Machine learning for beam prediction with confidence indication

By using machine learning components in wireless communication systems to generate predicted communication metrics and confidence indications, the problem of inaccurate beam prediction is solved, and network performance and communication quality is improved.

CN119072864APending Publication Date: 2024-12-03QUALCOMM INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380035696.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-29
Filing Date
2023-04-25
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In wireless communication, the prior art is difficult to provide accurate beam prediction, resulting in poor scheduling decisions and affecting network performance.

Method used

By using machine learning components in user equipment (UE) and network nodes, combining input metrics and error measurements, predicted communication metrics and confidence indications are generated for performing wireless communication tasks. The machine learning component includes a machine learning model that is able to receive input metrics and error measurements and provide predicted communication metrics and confidence indications through machine learning functions.

Benefits of technology

Improves the accuracy of beam prediction, promotes more efficient scheduling decisions and higher quality communication, thereby improving network performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119072864A_ABST
    Figure CN119072864A_ABST
Patent Text Reader

Abstract

Aspects of the present disclosure generally relate to wireless communications. In some aspects, a user equipment (UE) may receive a signal. The UE may determine a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises: receiving, by the machine learning model, an input comprising an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input. The UE may perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication. Numerous other aspects are described.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims priority to U.S. non-provisional patent application No. 17 / 661,543, filed on April 29, 2022, entitled “MACHINE LEARNING FOR BEAM PREDICTIONS WITH CONFIDENCE INDICATIONS,” which is hereby expressly incorporated herein by reference. Technical Field

[0003] Aspects of the present disclosure relate generally to wireless communications, and to techniques and apparatus for machine learning for beam prediction with confidence indications. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies that can support 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 enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0005] A wireless network may include one or more base stations that support communications for a user equipment (UE) or multiple UEs. A UE may communicate with a base station via downlink communications and uplink communications. A "downlink" (or "DL") refers to the communication link from a base station to a UE, and an "uplink" (or "UL") refers to the communication link from a UE to a base station.

[0006] The above-mentioned multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different UEs to communicate at a city, country, region and / or global level. 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 integrate with other open standards by improving spectrum efficiency, reducing costs, improving services, utilizing new spectrum, and using orthogonal frequency division multiplexing (OFDM) (CP-OFDM) with cyclic prefix (CP) on the downlink, using 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 supporting beamforming, multiple input multiple output (MIMO) antenna technology and carrier aggregation, so as to better support mobile broadband Internet access. As the demand for mobile broadband access continues to increase, further improvements in LTE, NR and other radio access technologies remain useful. Summary of the invention

[0007] Some aspects described herein relate to a method of wireless communication performed by a user equipment (UE). The method may include receiving a signal. The method may include determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: receiving an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and providing the predicted communication metric and the confidence indication through the machine learning model based at least in part on a machine learning function and the input. The method may include performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0008] Some aspects described herein relate to a method of wireless communication performed by a network node. The method may include sending a machine learning configuration associated with a machine learning component, the machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model configured to: obtain an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and provide the predicted communication metric and the confidence indication through the machine learning model based at least in part on a machine learning function and the input. The method may include sending a reference signal.

[0009] Some aspects described herein relate to a UE for wireless communication. The user equipment may include a memory and one or more processors coupled to the memory. The one or more processors may be configured to receive a signal. The one or more processors may be configured to determine a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein the one or more processors are configured to determine the predicted communication metric and the confidence indication. The one or more processors may be configured to perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0010] Some aspects described herein relate to a network node for wireless communication. 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 send a machine learning configuration associated with a machine learning component, the machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model configured to: obtain an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and provide the predicted communication metric and the confidence indication through the machine learning model at least in part based on a machine learning function and the input. The one or more processors may be configured to send a reference signal.

[0011] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a UE. The instruction set, when executed by one or more processors of the UE, may cause the UE to receive a signal. The instruction set, when executed by one or more processors of the UE, may cause the UE to determine a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein in order to determine the predicted communication metric and the confidence indication, the one or more instructions are configured to cause the UE to: obtain an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and provide the predicted communication metric and the confidence indication through the machine learning model based at least in part on a machine learning function and the input. The instruction set, when executed by one or more processors of the UE, may cause the UE to perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0012] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a network node. The instruction set, when executed by one or more processors of the network node, may cause the network node to send a machine learning configuration associated with a machine learning component, the machine learning component being configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, the machine learning model being configured to: obtain an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and provide the predicted communication metric and the confidence indication through the machine learning model based at least in part on a machine learning function and the input. The instruction set, when executed by one or more processors of the network node, may cause the network node to send a reference signal.

[0013] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include a component for receiving a signal. The apparatus may include a component for determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein the component for determining the predicted communication metric and the confidence indication includes: a component for receiving an input including an input metric and an error measurement result corresponding to the input metric and a component for providing the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input. The apparatus may include a component for performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0014] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include means for sending a machine learning configuration associated with a machine learning component, the machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model including: means for obtaining an input including an input metric and an error measurement corresponding to the input metric and means for providing the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input. The apparatus may include means for sending a reference signal.

[0015] Aspects of the present invention generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communication devices and / or processing systems as fully described herein with reference to and as illustrated in the accompanying drawings and description.

[0016] The features and technical advantages of the examples according to the present disclosure have been outlined quite extensively above so that the following specific embodiments may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent constructions do not depart from the scope of protection of the appended claims. The characteristics of the concepts disclosed herein, both in terms of their organization and method of operation, and the associated advantages will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the accompanying drawings is provided for the purpose of illustration and description, and not as a definition of the limitations of the claims.

[0017] Although various aspects are described in the present disclosure by illustrating some examples, it will be understood by those skilled in the art that such aspects can be implemented in many different arrangements and scenarios. The technology described herein can be implemented using different platform types, devices, systems, shapes, sizes and / or packaging arrangements. For example, some aspects can be implemented via integrated chip implementations or other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / shopping equipment, medical equipment and / or artificial intelligence devices). Various 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. The equipment incorporating the various aspects and features described may include additional components and features for implementing and practicing the various aspects claimed and described. For example, the transmission and reception of wireless signals may include one or more components for analog and digital purposes (e.g., hardware components, including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders and / or summers). The various aspects described herein are intended to be practiced in various devices, components, systems, distributed arrangements and / or end-user devices of various sizes, shapes and configurations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to fully understand the above-mentioned features of the present disclosure, a more specific description of the invention briefly summarized above can be obtained by referring to various aspects (some of which are illustrated in the accompanying drawings). However, it should be noted that the accompanying drawings only illustrate certain typical aspects of the present disclosure and are therefore not to be considered as limiting the scope thereof, as the specification may admit of other equally effective aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0019] Figure 1 is a diagram illustrating an example of a wireless network according to the present disclosure.

[0020] Figure 2 is a diagram illustrating an example of communication between a base station and a user equipment (UE) in a wireless network according to the present disclosure.

[0021] Figure 3 is a diagram illustrating an example of open radio access network communication according to the present disclosure.

[0022] Figures 4 to 6 is a diagram illustrating an example associated with machine learning for beam prediction with confidence indication according to the present disclosure.

[0023] Figure 7 and Figure 8 is a diagram illustrating an example process associated with machine learning for beam prediction with confidence indications according to the present disclosure.

[0024] Fig. 9 and Fig.10 is a diagram of an example apparatus for wireless communications according to the present disclosure. DETAILED DESCRIPTION

[0025] The various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure can be embodied in many different forms, and should not be construed as being limited to any specific structure or function presented throughout the present disclosure. Instead, these aspects are provided so that the present disclosure will be thorough and complete, and the scope of protection of the present disclosure will be fully conveyed to those skilled in the art. It should be appreciated by those skilled in the art that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether it is implemented independently or in combination with any other aspect of the present disclosure. For example, any number of aspects set forth herein may be used to implement a device or practice method. In addition, the scope of the present disclosure is intended to cover such a device or method implemented using other structures, functions, or structures and functions in addition to or different from the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of the claims.

[0026] Several aspects of telecommunication systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0027] Although various aspects may be described herein using terms generally associated with 5G or new radio (NR) radio access technology (RAT), various aspects of the present disclosure may be applicable to other RATs, such as 3G RAT, 4G RAT, and / or post-5G RATs (e.g., 6G).

[0028] Figure 1 1 is a diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, or may include elements of a 5G (e.g., NR) network and / or elements of a 4G (e.g., Long Term Evolution (LTE)) network, among other examples. The wireless network 100 may include one or more base stations 110 (shown as BS110a, BS110b, BS110c, and BS110d), a user equipment (UE) 120 or multiple UEs 120 (shown as UE120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other network entities. The base station 110 is an entity that communicates with the UE 120. Base station 110 (sometimes referred to as BS) may include, for example, an NR base station, an LTE base station, a Node B, an eNB (e.g., in 4G), a gNB (e.g., in 5G), an access point, and / or a transmit receive point (TRP). Each base station 110 may provide communication coverage for a particular geographic area. In the Third Generation Partnership Project (3GPP), the term "cell" may refer to a coverage area of ​​a base station 110 and / or a base station subsystem serving the coverage area, depending on the context in which the term is used.

[0029] The 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 radius of several kilometers) and may allow unrestricted access by a UE 120 with a service subscription. A pico cell may cover a relatively small geographic area and may allow unrestricted access by a UE 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 a UE 120 associated with the femto cell (e.g., a UE 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. In Figure 1 In the example shown in , BS 110a may be a macro base station for macro cell 102a, BS 110b may be a pico base station for pico cell 102b, and BS 110c may be a femto base station for femto cell 102c. A base station may support one or more (eg, three) cells.

