Performance Indicators for Combining Machine Learning Models

Abstract

Various aspects of the present disclosure generally relate to wireless communications. In some aspects, a user equipment (UE) may transmit capability information indicating support for one or more model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model. The UE may receive one or more instructions to use one or more of the ML models based at least in part on the capability information. Numerous other aspects are described.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This patent application claims priority to U.S. Non-Provisional Patent Application No. 17 / 659,129, entitled "PERFORMANCE INDICATORS FOR COMBINATIONS OF MACHINE LEARNING MODELS," filed on April 13, 2022, which is expressly incorporated by reference into this specification.

[0002] Aspects of the present disclosure relate generally to wireless communications and to techniques and apparatus for parameters for combining machine learning models. [Background technology]

[0003]

[0003] Wireless communication systems have been widely deployed to provide various telecommunication services, such as telephony, video, data, messaging, and broadcast. A typical wireless communication system may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single-carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and Long Term Evolution (LTE). LTE / LTE-Advanced is a set of extensions to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0004]

[0004] A wireless network may include one or more base stations supporting communication for a single user equipment (UE) or multiple UEs. A UE may communicate with a base station via downlink and uplink communications. "Downlink" (or "DL") refers to the communication link from a base station to a UE, and "uplink" (or "UL") refers to the communication link from a UE to a base station.

[0005]

[0005] The above multiple access techniques have been adopted in various telecommunication standards to provide a common protocol that allows different UEs to communicate on a city, national, regional, and / or global scale. New Radio (NR), which may be referred to as 5G, is a set of enhancements to the LTE mobile standard promulgated by 3GPP. NR is designed to better support mobile broadband Internet access through improved spectral efficiency, reduced costs, improved services, utilization of new spectrum, and better integration with other open standards through the use of orthogonal frequency division multiplexing (OFDM) with cyclic prefix (CP) (CP-OFDM) on the downlink, CP-OFDM and / or single-carrier frequency division multiplexing (SC-FDM) (also known as discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink, and support for beamforming, multiple-input multiple-output (MIMO) antenna technology, and carrier aggregation. As the demand for mobile broadband access continues to grow, further improvements in LTE, NR, and other radio access technologies will still be useful. Summary of the Invention

[0006]

[0006] Certain aspects described herein relate to a method of wireless communication performed by a user equipment (UE). The method may include transmitting capability information indicating support for one or more model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML models. The method may include receiving one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0007]

[0007] Certain aspects described herein relate to a method of wireless communication performed by a network node. The method may include receiving capability information indicating support by a UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model. The method may include sending one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0008]

[0008] Some aspects described herein relate to a UE for wireless communication. The UE may include a memory and one or more processors coupled to the memory. The one or more processors may be configured to transmit capability information indicating support for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model. The one or more processors may be configured to receive one or more instructions to use one or more of the ML models based at least in part on the capability information.

[0009]

[0009] Some aspects described herein relate to a network node for wireless communications. The network node may include a memory and one or more processors coupled to the memory. The one or more processors may be configured to receive capability information indicating support by a UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model. The one or more processors may be configured to transmit one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0010]

[0010] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a UE. The set of instructions, when executed by one or more processors of the UE, may cause the UE to transmit capability information indicating support for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model. The set of instructions, when executed by the one or more processors of the UE, may cause the UE to receive one or more instructions to use one or more of the ML models based at least in part on the capability information.

[0011]

[0011] Certain aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a network node. The set of instructions, when executed by one or more processors of the network node, may cause the network node to receive capability information indicating support by a UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model. The set of instructions, when executed by the one or more processors of the network node, may cause the network node to transmit one or more instructions to use one or more of the ML models based at least in part on the capability information.

[0012]

[0012] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include means for transmitting capability information indicating support for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model. The apparatus may include means for receiving one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0013]

[0013] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include means for receiving capability information indicating support by a UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model. The apparatus may include means for transmitting one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0014]

[0014] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communications devices, and / or processing systems substantially as described herein with reference to the drawings and specification.

[0015]

[0015] The above outlines rather broadly the features and technical advantages of the examples according to the present disclosure in order to better understand the following "Description of the Preferred Embodiments". Additional features and advantages are set forth below. The concepts and specific examples disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure. Such equivalent structures are within the scope of the appended claims. The characteristics and associated advantages of both the organization of the concepts and the method of operation disclosed herein will be better understood when the following description is considered in conjunction with the accompanying figures. Each of the figures is provided for illustration and explanation, and not as a definition of the limits of the claims.

[0016]

[0016] Although aspects are described in this disclosure by illustrating some examples, those skilled in the art will understand that such aspects can be implemented in many different configurations and scenarios. The techniques described herein can be implemented using different platform types, devices, systems, shapes, sizes, and / or packaging configurations. For example, some aspects can be implemented via integrated chip embodiments or other non-modular component-based devices (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, and / or artificial intelligence (AI) devices). Aspects can be implemented in chip-level components, modular components, non-modular components, non-chip-level components, device-level components, and / or system-level components. Devices incorporating the described aspects and features may include additional components and features for the implementation and practice of the claimed and described aspects. For example, the transmission and reception of wireless signals may include one or more components for analog and digital applications (e.g., hardware components including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders, and / or summers). It is contemplated that aspects described herein may be practiced in a wide variety of devices, components, systems, distributed configurations, and / or end-user devices of various sizes, shapes, and configurations. [Brief description of the drawings]

[0017]

[0017] In order to be able to understand in detail the above-listed features of the present disclosure, a more detailed description, briefly summarized above, may be obtained by referring to the embodiments, some of which are shown in the attached drawings. However, it should be noted that the attached drawings show only certain exemplary embodiments of the present disclosure, and therefore should not be considered as limiting the scope of the present disclosure, since the present description may admit other equally effective embodiments. The same reference signs in different drawings may identify the same or similar elements. [Figure 1]

[0018] FIG. 1 illustrates an example of a wireless network in accordance with the present disclosure. [Diagram 2]

[0019] FIG. 1 illustrates an example of a base station in communication with a user equipment (UE) in a wireless network in accordance with the present disclosure. [Diagram 3]

[0020] FIG. 3 illustrates an example disaggregated base station architecture 300 in accordance with the present disclosure. [Figure 4]

[0021] FIG. 1 illustrates an example associated with communicating UE capabilities for machine learning models in accordance with the present disclosure. [Diagram 5]

[0022] FIG. 1 illustrates an example of associated parameters for a combination of machine learning models according to the present disclosure. [Figure 6] FIG. 1 illustrates an example of associated parameters for a combination of machine learning models according to the present disclosure. [Figure 7] FIG. 1 illustrates an example of associated parameters for a combination of machine learning models according to the present disclosure. [Figure 8]

[0023] FIG. 1 illustrates an example process associated with parameters for a combination of machine learning models according to the present disclosure. [Figure 9] FIG. 1 illustrates an example process associated with parameters for a combination of machine learning models according to the present disclosure. [Figure 10]

[0024] FIG. 1 is an illustration of an exemplary apparatus for wireless communication in accordance with the present disclosure. [Figure 11] FIG. 1 is an illustration of an exemplary apparatus for wireless communication in accordance with the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018]

[0025] Various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure may be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout the present disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Those skilled in the art should understand that the scope of the disclosure herein is intended to cover any aspect of the disclosure herein, regardless of whether it is implemented independently or in combination with any other aspect of the disclosure. For example, an apparatus can be implemented or a method can be practiced using any number of the aspects described herein. In addition, the scope of the disclosure is intended to cover such an apparatus or method that is implemented using other structures, functions, or structures and functions in addition to or other than the various aspects of the disclosure described herein. It should be understood that any aspect of the disclosure disclosed herein can be embodied by one or more elements of a claim.

[0019]

[0026] Several aspects of a telecommunications system will now be illustrated with reference to various apparatus and techniques, which are described in the detailed description that follows and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the particular application and design constraints imposed on the overall system.

[0020]

[0027] Although aspects may be described herein using terminology commonly associated with 5G or New Radio (NR) radio access technology (RAT), aspects of the disclosure may be applicable to other RATs, such as 3G RATs, 4G RATs, and / or 5G and beyond RATs (e.g., 6G).

[0021]

[0028] 1 illustrates an example of a wireless network 100 in accordance with the present disclosure. Wireless network 100 may be or include elements of a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, among other examples. Wireless network 100 may include one or more base stations 110 (shown as BS 110a, BS 110b, BS 110c, and BS 110d), user equipment (UE) 120 or multiple UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other network entities. Base station 110 is an entity that communicates with UE 120. The base stations 110 (which may be referred to as BSs) may include, for example, NR base stations, LTE base stations, Node Bs, eNBs (e.g., in 4G), gNBs (e.g., in 5G), access points, and / or transmission reception points (TRPs). Each base station 110 may provide communication coverage for a particular geographic area. In the Third Generation Partnership Project (3GPP), the term "cell" can refer to the coverage area of ​​a base station 110 and / or a base station subsystem serving this coverage area, depending on the context in which the term is used.

[0022]

[0029] A base station 110 may provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell may cover a relatively large geographic area (e.g., a few kilometers in radius) and may allow unrestricted access by UEs 120 with a service subscription. A pico cell may cover a relatively small geographic area and may allow unrestricted access by UEs 120 with a service subscription. A femto cell may cover a relatively small geographic area (e.g., a home) and may allow restricted access by UEs 120 with an association with a femto cell (e.g., UEs 120 in a closed subscriber group (CSG)). A base station 110 for a macro cell may be referred to as a macro base station. A base station 110 for a pico cell may be referred to as a pico base station. A base station 110 for a femto cell may be referred to as a femto base station or a home base station. 1, BS 110a may be a macro base station for a macro cell 102a, BS 110b may be a pico base station for a pico cell 102b, and BS 110c may be a femto base station for a femto cell 102c. A base station may support one or multiple (e.g., three) cells.

[0023]

[0030] In some examples, the cells may not necessarily be fixed, and the geographic area of ​​the cells may move according to the location of the base stations 110 that are mobile (e.g., mobile base stations). In some examples, the base stations 110 may interconnect with each other and / or with one or more other base stations 110 or network nodes (not shown) in the wireless network 100 using any suitable transport network, through various types of backhaul interfaces, such as direct physical connections or virtual networks.

