WO2025178330A1 - Ai/ml method - Google Patents

Abstract

An embodiment of the present disclosure provides a method by which a UE communicates. The method comprises the steps in which: a UE selects a specific beam of a base station for downlink reception by performing AI beam management via an AI model; the UE measures the quality of a channel by means of the specific beam; the UE determines whether the result of the measurement is less than or equal to a quality threshold value; the UE performs legacy beam management on the basis of the measurement result being less than or equal to the quality threshold value; and the UE evaluates the performance of the AI beam management on the basis of the result of the legacy beam management.

Description

AI/ML methods

This specification relates to mobile communications.

3GPP (3rd Generation Partnership Project) LTE (Long-Term Evolution) is a technology designed to enable high-speed packet communications. Numerous approaches have been proposed to achieve LTE's goals of reducing costs for users and operators, improving service quality, expanding coverage, and increasing system capacity. 3GPP LTE's high-level requirements include reduced cost per bit, improved service availability, flexible use of frequency bands, a simple architecture, open interfaces, and adequate power consumption for terminals.

The International Telecommunication Union (ITU) and 3GPP have begun work on developing requirements and specifications for new radio (NR) systems. 3GPP must identify and develop the technical components necessary to successfully standardize NR in a timely manner, meeting both urgent market needs and the longer-term requirements outlined by the ITU-R (ITU radio communication sector) International Mobile Telecommunications (IMT)-2020 process. NR must also be able to utilize any spectrum band up to at least 100 GHz, ensuring that it remains available for wireless communications well into the future.

NR aims to be a single technology framework that addresses all deployment scenarios, usage scenarios, and requirements, including enhanced mobile broadband (eMBB), massive machine type communications (mMTC), and ultra-reliable and low latency communications (URLLC). NR must be inherently forward-compatible.

There is a need for a method to improve the performance of AI/ML models.

Evaluate the performance of AI/ML models.

Figure 1 illustrates an example of a communication system to which the implementation of this specification is applied.

Figure 2 illustrates an example of a wireless device to which the implementation of the present specification is applied.

Figure 3 shows an example of a UE to which the implementation of this specification is applied.

Figure 4 is a diagram showing an example of a communication structure that can be provided in a 6G system.

Figure 5 shows an example of an electromagnetic spectrum.

Figure 6 illustrates an example of subframe types in NR.

Figure 7 is an example diagram showing an example of SSB in NR.

Figure 8 is an exemplary diagram showing an example of beam sweeping in NR.

Figure 9 shows an example of an AI/ML model.

Figure 10 shows an example of a network managing an AI/ML model.

Fig. 11 shows an example of a blur measurement method 1 according to an embodiment of the present specification.

Fig. 12 shows an example of a blur measurement method 2 according to an embodiment of the present specification.

FIG. 13 illustrates an example of a beam management related procedure based on channel quality according to the disclosure of the present specification.

FIG. 14 illustrates an example of a beam management related procedure based on terminal location according to the disclosure of this specification.

FIG. 15 illustrates an example of a positioning accuracy evaluation procedure according to the disclosure of the present specification.

Figure 16 illustrates the UE's procedure for disclosure of this specification.

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 multicarrier frequency division multiple access (MC-FDMA) systems. CDMA can be implemented via wireless technologies such as universal terrestrial radio access (UTRA) or CDMA2000. TDMA can be implemented via wireless 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 wireless technologies such as IEEE (Institute of Electrical and Electronics Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or evolved UTRA (E-UTRA). UTRA is part of the universal mobile telecommunications system (UMTS). 3rd generation partnership project (3GPP) long-term evolution (LTE) is a 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-A (advanced), LTE-A Pro, and/or 5G NR (new radio).

For convenience of explanation, the implementation of this specification is primarily described in relation to a 3GPP-based wireless communication system. However, the technical features of this specification are not limited thereto. For example, the following detailed description is provided based on a mobile communication system corresponding to a 3GPP-based wireless communication system. However, aspects of this specification that are not limited to a 3GPP-based wireless communication system can be applied to other mobile communication systems.

For terms and technologies used in this specification that are not specifically described, reference may be made to wireless communication standard documents published prior to this specification.

As used herein, "A or B" can mean "only A," "only B," or "both A and B." Alternatively, as used herein, "A or B" can be interpreted as "A and/or B." For example, as used herein, "A, B or C" can mean "only A," "only B," "only C," or "any combination of A, B and C."

As used herein, a slash (/) or a comma can mean "and/or." For example, "A/B" can mean "A and/or B." Accordingly, "A/B" can mean "only A," "only B," or "both A and B." For example, "A, B, C" can mean "A, B, or C."

In this specification, “at least one of A and B” may mean “only A,” “only B,” or “both A and B.” Additionally, in this specification, the expressions “at least one of A or B” or “at least one of A and/or B” may be interpreted identically to “at least one of A and B.”

