, the code 1235, or any combination thereof. For example, the code 1235 can include instructions executable by the processor 1240 to cause the device 1205 to perform various aspects of the distributed machine learning model configuration as described herein, or the processor 1240 and the memory 1230 can be otherwise configured to perform or support such operations.

[0208] Figure 13 A block diagram 1300 of a device 1305 supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1305 can be an example of aspects of the network entity 105 as described herein. The device 1305 can include a receiver 1310, a transmitter 1315, and a communication manager 1320. The device 1305 can also include a processor. Each of these components can communicate with each other (e.g., via one or more buses).

[0209] Receiver 1310 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 1305. In some examples, receiver 1310 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1310 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof.

[0210] Transmitter 1315 may provide means for outputting (e.g., transmitting, providing, conveying, transmitting) information generated by other components of device 1305. For example, transmitter 1315 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, transmitter 1315 may support outputting information by transmitting signals via one or more antennas. Additionally or alternatively, transmitter 1315 may support outputting information by transmitting signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof. In some examples, transmitter 1315 and receiver 1310 may be co-located in a transceiver, which may include or be coupled to a modem.

[0211] The communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of the distributed machine learning model configuration as described herein. For example, the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0212] In some examples, the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof can be implemented in hardware (e.g., in a communication management circuit). The hardware can 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, the processor and a memory coupled to the processor can be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0213] Additionally or alternatively, in some examples, the communication manager 1320, receiver 1310, transmitter 1315, 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 1320, receiver 1310, transmitter 1315, or various combinations or components thereof may be performed by a general-purpose processor (e.g., a DSP, CPU, ASIC, FPGA, microcontroller, or any combination of these or other programmable logic devices) (e.g., configured as or otherwise supporting components for performing the functions described herein).

[0214] In some examples, communication manager 1320 can be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with receiver 1310, transmitter 1315, or both. For example, communication manager 1320 can receive information from receiver 1310, transmit information to transmitter 1315, or be integrated with receiver 1310, transmitter 1315, or both to obtain information, output information, or perform various other operations as described herein.

[0215] According to examples as disclosed herein, the communications manager 1320 may support wireless communications at a first core network entity. For example, the communications manager 1320 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 a UE. The communications manager 1320 may be configured to or otherwise support components for outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. The communications manager 1320 may be configured to or otherwise support components for outputting control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0216] By including or configuring the communication manager 1320 according to the examples described herein, the device 1305 (e.g., a processor controlling the receiver 1310, the transmitter 1315, the communication manager 1320, 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.

[0217] Figure 14 A block diagram 1400 of a device 1405 supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The device 1405 can be an example of aspects of the device 1305 or the network entity 105 as described herein. The device 1405 can include a receiver 1410, a transmitter 1415, and a communication manager 1420. The device 1405 can also include a processor. Each of these components can communicate with each other (e.g., via one or more buses).

[0218] Receiver 1410 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 1405. In some examples, receiver 1410 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1410 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof.

[0219] Transmitter 1415 may provide means for outputting (e.g., transmitting, providing, conveying, transmitting) information generated by other components of device 1405. For example, transmitter 1415 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, transmitter 1415 may support outputting information by transmitting signals via one or more antennas. Additionally or alternatively, transmitter 1415 may support outputting information by transmitting signals via one or more wired (e.g., electrical, optical fiber) interfaces, wireless interfaces, or any combination thereof. In some examples, transmitter 1415 and receiver 1410 may be co-located in a transceiver, which may include or be coupled to a modem.

[0220] Device 1405 or its various components can be examples of components for performing various aspects of distributed machine learning model configuration as described herein. For example, communication manager 1420 may include UE capability component 1425, network capability component 1430, machine learning model configuration component 1435, or any combination thereof. Communication manager 1420 can be an example of various aspects of communication manager 1320 as described herein. In some examples, communication manager 1420 or its various components can be configured to use or otherwise cooperate with receiver 1410, transmitter 1415, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, communication manager 1420 can receive information from receiver 1410, transmit information to transmitter 1415, or be integrated with receiver 1410, transmitter 1415, or both to obtain information, output information, or perform various other operations as described herein.

