Cross-node artificial intelligence (AI) / machine learning (ML) service

Abstract

Methods, systems, and devices for wireless communication are described. A network entity may obtain a first message indicating one or more artificial intelligence (AI) / machine learning (ML) capabilities of a user equipment (UE), and may also obtain a second message from an AI / ML service indicating one or more AI / ML service capabilities of the AI / ML service. The network entity may output a control message indicating one or more cross-node AI / ML configurations based on the one or more AI / ML capabilities of the UE and the one or more AI / ML service capabilities of the AI / ML service. The one or more cross-node AI / ML configurations may configure the AI / ML functionality of the UE for use with the AI / ML service. In some examples, a lifecycle management (LCM) process may be triggered by the UE, and the UE may send signaling associated with the LCM process (e.g., a request for LCM signaling or an indication of the LCM).

Description

[0001] Cross-references

[0002] This patent application claims the benefit of U.S. Patent Application No. 18 / 473,167, filed September 22, 2023, entitled “CROSS-NODEARTIFICIAL INTELLIGENCE (AI) / MACHINE LEARNING (ML) SERVICES”, which has been assigned to the assignee of this application and is expressly incorporated herein by reference. Technical Field

[0003] The following text relates to wireless communication, including cross-node artificial intelligence / machine learning services. Background Technology

[0004] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, message sending and receiving, broadcasting, and so on. These systems can 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, LTE-A Advanced (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 technologies such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), or Discrete Fourier Transform Extended Orthogonal Frequency Division Multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations, each supporting wireless communication of communication devices, which may be referred to as User Equipment (UE).

[0005] Some wireless communication systems can support artificial intelligence (AI) / machine learning (ML) functions or models at devices communicating within the wireless communication system, such as UEs, network entities (e.g., radio access networks (RANs)), and AI / ML services. For example, various devices may support one or more AI / ML models for optimizing communications within the wireless communication system (e.g., efficient network power saving, beam management, load balancing, and mobility optimization). Summary of the Invention

[0006] The described technologies relate to improved methods, systems, devices, and apparatuses supporting cross-node artificial intelligence (AI) / machine learning (ML) services. User equipment (UE) can communicate UE ML capabilities (e.g., AI / ML capabilities) to a radio access network (RAN), and ML services (e.g., AI / ML services) can also provide ML service ML capabilities to the RAN. The RAN can facilitate cross-node configuration, cross-node ML inference, and / or performance monitoring based on the UE ML capabilities and ML service ML capabilities. By relaying information between the UE and the ML service, the UE can communicate indirectly with the ML service, enabling the UE to be updated using an ML model that facilitates the UE performing functions as expected (e.g., above a performance threshold) and is compatible with the ML service. Additionally or alternatively, the UE can request signaling associated with lifecycle management (LCM) procedures for maintaining wireless communication links with network entities. In some examples, the UE can perform LCM procedures and send instructions for the LCM procedures to the AI / ML service (e.g., via a network entity). In other examples, the UE may send a request to perform an LCM procedure for the ML service (e.g., via a network entity), where in some cases the UE may include a monitoring report with the request.

[0007] A method for wireless communication by a network entity is described. The method may include: obtaining a first message indicating one or more machine learning capabilities of a UE; obtaining a second message indicating one or more ML service capabilities of the ML service from an ML service; and outputting a control message to the UE indicating one or more cross-node machine learning configurations based on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the ML service.

[0008] A network entity for wireless communication is described. The network entity may include one or more memories storing processor-executable code and one or more processors coupled to the one or more memories. The one or more processors may operate individually or collectively to execute the code so that the network entity: receives a first message indicating one or more machine learning capabilities of a UE; receives a second message from an ML service indicating one or more ML service capabilities of the ML service; and outputs a control message to the UE indicating one or more cross-node machine learning configurations based on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the ML service.

[0009] Another network entity for wireless communication is described. This network entity may include: components for obtaining a first message indicating one or more machine learning capabilities of a UE; components for obtaining a second message from an ML service indicating one or more ML service capabilities of that ML service; and components for outputting control messages to the UE indicating one or more cross-node machine learning configurations based on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the ML service.

[0010] A non-transitory computer-readable medium storing code for wireless communication is described. The code may include instructions executable by a processor to perform the following actions: obtaining a first message indicating one or more machine learning capabilities of a UE; obtaining a second message indicating one or more ML service capabilities of an ML service from an ML service; and outputting control messages to the UE indicating one or more cross-node machine learning configurations based on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the ML service.

[0011] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, a service capability request message for one or more ML service capabilities is output to an ML service, wherein a second message indicating one or more ML service capabilities may be obtained in response to the service capability request message, and wherein the one or more ML service capabilities include capabilities that are compatible with the UE based on one or more machine learning capabilities of the UE.

[0012] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, a service capability request message may contain a set of UE identifiers, including the UE's identifier, an indication of one or more machine learning capabilities of the UE, or any combination thereof.

[0013] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, obtaining a second message indicating one or more ML service capabilities may include operations, features, components, or instructions for obtaining notification of one or more ML service capabilities from an ML service, the notification including the second message.

[0014] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: selecting one or more machine learning functions based on one or more machine learning capabilities of the UE and one or more ML service capabilities of the ML service; outputting a configuration request message to the ML service requesting one or more cross-node machine learning configurations based on the selection; and obtaining from the ML service a configuration response message indicating one or more cross-node machine learning configurations, one or more machine learning functions, a set of UE identifiers including the UE's identifier, or any combination thereof, wherein the control message indicating one or more cross-node machine learning configurations may be based on obtaining the configuration response message.

[0015] The methods, network entities, and some examples of non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining a third message indicating that the UE shall complete one or more cross-node machine learning configurations in response to a control message.

[0016] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, a fourth message is output to the ML service indicating that one or more cross-node machine learning configurations may have been configured by the UE.

[0017] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for outputting a second control message that includes instructions for activating one or more machine learning functions based on one or more cross-node machine learning configurations.

[0018] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, an activation request message is output to an ML service, the activation request message indicating a set of UE identifiers including the identifier of the UE, one or more machine learning functions, or any combination thereof; and in response to the activation request message, an activation confirmation message is obtained from the ML service, the activation confirmation message indicating a set of UE identifiers including the identifier of the UE, one or more machine learning functions, or any combination thereof, wherein a second control message may be output based on the activation confirmation message.

[0019] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining an activation request message from an ML service, the activation request message indicating a set of UE identifiers including an identifier of the UE, one or more machine learning functions, or any combination thereof; and outputting an activation confirmation message from the ML service to the ML service in response to the activation request message, the activation confirmation message indicating a set of UE identifiers including an identifier of the UE, one or more machine learning functions, or any combination thereof, wherein a second control message may be output based on the activation confirmation message.

[0020] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining a first activation request message from a UE indicating one or more machine learning functions; outputting a second activation request message to an ML service in response to the first activation request message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof; and obtaining an activation confirmation message from an ML service in response to the second activation request message, the activation confirmation message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof, wherein a second control message may be output based on the activation confirmation message.

[0021] Some examples of the methods, network entities, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining a sixth message including UE inferred input data associated with one or more machine learning functions; outputting a service data request message including the UE inferred input data to the ML service; and obtaining a service data response message from the ML service indicating ML service inferred output data associated with one or more machine learning functions.

[0022] In some examples of the methods, network entities, and non-transitory computer-readable media described herein, a seventh message is output to the UE, including ML service inference output data from the ML service.

[0023] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: monitoring one or more triggering conditions based on UE-inferred input data, ML service-inferred input data from ML services, or any combination thereof; and outputting a third control message to the UE based on the occurrence of the one or more triggering conditions, the third control message including an indication to switch or disable at least one of one or more machine learning functions.

[0024] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, the one or more triggering conditions include the measurement of one or more key performance indicators that satisfy a key performance indicator threshold.

[0025] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, monitoring reports are output to ML services that indicate one or more key performance indicators associated with one or more machine learning functions.

[0026] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, the one or more triggering conditions may be based on monitoring reports including measurements performed by the UE, by the network entity, or any combination thereof.

[0027] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining a monitoring report from the UE, which includes one or more key performance indicators associated with one or more machine learning functions; and outputting instructions to the UE to switch or disable one or more machine learning functions of the UE based on the occurrence of one or more triggering conditions.

[0028] In some examples of the methods, network entities, and nontransitory computer-readable media described herein, monitoring reports are output to ML services that indicate one or more key performance indicators associated with one or more machine learning functions.

[0029] Some examples of the methods, network entities, and nontransitory computer-readable media described herein may also include operations, features, components, or instructions for: obtaining from the UE an LCM control request message including a request for lifecycle management control signaling, the lifecycle management control signaling including indications for activating, deactivating, switching the default configuration in one or more cross-node machine learning configurations, or any combination thereof; outputting a first LCM control message to the ML service in response to the LCM control request message, including an indication for the request for lifecycle management control signaling; and outputting a second LCM control message to the UE including an indication of the lifecycle management control signaling indicated by the ML service.

[0030] The methods, network entities, and some examples of non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining LCM control request messages based on monitoring reports from the UE, network entities, or a combination thereof.

[0031] A method for wireless communication by a UE is described. The method may include: receiving a first message indicating one or more lifecycle management triggering conditions for a channel between the UE and a network entity; sending an LCM control request message to the network entity in response to the occurrence of the one or more lifecycle management triggering conditions, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE; and receiving a second message from the network entity in response to the LCM control request message indicating the lifecycle management control signaling.

[0032] A UE for wireless communication is described. The UE may include one or more memories storing processor-executable code and one or more processors coupled to the one or more memories. The one or more processors may operate individually or collectively to execute code such that the UE: receives a first message indicating one or more lifecycle management trigger conditions for a channel between the UE and a network entity; in response to the occurrence of the one or more lifecycle management trigger conditions, sends an LCM control request message to the network entity including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE; and in response to the LCM control request message, receives a second message from the network entity indicating the lifecycle management control signaling.

[0033] Another UE for wireless communication is described. The UE may include: components for receiving a first message indicating one or more lifecycle management triggering conditions for a channel between the UE and a network entity; components for sending an LCM control request message to the network entity in response to the occurrence of one or more lifecycle management triggering conditions, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE; and components for receiving a second message indicating lifecycle management control signaling from the network entity in response to the LCM control request message.

[0034] A non-transitory computer-readable medium storing code for wireless communication is described. The code may include instructions executable by a processor to perform the following actions: receiving a first message indicating one or more lifecycle management trigger conditions for a channel between a UE and a network entity; sending an LCM control request message to the network entity in response to the occurrence of one or more lifecycle management trigger conditions, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE; and receiving a second message from the network entity in response to the LCM control request message indicating lifecycle management control signaling.

[0035] The methods described herein, UEs, and some examples of non-transitory computer-readable media may also include operations, features, components, or instructions for sending monitoring reports to network entities that indicate one or more key performance indicators associated with the UE, wherein receiving a second message indicating lifecycle management control signaling may be based on the monitoring reports.

[0036] In some examples of the methods, UEs, and nontransitory computer-readable media described herein, one or more lifecycle management triggering conditions include one or more thresholds associated with the inferred performance of the UE, one or more key performance indicators associated with the UE, or a combination thereof. Attached Figure Description

[0037] Figure 1 An example of a wireless communication system supporting cross-node artificial intelligence (AI) / machine learning (ML) services is shown, according to one or more aspects of this disclosure.

[0038] Figure 2 An example of a network architecture supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0039] Figure 3 An example of a wireless communication system supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0040] Figures 4 to 10 An example of a process flow supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0041] Figure 11 and Figure 12 A block diagram of a device supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0042] Figure 13A block diagram of a communication manager supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0043] Figure 14 A diagram of a system including a device supporting cross-node AI / ML services, according to one or more aspects of this disclosure, is shown.

[0044] Figure 15 and Figure 16 A block diagram of a device supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0045] Figure 17 A block diagram of a communication manager supporting cross-node AI / ML services is shown, according to one or more aspects of this disclosure.

[0046] Figure 18 A diagram of a system including a device supporting cross-node AI / ML services, according to one or more aspects of this disclosure, is shown.

[0047] Figures 19 to 22 A flowchart illustrating a method for supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Detailed Implementation

[0048] The various aspects involve wireless communication as a whole, and more specifically, cross-node artificial intelligence (AI) / machine learning (ML) services. Some aspects are more specifically related to wireless communication systems that support AI / ML operations or models at devices (such as user equipment (UE), network entities (e.g., radio access network (RAN)), and AI / ML services (which may be referred to as machine learning services)) communicating within a wireless communication system. For example, a UE may support one or more AI / ML models (e.g., channel state information (CSI) calculation, beam management, load balancing, and location / mobility optimization) used to optimize communication with network entities in a wireless communication system. In some cases, the UE may be unaware of how the AI / ML service is deployed within a specific architecture (e.g., together with the RAN, separately from the RAN), and therefore the UE may communicate with the RAN. For example, AI / ML functionality may be implemented by both the RAN and the UE, where the RAN (e.g., a network entity) may send AI / ML control signaling or input signaling or both to the UE, and the UE may send AI / ML input data to the network entity. In other examples, one or more AI / ML services that implement and provide one or more AI / ML models for use at the UE can be deployed separately from the RAN, and the RAN (e.g., a network entity) can facilitate signaling between the UE and the AI / ML services. In any case, the deployment of AI / ML functionality across multiple devices and / or entities can be referred to as cross-node inference, where AI / ML-related inference is performed by the UE as well as the AI / ML services and / or the RAN.

[0049] The UE can communicate its ML capabilities (e.g., AI / ML capabilities) to the RAN, and the AI / ML service can also provide the RAN with AI / ML service ML capabilities (e.g., AI / ML service capabilities). The RAN can facilitate cross-node configuration, cross-node AI / ML inference, and / or performance monitoring based on the UE's AI / ML capabilities and AI / ML service capabilities. By relaying information between the UE and the AI / ML service, the UE can communicate indirectly with the AI / ML service, enabling the UE to be updated using an AI / ML model that facilitates the UE's expected (e.g., above performance thresholds) functional performance and compatibility with the AI / ML service.

[0050] To exchange AI / ML capabilities with the AI / ML service, the RAN can request AI / ML service capabilities from the AI / ML service before or after receiving UE AI / ML capabilities from the UE, and the AI / ML service can provide AI / ML service capabilities to the RAN based on this request. In some examples, the AI / ML service can advertise its AI / ML service capabilities to other nodes, including the RAN, without request. For cross-node ML configuration, the RAN can determine whether the UE can be configured for cross-node AI / ML services based on capability information from the UE and the AI / ML service, and the RAN can request and obtain configuration from the AI / ML service to provide to the UE. For cross-node ML inference, the UE can transmit AI / ML service input data to the RAN for forwarding to the AI / ML service, and the AI / ML service can provide AI / ML service data responses or output data (e.g., input / output data streams between the UE and the AI / ML service via the RAN). For performance monitoring, the UE, RAN, and / or AI / ML service can monitor performance (e.g., by monitoring relevant key performance indicators and associated thresholds). In some examples, the UE and / or RAN can send monitoring reports to the AI / ML service. The monitored conditions can enable, disable, or switch (e.g., to a new or default configuration) one or more AI / ML configurations for the UE, RAN, and / or AI / ML services. For example, the RAN, together with the AI / ML services, can control the activation or deactivation of one or more AI / ML configurations for the UE.

[0051] Specific aspects of the subject matter described in this disclosure can be implemented to achieve one or more of the following potential advantages. By relaying information between the UE and the AI / ML service, the UE can communicate indirectly with the AI / ML service, enabling the UE to be updated using an ML model that facilitates the UE's expected (e.g., above a performance threshold) performance and compatibility with the AI / ML service. Additionally, in some cases, the RAN can be updated with new or additional configurations to facilitate the RAN or UE's expected performance and compatibility with new AI / ML services. For example, the RAN can be updated to determine the appropriate timing and configuration associated with the new or additional AI / ML service. For example, a dynamic implementation of the AI / ML model based on one or more system conditions can ensure that the wireless communication system performance or the AI / ML model performance operates as expected (e.g., above a threshold). Using an appropriate AI / ML model based on changing wireless system conditions can reduce latency that would otherwise be associated with the wireless communication system not operating as expected or becoming incompatible with the AI / ML service.

[0052] The aspects of this disclosure are first described in the context of a wireless communication system. These aspects are further illustrated and described with reference to apparatus diagrams, system diagrams, and flowcharts relating to cross-node AI / ML services. It should also be understood that the techniques described herein can be applied to other devices or services used to process functions or operations offloaded from the RAN. For example, the UE and associated services can provide offload processing. The UE and associated services can also be updated, while the RAN can continue with its current configuration or software (e.g., with minimal or no software or configuration updates). Therefore, although AI / ML services are described herein as examples, other devices and services (e.g., not performed or supported at the RAN) can also utilize the same or similar techniques described herein, and some aspects related to AI / ML services described herein should not be considered as limiting the scope of the claims or this disclosure.

[0053] Figure 1 An example of a wireless communication system 100 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. The wireless communication system 100 may include one or more network entities 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be 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 under other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.