[0024]

[0031] The wireless network 100 may include one or more relay stations. A relay station is an entity capable of receiving a transmission of data from an upstream station (e.g., a base station 110 or a UE 120) and transmitting the transmission of the data to a downstream station (e.g., a UE 120 or a base station 110). A relay station may be a UE 120 that may relay a transmission of another UE 120. In the example shown in FIG. 1, a BS 110d (e.g., a relay base station) may communicate with a BS 110a (e.g., a macro base station) and a UE 120d to facilitate communication between the BS 110a (e.g., a macro base station) and the UE 120d. A base station 110 that relays communication may be referred to as a relay station, a relay base station, a repeater, etc.

[0025]

[0032] The wireless network 100 may be a heterogeneous network including different types of base stations 110, such as macro base stations, pico base stations, femto base stations, relay base stations, etc. These different types of base stations 110 may have different transmit power levels, different coverage areas, and / or different susceptibility to interference within the wireless network 100. For example, a macro base station may have a high transmit power level (e.g., 5-40 Watts), while the pico, femto, and relay base stations may have a lower transmit power level (e.g., 0.1-2 Watts).

[0026]

[0033] A network controller 130 may couple to or communicate with a set of base stations 110 and provide coordination and control for these base stations 110. The network controller 130 may communicate with the base stations 110 via backhaul communication links. The base stations 110 may communicate with each other directly or indirectly via wireless backhaul communication links or wireline backhaul communication links.

[0027]

[0034] The UEs 120 may be dispersed throughout the wireless network 100, and each UE 120 may be fixed or mobile. The UEs 120 may include, for example, an access terminal, a terminal, a mobile station, and / or a subscriber unit. The UEs 120 may be a cellular telephone (e.g., a smartphone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device, a biometric device, a wearable device (e.g., a smart watch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or a smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio), a vehicle component, or a sensor, a smart meter / sensor, industrial manufacturing equipment, a global positioning system device, and / or any other suitable device configured to communicate over a wireless medium.

[0028]

[0035] Some UEs 120 may be considered as machine-type communication (MTC) UEs or evolved or enhanced machine-type communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, a robot, a drone, a remote device, a sensor, a meter, a monitor, and / or a location tag that may communicate with a base station, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered as Internet-of-Things (IoT) devices and / or may be implemented as NB-IoT (narrowband IoT) devices. Some UEs 120 may be considered as customer premises equipment. The UE 120 may be included within a housing that houses components of the UE 120, such as a processor component and / or a memory component. In some examples, the processor component and the memory component may be coupled together. For example, a processor component (e.g., one or more processors) and a memory component (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0029]

[0036] In general, any number of wireless networks 100 may be deployed in a given geographic area. Each wireless network 100 may support a particular RAT and may operate on one or more frequencies. The RAT may be referred to as a radio technology, an air interface, etc. The frequencies may be referred to as a carrier, a frequency channel, etc. To avoid interference between wireless networks of different RATs, each frequency may support a single RAT in a given geographic area. In some cases, NR networks or 5G RAT networks may be deployed.

[0030]

[0037] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly (e.g., without using a base station 110 as an intermediary to communicate with each other) using one or more sidelink channels. For example, the UEs 120 may communicate using peer-to-peer (P2P) communications, device-to-device (D2D) communications, vehicle-to-everything (V2X) protocols (which may include, e.g., a vehicle-to-vehicle (V2V) protocol, a vehicle-to-infrastructure (V2I) protocol, or a vehicle-to-pedestrian (V2P) protocol), and / or a mesh network. In such examples, the UEs 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by the base station 110.

[0031]

[0038] The devices of the wireless network 100 may communicate using an electromagnetic spectrum, which may be subdivided by frequency or wavelength into various classes, bands, channels, etc. For example, the devices of the wireless network 100 may communicate using one or more operating bands. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz to 7.125 GHz) and FR2 (24.25 GHz to 52.6 GHz). It should be understood that FR1 is often referred to (interchangeably) as a "sub-6 GHz" band in various documents and papers, although a portion of FR1 is higher than 6 GHz. A similar nomenclature issue may arise with respect to FR2, which is often referred to (interchangeably) as a "millimeter wave" band in documents and papers, even though it is different from the extremely high frequency (EHF) band (30 GHz to 300 GHz) identified as a "millimeter wave" band by the International Telecommunications Union (ITU).

[0032]

[0039] Frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Recent 5G NR studies have identified the operating band for these mid-band frequencies as frequency range designation FR3 (7.125 GHz to 24.25 GHz). Frequency bands included within FR3 may inherit FR1 and / or FR2 characteristics, and thus, in effect, extend the features of FR1 and / or FR2 to the mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as frequency range designations FR4a or FR4-1 (52.6 GHz to 71 GHz), FR4 (52.6 GHz to 114.25 GHz), and FR5 (114.25 GHz to 300 GHz). Each of these higher frequency bands is included within the EHF band.

[0033]

[0040] With the above examples in mind, it should be understood that unless otherwise specified, terms such as "sub-6 GHz" as used herein may broadly refer to frequencies that may be below 6 GHz, may be within FR1, or may include mid-band frequencies. Additionally, unless otherwise specified, it should be understood that terms such as "millimeter wave" as used herein may broadly refer to frequencies that may be within FR2, FR4, FR4-a, or FR4-1, and / or FR5, may include mid-band frequencies, or may be within the EHF band. Frequencies included within these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) may be subject to modifications, and it is contemplated that the techniques described herein are applicable to those modified frequency ranges.

[0034]

[0041] In some aspects, UE 120 may include a communications manager 140. As described in more detail elsewhere herein, communications manager 140 may transmit capability information indicating support for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combinations of the one or more model combinations that include the ML models, and receive one or more instructions to use one or more of the ML models based at least in part on the capability information. Additionally or alternatively, communications manager 140 may perform one or more other operations described herein.

[0035]

[0042] In some aspects, a network node (e.g., base station 110) may include a communications manager 150. As described in more detail elsewhere herein, communications manager 150 may receive capability information indicating support by the UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model, and transmit one or more instructions to use one or more of the ML models based at least in part on the capability information. Additionally or alternatively, communications manager 150 may perform one or more other operations described herein.

[0036]

[0043] In some aspects, the term "base station" (e.g., base station 110) or "network node" or "network entity" may refer to an aggregated base station, a non-aggregated base station (e.g., as described in connection with FIG. 9), an integrated access and backhaul (IAB) node, a relay node, and / or one or more components thereof. For example, in some aspects, a "base station", "network node", or "network entity" may refer to a central unit (CU or centralized unit), a distributed unit (DU), a radio unit (RU), a Near-Real Time (Near-RT) RAN Intelligent Controller (RIC), or a Non-Real Time (Non-RT) RIC, or a combination thereof. In some aspects, the term "base station", "network node", or "network entity" may refer to a device configured to perform one or more functions, such as those described herein with respect to base station 110. In some aspects, the term "base station," "network node," or "network entity" may refer to multiple devices configured to perform one or more functions. For example, in some distributed systems, several different devices (which may be located at the same geographic location or different geographic locations) may each be configured to perform at least a portion of a function or to replicate the performance of at least a portion of a function, and the term "base station," "network node," or "network entity" may refer to any one or more of those different devices. In some aspects, the term "base station," "network node," or "network entity" may refer to one or more virtual base stations and / or one or more virtual base station functions. For example, in some aspects, two or more base station functions may be instantiated on a single device.In some aspects, the terms "base station," "network node," or "network entity" may refer to one of the base station functions and not to another. In this manner, a single device may include two or more base stations.

[0037]

[0044] As noted above, Figure 1 is provided as an example. Other examples may differ from those described with respect to Figure 1.

[0038]

[0045] 2 illustrates an example base station 200 in communication with a UE 120 in a wireless network 100 in accordance with the present disclosure. The base station 110 may be equipped with a set of antennas 234a-t, such as T antennas, where T≧1. The UE 120 may be equipped with a set of antennas 252a-r, such as R antennas, where R≧1.

[0039]

[0046] At the base station 110, a transmit processor 220 may receive data destined for a UE 120 (or set of UEs 120) from a data source 212. The transmit processor 220 may select one or more modulation and coding schemes (MCSs) for the UE 120 based at least in part on one or more channel quality indicators (CQIs) received from the UE 120. The base station 110 may process (e.g., encode and modulate) data for the UE 120 based at least in part on the MCS(es) selected for the UE 120 and provide data symbols to the UE 120. The transmit processor 220 may process system information (e.g., related to semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or higher layer signaling) and provide overhead symbols and control symbols. The transmit processor 220 may generate reference symbols for a reference signal (e.g., a cell-specific reference signal (CRS) or demodulation reference signal (DMRS)) and a synchronization signal (e.g., a primary synchronization signal (PSS) or a secondary synchronization signal (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., precoding) on ​​the data symbols, control symbols, overhead symbols, and / or reference symbols, where applicable, and may provide a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modems), illustrated as modems 232a through 232t. For example, each output symbol stream may be provided to a modulator component (illustrated as MOD) of modem 232.Each modem 232 may use a separate modulator component to process a separate output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modem 232 may further use a separate modulator component to process (e.g., convert to analog, amplify, filter, and / or upconvert) the output sample stream to obtain a downlink signal. Modems 232a through 232t may transmit a set of downlink signals (e.g., T downlink signals) via a corresponding set of antennas 234 (e.g., T antennas), which are shown as antennas 234a through 234t.