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

[0031] The wireless network 100 may include one or more relay stations. A relay station is an entity that can receive transmissions of data from an upstream station (e.g., a base station 110 or a UE 120) and transmit transmissions of data to a downstream station (e.g., a UE 120 or a base station 110). A relay station may be a UE 120 that is capable of relaying transmissions for other UEs 120. Figure 1 In the example shown in FIG. 1 , BS 110d (eg, a relay base station) can communicate with BS 110a (eg, a macro base station) and UE 120d to facilitate communication between BS 110a and UE 120d. Base station 110 that relays communication may be referred to as a relay station, relay base station, relay, or the like.

[0032] The wireless network 100 may be a heterogeneous network that includes 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 impacts on interference in the wireless network 100. For example, a macro base station may have a high transmit power level (e.g., 5 watts to 40 watts), while a pico base station, a femto base station, and a relay base station may have a lower transmit power level (e.g., 0.1 watt to 2 watts).

[0033] The network controller 130 may be coupled to or in communication with a set of base stations 110 and may provide coordination and control for the base stations 110. The network controller 130 may communicate with the base stations 110 via backhaul communication links. The base stations 110 may also communicate directly with each other or indirectly via wireless or wired backhaul communication links.

[0034] UE 120 may be distributed throughout wireless network 100, and each UE 120 may be stationary or mobile. UE 120 may include, for example, an access terminal, a terminal, a mobile station, and / or a subscriber unit. UE 120 may be a cellular phone (e.g., a smart phone), 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 computer, 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 sensor, a smart meter / sensor, an industrial manufacturing equipment, a global positioning system device, and / or any other suitable device configured to communicate via a wireless medium.

[0035] Some UEs 120 may be considered as machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors and / or location tags, which 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. UE 120 may be included inside a housing that houses components of 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., a memory) may be operably coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

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

[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 base station 110 as an intermediary to communicate with each other) using one or more side link channels. For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks. In such examples, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by base station 110.

[0038] The devices of the wireless network 100 may communicate using an electromagnetic spectrum, which may be subdivided into various categories, bands, channels, etc., based on frequency or wavelength. 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 ranges designated FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). It should be understood that, although portions of FR1 are greater than 6 GHz, FR1 is often (interchangeably) referred to as the "below 6 GHz" band in various documents and articles. Similar naming issues sometimes occur with respect to FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the "millimeter wave" band by the International Telecommunication Union (ITU).

[0039] The frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz-24.25GHz). The frequency bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and therefore the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR4a or FR4-1 (52.6GHz-71GHz), FR4 (52.6GHz-114.25GHz) and FR5 (114.25GHz-300GHz). Each of these higher frequency bands falls within the EHF band.

[0040] In view of the above examples, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used herein, the term can be broadly referred to as frequencies that can be lower than 6 GHz, can be within FR1, or can include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that the term "millimeter wave" or the like, if used herein, can be broadly referred to as frequencies that can include mid-band frequencies, can be within FR2, FR4, FR4-a or FR4-1 and / or FR5, or can be within the EHF band. It is contemplated that the frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) can be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0041] In some aspects, UE 120 may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may perform the following operations: receiving a signal; determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: receiving an input including an input metric and an error measurement corresponding to the input metric; and providing the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input; and performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0042] In some aspects, the network node may include a communication manager 140 or a communication manager 150. As described in more detail elsewhere herein, the communication manager 140 or 150 may: send a machine learning configuration associated with a machine learning component, the machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model configured to: obtain an input including an input metric and an error measurement corresponding to the input metric; and provide the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input; and send a reference signal. Additionally or alternatively, the communication manager 140 or 150 may perform one or more other operations described herein.

[0043] As indicated above, Figure 1 are provided as examples. Other examples can be found in the Figure 1 Different than described.

[0044] Figure 22 is a diagram illustrating an example 200 of base station 110 communicating with UE 120 in wireless network 100 according to the present disclosure. Base station 110 may be equipped with a set of antennas 234a to 234t, such as T antennas (T≥1). UE 120 may be equipped with a set of antennas 252a to 252r, such as R antennas (R≥1).

[0045] At the base station 110, the transmit processor 220 may receive data intended for the UE 120 (or a set of UEs 120) from the data source 212. The transmit processor 220 may select one or more modulation and coding schemes (MCS) for the UE 120 based at least in part on one or more channel quality indicators (CQI) received from the UE 120. The base station 110 may process (e.g., encode and modulate) the data for the UE 120 based at least in part on the MCS selected for the UE 120, and provide data symbols for the UE 120. The transmit processor 220 may process system information (e.g., for semi-static resource allocation information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling), and provide overhead symbols and control symbols. The transmit processor 220 may generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) and synchronization signals (e.g., primary synchronization signals (PSS) or secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., pre-coding) on ​​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) (shown as modems 232a to 232t). For example, each output symbol stream may be provided to a modulator component (shown as MOD) of the modem 232. Each modem 232 may process a corresponding output symbol stream (e.g., for OFDM) using a corresponding modulator component to obtain an output sample stream. Each modem 232 may further process (e.g., convert to analog, amplify, filter, and / or up-convert) the output sample stream using a corresponding modulator component to obtain a downlink signal. The modems 232a to 232t may transmit a set of downlink signals (e.g., T downlink signals) via a corresponding set of antennas 234 (e.g., T antennas) (shown as antennas 234a to 234t).

[0046] At the UE 120, a set of antennas 252 (shown 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) (shown as modems 254a through 254r). For example, each received signal may be provided to a demodulator component (shown as DEMOD) of the modem 254. Each modem 254 may use a corresponding 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 modem 254, may perform MIMO detection on the received symbols where applicable, and may provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, may provide decoded data for the UE 120 to the data sink 260, and may provide decoded control information 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 things. In some examples, one or more components of the UE 120 may be included in the housing 284.

[0047] 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 station 110 via the communication unit 294.

[0048] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include or be included 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, etc. Antenna panels, antenna groups, sets of antenna elements, and / or antenna arrays may include one or more antenna elements (in a single housing or multiple housings), sets of coplanar antenna elements, sets of non-coplanar antenna elements, and / or may be coupled to one or more transmit and / or receive components (such as, Figure 2 One or more antenna elements of one or more components in.

[0049] On the uplink, at the UE 120, the transmit processor 264 may receive and process data from the data source 262 and control information from the 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 pre-decoded by the TX MIMO processor 266, where 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 an antenna 252, a modem 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, and / or a TX MIMO processor 266. The transceiver may be used by a processor (eg, controller / processor 280) and memory 282 to perform the functions described herein (eg, with reference to Figures 4 to 10 )Aspects of any of the methods described herein.

[0050] 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 shown as DEMOD), detected by the MIMO detector 236 where applicable, and further processed by the receive processor 238 to obtain decoded data and control information transmitted by the UE 120. The receive processor 238 may provide the decoded data to the 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 to schedule 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 234, modem 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 operations described herein (e.g., with reference to Figures 4 to 10 )Aspects of any of the methods described herein.

[0051] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2Any other components of may perform one or more techniques associated with machine learning for beam prediction using confidence indications, as described in more detail elsewhere herein. In some aspects, the network node described herein is a base station 110, is included in a base station 110, or includes Figure 2 One or more components of the base station 110 shown. In some aspects, the network node described herein is Figure 2 The UE 120 shown is included in the UE 120, or includes one or more components of the UE 120. For example, the controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other component of the Figure 7 The process 700 Figure 8 800 and / or operations of other processes as described herein. Memory 242 and memory 282 may store data and program codes for base station 110 and 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, one or more instructions, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly, or after compilation, conversion, and / or interpretation), may cause one or more processors, UE 120, and / or base station 110 to perform or direct, for example Figure 7 The process of 700 Figure 8 The process 800 and / or operations of other processes as described herein. In some examples, executing instructions may include running instructions, converting instructions, compiling instructions, and / or interpreting instructions, etc.

[0052] In some aspects, a UE includes: means for receiving a signal; means for determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: means for receiving an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model; and / or means for providing the predicted communication metric and the confidence indication through the machine learning model based at least in part on a machine learning function and the input; and / or means for performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication. Means for the UE to perform operations described herein may include, for example, one or more of the following: communication 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.

[0053] In some aspects, a network node includes: a means for sending a machine learning configuration associated with a machine learning component, the machine learning component being configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model being configured to: obtain an input means including an input metric and an error measurement result corresponding to the input metric by the machine learning model; and / or a means for providing the predicted communication metric and the confidence indication by the machine learning model at least in part based on a machine learning function and the input; and / or a means for sending a reference signal. In some aspects, the means for the network node to perform operations described herein may include, for example, one or more of the communication manager 150, the transmit processor 220, the TX MIMO processor 230, the modem 232, the antenna 234, the MIMO detector 236, the receive processor 238, the controller / processor 240, the memory 242, or the scheduler 246. In some aspects, means for the network node to perform operations described herein may include, for example, one or more of the communication 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.

[0054] Although Figure 2 The blocks in the 2000 and 2010 are illustrated as distinct components, but the functionality described above for these blocks may be implemented in a single hardware, software, or combined component or in various combinations of components. For example, the functionality described for the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 may be performed by or under the control of the controller / processor 280.

[0055] As indicated above, Figure 2 are provided as examples. Other examples can be found in the Figure 2 Different than described.