[0054] Network entity 105 may be distributed across a geographical area to form wireless communication system 100, and may include devices employing different forms or having different capabilities. In various examples, network entity 105 may be referred to as a network element, mobility element, radio access network (RAN) node, or network equipment, etc. In some examples, network entity 105 and UE 115 may wirelessly communicate via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, network entity 105 may support coverage area 110 (e.g., a geographical coverage area) within which UE 115 and network entity 105 may establish one or more communication links 125. Coverage area 110 may be an example of a geographical area within which network entity 105 and UE 115 may support the transmission of signals according to one or more radio access technologies (RATs).

[0055] UE 115 can be distributed throughout the coverage area 110 of wireless communication system 100, and each UE 115 can be stationary or mobile, or stationary and mobile at different times. UE 115 can be devices in different forms or with different capabilities. Figure 1 Some example UE 115s are illustrated herein. The UE 115 described herein can be able to support various types of devices (such as, e.g., ...). Figure 1 The UE 115 communicates with other UEs 115 or network entities 105 shown herein. In some examples, the UE 115 may support AI and / or ML functionality, which the UE 115 may use to perform wireless communication procedures (e.g., CSI prediction, beam selection, or beam prediction, etc.). For example, the UE 115 may generate inference data associated with one or more AI / ML functions. Additionally or alternatively, the UE 115 may perform lifecycle management (LCM) operations (e.g., model or functionality selection, activation, deactivation, switching, and rollback, etc.) for a given AI / ML model and / or functionality. As described herein, an AI functionality or AI model may be referred to as an ML functionality or ML model, and vice versa. That is, in some examples, the terms “AI” and “ML” are used interchangeably to refer to similar technologies, models, functions, or any combination thereof. In some examples, ML operations may be considered a subset of AI operations. In any event, aspects of the features described herein may be referred to as ML functionality, ML function, ML model, ML service, ML operation, etc., but these aspects may similarly apply to AI functionality, AI function, AI model, AI service, AI operation, or any combination thereof. Therefore, reference to “ML” herein may refer to ML, AI, or both, and the term “ML” should not be considered as a limitation on the scope of the claims or this disclosure.

[0056] As described herein, nodes of the wireless communication system 100 (which may be referred to as network nodes or wireless nodes) may be network entity 105 (e.g., any network entity described herein), UE 115 (e.g., any UE described herein), network controller, apparatus, device, computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, a node may be UE 115. Alternatively, a node may be network entity 105. Furthermore, a first node may be configured to communicate with a second or third node. In one aspect of this example, the first node may be UE 115, the second node may be network entity 105, and the third node may be UE 115. In another aspect of this example, the first node may be UE 115, the second node may be network entity 105, and the third node may be network entity 105. In other aspects of this example, the first node, the second node, and the third node may be different from these examples. Similarly, references to UE 115, network entity 105, device, equipment, computing system, etc., may include disclosures of UE 115, network entity 105, device, equipment, computing system, etc., as nodes. For example, a disclosure that UE 115 is configured to receive information from network entity 105 also discloses that a first node is configured to receive information from a second node.

[0057] In some examples, network entity 105 may communicate with core network 130, communicate with each other, or both. For example, network entity 105 may communicate with core network 130 via one or more backhaul communication links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some examples, network entities 105 may communicate with each other directly (e.g., directly between network entities 105) or indirectly (e.g., via core network 130) via backhaul communication links 120 (e.g., according to X2, Xn, or other interface protocols). In some examples, network entities 105 may communicate with each other via midhaul communication link 162 (e.g., according to midhaul interface protocol) or fronthaul communication link 168 (e.g., according to fronthaul interface protocol) or any combination thereof. The backhaul communication link 120, midhaul communication link 162, or fronthaul communication link 168 may be 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, or may 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 the core network 130 via communication link 155.

[0058] One or more network entities in network entity 105 described herein may include or be referred to as base station 140 (e.g., transceiver base station, radio base station, NR base station, access point, radio transceiver, node B, eNodeB (eNB), next-generation node B or gigabit node B (any of which may be referred to as gNB), 5G NB, next-generation eNB (ng-eNB), home node B, home evolution node B, or other suitable terms). In some examples, network entity 105 (e.g., base station 140) may be implemented in an aggregated (e.g., monolithic, 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 base station 140).

[0059] In some examples, network entity 105 may be implemented in a decomposed architecture (e.g., a decomposed base station architecture, a decomposed RAN architecture) that can be configured to utilize protocol stacks physically or logically distributed across 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, network entity 105 may include one or more of the following: a Central Unit (CU) 160, a Distributed Unit (DU) 165, a Radio Unit (RU) 170, a RAN Intelligent Controller (RIC) 175 (e.g., a near-real-time RIC, a non-real-time RIC), a Service Management and Orchestration (SMO) 180 system, or any combination thereof. 170 may also be referred to as a radio headend, intelligent radio headend, remote radio headend (RRH), remote radio unit (RRU), or transmit / receive point (TRP). One or more components of network entity 105 in a decomposed RAN architecture may be co-located, or one or more components of network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 in a decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0060] The functional splitting among CU 160, DU 165, and RU 170 is flexible and can support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, and any combination thereof) are performed at CU 160, DU 165, or RU 170. For example, a protocol stack functional splitting can be used between CU 160 and DU 165, allowing CU 160 to support one or more layers of the protocol stack, and DU 165 to support one or more different layers of the protocol stack. In some examples, CU 160 can host higher protocol layer (e.g., Layer 3 (L3), Layer 2 (L2)) functionalities and signaling (e.g., Radio Resource Control (RRC), Serving Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP)). CU 160 can connect to one or more DU 165 or RU 170, and one or more DU 165 or RU 170 can 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 each can be at least partially controlled by CU 160. Additionally or alternatively, a protocol stack functional split can be employed between DU 165 and RU 170, such that DU 165 can support one or more layers of the protocol stack, and RU 170 can support one or more different layers of the protocol stack. DU 165 can support one or more different cells (e.g., via one or more RU 170). In some cases, functional decomposition between CU 160 and DU 165, or between DU 165 and RU 170, can be performed within the protocol layer (e.g., some functions of the protocol layer can be performed by one of CU 160, DU 165, or RU 170, while other functions of the protocol layer can be performed by different of CU 160, DU 165, or RU 170). CU 160 can be further functionally decomposed into CU control plane (CU-CP) functions and CU user plane (CU-UP) functions. CU 160 can be connected to one or more DU 165 via midhaul communication link 162 (e.g., F1, F1-c, F1-u), and DU 165 can be connected to one or more RU 170 via fronthaul communication link 168 (e.g., open fronthaul (FH) interface). In some examples, the midhaul communication link 162 or the fronthaul communication link 168 may be implemented based on the interfaces (e.g., channels) between the layers of the protocol stack, which are supported by the corresponding network entities 105 communicating via such communication links.

[0061] 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 core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB node 104) may be partially controlled by each other. One or more IAB nodes 104 may be referred to as donor entities or IAB donors. One or more DU 165s or one or more RU 170s may be partially controlled by one or more CU 160s associated with donor network entity 105 (e.g., donor base station 140). One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB node 104) via supported access and backhaul links (e.g., backhaul communication link 120). IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a DU 165 of a coupled IAB donor. The IAB-MT may include a separate set of antennas for relaying communication with UE 115, or may share the same antennas (e.g., those of RU 170) for access to IAB node 104 via DU 165 of IAB node 104. (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, IAB node 104 may include a DU 165 that supports communication links with additional entities (e.g., IAB node 104, UE 115) within a relay chain or configuration (e.g., downstream) of the access network. In such cases, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of IAB node 104) may be configured to operate according to the techniques described herein.

[0062] For example, the access network (AN) or RAN may include communication between an access node (e.g., an IAB donor), IAB node 104, and one or more UEs 115. The IAB donor may facilitate connectivity between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, an IAB donor may refer to a RAN node having a wired or wireless connection to the core network 130. The IAB donor may include a CU 160 and at least one DU 165 (e.g., and RU 170), wherein the CU 160 may communicate with the core network 130 via an interface (e.g., a backhaul link). The IAB donor and IAB node 104 may communicate via an F1 interface according to a protocol defining the signaling messages (e.g., the F1 AP protocol). Additionally or alternatively, the CU 160 may communicate with the core network via an interface (which may be part of a backhaul link) and may communicate with other CU 160s (e.g., CU 160 associated with an alternative IAB donor) via an Xn-C interface (which may be part of a backhaul link).

[0063] IAB node 104 may refer to a RAN node that provides IAB functionality (e.g., access for UE 115, radio self-backhaul capability, etc.). DU 165 may act as a distributed scheduling node toward child nodes associated with IAB node 104, and IAB-MT may act as a scheduled node toward a parent node associated with IAB node 104. That is, an IAB donor may be referred to as a parent node communicating with one or more child nodes (e.g., an IAB donor may relay UE transmissions through one or more other IAB nodes 104). Additionally or alternatively, depending on the AN's relay chain or configuration, IAB node 104 may also be referred to as a parent node or child node of other IAB nodes 104. Therefore, the IAB-MT entity of IAB node 104 can provide a Uu interface for child IAB node 104 to receive signaling from parent IAB node 104, and the DU interface (e.g., DU 165) can provide a Uu interface for parent IAB node 104 to send signaling notifications to child IAB node 104 or UE 115.

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

[0065] In the context of applying the techniques described herein to a decomposed RAN architecture, one or more components of the decomposed RAN architecture can be configured to support cross-node AI / ML services as described herein. For example, some operations described as being performed by UE115 or network entity 105 (e.g., base station 140) may additionally or alternatively be performed by one or more components of the decomposed RAN architecture (e.g., IAB node 104, DU 165, CU 160, RU 170, RIC 175, SMO 180).

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

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

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

[0069] In some examples, such as in carrier aggregation configurations, a carrier may also have acquisition signaling or control signaling to coordinate 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 identified according to a channel grating used for discovery by UE 115. A carrier may operate in standalone mode, in which case initial acquisition and connection can be performed by UE 115 via that carrier, or the carrier may operate in non-standalone mode, in which case different carriers (e.g., the same or different radio access technologies) are used to anchor the connection.

[0070] The communication link 125 shown in the wireless communication system 100 may include downlink transmission (e.g., forward link transmission) from network entity 105 to UE 115, uplink transmission (e.g., return link transmission) from UE 115 to network entity 105, or both, as well as other transmission configurations. A carrier may carry downlink communication or uplink communication (e.g., in FDD mode), or may be configured to carry both downlink and uplink communication (e.g., in TDD mode).

[0071] A carrier may be associated with a specific bandwidth of the RF spectrum, and in some examples, the carrier bandwidth may be referred to as the carrier or the “system bandwidth” of the wireless communication system 100. For example, the carrier bandwidth may be one bandwidth in a set of bandwidths for a particular radio access technology (e.g., 1.4 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., network entity 105, UE 115, or both) may have hardware configurations that support communication using a specific carrier bandwidth, or may be configured to support communication using one carrier bandwidth in a set of carrier bandwidths. In some examples, the wireless communication system 100 may include network entity 105 or UE 115 that supports concurrent communication using carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured to operate using a portion (e.g., subband, BWP) or all of the carrier bandwidth.

[0072] The signal waveform transmitted via a carrier may include multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform extended OFDM (DFT-S-OFDM)). In a system employing MCM, a resource element may refer to a resource of one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, where the symbol period and subcarrier spacing may be inversely related. The number of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the decoding rate of the modulation scheme, or both), such that a relatively high number of resource elements (e.g., in the transmission duration) and a relatively high modulation scheme order correspond to a relatively high communication rate. Wireless communication resources may refer to a combination of RF spectrum resources, temporal resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial resources may increase the data rate or data integrity used for communication with UE 115.

[0073] The time interval for network entity 105 or UE 115 can be expressed as a multiple of a basic time unit, such as the sampling period. seconds, in response This can represent the supported subcarrier spacing, and The supported Discrete Fourier Transform (DFT) size can be represented. Time intervals for communication resources can be organized according to radio frames, each with a specified duration (e.g., 10 milliseconds (ms)). Each radio frame can be identified by a System Frame Number (SFN) (e.g., ranging from 0 to 1023).

[0074] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, a frame may (e.g., in the time domain) be divided into subframes, and each subframe may also be 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 each symbol period). In some wireless communication systems 100, time slots may be further divided into multiple micro-time slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., The duration of a symbol period is associated with a (number) sampling period. The duration of a symbol period can depend on the subcarrier spacing or the operating frequency band.

[0075] A subframe, time slot, micro-time slot, or symbol can be the smallest scheduling unit of the wireless communication system 100 (e.g., in the time domain) and can be referred to as a transmission time interval (TTI). In some examples, the duration of the TTI (e.g., the number of symbol periods in the TTI) can be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 can be dynamically selected (e.g., in a burst of shortened TTIs (sTTIs)).

[0076] Depending on the technology, carriers can be used to multiplex physical channels for communication. One or more of Time Division Multiplexing (TDM), Frequency Division Multiplexing (FDM), or hybrid TDM-FDM techniques can be used, for example, to multiplex physical control channels and physical data channels for signaling via a downlink carrier. The control region (e.g., control resource set (CORESET)) of the physical control channel can be defined by a set of symbol periods and can extend across the system bandwidth of the carrier or a subset of that bandwidth. One or more control regions (e.g., CORESET) can be configured for a set of UEs 115. For example, one or more UEs in UE 115 can monitor or search for control regions to obtain control information based on one or more search space sets, and each search space set can include one or more control channel candidates in one or more aggregation levels arranged in a concatenated manner. The aggregation level of control channel candidates can refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space set may include: a common search space set configured to transmit control information to multiple UEs 115, and a UE-specific search space set used to transmit control information to a specific UE 115.

[0077] In some examples, network entity 105 (e.g., base station 140, RU 170) may be mobile, and thus provide communication coverage to mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 use the same or different radio access technologies to provide coverage for various coverage areas 110.

[0078] The wireless communication system 100 can support synchronous or asynchronous operation. For synchronous operation, network entities 105 (e.g., base station 140) can have similar frame timings, and transmissions from different network entities 105 can be approximately time-aligned. For asynchronous operation, network entities 105 can have different frame timings, and in some examples, transmissions from different network entities 105 may not be time-aligned. The techniques described herein can be used for both synchronous and asynchronous operation.

[0079] Some UE 115 devices (such as MTC or IoT devices) can be low-cost or low-complexity devices and can provide automated communication between machines (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC can refer to data communication technologies that allow devices to communicate with each other or with network entity 105 (e.g., base station 140) without human intervention. In some examples, M2M communication or MTC may include communication from devices with integrated sensors or instruments to measure or acquire information and relay such information to a central server or application that uses the information or presents it to people interacting with the application. Some UE 115 devices may be designed to collect information or enable 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, fleet management and tracking, remote security sensing, physical access control, and transaction-based billing.

[0080] Some UE 115s can be configured to operate in a power-saving mode, such as half-duplex communication (e.g., a mode that supports unidirectional communication via transmission or reception but does not involve concurrent transmission and reception). In some examples, half-duplex communication can be performed at a reduced peak rate. Other power-saving techniques for UE 115s include entering a power-saving deep sleep mode when not engaged in active communication, operating with limited bandwidth (e.g., according to narrowband communication), or a combination of these techniques. For example, some UE 115s can be configured to operate using a narrowband protocol type associated with a defined portion or range (e.g., a set of subcarriers or resource blocks (RBs)) within a carrier, within a carrier's guard band, or outside a carrier.

[0081] Wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication, or various combinations thereof. For example, wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable 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 functions may include prioritization of services, and such services may be used for public safety or general business applications. The terms “ultra-reliable,” “low-latency,” and “ultra-reliable low-latency” are used interchangeably herein.

[0082] In some examples, UE 115 may be configured to support direct communication with other UE 115s via device-to-device (D2D) communication link 135 (e.g., according to peer-to-peer (P2P), D2D, or sidelink protocols). In some examples, one or more UE 115s performing D2D communication in a group may be within the coverage area 110 of network entity 105 (e.g., base station 140, RU 170), which may support aspects of such D2D communication configured (e.g., scheduled by network entity 105). In some examples, one or more UE 115s in such a group may be outside the coverage area 110 of network entity 105, or may otherwise be unable or not configured to receive transmissions from network entity 105. In some examples, the group of UE 115s communicating via D2D communication may support a one-to-many (1:M) system in which each UE 115 transmits to each of the other UE 115s in the group. In some examples, network entity 105 may facilitate the scheduling of resources used for D2D communication. In other examples, D2D communication may be performed between UEs 115 without involving network entity 105.

[0083] In some systems, the D2D communication link 135 may be an example of a communication channel (such as a sidelink communication channel) between vehicles (e.g., UE 115). In some examples, vehicles may communicate using vehicle-to-vehicle (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination of these. Vehicles may signal information related to traffic conditions, signaling, weather, safety, emergencies, or any other information relevant to the V2X system. In some examples, vehicles in a V2X system may 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 170) using vehicle-to-network (V2N) communication, or both.