[0040]

[0047] At the UE 120, a set of antennas 252 (depicted as antennas 252a through 252r) may receive downlink signals from the base station 110 and / or other base stations 110 and may provide a set of received signals (e.g., R received signals) to a set of modems 254 (e.g., R modems), depicted as modems 254a through 254r. For example, each received signal may be provided to a demodulator component (depicted as DEMOD) of the modems 254. Each modem 254 may use a separate demodulator component to condition (e.g., filter, amplify, downconvert, and / or digitize) the received signal to obtain input samples. Each modem 254 may use a demodulator component to further process the input samples (e.g., for OFDM) to obtain received symbols. A MIMO detector 256 may obtain received symbols from the modems 254, perform MIMO detection on the received symbols if applicable, and provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide decoded data for the UE 120 to a data sink 260, and provide decoded control and system information to the controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine a reference signal received power (RSRP) parameter, a received signal strength indicator (RSSI) parameter, a reference signal received quality (RSRQ) parameter, and / or a CQI parameter, among other examples. In some examples, one or more components of the UE 120 may be included within a housing 284.

[0041]

[0048] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in a core network. The network controller 130 may communicate with the base stations 110 via the communication unit 294.

[0042]

[0049] One or more antennas (e.g., antennas 234a-t and / or antennas 252a-r) may include or be contained within one or more antenna panels, one or more antenna groups, one or more sets of antenna elements, and / or one or more antenna arrays, among other examples. An antenna panel, antenna group, set of antenna elements, and / or antenna array may include one or more antenna elements (in a single housing or multiple housings), a set of coplanar antenna elements, a set of non-coplanar antenna elements, and / or one or more antenna elements coupled to one or more transmitting and / or receiving components, such as one or more components of FIG.

[0043]

[0050] On the uplink, at the UE 120, a transmit processor 264 may receive and process data from a data source 262 and control information from a controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 may generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be precoded by a TX MIMO processor 266, if applicable, further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to the base station 110. In some examples, the modem 254 of the UE 120 may include a modulator and a demodulator. In some examples, the UE 120 includes a transceiver. The transceiver may include any combination of the antenna(s) 252, the modem(s) 254, the MIMO detector 256, the receive processor 258, the transmit processor 264, and / or the TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and memory 282 to perform aspects of any of the methods described herein (e.g., with reference to Figures 5-11).

[0044]

[0051] At the base station 110, uplink signals from the UE 120 and / or other UEs may be received by the antenna 234, processed by the modem 232 (e.g., a demodulator component of the modem 232, denoted as DEMOD), detected by a MIMO detector 236, if applicable, and further processed by a receive processor 238 to obtain decoded data and control information to be transmitted by the UE 120. The receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to the controller / processor 240. The base station 110 may include a communication unit 244 and may communicate with the network controller 130 via the communication unit 244. The base station 110 may include a scheduler 246 for scheduling one or more UEs 120 for downlink and / or uplink communications. In some examples, the modem 232 of the base station 110 may include a modulator and a demodulator. In some examples, the base station 110 includes a transceiver. The transceiver may include any combination of antenna(s) 234, modem(s) 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein (e.g., with reference to FIGS. 5-11).

[0045]

[0052] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or any other component(s) of FIG. 2 may perform one or more techniques associated with parameters for the combination of ML models, as described in more detail elsewhere herein. In some aspects, a network node described herein is the base station 110, is included within the base station 110, or includes one or more components of the base station 110 shown in FIG. 2. For example, the controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or any other component(s) of FIG. 2 may perform or direct operations, such as process 800 of FIG. 8, process 900 of FIG. 9, and / or other processes as described herein. The memory 242 and the memory 282 may store data and program codes for the base station 110 and the UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, the one or more instructions, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly or after compiling, translating, and / or interpreting), may cause the one or more processors, UE 120, and / or base station 110 to perform or direct operations of, for example, process 800 of FIG. 8, process 900 of FIG. 9, and / or other processes as described herein. In some examples, executing instructions may include executing instructions, translating instructions, compiling instructions, and / or interpreting instructions, among other examples.

[0046]

[0053] In some aspects, a UE (e.g., UE 120) includes means for transmitting capability information indicating support for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML models, and / or means for receiving one or more instructions to use one or more of the ML models based at least in part on the capability information. Means for causing a UE to perform operations described herein may include, for example, one or more of communications manager 140, antenna 252, modem 254, MIMO detector 256, receive processor 258, transmit processor 264, TX MIMO processor 266, controller / processor 280, or memory 282.

[0047]

[0054] In some aspects, a network node (e.g., base station 110) includes means for receiving capability information indicative of support by the UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model, and / or means for transmitting one or more instructions to use one or more of the ML models based at least in part on the capability information. In some aspects, means for causing a network node to perform operations described herein may include, for example, one or more of communications manager 150, transmit processor 220, TX MIMO processor 230, modem 232, antenna 234, MIMO detector 236, receive processor 238, controller / processor 240, memory 242, or scheduler 246.

[0048]

[0055] 2 are shown as separate components, the functionality described above with respect to the blocks may be implemented in a single hardware, software, or combined component, or in various combinations of components. For example, functionality described with respect to transmit processor 264, receive processor 258, and / or TX MIMO processor 266 may be implemented by or under the control of controller / processor 280.

[0049]

[0056] As noted above, Figure 2 is provided as an example. Other examples may differ from those described with respect to Figure 2.

[0050]

[0057] FIG. 3 is a diagram illustrating an example disaggregated base station architecture 300 in accordance with the present disclosure.

[0051]

[0058] The deployment of a communication system such as a 5G NR system may be configured in multiple ways with various components or parts. In a 5G NR system or network, a network node, a network entity, a mobility element of the network, a RAN node, a core network node, a network element, or a network equipment such as a base station (BS, e.g., base station 110), or one or more units (or one or more components) performing a base station function may be implemented in an aggregated or non-aggregated architecture. For example, a BS (such as a Node B (NB), eNB, NR BS, 5G NB, access point (AP), TRP, or cell) may be implemented as an aggregated base station (also known as a standalone BS or monolithic BS) or a non-aggregated base station.

[0052]

[0059] An aggregated base station may be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. A non-aggregated base station may be configured to utilize a protocol stack that is physically or logically distributed between two or more units (e.g., one or more CUs, one or more DUs, or one or more RUs). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU or alternatively geographically or virtually distributed across one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of the CU, DU, and RU may also be implemented as a virtual unit, i.e., a virtual centralized unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0053]

[0060] The operation of a base station type or network design may take into account the aggregation characteristics of the base station functions. For example, a non-aggregated base station may be utilized in an integrated access backhaul (IAB) network, an O-RAN (such as a network configuration sponsored by the O-RAN Alliance), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Non-aggregation may include distributing functions across two or more units in various physical locations, as well as virtually distributing the functions of at least one unit, which may allow flexibility in network design. Various units of a non-aggregated base station, or a non-aggregated RAN architecture, may be configured for wired or wireless communication with at least one other unit.

[0054]

[0061] The disaggregated base station architecture shown in FIG. 3 may include one or more CUs 310 that may communicate directly with the core network 320 via a backhaul link or indirectly with the core network 320 through one or more disaggregated base station units (such as a quasi-RT RAN RIC 325 via an E2 link, or a non-RT RIC 315 associated with a service management and orchestration (SMO) framework 305, or both). The CUs 310 may communicate with one or more DUs 330 via respective midhaul links, such as an F1 interface. The DUs 330 may communicate with one or more RUs 340 via respective fronthaul links. The RUs 340 may communicate with respective UEs 120 via one or more radio frequency (RF) access links. In some implementations, a UE 120 may be served by multiple RUs 340 simultaneously.

[0055]

[0062] Each of the units (e.g., CU 310, DU 330, RU 340), as well as quasi-RT RIC 325, non-RT RIC 315, and SMO framework 305, may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) over a wired or wireless transmission medium. Each of the units, or an associated processor or controller that provides instructions to the unit's communication interface, may be configured to communicate with one or more of the other units over a transmission medium. For example, a unit may include a wired interface configured to receive or transmit signals to one or more of the other units over a wired transmission medium. In addition, a unit may include a wireless interface, which may include a receiver, transmitter, or transceiver (such as an RF transceiver), configured to receive signals from and / or transmit signals to one or more of the other units over the wireless transmission medium.

[0056]

[0063] In some aspects, the CU 310 may host one or more higher layer control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), Service Data Adaptation Protocol (SDAP), and the like. Each control function may be implemented with an interface configured to communicate signals with other control functions hosted by the CU 310. The CU 310 may be configured to handle user plane functions (e.g., Central Unit - User Plane (CU-UP)), control plane functions (e.g., Central Unit - Control Plane (CU-CP)), or a combination thereof. In some implementations, the CU 310 may be logically divided into one or more CU-UP units and one or more CU-CP units. The CU-UP units may communicate bidirectionally with the CU-CP units over an interface such as an E1 interface when implemented in an O-RAN configuration. The CU 310 may be implemented to communicate with the DU 330 as needed for network control and signaling.

[0057]

[0064] The DU 330 may correspond to a logical unit including one or more base station functions for controlling the operation of one or more RUs 340. In some aspects, the DU 330 may host one or more of a Radio Link Control (RLC) layer, a Medium Access Control (MAC) layer, and one or more upper physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional division such as that defined by the 3rd Generation Partnership Project (3GPP). In some aspects, the DU 330 may further host one or more lower PHY layers. Each layer (or module) may be implemented with an interface configured to communicate signals with other layers (and modules) hosted by the DU 330 or with a control function hosted by the CU 310.

[0058]

[0065] The lower layer functionality may be implemented by one or more RUs 340. In some deployments, the RUs 340 controlled by the DU 330 may correspond to logical nodes hosting RF processing functions, or lower PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on a functional division such as a lower layer functional division. In such an architecture, the RU(s) 340 may be implemented to handle over the air (OTA) communications with one or more UEs 120. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU(s) 340 may be controlled by the corresponding DU 330. In some scenarios, this configuration may enable the DU(s) 330 and CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0059]

[0066] The SMO framework 305 may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO framework 305 may be configured to support deployment of dedicated physical resources for RAN coverage requirements that may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 305 may be configured to interact with a cloud computing platform (such as an open cloud (O-cloud) 390) to perform network element lifecycle management (e.g., instantiate virtualized network elements) via a cloud computing platform interface (e.g., an O2 interface). Such virtualized network elements may include, but are not limited to, the CU 310, the DU 330, the RU 340, and the quasi-RT RIC 325. In some implementations, the SMO framework 305 may communicate with hardware aspects of a 4G RAN, such as an open eNB (O-eNB) 311, via an O1 interface. Additionally, in some implementations, the SMO framework 305 can communicate directly with one or more RUs 340 via an O1 interface. The SMO framework 305 can also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305.