[0221] According to examples as disclosed herein, the communication manager 1420 may support wireless communications at a first core network entity. The UE capability component 1425 may be configured to or otherwise support means for obtaining an indication of a first set of one or more machine learning models supported at the UE. The network capability component 1430 may be configured to or otherwise support means for outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. The machine learning model configuration component 1435 may be configured to or otherwise support means for outputting control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0222] Figure 15 A block diagram 1500 is shown of a communication manager 1520 that supports distributed machine learning model configuration according to one or more aspects of the present disclosure. The communication manager 1520 can be an example of aspects of the communication manager 1320, the communication manager 1420, or both, as described herein. The communication manager 1520 or its various components can be examples of means for performing various aspects of the distributed machine learning model configuration as described herein. For example, the communication manager 1520 can include a UE capability component 1525, a network capability component 1530, a machine learning model configuration component 1535, a request receiving component 1540, a completion message component 1545, a network entity communication component 1550, or any combination thereof. Each of these components can communicate with each other directly or indirectly (e.g., via one or more buses), which communication can include communication within a protocol layer of a protocol stack, communication associated with a logical channel of the protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with the network entity 105, or between devices, components, or virtualized components associated with the network entity 105), or any combination thereof.

[0223] According to examples as disclosed herein, communications manager 1520 may support wireless communications at a first core network entity. UE capabilities component 1525 may be configured to or otherwise support means for obtaining an indication of a first set of one or more machine learning models supported at the UE. Network capabilities component 1530 may be configured to or otherwise support means for outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. Machine learning model configuration component 1535 may be configured to or otherwise support means for outputting control signaling indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0224] In some examples, request receiving component 1540 can be configured or otherwise support means for obtaining a service request message requesting a machine learning model. In some examples, machine learning model configuring component 1535 can be configured or otherwise support means for outputting control signaling via a service response message in response to the service request message.

[0225] In some examples, request receiving component 1540 can be configured or otherwise support means for obtaining a protocol data unit session modification request message requesting a machine learning model. In some examples, machine learning model configuring component 1535 can be configured or otherwise support means for outputting control signaling via a protocol data unit session modification command message in response to the protocol data unit session modification request message.

[0226] In some examples, completion message component 1545 can be configured or otherwise support means for obtaining a UE configuration update completion message in response to control signaling indicating configuration for a machine learning model. In some examples, machine learning model configuration component 1535 can be configured or otherwise support means for outputting control signaling via a UE configuration update command.

[0227] In some examples, completion message component 1545 can be configured or otherwise support means for obtaining a protocol data unit session modification completion message in response to control signaling indicating configuration for the machine learning model. In some examples, machine learning model configuration component 1535 can be configured or otherwise support means for outputting control signaling via a protocol data unit session modification command message.

[0228] In some examples, request receiving component 1540 can be configured to or otherwise support components for obtaining a request from another core network entity for the UE to perform analysis based on a machine learning model. In some examples, machine learning model configuring component 1535 can be configured to or otherwise support components for outputting control signaling in response to the request.

[0229] In some examples, to support output control signaling, the machine learning model configuration component 1535 may be configured as or otherwise support components for outputting 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 based on the machine learning model, an activation event for reporting analysis, one or more parameters for performing analysis, or any combination thereof.

[0230] In some examples, to support outputting an indication of the first set of one or more machine learning models, UE capability component 1525 can be configured or otherwise support means for obtaining a registration request indicating the first set of one or more machine learning models supported at the UE. In some examples, to support outputting an indication of the first set of one or more machine learning models, network capability component 1530 can be configured or otherwise support means for outputting an indication of the second set of one or more machine learning models via a registration response message.

[0231] In some examples, to support obtaining an indication of a first set of one or more machine learning models, UE capability component 1525 can be configured to or otherwise support means for obtaining a session establishment message or modification request message indicating a first set of one or more machine learning models supported at the UE. In some examples, to support obtaining an indication of a first set of one or more machine learning models, network capability component 1530 can be configured to or otherwise support means for outputting an indication of a second set of one or more machine learning models via a session establishment response message or a modification response message.