[0084] Core network 130 provides user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. Core network 130 may be an evolved packet core (EPC) or a 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), access and mobility management function (AMF)) for managing access and mobility, and at least one user plane entity (e.g., a serving gateway (S-GW), packet data network (PDN) gateway (P-GW), or user plane function (UPF)) for routing packets or interconnecting to external networks. The control plane entity manages non-access stratum (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by network entity 105 (e.g., base station 140) associated with core network 130. User IP packets can be delivered through the user plane entity, which provides IP address allocation and other functions. The user plane entity may connect to one or more network operator IP services 150. IP services 150 may include access to the Internet, intranets, IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0085] Wireless communication system 100 can operate using one or more frequency bands in the range of 300 MHz to 300 GHz. Generally, the area from 300 MHz to 3 GHz is referred to as the Ultra High Frequency (UHF) band or decimeter band because the wavelength range is approximately one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features (which may be referred to as clusters), but these waves are sufficient to penetrate structures so that macrocells can provide service to UE 115 located indoors. Compared to communication using smaller frequencies and longer wavelengths in the lower frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz, communication using UHF waves can be associated with smaller antennas and shorter ranges (e.g., less than 100 km).

[0086] The wireless communication system 100 can also operate in the ultra-high frequency (SHF) region (also known as the centimeter band) in the range of 3 GHz to 30 GHz or in the extremely high frequency (EHF) region (e.g., 30 GHz to 300 GHz) (also known as the millimeter band) using the spectrum. In some examples, the wireless communication system 100 can support millimeter-wave (mmW) communication between the UE 115 and network entity 105 (e.g., base station 140, RU 170), and the EHF antennas of the corresponding devices can be smaller and more closely spaced than UHF antennas. In some examples, such techniques facilitate the use of antenna arrays within the device. However, compared to SHF or UHF transmission, EHF transmission may experience even greater attenuation and a shorter range. The techniques disclosed herein can be adopted for transmission across one or more different frequency regions, and the frequency band usage specified across these frequency regions may vary by country or regulatory authority.

[0087] Wireless communication system 100 may utilize both licensed and unlicensed RF spectrum bands. For example, wireless communication system 100 may employ licensed assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology using unlicensed frequency bands (such as the 5 GHz Industrial, Scientific, and Medical (ISM) band). When operating with unlicensed RF spectrum, devices such as network entity 105 and UE 115 may employ carrier sensing for collision detection and avoidance. In some examples, operation using unlicensed frequency bands may be based on carrier aggregation configurations combined with component carriers operating with licensed frequency bands (e.g., LAA). Operation using unlicensed spectrum may include downlink transmission, uplink transmission, P2P transmission, or D2D transmission, etc.

[0088] Network entity 105 (e.g., base station 140, RU 170) or UE 115 may be equipped with multiple antennas that can be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communication, or beamforming. The antennas of network entity 105 or UE 115 may be located within one or more antenna arrays or antenna panels, which can support MIMO operation or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly (such as an antenna tower). In some examples, the antennas or antenna arrays associated with network entity 105 may be located at different geographical locations. Network entity 105 may include an antenna array having a collection of multiple rows and columns of antenna ports that network entity 105 can use to support beamforming for communication with UE 115. Similarly, UE 115 may include one or more antenna arrays that can support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals transmitted via the antenna ports.

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

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

[0091] The wireless communication system 100 can be a packet-based network operating according to a layered protocol stack. In the user plane, communication at the bearer or PDCP layer can be IP-based. The RLC layer performs packet segmentation and reassembly for transmission via logical channels. The MAC layer performs priority processing and multiplexing of logical channels to transport channels. The MAC layer can also implement error detection, error correction, or both to support retransmission and improve link efficiency. In the control plane, the RRC layer can provide the establishment, configuration, and maintenance of RRC connections between the UE 115 and network entity 105 or core network 130 supporting user plane data radio bearers. The PHY layer maps transport channels to physical channels.

[0092] UE 115 and network entity 105 can support data retransmission to increase the likelihood of successful data reception. Hybrid Automatic Repeat Request (HARQ) feedback is a technique used to increase the likelihood of correctly receiving data via communication links (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using Cyclic Redundancy Check (CRC)), forward error correction (FEC), and retransmission (e.g., Automatic Repeat Request (ARQ)). HARQ can improve throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, the device may support same-slot HARQ feedback, in which case the device may provide HARQ feedback in a specific time slot for data received via a previous symbol in that time slot. In some other examples, the device may provide HARQ feedback in subsequent time slots or according to a different time interval.

[0093] Additionally, UE 115 and network entity 105 (e.g., RAN) may support artificial intelligence (AI / ML) operations or models. For example, UE 115 may support one or more AI / ML models for optimizing wireless communication system 100. UE 115 may be unaware of the ML service, and thus UE 115 can communicate with network entity 105. However, the AI / ML service may provide one or more AI / ML models used at UE 115. In some examples, one or more AI / ML models associated with UE 115 may no longer promote the expected model or system performance (e.g., exceeding performance thresholds). Therefore, UE 115 may no longer use the current AI / ML model to provide the expected optimization for the wireless communication system.

[0094] UE 115 can communicate UE ML capabilities (e.g., AI / ML capabilities) to network entity 105 (e.g., RAN), and ML services (e.g., AI / ML services) can also provide ML service capabilities to network entity 105. Network entity 105 can facilitate cross-node configuration, cross-node ML inference, and / or performance monitoring based on UE ML capabilities and ML service capabilities. By relaying information between UE 115 and ML services, UE 115 can communicate indirectly with ML services, enabling the use of ML models to update UE 115, which facilitates the UE's expected (e.g., above performance thresholds) functional performance and compatibility with ML services.

[0095] To exchange ML capabilities with the ML service, network entity 105 may request ML service capabilities from the ML service after receiving UE ML capabilities from UE 115, and the ML service may provide ML service capabilities to network entity 105 based on this request. In some examples, the ML service may advertise ML service capabilities to other nodes, including network entity 105, without request. For cross-node ML configuration, network entity 105 may determine that UE 115 can enable cross-node ML services based on capability information from UE 115 and the ML service, and network entity 105 may request and obtain configuration from the ML service to provide to UE 115. For cross-node ML inference, UE 115 may transmit ML service input data to network entity 105 for forwarding to the ML service, and the ML service may provide ML service data response or output data (e.g., input / output data streams between UE 115 and the ML service via network entity 105). For performance monitoring, UE 115, network entity 105, and / or the ML service may monitor performance (e.g., by monitoring relevant key performance indicators and associated thresholds). In some examples, UE 115 and / or network entity 105 may send monitoring reports to the ML service. The monitored conditions may cause UE 115 to activate, deactivate, or switch (e.g., to a new or default configuration) one or more ML configurations, for example, to optimize the wireless communication system 100 to operate as expected (e.g., above a system or model performance threshold).

[0096] Figure 2 An example of a network architecture 200 (e.g., a decomposed base station architecture, a decomposed RAN architecture) supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Network architecture 200 may exemplify examples of one or more aspects for implementing wireless communication system 100. Network architecture 200 may include one or more CUs 160-a that can communicate directly with core network 130-a via backhaul communication link 120-a, or indirectly with core network 130-a via one or more decomposed network entities 105 (e.g., near-RT RIC 175-b via an E2 link or a non-RT RIC 175-a associated with SMO 180-a (e.g., an SMO framework) or both). CUs 160-a may communicate with one or more DUs 165-a via a corresponding midhaul communication link 162-a (e.g., an F1 interface). DUs 165-a may communicate with one or more RUs 170-a via a corresponding fronthaul communication link 168-a. RU 170-a may be associated with a corresponding coverage area 110-a and may communicate with UE 115-a via one or more communication links 125-a. In some implementations, UE 115-a may be served simultaneously by multiple RU 170-a.

[0097] Each network entity in network entity 105 of network architecture 200 (e.g., CU 160-a, DU 165-a, RU170-a, non-RT RIC 175-a, near-RT RIC 175-b, SMO 180-a, Open Cloud (O-Cloud) 205, Open eNB (O-eNB) 210) may include one or more interfaces or may be coupled to one or more interfaces configured to receive or transmit signals (e.g., data, information) via wired or wireless transmission media. Each network entity 105 or an associated processor (e.g., a controller) that provides instructions to the interfaces of network entity 105 may be configured to communicate with one or more network entities in other network entities 105 via transmission media. For example, these network entities 105 may include wired interfaces configured to receive signals or transmit signals to one or more network entities in other network entities 105 via wired transmission media. Additionally or alternatively, network entity 105 may include a wireless interface that may include a receiver, transmitter, or transceiver (e.g., an RF transceiver) configured to receive signals via a wireless transmission medium or to transmit signals to one or more other network entities in network entity 105, or both.

[0098] In some examples, the CU 160-a can host one or more higher-level control functions. Such control functions may include RRC, PDCP, SDAP, etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by the CU 160-a. The CU 160-a can be configured to handle user plane functionalities (e.g., CU-UP), control plane functionalities (e.g., CU-CP), or combinations thereof. In some examples, the CU 160-a can be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units can communicate bidirectionally with the CU-CP units via an interface such as an E1 interface. The CU 160-a can be implemented to communicate with the DU 165-a for network control and signaling purposes, as needed.

[0099] DU 165-a may correspond to a logical unit comprising one or more functions (e.g., base station functions, RAN functions) for controlling the operation of one or more RU 170-a. In some examples, DU 165-a may at least partially host one or more aspects of the RLC layer, MAC layer, and PHY layer (e.g., high PHY layers, such as modules for FEC encoding and decoding, scrambling, modulation and demodulation, etc.), depending at least in part on the functional breakdown, such as those defined by the 3rd Generation Partnership Project (3GPP). In some examples, DU 165-a may also host one or more low PHY layers. Each layer may be implemented using an interface configured to communicate signaling with other layers hosted by DU 165-a or with control functions hosted by CU 160-a.

[0100] In some examples, lower-layer functionality may be implemented by one or more RU 170-a units. For example, an RU 170-a controlled by a DU 165-a may correspond to a logical node that hosts RF processing functions or low-PHY layer functions (e.g., performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, Physical Random Access Channel (PRACH) extraction and filtering, or both) based at least in part on functional decomposition (such as lower-layer functional decomposition). In such architectures, the RU 170-a may be implemented to handle over-the-air (OTA) communications with one or more UE 115-a units. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communications with the RU 170-a may be controlled by the corresponding DU 165-a unit. In some examples, such configurations enable the implementation of DU 165-a and CU160-a units in cloud-based RAN architectures such as vRAN architectures.

[0101] The SMO 180-a can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network entities 105. For non-virtualized network entities 105, the SMO 180-a can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via an operation and maintenance interface (e.g., the O1 interface). For virtualized network entities 105, the SMO 180-a can be configured to interact with a cloud computing platform (e.g., O-Cloud 205) via a cloud computing platform interface (e.g., the O2 interface) to perform network entity lifecycle management (e.g., to instantiate virtualized network entities 105). Such virtualized network entities 105 may include, but are not limited to, CU 160-a, DU 165-a, RU 170-a, and near-RT RIC 175-b. In some specific implementations, the SMO 180-a can (e.g., via the O1 interface) communicate with components configured according to the 4G RAN. Additionally or alternatively, in some implementations, the SMO 180-a may communicate directly with one or more RU 170-a via the O1 interface. The SMO 180-a may also include a non-RT RIC 175-a configured to support the functionality of the SMO 180-a.

[0102] The non-RT RIC 175-a can be configured to include logical functions enabling non-real-time control and optimization of RAN elements and resources, including artificial intelligence (AI) or machine learning (ML) workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 175-b. The non-RT RIC 175-a can be coupled to or communicate with the near-RT RIC 175-b (e.g., via an A1 interface). The near-RT RIC 175-b can be configured to include logical functions enabling near real-time control and optimization of RAN elements and resources via data collection and actions on an interface (e.g., via an E2 interface) that connects one or more CU 160-a, one or more DU 165-a, or both, and an O-eNB 210 to the near-RT RIC 175-b.

[0103] In some examples, to generate AI / ML models to be deployed in a near-RT RIC 175-b, a non-RT RIC 175-a may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 175-b and can be received from non-network data sources or network functions at the SMO 180-a or non-RT RIC 175-a. In some examples, a non-RT RIC 175-a or near-RT RIC 175-b may be configured to tune RAN behavior or performance. For example, a non-RT RIC 175-a may monitor long-term trends and patterns in performance and employ AI or ML models to perform corrective actions via the SMO 180-a (e.g., via O1 reconfiguration) or via the generation of RAN management policies such as the A1 policy.

[0104] As described herein, UE 115-a can communicate its ML capabilities (e.g., AI / ML capabilities) to network entities (e.g., via one or more RU 170-a, one or more DU 165-a, one or more CU 160-a, etc.), and AI / ML services (e.g., AI / ML services) can provide AI / ML service capabilities to network entities. Network entities can facilitate cross-node configuration, cross-node AI / ML inference, and / or performance monitoring based on the AI / ML capabilities of UE 115-a and the AI / ML service capabilities of the AI / ML service. By relaying information between UE 115-a and the AI / ML service, UE 115-a can communicate indirectly with the AI / ML service, enabling the use of ML models to update UE 115-a, which facilitates UE 115-a performing functions as expected (e.g., above performance thresholds) and is compatible with the AI / ML service.

[0105] To exchange capabilities with the AI / ML service, a network entity may request AI / ML service capabilities from the AI / ML service after receiving capabilities from UE 115-a, and the AI / ML service may respond to the request by providing the AI / ML service capabilities to the network entity. In some examples, the AI / ML service may (e.g., without request) advertise its AI / ML service capabilities to other nodes, including the network entity. For cross-node AI / ML configuration, the network entity may determine that UE 115-a can enable cross-node ML services based on capability information from UE 115-a and the AI / ML service, and the network entity may request and obtain configuration from the AI / ML service to provide to UE 115. For cross-node AI / ML inference, UE 115 may transmit AI / ML service input data to the network entity for forwarding to the AI / ML service, and the AI / ML service may provide AI / ML service data response or output data (e.g., input / output data streams between UE 115 and the AI / ML service via network entity 105). For performance monitoring, UE 115, network entity 105, and / or the AI / ML service can monitor performance (e.g., by monitoring relevant key performance indicators and associated thresholds). In some examples, UE 115-a and / or the network entity can send monitoring reports to the AI / ML service. The monitored conditions may cause UE 115-a to activate, deactivate, or switch (e.g., to a new or default configuration) one or more AI / ML configurations, for example, to optimize the wireless communication system to operate as expected (e.g., above system or model performance thresholds).

[0106] Figure 3 An example of a wireless communication system 300 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. The wireless communication system 300 may implement aspects of the wireless communication system 100, or may be implemented by aspects of the wireless communication system. For example, the wireless communication system 300 includes a UE 115-b, which may be related to... Figure 1 The example of UE115 described. The wireless communication system 300 also includes network entity 105-b, which can be as described in... Figure 1 An example of the described network entity 105.

[0107] Wireless communication system 300 may be a UE 115 (e.g., UE 115-b), a network entity 105 (e.g., 105-b, RAN), and an ML service 305 (e.g., AI / ML service) that supports ML operations or models (e.g., AI / ML operations or models). ML operations or models enable corresponding devices with ML functionality to optimize wireless communication system 300, for example, by predicting traffic patterns and adjusting the network accordingly to reduce network congestion and optimize the use of system resources. In such wireless communication system 300, UE 115 and network entity 105 may involve one or more paired or bilateral AI / ML models and joint inference between UE 115 and network entity 105. As used herein, "inference" may refer to an output or prediction based on applying one or more AI / ML models to input data (e.g., current data associated with wireless communication system 300). Therefore, paired AI / ML models can be used to perform joint inference, where AI / ML inference is performed jointly across UE 115 and network entity 105. For example, UE 115 may perform the first part of the joint inference, and network entity 105 may subsequently perform the remainder of the joint inference, and vice versa. UE 115 may receive AI / ML-specific control information or input from network entity 105 (e.g., in addition to existing signaling from network entity 105), and vice versa.

[0108] Network entity 105 (e.g., network entity 105-b) can communicate with UE 115 (e.g., UE 115-b) using communication link 125 (e.g., communication link 125-a). Communication link 125 can be an example of an NR or LTE link between UE 115 and network entity 105. Communication link 125 can include a bidirectional link that enables both uplink and downlink communication. For example, UE 115-a can use communication link 125 to send uplink signals 310 (e.g., uplink signal 310-a, uplink transmit) such as uplink control signals or uplink data signals to network entity 105-b, and network entity 105-b can use communication link 125 to send downlink signals 315 (e.g., downlink signal 315-a, downlink transmit) such as downlink control signals or downlink data signals to UE 115.

[0109] Network entity 105 (e.g., network entity 105-b) can communicate with ML service 305 using communication link 125 (e.g., communication link 125-b). Communication link 125 can be an example of an NR or LTE link between ML service 305 and network entity 105. Communication link 125 can include a bidirectional link that enables both uplink and downlink communication. For example, network entity 105 can use communication link 125 to send uplink signals 310 (e.g., uplink signal 310-b, uplink transmit), such as uplink control signals or uplink data signals, to ML service 305, and ML service 305 can use communication link 125 to send downlink signals 315 (e.g., downlink signal 315-b, downlink transmit), such as downlink control signals or downlink data signals, to network entity 105.