[0056] Figure 3 3 is a diagram illustrating an example 300 of an O-RAN architecture according to the present disclosure. Figure 3As shown, the O-RAN architecture may include a control unit (CU) 310 that communicates with a core network 320 via a backhaul link. In addition, the CU 310 may communicate with one or more distributed units (DU) 330 via corresponding midhaul links. The DU 330 may each communicate with one or more radio units (RU) 340 via corresponding fronthaul links, and the RU 340 may each communicate with a corresponding UE 120 via a radio frequency (RF) access link. The DU 330 and the RU 340 may also be referred to as an O-RAN DU (O-DU) 330 and an O-RAN RU (O-RU) 340, respectively.

[0057] In some aspects, the DU 330 and the RU 340 may be implemented according to a functional split architecture, wherein the functionality of a base station 110 (e.g., an eNB or gNB) is provided by the DU 330 and one or more RUs 340 that communicate via a fronthaul link. Thus, as described herein, the base station 110 may include a DU 330 and one or more RUs 340, which may be co-located or geographically distributed. In some aspects, the DU 330 and the associated RU 340 may communicate via the fronthaul link to exchange real-time control plane information via a lower layer split (LLS) control plane (LLS-C) interface, non-real-time management information via an LLS management plane (LLS-M) interface, and / or user plane information via an LLS user plane (LLS-U) interface.

[0058] Thus, the DU 330 may correspond to a logical unit that includes one or more base station functions to control the operation of one or more RUs 340. For example, in some aspects, the DU 330 may host a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (e.g., forward error correction (FEC) encoding and decoding, scrambling, and / or modulation and demodulation) based at least in part on the lower layer functional split. Higher layer control functions (such as packet data convergence protocol (PDCP), radio resource control (RRC), and / or service data adaptation protocol (SDAP)) may be hosted by the CU 310. Based at least in part on the lower layer functional split, the RU 340 controlled by the DU 330 may correspond to a logical node that hosts RF processing functions and low PHY layer functions (e.g., fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, and / or physical random access channel (PRACH) extraction and filtering). Thus, in the O-RAN architecture, the RU 340 handles all over-the-air (OTA) communications with the UE 120, and the real-time and non-real-time aspects of the control plane and user plane communications with the RU 340 are controlled by the corresponding DU 330, which enables the DU 330 and the CU 310 to be implemented in a cloud-based RAN architecture.

[0059] As indicated above, Figure 3 are provided as examples. Other examples can be found in the Figure 3 Different than described.

[0060] Machine learning can be used in wireless communications to facilitate channel estimation, beam selection, beamforming, and / or other processes in which predicted values ​​may be useful. In some cases, for example, machine learning can be used for beam prediction. In beam prediction, a machine learning component, such as implemented at a UE, can be used to predict a channel metric (e.g., RSRP) based on a machine learning model that is trained based on empirical data (e.g., past values ​​of the metric).

[0061] Beam prediction based on machine learning may be erroneous. For example, given previous channel metric measurements, future channel metric values ​​are random variables and have randomness due to fading and noise, uncertainty in the future position of the UE, and / or errors due to model limitations. Therefore, in some cases, using a single predicted value from a machine learning model as a predictor may lead to poor scheduling decisions, resulting in scheduling conflicts, channel starvation, and / or missed communications, thereby having a negative impact on network performance.

[0062] Some aspects of the techniques and devices described herein may provide a machine learning component that takes a measurement error as input in addition to a channel measurement result, and provides a predicted value and a confidence indication associated with the predicted value as an output. For example, in some aspects, a UE may receive a signal and determine a predicted communication metric and a confidence indication based at least in part on a machine learning component. In some aspects, the machine learning component may include a machine learning model. The UE may determine the predicted communication metric and the confidence indication based on: receiving an input including an input metric and an error measurement result corresponding to the input metric through the machine learning model. The UE may provide the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input through the machine learning model. In some aspects, the UE may perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0063] In this manner, some aspects may provide a more accurate machine learning component for beam prediction. For example, in some aspects, a machine learning component may provide a predicted average communication metric and a standard deviation of the average relative to past measurements of the communication metric. In this manner, the standard deviation may provide a confidence level in the predicted average. The improved predictions facilitated by some of the described aspects may result in more efficient scheduling decisions and / or may result in higher quality communications, thereby positively impacting network performance.

[0064] Some aspects may include a machine learning model with certain properties. For example, to facilitate standard deviation output, the output layer of the machine learning model may be configured such that the output is always positive. In some aspects, past measurement patterns and measurement error quality may be used to facilitate determining a predicted standard deviation. In some aspects, the machine learning model may also be configured to receive sparse measurement patterns (e.g., where only a subset of beams are measured). Some aspects may facilitate more reliable beam predictions, proactive rejection of bad predictions, more accurate beam selection, fewer beam failures, and / or higher throughput, among other things.

[0065] Figure 4 4 is a diagram illustrating an example 400 of machine learning for beam prediction with confidence indication according to the present disclosure. Figure 4 As shown, UE 402 and network node 404 may communicate with each other.

[0066] As indicated by reference numeral 406, the UE 402 may send, and the network node 404 may receive, a capability report indicating the UE 402's ability to provide a confidence indication. In some aspects, the capability report may also indicate supported activation types associated with an output layer of a machine learning model implemented at the UE 402.

[0067] As shown at reference numeral 408, the network node 404 may send and the UE 402 may receive a machine learning configuration associated with the machine learning component. In some aspects, the machine learning configuration may include a machine learning component 410, which includes a machine learning model 412, a machine learning parameter set 414, and / or an activation indication associated therewith. As shown, the machine learning component 410 may be configured to use the machine learning model 412 to generate a predicted communication metric Y and a confidence indication C. The machine learning model 412 may generate an input metric X and an error measurement result E corresponding to the input metric X. x As input, the machine learning model 412 may be configured to use the machine learning function F(X) to determine the predicted communication metric Y. For example, the machine learning model 412 may be configured to evaluate Y=F(X). In some aspects, the machine learning model 412 may be a neural network function.

[0068] In some aspects, the machine learning model may be identified by a machine learning model identifier (ID) such as, for example, a neural network function (NNF) ID. In some aspects, each NNF supported by the machine learning component 410 may be identified by a standardized NNF ID. In some aspects, non-standardized IDs may be used to support NNF private extensions. In some aspects, the input metric X and the output metric Y may be standardized. In some aspects, the machine learning parameter set 414 may be context-dependent. For example, the machine learning parameter set 414 may be location-specific and / or configuration-specific.

[0069] As indicated by reference numeral 416, the network node 404 may send and the UE 402 may receive a signal. The signal may include a reference signal, such as, for example, a synchronization signal block (SSB) and / or a channel state information reference signal (CSI-RS), etc. As indicated by reference numeral 418, the UE 402 may determine a predicted communication metric and a confidence indication based at least in part on the machine learning component 410. The machine learning component may include a machine learning model, and the UE 402 may determine the predicted communication metric and the confidence indication based on: receiving, by the machine learning model, an input including an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input.

[0070] In some aspects, the input metric may include RSRP, and the predicted communication metric may include the predicted RSRP. The confidence indication includes a standard deviation associated with the predicted communication metric. In some aspects, the input metric may include an interpolated metric value. The UE 402 may determine a plurality of interpolated metric values ​​including the interpolated metric value, and may select the interpolated metric value based at least in part on an error measurement, the error measurement including a minimum error measurement among a plurality of error measurements corresponding to the plurality of interpolated metric values.

[0071] As shown by reference numeral 420, UE 402 may send and network node 404 may receive a model error report indicating a model inference error associated with the predicted communication metric. In some aspects, sending the model error report may include sending the model error report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition. As shown by reference numeral 422, UE 402 may send and network node 404 may receive an output report. The output report may indicate at least one of the predicted communication metric or the confidence indication. In some aspects, UE 402 may send the output report using air communication. In some aspects, the output report may include a dedicated uplink control information (UCI) type in a physical layer beam report. In some aspects, the output report may be triggered based at least in part on a confidence indicator satisfying a reporting threshold. In some aspects, reporting a confidence indicator satisfying a mitigation threshold may cause network node 404 to trigger additional reference signal transmission and / or reporting in the corresponding beam direction.

[0072] As indicated above, Figure 4 are provided as examples. Other examples can be found in the Figure 4 Different than described.

[0073] Figure 5 is a diagram illustrating an example 500 associated with machine learning for beam prediction using confidence indication according to the present disclosure. Example 500 illustrates a machine learning function 502. The machine learning function 502 may be Figure 4 The depicted machine learning model 412 is implemented.

[0074] As shown, the machine learning function includes a first set of input ports 504 associated with a set of reference signals, a second set of input ports 506 associated with a set of error metrics, a first set of output ports 508 associated with a set of predicted communication metrics, and a second set of output ports 510 associated with a set of confidence measurement outputs. In some aspects, the machine learning function 502 can be configured to perform a pre-processing operation, wherein the machine learning function normalizes a set of input data based at least in part on a normalization metric.

[0075] In some aspects, for example, a machine learning component implementing the machine learning function 502 may obtain a set of measurement results associated with a subset of the set of reference signals. The subset may include fewer reference signals than the set of reference signals, and the UE may obtain the set of measurement results by skipping the configured measurement based at least in part on receiving downlink communications during a measurement opportunity corresponding to at least one configured measurement. In some aspects, the UE may generate a measurement mode indication corresponding to the set of measurement results, wherein the measurement mode indication indicates at least one of: an input port in the set of input ports 504 for which no measurement results were obtained or an input port in the set of input ports 504 for which measurement results were obtained.