Additionally, in this specification, “at least one of A, B and C” can mean “only A”, “only B”, “only C”, or “any combination of A, B and C”. Additionally, “at least one of A, B or C” or “at least one of A, B and/or C” can mean “at least one of A, B and C”.

Additionally, parentheses used herein may mean "for example." Specifically, when indicated as "control information (PDCCH)", "PDCCH" may be proposed as an example of "control information." In other words, "control information" in this specification is not limited to "PDCCH," and "PDCCH" may be proposed as an example of "control information." Furthermore, even when indicated as "control information (i.e., PDCCH)", "PDCCH" may be proposed as an example of "control information."

Technical features individually described in a single drawing in this specification may be implemented individually or simultaneously.

Although not limited thereto, the various descriptions, functions, procedures, proposals, methods and/or operational flowcharts disclosed herein may be applied to various fields requiring wireless communication and/or connectivity between devices (e.g., 5G).

Hereinafter, the present specification will be described in more detail with reference to the drawings. In the following drawings and/or description, the same reference numbers may refer to the same or corresponding hardware blocks, software blocks, and/or functional blocks, unless otherwise indicated.

Figure 1 illustrates an example of a communication system to which the implementation of this specification is applied.

The 5G usage scenario shown in FIG. 1 is only an example, and the technical features of this specification can be applied to other 5G usage scenarios not shown in FIG. 1.

The three main requirement categories for 5G are (1) enhanced mobile broadband (eMBB), (2) massive machine type communication (mMTC), and (3) ultra-reliable and low latency communications (URLLC).

Referring to FIG. 1, a communication system (1) includes wireless devices (100a to 100f), a base station (BS; 200), and a network (300). FIG. 1 illustrates a 5G network as an example of a network of the communication system (1), but the implementation of the present disclosure is not limited to a 5G system and can be applied to future communication systems beyond the 5G system.

The base station (200) and the network (300) may be implemented as wireless devices, and a particular wireless device may operate as a base station/network node in relation to other wireless devices.

Wireless devices (100a to 100f) refer to devices that perform communication using radio access technology (RAT) (e.g., 5G NR or LTE) and may also be referred to as communication/wireless/5G devices. Wireless devices (100a to 100f) may include, but are not limited to, robots (100a), vehicles (100b-1 and 100b-2), extended reality (XR) devices (100c), portable devices (100d), home appliances (100e), IoT devices (100f), and artificial intelligence (AI) devices/servers (400). For example, vehicles may include vehicles having wireless communication capabilities, autonomous vehicles, and vehicles capable of performing vehicle-to-vehicle communication. Vehicles may include unmanned aerial vehicles (UAVs) (e.g., drones). XR devices may include AR/VR/mixed reality (MR) devices, and may be implemented in the form of head-mounted devices (HMDs) and heads-up displays (HUDs) mounted on vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signs, vehicles, robots, etc. Portable devices may include smartphones, smart pads, wearable devices (e.g., smart watches or smart glasses), and computers (e.g., laptops). Home appliances may include TVs, refrigerators, and washing machines. IoT devices may include sensors and smart meters.

In this specification, wireless devices (100a to 100f) may be referred to as user equipment (UE). The UE may include, for example, a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a slate PC, a tablet PC, an ultrabook, a vehicle, a vehicle with autonomous driving functions, a connected car, a UAV, an AI module, a robot, an AR device, a VR device, an MR device, a holographic device, a public safety device, an MTC device, an IoT device, a medical device, a fintech device (or a financial device), a security device, a weather/environmental device, a 5G service-related device, or a 4th industrial revolution-related device.

For example, a UAV may be an aircraft that is unmanned and navigated by radio control signals.

For example, a VR device may include a device for implementing objects or backgrounds in a virtual environment. For example, an AR device may include a device that implements objects or backgrounds in a virtual world by connecting them to objects or backgrounds in the real world. For example, an MR device may include a device that implements objects or backgrounds in a virtual world by merging them with objects or backgrounds in the real world. For example, a holographic device may include a device that implements 360-degree stereoscopic images by recording and reproducing three-dimensional information using the light interference phenomenon that occurs when two laser lights, called holograms, meet.

For example, a public safety device may include an image relay device or imaging device that can be worn on the user's body.

For example, MTC devices and IoT devices may be devices that do not require direct human intervention or manipulation. Examples include smart meters, vending machines, thermometers, smart light bulbs, door locks, or various sensors.

For example, a medical device may be a device used for the purpose of diagnosing, treating, alleviating, curing, or preventing a disease. For example, a medical device may be a device used for diagnosing, treating, alleviating, or correcting an injury or damage. For example, a medical device may be a device used for the purpose of examining, replacing, or modifying a structure or function. For example, a medical device may be a device used for the purpose of regulating pregnancy. For example, a medical device may include a therapeutic device, a driving device, an (in vitro) diagnostic device, a hearing aid, or a surgical device.