[0110] In some examples, as discussed herein, UE 115 may not be able to discover ML service 105 or communicate directly with that ML service. In such examples, network entity 105 may output or send control messages (e.g., control signals) 320 to UE 115 on communication link 125-a, wherein control message 320 indicates one or more ML configurations for UE 115 to perform ML procedures. UE 115 may output message 325 to network entity 105 on communication link 125-a, indicating AI / ML input data from UE 115, such as one or more model inference results at UE 115. The model inference results from UE 115 may be used by ML service 305. Network entity 105 may forward the AI / ML input data in message 330 to ML service 305 on communication link 125-b. ML service 305 may use the input data from UE 115 to generate output data (e.g., using one or more model inference results from UE 115). For example, ML service 305 can output message 335 to network entity 105 on communication link 125-b, where message 335 includes AI / ML output data.

[0111] According to the techniques described herein, UE 115-b, network entity 105-b, and ML service 305 can perform corresponding capability exchange procedures, cross-node AI / ML configuration procedures, cross-node AI / ML inference procedures, and monitoring and LCM operations. LCM can refer to operations that use AI and / or ML to maintain one or more wireless communication links, such as CSI reporting (e.g., CSI prediction), beam management operations (e.g., spatial and temporal beam prediction), positioning (e.g., AI and / or ML-assisted positioning), etc. As an example, the capability exchange procedure may include ML service 305 providing AI / ML service capability information to network entity 105-b and UE 115-b providing AI / ML capability information to network entity 105-b. The cross-node AI / ML configuration process may include configuring AI / ML functions for the UE based on UE and AI / ML service capabilities, and the cross-node AI / ML inference process may include the exchange of AI / ML input data (e.g., encoder output) from UE 115-b to network entity 105-b and AI / ML output data (e.g., decoder output) from ML service 305 to network entity 105-b. The monitoring and LCM process may include monitoring by UE 115-b, network entity 105-b, and / or ML service 305, wherein the LCM process may be performed based on monitoring output, which may include activation, deactivation, rollback, switching, or any combination thereof of AI / ML functions at UE 115-b and / or ML service 305. For example, network entity 105-b (e.g., RAN), together with AI / ML service 305, may control the activation or deactivation of one or more AI / ML configurations for UE 115-b.

[0112] Figure 4An example of a process flow 400 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 400 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 400 may include UE 115-c, which may be an example of UE 115 as described herein. Process flow 400 may include network entity 105-c, which may be an example of network entity 105 as described herein. Process flow 400 may include ML service 305-c, which may be an example of ML service 305 as described herein. In the following description of process flow 400, operations performed by network entity 105-c, UE 115-c, and ML service 305-c may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 400 may also be omitted, or other operations may be added to process flow 400. Furthermore, although the operations in process flow 400 are illustrated as being performed by network entity 105-c, UE 115-c, and ML service 305-c, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0113] Process flow 400 can exemplify cross-node AI / ML inference services, where at least some inference services are provided via cross-node connections (e.g., relay, handover, traversal, or indirect). For example, at 405, UE 115-c may send UE capability information to network entity 105-c (e.g., RAN), and at 410, ML service 305-c (e.g., AI / ML service) may output service capabilities to network entity 105. Network entity 105-c may facilitate the exchange of capability information or otherwise provide capability information across nodes (e.g., UE nodes and ML service nodes). The exchange of capability information facilitates cross-node configuration. Therefore, at 420, a cross-node configuration process can be performed. This can be as described regarding... Figure 6 The cross-node configuration process is performed as discussed. For example, the process may involve multiple nodes (such as UE 115, network entity 105, and ML service 305-c), and information may be relayed across these multiple nodes to configure UE 115-c to have one or more ML configurations. The configuration may be based on UE capabilities and AI / ML service capabilities.

[0114] At position 425, cross-node AI / ML inference processes can be performed. This can be seen in... Figure 7The cross-node AI / ML inference process is performed as discussed. For example, this process may involve multiple nodes (such as UE 115, network entity 105, and ML service 305-c), and information may be relayed across these nodes to exchange inferences between UE 115-c and ML service 305-c. The cross-node AI / ML inference process may include cross-node AI / ML input data (e.g., encoder output) from UE 115-c to network entity 105 and AI / ML output data (e.g., decoder output) from ML service 305-c to network entity 105.

[0115] At point 430, a cross-node monitoring process can be performed. This can be seen in the following... Figure 8 , Figure 9 and Figure 10 The cross-node monitoring process is performed as discussed. For example, the process may involve multiple nodes (such as UE 115, network entity 105, and ML service 305-c), and information may be relayed across these nodes to exchange monitored information between UE 115, network entity 105, and ML service 305-c. The monitoring process may include monitoring and LCM procedures, where monitoring occurs at UE 115, network entity 105, or ML service 305-c. LCM may be based on monitoring output from UE 115, network entity 105, or ML service 305-c. Monitoring may, for example, be performed via network entity 105 (e.g., RAN) in conjunction with ML service 305-c to activate, deactivate, or switch one or more ML configurations (e.g., to a default ML configuration or another ML configuration).

[0116] Figure 5An example of a process flow 500 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 500 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 500 may include UE 115-d, which may be an example of UE 115 as described herein. Process flow 500 may include network entity 105-d, which may be an example of network entity 105 as described herein. Process flow 500 may include AI / ML service 305-d, which may be an example of ML service 305 as described herein. In the following description of process flow 500, operations performed by network entity 105-d, UE 115-d, and ML service 305-d may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 500 may also be omitted, or other operations may be added to process flow 500. Furthermore, although the operations in process flow 500 are illustrated as being performed by network entity 105-d, UE 115-d, and ML service 305-d, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0117] Process flow 500 may exemplify a capability exchange process, in which at least some capabilities are exchanged across nodes (e.g., relay, handover, traversal, or indirect). In some examples, at 505, ML service 305-d may output an AI / ML service capability advertisement to facilitate the exchange of AI / ML service capabilities between AI / ML service 305-d and network entity 105-d. For example, ML service 305-d may advertise AI / ML service capabilities, such as a list of supported functions, to network entity 105-d. The advertisement may also include a list of AI / ML models supported by each function, feature, or feature group, as well as a region configuration including the AI / ML service, function, or model.

[0118] At position 510, UE 115-d can output UE capability information to network entity 105, such as regarding... Figure 4As discussed in section 405. At 515, network entity 105-d may output an AI / ML service capability query, whereby network entity 105-d may query ML service 305-d for AI / ML service capabilities. Because network entity 105-d receives UE capability information from UE 115-d, network entity 105-d may include a set of UE identities (e.g., multiple UE identities) that includes the UE identities along with the UE capability information of ML service 305-d. In some examples, at 520, ML service 305-d may output a UE subscription request to subscription service 550 based on information received from network entity 105-d (such as UE identities (e.g., the set of UE identities)). At 525, subscription service 550 may output a UE subscription response 525 based on the UE subscription request. For example, subscription service 550 may provide one or more ML configurations corresponding to one or more ML models based on UE identities. In some examples, upon receiving an AI / ML service capability request, ML service 305-d can verify the UE subscription information and policies from subscription service 550 to determine whether UE 115 allows ML services such as models. ML service 305-d can, for example, reject AI / ML service capability queries based on UE identity. At 530, ML service 305-d can output AI / ML service capability information, such as information about... Figure 4 The discussion in section 410.

[0119] Figure 6 An example of a process flow 600 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 600 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 600 may include UE 115-e, which may be an example of UE 115 as described herein. Process flow 600 may include network entity 105-e, which may be an example of network entity 105 as described herein. Process flow 600 may include ML service 305-e, which may be an example of ML service 305 as described herein. In the following description of process flow 600, operations performed by network entity 105-e, UE 115-e, and ML service 305-e may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 600 may also be omitted, or other operations may be added to process flow 600. Furthermore, although the operations in process flow 600 are illustrated as being performed by network entity 105-e, UE 115-e, and ML service 305-e, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0120] Process flow 600 can provide cross-node AI / ML configuration, where at least some ML configuration is provided via cross-node (e.g., relay, handover, traversal, or indirectly). Cross-node AI / ML configuration between network entity 105-e and UE 115-e can be based on AI / ML service input, such as regarding... Figure 4 As discussed. For example, at 605, network entity 105-e (e.g., RAN) can determine that UE 115-e can enable cross-node AI / ML configuration, allowing network entity 105-e to select ML functionality for either UE 115-e or ML service 305-e. Network entity 105-e can determine that UE 115-e can enable cross-node AI / ML configuration based on UE capability information and ML service capability information, as per the discussion. Figure 5 The subject of discussion.

[0121] At point 610, after determining the cross-node AI / ML configuration, network entity 105-e may output a request message for a configuration request to ML service 305-e. This request may include a request for ML configuration information from ML service 305-e. For example, network entity 105-e may include the UE identity or selected ML function (e.g., ML model) for configuration in the configuration request. At point 615, ML service 305-e may output AI / ML input and output data configuration in a configuration response message. The configuration response may include one or more ML configurations, preferred one or more configurations (e.g., default configuration), triggers or periodicity associated with the ML configurations. ML service 305-e may also provide monitoring configuration in a monitoring configuration message. The monitoring configuration may indicate monitoring events, monitoring key performance indicator (KPI) configurations, thresholds, monitoring report configurations, or other monitoring-related configurations.

[0122] At 620, network entity 105-e may output a message to UE 115-e for the cross-node AI / ML process. For example, network entity 105-e may output one or more messages with one or more ML configurations to UE 115-e from a configuration response. This process may involve relaying the one or more ML configurations to UE 115-e individually or as a whole. Once the process is complete, at 625, UE 115-e may output a completion message for the cross-node AI / ML configuration completion, indicating that UE 115-e has completed the cross-node AI / ML configuration process. For example, completing the process may result in configuring UE 115-e using one or more ML configurations and one or more corresponding ML models. After configuration, one or more ML configurations may be activated. Network entity 105-e may activate the AI / ML service. In some examples, activation may be requested by UE 115-e or ML service 305-e. In some cases, at 630, network entity 105-e may output a message to ML service 305-e, which includes an indication that AI / ML configuration is complete (e.g., at UE 115-e).

[0123] In the example of network entity 105-e requesting activation, at 635, network entity 105-e may output an activation request message to ML service 305-e to request activation of a configuration. This request may include the UE identity or ML function (e.g., model) as determined at 610. At 640, ML service 305-e may confirm the request by outputting an activation confirmation message. This confirmation may include the UE identity and the ML function. At 645, network entity 105-e may output an activation indication message to UE 115-e to instruct UE 115-e to activate one or more ML configurations received by UE 115-e. The activation indication may also instruct UE 115-e to activate cross-node AI / ML inference.

[0124] In the example of ML service 305-e requesting activation, at 650, ML service 305-e may output an activation request message to network entity 105-e to request activation of the configuration. At 655, network entity 105-e may output an activation confirmation message to confirm the activation of one or more ML configurations at UE 115-e or to activate AI / ML inference of the configuration at the UE (e.g., cross-node AI / ML inference activation performed by ML service 305-e). Therefore, at 660, network entity 105-e may output an activation indication 660 to instruct the UE to activate one or more ML configurations.

[0125] In the example of UE 115-e requesting activation, at point 665, UE 115-e may send an activation request message to network entity 105-e to request activation configuration. For example, after configuration is complete, UE 115-e may use UE Assistance Information (UAI), Media Access Control (MAC) Control Element (MAC CE), etc., to transmit the activation request to network entity 105-e. Network entity 105-e may activate cross-node AI / ML inference operations in response to the request from UE 115. For example, at point 670, network entity 105-e may forward the request to ML service 305-e. Therefore, at point 675, ML service 305-e may output an activation confirmation message to network entity 105. At point 680, network entity 105-e may output an activation indication message to instruct the UE to activate one or more ML configurations or ML inferences at UE 115.

[0126] Figure 7 An example of a process flow 700 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 700 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 700 may include UE 115-f, which may be an example of UE 115 as described herein. Process flow 700 may include network entity 105-f, which may be an example of network entity 105 as described herein. Process flow 700 may include ML service 305-f, which may be an example of ML service 305 as described herein. In the following description of process flow 700, operations performed by network entity 105-f, UE 115-f, and ML service 305-f may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 700 may also be omitted, or other operations may be added to process flow 700. Furthermore, although the operations in process flow 700 are illustrated as being performed by network entity 105-f, UE 115-f, and ML service 305-f, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0127] Process flow 700 can provide a process for cross-node AI / ML inference, wherein at least some ML inference is provided via cross-node (e.g., relay, handover, traversal, or indirect). The cross-node AI / ML inference process can be based on AI / ML input and output data streams between UE 115-f and ML service 305-f via network entity 105.

[0128] At 705, UE 115-f may output an inference message with AI / ML service input data (e.g., inference results of the UE model) to network entity 105. The inference results from the UE may be used as input to the corresponding service model at ML service 305-f. For example, the inference input data from UE 115-f may be used as input to the decoder model for channel state information (CSI) feedback for ML service 305-f. At 710, network entity 105-f may output a request message for AI / ML service data requests or input data to ML service 305-f to forward AI / ML service input data to ML service 305-f. At 715, ML service 305-f uses the input data (e.g., UE inference results) to perform inference in order to generate output data or service data response. Therefore, at 720, ML service 305-f may output a response message or output data for AI / ML service data response to network entity 105. In some examples, ML inference from ML service 305-f may be forwarded to UE 115-f via network entity 105. Some services may involve bounded response times to meet latency constraints, such as based on data forwarding across nodes (e.g., ML service 305-f to network entity 105, and network entity 105-f to UE 115). Bounded response times may limit whether certain cross-node AI / ML features can be deployed as separate services. At 725, network entity 105-f may output and UE 115-f may receive AI / ML service output data (e.g., received from ML service 305-f).

[0129] Figure 8 An example of a process flow 800 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 800 may implement aspects of wireless communication systems 100 or 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 800 may be implemented by UE 115, network entity 105, or ML service 305, which may be examples of UE 115, network entity 105, and ML service 305 as described herein. In the following description of process flow 800, the operations performed may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 800 may also be omitted, or other operations may be added to process flow 800. Furthermore, although the operations in process flow 800 are illustrated as being performed by UE 115, network entity 105, or ML service 305, the examples herein should not be construed as limiting, as the described features may be associated with any number of different devices.

[0130] Process flow 800 can provide monitoring and reporting, wherein at least some monitoring and reporting services are provided via cross-node (e.g., relay, handover, traversal, or indirect). Monitoring input data and reporting can cause UE 115 to switch or deactivate one or more current AI / ML models configured for use by UE 115. As discussed herein, process flow 800 can be performed by UE 115, network entity 105, and / or ML service 305. Monitoring may involve AI / ML input data 805 used as input to AI / ML inference 810, wherein data is applied to one or more ML models. Inference data may be model output 815, which can be used as input to monitor 820.

[0131] For example, monitoring can trigger model switching or deactivation when model or system performance degrades below a threshold. Performance can be determined based on monitor reports, such as UE monitor reports from UE 115 or network entity monitoring reports from network entity 105. In such examples, the model's use case may change, such as changes in system settings (e.g., number of antennas, carriers in use, etc.), location or environment (e.g., indoor vs. outdoor), or service changes (e.g., network slicing, Quality of Service (QoS) streaming, sessions, etc.).

[0132] Monitoring input data 825 can be the input to monitor 820, and can be used to evaluate the performance of the wireless communication system. For example, a monitoring device can use monitoring input data 825 to output monitoring report 830. Monitoring report 830 can be the output from a device (e.g., UE 115) to be monitored 820. The monitoring report may include AI / ML service KPIs. KPIs can be used to track inference performance (e.g., UE inference or ML service inference) relative to ground reality (e.g., a target used to train or validate a model with a dataset). For example, the monitoring report may indicate a minimum mean squared error (MMSE) threshold compared to ground reality, inference latency, etc.

[0133] Monitoring report 830 (feedback KPIs) may include (e.g., AI / ML service KPIs or system KPIs for ML service 305 or UE 115) which can be used to track overall system performance when AI / ML inference is in operation at UE 115 and network entity 105. For example, system KPIs can be used to track network load, uplink and downlink throughput, latency, packet loss, radio link failure (RLF) rate, etc., which indicate system performance. Monitoring report 830 may include feedback KPIs with event-based feedback. For example, feedback KPIs may be based on configured events, such as performance KPIs below a threshold. In some examples, feedback may be provided periodically, such as periodic feedback with configured periodicity.