[0060]

[0067] The non-RT RIC 315 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, Artificial Intelligence / Machine Learning (AI / ML) workflows including model training and updates, or policy-based guidance of applications / features in the quasi-RT RIC 325. The non-RT RIC 315 may be coupled to or communicate with the quasi-RT RIC 325 (e.g., via an A1 interface). The quasi-RT RIC 325 may be configured to include logic functions that enable near real-time control and optimization of RAN elements and resources through one or more CUs 310, one or more DUs 330, or both, and data collection and action on interfaces connecting the O-eNB to the quasi-RT RIC 325 (e.g., via an E2 interface).

[0061]

[0068] In some implementations, the non-RT RIC 315 may receive parameters or external enrichment information from an external server to generate AI / ML models to be deployed to the quasi-RT RIC 325. Such information may be utilized by the quasi-RT RIC 325 or may be received at the SMO framework 305 or the non-RT RIC 315 from non-network data sources or from network functions. In some examples, the non-RT RIC 315 or the quasi-RT RIC 325 may be configured to adjust RAN behavior or performance. For example, the non-RT RIC 315 may employ AI / ML models to monitor long-term trends and patterns in performance and implement corrective actions through the SMO framework 305 (e.g., reconfiguration via O1) or through the creation of RAN management policies (e.g., A1 policies).

[0062]

[0069] As noted above, Figure 3 is provided as an example. Other examples may differ from those described with respect to Figure 3.

[0063]

[0070] 4 is a diagram illustrating an example 400 associated with communicating UE capabilities for ML models according to the present disclosure. As shown in FIG. 4, a network node and a UE may communicate over a wireless network (e.g., wireless network 100). The UE may support one or more ML models associated with communicating with the network node.

[0064]

[0071] The UE may receive, and the network node may send, a UE capability inquiry, as indicated by reference numeral 405. For example, the network node may request an indication of supported ML models and / or the capabilities of each of the ML models.

[0065]

[0072] The UE may transmit, and the network node may receive, a capability report associated with individual ML models, as indicated by reference numeral 410. For example, the capability report may indicate each ML model supported and may indicate performance parameters for each of the supported ML models.

[0066]

[0073] The UE may receive, and the network node may transmit, an indication of a set of one or more ML models to use in communicating with the network node, as indicated by reference numeral 415. The ML models may include ML models that the UE may execute to improve communication efficiency when communicating via the network node.

[0067]

[0074] The UE may indicate values ​​of the performance parameters for each of the ML models when used individually, however, the value associated with a first ML model may vary based at least in part on other ML models used in combination with the first ML model.

[0068]

[0075] The ML models used in the combination of ML models may compete for resources of the UE, such as the UE's central processing unit (CPU) resources, neural processing unit (NPU) resources, graphics processing unit (GPU) resources, memory resources, and / or input / output (I / O) resources, among other examples. For example, the ML models may share and / or compete for specialized resources other than general resources, such as specialized hardware acceleration modules like Fast Fourier Transform (FFT) modules, among other examples.

[0069]

[0076] Additionally or alternatively, multiple ML models used in combination may target the same or related network functions, such as a first ML model controlling radio resource management (RRM) measurements and a second ML model controlling cell reselection. In this case, the UE may consume resources for the first and second ML models that may be unnecessary and / or overlapping, and may consume resources that could otherwise be used in applying another ML model. Furthermore, multiple ML models used in combination may have dependencies, such as a first ML model having an output that is used as an input for a second ML model.

[0070]

[0077] In some examples, the first ML model may include a CSI reporting ML model for determining a set of subbands to use for reporting. Accurate selection of the set of subbands using the first ML model may improve communication efficiency and / or reduce overhead. However, the second ML model consumes resources (e.g., computing resources and / or memory resources, among other examples) required by the first ML model, and the UE may fail to identify the set of subbands before the CSI reporting expires and / or becomes stale.

[0071]

[0078] In these cases, among other examples, the reported values ​​of the performance parameters for each of the ML models when used individually may not be representative of the performance parameters of the ML models when used in the model combination of the ML models. For example, the performance of the ML models when used in the model combination may be reduced and / or diminished to a point where use of the ML models reduces communication efficiency and / or consumes unnecessary power, communication, network, and / or computing resources, based at least in part on, for example, the latency in generating the output of the ML models.

[0072]

[0079] As noted above, Figure 4 is provided as an example. Other examples may differ from those described with respect to Figure 4.

[0073]

[0080] In some aspects described herein, the UE may indicate performance parameters for the ML models when used in different model combinations. For example, the UE may transmit capability information indicating support for one or more model combinations of ML models, where the capability information indicates one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model. In some aspects, the mapping between the model identification and the performance class indication is not fixed and is based at least in part on the combination in which the associated ML model is used. In some aspects, the performance parameters may be based at least in part on the ML models competing for resources of the UE, such as CPU resources, NPU resources, GPU resources, memory resources, and / or I / O resources of the UE, among other examples.

[0074]

[0081] In some aspects, the UE may indicate supported model combinations (eg, in the same or a separate communication as the indication of the performance parameters) and / or may indicate unsupported model combinations.

[0075]

[0082] The UE may transmit capability information including a list of model combinations (e.g., indicating combinations of ML models the UE may support). The capability information may also include information about the first model combination indicating a first ML model and an associated indication of the performance of the first ML model when used in the first model combination (e.g., model capability class), and a second ML model identification and an associated indication of the performance of the second ML model when used in the first model combination. The information about the first model combination may include an indication of the capabilities for any number of ML models supported by the UE for the combination. The capability information may also include information about the second model combination indicating a third ML model identification (e.g., the same ML model identification as the first or second ML model identification, or an additional ML model identification) and an associated indication of the performance of the third ML model when used in the second model combination, and a fourth ML model identification (e.g., the same ML model identification as the first or second ML model identification, or an additional ML model identification) and an associated indication of the performance of the fourth ML model when used in the first model combination. In some aspects, the ML models may have different indications of performance when used in different model combinations.

[0076]

[0083] In some aspects, the indication of performance may map to a set and / or value of a performance metric. For example, the indication of performance may include an indication of a performance class that maps to a value of a performance parameter related to, for example, an AI engine, memory, quantization (e.g., granularity of the model output), and / or delay in generating the output. The value of the performance parameter may be an explicit value and / or may be relative to the value of the performance parameter when the ML model is used independently (e.g., not in combination with other ML models). In some aspects, the mapping may be defined in a table or other data storage structure. The mapping may be defined in a communication protocol, communication standard, and / or via two-way or multi-way coordination. For example, a UE vendor and an infrastructure vendor may share the same understanding of the meaning of each performance class and / or other indication of performance.

[0077]

[0084] In some aspects, the UE may transmit the capability information in an RRC message or other message type indicating the capabilities. The UE may report the capability information via a portion of the UE radio capabilities (e.g., received by the base station and forwarded to the core network network node), the UE core network capabilities (e.g., received by the core network network node and forwarded to the network node), and / or the UE ML capabilities (e.g., a new indication, or combined with the UE radio capabilities or core network capability information). In some aspects, based at least in part on the UE reporting capability information related to the model combination to the first network node, the first network node may forward the capability information to the second network node and / or additional network nodes.

[0078]

[0085] Based at least in part on the UE indicating performance parameters of the ML model when used in combination with other ML models, the UE may provide an indication of the performance of the ML model with improved accuracy to the network node. In this manner, the network node may configure the UE to use a combination of ML models based at least in part on the improved accuracy, such that performance of the ML model may be sufficient to improve communication efficiency and / or save power, communication, network, and / or computing resources that might otherwise be consumed to attempt to use additional ML models with further reduced performance.

[0079]

[0086] 5 is a diagram of an example 500 associated with parameters for a combination of ML models according to the present disclosure. As shown in FIG. 5, one or more network nodes (e.g., base station 110, core network node, CU, DU, and / or RU) may communicate with a UE (e.g., UE 120). In some aspects, the network nodes and the UE may be part of a wireless network (e.g., wireless network 100). The UE and the network nodes may establish a wireless connection prior to the operations shown in FIG. 5.

[0080]

[0087] As indicated by reference numeral 505, a network node of one or more network nodes may transmit configuration information, and the UE may receive the configuration information. In some aspects, the UE may receive the configuration information via one or more of RRC signaling, one or more Medium Access Control (MAC) control elements (CEs), and / or Downlink Control Information (DCI), among other examples. In some aspects, the configuration information may include an indication of one or more configuration parameters (e.g., already known to the UE and / or previously indicated by a network node or other network device) for selection by the UE, and / or explicit configuration information for use by the UE to configure the UE, among other examples.

[0081]

[0088] In some aspects, the configuration information may indicate that the UE should transmit capability information for using ML models. In some aspects, the configuration information may indicate that the UE should transmit an indication of a maximum number of ML models that may be combined (e.g., configured to use during a communication). Additionally or alternatively, the configuration information may indicate that the UE should transmit an indication of supported and / or unsupported model combinations. In some aspects, the configuration information may indicate a configuration for the UE to transmit one or more indications of capability information. For example, the configuration information may indicate that the UE should transmit capability information via an RRC communication. In some aspects, the configuration information may indicate that the UE should transmit the same or a different communication as the capability information and an indication of a maximum number of ML models that may be combined and / or an indication of supported and / or unsupported model combinations.

[0082]

[0089] In some aspects, the configuration information may indicate that the capability information should indicate one or more performance parameters for each ML model based at least in part on a model combination of additional ML models used with the respective ML model. In some aspects, the configuration information may indicate that the capability information should indicate a model combination and one or more performance parameters (e.g., values ​​of one or more performance parameters) for one or more ML models included in the model combination, where the one or more performance parameters are based at least in part on other ML models used in the model combination. For example, the configuration information may indicate that the capability information should indicate a performance parameter for the ML model for each of the model combinations that include the ML model. The ML models may have different performance parameters for different model combinations.