For example, a security device may be a device installed to prevent potential hazards and maintain safety. For example, a security device may be a camera, closed-circuit television (CCTV), a recorder, or a black box.

For example, a fintech device may be a device capable of providing financial services, such as mobile payments. For example, a fintech device may include a payment device or a point-of-sale system.

For example, a weather/environment device may include a device that monitors or predicts the weather/environment.

Wireless devices (100a to 100f) can be connected to a network (300) via a base station (200). AI technology can be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) via the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, and a network after 5G. The wireless devices (100a to 100f) can communicate with each other via the base station (200)/network (300), but can also communicate directly (e.g., sidelink communication) without going through the base station (200)/network (300). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., vehicle-to-vehicle (V2V)/vehicle-to-everything (V2X) communication). Additionally, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

Wireless communication/connection (150a, 150b, 150c) can be established between wireless devices (100a to 100f) and/or between wireless devices (100a to 100f) and a base station (200) and/or between base stations (200). Here, the wireless communication/connection can be established through various RATs (e.g., 5G NR), such as uplink/downlink communication (150a), sidelink communication (150b) (or, device-to-device (D2D) communication), and base station-to-base station communication (150c) (e.g., relay, integrated access and backhaul (IAB)). Through the wireless communication/connection (150a, 150b, 150c), the wireless devices (100a to 100f) and the base station (200) can transmit/receive wireless signals to/from each other. For example, wireless communication/connection (150a, 150b, 150c) can transmit/receive signals through various physical channels. To this end, at least some of the various configuration information setting processes for transmitting/receiving wireless signals, various signal processing processes (e.g., channel encoding/decoding, modulation/demodulation, resource mapping/demapping, etc.), and resource allocation processes can be performed based on various proposals of the present specification.

AI is the study of artificial intelligence or the methodologies for creating it, while machine learning (ML) defines various problems in the field of AI and studies the methodologies for solving them. Machine learning is also defined as an algorithm that improves performance on a task through consistent experience.

A robot can be defined as a machine that automatically processes or operates a given task based on its own capabilities. Specifically, a robot capable of perceiving its environment, making decisions, and performing actions on its own can be called an intelligent robot. Robots can be categorized into industrial, medical, household, and military applications based on their intended use or field. Robots are equipped with a drive unit, including an actuator or motor, enabling them to perform various physical actions, such as moving robot joints. Furthermore, mobile robots include wheels, brakes, and propellers in their drive unit, enabling them to drive on the ground or fly in the air.

Autonomous driving refers to the technology of driving on one's own, while autonomous vehicles refer to vehicles that drive without, or with minimal, user intervention. For example, autonomous driving can include technologies such as lane keeping, automatic speed control like adaptive cruise control, autonomous driving along a set route, and autonomous driving based on a set destination. Vehicles encompass all types of vehicles: those with internal combustion engines, hybrid vehicles with both internal combustion engines and electric motors, and electric vehicles with only electric motors. These vehicles can include not only cars but also trains and motorcycles. Autonomous vehicles can be viewed as robots with autonomous driving capabilities.

Extended reality is a general term for VR, AR, and MR. VR technology provides real-world objects and backgrounds as CG images only, AR technology provides virtual CG images over images of real objects, and MR technology is a CG technology that mixes and combines virtual objects with the real world. MR technology is similar to AR in that it displays real and virtual objects together. However, there is a difference: while AR uses virtual objects to complement real objects, MR uses virtual and real objects equally.

NR supports multiple numerologies, or subcarrier spacing (SCS), to support diverse 5G services. For example, an SCS of 15 kHz supports wide areas in traditional cellular bands; an SCS of 30 kHz/60 kHz supports dense urban areas, lower latency, and wider carrier bandwidth; and an SCS of 60 kHz or higher supports bandwidths greater than 24.25 GHz to overcome phase noise.

The NR frequency band can be defined by two types of frequency ranges (FR1 and FR2). The numerical values of the frequency ranges can be changed. For example, the two types of frequency ranges (FR1 and FR2) can be as shown in Table 1 below. For convenience of explanation, among the frequency ranges used in NR systems, FR1 can mean the "sub-6GHz range," and FR2 can mean the "above 6GHz range," which can be referred to as millimeter wave (mmW).