[0134] Figure 9 An example of a process flow 900 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 900 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 900 may include UE 115-g, which may be an example of UE 115 as described herein. Process flow 900 may include network entity 105-g, which may be an example of network entity 105 as described herein. Process flow 900 may include ML service 305-g, which may be an example of ML service 305-g as described herein. In the following description of process flow 900, operations performed by network entity 105-g, UE 115-g, and ML service 305-g may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 900 may also be omitted, or other operations may be added to process flow 900. Furthermore, although the operations in process flow 900 are illustrated as being performed by network entity 105-g, UE 115-g, and ML service 305-g, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0135] In some examples, performance monitoring may be performed at UE 115-g or network entity 105, as shown at 905 and 910 (e.g., monitoring input data transmitted from ML service 305-g to network entity 105-g or from network entity 105-g to UE 115-g). Monitoring input data may be sent to UE 115-g via unicast communication or via broadcast. Upon receiving monitoring input data (e.g., from ML service 305-g), UE 115-g or network entity 105-g may perform monitoring and subsequently provide a monitoring report to ML service 305-g. For example, at 915, UE 115-g may generate a monitor report based on a trigger (e.g., KPI trigger, system or model performance below a threshold, etc.). At 920, UE 115-g may transmit a monitoring report to network entity 105, and at 925, network entity 105-g may transmit a UE monitor report to ML service 305-g. In some examples, monitoring reports are transmitted by UE 115-g or network entity 105-g when configured monitoring or reporting conditions occur. The AI / ML configuration for UE 115-g or network entity 105-g may include a list of performance KPIs to monitor and report, where monitoring events may include thresholds, UE environment, UE or network entity configuration changes, etc. The AI / ML configuration for UE 115-g or network entity 105-g may include a list of performance KPIs to report, where reporting configuration includes reporting events, reporting cycles, etc. This configuration may be based on monitoring input data from ML service 305-g. In some examples, at 930, network entity 105-g may monitor and report based on trigger events, and at 935, network entity 105-g may also transmit monitor reports to ML service 305-g. For example, monitor reports can be used to evaluate feedback KPIs or model switching conditions.

[0136] Figure 10An example of a process flow 1000 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Process flow 1000 may implement aspects of wireless communication systems 100 and 300, or may be implemented by aspects of these wireless communication systems. For example, process flow 1000 may include UE 115-h, which may be an example of UE 115 as described herein. Process flow 1000 may include network entity 105-h, which may be an example of network entity 105 as described herein. Process flow 1000 may include ML service 305-h, which may be an example of ML service 305 as described herein. In the following description of process flow 1000, operations performed by network entity 105-h, UE 115-h, and ML service 305-h may be performed in a different order than the exemplary order shown or at different times. Some operations in process flow 1000 may also be omitted, or other operations may be added to process flow 1000. Furthermore, although the operations in process flow 1000 are illustrated as being performed by network entity 105-h, UE 115-h, and ML service 305-h, the examples in this document should not be construed as limiting, as the described features can be associated with any number of different devices.

[0137] Process flow 1000 can provide cross-node LCM monitoring, wherein at least some of the LCM monitoring is provided via cross-node (e.g., relay, handover, traversal, or indirect). Process flow 1000 can facilitate the monitoring of monitoring reports by UE 115-h or network entity 105-h and the provision of monitoring reports to AI / ML services used for LCM. Performance monitoring can be performed at UE 115-h or network entity 105-h. In such an example, UE 115-h or network entity 105-h can perform monitoring and provide monitoring reports to ML service 305-h.

[0138] For example, at 1005, UE 115-h may perform LCM operation based on one or more triggers. The triggers may cause UE 115-h to generate an LCM monitoring report. At 1010, UE 115-h may transmit a monitor report to network entity 105. In some examples, UE 115-h may perform LCM and indicate LCM to ML service 305-h, or request ML service 305-h to perform LCM. UE 115-h may additionally provide a monitoring report to ML service 305-h.

[0139] Alternatively or additionally, at 1012, LCM operation may be controlled by network entity 105-h. In such cases, LCM may be triggered based on one or more thresholds, which may be determined by network entity 105-h based on UE monitoring reports (e.g., reports received at 1010) or by monitoring performed by network entity 105-h.

[0140] For LCM control signaling, at 1015, UE 115-h may transmit an LCM control request to network entity 105-h. This request may be an indication to activate, deactivate, switch, or roll back the current ML configuration. At 1020, network entity 105-h may transmit LCM control signaling to ML service 305-h, which forwards the request to activate, deactivate, switch, or roll back the current ML configuration. This request may include a configuration request (e.g., a reconfiguration request) to switch from one AI / ML function to another, from an AI / ML-based procedure to a non-AI / ML-based procedure, or from a non-AI / ML-based procedure to an AI / ML-based procedure. At 1025, network entity 105-h may send LCM control signaling to UE 115-h to instruct UE 115-h on configuration (e.g., reconfiguration).

[0141] In some examples, ML server 305-h can execute LCM control signaling (e.g., disable, handover, rollback, etc.) based on a request from UE 115. In such examples, network entity 105-h transmits LCM control signals to ML service 305-h and also to UE 115-h. Thus, UE 115-h can execute LCM and indicate the result to ML service 305-h, UE 115-h can request ML service 305-h to execute LCM, or UE 115-h can transmit monitoring reports (e.g., to network entity 105).

[0142] In some examples, LCM can be controlled by network entity 105-h (e.g., based on UE monitoring reports or monitoring at network entity 105). In such examples, network entity 105-h can translate system KPIs into ML service KPIs based on a qualitative or quantitative mapping between system KPIs and ML service KPIs provided by ML service 305-h, LCM triggers (e.g., thresholds) provided by ML service 305-h, or ML service KPIs. Network entity 105-h can evaluate system performance (e.g., calculated by network entity 105-h or reported by the UE) and monitor events (e.g., as implemented by network entity 105-h).

[0143] Network entity 105-h can configure UE 115-h to provide monitoring reports. Therefore, at 1030, UE 115-h can send a monitoring report to network entity 105, and this report can be used to assess system performance or monitor events. Additionally, in such examples, network entity 105-h can provide LCM control signaling, as discussed with respect to 1020 and 1025 (e.g., in the absence of an LCM request at 1015). LCM control signaling can include requests or indications to activate, deactivate, switch, or roll back the current ML configuration. This request can include a configuration request (e.g., a reconfiguration request) to switch from one AI / ML function to another, from an AI / ML-based procedure to a non-AI / ML-based procedure, or from a non-AI / ML-based procedure to an AI / ML-based procedure. Network entity 105-h can send LCM control signaling to UE 115-h to instruct UE 115 on configuration (e.g., reconfiguration). In some examples, network entity 105-h may execute LCM control signaling based on performance and event monitoring. Network entity 105-h may transmit LCM control signals to ML service 305-h or UE 115-h.

[0144] In some examples (e.g., at 1040), LCM may be controlled by ML service 305-h (e.g., based on UE monitoring reports, monitoring at network entity 105, or ML service monitoring). In such examples, ML service 305-h may evaluate ML service KPIs based on monitoring reports from UE 115-H and network entity 105. Therefore, at 1035, UE 115-h may transmit monitoring input data to network entity 105, which may forward the input data to ML service 305-h at 1040 (e.g., performance monitoring at the ML service). ML service 305-h may evaluate ML service KPIs based on monitoring input data (e.g., ground real-time data used to evaluate feedback KPIs at ML service 305-h).

[0145] In such an instance, the LCM control signaling for ML service 305-h can be performed as discussed with respect to 1020 and 1025, except that ML service 305-h forwards the LCM control signaling to network entity 105-h at 1045 (e.g., instead of network entity 105-h forwarding the LCM control signaling to ML service 305-h). Therefore, at 1050, network entity 105-h can forward the LCM control signaling to UE 115-h.

[0146] Figure 11A block diagram 1100 of a device 1105 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Device 1105 may be an example of aspects of network entity 105 as described herein. Device 1105 may include receiver 1110, transmitter 1115, and communication manager 1120. Device 1105, or one or more components of device 1105 (e.g., receiver 1110, transmitter 1115, and communication manager 1120), may include at least one processor that may be coupled to at least one memory to individually or jointly support or implement the described technologies. Each of these components may communicate with each other (e.g., via one or more buses).

[0147] Receiver 1110 may provide components for acquiring (e.g., receiving, determining, identifying) information (such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units)) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). The information may be delivered to other components of device 1105. In some examples, receiver 1110 may support acquiring information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1110 may support acquiring information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.

[0148] Transmitter 1115 may provide components for outputting (e.g., transmitting, providing, conveying, transmitting) information generated by other components of device 1105. For example, transmitter 1115 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, transmitter 1115 may support outputting information by transmitting signals via one or more antennas. Additionally or alternatively, transmitter 1115 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, transmitter 1115 and receiver 1110 may be co-located in a transceiver, which may include or be coupled to a modem.

[0149] The communication manager 1120, receiver 1110, transmitter 1115, or various combinations thereof, or various components thereof, may be examples of components used to perform various aspects of the cross-node AI / ML services as described herein. For example, the communication manager 1120, receiver 1110, transmitter 1115, or various combinations thereof, or components thereof, may be able to perform one or more of the functions described herein.

[0150] In some examples, the communication manager 1120, receiver 1110, transmitter 1115, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). The hardware may include at least one of a processor, DSP, CPU, ASIC, FPGA, or other programmable logic device, microcontroller, discrete gate or transistor logic device, discrete hardware component, or any combination thereof, configured as or otherwise individually or collectively to support components for performing the functions described herein. In some examples, at least one processor and at least one memory coupled to said at least one processor may be configured to perform one or more of the functions described herein (e.g., instructions stored in at least one memory are executed individually or collectively by one or more processors).

[0151] Additionally or alternatively, the communication manager 1120, receiver 1110, transmitter 1115, or various combinations or components thereof may be implemented in code executed by at least one processor (e.g., as communication management software or firmware). If implemented in code executed by at least one processor, the functionality of the communication manager 1120, receiver 1110, transmitter 1115, or various combinations or components thereof may be performed by any combination of a general-purpose processor, DSP, CPU, ASIC, FPGA, microcontroller, or these or other programmable logic devices (e.g., configured as or otherwise individually or collectively to support components for performing the functions described in this disclosure).

[0152] In some examples, the communication manager 1120 may be configured to use or otherwise cooperate with the receiver 1110, the transmitter 1115, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, the communication manager 1120 may receive information from the receiver 1110, transmit information to the transmitter 1115, or be integrated with the receiver 1110, the transmitter 1115, or both to acquire information, output information, or perform various other operations as described herein.

[0153] The communication manager 1120 may support wireless communication according to examples disclosed herein. For example, the communication manager 1120 may be capable of, configured to, or operable to support components for obtaining a first message indicating one or more machine learning capabilities of the UE. The communication manager 1120 may be capable of, configured to, or operable to support components for obtaining a second message indicating one or more machine learning service capabilities of the machine learning service from a machine learning service. The communication manager 1120 may be capable of, configured to, or operable to support components for outputting control messages to the UE indicating one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning functions of the UE for use with the machine learning service.

[0154] By including or configuring a communication manager 1120 according to an example as described herein, device 1105 (e.g., controlling receiver 1110, transmitter 1115, communication manager 1120, or a combination thereof, or at least one processor otherwise coupled thereto) can support techniques for updating UE 115 with an ML model that facilitates UE functioning as intended (e.g., above a performance threshold) and is compatible with ML service 305, for example, even when UE 115 does not have access to ML service 305 or does not communicate with ML service.

[0155] Figure 12 A block diagram 1200 of a device 1205 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Device 1205 may be an example of aspects of device 1105 or network entity 105 as described herein. Device 1205 may include receiver 1210, transmitter 1215, and communication manager 1220. Device 1205, or one or more components of device 1205 (e.g., receiver 1210, transmitter 1215, and communication manager 1220), may include at least one processor that may be coupled to at least one memory to support the described technologies. Each of these components may communicate with each other (e.g., via one or more buses).

[0156] Receiver 1210 may provide components for acquiring (e.g., receiving, determining, identifying) information (such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units)) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack). The information may be passed to other components of device 1205. In some examples, receiver 1210 may support acquiring information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1210 may support acquiring information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.

[0157] Transmitter 1215 may provide components for outputting (e.g., transmitting, providing, conveying, transmitting) information generated by other components of device 1205. For example, transmitter 1215 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, transmitter 1215 may support outputting information by transmitting signals via one or more antennas. Additionally or alternatively, transmitter 1215 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, transmitter 1215 and receiver 1210 may be co-located in a transceiver, which may include or be coupled to a modem.

[0158] Device 1205 or its various components may be examples of parts used to perform various aspects of the cross-node AI / ML services as described herein. For example, communication manager 1220 may include capability manager 1225, AI / ML configuration manager 1230, or any combination thereof. Communication manager 1220 may be examples of aspects of communication manager 1120 as described herein. In some examples, communication manager 1220 or its various components may be configured to use or otherwise cooperate with receiver 1210, transmitter 1215, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, communication manager 1220 may receive information from receiver 1210, transmit information to transmitter 1215, or integrate with receiver 1210, transmitter 1215, or both to acquire information, output information, or perform various other operations as described herein.

[0159] Communication Manager 1220 may support wireless communication according to examples disclosed herein. Capability Manager 1225 is capable of, configured to, or operable to support components for obtaining a first message indicating one or more machine learning capabilities of the UE. Capability Manager 1225 is capable of, configured to, or operable to support components for obtaining a second message indicating one or more machine learning service capabilities of the machine learning service from the machine learning service. AI / ML Configuration Manager 1230 is capable of, configured to, or operable to support components for outputting control messages to the UE indicating one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning functions of the UE for use with the machine learning service.

[0160] Figure 13 A block diagram 1300 is shown of a communication manager 1320 supporting cross-node AI / ML services according to one or more aspects of this disclosure. The communication manager 1320 may be an example of a communication manager 1120, a communication manager 1220, or aspects thereof as described herein. The communication manager 1320 or its various components may be examples of parts for performing various aspects of the cross-node AI / ML services as described herein. For example, the communication manager 1320 may include a capability manager 1325, an AI / ML configuration manager 1330, an AI / ML function manager 1335, an inference data manager 1340, a monitoring report manager 1345, an LCM manager 1350, an AI / ML activation manager 1355, a monitoring trigger condition manager 1360, or any combination thereof. These components, or each of their components or sub-components (e.g., one or more processors, one or more memories), may communicate directly or indirectly with each other (e.g., via one or more buses), and such communication may include communication within protocol layers of the protocol stack, communication associated with logical channels of the protocol stack (e.g., between protocol layers of the protocol stack, within devices, components, or virtualization components associated with network entity 105, between devices, components, or virtualization components associated with network entity 105), or any combination thereof.

[0161] Communication Manager 1320 may support wireless communication according to examples disclosed herein. Capability Manager 1325 is capable of, configured to, or operable to support components for obtaining a first message indicating one or more machine learning capabilities of the UE. In some examples, Capability Manager 1325 is capable of, configured to, or operable to support components for obtaining a second message indicating one or more machine learning service capabilities of the machine learning service from a machine learning service. AI / ML Configuration Manager 1330 is capable of, configured to, or operable to support components for outputting control messages to the UE indicating one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning functions of the UE for use with the machine learning service.

[0162] In some examples, the capability manager 1325 is capable of, configured to, or operable to support components for outputting service capability request messages for one or more machine learning service capabilities to a machine learning service, wherein a second message indicating the one or more machine learning service capabilities is obtained in response to the service capability request message, and wherein the one or more machine learning service capabilities include capabilities compatible with the UE based on the one or more machine learning capabilities of the UE.

[0163] In some examples, the service capability request message contains a set of UE identifiers, including the UE's identifier, an indication of one or more machine learning capabilities of the UE, or any combination thereof.

[0164] In some examples, in order to support obtaining a second message indicating one or more machine learning service capabilities, the capability manager 1325 is capable, configured, or operable to support components for announcing an announcement for obtaining one or more machine learning service capabilities from a machine learning service, the announcement including the second message.

[0165] In some examples, the AI / ML Function Manager 1335 is capable of, configured to, or operable to support components for selecting one or more machine learning functions based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service. In some examples, the AI / ML Configuration Manager 1330 is capable of, configured to, or operable to support components for outputting configuration request messages to the machine learning service requesting one or more cross-node machine learning configurations based on selection. In some examples, the AI / ML Configuration Manager 1330 is capable of, configured to, or operable to support components for obtaining configuration response messages from the machine learning service, the configuration response messages indicating one or more cross-node machine learning configurations, one or more machine learning functions, a set of UE identifiers including the UE's identifier, or any combination thereof, wherein control messages indicating one or more cross-node machine learning configurations are based on obtaining the configuration response messages.

[0166] In some examples, the AI / ML configuration manager 1330 is capable of, configured to, or able to operate to support components for obtaining a third message in response to a control message, indicating that the UE has completed one or more cross-node machine learning configurations.

[0167] In some examples, the AI / ML configuration manager 1330 is capable of, configured to, or able to operate to support components for outputting a fourth message to the machine learning service, indicating that one or more cross-node machine learning configurations have been configured by the UE.

[0168] In some examples, the AI / ML function manager 1335 is capable of, configured to, or operable to support components for outputting a second control message, which includes an indication to activate one or more machine learning functions based on one or more cross-node machine learning configurations.

[0169] In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for outputting an activation request message to a machine learning service, the activation request message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof. In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for obtaining an activation confirmation message from a machine learning service in response to the activation request message, the activation confirmation message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof, wherein a second control message is output based on the activation confirmation message.

