Measurement reporting based on machine learning in wireless communication system

Abstract

The invention relates to machine learning based measurement reporting in wireless communications. According to an embodiment of the present disclosure, a method performed by a user equipment (UE) configured to operate in a wireless communication system includes: receiving, from a network, a configuration for measurement reports related to a plurality of machine learning (ML) models; determining, based on the configuration, a set of ML models for measurement reporting among a plurality of ML models configured for the UE; obtaining a measurement by providing input to the set of ML models; and transmitting at least one of the measurement results to the network.

Description

Technical Field

[0001] The present disclosure relates to machine learning based measurement reporting in wireless communications. Background Art

[0002] The 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) is a technology that enables high-speed packet communications. Many solutions have been proposed for LTE, including those aimed at reducing user and provider costs, improving service quality, and expanding and improving coverage and system capacity. As high-level requirements, 3GPP LTE requires reduced cost per bit, increased service availability, flexible use of frequency bands, a simple structure, open interfaces, and appropriate power consumption of terminals.

[0003] The International Telecommunication Union (ITU) and 3GPP have begun developing requirements and specifications for New Radio (NR) systems. 3GPP must identify and develop the technical components necessary for successful standardization of the new RAT, which will meet both immediate market needs and the longer-term requirements outlined by the ITU Radiocommunication Sector (ITU-R) International Mobile Telecommunications (IMT)-2020 process. Furthermore, NR should be able to use any spectrum band available for wireless communications in the more distant future, at least up to 100 GHz.

[0004] The goal of NR is to be a single technology framework that addresses all use cases, requirements, and deployment scenarios, including enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), ultra-reliable and low-latency communications (URLLC), etc. NR should be inherently forward-compatible.

[0005] A user equipment (UE) may perform actual measurements on reference signals associated with a measurement target to obtain measurement results. The UE may report the measurement results to the network. The UE may also obtain measurement results by using an artificial intelligence (AI) / machine learning (ML) model. The UE may apply a machine learning algorithm associated with the AI / ML model to the model input and obtain AI / ML-based measurement results. Summary of the Invention

[0006] Solution to the problem

[0007] One aspect of the present disclosure is to provide a method and apparatus for machine learning-based measurement reporting in a wireless communication system.

[0008] Another aspect of the present disclosure is to provide a method and apparatus for measurement reporting based on one or more ML models in a wireless communication system.

[0009] According to an embodiment of the present disclosure, a method performed by a user equipment (UE) configured to operate in a wireless communication system includes: receiving a configuration for measurement reporting related to multiple machine learning (ML) models from a network; based on the configuration, determining a set of ML models for measurement reporting from the multiple ML models configured for the UE; obtaining measurement results by providing input to the set of ML models; and sending at least one of the measurement results to the network.

[0010] According to an embodiment of the present disclosure, a user equipment (UE) configured to operate in a wireless communication system includes: at least one transceiver; at least one processor; and at least one memory, wherein the at least one memory is operatively connected to the at least one processor and stores instructions, and the instructions perform operations based on being executed by the at least one processor, wherein the operations include: receiving a configuration for measurement reporting related to multiple machine learning (ML) models from a network; based on the configuration, determining a set of ML models for measurement reporting from the multiple ML models configured for the UE; obtaining measurement results by providing input to the set of ML models; and sending at least one of the measurement results to the network.

[0011] According to an embodiment of the present disclosure, a network node configured to operate in a wireless communication system includes: at least one transceiver; at least one processor; and at least one memory, the at least one memory being operatively coupled to the at least one processor and storing instructions, the instructions being executed by the at least one processor to perform operations, the operations including: sending a configuration for measurement reporting related to multiple machine learning (ML) models to a user equipment (UE); and receiving from the UE at least one of measurement results obtained by providing input to a set of ML models for measurement reporting, wherein the set of ML models is determined from a plurality of ML models configured for the UE based on the configuration.

[0012] According to an embodiment of the present disclosure, a method performed by a network node configured to operate in a wireless communication system includes: sending a configuration for measurement reporting related to multiple machine learning (ML) models to a user equipment (UE); and receiving, from the UE, at least one of measurement results obtained by providing input to a set of ML models for measurement reporting, wherein the set of ML models is determined from the multiple ML models configured for the UE based on the configuration.

[0013] According to an embodiment of the present disclosure, a device suitable for operating in a wireless communication system includes: at least one processor; and at least one memory, the at least one memory being operatively coupled to the at least one processor and storing instructions, wherein the instructions are executed by the at least one processor to perform operations, the operations including: receiving a configuration for measurement reporting related to a plurality of machine learning (ML) models from a network; determining, based on the configuration, a set of ML models for measurement reporting from a plurality of ML models configured for a UE; obtaining measurement results by providing input to the set of ML models; and sending at least one of the measurement results to the network.

[0014] According to an embodiment of the present disclosure, a non-transitory computer-readable medium (CRM) has program code stored thereon, the program code implementing instructions. These instructions are executed by at least one processor to perform operations, the operations including: receiving a configuration for measurement reporting related to multiple machine learning (ML) models from a network; based on the configuration, determining a group of ML models for measurement reporting from multiple ML models configured for a UE; obtaining measurement results by providing input to the group of ML models; and sending at least one of the measurement results to the network.

[0015] The present disclosure may have various beneficial effects.

[0016] For example, the UE may be configured to operate in an optimal mode, resulting in better performance and / or lower power consumption.

[0017] The beneficial effects that can be obtained through the specific embodiments of the present disclosure are not limited to the beneficial effects listed above. For example, there may be various technical effects that can be understood and / or derived from the present disclosure by a person of ordinary skill in the relevant art. Therefore, the specific effects of the present disclosure are not limited to those explicitly described herein, but may include various effects that can be understood or derived from the technical features of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 An example of a communication system to which an implementation of the present disclosure is applied is shown.

[0019] Figure 2 An example of a wireless device to which an implementation of the present disclosure is applied is shown.

[0020] Figure 3 An example of a UE to which an implementation of the present disclosure is applied is shown.

[0021] Figure 4 and Figure 5 An example of a protocol stack in a 3GPP-based wireless communication system to which implementations of the present disclosure are applied is shown.

[0022] Figure 6 The frame structure in a 3GPP-based wireless communication system to which the implementation of the present disclosure is applied is shown.

[0023] Figure 7 An example of data flow in a 3GPP NR system to which an implementation of the present disclosure is applied is shown.

[0024] Figure 8 An example of a functional framework of AI / ML according to an embodiment of the present disclosure is shown.

[0025] Figure 9 An example of a normal measurement process according to an embodiment of the present disclosure is shown.

[0026] Figure 10 An example of an ML-based / assisted measurement process according to an embodiment of the present disclosure is shown.

[0027] Figure 11 An example of a method performed by a UE according to an embodiment of the present disclosure is shown.

[0028] Figure 12 An example of a method performed by a network node according to an embodiment of the present disclosure is shown.

[0029] Figure 13 An example of a procedure between a UE and a network for combined reporting and subsequent model down-selection according to an embodiment of the present disclosure is shown.

[0030] Figure 14 An example of concurrent measurement for deriving model-specific outputs / measurements for multiple models according to an embodiment of the present disclosure is shown.

[0031] Figure 15A An example of combined reporting of measurements derived according to various measurement models according to an embodiment of the present disclosure is shown.

[0032] Figure 15B Examples of combined reporting of measurements derived from various measurement models with output selections are shown. DETAILED DESCRIPTION

[0033] The following techniques, devices, and systems can be applied to various wireless multiple access systems. Examples of multiple access systems include code division multiple access (CDMA) systems, frequency division multiple access (FDMA) systems, time division multiple access (TDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and multi-carrier frequency division multiple access (MC-FDMA) systems. CDMA can be implemented using radio technologies such as Universal Terrestrial Radio Access (UTRA) or CDMA2000. TDMA can be implemented using radio technologies such as Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), or Enhanced Data Rates for GSM Evolution (EDGE). OFDMA can be implemented using radio technologies such as Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or Evolved UTRA (E-UTRA). UTRA is part of Universal Mobile Telecommunications System (UMTS). 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) is part of Evolved UMTS (E-UMTS) that uses E-UTRA. 3GPP LTE uses OFDMA in the downlink (DL) and SC-FDMA in the uplink (UL). Evolutions of 3GPP LTE include LTE-Advanced (LTE-A), LTE-A Pro, and / or 5G New Radio (NR).

[0034] For ease of description, the implementation of the present disclosure is primarily described with respect to a 3GPP-based wireless communication system. However, the technical features of the present disclosure are not limited thereto. For example, although the following detailed description is given based on a mobile communication system corresponding to a 3GPP-based wireless communication system, various aspects of the present disclosure that are not limited to a 3GPP-based wireless communication system are applicable to other mobile communication systems.

[0035] For terms and techniques not specifically described among the terms and techniques employed in the present disclosure, reference may be made to wireless communication standard documents published prior to the present disclosure.

[0036] In the present disclosure, "A or B" may mean "only A", "only B", or "both A and B". In other words, in the present disclosure, "A or B" may be interpreted as "A and / or B". For example, in the present disclosure, "A, B, or C" may mean "only A", "only B", "only C", or "any combination of A, B, and C".