[0083]

[0090] The UE may configure itself based at least in part on the configuration information. In some aspects, the UE may be configured to perform one or more operations described herein based at least in part on the configuration information.

[0084]

[0091] As indicated by reference numeral 510, the UE may identify one or more model combinations of ML models that the UE supports and / or that the UE does not support (e.g., ML models associated with communicating with a network node, an additional network node, and / or an application server). For example, the UE may identify support for multiple ML models (e.g., communication-based ML models) based at least in part on overlapping resource demands (e.g., using primarily different processing units) (e.g., based at least in part on UE hardware and / or software), based at least in part on total resource demands that the UE supports, based at least in part on target network capabilities, and / or based at least in part on dependencies, among other examples.

[0085]

[0092] In some aspects, the ML models may include one or more decision tree models, one or more decision forest models, one or more convolutional neural network models, one or more cluster models, one or more linear regression models, one or more feedforward neural network models, and / or one or more recurrent neural network models, among other examples. A model combination may include one or more types of ML models.

[0086]

[0093] As indicated by reference numeral 515, the UE may determine one or more performance parameters for the ML model with respect to one or more model combinations. For example, the UE may determine a first set of one or more performance parameters (e.g., AI engine performance, memory performance, quantization (e.g., granularity of model output), and / or delay in generating output) associated with the ML model based at least in part on the ML model being in a first model combination. Additionally or alternatively, the UE may determine a second set of one or more performance parameters associated with the ML model based at least in part on the ML model being in a second model combination (e.g., a combination of the ML model with a set of one or more ML models different from the first model combination).

[0087]

[0094] As indicated by reference numeral 520, the UE may transmit, and the network node may receive, capability information indicating support for one or more model combinations and / or one or more performance parameters for the ML models (e.g., ML models for communication) for the one or more model combinations. For example, the capability information may indicate respective performance parameters for each ML model as used in the model combination. In some aspects, the capability information may indicate a first performance parameter for a first ML model of the model combination, a second performance parameter for a second ML model of the model combination, and / or a third performance parameter for a third ML model of the model combination, etc. In some aspects, the performance parameters of the ML models may be different when indicated for different model combinations.

[0088]

[0095] In some aspects, the capability information may indicate support for one or more model combinations based at least in part on including an indication of supported model combinations and / or an indication of unsupported model combinations. In some aspects, the UE may transmit the capability information in a capability report. In some aspects, the capability information includes or is included in UE radio capability information, ML capability information, and / or core network capability information. In some aspects, the UE may transmit the capability information to a first network node for forwarding to a second network node.

[0089]

[0096] In some aspects, the model combination may be based at least in part on a first set of ML models associated with a RAN network node, a second set of ML models associated with a core network node, and / or a third set of ML models associated with an application server, In some aspects, each ML model of the model combination is associated with only one of the RAN network node, the core network node, or the application server.

[0090]

[0097] In some aspects, the UE may indicate one or more performance parameters based at least in part on including one or more instructions. For example, the one or more instructions may include a hash of values ​​of a set of performance metrics of the ML models for the model combination, an indicator (e.g., a mapping indicator) that maps to values ​​of the set of performance metrics, or a performance class of the ML models for the model combination. In some aspects, the indicator may map to values ​​of the set of performance metrics based at least in part on a communication protocol and / or definition based at least in part on the UE and / or a network node configured to communicate with the UE. In some aspects, the indicator may map to values ​​of the set of performance metrics based at least in part on a definition based at least in part on a core network node (e.g., associated with the ML model) and / or a RAN network node.

[0091]

[0098] In some aspects, the one or more performance parameters indicate processing resources available to apply to the ML models when they are used in the model combination, memory resources available to apply to the ML models when they are used in the model combination, quantization of the ML models when they are used in the model combination, and / or a value of delay in using the ML models associated in the model combination.

[0092]

[0099] In some aspects, the UE may transmit the capability information via an RRC message or another type of communication. In some aspects, the RRC message or other type of communication may include an indication of a set of one or more model combinations supported or not supported by the UE. In some aspects, the RRC message or other type of communication may include an indication of a maximum number of ML models supported for inclusion in the model combination. In some aspects, the RRC message or other type of communication may include an indication of a first model combination including a first indication of model parameters associated with a first ML model of the model combination. The indication of the first model combination may include a second indication of model parameters associated with a second ML model of the model combination. In some aspects, the RRC message or other type of communication may include an indication of a second model combination including a third indication of model parameters associated with a third ML model of the second model combination and a fourth indication of model parameters associated with a fourth ML model of the second model combination. In some aspects, the first ML model or the second ML model may be the same ML model as the third ML model or the fourth ML model, and the same ML model has different indications of model parameters based at least in part on the same ML model being used in the different model combinations. For example, the first ML model and the third ML model may be the same ML model, and the first indication of the model parameters may be associated with a first set of one or more values, and the third indication of the model parameters may be associated with a second set of one or more values, and the first set of one or more values ​​may be different from the second set of one or more values.

[0093]

[0100] As indicated by reference numeral 525, the network node may forward the capability information to an additional network node (e.g., a core network node or a RAN network node) of the one or more network nodes. For example, the network node may forward the capability information to the additional network node based at least in part on the additional network node being associated with an ML model of one or more model combinations. For example, the core network node may control, support, and / or be affected by operations associated with ML models for higher layers of communication (e.g., L3 and above). Similarly, the RAN network node may control, support, and / or be affected by operations associated with ML models for lower layers of communication (e.g., L2 and below).

[0094]

[0101] In some aspects, the network node may modify (e.g., add or remove portions of) the capability information before forwarding it to the additional network node. For example, a first portion of the capability information may be intended for the network node and a second portion of the capability information may be intended for the additional network node (e.g., a core network node or an additional RAN network node). The network node may forward only the portion of the capability information intended for the additional network node (e.g., via a destination identity and / or based at least in part on the type of capability information).

[0095]

[0102] As indicated by reference numeral 530, the network node may identify a model combination for the UE to use for communication. The network node may identify the model combination based at least in part on the capability information. In some aspects, the network node may identify the model combination to optimize communication efficiency and / or power consumption based at least in part on one or more performance parameters of the ML models of the model combination.

[0096]

[0103] For example, the network node may identify a first model combination that would provide the highest amount of communication efficiency if the UE were able to provide full resources for each ML model of the first model combination. However, the first model combination may not provide the highest amount of communication efficiency because the UE indicates, at least in part, that one or more of the ML models of the first model combination will have reduced resources available (e.g., based at least in part on the ML models competing for resources). For example, a second model combination may include a different set of ML models that may not be as efficient as those of the first model combination if both had full resources available, and the UE indicates an amount of resources available for the models of the second model combination that the second model combination will provide a higher amount of communication efficiency than the first model combination. In this manner, the network node may select a model combination based, at least in part, on the resources available for the ML models of the different model combinations and the amount of communication efficiency gained by using the ML models with the resources available for the ML models.

[0097]

[0104] As indicated by reference numeral 535, the UE may receive, and the network node may transmit, an indication of the model combination. For example, the UE may receive, an indication of the model combination based at least in part on the capability information. In this manner, the UE may receive, an indication to use one or more of the ML models based at least in part on the capability information. For example, the UE may receive, an indication to use an ML model belonging to the indicated model combination.

[0098]

[0105] As indicated by reference numeral 540, the UE and the network node may communicate based at least in part on the ML model of the model combination. In some aspects, the UE may configure wireless communications (e.g., RAN configuration) of the UE using a selected model combination. For example, based at least in part on the selected model combination, the UE may configure connection operations (e.g., random access channel (RACH) or physical RACH (PRACH) configuration), traffic management operations, timing synchronization operations, measurement operations, reporting operations (e.g., channel state information (CSI) reports), reference signal configuration, handover operations, and / or resource configuration operations, among other examples.

[0099]

[0106] In some aspects, communicating based at least in part on the ML models may include applying the ML models of a model combination to improve communication efficiency. The UE may apply a set of ML models to one or more network functions, such as RRM measurements, CSI reporting, and / or cell reselection, among other examples.

[0100]

[0107] Based at least in part on the UE indicating performance parameters of the ML model when used in combination with other ML models, the UE may provide an indication of the performance of the ML model with improved accuracy to the network node. In this manner, the network node may configure the UE to use a combination of ML models based at least in part on the improved accuracy, such that performance of the ML model may be sufficient to improve communication efficiency and / or save power, communication, network, and / or computing resources that might otherwise be consumed to attempt to use additional ML models with further reduced performance.

[0101]

[0108] As noted above, Figure 5 is provided as an example. Other examples may differ from those described with respect to Figure 5. For example, one or more of the operations described with respect to Figure 5 may be omitted or may be performed by an additional node (e.g., a network node or a UE).

[0102]

[0109] 6 is a diagram of an example 600 associated with parameters for a combination of ML models according to the present disclosure. With reference to FIG. 6, one or more network nodes (e.g., base station 110, core network node, CU, DU, and / or RU) may be in communication with a UE (e.g., UE 120). In some aspects, the network nodes and the UE may be part of a wireless network (e.g., wireless network 100). The UE and the network nodes may establish a wireless connection prior to the operations illustrated in FIG. 6.

[0103]

[0110] As shown in FIG. 6, the indication of the performance parameters 605 (e.g., performance class) for the combination of ML models may be based at least in part on a mapping of the indication of the performance parameters 605 to the set of parameters 610 and the set of performance metric values ​​615 for the set of parameters. For example, an indication that a first ML model is associated with performance indicator A (e.g., performance class A) when in a first model combination indicates that the first ML model is expected to perform with a performance value 615 of the set of parameters 610 associated with performance indicator A (e.g., the performance value in the same row as indicator A) when used in the first model combination. Similarly, an indication that a first ML model is associated with performance indicator C when in a second model combination indicates that the first ML model is expected to perform with a performance value 615 of the set of parameters 610 associated with performance indicator C (e.g., the performance value in the same row as indicator C) when used in the second model combination. Other performance indicators may map to other combinations of performance values ​​and may be associated with other ML models in one or more model combinations, not just the first ML model.