[0170] In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for obtaining an activation request message from a machine learning service, the activation request message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof. In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for outputting an activation confirmation message from a machine learning service in response to the activation request message, the activation confirmation message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof, wherein a second control message is output based on the activation confirmation message.

[0171] In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for obtaining a first activation request message from the UE indicating one or more machine learning functions. In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for outputting a second activation request message to a machine learning service in response to the first activation request message, the second activation request message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof. In some examples, the AI / ML activation manager 1355 is capable of, configured to, or operable to support components for obtaining an activation confirmation message from a machine learning service in response to the second activation request message, the activation confirmation message indicating a set of UE identifiers including the UE's identifier, one or more machine learning functions, or any combination thereof, wherein the second control message is output based on the activation confirmation message.

[0172] In some examples, the inference data manager 1340 is capable of, configured to, or operable to support components for obtaining a sixth message that includes UE inference input data associated with one or more machine learning functions. In some examples, the inference data manager 1340 is capable of, configured to, or operable to support components for outputting a service data request message including UE inference input data to a machine learning service. In some examples, the inference data manager 1340 is capable of, configured to, or operable to support components for obtaining a service data response message from a machine learning service that indicates machine learning service inference output data associated with one or more machine learning functions.

[0173] In some examples, the inference data manager 1340 is capable of, configured to, or able to operate to support components for outputting a seventh message to the UE, including machine learning service inference output data from the machine learning service.

[0174] In some examples, the Trigger Condition Monitoring Manager 1360 is capable of, configured to, or operable to support components for monitoring one or more trigger conditions based on UE-inferred input data, machine learning service-inferred input data from a machine learning service, or any combination thereof. In some examples, the AI / ML Function Manager 1335 is capable of, configured to, or operable to support components for outputting a third control message to the UE based on the occurrence of one or more trigger conditions, the third control message including an indication to switch or disable at least one of one or more machine learning functions.

[0175] In some examples, the one or more triggering conditions include the measurement of one or more key performance indicators that meet the key performance indicator threshold.

[0176] In some examples, the monitoring report manager 1345 is capable of, configured to, or operable to support components for outputting monitoring reports to the machine learning service that indicate one or more key performance indicators associated with one or more machine learning functions.

[0177] In some examples, the one or more triggering conditions are based on monitoring reports that include measurements performed by the UE, by network entities, or any combination thereof.

[0178] In some examples, the monitoring report manager 1345 is capable of, configured to, or operable to support components for obtaining monitoring reports from the UE, which include one or more key performance indicators associated with one or more machine learning functions. In some examples, the AI / ML function manager 1335 is capable of, configured to, or operable to support components for outputting instructions to the UE to switch or disable one or more machine learning functions of the UE based on the occurrence of one or more trigger conditions.

[0179] In some examples, the monitoring report manager 1345 is capable of, configured to, or operable to support components for outputting monitoring reports to the machine learning service that indicate one or more key performance indicators associated with one or more machine learning functions.

[0180] In some examples, the LCM manager 1350 is capable of, configured to, or operable to support components for obtaining a lifecycle management control request message from the UE, including a request for lifecycle management control signaling, which includes indications for activating, deactivating, or switching default configurations in one or more cross-node machine learning configurations, or any combination thereof. In some examples, the LCM manager 1350 is capable of, configured to, or operable to support components for outputting a first lifecycle management control message to a machine learning service in response to a lifecycle management control request message, which includes indications for a request for lifecycle management control signaling. In some examples, the LCM manager 1350 is capable of, configured to, or operable to support components for outputting a second lifecycle management control message to the UE, which includes indications for lifecycle management control signaling indicated by the machine learning service.

[0181] In some examples, lifecycle management control request messages are obtained based on monitoring reports from the UE, network entities, or a combination thereof.

[0182] Figure 14 A diagram of a system 1400 including device 1405 supporting cross-node AI / ML services, according to one or more aspects of this disclosure, is shown. Device 1405 may be an example of device 1105, device 1205, or network entity 105 as described herein, or may include components thereof. Device 1405 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, and such communication may include communication via one or more wired interfaces, one or more wireless interfaces, or any combination thereof. Device 1405 may include components that support output and enable communication, such as a communication manager 1420, a transceiver 1410, an antenna 1415, at least one memory 1425, code 1430, and at least one processor 1435. These components may communicate electronically or otherwise (e.g., operative ground, communicative ground, functional ground, electronic ground, electrical ground) via one or more buses (e.g., bus 1440).

[0183] Transceiver 1410 may support bidirectional communication via a wired link, a wireless link, or both, as described herein. In some examples, transceiver 1410 may include a wired transceiver and be capable of bidirectional communication with another wired transceiver. Additionally or alternatively, in some examples, transceiver 1410 may include a wireless transceiver and be capable of bidirectional communication with another wireless transceiver. In some examples, device 1405 may include one or more antennas 1415 that are capable of transmitting or receiving wireless transmissions (e.g., concurrently). Transceiver 1410 may also include a modem for: modulating a signal; providing the modulated signal for transmission (e.g., via one or more antennas 1415, via a wired transmitter); receiving the modulated signal (e.g., from one or more antennas 1415, from a wired receiver); and demodulating the signal. In some embodiments, transceiver 1410 may include one or more interfaces, such as one or more interfaces coupled to one or more antennas 1415 configured to support various receive or acquire operations, or one or more interfaces coupled to one or more antennas 1415 configured to support various transmit or output operations, or combinations thereof. In some embodiments, transceiver 1410 may include one or more processors or one or more memory components or configured to be coupled to such processors or memory components, which are operable to perform or support operations based on received or acquired information or signals, or to generate information or other signals for transmission or other output, or any combination thereof. In some embodiments, transceiver 1410, or transceiver 1410 and one or more antennas 1415, or transceiver 1410 and one or more antennas 1415 and one or more processors or one or more memory components (e.g., at least one processor 1435, at least one memory 1425, or both) may be included in a chip or chip assembly mounted in device 1405. In some examples, transceiver 1410 may be able to operate 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).

[0184] At least one memory 1425 may include RAM, ROM, or any combination thereof. At least one memory 1425 may store computer-readable, computer-executable code 1430 including instructions that, when executed by one or more processors of at least one processor 1435, cause device 1405 to perform the various functions described herein. Code 1430 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1430 may not be directly executable by one of the at least one processor 1435, but may enable a computer (e.g., when compiled and executed) to perform the functions described herein. In some cases, at least one memory 1425 may also include a BIOS, among other things, that controls basic hardware or software operation, such as interaction with peripheral components or devices. In some examples, at least one processor 1435 may include multiple processors, and at least one memory 1425 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, which may be configured individually or collectively to perform the various functions described herein (e.g., as part of a processing system).

[0185] At least one processor 1435 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, ASICs, CPUs, FPGAs, microcontrollers, programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any combination thereof). In some cases, at least one processor 1435 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into one or more processors in at least one processor 1435. At least one processor 1435 may be configured to execute computer-readable instructions stored in memory (e.g., one or more memories in at least one memory 1425) to cause device 1405 to perform various functions (e.g., functions or tasks supporting cross-node AI / ML services). For example, device 1405 or components of device 1405 may include at least one processor 1435 and at least one memory 1425 coupled to one or more processors in at least one processor 1435, wherein at least one processor 1435 and at least one memory 1425 are configured to perform the various functions described herein. At least one processor 1435 may be an example of a cloud computing platform (e.g., one or more physical nodes and supporting software such as an operating system, virtual machine, or container instance) that can (e.g., by executing code 1430) host functions for performing the functions of device 1405. At least one processor 1435 may be any one or more suitable processors capable of executing scripts or instructions of one or more software programs stored in device 1405 (such as within one or more memories of at least one memory 1425). In some examples, at least one processor 1435 may include multiple processors, and at least one memory 1425 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, which may be configured individually or collectively to perform the various functions described herein. In some examples, at least one processor 1435 may be a component of a processing system, which may refer to a system of machines (such as a series of machines), circuits (including, for example, one or both of processor circuitry (which may include at least one processor 1435) and memory circuitry (which may include at least one memory 1425)) or components that receive or acquire input and process the input to produce, generate, or acquire a set of outputs. The processing system may be configured to perform one or more of the functions described herein. Therefore, at least one processor 1435 or a processing system including at least one processor 1435 may be configured, can be configured, or can be operated to cause the device 1405 to perform one or more of the functions described herein.Furthermore, as described herein, “configured to,” “capable of being configured to,” and “capable of operating to” are used interchangeably and may be associated with the ability to perform one or more of the functions described herein when executing code stored in at least one memory 1425 or otherwise.

[0186] In some examples, bus 1440 may support communication at the protocol layer of the protocol stack (e.g., within a protocol layer). In some examples, bus 1440 may support communication associated with logical channels of the protocol stack (e.g., between protocol layers of the protocol stack), which may include communication performed within components of device 1405, or communication performed between different components of device 1405 that are co-addressable or may be located in different locations (e.g., where device 1405 may refer to a system in which one or more processors of communication manager 1420, transceiver 1410, at least one memory 1425, code 1430, and at least one processor 1435 may be located in one of the different components or partitioned between the different components).

[0187] In some examples, the communication manager 1420 can manage (e.g., via one or more wired or wireless backhaul links) various aspects of communication with the core network 130. For example, the communication manager 1420 can manage the delivery of data communications by client devices, such as one or more UEs 115. In some examples, the communication manager 1420 can manage communication with other network entities 105 and may include a controller or scheduler for cooperating with other network entities 105 to control communication with UE 115. In some examples, the communication manager 1420 may support an X2 interface within LTE / LTE-A wireless communication network technology to provide communication between network entities 105.

[0188] The communication manager 1420 may support wireless communication according to examples disclosed herein. For example, the communication manager 1420 may be capable of, configured to, or operable to support components for obtaining a first message indicating one or more machine learning capabilities of the UE. The communication manager 1420 may be capable of, configured to, or operable to support components for obtaining a second message indicating one or more machine learning service capabilities of the machine learning service from a machine learning service. The communication manager 1420 may be capable of, configured to, or operable to support components for outputting control messages to the UE indicating one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning functions of the UE for use with the machine learning service.

[0189] By including or configuring a communication manager 1420 according to an example as described herein, device 1405 may support a technology for updating UE 115 with an ML model that enables the UE to perform functions as expected (e.g., above a performance threshold) and is compatible with ML service 305, for example, even when UE 115 does not have access to ML service 305 or does not communicate with ML service 305.

[0190] In some examples, the communication manager 1420 may be configured to use or otherwise coordinate with the transceiver 1410, one or more antennas 1415 (e.g., where applicable), or any combination thereof to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). Although the communication manager 1420 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1420 may be supported or performed by the transceiver 1410, one or more processors in at least one processor 1435, one or more memories in at least one memory 1425, code 1430, or any combination thereof (e.g., by a processing system including at least a portion of at least one processor 1435, at least one memory 1425, code 1430, or any combination thereof). For example, code 1430 may include instructions that can be executed by one or more processors in at least one processor 1435 to cause the device 1405 to perform various aspects of the cross-node AI / ML services as described herein, or at least one processor 1435 and at least one memory 1425 may be otherwise configured to perform or support such operations individually or jointly.

[0191] Figure 15 A block diagram 1500 of a device 1505 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Device 1505 may be an example of aspects of a UE 115 as described herein. Device 1505 may include a receiver 1510, a transmitter 1515, and a communication manager 1520. Device 1505, or one or more components of device 1505 (e.g., receiver 1510, transmitter 1515, and communication manager 1520), may include at least one processor that may be coupled to at least one memory to individually or jointly support or implement the described technologies. Each of these components may communicate with each other (e.g., via one or more buses).

[0192] Receiver 1510 may provide components for receiving information such as packets associated with various information channels (e.g., control channels, data channels, information channels related to cross-node AI / ML services), user data, control information, or any combination thereof). The information may be passed to other components of device 1505. Receiver 1510 may utilize a single antenna or a collection of antennas.

[0193] Transmitter 1515 may provide components for transmitting signals generated by other components of device 1505. For example, transmitter 1515 may transmit information such as packets associated with various information channels (e.g., control channels, data channels, information channels related to cross-node AI / ML services), user data, control information, or any combination thereof. In some examples, transmitter 1515 may be co-located with receiver 1510 in a transceiver module. Transmitter 1515 may utilize a single antenna or a collection of multiple antennas.

[0194] The communication manager 1520, receiver 1510, transmitter 1515, or various combinations thereof, or various components thereof, may be examples of components used to perform various aspects of the cross-node AI / ML services as described herein. For example, the communication manager 1520, receiver 1510, transmitter 1515, or various combinations thereof, or components thereof, may be able to perform one or more of the functions described herein.

[0195] In some examples, the communication manager 1520, receiver 1510, transmitter 1515, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). The hardware may include at least one of the following: a processor, digital signal processor (DSP), central processing unit (CPU), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, microcontroller, discrete gate or transistor logic device, discrete hardware component, or any combination thereof, configured as or otherwise individually or collectively to support components for performing the functions described herein. In some examples, at least one processor and at least one memory coupled to said at least one processor may be configured to perform one or more of the functions described herein (e.g., instructions stored in at least one memory are executed individually or collectively by one or more processors).

[0196] Additionally or alternatively, the communication manager 1520, receiver 1510, transmitter 1515, or various combinations or components thereof may be implemented in code executed by at least one processor (e.g., as communication management software or firmware). If implemented in code executed by at least one processor, the functionality of the communication manager 1520, receiver 1510, transmitter 1515, or various combinations or components thereof may be performed by any combination of a general-purpose processor, DSP, CPU, ASIC, FPGA, microcontroller, or these or other programmable logic devices (e.g., configured as or otherwise individually or collectively to support components for performing the functions described in this disclosure).

[0197] In some examples, the communication manager 1520 may be configured to use or otherwise cooperate with the receiver 1510, the transmitter 1515, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, the communication manager 1520 may receive information from the receiver 1510, transmit information to the transmitter 1515, or be integrated with the receiver 1510, the transmitter 1515, or both to acquire information, output information, or perform various other operations as described herein.

[0198] The communication manager 1520 may support wireless communication according to examples disclosed herein. For example, the communication manager 1520 may be capable of, configured to, or operable to support components for receiving a first message indicating one or more lifecycle management trigger conditions for a channel between the UE and a network entity. The communication manager 1520 may be capable of, configured to, or operable to support components for sending a lifecycle management control request message to a network entity in response to the occurrence of one or more lifecycle management trigger conditions, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. The communication manager 1520 may be capable of, configured to, or operable to support components for receiving a second message indicating lifecycle management control signaling from a network entity in response to the lifecycle management control request message.

[0199] By including or configuring a communication manager 1520 according to an example as described herein, device 1505 (e.g., controlling receiver 1510, transmitter 1515, communication manager 1520, or a combination thereof, or at least one processor otherwise coupled thereto) can support techniques for updating UE 115 with an ML model that facilitates UE functioning as intended (e.g., above a performance threshold) and is compatible with ML service 305, for example, even when UE 115 does not have access to ML service 305 or does not communicate with ML service.

[0200] Figure 16 A block diagram 1600 of a device 1605 supporting cross-node AI / ML services according to one or more aspects of this disclosure is shown. Device 1605 may be an example of aspects of device 1505 or UE 115 as described herein. Device 1605 may include a receiver 1610, a transmitter 1615, and a communication manager 1620. Device 1605, or one or more components of device 1605 (e.g., receiver 1610, transmitter 1615, and communication manager 1620), may include at least one processor that may be coupled to at least one memory to support the described technologies. Each of these components may communicate with each other (e.g., via one or more buses).

[0201] Receiver 1610 may provide components for receiving information such as packets associated with various information channels (e.g., control channels, data channels, information channels related to cross-node AI / ML services), user data, control information, or any combination thereof. The information may be passed to other components of device 1605. Receiver 1610 may utilize a single antenna or a collection of antennas.

[0202] Transmitter 1615 may provide components for transmitting signals generated by other components of device 1605. For example, transmitter 1615 may transmit information such as packets associated with various information channels (e.g., control channels, data channels, information channels related to cross-node AI / ML services), user data, control information, or any combination thereof. In some examples, transmitter 1615 may be co-located with receiver 1610 in a transceiver module. Transmitter 1615 may utilize a single antenna or a collection of multiple antennas.

[0203] Device 1605 or its various components may be examples of parts for performing various aspects of the cross-node AI / ML services as described herein. For example, communication manager 1620 may include LCM control component 1625, LCM control request component 1630, or any combination thereof. Communication manager 1620 may be examples of aspects of communication manager 1520 as described herein. In some examples, communication manager 1620 or its various components may be configured to use or otherwise cooperate with receiver 1610, transmitter 1615, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, communication manager 1620 may receive information from receiver 1610, transmit information to transmitter 1615, or be integrated in combination with receiver 1610, transmitter 1615, or both to acquire information, output information, or perform various other operations as described herein.