[0232] In some examples, the first core network entity is an AMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for outputting an indication of a first set of one or more machine learning models supported at the UE to an SMF entity, wherein the second core network entity is an SMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for obtaining, from the SMF entity, an indication of a second set of one or more machine learning models supported at the SMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for obtaining, from the SMF entity, control signaling indicating configuration for the machine learning model.

[0233] In some examples, the first core network entity is an SMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for obtaining an indication of a first set of one or more machine learning models supported at the UE from an AMF entity, wherein the second core network entity is an AMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for outputting an indication of a second set of one or more machine learning models supported at the SMF entity to the AMF entity. In some examples, the network entity communication component 1550 may be configured to or otherwise support means for outputting control signaling indicating configuration for the machine learning model to the AMF entity.

[0234] Figure 16A diagram of a system 1600 including a device 1605 supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. Device 1605 can be an example of device 1305, device 1405, or network entity 105 as described herein, or include components thereof. Device 1605 can communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, which communication may include communication via one or more wired interfaces, via one or more wireless interfaces, or any combination thereof. Device 1605 may include components that support output and acquisition of communications, such as a communication manager 1620, a transceiver 1610, an antenna 1615, a memory 1625, code 1630, and a processor 1635. 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 1640).

[0235] The transceiver 1610 may support bidirectional communication via a wired link, a wireless link, or both as described herein. In some examples, the transceiver 1610 may include a wired transceiver and may communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, the transceiver 1610 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1605 may include one or more antennas 1615, which may be capable of sending or receiving wireless transmissions (e.g., concurrently). The transceiver 1610 may also include a modem for: modulating a signal; providing the modulated signal for transmission (e.g., by one or more antennas 1615, by a wired transmitter); receiving the modulated signal (e.g., from one or more antennas 1615, from a wired receiver); and demodulating the signal. Transceiver 1610, or transceiver 1610 and one or more antennas 1615, or a wired interface (where applicable), can be examples of transmitter 1315, transmitter 1415, receiver 1310, receiver 1410, or any combination thereof, or any components thereof, as described herein. In some examples, the transceiver is 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).

[0236] Memory 1625 may include RAM and ROM. Memory 1625 may store computer-readable, computer-executable code 1630 including instructions that, when executed by processor 1635, cause device 1605 to perform the various functions described herein. Code 1630 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1630 may not be directly executed by processor 1635, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, memory 1625 may also contain, among other things, a BIOS that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0237] The processor 1635 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA, a microcontroller, a programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof). In some cases, the processor 1635 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1635. The processor 1635 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1625) to cause the device 1605 to perform various functions (e.g., functions or tasks supporting distributed machine learning model configuration). For example, the device 1605 or a component of the device 1605 may include a processor 1635 and a memory 1625 coupled to the processor 1635, the processor 1635 and the memory 1625 being configured to perform the various functions described herein. The processor 1635 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) that may host functions for performing the functions of the device 1605 (e.g., by executing code 1630).

[0238] In some examples, bus 1640 may support communications for protocol layers of a protocol stack (e.g., within a protocol layer). In some examples, bus 1640 may support communications associated with logical channels of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within components of device 1605 or between different components of device 1605 that may be co-located or located in different locations (e.g., where device 1605 may refer to a system in which one or more of communication manager 1620, transceiver 1610, memory 1625, code 1630, and processor 1635 may be located in one of these different components or divided between different components).

[0239] In some examples, communication manager 1620 can manage aspects of communications with core network 130 (e.g., via one or more wired or wireless backhaul links). For example, communication manager 1620 can manage the delivery of data communications to client devices, such as one or more UEs 115. In some examples, communication manager 1620 can manage communications with other network entities 105 and can include a controller or scheduler for controlling communications with UEs 115 in coordination with other network entities 105. In some examples, communication manager 1620 can support an X2 interface within LTE / LTE-A wireless communication network technology to provide communications between network entities 105.

[0240] According to examples as disclosed herein, the communication manager 1620 may support wireless communications at a first core network entity. For example, the communication manager 1620 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 a UE. The communication manager 1620 may be configured to or otherwise support components for outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. The communication manager 1620 may be configured to or otherwise support components for outputting control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model.