[0037] In the present disclosure, a slash ( / ) or a comma (,) may mean "and / or". For example, "A / B" may mean "A and / or B". Thus, "A / B" may mean "only A", "only B", or "both A and B". For example, "A, B, C" may mean "A, B, or C".

[0038] In the present disclosure, “at least one of A and B” may mean “only A”, “only B”, or “both A and B”. In addition, the expression “at least one of A or B” or “at least one of A and / or B” in the present disclosure may be interpreted as being the same as “at least one of A and B”.

[0039] In addition, in the present disclosure, “at least one of A, B, and C” may mean “only A,” “only B,” “only C,” or “any combination of A, B, and C.” In addition, “at least one of A, B, or C” or “at least one of A, B, and / or C” may mean “at least one of A, B, and C.”

[0040] In addition, the brackets used in this disclosure may mean "for example". Specifically, when "control information (PDCCH)" is shown, "PDCCH" can be cited as an example of "control information". In other words, in this disclosure, "control information" is not limited to "PDCCH", and "PDCCH" can be cited as an example of "control information". In addition, even when "control information (i.e., PDCCH)" is shown, "PDCCH" can be cited as an example of "control information".

[0041] The technical features described separately in one figure in this disclosure can be implemented separately or simultaneously.

[0042] Although not limited thereto, the various descriptions, functions, processes, suggestions, methods and / or operational flowcharts of the present disclosure disclosed herein may be applied to various fields requiring wireless communication and / or connectivity (e.g., 5G) between devices.

[0043] Hereinafter, the present disclosure will be described in more detail with reference to the accompanying drawings. Unless otherwise specified, the same reference numerals in the following drawings and / or descriptions may refer to the same and / or corresponding hardware blocks, software blocks and / or functional blocks.

[0044] Figure 1 An example of a communication system to which an implementation of the present disclosure is applied is shown.

[0045] Figure 1 The 5G usage scenarios shown are only exemplary, and the technical features of the present disclosure can be applied to Figure 1 Other 5G usage scenarios not shown.

[0046] The three main demand categories for 5G include: (1) enhanced mobile broadband (eMBB) category, (2) massive machine type communication (mMTC) category, and (3) ultra-reliable and low-latency communication (URLLC) category.

[0047] Reference Figure 1, the communication system 1 includes wireless devices 100a to 100f, a base station (BS) 200, and a network 300. Figure 1 A 5G network is illustrated as an example of the network of the communication system 1 , but implementations of the present disclosure are not limited to the 5G system and may be applied to future communication systems other than the 5G system.

[0048] BS 200 and network 300 may be implemented as wireless devices, and certain wireless devices may operate as BSs / network nodes relative to other wireless devices.

[0049] Wireless devices 100a to 100f represent devices that perform communication using a radio access technology (RAT) (e.g., 5G NR or LTE) and may be referred to as communication / radio / 5G devices. Wireless devices 100a to 100f may include, but are not limited to, a robot 100a, vehicles 100b-1 and 100b-2, an extended reality (XR) device 100c, a handheld device 100d, a home appliance 100e, an Internet of Things (IoT) device 100f, and an artificial intelligence (AI) device / server 400. For example, a vehicle may include a vehicle with wireless communication capabilities, an autonomous vehicle, and a vehicle capable of performing communication between vehicles. A vehicle may include an unmanned aerial vehicle (UAV) (e.g., a drone). XR devices may include augmented reality (AR) / virtual reality (VR) / mixed reality (MR) devices and may be implemented in the form of a head-mounted device (HMD), a head-up display (HUD) installed in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance device, a digital signage, a vehicle, a robot, and the like. Handheld devices can include smartphones, smart tablets, wearable devices (e.g., smart watches or smart glasses), and computers (e.g., laptops). Home appliances can include TVs, refrigerators, and washing machines. IoT devices can include sensors and smart meters.

[0050] In the present disclosure, wireless devices 100a to 100f may be referred to as user equipment (UE). UE may include, for example, a cellular phone, a smartphone, a laptop computer, a digital broadcast terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a tablet-shaped personal computer (PC), a tablet PC, an ultrabook, a vehicle, a vehicle with autonomous driving capabilities, a connected car, an unmanned aerial vehicle (UAV), an AI module, a robot, an AR device, a VR device, an MR device, a hologram device, a public safety device, an MTC device, an IoT device, a medical device, a FinTech device (or financial device), a security device, a weather / environmental device, a device related to 5G services, or a device related to the Fourth Industrial Revolution.

[0051] Wireless devices 100a to 100f can connect to network 300 via BS 200. AI technology can be applied to wireless devices 100a to 100f, and wireless devices 100a to 100f can connect to AI server 400 via network 300. Network 300 can be configured using a 3G network, a 4G network (e.g., LTE), a 5G network (e.g., NR), and a beyond 5G network. While wireless devices 100a to 100f can communicate with each other via BS 200 / network 300, wireless devices 100a to 100f can perform direct communication with each other (e.g., sidelink communication) without going through BS 200 / network 300. For example, vehicles 100b-1 and 100b-2 can perform direct communication (e.g., vehicle-to-vehicle (V2V) / vehicle-to-everything (V2X) communication). IoT devices (e.g., sensors) can perform direct communication with other IoT devices (e.g., sensors) or other wireless devices 100a to 100f.

[0052] Wireless communications / connections 150a, 150b, and 150c may be established between wireless devices 100a to 100f and / or between wireless devices 100a to 100f and BS 200 and / or between BSs 200. Wireless communications / connections may be established via various RATs (e.g., 5G NR), such as uplink / downlink communication 150a, sidelink communication (or device-to-device (D2D) communication) 150b, and inter-base station communication 150c (e.g., relay, integrated access and backhaul (IAB)). Wireless devices 100a to 100f and BS 200 / wireless devices 100a to 100f may transmit / receive radio signals to / from each other via wireless communications / connections 150a, 150b, and 150c. For example, wireless communications / connections 150a, 150b, and 150c may transmit / receive signals via various physical channels. To this end, various configuration information configuration processes for sending / receiving radio signals, various signal processing processes (e.g., channel coding / decoding, modulation / demodulation, and resource mapping / demapping), and at least a portion of the resource allocation process can be performed based on the various proposals of the present disclosure.

[0053] NR supports multiple numerologies (and / or multiple subcarrier spacings (SCS)) to support various 5G services. For example, if the SCS is 15kHz, wide areas can be supported in traditional cellular bands, while if the SCS is 30kHz / 60kHz, dense cities, lower latency, and wider carrier bandwidths can be supported. If the SCS is 60kHz or higher, bandwidths greater than 24.25GHz can be supported to overcome phase noise.

[0054] The NR frequency band can be defined as two types of frequency ranges, namely, frequency range 1 (FR1) and frequency range 2 (FR2). The numerical values ​​of the frequency ranges can be changed. For example, the two types of frequency ranges (FR1 and FR2) can be shown in Table 1 below. For ease of explanation, in the frequency range used in the NR system, FR1 can mean "a range below 6 GHz", FR2 can mean "a range above 6 GHz", and can be referred to as millimeter wave (mmW).

[0055] [Table 1]

[0056] Frequency range name Corresponding frequency range Subcarrier spacing FR1 450MHz-6000MHz 15, 30, 60kHz FR2 24250MH-52600MHz 60, 120, 240kHz

[0057] As described above, the numerical value of the frequency range of the NR system can be changed. For example, FR1 may include a frequency band of 410 MHz to 7125 MHz as shown in Table 2 below. That is, FR1 may include a frequency band of 6 GHz (or 5850 MHz, 5900 MHz, 5925 MHz, etc.) or higher. For example, the frequency band of 6 GHz (or 5850 MHz, 5900 MHz, 5925 MHz, etc.) or higher included in FR1 may include an unlicensed frequency band. The unlicensed frequency band can be used for various purposes, for example, for communication of vehicles (e.g., autonomous driving).

[0058] [Table 2]

[0059] Frequency range name Corresponding frequency range Subcarrier spacing FR1 410MHz-7125MHz 15, 30, 60kHz FR2 24250MHz-52600MHz 60, 120, 240kHz

[0060] Here, the radio communication technology implemented in the wireless device in the present disclosure may include narrowband Internet of Things (NB-IoT) technology for low-power communication as well as LTE, NR and 6G. For example, NB-IoT technology may be an example of a low-power wide area network (LPWAN) technology, may be implemented in specifications such as LTE Cat NB1 and / or LTE Cat NB2, and may not be limited to the above names. Additionally and / or alternatively, the radio communication technology implemented in the wireless device in the present disclosure may communicate based on LTE-M technology. For example, LTE-M technology may be an example of an LPWAN technology and may be referred to by various names such as enhanced machine type communication (eMTC). For example, LTE-M technology may be implemented in at least one of various specifications, such as 1) LTE Cat 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-bandwidth limited (non-BL), 5) LTE-MTC, 6) LTE machine type communication and / or 7) LTE M, and may not be limited to the above names. Additionally and / or alternatively, the radio communication technology implemented in the wireless device of the present disclosure may include at least one of ZigBee, Bluetooth, and / or LPWAN considering low-power communication, and may not be limited to the above names. For example, ZigBee technology can generate a personal area network (PAN) associated with small / low-power digital communication based on various specifications (such as IEEE 802.15.4) and may be referred to by various names. Figure 2 An example of a wireless device to which an implementation of the present disclosure is applied is shown.