[0204] The communication manager 1620 may support wireless communication according to examples disclosed herein. The LCM control component 1625 is capable of, configured to, or operable to support components for receiving a first message indicating one or more lifecycle management trigger conditions for a channel between the UE and a network entity. The LCM control request component 1630 is capable of, configured to, or operable to support components for sending a lifecycle management control request message to a network entity in response to the occurrence of one or more lifecycle management trigger conditions, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, or switching default configurations or any combination thereof in one or more cross-node machine learning configurations for the UE. The LCM control component 1625 is capable of, configured to, or operable to support components for receiving a second message indicating lifecycle management control signaling from a network entity in response to the LCM control request message.

[0205] Figure 17 A block diagram 1700 is shown of a communication manager 1720 supporting cross-node AI / ML services according to one or more aspects of this disclosure. The communication manager 1720 may be an example of a communication manager 1520, a communication manager 1620, or aspects thereof as described herein. The communication manager 1720 or its various components may be examples of parts for performing various aspects of the cross-node AI / ML services as described herein. For example, the communication manager 1720 may include an LCM control component 1725, an LCM control request component 1730, a monitor reporting component 1735, or any combination thereof. Each of these components, or its components or sub-components (e.g., one or more processors, one or more memories), may communicate directly or indirectly with each other (e.g., via one or more buses).

[0206] The communication manager 1720 may support wireless communication according to examples disclosed herein. The LCM control component 1725 is capable of, configured to, or operable to support components for receiving a first message indicating one or more LCM trigger conditions for a channel between the UE and a network entity. The LCM control request component 1730 is capable of, configured to, or operable to support components for sending an LCM control request message to a network entity in response to the occurrence of one or more LCM trigger conditions, including a request for LCM control signaling, wherein the LCM control signaling includes indications for activating, deactivating, switching default configurations or any combination thereof in one or more cross-node machine learning configurations for the UE. In some examples, the LCM control component 1725 is capable of, configured to, or operable to support components for receiving a second message indicating LCM control signaling from a network entity in response to an LCM control request message.

[0207] In some examples, the monitor reporting component 1735 is capable of, configured to, or able to operate to support components for sending monitoring reports to network entities that indicate one or more key performance indicators associated with the UE, wherein a second message indicating LCM control signaling is received based on the monitoring report.

[0208] In some examples, one or more LCM triggering conditions include one or more thresholds associated with the inferred performance of the UE, one or more key performance indicators associated with the UE, or a combination thereof.

[0209] Figure 18 A diagram of a system 1800 including a device 1805 supporting cross-node AI / ML services, according to one or more aspects of this disclosure, is shown. Device 1805 may be an example of device 1505, device 1605, or UE 115 as described herein, or may include components thereof. Device 1805 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof (e.g., wirelessly). Device 1805 may include components for bidirectional voice and data communication, including components for transmitting and receiving communications, such as a communication manager 1820, an input / output (I / O) controller 1810, a transceiver 1815, an antenna 1825, at least one memory 1830, code 1835, and at least one processor 1840. These components may communicate electronically or be coupled in other ways (e.g., operational ground, communication ground, functional ground, electronic ground, electrical ground) via one or more buses (e.g., bus 1845).

[0210] I / O controller 1810 manages the input and output signals of device 1805. I / O controller 1810 can also manage peripheral devices not integrated into device 1805. In some cases, I / O controller 1810 may represent a physical connection or port to an external peripheral device. In some cases, I / O controller 1810 may utilize an operating system such as iOS. ® ANDROID ® MS-DOS ® MS-WINDOWS ® OS / 2 ® UNIX ® LINUX ®Alternatively, the I / O controller 1810 may represent or interact with a modem, keyboard, mouse, touchscreen, or similar device. In some cases, the I / O controller 1810 may be implemented as part of one or more processors, such as at least one processor 1840. In some cases, a user may interact with the device 1805 via the I / O controller 1810 or via hardware components controlled by the I / O controller 1810.

[0211] In some cases, device 1805 may include a single antenna 1825. However, in other cases, device 1805 may have more than one antenna 1825, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. Transceiver 1815 may communicate bidirectionally via one or more antennas 1825 as described herein, or via a wired or wireless link. For example, transceiver 1815 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Transceiver 1815 may also include a modem for: modulating packets; providing the modulated packets to one or more antennas 1825 for transmission; and demodulating packets received from one or more antennas 1825. Transceiver 1815, or transceiver 1815 and one or more antennas 1825, may be an example of transmitter 1515, transmitter 1615, receiver 1510, receiver 1610, or any combination thereof or components thereof as described herein.

[0212] At least one memory 1830 may include random access memory (RAM) and read-only memory (ROM). At least one memory 1830 may store computer-readable, computer-executable code 1835, including instructions that, when executed by at least one processor 1840, cause device 1805 to perform the various functions described herein. Code 1835 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1835 may not be directly executable by at least one processor 1840, but may enable a computer (e.g., when compiled and executed) to perform the functions described herein. In some cases, among other things, at least one memory 1830 may also include a basic I / O system (BIOS) that controls basic hardware or software operations, such as interaction with peripheral components or devices.

[0213] At least one processor 1840 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, at least one processor 1840 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into at least one processor 1840. At least one processor 1840 may be configured to execute computer-readable instructions stored in memory (e.g., at least one memory 1830) to cause device 1805 to perform various functions (e.g., functions or tasks supporting cross-node AI / ML services). For example, device 1805 or components of device 1805 may include at least one processor 1840 and at least one memory 1830 coupled to or coupled to at least one processor 1840, wherein at least one processor 1840 and at least one memory 1830 are configured to perform the various functions described herein. In some examples, at least one processor 1840 may include multiple processors, and at least one memory 1830 may include multiple memories. One or more of a plurality of processors may be coupled to one or more of a plurality of memories, which may be configured individually or collectively to perform the various functions described herein. In some examples, at least one processor 1840 may be a component of a processing system, which may refer to a machine (such as a series of machines), circuitry (including, for example, one or both of processor circuitry (which may include at least one processor 1840) and memory circuitry (which may include at least one memory 1830)) or system of components that receive or receive input and process the input to produce, generate or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. Thus, at least one processor 1840 or a processing system including at least one processor 1840 may be configured, capable of being configured, or operable to cause device 1805 to perform one or more of the functions described herein. Furthermore, as described herein, “configured to,” “capable of being configured,” and “operable to” are used interchangeably and may be associated with the ability to perform one or more of the functions described herein when executing code stored in at least one memory 1830 or otherwise.

[0214] The communication manager 1820 may support wireless communication according to examples disclosed herein. For example, the communication manager 1820 may be capable of, configured to, or operable to support components for receiving a first message indicating one or more LCM trigger conditions for a channel between the UE and a network entity. The communication manager 1820 may be capable of, configured to, or operable to support components for sending an LCM control request message to a network entity in response to the occurrence of one or more LCM trigger conditions, including a request for LCM control signaling, wherein the LCM control signaling includes indications for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. The communication manager 1820 may be capable of, configured to, or operable to support components for receiving a second message indicating LCM control signaling from a network entity in response to the LCM control request message.

[0215] By including or configuring a communication manager 1820 according to an example as described herein, device 1805 can support a technology for updating UE 115 with an ML model that enables the UE to perform functions as expected (e.g., above a performance threshold) and is compatible with ML service 305, for example, even when UE 115 does not have access to ML service 305 or does not communicate with ML service.

[0216] In some examples, the communication manager 1820 may be configured to perform various operations (e.g., receiving, monitoring, transmitting) using a transceiver 1815, one or more antennas 1825, or any combination thereof, or otherwise cooperating with them. Although the communication manager 1820 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1820 may be supported by or executed by at least one processor 1840, at least one memory 1830, code 1835, or any combination thereof. For example, code 1835 may include instructions that can be executed by at least one processor 1840 to cause device 1805 to perform various aspects of the cross-node AI / ML services as described herein, or at least one processor 1840 and at least one memory 1830 may be otherwise configured to perform or support such operations individually or jointly.

[0217] Figure 19 A flowchart illustrating a method 1900 supporting cross-node AI / ML services according to various aspects of this disclosure is shown. The operation of method 1900 can be implemented by a network entity or its components as described herein. For example, the operation of method 1900 can be implemented by, as referenced... Figures 1 to 18The network entity described is used to perform this function. In some examples, the network entity may execute a set of instructions to control the functional elements of the network entity to perform the described function. Additionally or alternatively, the network entity may use dedicated hardware to perform aspects of the described function.

[0218] At point 1905, the method may include: obtaining a first message indicating one or more machine learning capabilities of the UE. The operation at point 1905 may be performed according to examples disclosed herein. In some examples, aspects of the operation at point 1905 may be derived from references... Figure 12 The described capability manager 25 is used to execute this.

[0219] At point 1910, the method may include obtaining a second message from the machine learning service indicative of one or more machine learning service capabilities of the machine learning service. The operation of point 1910 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of point 1910 may be derived from references... Figure 12 The described capability manager 25 is used to execute this.

[0220] At point 1915, the method may include: outputting a control message to the UE indicative of one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the machine learning service. Operation of point 1915 may be performed according to examples as disclosed herein. In some examples, aspects of operation of point 1915 may be derived from references... Figure 12 The AI / ML configuration manager 30 described is used to execute this.

[0221] Figure 20 A flowchart illustrating a method 2000 supporting cross-node AI / ML services according to various aspects of this disclosure is shown. The operation of method 2000 can be implemented by a network entity or its components as described herein. For example, the operation of method 2000 can be implemented by, as referenced... Figures 1 to 18 The network entity described is used to perform this function. In some examples, the network entity may execute a set of instructions to control the functional elements of the network entity to perform the described function. Additionally or alternatively, the network entity may use dedicated hardware to perform aspects of the described function.

[0222] At 2005, the method may include: outputting a service capability request message for one or more machine learning service capabilities to a machine learning service, wherein a second message indicating the one or more machine learning service capabilities is obtained in response to the service capability request message, and wherein the one or more machine learning service capabilities include capabilities compatible with the UE based on the one or more machine learning capabilities of the UE. Operation of 2005 may be performed according to the examples disclosed herein. In some examples, aspects of operation of 2005 may be provided by reference to [reference needed]. Figure 12 The AI / ML configuration manager 30 described is used to execute this.

[0223] At point 2010, the method may include: obtaining a first message indicating one or more machine learning capabilities of the UE. The operation of 2010 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 2010 may be derived from references... Figure 12 The described capability manager 25 is used to execute this.

[0224] At 2015, the method may include obtaining a second message from a machine learning service indicative of one or more machine learning service capabilities of the machine learning service. The operation of 2015 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 2015 may be derived from references... Figure 12 The described capability manager 25 is used to execute this.

[0225] At 2020, the method may include: outputting a control message to the UE instructing one or more cross-node machine learning configurations based on one or more machine learning capabilities of the UE and one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure the one or more machine learning capabilities of the UE for use with the machine learning service. Operation of 2020 may be performed according to the examples disclosed herein. In some examples, aspects of operation of 2020 may be provided by reference to [reference]. Figure 12 The AI / ML configuration manager 30 described is used to execute this.

[0226] Figure 21 A flowchart illustrating a method 2100 for supporting cross-node AI / ML services according to various aspects of this disclosure is shown. Operation of method 2100 may be implemented by a UE or its components as described herein. For example, operation of method 2100 may be performed by, as referenced... Figures 1 to 18 The UE 115 described herein is used to perform this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0227] At 2105, the method may include: receiving a first message indicating one or more LCM triggering conditions for a channel between the UE and a network entity. Operation of 2105 may be performed according to examples as disclosed herein. In some examples, aspects of operation of 2105 may be provided by reference to... Figure 16 The LCM control component 25 described herein is used to perform this action.

[0228] At 2110, the method may include: sending an LCM control request message to a network entity in response to the occurrence of one or more LCM triggering conditions, including a request for LCM control signaling, wherein the LCM control signaling includes an indication for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. The operation of 2110 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 2110 may be provided by reference to [reference]. Figure 16 The LCM control request component 30 described herein is used to execute the request.

[0229] At 2115, the method may include: receiving a second message indicating LCM control signaling from a network entity in response to an LCM control request message. The operation of 2115 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 2115 may be provided by reference to... Figure 16 The LCM control component 25 described herein is used to perform this action.

[0230] Figure 22 A flowchart illustrating a method 2200 for supporting cross-node AI / ML services according to various aspects of this disclosure is shown. Operation of method 2200 may be implemented by a UE or its components as described herein. For example, operation of method 2200 may be performed by, as referenced... Figures 1 to 18 The UE 115 described herein is used to perform this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0231] At 2205, the method may include: receiving a first message indicating one or more LCM triggering conditions for a channel between the UE and a network entity. Operation of 2205 may be performed according to examples as disclosed herein. In some examples, aspects of operation of 2205 may be provided by reference to... Figure 17 The LCM control component 25 described herein is used to perform this action.

[0232] At 2210, the method may include: sending an LCM control request message to a network entity in response to the occurrence of one or more LCM triggering conditions, including a request for LCM control signaling, wherein the LCM control signaling includes an indication for activating, deactivating, or switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. The operation of 2210 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 2210 may be provided by reference to [reference]. Figure 17 The LCM control request component 30 described herein is used to execute the request.

[0233] At 2215, the method may include sending a monitoring report to a network entity indicating one or more key performance indicators associated with the UE. Operation of 2215 may be performed according to the examples disclosed herein. In some examples, aspects of operation of 2215 may be derived from references... Figure 17 The monitor reporting component 35 described herein is used to perform this action.

[0234] At 2220, the method may include receiving a second message indicating LCM control signaling from a network entity in response to an LCM control request message, wherein receiving the second message indicating LCM control signaling is based on a monitoring report. The operation of 2220 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 2220 may be provided by reference to [reference needed]. Figure 17 The LCM control component 25 described herein is used to perform this action.

[0235] The following provides an overview of the various aspects of this disclosure:

[0236] Aspect 1: A method for wireless communication at a network entity, the method comprising: obtaining a first message indicating one or more machine learning capabilities of a UE; obtaining a second message indicating one or more ML service capabilities of the ML service from an ML service; and outputting a control message to the UE indicating one or more cross-node machine learning configurations based at least in part on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service, wherein the one or more cross-node machine learning configurations configure one or more machine learning functions of the UE for use with the ML service.

[0237] Aspect 2: According to the method of aspect 1, the method further includes: outputting a service capability request message for the one or more ML service capabilities to the ML service, wherein the second message indicating the one or more ML service capabilities is obtained in response to the service capability request message, and wherein the one or more ML service capabilities include capabilities that are at least partially compatible with the UE based on the one or more machine learning capabilities of the UE.

[0238] Aspect 3: According to the method of aspect 2, the service capability request message includes a set of UE identifiers including the identifier of the UE, an indication of the one or more machine learning capabilities of the UE, or any combination thereof.

[0239] Aspect 4: The method according to any one of Aspects 1 to 3, wherein obtaining the second message indicating the one or more ML service capabilities comprises: an announcement of obtaining the one or more ML service capabilities from the ML service, the announcement comprising the second message.

[0240] Aspect 5: The method according to any one of Aspects 1 to 4, the method further comprising: selecting one or more machine learning functions at least in part based on the one or more machine learning capabilities of the UE and the one or more ML service capabilities of the ML service; outputting a configuration request message requesting one or more cross-node machine learning configurations to the ML service at least in part based on the selection; and obtaining a configuration response message from the ML service, the configuration response message indicating the one or more cross-node machine learning configurations, the one or more machine learning functions, a set of UE identifiers including the identifier of the UE, or any combination thereof, wherein the control message indicating one or more cross-node machine learning configurations is at least in part based on obtaining the configuration response message.

[0241] Aspect 6: The method according to any one of Aspects 1 to 5, the method further comprising: in response to the control message, obtaining a third message indicating that the UE completes the one or more cross-node machine learning configurations.

[0242] Aspect 7: According to the method of aspect 6, the method further includes: outputting a fourth message to the ML service indicating that the one or more cross-node machine learning configurations have been configured by the UE.

[0243] Aspect 8: The method according to any one of Aspects 1 to 7, the method further comprising: outputting a second control message at least in part based on the one or more cross-node machine learning configurations, the second control message including an indication to activate the one or more machine learning functions.

[0244] Aspect 9: The method according to aspect 8, the method further comprising: outputting an activation request message to the ML service, the activation request message indicating a set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof; and in response to the activation request message, obtaining an activation confirmation message from the ML service, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

[0245] Aspect 10: The method according to any one of Aspects 8 to 9, the method further comprising: obtaining an activation request message from the ML service, the activation request message indicating a set of UE identifiers including an identifier of the UE, the one or more machine learning functions, or any combination thereof; and outputting an activation confirmation message from the ML service to the ML service in response to the activation request message, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

[0246] Aspect 11: The method according to any one of Aspects 8 to 10, the method further comprising: obtaining from the UE a first activation request message indicating the one or more machine learning functions; outputting a second activation request message to the ML service in response to the first activation request message, the second activation request message indicating a set of UE identifiers including an identifier of the UE, the one or more machine learning functions, or any combination thereof; and obtaining an activation confirmation message from the ML service in response to the second activation request message, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

[0247] Aspect 12: The method according to any one of Aspects 1 to 11, the method further comprising: obtaining a sixth message including UE inferred input data associated with the one or more machine learning functions; outputting a service data request message including the UE inferred input data to the ML service; and obtaining a service data response message from the ML service indicating ML service inferred output data associated with the one or more machine learning functions.