[0076] In some aspects, the UE may receive a configuration associated with a measurement input format corresponding to a measurement mode indication. The UE may generate the measurement mode indication based at least in part on the measurement input format. In some aspects, for example, the UE may generate an interpolated measurement result corresponding to a port for which no measurement result was obtained, wherein the measurement mode indication includes an indication of an interpolation error corresponding to the interpolated measurement result.

[0077] For example, Figure 5 As shown, each input port in the set of input ports 504 is marked with an "M" to indicate an input port that obtains a measurement result, or is marked with an "I" to indicate an input port that does not obtain a measurement result (and therefore generates an interpolation). The corresponding error value can be provided via the set of input ports 506. In some aspects, as shown, the error value can be set to "0" for those ports that obtain measurement results. In some aspects, instead of providing all interpolated measurement results and corresponding errors to the machine learning function 502, a selection process can be performed by which one or more interpolations and corresponding errors are selected for provision to the machine learning function 502. For example, one or more interpolations with the smallest error value can be selected for provision to the machine learning function 502.

[0078] In some aspects, the UE may provide a predicted communication metric based on performing an autoregressive process associated with a previously predicted communication metric. For example, in some aspects, no beam may be measured. In this case, the UE may perform time domain interpolation based on previous beam measurements via a machine learning model. In some aspects, the predicted communication metric from the previous step may be used as an input to predict the communication metric using autoregression in the next step. The standard deviation of the output of the previous step may be provided as an error metric and as an input to the machine learning function 502. In some aspects, for example, the UE may determine multiple candidate inputs for the input of a beam. For example, the UE may identify a previous RSRP estimate from a previous long short-term (LSTM) prediction and another previous estimate from the spatial domain interpolation of the current step. In some aspects, the network may configure rules for the UE to select which RSRP (or other communication metric) can be used as a predicted input. For example, in some aspects, the UE may select an input corresponding to a smaller interpolation and / or prediction error between the two candidates.

[0079] As indicated above, Figure 5 are provided as examples. Other examples can be found in the Figure 5 Different than described.

[0080] Figure 6 600 is a diagram illustrating an example associated with machine learning for beam prediction with confidence indication according to the present disclosure. Example 600 illustrates an output layer design. The output layer design may be Figure 4 The depicted machine learning model 412 is implemented.

[0081] As shown, the first fully connected layer (FC 24*12) may generate a first output having a first dimension. The rectified linear unit (RELU) activation layer may receive the first output and generate a second output having a first dimension. The LSTM layer may receive the output of the RELU activation layer and may provide an output to the second fully connected layer (FC 120*60) 602. The parallel output layer stack may include a fully connected layer (FC 120*60) 604. The LSTM layer may provide outputs to both the fully connected layer 602 and the layer 604. The fully connected layer 602 may be connected to another RELU 606 and a final fully connected layer 608. The fully connected layer 604 may be connected to the RELU 610, another fully connected layer (FC 60*24) 612, and a shifted exponential linear unit (ELU) 614. Although the fully connected layer 608 may be configured to output an average communication metric, the shifted ELU layer 614 may be configured to output a standard deviation.

[0082] In some aspects, for example, the error measurement result may include at least one previous confidence indication associated with a previously predicted communication metric. The UE may generate a predicted standard deviation based on an activation function. The activation function may be based at least in part on at least one of a shifted ELU or an optimal ε (eps) value. For example, a shifted ELU output may be given by ELU (x) + 1 + eps, where eps corresponds to a predefined small positive number. In some aspects, the activation function may be given by | X | + eps, X^2 + eps or | X + eps |, etc. In some aspects, the output may be non-negative. In order to better converge when a certain loss function (e.g., a negative log-likelihood function) is applied during model training, the output of the standard deviation prediction layer may be configured to be positive in most cases. Alternatively, in some aspects, prior knowledge of the range of standard deviations (e.g., the maximum standard deviation) may be used to facilitate the generation of a shifted and scaled version of a softmax, tanh function as an output layer. The scaling or shift factor applied to the softmax or tanh function may be determined by prior knowledge of the range of standard deviations.

[0083] In some aspects, the activation function may be selected based on a balance between standard deviation prediction accuracy and training convergence rate. In some aspects, if an eps value is used, a small positive offset may be added to avoid steep gradient regions in the loss function.

[0084] In some aspects, the UE may use dedicated hardware and / or software to run the machine learning model. In some aspects, the UE may support customized output activation layers, as described above. In some other aspects, the UE may not support customized output activation layers, as described above. In some aspects, for example, the UE may report the activation function type capabilities of the UE to the network node.

[0085] As indicated above, Figure 6 are provided as examples. Other examples can be found in the Figure 6 Different than described.

[0086] Figure 7 7 is a diagram illustrating an example process 700 performed, for example, by a UE in accordance with the present disclosure. Example process 700 is an example of operations in which a UE (eg, UE 402) performs machine learning for beam prediction with confidence indicators.

[0087] like Figure 7 As shown, in some aspects, process 700 may include receiving a signal (block 710). For example, a UE (e.g., using Fig. 9 The depicted communications manager 908 and / or receiving component 902) can receive signals as described above.

[0088] like Figure 7As further shown, in some aspects, process 700 may include: determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: receiving, by the machine learning model, an input including an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input (block 720). For example, a UE (e.g., using Fig. 9 The depicted communication manager 908 and / or determination component 910) may determine a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: receiving, by the machine learning model, an input including an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input, as described above.

[0089] like Figure 7 As further shown, in some aspects, process 700 may include: performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication (block 730). Fig. 9 The depicted communications manager 908, receiving component 902, and / or sending component 904) can perform wireless communications tasks based at least in part on the predicted communications metric and the confidence indication, as described above.

[0090] Process 700 may include additional aspects, such as any single aspect and / or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0091] In some aspects, the input metric includes RSRP, and wherein the predicted communication metric includes the predicted RSRP. In some aspects, the confidence indication includes a standard deviation associated with the predicted communication metric. In some aspects, the input metric includes an interpolated metric value. In some aspects, process 700 includes: determining a plurality of interpolated metric values ​​including the interpolated metric value, and selecting the interpolated metric value based at least in part on an error measurement result, the error measurement result including a minimum error measurement result among a plurality of error measurements corresponding to the plurality of interpolated metric values.

[0092] In some aspects, process 700 includes: sending a model error report indicating a model inference error associated with the predicted communication metric. In some aspects, sending the model error report includes sending the model error report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition. In some aspects, the at least one analysis metric includes at least one of a mean deviation or a standard deviation. In some aspects, the analysis metric may be a likelihood. For example, the likelihood may be calculated based on a predicted mean, a predicted standard deviation, and / or a measured value. In some aspects, the likelihood may be calculated using a function configured by a network node (e.g., a function configured by the network).

[0093] In some aspects, process 700 includes: receiving a machine learning configuration associated with a machine learning component. In some aspects, the machine learning function includes: a first set of input ports associated with a set of reference signals; a second set of input ports associated with a set of error metrics, wherein the set of error metrics includes error measurements; a first set of output ports associated with a set of predicted communication metrics, wherein the set of predicted communication metrics includes predicted communication metrics; and a second set of output ports associated with a set of confidence measurement outputs, wherein the set of confidence measurement outputs includes confidence indications. In the tenth aspect, alone or in combination with the ninth aspect, the set of reference signals includes at least one of a synchronization signal block or a channel state information reference signal.

[0094] In some aspects, the first set of input ports is associated with at least one transmit configuration indication. In some aspects, the set of confidence measurement outputs includes at least one of a standard deviation, a variance, a confidence range, or a probability of failure. In some aspects, the set of error metrics includes at least one of a timestamp, a measurement indication, an interpolation error, a measurement error, a prediction error, or an interference estimate.

[0095] In some aspects, process 700 includes: performing a preprocessing operation corresponding to the set of reference signals. In some aspects, performing the preprocessing operation includes normalizing a set of input data. In some aspects, normalizing the set of input data includes normalizing the set of input data based at least in part on a normalization metric. In some aspects, the normalization metric includes at least one of a mean deviation or a standard deviation. In some aspects, process 700 includes: receiving an indication of the normalization metric.

[0096] In some aspects, process 700 includes obtaining a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals. In some aspects, obtaining the set of measurements includes skipping measurements of the configuration based at least in part on receiving downlink communications during a measurement opportunity corresponding to at least one configured measurement.

[0097] In some aspects, obtaining the set of measurements includes obtaining a first measurement using a first receive beam and obtaining a second measurement using a second receive beam. In some aspects, process 700 includes generating a measurement mode indication corresponding to the set of measurements. In some aspects, the measurement mode indication indicates at least one of: an input port in the set of input ports for which no measurement was obtained or an input port in the set of input ports for which a measurement was obtained.

[0098] In some aspects, process 700 includes receiving a configuration associated with a measurement input format corresponding to a measurement mode indication, wherein generating the measurement mode indication includes generating the measurement mode indication based at least in part on the measurement input format. In some aspects, process 700 includes generating interpolated measurement results corresponding to ports for which no measurement results were obtained. In some aspects, the measurement mode indication includes an indication of an interpolation error corresponding to the interpolated measurement results.

[0099] In some aspects, the measurement mode indication indicates an interpolation error value of zero associated with the port at which the measurement result is obtained. In some aspects, generating the interpolated measurement result includes performing spatial interpolation associated with at least one obtained measurement result. In some aspects, generating the interpolated measurement result includes performing time domain interpolation associated with at least one obtained measurement result corresponding to a previous measurement occasion.