[0061] exist Figure 2 In the embodiment, the first wireless device 100 and / or the second wireless device 200 may be implemented in various forms according to the use case / service. For example, {the first wireless device 100 and the second wireless device 200} may correspond to Figure 1 {wireless devices 100a to 100f and BS 200}, {wireless devices 100a to 100f and wireless devices 100a to 100f} and / or {BS 200 and BS

[0062] 200}. The first wireless device 100 and / or the second wireless device 200 may be configured by various elements, devices / components and / or modules.

[0063] The first wireless device 100 may include at least one transceiver (eg, transceiver 106 ), at least one processing chip (eg, processing chip 101 ), and / or one or more antennas 108 .

[0064] The processing chip 101 may include at least one processor (eg, processor 102 ) and at least one memory (eg, memory 104 ). Additionally and / or alternatively, the memory 104 may be located outside the processing chip 101 .

[0065] The processor 102 may control the memory 104 and / or the transceiver 106 and may be adapted to implement the descriptions, functions, processes, suggestions, methods, and / or operational flow charts described in the present disclosure. For example, the processor 102 may process information in the memory 104 to generate first information / signals, and then transmit a radio signal including the first information / signals through the transceiver 106. The processor 102 may receive a radio signal including second information / signals through the transceiver 106, and then store information obtained by processing the second information / signals in the memory 104.

[0066] Memory 104 may be operatively connected to processor 102. Memory 104 may store various types of information and / or instructions. Memory 104 may store firmware and / or software code 105 that implements codes, commands, and / or command sets that, when executed by processor 102, perform the descriptions, functions, procedures, suggestions, methods, and / or operational flow charts disclosed herein. For example, firmware and / or software code 105 may implement instructions that, when executed by processor 102, perform the descriptions, functions, procedures, suggestions, methods, and / or operational flow charts disclosed herein. For example, firmware and / or software code 105 may control processor 102 to execute one or more protocols. For example, firmware and / or software code 105 may control processor 102 to execute one or more layers of a wireless interface protocol.

[0067] In this document, the processor 102 and the memory 104 may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). The transceiver 106 may be connected to the processor 102 and transmit and / or receive radio signals via one or more antennas 108. Each transceiver 106 may include a transmitter and / or a receiver. The transceiver 106 may be used interchangeably with a radio frequency (RF) unit. In this disclosure, the first wireless device 100 may represent a communication modem / circuit / chip.

[0068] The second wireless device 200 may include at least one transceiver (eg, transceiver 206 ), at least one processing chip (eg, processing chip 201 ), and / or one or more antennas 208 .

[0069] The processing chip 201 may include at least one processor (eg, processor 202 ) and at least one memory (eg, memory 204 ). Additionally and / or alternatively, the memory 204 may be located outside the processing chip 201 .

[0070] The processor 202 may control the memory 204 and / or the transceiver 206 and may be adapted to implement the descriptions, functions, processes, suggestions, methods, and / or operational flow charts described in the present disclosure. For example, the processor 202 may process the information in the memory 204 to generate third information / signals, and then transmit a radio signal including the third information / signals through the transceiver 206. The processor 202 may receive a radio signal including fourth information / signals through the transceiver 106, and then store information obtained by processing the fourth information / signals in the memory 204.

[0071] Memory 204 may be operatively connected to processor 202. Memory 204 may store various types of information and / or instructions. Memory 204 may store firmware and / or software code 205 that implements code, commands, and / or command sets that, when executed by processor 202, perform the descriptions, functions, procedures, suggestions, methods, and / or operational flow charts disclosed herein. For example, firmware and / or software code 205 may implement instructions that, when executed by processor 202, perform the descriptions, functions, procedures, suggestions, methods, and / or operational flow charts disclosed herein. For example, firmware and / or software code 205 may control processor 202 to execute one or more protocols. For example, firmware and / or software code 205 may control processor 202 to execute one or more layers of a wireless interface protocol.

[0072] In this document, the processor 202 and the memory 204 may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). The transceiver 206 may be connected to the processor 202 and transmit and / or receive radio signals via one or more antennas 208. Each of the transceivers 206 may include a transmitter and / or a receiver. The transceiver 206 may be used interchangeably with an RF unit. In this disclosure, the second wireless device 200 may represent a communication modem / circuit / chip.

[0073] In the following, the hardware elements of the wireless devices 100 and 200 will be described in more detail. One or more protocol layers may be implemented by, but are not limited to, one or more processors 102 and 202. For example, one or more processors 102 and 202 may implement one or more layers (e.g., functional layers such as a physical (PHY) layer, a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, and a service data adaptation protocol (SDAP) layer). The one or more processors 102 and 202 may generate one or more protocol data units (PDUs), one or more service data units (SDUs), messages, control information, data, or information according to the descriptions, functions, processes, suggestions, methods, and / or operational flowcharts disclosed in the present disclosure. The one or more processors 102 and 202 may generate a signal (e.g., a baseband signal) including a PDU, SDU, message, control information, data, or information according to the description, functions, procedures, suggestions, methods, and / or operational flowcharts disclosed in the present disclosure and provide the generated signal to the one or more transceivers 106 and 206. The one or more processors 102 and 202 may receive a signal (e.g., a baseband signal) from the one or more transceivers 106 and 206 and obtain the PDU, SDU, message, control information, data, or information according to the description, functions, procedures, suggestions, methods, and / or operational flowcharts disclosed in the present disclosure.

[0074] One or more processors 102 and 202 may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors 102 and 202 may be implemented by hardware, firmware, software, or a combination thereof. As an example, one or more application specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), or one or more field programmable gate arrays (FPGAs) may be included in one or more processors 102 and 202. For example, one or more processors 102 and 202 may be configured by a group of communication control processors, application processors (APs), electronic control units (ECUs), central processing units (CPUs), graphics processing units (GPUs), and memory control processors.

[0075] One or more memories 104 and 204 can be connected to one or more processors 102 and 202 and store various types of data, signals, messages, information, programs, codes, instructions and / or commands. One or more memories 104 and 204 can be configured by random access memory (RAM), dynamic RAM (DRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EPROM), flash memory, volatile memory, non-volatile memory, hard drive, registers, cache memory, computer-readable storage media and / or combinations thereof. One or more memories 104 and 204 can be located inside and / or outside of one or more processors 102 and 202. One or more memories 104 and 204 can be connected to one or more processors 102 and 202 via various technologies such as wired connections or wireless connections.

[0076] One or more transceivers 106 and 206 may transmit user data, control information, and / or radio signals / channels as described in the descriptions, functions, processes, suggestions, methods, and / or operational flowcharts disclosed in this disclosure to one or more other devices. One or more transceivers 106 and 206 may receive user data, control information, and / or radio signals / channels as described in the descriptions, functions, processes, suggestions, methods, and / or operational flowcharts disclosed in this disclosure from one or more other devices. For example, one or more transceivers 106 and 206 may be connected to one or more processors 102 and 202 and transmit and receive radio signals. For example, one or more processors 102 and 202 may control one or more transceivers 106 and 206 to transmit user data, control information, or radio signals to one or more other devices. One or more processors 102 and 202 may control one or more transceivers 106 and 206 to receive user data, control information, or radio signals from one or more other devices.

[0077] One or more transceivers 106 and 206 may be connected to one or more antennas 108 and 208. Additionally or alternatively, one or more transceivers 106 and 206 may include one or more antennas 108 and 208. One or more transceivers 106 and 206 may be adapted to transmit and receive user data, control information, and / or radio signals / channels mentioned in the descriptions, functions, processes, suggestions, methods, and / or operational flow charts disclosed in the present disclosure through one or more antennas 108 and 208. In the present disclosure, one or more antennas 108 and 208 may be multiple physical antennas or multiple logical antennas (e.g., antenna ports).

[0078] The one or more transceivers 106 and 206 may convert received user data, control information, radio signals / channels, etc. from RF band signals to baseband signals so that the received user data, control information, radio signals / channels, etc. may be processed by the one or more processors 102 and 202. The one or more transceivers 106 and 206 may convert user data, control information, radio signals / channels, etc. processed by the one or more processors 102 and 202 from baseband signals to RF band signals. To this end, the one or more transceivers 106 and 206 may include (analog) oscillators and / or filters. For example, under the control of the one or more processors 102 and 202, the one or more transceivers 106 and 206 may up-convert an OFDM baseband signal into an OFDM signal through their (analog) oscillators and / or filters and transmit the up-converted OFDM signal at the carrier frequency. One or more transceivers 106 and 206 may receive an OFDM signal at a carrier frequency and down-convert the OFDM signal to an OFDM baseband signal through their (analog) oscillators and / or filters under the control of one or more processors 102 and 202 .

[0079] although Figure 2 Although not shown in the figures, the wireless devices 100 and 200 may further include additional components. The additional components 140 may be configured differently depending on the type of the wireless devices 100 and 200. For example, the additional components 140 may include at least one of a power supply unit / battery, an input / output (I / O) device (e.g., an audio I / O port, a video I / O port), a drive device, and a computing device. The additional components 140 may be coupled to one or more processors 102 and 202 via various technologies, such as a wired or wireless connection.