[0248] Aspect 13: According to the method of aspect 12, the method further includes: outputting a seventh message to the UE including ML service inferred output data from the ML service.

[0249] Aspect 14: The method according to any one of Aspects 12 to 13, the method further comprising: monitoring one or more triggering conditions based at least in part on the UE inferred input data, ML service inferred input data from the ML service, or any combination thereof; and outputting a third control message to the UE, the third control message including an indication to switch or disable at least one of the one or more machine learning functions based at least in part on the occurrence of the one or more triggering conditions.

[0250] Aspect 15: According to the method of aspect 14, wherein the one or more triggering conditions include the measurement of one or more key performance indicators that satisfy a key performance indicator threshold.

[0251] Aspect 16: The method according to any one of Aspects 14 to 15, the method further comprising: outputting a monitoring report to the ML service, the monitoring report indicating one or more key performance indicators associated with the one or more machine learning functions.

[0252] Aspect 17: The method according to any one of Aspects 14 to 16, wherein the one or more triggering conditions are based at least in part on a monitoring report including measurements performed by the UE, by the network entity, or any combination thereof.

[0253] Aspect 18: The method according to any one of Aspects 1 to 17, the method further comprising: obtaining a monitoring report from the UE, the monitoring report including one or more key performance indicators associated with the one or more machine learning functions; and outputting an indication to the UE to switch or disable the one or more machine learning functions of the UE based at least in part on the occurrence of one or more triggering conditions.

[0254] Aspect 19: The method according to aspect 18 further includes: outputting a monitoring report to the ML service, the monitoring report indicating one or more key performance indicators associated with the one or more machine learning functions.

[0255] Aspect 20: The method according to any one of Aspects 1 to 19, the method further comprising: obtaining from the UE an LCM control request message including a request for lifecycle management control signaling, the lifecycle management control signaling including an indication for activating, deactivating, switching a default configuration or any combination thereof in one or more cross-node machine learning configurations; outputting a first LCM control message including an indication for the request for the LCM control signaling to the ML service in response to the LCM control request message; and outputting a second LCM control message to the UE including an indication of the lifecycle management control signaling indicated by the ML service.

[0256] Aspect 21: The method according to aspect 20, wherein obtaining the LCM control request message is based at least in part on monitoring reports from the UE, the network entity, or a combination thereof.

[0257] Aspect 22: A method for wireless communication at a UE, the method comprising: receiving a first message indicating one or more lifecycle management triggering conditions for a channel between the UE and a network entity; in response to the occurrence of the one or more lifecycle management triggering conditions, sending to the network entity an LCM control request message including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, switching a default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE; and in response to the LCM control request message, receiving from the network entity a second message indicating the lifecycle management control signaling.

[0258] Aspect 23: The method according to aspect 22, the method further comprising: sending a monitoring report to the network entity indicating one or more key performance indicators associated with the UE, wherein receiving the second message indicating the lifecycle management control signaling is at least in part based on the monitoring report.

[0259] Aspect 24: The method according to any one of Aspects 22 to 23, wherein the one or more lifecycle management triggering conditions include one or more thresholds associated with the inferred performance of the UE, one or more key performance indicators associated with the UE, or a combination thereof.

[0260] Aspect 25: A network entity for wireless communication, the network entity comprising: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories and capable of operating individually or jointly to execute the code, so that the network entity performs a method according to any one of aspects 1 to 21.

[0261] Aspect 26: A network entity for wireless communication, the network entity comprising at least one component for performing the method according to any one of aspects 1 to 21.

[0262] Aspect 27: A non-transitory computer-readable medium storing code for wireless communication, said code including instructions executable by a processor to perform the method according to any one of aspects 1 to 21.

[0263] Aspect 28: A UE for wireless communication, the UE comprising: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories and capable of operating individually or jointly to execute the code, so that the UE performs a method according to any one of Aspects 22 to 24.

[0264] Aspect 29: A UE for wireless communication, the UE including at least one component for performing a method according to any one of aspects 22 to 24.

[0265] Aspect 30: A non-transitory computer-readable medium storing code for wireless communication, said code including instructions executable by a processor to perform a method according to any one of aspects 22 to 24.

[0266] It should be noted that the methods described herein describe possible specific implementations, and the operations and steps can be rearranged or otherwise modified, and other specific implementations are also possible. Furthermore, aspects from two or more of these methods can be combined.

[0267] While aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for illustrative purposes, and the terms LTE, LTE-A, LTE-A Pro, or NR may be used in most of the description, the techniques described herein are also applicable to networks outside of LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described are applicable to a variety of other wireless communication systems, such as Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0268] The information and signals described herein can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the description can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0269] The various exemplary blocks and components described herein can be implemented or performed using a general-purpose processor, DSP, ASIC, CPU, FPGA or other programmable logic device, discrete gate or transistor logic unit, discrete hardware component, or any combination thereof, designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in alternative embodiments, a 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, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration). Any function or operation described herein that can be performed by a processor may be performed by multiple processors capable of performing the described functions or operations individually or jointly.

[0270] The functions described herein can be implemented using hardware, software executed by a processor, firmware, or any combination thereof. When implemented using software executed by a processor, the functions can be stored as one or more instructions or code on a computer-readable medium or transmitted using one or more instructions or code on a computer-readable medium. Other examples and specific implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein can be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination of these. Features implementing the functions can also be physically located in various locations, including various portions distributed such that the functions are implemented in different physical locations.

[0271] Computer-readable media includes both non-transitory computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. Non-transitory storage media can be any available medium accessible by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compressed optical disc (CD) ROM or other optical disc storage devices, magnetic disk storage devices or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code components in the form of instructions or data structures, and accessible by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Furthermore, any connection is appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included within the definition of computer-readable media. As used herein, disks and optical discs include CDs, laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs. Disks can magnetically reproduce data, and optical discs can optically reproduce data using lasers. Combinations of the above are also included within the scope of computer-readable media. Any function or operation described herein that can be performed by memory can be performed by multiple memories capable of performing the described function or operation individually or jointly.

[0272] As used herein, the word "or" in a list of items (e.g., a list of items accompanied by phrases such as "at least one of" or "one or more of") in the claims indicates an inclusive list, such that a list of at least one of, for example, A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Furthermore, as used herein, the phrase "based on" should not be construed as a reference to a closed set of conditions. For example, an example step described as "based on condition A" could be based on both condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "at least partially based on".

[0273] As used herein, including in claims, the article “a” preceding a noun is open-ended and is understood to refer to “at least one” or “one or more” of those nouns. Therefore, the terms “a,” “at least one,” “one or more,” and “at least one of one or more” are interchangeable. For example, where a claim enumerates “components” performing one or more functions, each of the individual functions may be performed by a single component or by any combination of multiple components. Thus, the term “component” having a characteristic or performing a function may refer to “at least one of one or more components” having a particular characteristic or performing a particular function. Subsequent references to a component introduced with the article “a” using the terms “the” or “the” can refer to any or all of the one or more components. For example, a component introduced with the article “a” can be understood to mean “one or more components,” and subsequent reference to “the component” in a claim can be understood as equivalent to referring to “at least one of the one or more components.” Similarly, subsequent references to a component introduced with the terms “the” or “the” as “one or more components” can refer to any or all of the one or more components. For example, reference to "the one or more components" in the subsequent claims can be understood as equivalent to reference to "at least one of the one or more components".

[0274] The term "determine" encompasses a variety of actions, and therefore, "determine" can include calculation, computation, processing, derivation, investigation, searching (such as by searching in a table, database, or other data structure), ascertainment, etc. Furthermore, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data stored in memory), etc. Moreover, "determine" can include parsing, obtaining, selecting, choosing, creating, and other similar actions.

[0275] In the accompanying drawings, similar components or features may have the same reference numerals. Furthermore, various components of the same type can be distinguished by adding a dash after the reference numeral and a second reference numeral to differentiate them. If only the first reference numeral is used in the description, the description can be applied to any of the similar components having the same first reference numeral, regardless of the second or other subsequent reference numerals.

[0276] The description herein, illustrated with reference to the accompanying drawings, describes an example configuration and does not represent all achievable examples or those within the scope of the claims. The term "example" as used herein means "serving as an example, instance, or illustration," not "preferred" or "advantageous over other examples." The detailed description includes specific details used to provide an understanding of the described techniques. However, these techniques can be practiced without these specific details. In some instances, known structures and devices are shown in block diagram form to avoid obscuring the concept of the described examples.

[0277] The description herein is provided to enable those skilled in the art to implement or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of this disclosure. Therefore, this disclosure is not limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A network entity, the network entity comprising: One or more memories, the one or more memories storing processor-executable code; and One or more processors, coupled to one or more memories and capable of operating individually or jointly to execute the code to enable the network entity: Receive the first message indicating one or more machine learning capabilities of the user equipment (UE); Obtain a second message from the machine learning service indicating one or more machine learning service capabilities of the machine learning service; as well as Control messages instructing one or more cross-node machine learning configurations are output to the UE at least in part based on the one or more machine learning capabilities of the UE and the one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure one or more machine learning functions of the UE for use with the machine learning service.

2. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Output a service capability request message for the one or more machine learning service capabilities to the machine learning service, wherein the second message indicating the one or more machine learning service capabilities is obtained in response to the service capability request message, and wherein the one or more machine learning service capabilities include capabilities that are at least partially compatible with the UE based on the one or more machine learning capabilities of the UE.

3. The network entity of claim 2, wherein the service capability request message includes a set of UE identifiers including the identifier of the UE, an indication of the one or more machine learning capabilities of the UE, or any combination thereof.

4. The network entity of claim 1, wherein, in order to obtain the second message indicating the capabilities of the one or more machine learning services, the one or more processors are capable of operating individually or jointly to execute the code to cause the network entity to: A notification of obtaining the capabilities of the one or more machine learning services from the machine learning service, the notification including the second message.

5. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: The one or more machine learning functions are selected based at least in part on the one or more machine learning capabilities of the UE and the one or more machine learning service capabilities of the machine learning service; At least in part based on the selection, output a configuration request message to the machine learning service requesting one or more cross-node machine learning configurations; as well as A configuration response message is obtained from the machine learning service, the configuration response message indicating the one or more cross-node machine learning configurations, the one or more machine learning functions, a set of UE identifiers including the UE's identifier, or any combination thereof, wherein the control message indicating the one or more cross-node machine learning configurations is at least partially based on obtaining the configuration response message.

6. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: In response to the control message, a third message is obtained indicating that the UE completes the one or more cross-node machine learning configurations.

7. The network entity of claim 6, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Output a fourth message to the machine learning service indicating that the one or more cross-node machine learning configurations have been configured by the UE.

8. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: A second control message is output, at least in part, based on the one or more cross-node machine learning configurations, the second control message including an indication to activate the one or more machine learning functions.

9. The network entity of claim 8, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Output an activation request message to the machine learning service, the activation request message indicating a set of UE identifiers including the UE's identifier, the one or more machine learning functions, or any combination thereof; and In response to the activation request message, an activation confirmation message is obtained from the machine learning service, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

10. The network entity of claim 8, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: An activation request message is obtained from the machine learning service, the activation request message indicating a set of UE identifiers including the UE's identifier, the one or more machine learning functions, or any combination thereof; and In response to the activation request message, an activation confirmation message from the machine learning service is output to the machine learning service, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

11. The network entity of claim 8, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: The UE receives a first activation request message indicating one or more machine learning functions; In response to the first activation request message, a second activation request message is output to the machine learning service, the second activation request message indicating a set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof; as well as In response to the second activation request message, an activation confirmation message is obtained from the machine learning service, the activation confirmation message indicating the set of UE identifiers including the identifier of the UE, the one or more machine learning functions, or any combination thereof, wherein the second control message is output at least in part based on the activation confirmation message.

12. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Obtain a sixth message including UE inferred input data associated with the one or more machine learning functions; Output a service data request message including the UE's inferred input data to the machine learning service; as well as Obtain a service data response message from the machine learning service that indicates the machine learning service inferred output data associated with the one or more machine learning functions.

13. The network entity of claim 12, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: A seventh message is output to the UE, including the machine learning service inferred output data from the machine learning service.

14. The network entity of claim 12, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Monitoring one or more triggering conditions is based at least in part on the UE-inferred input data, machine learning service-inferred input data from the machine learning service, or any combination thereof; and A third control message is output to the UE, the third control message including an indication to switch or disable at least one of the one or more machine learning functions based at least in part on the occurrence of the one or more triggering conditions.

15. The network entity of claim 14, wherein the one or more triggering conditions include the measurement of one or more key performance indicators that satisfy a key performance indicator threshold.

16. The network entity of claim 14, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Output a monitoring report to the machine learning service, the monitoring report indicating one or more key performance indicators associated with the one or more machine learning functions.

17. The network entity of claim 14, wherein the one or more triggering conditions are based at least in part on a monitoring report including measurements performed by the UE, by the network entity, or any combination thereof.

18. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: A monitoring report is obtained from the UE, the monitoring report including one or more key performance indicators associated with the one or more machine learning functions; and The instruction to switch or disable one or more machine learning functions of the UE is output to the UE at least in part based on the occurrence of one or more triggering conditions.

19. The network entity of claim 18, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: Output a monitoring report to the machine learning service, the monitoring report indicating one or more key performance indicators associated with the one or more machine learning functions.

20. The network entity of claim 1, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the network entity to: The UE receives a lifecycle management control request message that includes a request for lifecycle management control signaling, the lifecycle management control signaling including instructions for activating, deactivating, switching the default configuration or any combination thereof in one or more cross-node machine learning configurations; In response to the lifecycle management control request message, a first lifecycle management control message is output to the machine learning service, the first lifecycle management control message including an indication of a request for the lifecycle management control signaling; and A second lifecycle management control message is output to the UE, including an indication of the lifecycle management control signaling indicated by the machine learning service.

21. The network entity of claim 20, wherein obtaining the lifecycle management control request message is based at least in part on monitoring reports from the UE, the network entity, or a combination thereof.

22. A user equipment (UE), the user equipment (UE) comprising: One or more memories, the one or more memories storing processor-executable code; and One or more processors, coupled to one or more memories and capable of operating individually or jointly to execute the code to enable the UE: Receive a first message indicating one or more lifetime management trigger conditions for the channel between the UE and the network entity; In response to the occurrence of one or more lifecycle management triggering conditions, a lifecycle management control request message is sent to the network entity, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, switching the default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. as well as In response to the lifecycle management control request message, a second message instructing the lifecycle management control signaling is received from the network entity.

23. The UE of claim 22, wherein the one or more processors are further capable of operating individually or jointly to execute the code to cause the UE to: A monitor report indicating one or more key performance indicators associated with the UE is sent to the network entity, wherein the second message indicating the lifecycle management control signaling is received at least in part based on the monitor report.

24. The UE of claim 22, wherein the one or more lifecycle management triggering conditions include one or more thresholds associated with the inferred performance of the UE, one or more key performance indicators associated with the UE, or a combination thereof.

25. A method for conducting wireless communication at a network entity, the method comprising: Receive the first message indicating one or more machine learning capabilities of the user equipment (UE); Obtain a second message from the machine learning service indicating one or more machine learning service capabilities of the machine learning service; as well as Control messages instructing one or more cross-node machine learning configurations are output to the UE at least in part based on the one or more machine learning capabilities of the UE and the one or more machine learning service capabilities of the machine learning service, wherein the one or more cross-node machine learning configurations configure one or more machine learning functions of the UE for use with the machine learning service.

26. The method according to claim 25, further comprising: Output a service capability request message for the one or more machine learning service capabilities to the machine learning service, wherein the second message indicating the one or more machine learning service capabilities is obtained in response to the service capability request message, and wherein the one or more machine learning service capabilities include capabilities that are at least partially compatible with the UE based on the one or more machine learning capabilities of the UE.

27. The method of claim 26, wherein the service capability request message includes a set of UE identifiers including the identifier of the UE, an indication of the one or more machine learning capabilities of the UE, or any combination thereof.

28. The method of claim 25, wherein obtaining the second message indicating the capabilities of the one or more machine learning services comprises: A notification of obtaining the capabilities of the one or more machine learning services from the machine learning service, the notification including the second message.

29. A method for conducting wireless communication at a user equipment (UE), the method comprising: Receive a first message indicating one or more lifecycle management trigger conditions for the channel between the UE and the network entity; In response to the occurrence of one or more lifecycle management triggering conditions, a lifecycle management control request message is sent to the network entity, including a request for lifecycle management control signaling, wherein the lifecycle management control signaling includes indications for activating, deactivating, switching the default configuration or any combination thereof in one or more cross-node machine learning configurations for the UE. as well as In response to the lifecycle management control request message, a second message instructing the lifecycle management control signaling is received from the network entity.

30. The method according to claim 29, further comprising: A monitoring report indicating one or more key performance indicators associated with the UE is sent to the network entity, wherein the second message indicating the lifecycle management control signaling is received is at least in part based on the monitoring report.

Images