[0100] In some aspects, the input metric includes at least one of a previously predicted communication metric or an interpolated measurement. In some aspects, providing the predicted communication metric includes performing an autoregressive process associated with the previously predicted communication metric. In some aspects, the error measurement includes at least one previous confidence indication associated with the previously predicted communication metric. In some aspects, process 700 includes: selecting the input metric from a plurality of potential input metrics associated with the beam based at least in part on a selection criterion.

[0101] In some aspects, providing the confidence indication includes determining a predicted standard deviation using a dedicated output layer. In some aspects, generating the predicted standard deviation includes generating the predicted standard deviation based at least in part on an activation function, wherein the activation function is based at least in part on at least one of a shifted exponential linear unit or an optimal epsilon value. In some aspects, process 700 includes receiving an epsilon value configuration indicating an optimal epsilon value.

[0102] In some aspects, providing the confidence indication includes determining an average value corresponding to the predicted communication metric. In some aspects, providing the confidence indication includes determining the confidence indication using a central processing unit and based at least in part on outputs from a plurality of configured model layers. In some aspects, process 700 includes sending a capability report indicating the UE's ability to provide the confidence indication. In some aspects, the capability report further indicates supported activation types associated with an output layer of the machine learning model.

[0103] In some aspects, process 700 includes: using over-the-air communications to send an output report associated with a machine learning component, the output report indicating at least one of a predicted communication metric or a confidence indication. In some aspects, the output report corresponds to a dedicated uplink control information type associated with a physical layer beam report. In some aspects, sending the output report includes sending the output report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0104] although Figure 7 Example blocks of process 700 are shown, but in some aspects, process 700 may include Figure 7 The blocks depicted may be additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner than those depicted. Additionally or alternatively, two or more of the blocks of process 700 may be performed in parallel.

[0105] Figure 8 is a diagram illustrating an example process 800 performed, for example, by a network node in accordance with the present disclosure. The example process 800 is an example of operations in which a network node (eg, network node 404) performs machine learning for beam prediction with confidence indicators.

[0106] like Figure 8 As shown, in some aspects, process 800 may include: sending a machine learning configuration associated with a machine learning component, the machine learning component being configured to generate a predicted communication metric and a confidence indication, the machine learning component including a machine learning model, the machine learning model being configured to: obtain, by the machine learning model, an input including an input metric and an error measurement result corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input (block 810). For example, a network node (e.g., using Fig.10The depicted communication manager 1008 and / or sending component 1004) may send a machine learning configuration associated with a machine learning component, the machine learning component being configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, the machine learning model being configured to: obtain, through the machine learning model, an input comprising an input metric and an error measurement result corresponding to the input metric; and provide, through the machine learning model, the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input, as described above.

[0107] like Figure 8 As further shown, in some aspects, process 800 may include sending a reference signal (block 820). For example, a network entity (e.g., using Fig.10 The depicted communications manager 1008 and / or transmitting component 1004) can transmit a reference signal, as described above.

[0108] Process 800 may include additional aspects, such as any single aspect and / or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0109] In some aspects, the input metric includes an RSRP associated with a reference signal, and wherein the predicted communication metric includes the predicted RSRP. In some aspects, the confidence indication includes a standard deviation associated with the predicted communication metric. In some aspects, the input metric includes an interpolated metric value. In some aspects, process 800 includes: receiving a model error report indicating a model inference error associated with the predicted communication metric. In some aspects, receiving the model error report includes receiving the model error report based at least in part on at least one analytical metric associated with the predicted communication metric satisfying a reporting condition. In some aspects, the at least one analytical metric includes at least one of a mean deviation or a standard deviation.

[0110] In some aspects, the machine learning function includes: a first set of input ports associated with a set of reference signals; a second set of input ports associated with a set of error metrics, wherein the set of error metrics includes error measurements; a first set of output ports associated with a set of predicted communication metrics, wherein the set of predicted communication metrics includes predicted communication metrics; and a second set of output ports associated with a set of confidence measurement outputs, wherein the set of confidence measurement outputs includes confidence indications. In some aspects, the set of reference signals includes at least one of a synchronization signal block or a channel state information reference signal.

[0111] In some aspects, the first set of input ports is associated with at least one transmit configuration indication. In some aspects, the set of confidence measurement outputs includes at least one of a standard deviation, a variance, a confidence range, or a probability of failure. In some aspects, the set of error metrics includes at least one of a timestamp, a measurement indication, an interpolation error, or a measurement error.

[0112] In some aspects, the machine learning component is further configured to perform a preprocessing operation corresponding to the set of reference signals. In some aspects, the preprocessing operation includes a normalization operation associated with the set of input data. In some aspects, the normalization operation is configured to normalize the set of input data based at least in part on a normalization metric.

[0113] In some aspects, the normalized metric includes at least one of a mean deviation or a standard deviation. In some aspects, process 800 includes: sending an indication of the normalized metric. In some aspects, process 800 includes: sending a configuration associated with a measurement input format corresponding to a measurement mode indication, wherein the measurement mode indication indicates at least one of: an input port in the group of input ports that did not obtain a measurement result or an input port in the group of input ports that obtained a measurement result. In some aspects, the measurement mode indication includes an indication of an interpolation error corresponding to an interpolated measurement result, the interpolated measurement result corresponding to a port that did not obtain a measurement result. In some aspects, the measurement mode indication indicates an interpolation error value of zero associated with a port that obtained a measurement result.

[0114] In some aspects, the input metric includes at least one of a previously predicted communication metric or an interpolated measurement. In some aspects, to provide the predicted communication metric, the machine learning model is configured to perform an autoregressive process associated with the previously predicted communication metric. In some aspects, the error measurement includes at least one previous confidence indication associated with the previously predicted communication metric.

[0115] In some aspects, the machine learning component includes a dedicated output layer configured to generate a predicted standard deviation. In some aspects, to generate the predicted standard deviation, the machine learning component is configured to generate the predicted standard deviation based at least in part on an activation function, wherein the activation function is based at least in part on at least one of a shifted exponential linear unit or an optimal ε value. In some aspects, process 800 includes: sending an ε value configuration indicating the optimal ε value. In some aspects, to provide a confidence indication, the machine learning component is configured to determine an average value corresponding to the predicted communication metric.

[0116] In some aspects, process 800 includes: receiving a capability report from a UE indicating the UE's ability to provide a confidence indication. In some aspects, the capability report also indicates supported activation types associated with an output layer of the machine learning model. In some aspects, process 800 includes: using over-the-air communications to receive an output report associated with a machine learning component, the output report indicating at least one of a predicted communication metric or a confidence indication. In some aspects, the output report corresponds to a dedicated uplink control information type associated with a physical layer beam report. In some aspects, receiving the output report includes receiving the output report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0117] although Figure 8 An example block diagram of process 800 is shown, but in some aspects, process 800 may include Figure 8 The blocks depicted may be additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner than those depicted. Additionally or alternatively, two or more of the blocks of process 800 may be performed in parallel.

[0118] Fig. 9 900 is a diagram of an example apparatus 900 for wireless communication. Apparatus 900 may be a UE, or a UE may include apparatus 900. In some aspects, apparatus 900 includes a receiving component 902 and a transmitting component 904 that may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 900 may communicate with another apparatus 906 (such as a UE, a base station, or another wireless communication device) using receiving component 902 and transmitting component 904. As further shown, apparatus 900 may include a communication manager 908. Communication manager 908 may include a determining component 910.

[0119] In some aspects, the apparatus 900 may be configured to perform Figures 4 to 6 Additionally or alternatively, the apparatus 900 may be configured to perform one or more processes described herein, such as Figure 7 The process 700. In some aspects, Fig. 9 The device 900 and / or one or more components shown may include a combination of Figure 2 One or more components of the UE. Additionally or alternatively, Fig. 9 One or more of the components shown may be combined with Figure 2 Additionally or alternatively, one or more components in the component set 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 can be executed by a controller or processor to perform the function or operation of the component.

[0120] The receiving component 902 may receive communications from the device 906, such as reference signals, control information, data communications, or combinations thereof. The receiving component 902 may provide the received communications to one or more other components of the device 900. In some aspects, the receiving component 902 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, etc.) on the received communications and may provide the processed signals to one or more other components of the device 900. In some aspects, the receiving component 902 may include combining Figure 2 One or more antennas, modems, demodulators, MIMO detectors, receiving processors, controllers / processors, memories or combinations thereof of the UE.

[0121] The transmitting component 904 may transmit communications, such as reference signals, control information, data communications, or combinations thereof, to the device 906. In some aspects, one or more other components of the device 900 may generate communications and may provide the generated communications to the transmitting component 904 for transmission to the device 906. In some aspects, the transmitting component 904 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to the device 906. In some aspects, the transmitting component 904 may include combining Figure 2 One or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the UE. In some aspects, the transmit component 904 can be co-located with the receive component 902 in a transceiver.

[0122] The receiving component 902 can receive a signal. The communication manager 908 and / or the determining component 910 can determine a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component including a machine learning model, and wherein determining the predicted communication metric and the confidence indication includes: receiving, by the machine learning model, an input including an input metric and an error measurement result corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input. In some aspects, the communication manager 908 can include combining Figure 2 One or more antennas, modems, demodulators, controllers / processors, memories, or combinations thereof of the UE. In some aspects, the communication manager 908 may include a receiving component 902 and / or a sending component 904. In some aspects, the communication manager 908 may be, be similar to, include, or be included in Figure 1 and Figure 2In the depicted communication manager 140. In some aspects, the determining component 910 may include combining Figure 2 One or more antennas, modems, controllers / processors, memories, or combinations thereof of the UE. In some aspects, the determining component 910 may include a receiving component 902 and / or a sending component 904.