[0080] In implementations of the present disclosure, a UE may function as a transmitting device in the uplink (UL) and a receiving device in the downlink (DL). In implementations of the present disclosure, a base station (BS) may function as a receiving device in the UL and a transmitting device in the DL. Hereinafter, for ease of description, it is primarily assumed that a first wireless device 100 functions as a UE and a second wireless device 200 functions as a base station (BS). For example, a processor 102 connected to, installed on, or activated in the first wireless device 100 may be adapted to perform UE behavior according to implementations of the present disclosure or to control a transceiver 106 to perform UE behavior according to implementations of the present disclosure. A processor 202 connected to, installed on, or activated in the second wireless device 200 may be adapted to perform BS behavior according to implementations of the present disclosure or to control a transceiver 206 to perform BS behavior according to implementations of the present disclosure.

[0081] In this disclosure, a BS is also referred to as a Node B (NB), an eNode B (eNB), or a gNB.

[0082] Figure 3 An example of a UE to which an implementation of the present disclosure is applied is shown.

[0083] Reference Figure 3 , UE 100 may correspond to Figure 2 The first wireless device 100 is configured to:

[0084] UE 100 includes a processor 102 , memory 104 , a transceiver 106 , one or more antennas 108 , a power management module 141 , a battery 142 , a display 143 , a keypad 144 , a subscriber identity module (SIM) card 145 , a speaker 146 , and a microphone 147 .

[0085] The processor 102 may be adapted to implement the descriptions, functions, processes, suggestions, methods and / or operational flowcharts disclosed in the present disclosure. The processor 102 may be adapted to control one or more other components of the UE 100 to implement the descriptions, functions, processes, suggestions, methods and / or operational flowcharts disclosed in the present disclosure. The radio interface protocol layer may be implemented in the processor 102. The processor 102 may include an ASIC, other chipsets, logic circuits and / or data processing devices. The processor 102 may be an application processor. The processor 102 may include at least one of a digital signal processor (DSP), a central processing unit (CPU), a graphics processing unit (GPU), a modem (modulator and demodulator). An example of the processor 102 may be a processor in a Qualcomm processor. SNAPDRAGON MANUFACTURED TM series processors, Samsung Manufactured by EXYNOS TM series processors, Apple A series of processors manufactured by MediaTek Manufactured by HELIO TM series processors, Intel ATOM manufactured TM series processors or the corresponding next-generation processors.

[0086] The memory 104 is coupled to the processor 102 during operation and stores various information to operate the processor 102. The memory 104 may include ROM, RAM, flash memory, memory card, storage medium, and / or other storage devices. When the embodiment is implemented in software, the technology described herein may be implemented using modules (e.g., processes, functions, etc.) that execute the descriptions, functions, processes, suggestions, methods, and / or operational flowcharts disclosed in this disclosure. The modules may be stored in the memory 104 and implemented by the processor 102. The memory 104 may be implemented within the processor 102 or external to the processor 102 (in which case, the memory may be communicatively coupled to the processor 102 via various means known in the art).

[0087] The transceiver 106 is coupled to the processor 102 during operation and transmits and / or receives radio signals. The transceiver 106 includes a transmitter and a receiver. The transceiver 106 may include baseband circuitry to process radio frequency signals. The transceiver 106 controls one or more antennas 108 to transmit and / or receive radio signals.

[0088] The power management module 141 manages the power of the processor 102 and / or the transceiver 106. The battery 142 provides power to the power management module 141.

[0089] The display 143 outputs a result processed by the processor 102. The keypad 144 receives an input to be used by the processor 102. The keypad 144 may be displayed on the display 143.

[0090] The SIM card 145 is an integrated circuit designed to securely store an International Mobile Subscriber Identity (IMSI) number and its associated keys, which are used to identify and authenticate subscribers on mobile telephony devices such as mobile phones and computers. Contact information can also be stored on many SIM cards.

[0091] The speaker 146 outputs sound-related results processed by the processor 102. The microphone 147 receives sound-related input to be used by the processor 102.

[0092] Figure 4 and Figure 5 An example of a protocol stack in a 3GPP-based wireless communication system to which implementations of the present disclosure are applied is shown.

[0093] Specifically, Figure 4 An example of a radio interface user plane protocol stack between a UE and a BS is illustrated, and Figure 5 An example of a radio interface control plane protocol stack between a UE and a BS is illustrated. The control plane refers to a path for transmitting control messages used by the UE and the network to manage calls. The user plane refers to a path for transmitting data generated in the application layer (for example, voice data or Internet packet data). Figure 4 , the user plane protocol stack can be divided into layer 1 (ie, PHY layer) and layer 2. Figure 5 , the control plane protocol stack can be divided into layer 1 (ie, PHY layer), layer 2, layer 3 (eg, RRC layer) and non-access stratum (NAS) layer. Layer 1, layer 2 and layer 3 are called access stratum (AS).

[0094] In 3GPP LTE systems, Layer 2 is divided into the following sublayers: MAC, RLC, and PDCP. In 3GPP NR systems, Layer 2 is divided into the following sublayers: MAC, RLC, PDCP, and SDAP. The PHY layer provides transport channels to the MAC sublayer, the MAC sublayer provides logical channels to the RLC sublayer, the RLC sublayer provides RLC channels to the PDCP sublayer, and the PDCP sublayer provides radio bearers to the SDAP sublayer. The SDAP sublayer provides Quality of Service (QoS) flows to the 5G core network.

[0095] In 3GPP NR systems, the main services and functions of the MAC sublayer include: mapping between logical channels and transport channels; multiplexing MAC SDUs belonging to one or different logical channels into / demultiplexing transport blocks (TBs) delivered to / from the physical layer on the transport channel; scheduling information reporting; error correction through hybrid automatic repeat request (HARQ) (one HARQ entity per cell in the case of carrier aggregation (CA); priority handling between UEs with dynamic scheduling; priority handling between logical channels of a UE with logical channel prioritization; and padding. A single MAC entity can support multiple parameter sets, transmission timings, and cells. Mapping restrictions in logical channel prioritization control which parameter set(s), cell, and transmission timing can be used by a logical channel.

[0096] MAC provides different types of data transmission services. In order to accommodate different types of data transmission services, multiple types of logical channels are defined, that is, each logical channel supports the transmission of a specific type of information. Each logical channel type is defined by what type of information is transmitted. Logical channels are divided into two groups: control channels and traffic channels. Control channels are only used for the transmission of control plane information, and traffic channels are only used for the transmission of user plane information. The Broadcast Control Channel (BCCH) is a downlink logical channel used to broadcast system control information, the Paging Control Channel (PCCH) is a downlink logical channel that transmits paging information, system information change notifications, and indications of ongoing Public Warning Service (PWS) broadcasts, the Common Control Channel (CCCH) is a logical channel used to send control information between the UE and the network and is used for UEs that do not have an RRC connection with the network, and the Dedicated Control Channel (DCCH) is a point-to-point bidirectional logical channel that sends dedicated control information between the UE and the network and is used by UEs with an RRC connection. The Dedicated Traffic Channel (DTCH) is a point-to-point logical channel dedicated to one UE, which is used to transmit user information. The DTCH can exist in both the uplink and downlink. In the downlink, the following connections exist between logical channels and transport channels: BCCH can be mapped to the broadcast channel (BCH); BCCH can be mapped to the downlink shared channel (DL-SCH); PCCH can be mapped to the paging channel (PCH); CCCH can be mapped to DL-SCH; DCCH can be mapped to DL-SCH; and DTCH can be mapped to DL-SCH. In the uplink, the following connections exist between logical channels and transport channels: CCCH can be mapped to the uplink shared channel (UL-SCH); DCCH can be mapped to UL-SCH; and DTCH can be mapped to UL-SCH.

[0097] The RLC sublayer supports three transmission modes: transparent mode (TM), unacknowledged mode (UM), and acknowledged mode (AM). RLC configuration is specific to each logical channel and is independent of the parameter set and / or transmission duration. In 3GPP NR systems, the main services and functions of the RLC sublayer depend on the transmission mode and include: delivery of upper layer PDUs; sequence numbering independent of either PDCP (UM and AM); error correction through ARQ (AM only); segmentation (AM and UM) and re-segmentation (AM only) of RLC SDUs; reassembly of SDUs (AM and UM); duplicate detection (AM only);

[0098] RLC SDU discard (AM and UM); RLC re-establishment; protocol error detection (AM only).

[0099] In the 3GPP NR system, the main services and functions of the PDCP sublayer for the user plane include: sequence numbering; header compression and decompression using Robust Header Compression (ROHC); delivery of user data; reordering and duplicate detection; in-sequence delivery; PDCP PDU routing (in the case of split bearers); retransmission of PDCP SDUs; ciphering, deciphering, and integrity protection; PDCP SDU discard; PDCP re-establishment and data recovery for RLC AM; PDCP status reporting for RLC AM; PDCP PDU duplication and duplicate discard indication to lower layers. The main services and functions of the PDCP sublayer for the control plane include: sequence numbering; ciphering, deciphering, and integrity protection; delivery of control plane data; reordering and duplicate detection; in-sequence delivery; PDCP PDU duplication and duplicate discard indication to lower layers.