[0241] By including or configuring the communication manager 1620 according to the examples described herein, the device 1605 can support techniques for improving coordination between devices by identifying optimizations at the UE 115, the core network, or both based on the UE 115 using a machine learning model to perform inferences. For example, an application client can request that the UE 115 perform analysis using a machine learning model, and the UE 115 can report analysis information from the machine learning model. The application client can use the reported information to, for example, perform split rendering, reduce processing power at the UE 115 or the network, or both.

[0242] In some examples, the communication manager 1620 can be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the transceiver 1610, one or more antennas 1615 (e.g., where applicable), or any combination thereof. Although the communication manager 1620 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1620 can be supported or performed by the processor 1635, the memory 1625, the code 1630, the transceiver 1610, or any combination thereof. For example, the code 1630 can include instructions executable by the processor 1635 to cause the device 1605 to perform various aspects of the distributed machine learning model configuration as described herein, or the processor 1635 and the memory 1625 can be otherwise configured to perform or support such operations.

[0243] Figure 17 A flowchart illustrating a method 1700 for supporting distributed 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 herein. Figures 1 to 12 The UE 115 may be used to perform the described functions. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0244] 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 a 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 Figure 11 The UE capability component 1125 is used to perform the above operations.

[0245] At 1710, the method may include sending, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity. The operations of 1710 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed as described in reference to Figure 11 The network capability component 1130 is used to execute.

[0246] At 1715, the method may include: receiving control signaling from a core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The operations of 1715 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1715 may be performed as described in reference to Figure 11 The machine learning model is configured by component 1135 for execution.

[0247] At 1720, the method may include performing analysis based on the machine learning model. The operations of 1720 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 1720 may be performed as described in reference to Figure 11 The analysis component 1140 is used to perform the analysis.

[0248] Figure 18 A flowchart illustrating a method 1800 for supporting distributed 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 UE or a component thereof as described herein. For example, the operations of the method 1800 may be implemented by a UE or a component thereof as described herein. Figures 1 to 12 The UE 115 may be used to perform the described functions. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0249] At 1805, the method may include sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity. The operations of 1805 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed as described in reference to Figure 11 The UE capability component 1125 is used to perform the above operations.

[0250] At 1810, the method may include sending, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity. The operations of 1810 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed as described in reference to Figure 11 The network capability component 1130 is used to execute.

[0251] At 1815, the method may include sending a request for a machine learning model to a core network entity. The operations of 1815 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 1815 may be described by reference to Figure 11 The request component 1145 is executed.

[0252] At 1820, the method may include: receiving control signaling from a core network entity in response to the request indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The operations of 1820 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1820 may be performed as described in reference to Figure 11 The machine learning model is configured by component 1135 for execution.

[0253] At 1825, the method may include performing analysis based on the machine learning model. The operations of 1825 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 1825 may be performed as described in reference to Figure 11 The analysis component 1140 is used to perform the analysis.

[0254] Figure 19 A flowchart illustrating a method 1900 for supporting distributed 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 UE or a component thereof as described herein. For example, the operations of the method 1900 may be implemented by a UE or a component thereof as described herein. Figures 1 to 12 The UE 115 may be used to perform the described functions. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0255] At 1905, the method may include: sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity. The operations of 1905 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed as described in reference to Figure 11 The UE capability component 1125 is used to perform the above operations.

[0256] At 1910, the method may include sending, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity. The operations of 1910 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1910 may be performed as described in reference to Figure 11 The network capability component 1130 is used to execute.

[0257] At 1915, the method may include: receiving control signaling from a core network entity indicating configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The operations of 1915 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1915 may be performed as described in reference to Figure 11 The machine learning model is configured by component 1135 for execution.

[0258] At 1920, the method may include obtaining a machine learning model from a core network based on an address indicated via control signaling. The operations of 1920 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1920 may be performed as described in reference to Figure 11 The machine learning model is obtained by component 1155 for execution.