[0123] The communication manager 908, the receiving component 902, and / or the sending component 904 can perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication. The determining component 910 can determine a plurality of interpolated metric values ​​including the interpolated metric value. The determining component 910 can select the interpolated metric value based at least in part on an error measurement result, the error measurement result including a minimum error measurement result among a plurality of error measurements corresponding to the plurality of interpolated metric values.

[0124] The sending component 904 can send a model error report indicating a model inference error associated with the predicted communication metric. The receiving component 902 can receive a machine learning configuration associated with the machine learning component. The communication manager 908, the receiving component 902, and / or the sending component 904 can perform pre-processing operations corresponding to the set of reference signals. The receiving component 902 can receive an indication of the normalized metric.

[0125] Communications manager 908 and / or receiving component 902 can obtain a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals. Communications manager 908 can generate a measurement mode indication corresponding to the set of measurements.

[0126] The receiving component 902 can receive a configuration associated with a measurement input format corresponding to a measurement mode indication, wherein generating the measurement mode indication comprises generating the measurement mode indication based at least in part on the measurement input format. The communication manager 908 can generate interpolated measurement results corresponding to ports for which no measurement results were obtained. The determining component 910 can select an input metric from a plurality of potential input metrics associated with a beam based at least in part on a selection criterion.

[0127] Receiving component 902 can receive an epsilon value configuration indicating an optimal epsilon value. Sending component 904 can send a capability report indicating the capability of the UE to provide a confidence indication. Sending component 904 can use over-the-air communication to send an output report associated with the machine learning component indicating at least one of a predicted communication metric or a confidence indication.

[0128] Fig. 9 The number and arrangement of components shown are provided as examples. In practice, there may be Fig. 9Additional components, fewer components, different components, or components arranged in a different manner than those shown. Fig. 9 Two or more components shown may be implemented in a single component, or Fig. 9 The single component shown may be implemented as multiple distributed components. Additionally or alternatively, Fig. 9 The illustrated set (one or more) of components may be described as being executable by Fig. 9 Another group of components shown performs one or more functions.

[0129] Fig.10 1 is a diagram of an example apparatus 1000 for wireless communication. Apparatus 1000 may be a network node, or a network node may include apparatus 1000. In some aspects, apparatus 1000 includes a receiving component 1002 and a transmitting component 1004 that may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 1000 may communicate with another apparatus 1006 (such as a UE, a base station, or another wireless communication device) using receiving component 1002 and transmitting component 1004. As further shown, apparatus 1000 may include a communication manager 1008.

[0130] In some aspects, the apparatus 1000 may be configured to perform Figures 4 to 6 Additionally or alternatively, the apparatus 1000 may be configured to perform one or more processes described herein, such as Figure 8 The process 800. In some aspects, Fig.10 The device 1000 and / or one or more components shown may include a combination of Figure 2 One or more components of the UE and / or base station. Additionally or alternatively, Fig.10 One or more of the components shown may be combined with Figure 2 Additionally or alternatively, one or more components in the component set 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 can be executed by a controller or processor to perform the function or operation of the component.

[0131] The receiving component 1002 may receive communications, such as reference signals, control information, data communications, or combinations thereof, from the device 1006. 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, etc.) on the received communications and may provide the processed signals to one or more other components of the device 1000. In some aspects, the receiving component 1002 may include combining Figure 2 One or more antennas, modems, demodulators, MIMO detectors, receiving processors, controllers / processors, memories or combinations thereof of the UE and / or base station.

[0132] The transmitting component 1004 may transmit communications, such as reference signals, control information, data communications, or combinations thereof, to the device 1006. In some aspects, one or more other components of the device 1000 may generate communications and may provide the generated communications 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, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to the device 1006. In some aspects, the transmitting component 1004 may include combining Figure 2 One or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the UE and / or base station. In some aspects, the transmit component 1004 can be co-located with the receive component 1002 in a transceiver.

[0133] The communication manager 1008 and / or the sending component 1004 may send a machine learning configuration associated with a machine learning component, the machine learning component being configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, the machine learning model being configured to: obtain, by the machine learning model, an input comprising an input metric and an error measurement result corresponding to the input metric; and provide, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on the machine learning function and the input. In some aspects, the communication manager 1008 may include combining Figure 2 One or more antennas, modems, controllers / processors, memories, or combinations thereof of the UE and / or base station. In some aspects, the communication manager 1008 may include a receiving component 1002 and / or a sending component 1004. In some aspects, the communication manager 1008 may be, be similar to, or include Figure 1 and Figure 2Communications manager 140 or communications manager 150 are depicted, or included therein.

[0134] The sending component 1004 may send a reference signal. The receiving component 1002 may receive a model error report indicating a model inference error associated with the predicted communication metric. The sending component 1004 may send an indication of a normalized metric. The sending component 1004 may send a configuration associated with a measurement input format corresponding to a measurement mode indication, wherein the measurement mode indication indicates at least one of: an input port in the set of input ports for which a measurement result is not obtained or an input port in the set of input ports for which a measurement result is obtained.

[0135] The sending component 1004 can send an epsilon value configuration indicating an optimal epsilon value. The receiving component 1002 can receive a capability report from the UE, the capability report indicating the UE's ability to provide a confidence indication. The receiving component 1002 can use over-the-air communication to receive an output report associated with the machine learning component, the output report indicating at least one of a predicted communication metric or a confidence indication.

[0136] Fig.10 The number and arrangement of components shown are provided as examples. In practice, there may be Fig.10 Additional components, fewer components, different components, or components arranged in a different manner than those shown. Fig.10 Two or more components shown may be implemented in a single component, or Fig.10 The single component shown may be implemented as multiple distributed components. Additionally or alternatively, Fig.10 The illustrated set (one or more) of components may be described as being executable by Fig.10 Another group of components shown performs one or more functions.

[0137] The following provides an overview of some aspects of the disclosure:

[0138] Aspect 1: A method of wireless communication performed by a user equipment (UE), the method comprising: receiving a signal; determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises: receiving an input comprising an input metric and an error measurement result corresponding to the input metric through the machine learning model; and providing the predicted communication metric and the confidence indication through the machine learning model at least in part based on a machine learning function and the input; and performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

[0139] Aspect 2: The method according to aspect 1, wherein the input metric comprises reference signal received power (RSRP), and wherein the predicted communication metric comprises predicted RSRP.

[0140] Aspect 3: The method according to any one of aspects 1 or 2, wherein the confidence indication comprises a standard deviation associated with the predicted communication metric.

[0141] Aspect 4: The method according to any one of aspects 1 to 3, wherein the input metric comprises an interpolated metric value.

[0142] Aspect 5: According to the method described in Aspect 4, the method also includes: determining multiple interpolated metric values ​​including the interpolated metric value; and selecting the interpolated metric value based at least in part on the error measurement result, wherein the error measurement result includes the minimum error measurement result among multiple error measurement results corresponding to the multiple interpolated metric values.

[0143] Aspect 6: The method according to any one of aspects 1 to 5, further comprising: sending a model error report indicating a model inference error associated with the predicted communication metric.

[0144] Aspect 7: The method of aspect 6, wherein sending the model error report comprises sending the model error report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0145] Aspect 8: The method of aspect 7, wherein the at least one analytical metric comprises at least one of a mean deviation or a standard deviation.

[0146] Aspect 9: According to the method described in any one of Aspects 1 to 8, the method also includes: receiving a machine learning configuration associated with the machine learning component.

[0147] Aspect 10: A method according to any one of Aspects 1 to 9, wherein the machine learning function comprises: a first group of input ports, the first group of input ports being associated with a group of reference signals; a second group of input ports, the second group of input ports being associated with a group of error metrics, wherein the group of error metrics comprises the error measurement results; a first group of output ports, the first group of output ports being associated with a group of predicted communication metrics, wherein the group of predicted communication metrics comprises the predicted communication metrics; and a second group of output ports, the second group of output ports being associated with a group of confidence measurement outputs, wherein the group of confidence measurement outputs comprises the confidence indications.

[0148] Aspect 11: The method according to aspect 10, wherein the set of reference signals includes at least one of a synchronization signal block or a channel state information reference signal.

[0149] Aspect 12: The method according to any one of aspects 10 or 11, wherein the first group of input ports is associated with at least one transmission configuration indication.

[0150] Aspect 13: The method according to any one of aspects 10 to 12, wherein the set of confidence measurement outputs includes at least one of a standard deviation, a variance, a confidence range, or a probability of failure.

[0151] Aspect 14: The method according to any one of aspects 10 to 13, wherein the set of error metrics comprises at least one of a timestamp, a measurement indication, an interpolation error, or a measurement error.

[0152] Aspect 15: The method according to any one of aspects 10 to 14, further comprising: performing a pre-processing operation corresponding to the set of reference signals.

[0153] Aspect 16: The method according to Aspect 15, wherein performing the preprocessing operation includes normalizing a set of input data.

[0154] Aspect 17: The method according to any one of aspects 15 or 16, wherein normalizing the set of input data comprises normalizing the set of input data based at least in part on a normalization metric.

[0155] Aspect 18: The method according to aspect 17, wherein the normalized metric includes at least one of a mean deviation or a standard deviation.

[0156] Aspect 19: The method according to any one of Aspects 17 or 18, further comprising: receiving an indication of the normalized metric.

[0157] Aspect 20: The method according to any one of aspects 10 to 19, the method further comprising: obtaining a set of measurement results associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals.

[0158] Aspect 21: The method according to aspect 20, wherein obtaining the set of measurement results includes: skipping the configured measurement based at least in part on receiving downlink communication during a measurement opportunity corresponding to at least one configured measurement.