[0100] In 3GPP NR systems, the main services and functions of SDAP include: mapping between QoS flows and data radio bearers; marking QoS flow IDs (QFIs) in both DL and UL packets; and configuring a single SDAP protocol entity for each individual PDU session.

[0101] In the 3GPP NR system, the main services and functions of the RRC sublayer include: broadcast of system information related to AS and NAS; paging initiated by 5GC or NG-RAN; establishment, maintenance and release of RRC connection between UE and NG-RAN; security functions including key management; establishment, configuration, maintenance and release of signaling radio bearers (SRBs) and data radio bearers (DRBs); mobility functions (including: handover and context transfer; UE cell selection and reselection and control of cell selection and reselection; inter-RAT mobility); QoS management functions; UE measurement reporting and control of reporting; detection and repair of radio link failure; transmission of NAS messages from UE to NAS / from NAS to UE.

[0102] Figure 6 The frame structure in a 3GPP-based wireless communication system to which the implementation of the present disclosure is applied is shown.

[0103] Figure 6The frame structure shown is only exemplary, and the number of subframes, the number of time slots and / or the number of symbols in a frame may vary. In a 3GPP-based wireless communication system, OFDM parameter sets (e.g., subcarrier spacing (SCS), transmission time interval (TTI) duration) may be configured differently between multiple cells aggregated for one UE. For example, if a UE is configured with different SCSs for cells aggregated for a cell, the (absolute time) duration of time resources (e.g., subframes, time slots, or TTIs) comprising the same number of symbols may be different among the aggregated cells. In this document, symbols may include OFDM symbols (or CP-OFDM symbols), SC-FDMA symbols (or discrete Fourier transform-spread-OFDM (DFT-s-OFDM) symbols).

[0104] Reference Figure 6 , downlink and uplink transmissions are organized into frames. Each frame has T f =10ms duration. Each frame is divided into two half-frames, where each half-frame has a duration of 5ms. Each half-frame includes 5 sub-frames, where the duration of each sub-frame is T sf is 1 ms. Each subframe is divided into slots, and the number of slots in a subframe depends on the subcarrier spacing. Each slot includes 14 or 12 OFDM symbols based on the cyclic prefix (CP). In normal CP, each slot includes 14 OFDM symbols, and in extended CP, each slot includes 12 OFDM symbols. The parameter set is based on an exponentially scalable subcarrier spacing βf=2 u *15kHz.

[0105] Table 3 shows the subcarrier spacing βf=2 u *N number of OFDM symbols per slot for normal CP of 15 kHz slot symb , the number of time slots per frame N frame，u slot and the number of time slots per subframe N subframe，u slot .

[0106] [Table 3]

[0107] u <![CDATA[N slot symb ]]> <![CDATA[N frame，u slot ]]> <![CDATA[N subframe，u slot ]]> 0 14 10 1 1 14 20 2 2 14 40 4 3 14 80 8 4 14 160 16

[0108] Table 4 shows the subcarrier spacing βf=2 u *N number of OFDM symbols per slot for extended CP of 15 kHz slot symb , the number of time slots per frame N frame，u slot and the number of time slots per subframe Nsubframe，u slot .

[0109] [Table 4]

[0110] u <![CDATA[N slot symb ]]> <![CDATA[N frame，u slot ]]> <![CDATA[N subframe，u slot ]]> 2 12 40 4

[0111] A slot includes a plurality of symbols (e.g., 14 or 12 symbols) in the time domain. For each parameter set (e.g., subcarrier spacing) and carrier, a common resource block (CRB) N indicated by higher layer signaling (e.g., RRC signaling) is defined. start，u grid Starting N size，u grid，x *N RB sc subcarriers and N subframe，u symb OFDM symbol resource grid, where N si z e，u grid，x is the number of resource blocks (RBs) in the resource grid, and the subscript x is DL for the downlink and UL for the uplink. N RB sc is the number of subcarriers per RB. In 3GPP-based wireless communication systems, N RB sc Typically 12. For a given antenna port p, subcarrier spacing configuration u, and transmission direction (DL or UL), there is one resource grid. The carrier bandwidth N for subcarrier spacing configuration u size，u grid Given by high-level parameters (e.g., RRC parameters). Each element in the resource grid for antenna port p and subcarrier spacing configuration u is called a resource element (RE), and one complex symbol can be mapped to each RE. Each RE in the resource grid is uniquely identified by an index k in the frequency domain and an index l in the time domain that represents the symbol position relative to a reference point. In a 3GPP-based wireless communication system, an RB is defined by 12 consecutive subcarriers in the frequency domain. Figure 6As shown in the figure, as the SCS is doubled, the slot length and symbol length are halved. For example, when the SCS is 15kHz, the slot length is 1ms, which is the same as the subframe length. When the SCS is 30kHz, the slot length is 0.5ms (=500us), and the symbol length is half of the symbol length when the SCS is 15kHz. When the SCS is 60kHz, the slot length is 0.25ms (=250us), and the symbol length is half of the symbol length when the SCS is 30kHz. When the SCS is 120kHz, the slot length is 0.125ms (=125us), and the symbol length is half of the symbol length when the SCS is 60kHz. When the SCS is 240kHz, the slot length is 0.0625ms (=62.5us), and the symbol length is half of the symbol length when the SCS is 120kHz.

[0112] In 3GPP NR systems, RBs are classified into CRBs and physical resource blocks (PRBs). For subcarrier spacing configuration u, CRBs are numbered from 0 upwards in the frequency domain. The center of subcarrier 0 of CRB0 for subcarrier spacing configuration u coincides with "point A", which is used as a common reference point for the resource block grid. In 3GPP NR systems, PRBs are defined within a bandwidth part (BWP) and are numbered from 0 to N. size BWP，i -1 numbering, where i is the number of bandwidth parts. Physical resource blocks n in bandwidth part i PRB With public resource block n CRB The relationship between them is as follows: PRB =n CRB +N size BWP，i , where N size BWP，i A BWP is a common resource block where the bandwidth portion begins relative to CRB0. A BWP consists of multiple contiguous RBs. A carrier can include up to N (e.g., 5) BWPs. A UE can be configured with one or more BWPs on a given component carrier. Only one BWP configured for a UE can be active at a time. The active BWP defines the UE's operating bandwidth within the cell's operating bandwidth.

[0113] In the present disclosure, the term "cell" may refer to a geographical area in which one or more nodes provide a communication system or to a radio resource. A "cell" as a geographical area may be understood as a coverage area within which a node can provide services using a carrier, and a "cell" as a radio resource (e.g., a time-frequency resource) is associated with a bandwidth that is a frequency range configured by a carrier. A "cell" associated with a radio resource is defined by a combination of downlink resources and uplink resources (e.g., a combination of a DL component carrier (CC) and a ULCC). A cell may be configured only by downlink resources, or may be configured by downlink resources and uplink resources. Since the DL coverage (which is the range within which a node can send a valid signal) and the UL coverage (which is the range within which a node can receive a valid signal from a UE) depend on the carrier carrying the signal, the coverage of a node may be associated with the coverage of a "cell" of the radio resource used by the node. Therefore, the term "cell" may sometimes be used to refer to the service coverage of a node, at other times to refer to a radio resource, or at other times to refer to a range within which a signal using a radio resource can reach with effective strength.

[0114] In CA, two or more CCs are aggregated. The UE can receive or transmit on one or more CCs simultaneously depending on its capabilities. CA is supported for both contiguous CCs and non-contiguous CCs. When CA is configured, the UE has only one RRC connection with the network. During RRC connection establishment / reestablishment / handover, one serving cell provides NAS mobility information, and during RRC connection reestablishment / handover, one serving cell provides security input. This cell is called a primary cell (PCell). A PCell is a cell operating on the primary frequency, where the UE performs an initial connection establishment procedure or initiates a connection reestablishment procedure. Depending on the UE capabilities, a secondary cell (SCell) can be configured to form a set of serving cells together with the PCell. An SCell is a cell that provides additional radio resources on top of a special cell (SpCell). Therefore, the set of serving cells configured for a UE always consists of one PCell and one or more SCells. For dual connectivity (DC) operation, the term SpCell refers to the PCell of a primary cell group (MCG) or the primary SCell (PSCell) of a secondary cell group (SCG). SpCell supports PUCCH transmission and contention-based random access and is always activated. MCG is a group of serving cells associated with a master node, which includes SpCell (PCell) and optionally one or more SCells. For UEs configured with DC, SCG is a subset of serving cells associated with a secondary node, which includes PSCell and zero or more SCells. For RRC_CONNECTED UEs not configured with CA / DC, there is only one serving cell consisting of PCell. For RRC_CONNECTED UEs configured with CA / DC, the term "serving cell" is used to refer to a set of cells consisting of SpCell and all SCells. In DC, two MAC entities are configured in the UE: one for MCG and one for SCG.

[0115] Figure 7 An example of data flow in a 3GPP NR system to which an implementation of the present disclosure is applied is shown.

[0116] Reference Figure 7 "RB" stands for radio bearer, and "H" stands for header. Radio bearers are categorized into two groups: DRBs for user plane data and SRBs for control plane data. MAC PDUs are transmitted and received to and from external devices via the PHY layer using radio resources. MAC PDUs arrive at the PHY layer in the form of transport blocks.