[0259] At 1925, the method may include performing analysis based on the machine learning model. The operations of 1925 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 1925 may be performed as described in reference to Figure 11 The analysis component 1140 is used to perform the analysis.

[0260] Figure 20 A flowchart illustrating a method 2000 for supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 2000 may be implemented by a network entity or component thereof as described herein. For example, the operations of the method 2000 may be implemented by a network entity or component thereof as described herein. Figures 1 to 8 as well as Figures 13 to 16 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 2005, 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 2005 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2005 may be performed as described in reference to Figure 15 The UE capability component 1525 is used to perform the above operations.

[0262] At 2010, the method may include outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. The operations of 2010 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2010 may be performed as described in reference to Figure 15 The network capability component 1530 is used to execute.

[0263] At 2015, the method may include: outputting control signaling indicating a configuration for a machine learning model, the first set of one or more machine learning models including the machine learning model. The operations of 2015 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 2015 may be performed by reference to Figure 15 The machine learning model is configured by component 1535 for execution.

[0264] Figure 21 A flowchart illustrating a method 2100 for supporting distributed machine learning model configuration according to one or more aspects of the present disclosure is shown. The operations of the method 2100 may be implemented by a network entity or component thereof as described herein. For example, the operations of the method 2100 may be implemented by a network entity or component thereof as described herein. Figures 1 to 8 as well as Figures 13 to 16In 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.

[0265] At 2105, 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 2105 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2105 may be performed as described in reference to Figure 15 The UE capability component 1525 is used to perform the above operations.

[0266] At 2110, the method may include outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both. The operations of 2110 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2110 may be performed as described in reference to Figure 15 The network capability component 1530 is used to execute.

[0267] At 2115, the method may include: obtaining a service request message requesting a machine learning model. The operations of 2115 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 2115 may be performed as described in reference to Figure 15 The request receiving component 1540 is executed.

[0268] At 2120, the method may include: responding to the service request message and outputting control signaling indicating configuration for a machine learning model via a service response message, the first set of one or more machine learning models including the machine learning model. The operations of 2120 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 2120 may be performed as described in reference to Figure 15 The machine learning model is configured by component 1535 for execution.

[0269] The following provides an overview of various aspects of the disclosure:

[0270] 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 core network entity; receiving an indication of a second set of one or more machine learning models supported at the core network entity from the core network entity; receiving control signaling from the core network entity indicating a configuration for a machine learning model, 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.

[0271] Aspect 2: According to the method according to Aspect 1, the method also includes: sending a request for the machine learning model to the core network entity; and wherein receiving the control signaling includes: receiving the control signaling in response to sending the request.

[0272] 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.

[0273] Aspect 4: A method according to any one of Aspects 2 to 3, wherein sending the request includes: sending a protocol data unit session modification request message; and wherein receiving the control signaling includes: receiving the control signaling via a protocol data unit session modification command message.

[0274] Aspect 5: A method according to any one of aspects 2 to 4, wherein the request includes an identifier of the machine learning model.

[0275] Aspect 6: According to the method of any one of Aspects 1 to 5, the method also includes: sending a completion message to the core network entity based at least in part on the control signaling indicating the configuration for the machine learning model.

[0276] Aspect 7: A method according to any one of Aspects 1 to 6, 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.

[0277] Aspect 8: The method according to any one of Aspects 1 to 7, wherein receiving the control signaling includes: receiving a UE configuration update command indicating the configuration for the machine learning model.

[0278] Aspect 9: A method according to any one of Aspects 1 to 8, wherein sending the indication of the first group of one or more machine learning models includes: sending a registration request indicating the first group of one or more machine learning models supported at the UE; and wherein receiving the indication of the second group of one or more machine learning models includes: receiving the indication of the second group of one or more machine learning models via a registration response message.

[0279] Aspect 10: The method according to any one of aspects 1 to 9, wherein receiving the control signaling includes: receiving a protocol data unit session modification command indicating the configuration for the machine learning model.

[0280] Aspect 11: The method according to Aspect 10 further includes: sending a protocol data unit session modification completion message to the core network entity based at least in part on the protocol data unit session modification command indicating the configuration for the machine learning model.