[0159] Aspect 22: The method according to any one of aspects 20 or 21, wherein obtaining the set of measurement results comprises obtaining a first measurement result using a first receive beam and obtaining a second measurement result using a second receive beam.

[0160] Aspect 23: The method according to any one of aspects 20 to 22, further comprising: generating a measurement mode indication corresponding to the set of measurement results.

[0161] Aspect 24: The method according to aspect 23, wherein the measurement mode indication indicates at least one of: an input port in the set of input ports for which no measurement result is obtained or an input port in the set of input ports for which a measurement result is obtained.

[0162] Aspect 25: According to the method in any one of Aspects 23 or 24, the method further includes: receiving a configuration associated with a measurement input format corresponding to the measurement mode indication, wherein generating the measurement mode indication includes generating the measurement mode indication based at least in part on the measurement input format.

[0163] Aspect 26: The method according to any one of aspects 23 to 25, further comprising: generating an interpolated measurement result corresponding to a port for which no measurement result is obtained.

[0164] Aspect 27: The method according to aspect 26, wherein the measurement mode indication includes an indication of an interpolation error corresponding to the interpolated measurement result.

[0165] Aspect 28: The method according to any one of aspects 26 or 27, wherein the measurement mode indication indicates an interpolation error value of zero associated with the port at which the measurement result is obtained.

[0166] Aspect 29: The method according to any one of aspects 26 to 28, wherein generating the interpolated measurement result comprises performing spatial interpolation associated with at least one obtained measurement result.

[0167] Aspect 30: The method according to any one of aspects 26 to 29, wherein generating the interpolated measurement result comprises performing a time domain interpolation associated with at least one obtained measurement result corresponding to a previous measurement occasion.

[0168] Aspect 31: The method according to any one of aspects 1 to 30, wherein the input metric comprises at least one of a previously predicted communication metric or an interpolated measurement result.

[0169] Aspect 32: The method according to aspect 31, wherein providing the predicted communication metric includes performing an autoregressive process associated with the previously predicted communication metric.

[0170] Aspect 33: The method of aspect 32, wherein the error measurement comprises at least one previous confidence indication associated with the previously predicted communication metric.

[0171] Aspect 34: The method according to any one of aspects 31 to 33, the method further comprising: selecting the input metric from a plurality of potential input metrics associated with a beam based at least in part on a selection criterion.

[0172] Aspect 35: The method according to any one of aspects 1 to 34, wherein providing the confidence indication comprises determining a standard deviation of the prediction using a dedicated output layer.

[0173] Aspect 36: A method according to aspect 35, wherein generating the predicted standard deviation includes generating the predicted standard deviation based at least in part on an activation function, wherein the activation function is based at least in part on at least one of a shifted exponential linear unit or an optimal ε value.

[0174] Aspect 37: The method according to Aspect 36 further comprises: receiving an ε value configuration indicating the optimal ε value.

[0175] Aspect 38: The method according to any one of aspects 1 to 37, wherein providing the confidence indication comprises determining an average value corresponding to the predicted communication metric.

[0176] Aspect 39: The method according to any one of aspects 1 to 38, wherein providing the confidence indication includes determining the confidence indication using a central processing unit and based at least in part on outputs from multiple configured model layers.

[0177] Aspect 40: According to the method in any one of aspects 1 to 39, the method further comprises: sending a capability report indicating the capability of the UE to provide the confidence indication.

[0178] Aspect 41: A method according to Aspect 40, wherein the capability report also indicates supported activation types associated with an output layer of the machine learning model.

[0179] Aspect 42: The method according to any one of Aspects 1 to 41, further comprising: using over-the-air communication to send an output report associated with the machine learning component, the output report indicating at least one of the predicted communication metric or the confidence indication.

[0180] Aspect 43: A method according to aspect 42, wherein the output report corresponds to a dedicated uplink control information type associated with a physical layer beam report.

[0181] Aspect 44: The method according to any one of aspects 42 or 43, wherein sending the output report comprises sending the output report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0182] Aspect 45: A method of wireless communication performed by a network node, the method comprising: sending a machine learning configuration associated with a machine learning component, the machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, the machine learning model configured to: obtain an input comprising an input metric and an error measurement result corresponding to the input metric through the machine learning model; and provide the predicted communication metric and the confidence indication through the machine learning model at least partially based on a machine learning function and the input; and sending a reference signal.

[0183] Aspect 46: The method of aspect 45, wherein the input metric comprises a reference signal received power (RSRP) associated with the reference signal, and wherein the predicted communication metric comprises a predicted RSRP.

[0184] Aspect 47: The method according to any one of aspects 45 or 46, wherein the confidence indication comprises a standard deviation associated with the predicted communication metric.

[0185] Aspect 48: A method according to any one of aspects 45 to 47, wherein the input metric comprises an interpolated metric value.

[0186] Aspect 49: The method according to any one of aspects 45 to 48, the method further comprising: receiving a model error report indicating a model inference error associated with the predicted communication metric.

[0187] Aspect 50: The method of aspect 49, wherein receiving the model error report comprises receiving the model error report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0188] Aspect 51: The method according to aspect 50, wherein the at least one analytical metric includes at least one of a mean deviation or a standard deviation.

[0189] Aspect 52: A method according to any one of Aspects 45 to 51, wherein the machine learning function comprises: a first group of input ports, the first group of input ports being associated with a group of reference signals; a second group of input ports, the second group of input ports being associated with a group of error metrics, wherein the group of error metrics includes the error measurement results; a first group of output ports, the first group of output ports being associated with a group of predicted communication metrics, wherein the group of predicted communication metrics includes the predicted communication metrics; and a second group of output ports, the second group of output ports being associated with a group of confidence measurement outputs, wherein the group of confidence measurement outputs includes the confidence indications.

[0190] Aspect 53: The method according to aspect 52, wherein the set of reference signals includes at least one of a synchronization signal block or a channel state information reference signal.

[0191] Aspect 54: The method according to any one of aspects 52 or 53, wherein the first set of input ports is associated with at least one transmission configuration indication.

[0192] Aspect 55: The method according to any one of aspects 52 to 54, wherein the set of confidence measurement outputs includes at least one of a standard deviation, a variance, a confidence range, or a probability of failure.

[0193] Aspect 56: The method according to any one of aspects 52 to 55, wherein the set of error metrics comprises at least one of a timestamp, a measurement indication, an interpolation error, or a measurement error.

[0194] Aspect 57: A method according to any one of Aspects 52 to 56, wherein the machine learning component is further configured to perform pre-processing operations corresponding to the set of reference signals.

[0195] Aspect 58: The method according to Aspect 57, wherein the pre-processing operation includes a normalization operation associated with a set of input data.

[0196] Aspect 59: The method according to aspect 58, wherein the normalization operation is configured to normalize the set of input data based at least in part on a normalization metric.

[0197] Aspect 60: The method according to aspect 59, wherein the normalized metric includes at least one of a mean deviation or a standard deviation.

[0198] Aspect 61: The method according to any one of aspects 59 or 60, further comprising: sending an indication of the normalized metric.

[0199] Aspect 62: The method according to any one of Aspects 52 to 61, further comprising: sending a configuration associated with a measurement input format corresponding to a measurement mode indication, wherein the measurement mode indication indicates at least one of: an input port in the set of input ports that does not obtain a measurement result or an input port in the set of input ports that obtains a measurement result.

[0200] Aspect 63: The method according to aspect 62, wherein the measurement mode indication includes an indication of an interpolation error corresponding to an interpolated measurement result, the interpolated measurement result corresponding to a port for which no measurement result is obtained.

[0201] Aspect 64: The method according to any one of aspects 62 or 63, wherein the measurement mode indication indicates an interpolation error value of zero associated with the port at which the measurement result is obtained.

[0202] Aspect 65: The method according to any one of aspects 45 to 64, wherein the input metric comprises at least one of a previously predicted communication metric or an interpolated measurement result.

[0203] Aspect 66: A method according to Aspect 65, wherein in order to provide the predicted communication metric, the machine learning model is configured to perform an autoregressive process associated with the previously predicted communication metric.

[0204] Aspect 67: The method of aspect 66, wherein the error measurement comprises at least one previous confidence indication associated with the previously predicted communication metric.

[0205] Aspect 68: A method according to any one of aspects 45 to 67, wherein the machine learning component includes a dedicated output layer configured to generate a predicted standard deviation.

[0206] Aspect 69: A method according to Aspect 68, wherein in order to generate the predicted standard deviation, the machine learning component is configured to generate the predicted standard deviation based at least in part on an activation function, wherein the activation function is based at least in part on at least one of a shifted exponential linear unit or an optimal ε value.

[0207] Aspect 70: According to the method of aspect 69, the method further comprises: sending an ε value configuration indicating the optimal ε value.

[0208] Aspect 71: A method according to any one of Aspects 45 to 70, wherein to provide the confidence indication, the machine learning component is configured to determine an average value corresponding to the predicted communication metric.

[0209] Aspect 72: The method according to any one of aspects 45 to 71, the method further comprising: receiving a capability report from a user equipment (UE) indicating the capability of the UE to provide the confidence indication.

[0210] Aspect 73: A method according to Aspect 72, wherein the capability report also indicates supported activation types associated with an output layer of the machine learning model.

[0211] Aspect 74: The method according to any one of Aspects 45 to 73, the method further comprising: using over-the-air communication to receive an output report associated with the machine learning component, the output report indicating at least one of the predicted communication metric or the confidence indication.