[0117] In the PHY layer, the uplink transport channels UL-SCH and RACH are mapped to their physical channels, the physical uplink shared channel (PUSCH) and the physical random access channel (PRACH), respectively, and the downlink transport channels DL-SCH, BCH, and PCH are mapped to the physical downlink shared channel (PDSCH), the physical broadcast channel (PBCH), and the PDSCH, respectively. In the PHY layer, uplink control information (UCI) is mapped to the physical uplink control channel (PUCCH), and downlink control information (DCI) is mapped to the physical downlink control channel (PDCCH). The UE sends a MAC PDU related to the UL-SCH via the PUSCH based on the UL grant, and the BS sends a MAC PDU related to the DL-SCH via the PDSCH based on the DL assignment.

[0118] The following describes artificial intelligence (AI) / machine learning (ML) related features.

[0119] Figure 8 An example of a functional framework of AI / ML according to an embodiment of the present disclosure is shown.

[0120] exist Figure 8 In [1], data collection is the function of providing input data for model training, management, and inference functions. Input data can include at least one of the following items:

[0121] -Serves as training data required as input for AI / ML model training functions;

[0122] - Monitoring data required as input to AI / ML models or management of AI / ML functions; or

[0123] -Serves as the inference data required as input for AI / ML inference functions.

[0124] For example, the monitoring data may include at least one of the following:

[0125] - Beam prediction accuracy-related KPIs, such as Top-K / 1 beam prediction accuracy;

[0126] Link quality-related KPIs, such as throughput, L1-RSRP, L1-SINR, and assumed BLER;

[0127] - Performance metrics based on the input / output data distribution of AI / ML; or

[0128] - L1-RSRP difference evaluated by comparing measured RSRP and predicted RSRP.

[0129] The model training function performs training, validation, and testing of AI / ML models, which can generate model performance metrics that can be used as part of the model testing process. If necessary, the model training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function. In the case of a model storage function, the model training function is used to pass the trained, validated, and tested AI / ML model (i.e., the trained model) to the model storage function, or to pass the updated version of the model (i.e., the updated model) to the model storage function.

[0130] Management is the function of supervising the operation (e.g., selection / (de)activation / switching / fallback) and monitoring of AI / ML models or AI / ML functions. This function is also responsible for making decisions based on data received from the data collection function and the reasoning function to ensure correct reasoning operation. Selection / (de)activation / switching / fallback is information required as input for the management reasoning function. Relevant information may include selection / (de)activation / switching of AI / ML models or AI / ML-based functions, fallback to non-AI / ML operation (i.e., not relying on the reasoning process). Model transfer / delivery request is used to request a model from the model storage function. Performance feedback / retraining request is information required as input for the model training function, for example for model (re)training or updating purposes.

[0131] Inference is the function that provides the output from the process of applying an AI / ML model or AI / ML function to new data (i.e., inference data). If necessary, the inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered by the data collection function. Inference output is the data used by management functions to monitor the performance of the AI / ML model or AI / ML function.

[0132] Model storage is the function responsible for storing trained / updated models that can be used to perform inference. The model storage function, if any, serves primarily as a reference point for protocol termination, model delivery / transfer, and related processing (where applicable). It is important to emphasize that this does not intend to restrict the actual storage location of the model. Model delivery / transfer is used to pass AI / ML models to the inference function.

[0133] Typically, a UE may perform measurements based on actual measurements of known reference signals and derive measurement results strictly based on the actual measurements (possibly post-processing the reference signal measurement results, such as filtering based on linear averaging or exponential moving average). In this disclosure, this type of normal measurement may be referred to as a first type of measurement.

[0134] Figure 9 An example of a normal measurement process according to an embodiment of the present disclosure is shown.

[0135] Reference Figure 9 In step S901, the UE may receive a measurement configuration from the network. The measurement configuration may include a measurement object list (measObject), a report configuration list (reportConfig), and a measurement identifier ID list (measID). The measurement ID may be associated with / correspond to a combination of a measurement object and a report configuration. The measurement object may indicate information about the object that the UE should measure. For example, the object information may include a measurement frequency and / or a cell list including a serving cell / neighboring cell. The report configuration may include a condition for performing an action corresponding to a report type in the report configuration. For example, the condition may include a reporting condition that the UE should meet to send a measurement report.

[0136] In step S903, the UE may perform measurements based on the measurement configuration. For example, the UE may measure the reference signals received from the serving cell and / or the neighboring cell at the measurement frequency specified by the measurement object to obtain measurement results of the serving cell and / or the neighboring cell. The measurement results may include cell quality / signal strength / signal quality / channel quality / channel state / reference signal received power (RSRP) / reference signal received quality (RSRQ) of the serving cell and / or the neighboring cell. The UE may perform actual measurements on the reference signals and derive measurement results based on the actual measurements (the measurement results of the reference signals may be post-processed, for example, by filtering based on linear averaging or exponential moving average, etc.).

[0137] In step S905, the UE may send a measurement report to the network. The UE may send a measurement report including measurement results of the serving cell and / or neighbor cells to the network based on the reporting configuration (eg, when the reporting condition is met).

[0138] In addition, the UE may perform ML-based / assisted measurements, where ML-based / assisted measurements are measurement processes that derive measurement results with the aid of ML (based on certain measurements of known reference signals). ML-based / assisted measurements may be associated with the size of compressed measurement results, thereby reducing reporting overhead. For example, machine learning based on autoencoders / DNNs / CNNs may be used to implement compressed CSI reporting by generating compressed CSI information on the UE side and reconstructing the desired CSI information on the network side (i.e., a two-sided ML algorithm may be used). ML-based / assisted measurements may be associated with predicting measurement results at future times. Measurement prediction may be based on a machine learning model that uses current and / or past measurement results and other local / environmental / useful information available on the UE side, and provides available measurement results and possible available information as input. In the present disclosure, this type of ML-based / assisted measurement may be referred to as a second type of measurement.

[0139] Figure 10An example of an ML-based / assisted measurement process according to an embodiment of the present disclosure is shown.

[0140] Reference Figure 10 In step S1001, the UE may receive a measurement configuration from the network. The measurement configuration may include: Figure 9 The information elements described in step 901.

[0141] In step S1003, the UE may receive an ML model configuration from the network. In order to derive an ML-assisted result, the UE may be provided with the ML model configuration. The ML model configuration may include prediction model structure information.

[0142] In some implementations, the order of steps S1001 and S1003 may be changed, or steps S1001 and S1003 may be performed simultaneously. For example, the measurement configuration may include an ML model configuration.

[0143] In some implementations, the ML model information can include the machine learning type, such as reinforcement learning, supervised learning, or unsupervised learning.

[0144] In some implementations, the network may configure the machine learning model to be used by the UE. The ML model information may include machine learning models such as deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and deep reinforcement learning (DRL).

[0145] For example, the configured ML model can be a pre-trained ML model that the network has been pre-trained. The configured ML model can be described by model description information including model structure and parameters. For example, a model based on a neural network may include an input layer, an output layer, and a hidden layer, wherein each layer includes one or more neurons (equivalent to nodes). Different layers are connected based on the connections between neurons in different layers. Each connection between two different neurons in two different layers can be directed (for example, neuron A to neuron B, meaning that the output of neuron A is fed into neuron B). Each neuron can provide input to one or several connected neurons (1 to N connections). For the connection between two neurons (neuron A to neuron B), the output of one neuron A is scaled by a weight, and the other neuron uses the scaled output as its input. Each neuron can get input from one or several connected neurons (N to 1 connection), combine the inputs from the connected neurons, and generate output based on the activation function.

[0146] For example, a configured ML model can be an ML model to be trained. The configured ML model is described by model description information including the model structure and initial parameters to be trained. When the network configures the ML model to be trained, it can also configure training parameters such as optimization targets and optimization-related configuration parameters.

[0147] In some implementations, the ML model configuration may include machine learning input parameters of the machine learning model, such as UE location information, radio measurements related to the serving cell and neighbor cells, and UE mobility history.

[0148] In some implementations, the ML model configuration may include learning outputs such as UE trajectory prediction, predicted target cell, predicted time of handover, and UE traffic prediction.

[0149] In step S1005, the UE may perform training, validation, and testing of the machine learning model, which may generate model performance metrics based on the prediction model configuration / ML model configuration. The UE may perform model training using machine learning input parameters. In some implementations, step S1005 may be performed when the UE is configured with an ML model to be trained. That is, when the UE is configured with a pre-trained ML model that has been pre-trained by the network, step S1005 may be skipped.

[0150] In step S1007, the UE may perform an ML task, such as making measurement predictions based on the configured / trained ML model. The UE may derive machine learning outputs, which may be measurement results. In some implementations, the UE may infer measurement results from the outputs and use these outputs as feedback for the machine learning model.

[0151] In step S1009 , the UE may send a measurement report including measurement results derived based on the configured / trained ML model to the network.

[0152] If ML is used for information compression / reconstruction, using ML-based / assisted measurement reporting can help reduce reporting overhead. If ML is used to estimate or predict measurement results that exceed current / past available measurements in time and / or frequency, ML-based / assisted measurement reporting can assist the network in optimizing data scheduling and mobility of the relevant UE. However, there may be a risk of low accuracy in ML-based / assisted measurements. Low accuracy in ML-based / assisted measurements may be caused by several factors, which may include invalid model selection, insufficient or incomplete model training, invalid auxiliary information used as input to the ML algorithm, etc. If the network uses inaccurate ML-based / assisted measurements, it will lead to waste of radio resources, degradation of data communication quality, degradation of mobility performance, etc. Therefore, it is very important to ensure that the network can verify whether the reported ML-based / assisted measurements are sufficiently valid or accurate.