[0281] Aspect 12: A method according to any one of Aspects 1 to 11, wherein sending the indication of the first group of one or more machine learning models includes: sending a session establishment message or a modification request message indicating the first group of one or more machine learning models supported at the UE; and wherein receiving the indication of the second group of one or more machine learning models includes: receiving the indication of the second group of one or more machine learning models via a session establishment response message or a modification response message.

[0282] Aspect 13: A method according to any one of Aspects 1 to 12, 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.

[0283] Aspect 14: The method according to any one of Aspects 1 to 13, further comprising: obtaining the machine learning model from a core network based at least in part on the address indicated via the control signaling.

[0284] Aspect 15: The method according to any one of aspects 1 to 14, wherein the core network entity is an access and mobility management function (AMF) entity or a session management function (SMF) entity.

[0285] Aspect 16: A method for wireless communication at a first core network entity, the method comprising: obtaining an indication of a first set of one or more machine learning models supported at a UE; outputting an indication of a second set of one or more machine learning models supported at the first core network entity or a second core network entity or both; and outputting control signaling indicating a configuration for a machine learning model, wherein the first set of one or more machine learning models includes the machine learning model.

[0286] Aspect 17: The method according to Aspect 16 further includes: obtaining a service request message requesting the machine learning model; and wherein outputting the control signaling includes: outputting the control signaling via a service response message in response to the service request message.

[0287] Aspect 18: According to the method described in any one of Aspects 16 to 17, the method further includes: obtaining a protocol data unit session modification request message requesting the machine learning model; and wherein outputting the control signaling includes: outputting the control signaling via a protocol data unit session modification command message in response to the protocol data unit session modification request message.

[0288] Aspect 19: According to the method described in any one of Aspects 16 to 18, the method further includes: obtaining a UE configuration update completion message in response to the control signaling indicating the configuration for the machine learning model; and wherein outputting the control signaling includes: outputting the control signaling via a UE configuration update command.

[0289] Aspect 20: According to any one of Aspects 16 to 19, the method further includes: obtaining a protocol data unit session modification completion message in response to the control signaling indicating the configuration for the machine learning model; and wherein outputting the control signaling includes: outputting the control signaling via a protocol data unit session modification command message.

[0290] Aspect 21: According to any one of Aspects 16 to 20, the method further includes: obtaining a request from another core network entity for the UE to perform analysis at least partially based on the machine learning model; and wherein outputting the control signaling includes: outputting the control signaling in response to the request.

[0291] Aspect 22: A method according to any one of Aspects 16 to 21, wherein outputting the control signaling includes: outputting 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 analysis according to the machine learning model, an activation event for reporting the analysis, one or more parameters for performing the analysis, or any combination thereof.

[0292] Aspect 23: A method according to any one of Aspects 16 to 22, wherein outputting the indication of the first group of one or more machine learning models includes: outputting a registration request indicating that the first group of one or more machine learning models are supported at the UE; and wherein outputting the indication of the second group of one or more machine learning models includes: outputting the indication of the second group of one or more machine learning models via a registration response message.

[0293] Aspect 24: A method according to any one of Aspects 16 to 23, wherein obtaining the indication of the first group of one or more machine learning models includes: obtaining a session establishment message or a modification request message indicating that the first group of one or more machine learning models are supported at the UE; and wherein outputting the indication of the second group of one or more machine learning models includes: outputting the indication of the second group of one or more machine learning models via a session establishment response message or a modification response message.

[0294] Aspect 25: The method according to any one of aspects 16 to 24, wherein the first core network entity is an Access and Mobility Management Function (AMF) entity.

[0295] Aspect 26: According to the method according to Aspect 25, the method also includes: outputting the indication of the first group of one or more machine learning models supported at the UE to a session management function (SMF) entity, wherein the second core network entity is the SMF entity; obtaining the indication of the second group of one or more machine learning models supported at the SMF entity from the SMF entity; and obtaining the control signaling indicating the configuration for the machine learning model from the SMF entity.

[0296] Aspect 27: The method according to any one of aspects 16 to 26, wherein the first core network entity is a session management function (SMF) entity.