[0104]

[0111] In some aspects, the performance parameters 605 may similarly include a hash of the values ​​of the set of parameters 610. In this manner, the performance parameter indication 605 may use a reduced amount of overhead as compared to the amount of overhead that would be required to explicitly indicate each of the set of parameters 610 without hashing. In some aspects, the indicator may include a bit value associated with the indicator or may include a bitmap having a bit associated with each candidate indicator.

[0105]

[0112] In some aspects, the capability information may indicate performance indicators of the ML models in each indicated model combination. For example, the capability information may include an indication of a model combination set indicating all reported model combinations. The elements of the model combination set may be model combinations that the UE supports. For a model combination (e.g., for each model combination), the UE may indicate a list of ML models of the model combination and one or more model parameters. The one or more model parameters may include model identification for the included ML models and performance indicators of the ML models (e.g., a performance indicator for each of the included ML models).

[0106]

[0113] As noted above, Figure 6 is provided as an example. Other examples may differ from those described with respect to Figure 6.

[0107]

[0114] 7 is a diagram of an example 700 associated with parameters for a combination of ML models according to the present disclosure. With reference to FIG. 7, one or more network nodes (e.g., base station 110, core network node, CU, DU, and / or RU) may be in communication with a UE (e.g., UE 120). In some aspects, the network nodes and the UE may be part of a wireless network (e.g., wireless network 100). The UE and the network nodes may establish a wireless connection prior to the operations illustrated in FIG. 7.

[0108]

[0115] 7, the capability information may indicate that the UE supports model combinations of up to four ML models. The model combination list may include a first model combination 705, a second model combination 710, a third model combination 715, a fourth model combination 720, a fifth model combination 725, and / or a sixth model combination 730, among other examples. In some aspects, the model combinations may have a uniform number of model identifiers (IDs) or may have different numbers of model IDs. For example, each model combination may have the same number of model IDs, or some model combinations may have different numbers of model IDs.

[0109]

[0116] The capability information, when used in the first combination 705, may indicate that model identification (ID) 1 (e.g., the ML model associated with model ID 1) has performance indicator 1, model ID 2 has performance indicator 2, model ID 3 has performance indicator 3, and model ID 4 has performance indicator 4. The performance indicators may map to the same or different performance parameters. For example, performance indicators 1 and 3 may be indicator A of FIG. 6, performance indicator 2 may be indicator B of FIG. 6, and / or performance indicator 4 may be indicator C of FIG. 6, each of which is associated with a set of one or more performance values.

[0110]

[0117] Similarly, the second model combination 710, the third model combination 715, the fourth model combination 720, the fifth model combination 725, and / or the sixth model combination 730 may indicate a model ID and an association indicator for the model combination. In some aspects, the model ID has an association indicator that maps to different performance values ​​when used in different combinations based at least in part on other ML models used in the different combinations. In some aspects, the model ID has an associated indicator that maps to the same performance value when used in different combinations based at least in part on other ML models used in the different combinations.

[0111]

[0118] As noted above, Figure 7 is provided as an example. Other examples may differ from those described with respect to Figure 7.

[0112]

[0119] 8 illustrates an example process 800 performed, for example, by a UE, in accordance with the present disclosure. The example process 800 is an example in which a UE (e.g., UE 120) performs operations associated with a performance indicator for a combination of ML models.

[0113]

[0120] 8, in some aspects, process 800 may include transmitting capability information indicating support for one or more model combinations of the ML models, where the capability information further indicates one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model (block 810). For example, the UE may transmit (e.g., using the communications manager 140 and / or the transmitting component 1004 shown in FIG. 10) capability information indicating support for one or more model combinations of the ML models, where the capability information further indicates one or more performance parameters of the ML models of the ML models for the model combination of the one or more model combinations that include the ML model, as described above.

[0114]

[0121] 8, in some aspects, process 800 may include receiving one or more instructions to use one or more of the ML models based at least in part on the capability information (block 820). For example, the UE may receive (e.g., using the communications manager 140 and / or the receiving component 1002 shown in FIG. 10) one or more instructions to use one or more of the ML models based at least in part on the capability information, as described above.

[0115]

[0122] Process 800 may include additional aspects, such as any single aspect, or any combination of aspects, described below and / or in conjunction with one or more other processes described elsewhere herein.

[0116]

[0123] In a first aspect, the performance parameter of the one or more performance parameters includes one or more of: a hash of values ​​of the set of performance metrics of the ML models for the model combination, an indicator that maps to values ​​of the set of performance metrics, or a performance class of the ML models for the model combination.

[0117]

[0124] In a second aspect, alone or in combination with the first aspect, the indicator maps to a value of a set of performance metrics based at least in part on one or more of a communications protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE.

[0118]

[0125] In a third aspect, alone or in combination with one or more of the first and second aspects, the one or more performance parameters indicate one or more values ​​of processing resources available for applying the ML model, memory resources available for applying the ML model, quantization of the ML model, or delay in using the associated ML model.

[0119]

[0126] In a fourth aspect, alone or in combination with one or more of the first to third aspects, transmitting the capability information includes transmitting the capability information via an RRC message.

[0120]

[0127] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the RRC message comprises one or more of the following: an indication of a set of one or more model combinations, an indication of the model combination comprising a first indication of model parameters associated with an ML model of the model combination, where the ML model is a first ML model, and a second indication of model parameters associated with a second ML model of the model combination, or a third indication of model parameters associated with a third ML model of the further model combination, and a fourth indication of model parameters associated with a fourth ML model of the further model combination.

[0121]

[0128] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the first ML model and the third ML model are the same ML model, the first instruction of the model parameters is associated with a first set of one or more values, and the third instruction of the model parameters is associated with a second set of one or more values, and the first set of one or more values ​​is different from the second set of one or more values.

[0122]

[0129] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, the capability information includes one or more of UE radio capability information, ML capability information, or core network capability information.

[0123]

[0130] In an eighth aspect, either alone or in combination with one or more of the first to seventh aspects, transmitting the capability information includes transmitting the capability information to the first network node for forwarding to the second network node.

[0124]

[0131] In a ninth aspect, either alone or in combination with one or more of the first to eighth aspects, the one or more model combinations of ML models are based at least in part on one or more of: a first set of ML models associated with a Radio Access Network (RAN) network node, a second set of ML models associated with a Core Network (CN) network node, or a third set of ML models associated with an application server.

[0125]

[0132] In a tenth aspect, alone or in combination with one or more of the first through ninth aspects, the process 800 includes sending one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0126]

[0133] 8 illustrates example blocks of process 800, in some aspects process 800 may include additional, fewer, different, or differently configured blocks compared to the blocks illustrated in FIG 8. Additionally, or alternatively, two or more of the blocks of process 800 may be performed in parallel.

[0127]

[0134] 9 illustrates an example process 900 performed, for example, by a network node, in accordance with the present disclosure. The example process 900 is an example in which a network node (e.g., a base station 110 and / or a network node of FIG. 5) performs operations associated with a performance indicator for a combination of ML models.

[0128]

[0135] 9, in some aspects, process 900 may include receiving capability information indicative of support by the UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model (block 910). For example, the network node may receive (e.g., using the communications manager 150 and / or the receiving component 1102 shown in FIG. 11) capability information indicative of support by the UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model, as described above.

[0129]

[0136] 9, in some aspects, process 900 may include transmitting one or more instructions to use one or more of the ML models based at least in part on the capability information (block 920). For example, the network node (e.g., using the communications manager 150 and / or the transmitting component 1104 shown in FIG. 11) may transmit one or more instructions to use one or more of the ML models based at least in part on the capability information, as described above.

[0130]

[0137] Process 900 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0131]

[0138] In a first aspect, the performance parameter of the one or more performance parameters includes one or more of: a hash of values ​​of the set of performance metrics of the ML models for the model combination, an indicator that maps to values ​​of the set of performance metrics, or a performance class of the ML models for the model combination.

[0132]

[0139] In a second aspect, alone or in combination with the first aspect, the indicator maps to a value of a set of performance metrics based at least in part on one or more of a communications protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE.

[0133]

[0140] In a third aspect, alone or in combination with one or more of the first and second aspects, the one or more performance parameters indicate one or more values ​​of processing resources available for applying the ML model, memory resources available for applying the ML model, quantization of the ML model, or a delay in using the associated ML model.

[0134]

[0141] In a fourth aspect, alone or in combination with one or more of the first to third aspects, receiving the capability information includes receiving the capability information via an RRC message.

[0135]

[0142] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the RRC message comprises one or more of the following: an indication of a set of one or more model combinations, an indication of the model combination comprising a first indication of model parameters associated with an ML model of the model combination, where the ML model is a first ML model, and a second indication of model parameters associated with a second ML model of the model combination, or a third indication of model parameters associated with a third ML model of the further model combination, and a fourth indication of model parameters associated with a fourth ML model of the further model combination.

[0136]

[0143] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the first ML model and the third ML model are the same ML model, the first instruction of the model parameters is associated with a first set of one or more values, and the third instruction of the model parameters is associated with a second set of one or more values, and the first set of one or more values ​​is different from the second set of one or more values.

[0137]

[0144] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, the capability information includes one or more of UE radio capability information, ML capability information, or core network capability information.

[0138]

[0145] In an eighth aspect, either alone or in combination with one or more of the first through seventh aspects, the process 900 includes forwarding at least a portion of the capability information to additional network nodes.

[0139]

[0146] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the one or more model combinations of ML models are based at least in part on one or more of: a first set of ML models associated with a RAN network node, a second set of ML models associated with a CN network node, or a third set of ML models associated with an application server.

[0140]

[0147] In a tenth aspect, alone or in combination with one or more of the first through ninth aspects, the process 900 includes receiving one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0141]

[0148] 9 illustrates example blocks of process 900, in some aspects process 900 may include additional blocks, fewer blocks, different blocks, or differently configured blocks compared to the blocks illustrated in FIG 9. Additionally, or alternatively, two or more of the blocks of process 900 may be performed in parallel.