[0153] Different ML models produce different outputs. Different models require different computational complexity and power consumption. Different models produce different accuracy. Currently, measurement tasks are based on a single model. If the UE supports multiple models and performs concurrent measurements and / or concurrent measurement result derivation for multiple models, the network can select / reselect models to enhance performance and / or reduce UE power consumption.

[0154] In the present disclosure, a UE may be configured with a list of models for measurement. The model may generate measurement results by providing input to the model and performing mathematical operations to generate output. The model may be a trained model, so it is ready to generate output that can be considered valid based on valid input. For each model in the configured models, the UE may perform measurements using the model (model-specific measurements) and derive measurement results (model-specific measurement results). The UE may combine / aggregate the model-specific measurement results of the configured models. The UE may report the combined measurement results to the network.

[0155] The measurement may be related to the quality assessment of an RS, a specific RS, or a specific RS set used for CSI measurement or positioning measurement. The measurement may be related to the quality assessment of a cell, a specific cell, a specific cell set, or a specific frequency used for RRM measurement. The measurement may be related to measurement prediction in the time domain or frequency domain.

[0156] Figure 11 An example of a method performed by a UE according to an embodiment of the present disclosure is shown. The method may also be performed by a wireless device.

[0157] Reference Figure 11 In step S1101, the UE may receive configuration for measurement reporting related to multiple machine learning (ML) models from the network.

[0158] In step S1103 , the UE may determine a set of ML models for measurement reporting from a plurality of ML models configured for the UE based on the configuration.

[0159] In step S1105 , the UE may obtain measurement results by providing input to the set of ML models.

[0160] In step S1107 , the UE may send at least one of the measurement results to the network.

[0161] According to various embodiments, the measurement result may include a measurement result obtained by providing an input to a corresponding ML model in a set of ML models. The input may include at least one of the following: one or more ML input parameters received from a network; one or more reference signals; measurement values ​​of one or more reference signals; or past measurement results. The measurement result may include at least one of the following: an output of the corresponding ML model for the input; a compressed measurement result; a predicted measurement result derived from measurement results including past measurement results; a predicted measurement result of a reference signal derived from measurement results of other reference signals; or beam indices of one or more beams in descending order of beam quality from a beam with the highest beam quality. The one or more ML input parameters may include at least one of the following: location information of the UE, a measurement result for at least one reference signal configured for the UE, a measurement result for at least one of a serving cell or one or more neighboring cells, or mobility history information of the UE.

[0162] According to various embodiments, the plurality of ML models may include at least one of a deep neural network (DNN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or a deep reinforcement learning (DRL) model.

[0163] According to various embodiments, the UE may apply an ML algorithm corresponding to the ML model to the input of the ML model to obtain a measurement result as an output of the ML model.

[0164] According to various embodiments, the configuration may include at least one of: a list of a plurality of ML models; ML model information informing a group of ML models; or a condition for determining a group of ML models.

[0165] According to various embodiments, the UE may send capability information of the UE to the network, where the capability information notifies the supported ML models for measurement reporting. After sending the capability information, the UE may receive an ML model configuration including multiple ML models from the network. The multiple ML models may be determined from the supported ML models.

[0166] According to various embodiments, the UE may obtain model-specific measurement results by providing input to multiple ML models. The UE may send a measurement report including the model-specific measurement results to the network. The UE may receive a configuration from the network after sending the measurement report.

[0167] According to various implementations, a set of ML models may be determined based on model-specific measurements.

[0168] According to various embodiments, the input may include a common input provided to at least two ML models in a set of ML models.

[0169] According to various embodiments, the inputs may include model-specific inputs, each of which is provided to a corresponding ML model in a set of ML models.

[0170] According to various embodiments, the UE may send model preference information to the network, wherein the model preference information notifies the UE of one or more preferred ML models. At least one of the plurality of ML models or a group of ML models may be determined based on the preference information.

[0171] According to various embodiments, the one or more ML models may be determined based on at least one of power consumption, accuracy, effectiveness, user preference, or priority of each ML model.

[0172] According to various embodiments, the model preference information may be sent via at least one of a measurement report or UE assistance information.

[0173] According to various embodiments, a UE may receive a list of models for measurement, perform measurements based on each of the received models, and transmit measurement results including measurement results derived from more than one received model.

[0174] Figure 12 An example of a method performed by a network node according to an embodiment of the present disclosure is shown.The network node may include a base station (BS).

[0175] Reference Figure 12 In step S1201, the network node may send a configuration of measurement reports related to multiple machine learning (ML) models to the UE.

[0176] In step S1203, the network node may send ML model information to the UE, where the ML model information notifies a set of ML models for measurement reporting. The set of ML models may be determined from a plurality of ML models configured for the UE based on configuration.

[0177] Figure 13 An example of a process for combined reporting and subsequent model down-selection between a UE and a network according to an embodiment of the present disclosure is shown. The combined reporting may be performed by the UE, and the model down-selection may be triggered by the network.

[0178] Reference Figure 13 In step S1301, the UE may notify the network of the capabilities of the model supported by the UE for measurement. The UE may send capability information of the model supported by the UE for measurement to the network.

[0179] In step S1303, the network may configure a model list for combined reporting for the UE. The network may send an ML model configuration including the model list for combined reporting to the UE.

[0180] In step S1305, the UE may perform measurements using the model list. The UE may derive model-specific measurement results for each model used in the configured models. The UE may combine / aggregate the model-specific measurement results for the configured models.

[0181] In step S1307, the UE may report the combined measurement result to the network. The UE may send a measurement report message including the combined measurement result to the network.

[0182] The network may receive the combined measurement results.Then, the network may select a set of models to be used by the UE for subsequent measurement and reporting from the model list configured for the UE in step S1303.

[0183] In step S1309, the network may configure the UE with the selected set of models for subsequent measurement and reporting. The network may send ML model information to the UE, where the ML model information notifies the selected set of models for subsequent measurement and reporting.

[0184] The UE may determine a set of models based on the ML model information. The UE may perform measurements using the set of models. The UE may send a measurement report including the derived measurement results to the network. If more than one model is configured in the set of models, the UE may send a measurement report including a combined report, where the combined report includes multiple measurement result sets, each measurement result set derived according to a different model in the set of models. Otherwise (i.e., one model is configured in the set of models), the UE may send a measurement report including a single measurement result set derived according to the configured model.

[0185] Step S1305 will refer to Figure 14 Detailed description.

[0186] Figure 14 An example of concurrent measurement of model-specific outputs / measurements derived for multiple models according to an embodiment of the present disclosure is shown.

[0187] exist Figure 14 In

[15] , the UE may be configured with Model 1, Model 2, ..., Model N for measurement. Each model may obtain its input.

[0188] In some implementations, there may be a common input that is used as an input to the models of multiple or all configurations. For example, a set of known RSs or measurements of the set of known RSs may be used as the common input.

[0189] In some implementations, there may be model-specific inputs for a specific model. For example, a specific set of RSs or measurement results of these RSs may be used as input for a specific model, while another specific set of RSs may be used as input for another specific model. For example, a specific set of measurement results may be used as input for a specific model, while another specific set of measurement results may be used as input for another specific model.

[0190] like Figure 13 As shown in steps S1303 and S1309 in FIG, the UE may be configured with a model list (in step S1303) and / or a set of models among the configured models (in step S1309) for concurrent measurement and combined reporting based on multiple models. Depending on the capabilities of the UE, the UE may perform concurrent measurements and report measurement results of all configured models, such as Figure 15A As shown; or the UE can perform concurrent measurements and report the measurement results of a subset of the configuration models, such as Figure 15B shown.

[0191] Figure 15A An example of combined reporting of measurements derived according to various measurement models according to an embodiment of the present disclosure is shown.

[0192] refer to Figure 15A , the UE may receive a configuration for a combined report for model 1 to model N from the network at time / period t1. Then, the UE may send a measurement report including outputs 1 to N to the network at time / period t2, where output k (1≤k≤N, k is an integer) is derived according to model k.

[0193] Figure 15B An example of a combined report of measurement results derived according to various measurement models with output selections according to an embodiment of the present disclosure is shown.

[0194] Reference Figure 15B , the UE may receive configuration for combined reporting for Models 1 to N from the network at time / period t1. The UE may receive ML model information notifying a set of models from Models 1 to N configured for the UE at time / period t1. The UE may then send a measurement report including a subset of available outputs from Outputs 1 to N to the network at time / period t2, where:

[0195] - output k (1≤k≤N, k is an integer) is derived from model k; and

[0196] -The subset of available outputs is derived from a set of models informed by the ML model information.

[0197] The UE may indicate to the network one or more preferred configuration models. The UE may evaluate the power consumption and accuracy of each model to determine its preference. The UE may indicate its preference within a combined report. The UE may indicate its preference in a separate message (e.g., in a UE Assistance Information message, which is an RRC message).