[0212] Aspect 75: A method according to aspect 74, wherein the output report corresponds to a dedicated uplink control information type associated with a physical layer beam report.

[0213] Aspect 76: The method according to any one of aspects 74 or 75, wherein receiving the output report includes receiving the output report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

[0214] Aspect 77: An apparatus for performing wireless communications at a device, the apparatus comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to one or more of Aspects 1 to 44.

[0215] Aspect 78: A device for wireless communication, the device comprising: a memory; and one or more processors, the one or more processors coupled to the memory and configured to execute the method according to one or more of aspects 1 to 44.

[0216] Aspect 79: An apparatus for wireless communication, the apparatus comprising at least one means for performing the method according to one or more of aspects 1 to 44.

[0217] Aspect 80: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method according to one or more of aspects 1 to 44.

[0218] Aspect 81: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions, which, when executed by one or more processors of a device, causes the device to perform a method according to one or more aspects of Aspects 1 to 44.

[0219] Aspect 82: An apparatus for performing wireless communications at a device, the apparatus comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method according to one or more of Aspects 45 to 76.

[0220] Aspect 83: A device for wireless communication, the device comprising: a memory; and one or more processors, the one or more processors coupled to the memory and configured to execute the method according to one or more aspects of Aspects 45 to 76.

[0221] Aspect 84: An apparatus for wireless communication, the apparatus comprising at least one means for performing a method according to one or more of aspects 45 to 76.

[0222] Aspect 85: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method according to one or more of aspects 45 to 76.

[0223] Aspect 86: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform a method according to one or more of Aspects 45 to 76.

[0224] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of these aspects.

[0225] As used herein, the term "component" is intended to be broadly interpreted as a combination of hardware and / or hardware and software. Whether referred to as software, firmware, middleware, microcode, hardware description language or other names, "software" should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes and / or functions, etc. As used herein, a "processor" is implemented in a combination of hardware and / or hardware and software. It will be apparent that the systems and / or methods described herein can be implemented by a combination of hardware and / or hardware and software in different forms. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit various aspects. Therefore, the operation and behavior of the system and / or method are not described herein with reference to specific software codes, because those skilled in the art will understand that software and hardware can be designed to implement the system and / or method based at least in part on the description herein.

[0226] As used herein, "satisfying a threshold" may refer to a value being greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0227] Although specific combinations of features are set forth in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. Many of these features can be combined in a manner that is not specifically described in the claims and / or is not disclosed in the specification. The disclosure of various aspects includes each dependent claim combined with each other claim in the claim set. As used herein, the phrase "at least one of" the list of items refers to any combination of these items (which includes a single member). As an example, "at least one of a, b or c" is intended to cover a, b, c, a+b, a+c, b+c and a+b+c, and any combination with 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 ordering of a, b and c).

[0228] Any element, action or instruction used herein should not be interpreted as key or necessary, unless explicitly stated. In addition, as used herein, the article "one" is intended to include one or more items, and can be used interchangeably with "one or more". In addition, as used herein, the article "said" is intended to include one or more items connected with the article "said", and can be used interchangeably with "one or more". In addition, as used herein, the terms "set" and "group" are intended to include one or more items, and can be used interchangeably with "one or more". If only one item is intended to be referred to, the phrase "only one" or similar terms will be used. In addition, as used herein, the terms "have", "have" etc. are intended to be open terms, which do not limit the elements they modify (for example, "elements with" A can also have B). In addition, the phrase "based on" is intended to represent "based at least in part on", unless explicitly stated otherwise. Furthermore, as used herein, the term "or" when used in a series is intended to be open-ended and used interchangeably with "and / or" unless explicitly stated otherwise (eg, if used in conjunction with "either" or "only one of").

Claims

1. A method of wireless communication performed by a user equipment (UE), the method comprising: Receive a signal; determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises: receiving, by the machine learning model, an input comprising an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input; and A wireless communication task is performed based at least in part on the predicted communication metric and the confidence indication.

2. The method of claim 1, wherein the input metric comprises reference signal received power (RSRP), and wherein the predicted communication metric comprises predicted RSRP. The method of claim 1 , wherein the confidence indication comprises a standard deviation associated with the predicted communication metric.

4. The method of claim 1 , wherein the input metric comprises an interpolated metric value, the method further comprising: determining a plurality of interpolated metric values ​​including the interpolated metric value; as well as The interpolated metric value is selected based at least in part on the error measurement, the error measurement comprising a minimum error measurement among a plurality of error measurements corresponding to the plurality of interpolated metric values.

5. The method according to claim 1, further comprising: A model error report is sent indicating a model inference error associated with the predicted communication metric. 6 . The method of claim 5 , wherein sending the model error report comprises sending the model error report based at least in part on at least one analysis metric associated with the predicted communication metric satisfying a reporting condition.

7. The method according to claim 1, further comprising: A machine learning configuration associated with the machine learning component is received.

8. The method of claim 1, wherein the machine learning function comprises: a first set of input ports associated with a set of reference signals; a second set of input ports associated with a set of error metrics, wherein the set of error metrics includes the error measurement; a first set of output ports, the first set of output ports being associated with a set of predicted communication metrics, wherein the set of predicted communication metrics includes the predicted communication metrics; and A second set of output ports is associated with a set of confidence measurement outputs, wherein the set of confidence measurement outputs includes the confidence indication.

9. The method according to claim 8, further comprising: Preprocessing operations corresponding to the set of reference signals are performed.

10. The method of claim 9, wherein performing the preprocessing operation comprises normalizing a set of input data based at least in part on a normalization metric.

11. The method according to claim 10, further comprising: An indication of the normalized metric is received.

12. The method according to claim 8, further comprising: Obtaining a set of measurement results associated with a subgroup of the set of reference signals, wherein the subgroup includes fewer reference signals than the set of reference signals, wherein obtaining the set of measurement results includes: skipping the configured measurements based at least in part on receiving downlink communications during a measurement opportunity corresponding to at least one configured measurement.

13. The method according to claim 12, further comprising: A measurement mode indication corresponding to the set of measurement results is generated, wherein the measurement mode indication indicates at least one of: an input port in the set of input ports for which no measurement results are obtained or an input port in the set of input ports for which measurement results are obtained.

14. The method according to claim 13, further comprising: A configuration associated with a measurement input format corresponding to the measurement mode indication is received, wherein generating the measurement mode indication includes generating the measurement mode indication based at least in part on the measurement input format.

15. The method according to claim 13, further comprising: An interpolated measurement result corresponding to the port for which no measurement result was obtained is generated, wherein the measurement mode indication includes an indication of an interpolation error corresponding to the interpolated measurement result.

16. The method of claim 15, wherein the measurement mode indication indicates an interpolation error value of zero associated with a port at which a measurement result is obtained.

17. The method of claim 1, wherein the input metric comprises at least one of a previously predicted communication metric or an interpolated measurement result.

18. The method of claim 17, wherein providing the predicted communication metric comprises performing an autoregressive process associated with the previously predicted communication metric.

19. The method of claim 18, wherein the error measurement comprises at least one previous confidence indication associated with the previously predicted communication metric.

20. The method of claim 1, wherein providing the confidence indication comprises using a dedicated output layer to determine a standard deviation of the prediction.

21. The method of claim 20, wherein generating the predicted standard deviation comprises generating the predicted standard deviation based at least in part on an activation function, wherein the activation function is based at least in part on at least one of a shifted exponential linear unit or an optimal epsilon value.

22. The method of claim 1, wherein providing the confidence indication comprises determining the confidence indication using a central processing unit and based at least in part on outputs from a plurality of configured model layers.

23. The method according to claim 1, further comprising: Sending a capability report indicating the UE's ability to provide the confidence indication, and wherein the capability report also indicates supported activation types associated with an output layer of the machine learning model.

24. The method according to claim 1, further comprising: An output report associated with the machine learning component is sent using over-the-air communications, the output report indicating at least one of the predicted communication metric or the confidence indication.

25. A method of wireless communication performed by a network node, the method comprising: sending a machine learning configuration associated with a machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model configured to: obtaining, by the machine learning model, an input comprising an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input; and Send a reference signal.

26. The method of claim 25, wherein the input metric comprises a reference signal received power (RSRP) associated with the reference signal, and wherein the predicted communication metric comprises a predicted RSRP.

27. A user equipment (UE) for wireless communication, the user equipment (UE) comprising: Memory; and one or more processors, the one or more processors coupled to the memory and configured to: Receive a signal; determining a predicted communication metric and a confidence indication based at least in part on a machine learning component, the machine learning component comprising a machine learning model, and wherein to determine the predicted communication metric and the confidence indication, the one or more processors are configured to: receiving an input including an input metric and an error measurement corresponding to the input metric; as well as providing said predicted communication metric and said confidence indication based at least in part on a machine learning function and said input; as well as A wireless communication task is performed based at least in part on the predicted communication metric and the confidence indication.

28. The UE of claim 27, wherein the input metric comprises reference signal received power (RSRP), and wherein the predicted communication metric comprises predicted RSRP.

29. A network node for wireless communication, the network node comprising: Memory; and one or more processors, the one or more processors coupled to the memory and configured to: sending a machine learning configuration associated with a machine learning component configured to generate a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model configured to: obtaining an input comprising an input metric and an error measurement corresponding to the input metric; and providing the predicted communication metric and the confidence indication based at least in part on a machine learning function and the input; and Send a reference signal.

30. The network node of claim 29, wherein the input metric comprises a reference signal received power (RSRP) associated with the reference signal, and wherein the predicted communication metric comprises a predicted RSRP.