[0297] Aspect 28: According to the method according to Aspect 27, the method also includes: obtaining the indication of the first group of one or more machine learning models supported at the UE from an access and mobility management function (AMF) entity, wherein the second core network entity is the AMF entity; outputting the indication of the second group of one or more machine learning models supported at the SMF entity to the AMF entity; and outputting the control signaling indicating the configuration for the machine learning model to the AMF entity.

[0298] Aspect 29: An apparatus for wireless communication at a UE, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to perform the method according to any one of aspects 1 to 15.

[0299] Aspect 30: An apparatus for wireless communication at a UE, the apparatus comprising: at least one component for performing the method according to any one of aspects 1 to 15.

[0300] Aspect 31: 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 15.

[0301] Aspect 32: An apparatus for wireless communication at a first core network entity, the apparatus comprising: a processor; and a memory coupled to the processor, the processor configured to perform the method according to any one of aspects 16 to 28.

[0302] Aspect 33: An apparatus for wireless communication at a first core network entity, the apparatus comprising: at least one component for performing the method according to any one of aspects 16 to 28.

[0303] Aspect 34: A non-transitory computer-readable medium storing code for wireless communication at a first core network entity, the code comprising instructions executable by a processor to perform the method according to any one of aspects 16 to 28.

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

[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 referred to throughout the specification may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or 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, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in combination with a DSP core, or any other such configuration).

[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 transmitted via a computer-readable medium. Other examples and 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, hardwiring, or a combination of any of these. 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 that computer program is transferred from one place to another.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, magnetic disk storage device or other magnetic storage device or can be used for carrying or storing desired program code components and any other non-transient medium that can be accessed by general or special-purpose computer or general or special-purpose processor in the form of instruction or data structure.Moreover, any connection is suitably 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 CDs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs 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). Furthermore, 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" could be based on both condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "based at least in part on."

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

[0312] In the accompanying 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 applies to any of the similar components having the same first reference number, regardless of the second or subsequent reference numbers.

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

[0314] The description herein is provided to enable one of ordinary skill in the art to make or use the present disclosure. Various modifications to the present disclosure will be apparent to those 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 accorded 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 an indication of a first set of one or more machine learning models supported at the UE to a core network entity; receiving, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity; receiving control signaling from the core network entity indicative of configuration for a machine learning model, 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 core network entity; and wherein, In order to receive the control signaling, the processor is further configured to: The control signaling is received in response to sending 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 further configured to: The control signaling is received via a service response message.

4. The device according to claim 2, wherein To send the request, the processor is configured to: sending a protocol data unit session modification request message; and wherein, in order to receive the control signaling, the processor is further configured to: The control signaling is received via a protocol data unit session modification command message.

5. The apparatus of claim 2, wherein the request comprises an identifier of the machine learning model.

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

7. 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.

8. The device according to claim 1, wherein In order to receive the control signaling, the processor is configured to: Receiving a UE configuration update command indicating the configuration for the machine learning model.

9. The device according to claim 1, wherein To transmit, the processor is configured to: sending a registration request indicating the first set of one or more machine learning models supported at the UE; and wherein, to receive the indication of the second set of one or more machine learning models, the processor is configured to: Receive a registration response message indicating the second set of one or more machine learning models.

10. The device according to claim 1, wherein In order to receive the control signaling, the processor is configured to: A protocol data unit session modification command is received indicating the configuration for the machine learning model.

11. The apparatus of claim 10, wherein the processor is further configured to: Sending a protocol data unit session modification complete message to the core network entity based at least in part on the protocol data unit session modification command indicating the configuration for the machine learning model.

12. The apparatus of claim 1 , wherein the processor is further configured to: sending a session establishment message or a modification request message indicating the first set of one or more machine learning models supported at the UE; and wherein, To receive the indication of the second set of one or more machine learning models, the processor is configured to: The indication of the second set of one or more machine learning models is received via a session establishment response message or a modification response message.

13. 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.

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

15. The apparatus of claim 1, wherein the core network entity is an Access and Mobility Management Function (AMF) entity or a Session Management Function (SMF) entity.