[0198] In addition, the method described in this disclosure from the perspective of the UE (for example, Figure 11 (in Chinese) can be Figure 2 The first wireless device 100 and / or Figure 3 The UE 100 shown in FIG.

[0199] More specifically, the UE includes at least one transceiver, at least one processor, and at least one computer memory operatively connected to the at least one processor and storing instructions for performing operations upon execution by the at least one processor.

[0200] The operations include: receiving, from a network, a configuration for measurement reporting related to a plurality of machine learning (ML) models; determining, based on the configuration, a set of ML models for measurement reporting from the plurality of ML models configured for the UE; obtaining measurement results by providing input to the set of ML models; and sending at least one of the measurement results to the network.

[0201] In addition, the method described in this disclosure from the perspective of the UE (for example, Figure 11 in) can be stored in Figure 2 The software code 105 in the memory 104 included in the first wireless device 100 shown in FIG. 1 is executed.

[0202] More specifically, at least one computer-readable medium (CRM) stores instructions that, upon being executed by at least one processor, perform operations including: receiving a configuration for measurement reporting related to a plurality of machine learning (ML) models from a network; determining, based on the configuration, a set of ML models for measurement reporting from a plurality of ML models configured for a UE; obtaining measurement results by providing input to the set of ML models; and sending at least one of the measurement results to the network.

[0203] In addition, the method described in this disclosure from the perspective of the UE (for example, Figure 11 (in Chinese) can be Figure 2 The control and / or Figure 3 The control execution is performed by the processor 102 included in the UE 100 shown in FIG.

[0204] More specifically, an apparatus (e.g., a wireless device / UE) adapted to operate in a wireless communication system includes: at least one processor and at least one computer memory operably connected to the at least one processor. The at least one processor is configured / adapted to perform operations including: receiving a configuration for measurement reporting related to multiple machine learning (ML) models from a network; determining, based on the configuration, a set of ML models for measurement reporting from the multiple ML models configured for the UE; obtaining measurement results by providing input to the set of ML models; and transmitting at least one of the measurement results to the network.

[0205] Furthermore, the method described in this disclosure from a network node associated with a first cell (e.g., Figure 12 (in Chinese) can be Figure 2 The second wireless device 200 shown in FIG.

[0206] More specifically, the network node includes at least one transceiver, at least one processor, and at least one computer memory operatively connected to the at least one processor and storing instructions that perform operations upon execution by the at least one processor.

[0207] The operations include: transmitting a machine learning (ML) model configuration including a plurality of ML models to a user equipment (UE); and receiving, from the UE, at least one of measurement results obtained by providing input to a set of ML models for measurement reporting, wherein the set of ML models is determined based on the configuration among the plurality of ML models configured for the UE.

[0208] The present disclosure may have various beneficial effects.

[0209] For example, the UE may be configured to operate in an optimal mode, resulting in better performance and / or lower power consumption.

[0210] The beneficial effects that can be obtained through the specific embodiments of the present disclosure are not limited to the beneficial effects listed above. For example, there may be various technical effects that can be understood and / or derived from the present disclosure by a person of ordinary skill in the relevant art. Therefore, the specific effects of the present disclosure are not limited to those explicitly described herein, but may include various effects that can be understood or derived from the technical features of the present disclosure.

[0211] The claims in this disclosure may be combined in various ways. For example, the technical features in the method claims of this disclosure may be combined to be implemented or performed in a device, and the technical features in the device claims may be combined to be implemented or performed in a method. Furthermore, the technical features in the method claims and the device claims may be combined to be implemented or performed in a device. Furthermore, the technical features in the method claims and the device claims may be combined to be implemented or performed in a method. Other implementations are within the scope of the appended claims.

Claims

1. A method performed by a user equipment (UE) configured to operate in a wireless communication system, the method comprising: receiving, from a network, a configuration for measurement reporting associated with a plurality of machine learning (ML) models; Based on the configuration, determining a set of ML models for measurement reporting from the plurality of ML models configured for the UE; obtaining measurements by providing inputs to the set of ML models; as well as At least one of the measurements is sent to the network.

2. The method according to claim 1, wherein: The measurements include measurements obtained by providing input to a corresponding ML model in the set of ML models, The input includes at least one of the following items: one or more ML input parameters received from the network; one or more reference signals; measurements of the one or more reference signals; or Past measurement results, The measurement result includes at least one of the following items: the output of the corresponding ML model for the input; Compression measurements; predicted measurement results derived from measurement results including said past measurement results; Predicted measurements of a reference signal derived from measurements of other reference signals; or beam indices of one or more beams in descending order of beam quality from the beam with the highest beam quality, and The one or more ML input parameters include at least one of the following items: location information of the UE, measurement results of at least one reference signal configured for the UE, measurement results of at least one of the serving cell or one or more neighboring cells, or mobility history information of the UE.

3. The method according to claim 1, wherein: The multiple ML models include at least one of the following: a deep neural network DNN model, a convolutional neural network CNN model, a recurrent neural network RNN ​​model, or a deep reinforcement learning DRL model.

4. The method according to claim 1, wherein: The step of obtaining the measurement result includes: applying an ML algorithm corresponding to an ML model to an input of the ML model to obtain the measurement result as an output of the ML model.

5. The method according to claim 1, wherein: The configuration includes at least one of the following: a list of the plurality of ML models; Notify ML model information of the set of ML models; or A condition for determining the set of ML models.

6. The method according to claim 1, further comprising: sending capability information of the UE to the network, the capability information notifying supported ML models for measurement reporting; as well as After sending the capability information, receiving an ML model configuration including the plurality of ML models from the network, The multiple ML models are determined among the supported ML models.

7. The method according to claim 1, further comprising: obtaining model-specific measurements by providing inputs to the plurality of ML models; as well as sending a measurement report including the model-specific measurement results to the network, The step of receiving the configuration includes: after sending the measurement report, receiving the configuration from the network.

8. The method according to claim 7, wherein: The set of ML models is determined based on the model-specific measurements.

9. The method according to claim 1, wherein: The input comprises a common input provided to at least two ML models in the set of ML models.

10. The method according to claim 1, wherein: The inputs include model-specific inputs, each of the model-specific inputs being provided to a corresponding ML model in the set of ML models.

11. The method according to claim 1, further comprising: sending model preference information to the network, wherein the model preference information notifies the UE of one or more ML models preferred by the UE, Wherein, at least one of the plurality of ML models or the group of ML models is determined based on the preference information.

12. The method according to claim 11, wherein: The one or more ML models are determined based on at least one of power consumption, accuracy, effectiveness, user preference, or priority of each ML model.

13. The method according to claim 11, wherein: The model preference information is sent via at least one of a measurement report or UE assistance information.

14. The method according to claims 1 to 13, wherein: The UE communicates with at least one of a mobile device, a network, or an autonomous vehicle.

15. A user equipment (UE) configured to operate in a wireless communication system, the UE comprising: at least one transceiver; at least one processor; as well as at least one memory operatively coupled to the at least one processor and storing instructions, the instructions performing operations upon being executed by the at least one processor, the operations comprising: receiving, from a network, a configuration for measurement reporting associated with a plurality of machine learning (ML) models; Based on the configuration, determining a set of ML models for measurement reporting from the plurality of ML models configured for the UE; obtaining measurements by providing input to the set of ML models; and At least one of the measurements is sent to the network.

16. The UE according to claim 15, wherein: The UE is arranged to implement the method according to one of claims 2 to 14.

17. A network node configured to operate in a wireless communication system, the network node comprising: at least one transceiver; at least one processor; as well as at least one memory operatively coupled to the at least one processor and storing instructions, the instructions performing operations upon being executed by the at least one processor, the operations comprising: Sending a configuration for measurement reporting related to a plurality of machine learning (ML) models to a user equipment (UE); and receiving, from the UE, at least one of measurement results obtained by providing input to a set of ML models for measurement reporting, The group of ML models is determined among the multiple ML models configured for the UE based on the configuration.

18. A method performed by a network node configured to operate in a wireless communication system, the method comprising: Sending a configuration for measurement reports related to a plurality of machine learning ML models to a user equipment UE; as well as receiving, from the UE, at least one of measurement results obtained by providing input to a set of ML models for measurement reporting, The group of ML models is determined among the multiple ML models configured for the UE based on the configuration.

19. The method according to claim 18, wherein: The UE is arranged to implement the method according to one of claims 1 to 14.

20. A device adapted to operate in a wireless communication system, the device comprising: at least one processor; as well as at least one memory operatively coupled to the at least one processor and storing instructions, the instructions performing operations upon being executed by the at least one processor, the operations comprising: receiving, from a network, a configuration for measurement reporting associated with a plurality of machine learning (ML) models; Based on the configuration, determining a set of ML models for measurement reporting from the plurality of ML models configured for the UE; obtaining measurements by providing input to the set of ML models; and At least one of the measurements is sent to the network.

21. A non-transitory computer readable medium (CRM) having program code stored thereon, the program code implementing instructions, the instructions performing operations upon being executed by at least one processor, the operations comprising: receiving, from a network, a configuration for measurement reporting associated with a plurality of machine learning (ML) models; Based on the configuration, determining a set of ML models for measurement reporting from the plurality of ML models configured for the UE; obtaining measurements by providing inputs to the set of ML models; as well as At least one of the measurements is sent to the network.

Images