[0142]

[0149] FIG. 10 is a diagram of an example apparatus 1000 for wireless communication. The apparatus 1000 may be a UE, or a UE may include the apparatus 1000. In some aspects, the apparatus 1000 comprises a receiving component 1002 and a transmitting component 1004, which may communicate with one another (e.g., via one or more buses and / or one or more other components). As shown, the apparatus 1000 may communicate with another apparatus 1006 (such as a UE, a base station, or another wireless communication device) using the receiving component 1002 and the transmitting component 1004. As further shown, the apparatus 1000 may include a communications manager 1008 (e.g., communications manager 140). The communications manager 1008 may transmit control signaling to the transmitting component 1004 and / or receive control signaling via the receiving component 1002 to control communications of the apparatus 1000.

[0143]

[0150] In some aspects, the apparatus 1000 may be configured to perform one or more operations described herein with respect to FIGS. 5-7. Additionally or alternatively, the apparatus 1000 may be configured to perform one or more processes described herein, such as process 800 of FIG. 8. In some aspects, the apparatus 1000 and / or one or more components illustrated in FIG. 10 may include one or more components of a UE described with respect to FIG. 2. Additionally or alternatively, one or more components illustrated in FIG. 10 may be implemented within one or more components described with respect to FIG. 2. Additionally or alternatively, one or more components of the set of components may be implemented at least in part as software stored in a memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0144]

[0151] The receiving component 1002 may receive communications from the device 1006, such as reference signals, control information, data communications, or combinations thereof. The receiving component 1002 may provide the received communications to one or more other components of the device 1000. In some aspects, the receiving component 1002 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, among other examples) on the received communications and provide the processed signals to one or more other components of the device 1000. In some aspects, the receiving component 1002 may include one or more antennas, a modem, a demodulator, a MIMO detector, a receive processor, a controller / processor, a memory, or a combination thereof of a UE as described with respect to FIG.

[0145]

[0152] The transmitting component 1004 may transmit a communication, such as a reference signal, control information, a data communication, or a combination thereof, to the device 1006. In some aspects, one or more other components of the device 1000 may generate a communication and provide the generated communication to the transmitting component 1004 for transmission to the device 1006. In some aspects, the transmitting component 1004 may perform signal processing (such as filtering, amplifying, modulating, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, among other examples) on the generated communication and transmit the processed signal to the device 1006. In some aspects, the transmitting component 1004 may include one or more antennas, a modem, a modulator, a transmit MIMO processor, a transmit processor, a controller / processor, a memory, or a combination thereof, of a UE as described with respect to FIG. 2. In some aspects, the transmitting component 1004 may be co-located with the receiving component 1002 in a transceiver.

[0146]

[0153] The sending component 1004 may send capability information indicating support for one or more model combinations of the ML models, the capability information further indicating one or more performance parameters of the ML models of the ML models for the model combinations of the one or more model combinations that include the ML models. The receiving component 1002 may receive one or more instructions for using one or more of the ML models based at least in part on the capability information.

[0147]

[0154] The transmission component 1004 can transmit one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0148]

[0155] The number and configuration of components shown in Figure 10 are provided as an example. In practice, there may be additional, fewer, different, or differently configured components than those shown in Figure 10. Furthermore, two or more of the components shown in Figure 10 may be implemented within a single component, or a single component shown in Figure 10 may be implemented as multiple distributed components. Additionally, or instead, a set of components shown in Figure 10 may perform one or more functions that are described as being performed by another set of components shown in Figure 10.

[0149]

[0156] FIG. 11 is a diagram of an example apparatus 1100 for wireless communication. The apparatus 1100 may be a network node, or a network node may include the apparatus 1100. In some aspects, the apparatus 1100 comprises a receiving component 1102 and a transmitting component 1104 that may communicate with one another (e.g., via one or more buses and / or one or more other components). As shown, the apparatus 1100 may communicate with another apparatus 1106 (such as a UE, a base station, or another wireless communication device) using the receiving component 1102 and the transmitting component 1104. As further shown, the apparatus 1100 may include a communications manager 1108 (e.g., communications manager 150). The communications manager 1108 may transmit control signaling to the transmitting component 1104 and / or receive control signaling via the receiving component 1102 to control communications of the apparatus 1100.

[0150]

[0157] In some aspects, the device 1100 may be configured to perform one or more operations described herein with respect to FIGS. 5-7. Additionally or alternatively, the device 1100 may be configured to perform one or more processes described herein, such as process 900 of FIG. 9. In some aspects, the device 1100 and / or one or more components illustrated in FIG. 11 may include one or more components of a network node described with respect to FIG. 2. Additionally or alternatively, one or more components illustrated in FIG. 11 may be implemented within one or more components described with respect to FIG. 2. Additionally or alternatively, one or more components of the set of components may be implemented at least in part as software stored in a memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0151]

[0158] The receiving component 1102 may receive communications, such as reference signals, control information, data communications, or combinations thereof, from the device 1106. The receiving component 1102 may provide the received communications to one or more other components of the device 1100. In some aspects, the receiving component 1102 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, among other examples) on the received communications and provide the processed signals to one or more other components of the device 1100. In some aspects, the receiving component 1102 may include one or more antennas, a modem, a demodulator, a MIMO detector, a receive processor, a controller / processor, a memory, or a combination thereof of the network nodes described with respect to FIG.

[0152]

[0159] The transmitting component 1104 may transmit a communication, such as a reference signal, control information, a data communication, or a combination thereof, to the device 1106. In some aspects, one or more other components of the device 1100 may generate a communication and provide the generated communication to the transmitting component 1104 for transmission to the device 1106. In some aspects, the transmitting component 1104 may perform signal processing (such as filtering, amplifying, modulating, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, among other examples) on the generated communication and transmit the processed signal to the device 1106. In some aspects, the transmitting component 1104 may include one or more antennas, a modem, a modulator, a transmit MIMO processor, a transmit processor, a controller / processor, a memory, or a combination thereof of the network nodes described with respect to FIG. 2. In some aspects, the transmitting component 1104 may be co-located with the receiving component 1102 in a transceiver.

[0153]

[0160] The receiving component 1102 may receive capability information indicating support by the UE for one or more model combinations of ML models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model. The transmitting component 1104 may transmit one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0154]

[0161] The communications manager 1108 and / or the transmission component 1104 can forward at least a portion of the capability information to additional network nodes.

[0155]

[0162] The receiving component 1102 can receive one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0156]

[0163] The number and configuration of components shown in Figure 11 are provided as an example. In practice, there may be additional, fewer, different, or differently configured components than those shown in Figure 11. Furthermore, two or more of the components shown in Figure 11 may be implemented within a single component, or a single component shown in Figure 11 may be implemented as multiple distributed components. Additionally, or instead, a set of components shown in Figure 11 may perform one or more functions that are described as being performed by another set of components shown in Figure 11.

[0157]

[0164] The following provides a summary of several aspects of the disclosure.

[0158]

[0165] Aspect 1: A method of wireless communication performed by a user equipment (UE), comprising: transmitting capability information indicating support for one or more model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models for the model combinations of the one or more model combinations that include the ML models; and receiving one or more instructions to use one or more of the ML models based at least in part on the capability information.

[0159]

[0166] Aspect 2: The method of aspect 1, wherein the performance parameter of the one or more performance parameters includes one or more of: a hash of values ​​of the set of performance metrics of the ML models for the model combination, an indicator that maps to values ​​of the set of performance metrics, or a performance class of the ML models for the model combination.

[0160]

[0167] Aspect 3: The method of aspect 2, wherein the indicator maps to a value of a set of performance metrics based at least in part on one or more of a communication protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE.

[0161]

[0168] Aspect 4: A method as described in any of aspects 1 to 3, wherein the one or more performance parameters indicate values ​​for one or more of: processing resources available for applying the ML model, memory resources available for applying the ML model, quantization of the ML model, or delay in using the associated ML model.

[0162]

[0169] Example 5: The method of any one of Examples 1 to 4, wherein transmitting the capability information includes transmitting the capability information via a radio resource control (RRC) message.

[0163]

[0170] Aspect 6: The method of aspect 5, wherein the RRC message includes one or more of an indication of a set of one or more model combinations, an indication of a model combination including a first indication of model parameters associated with an ML model of the model combination, where the ML model is a first ML model, and a second indication of model parameters associated with a second ML model of the model combination, or an indication of an additional model combination including a third indication of model parameters associated with a third ML model of the additional model combination, and a fourth indication of model parameters associated with a fourth ML model of the additional model combination.

[0164]

[0171] Aspect 7: The method of aspect 6, wherein the first ML model and the third ML model are the same ML model, the first instruction of the model parameters is associated with a first set of one or more values, and the third instruction of the model parameters is associated with a second set of one or more values, and the first set of one or more values ​​is different from the second set of one or more values.

[0165]

[0172] Aspect 8: The method of any of aspects 1 to 7, wherein the capability information includes one or more of: UE radio capability information, ML capability information, or core network capability information.

[0166]

[0173] Example 9: The method of any of Examples 1 to 8, wherein transmitting the capability information includes transmitting the capability information to the first network node for forwarding to the second network node.

[0167]

[0174] Aspect 10: A method as described in any of aspects 1 to 9, wherein the one or more model combinations of ML models are based at least in part on one or more of a first set of ML models associated with a Radio Access Network (RAN) network node, a second set of ML models associated with a Core Network (CN) network node, or a third set of ML models associated with an application server.

[0168]

[0175] Aspect 11: The method of any of aspects 1 to 10, further comprising sending one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0169]

[0176] Aspect 12: A method of wireless communication performed by a network node, the method including: receiving capability information indicating support by a user equipment (UE) for one or more model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models of the one or more ML models for the model combination of the one or more model combinations that include the ML model; and transmitting one or more instructions to use the one or more of the ML models based at least in part on the capability information.

[0170]

[0177] Aspect 13: The method of aspect 12, wherein the performance parameter of the one or more performance parameters includes one or more of: a hash of values ​​of the set of performance metrics of the ML models for the model combination, an indicator that maps to values ​​of the set of performance metrics, or a performance class of the ML models for the model combination.

[0171]

[0178] Aspect 14: The method of aspect 12 or 13, wherein the indicator maps to a value of a set of performance metrics based at least in part on one or more of a communication protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE.