16. An apparatus for wireless communication at a first core network entity, 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); outputting an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both; as well as Output control signaling indicating configuration of a machine learning model at the UE, wherein the first set of one or more machine learning models includes the machine learning model.

17. The apparatus of claim 16, wherein the processor is further configured to: Obtaining a service request message requesting the machine learning model; and wherein, In order to output the control signaling, the processor is configured to: The control signaling is output via a service response message in response to the service request message.

18. The apparatus of claim 16, wherein the processor is further configured to: obtaining a protocol data unit session modification request message requesting the machine learning model; and wherein, In order to output the control signaling, the processor is configured to: The control signaling is output via a protocol data unit session modification command message in response to the protocol data unit session modification request message.

19. The apparatus of claim 16, wherein the processor is further configured to: obtaining a UE configuration update complete message in response to the control signaling indicating the configuration for the machine learning model; and wherein, In order to output the control signaling, the processor is further configured to: The control signaling is output via a UE configuration update command.

20. The apparatus of claim 16, wherein the processor is further configured to: obtaining a protocol data unit session modification complete message in response to the control signaling indicating the configuration for the machine learning model; and wherein, In order to output the control signaling, the processor is configured to: The control signaling is output via a protocol data unit session modification command message.

21. The apparatus of claim 16, wherein the processor is further configured to: obtaining, from another core network entity, a request for the UE to perform analysis based at least in part on the machine learning model; and wherein, In order to output the control signaling, the processor is configured to: The control signaling is output in response to the request.

22. The apparatus according to claim 16, wherein In order to output the control signaling, the processor is configured to: The output indicates the control signaling for the configuration of the machine learning model at the UE, 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 according to the machine learning model, an activation event for reporting the analysis, one or more parameters for performing the analysis, or any combination thereof.

23. The apparatus according to claim 16, wherein In order to obtain the indication, the processor is configured to: obtaining a registration request indicating the first set of one or more machine learning models supported at the UE, wherein to output the indication of the second set of one or more machine learning models, the processor is configured to: The indication of the second set of one or more machine learning models is output via a registration response message.

24. The apparatus according to claim 16, wherein In order to obtain the indication, the processor is configured to: obtaining a session establishment message or a modification request message indicating the first set of one or more machine learning models supported at the UE; and wherein, to output the indication of the second set of one or more machine learning models, the processor is configured to: The indication of the second set of one or more machine learning models is output via a session establishment response message or a modification response message.

25. The apparatus of claim 16, wherein the first core network entity is an Access and Mobility Management Function (AMF) entity.

26. The apparatus of claim 25, wherein the processor is further configured to: outputting the indication of the first set of one or more machine learning models supported at the UE to a session management function (SMF) entity, wherein the second core network entity is the SMF entity; obtaining, from said SMF entity, said indication of said second set of one or more machine learning models supported at said SMF entity; as well as Obtaining the control signaling from the SMF entity indicating the configuration for the machine learning model.

27. The apparatus of claim 16, wherein the first core network entity is a session management function (SMF) entity.

28. The apparatus of claim 27, wherein the processor is further configured to: obtaining, from an Access and Mobility Management Function (AMF) entity, the indication of the first set of one or more machine learning models supported at the UE, wherein the second core network entity is the AMF entity; outputting to said AMF entity said indication of said second set of one or more machine learning models supported at said SMF entity; as well as outputting the control signaling indicating the configuration of the machine learning model at the UE to the AMF entity.

29. A method for wireless communication at a user equipment (UE), the method comprising: sending an indication of a first set of one or more machine learning models supported at the UE to a core network entity; receiving, from the core network entity, an indication of a second set of one or more machine learning models supported at the core network entity; receiving control signaling from the core network entity indicative of configuration for a machine learning model, 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.

30. A method for wireless communication at a first core network entity, the method comprising: receiving, from a user equipment (UE), an indication of a first set of one or more machine learning models supported at the UE; sending, to the UE, an indication of a second set of one or more machine learning models supported at the first core network entity or the second core network entity, or both; as well as Send control signaling to the UE indicating a configuration for a machine learning model, wherein the first group of one or more machine learning models includes the machine learning model.

Images