[0172]

[0179] Aspect 15: A method as described in any of aspects 12 to 14, wherein the one or more performance parameters indicate values ​​for one or more of: processing resources available for applying the ML model, memory resources available for applying the ML model, quantization of the ML model, or delay in using the associated ML model.

[0173]

[0180] Example 16: The method of any of Examples 12-15, wherein receiving the capability information includes receiving the capability information via a radio resource control (RRC) message.

[0174]

[0181] Aspect 17: The method of aspect 16, wherein the RRC message includes one or more of an indication of a set of one or more model combinations, an indication of a model combination including a first indication of model parameters associated with an ML model of the model combination, where the ML model is a first ML model, and a second indication of model parameters associated with a second ML model of the model combination, or an indication of an additional model combination including a third indication of model parameters associated with a third ML model of the additional model combination, and a fourth indication of model parameters associated with a fourth ML model of the additional model combination.

[0175]

[0182] Aspect 18: The method of aspect 17, wherein the first ML model and the third ML model are the same ML model, the first instruction of the model parameters is associated with a first set of one or more values, the third instruction of the model parameters is associated with a second set of one or more values, and the first set of one or more values ​​is different from the second set of one or more values.

[0176]

[0183] Aspect 19: The method of any of aspects 12 to 18, wherein the capability information includes one or more of: UE radio capability information, ML capability information, or core network capability information.

[0177]

[0184] Example 20: The method of any of Examples 12 to 19, further comprising forwarding at least a portion of the capability information to additional network nodes.

[0178]

[0185] Aspect 21: A method as described in any of aspects 12 to 20, wherein the one or more model combinations of ML models are based at least in part on one or more of a first set of ML models associated with a Radio Access Network (RAN) network node, a second set of ML models associated with a Core Network (CN) network node, or a third set of ML models associated with an application server.

[0179]

[0186] Aspect 22: The method of any of aspects 12 to 21, further comprising receiving one or more of an indication of a supported model combination or an indication of an unsupported model combination.

[0180]

[0187] Aspect 23: An apparatus for wireless communication in a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory, the instructions being executable by the processor to cause the apparatus to perform one or more of the methods of aspects 1 to 22.

[0181]

[0188] Aspect 24: A device for wireless communication, comprising: a memory; and one or more processors coupled to the memory, the one or more processors configured to perform one or more of the methods of aspects 1 to 22.

[0182]

[0189] Aspect 25: An apparatus for wireless communication, comprising at least one means for performing one or more of the methods of aspects 1-22.

[0183]

[0190] Aspect 26: A non-transitory computer-readable medium storing code for wireless communications, the code including instructions executable by a processor to perform one or more of the methods of aspects 1-22.

[0184]

[0191] Aspect 27: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions including one or more instructions that, when executed by one or more processors of a device, cause the device to perform one or more of the methods of aspects 1-22.

[0185]

[0192] The above disclosure provides illustration and description, but is not intended to be exhaustive or to limit the embodiments to the precise form disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of the embodiments.

[0186]

[0193] As used herein, the term "component" is intended to be broadly construed as hardware and / or a combination of hardware and software. "Software" is intended to be broadly construed to mean, among other examples, instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, and / or functions, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. As used herein, a "processor" is implemented in hardware and / or a combination of hardware and software. It will be apparent that the systems and / or methods described herein may be implemented in different forms of hardware and / or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not intended to limit aspects. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code, as one skilled in the art will appreciate that software and hardware may be designed to implement the systems and / or methods based at least in part on the description herein.

[0187]

[0194] As used herein, "meeting a threshold" can refer to a value being greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc., depending on the context.

[0188]

[0195] Although certain combinations of features are recited in the claims and / or disclosed herein, these combinations are not intended to limit the disclosure of the various aspects. Many of these features may be combined in ways not specifically recited in the claims and / or disclosed herein. The disclosure of the various aspects includes each dependent claim in combination with all other claims in the set of claims. As used herein, a phrase referring to "at least one of" a list of items refers to any combination of those items, including single members. As an example, "at least one of a, b, or c" is intended to encompass a, b, c, a+b, a+c, b+c, and a+b+c, as well as any combination having multiple identical elements (e.g., a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c, and c+c+c, or any other order of a, b, and c).

[0189]

[0196] No element, act, or instruction used herein should be construed as critical or essential unless expressly described as such. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more." Additionally, as used herein, the definite article "the" is intended to include one or more items referred to in relation to the definite article "the" and may be used interchangeably with "one or more." Additionally, as used herein, the terms "set" and "group" are intended to include one or more items and may be used interchangeably with "one or more." When only one item is intended, the phrase "only one" or similar language is used. Also, as used herein, terms such as "has," "have," and "having" are intended to be open-ended terms that do not limit the elements they modify (e.g., an element that "has" A may also have B). Additionally, the phrase "based on" is intended to mean "based at least in part on," unless expressly stated otherwise. Also, as used herein, the term "or" is intended to be inclusive when used in conjunction and may be used interchangeably with "and / or," unless expressly stated otherwise (e.g., when used in combination with "either" or "only one of").

Claims

1. A method of wireless communication performed by a user equipment (UE), comprising: transmitting capability information indicating supported or unsupported model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models based at least in part on the ML models being included in the model combination; receiving one or more instructions for using one or more of the ML models based at least in part on the capability information; A method comprising:

2. a performance parameter of the one or more performance parameters: a hash of values ​​of a set of performance metrics for the ML model based at least in part on the ML model being included in the model combination; an indicator that maps to the values ​​of the set of performance metrics; or a performance class of the ML model based at least in part on the inclusion of the ML model; [0033] The indicator: communication protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE; 10. The method of claim 1, wherein the mapping to the values ​​of the set of performance metrics is based at least in part on one or more of:

3. The one or more performance parameters are: the processing resources available for applying said ML model; the memory resources available to apply said ML model; quantization of the ML model; or the delay in using the associated ML model, The method of claim 1 , wherein the method indicates values ​​for one or more of:

4. transmitting the capability information via a Radio Resource Control (RRC) message; Further provided with The RRC message The model combination instruction includes: a first indication of model parameters associated with the ML model, the ML model being a first ML model; and a second indication of model parameters associated with a second ML model included in the model combination; an indication of the model combination, including: An indication of an additional model combination, a third indication of model parameters associated with a third ML model included in the additional model combination; and a fourth indication of model parameters associated with a fourth ML model included in the additional model combination; Additional model combination instructions, including and preferably one or more of: the first ML model and the third ML model are the same ML model; the first indication of the model parameter is associated with a first set of one or more values; a third indication of the model parameters associated with a second set of one or more values; The method of claim 1 , wherein the first set of one or more values ​​is different from the second set of one or more values.

5. The capability information is UE radio capability information, ML capability information, or Core network capability information, The method of claim 1 , comprising one or more of:

6. 10. The method of claim 1, further comprising transmitting the capability information to a first network node for forwarding to a second network node.

7. The supported or unsupported model combinations of the ML models are: a first set of the ML models associated with a Radio Access Network (RAN) network node; a second set of said ML models associated with a core network (CN) network node; or a third set of the ML models associated with an application server; The method of claim 1 , based at least in part on one or more of:

8. A method for wireless communications performed by a network node, comprising: receiving capability information associated with a user equipment (UE) indicating supported or unsupported model combinations of machine learning (ML) models and one or more performance parameters of the ML models among the one or more ML models based at least in part on the ML model being included in the model combination; sending one or more instructions for using one or more of the ML models based at least in part on the capability information; A method comprising:

9. a performance parameter of the one or more performance parameters: a hash of values ​​of a set of performance metrics for the ML model based at least in part on the ML model being included in the model combination; an indicator that maps to the values ​​of the set of performance metrics; or a performance class of the ML model based at least in part on the ML model's inclusion in the model combination; and preferably one or more of: The indicator: communication protocol, or a definition based at least in part on one or more of the UE or a network node configured to communicate with the UE; 9. The method of claim 8, wherein the mapping to the values ​​of the set of performance metrics is based at least in part on one or more of:

10. The one or more performance parameters are: the processing resources available for applying said ML model; the memory resources available to apply said ML model; quantization of the ML model; or the delay in using the associated ML model, 9. The method of claim 8, wherein the method indicates values ​​for one or more of:

11. transmitting the capability information via a Radio Resource Control (RRC) message; and preferably further comprising: The RRC message The model combination instruction includes: a first indication of model parameters associated with the ML model, the ML model being a first ML model; and a second indication of model parameters associated with a second ML model included in the model combination; an indication of the model combination, including: An indication of an additional model combination, a third indication of model parameters associated with a third ML model included in the additional model combination; and a fourth indication of model parameters associated with a fourth ML model included in the additional model combination; Additional model combination instructions, including [0033] the first ML model and the third ML model are the same ML model; the first indication of the model parameter is associated with a first set of one or more values; a third indication of the model parameters associated with a second set of one or more values; The method of claim 8 , wherein the first set of one or more values ​​is different from the second set of one or more values.

12. The capability information is UE radio capability information, ML capability information, or Core network capability information, 9. The method of claim 8, comprising one or more of: forwarding at least a portion of said capability information to additional network nodes; The method of claim 8 further comprising:

13. The supported or unsupported model combinations of the ML models are: a first set of the ML models associated with a Radio Access Network (RAN) network node; a second set of said ML models associated with a core network (CN) network node; or a third set of the ML models associated with an application server; The method of claim 8 , based at least in part on one or more of:

14. A user equipment (UE) for wireless communications, comprising: means for transmitting capability information indicating supported or unsupported model combinations of machine learning (ML) models, the capability information further indicating one or more performance parameters of the ML models based at least in part on the ML models being included in the model combination; means for receiving one or more instructions for using one or more of the ML models based at least in part on the capability information; A UE comprising:

15. A network node for wireless communications, comprising: means for receiving capability information associated with a user equipment (UE) indicating supported or unsupported model combinations of machine learning (ML) models, and one or more performance parameters of the ML models of the one or more ML models based at least in part on the ML model being included in the model combination; means for transmitting one or more instructions for using one or more of the ML models based at least in part on the capability information; A network node comprising:

Images