Frequency range definition Frequency range Subcarrier spacing FR1 450MHz - 6000MHz 15, 30, 60kHz FR2 24250MHz - 52600MHz 60, 120, 240kHz

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

Frequency range definition Frequency range Subcarrier spacing FR1 410MHz - 7125MHz 15, 30, 60kHz FR2 24250MHz - 52600MHz 60, 120, 240kHz

Here, the wireless communication technology implemented in the wireless device of the present specification may include not only LTE, NR, and 6G, but also narrowband IoT (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of LPWAN (low power wide area network) technology and may be implemented with standards such as LTE Cat NB1 and/or LTE Cat NB2, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless device of the present specification may perform communication based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology and may be called by various names such as eMTC (enhanced MTC). For example, LTE-M technology can be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-bandwidth limited), 5) LTE-MTC, 6) LTE MTC, and/or 7) LTE M, and is not limited to the above-described names. Additionally or alternatively, the wireless communication technology implemented in the wireless device of the present specification can include at least one of ZigBee, Bluetooth, and/or LPWAN considering low-power communication, and is not limited to the above-described names. For example, ZigBee technology can create PAN (personal area networks) related to small/low-power digital communication based on various standards such as IEEE 802.15.4, and can be called by various names.

Figure 2 illustrates an example of a wireless device to which the implementation of the present specification is applied.

In FIG. 2, the first wireless device (100) and/or the second wireless device (200) may be implemented in various forms depending on the use case/service. For example, {the first wireless device (100) and the second wireless device (200)} may correspond to at least one of {the wireless devices (100a to 100f) and the base station (200)}, {the wireless devices (100a to 100f) and the wireless devices (100a to 100f)}, and/or {the base station (200) and the base station (200)} of FIG. 1. The first wireless device (100) and/or the second wireless device (200) may be configured by various components, devices/parts, and/or modules.

The first wireless device (100) may include at least one transceiver, such as a transceiver (106), at least one processing chip, such as a processing chip (101), and/or one or more antennas (108).

The processing chip (101) may include at least one processor, such as a processor (102), and at least one memory, such as a memory (104). Additionally and/or alternatively, the memory (104) may be located external to the processing chip (101).

The processor (102) may control the memory (104) and/or the transceiver (106) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and/or operational flowcharts disclosed herein. For example, the processor (102) may process information in the memory (104) to generate first information/signal and transmit a wireless signal including the first information/signal via the transceiver (106). The processor (102) may receive a wireless signal including second information/signal via the transceiver (106) and store information obtained by processing the second information/signal in the memory (104).

A memory (104) may be operatively connected to the processor (102). The memory (104) may store various types of information and/or instructions. The memory (104) may store firmware and/or software code (105) that implements code, instructions and/or sets of instructions that, when executed by the processor (102), perform the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the firmware and/or software code (105) may implement instructions that, when executed by the processor (102), perform the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the firmware and/or software code (105) may control the processor (102) to perform one or more protocols. For example, the firmware and/or software code (105) may control the processor (102) to perform one or more air interface protocol layers.

Here, the processor (102) and memory (104) may be part of a communication modem/circuit/chip designed to implement a RAT (e.g., LTE or NR). A transceiver (106) may be connected to the processor (102) and may transmit and/or receive wireless 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 an RF (radio frequency) unit. In the present specification, the first wireless device (100) may represent a communication modem/circuit/chip.

The second wireless device (200) may include at least one transceiver, such as a transceiver (206), at least one processing chip, such as a processing chip (201), and/or one or more antennas (208).

The processing chip (201) may include at least one processor, such as a processor (202), and at least one memory, such as a memory (204). Additionally and/or alternatively, the memory (204) may be located external to the processing chip (201).

The processor (202) may control the memory (204) and/or the transceiver (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods and/or operational flowcharts disclosed herein. For example, the processor (202) may process information in the memory (204) to generate third information/signal and transmit a wireless signal including the third information/signal via the transceiver (206). The processor (202) may receive a wireless signal including fourth information/signal via the transceiver (206) and store information obtained by processing the fourth information/signal in the memory (204).

A memory (204) may be operatively connected to the processor (202). The memory (204) may store various types of information and/or instructions. The memory (204) may store firmware and/or software code (205) that implements instruction codes, commands and/or sets of instructions that, when executed by the processor (202), perform the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the firmware and/or software code (205) may implement instructions that, when executed by the processor (202), perform the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the firmware and/or software code (205) may control the processor (202) to perform one or more protocols. For example, the firmware and/or software code (205) may control the processor (202) to perform one or more air interface protocol layers.

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

Hereinafter, hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as a physical (PHY) layer, a media 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). One or more processors (102, 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, procedures, proposals, methods, and/or operational flowcharts disclosed herein. One or more processors (102, 202) can generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and/or operational flowcharts disclosed herein and provide the signals to one or more transceivers (106, 206). One or more processors (102, 202) can receive signals (e.g., baseband signals) from one or more transceivers (106, 206) and obtain PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and/or operational flowcharts disclosed herein.

The one or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, and/or a microcomputer. The one or more processors (102, 202) may be implemented by hardware, firmware, software, and/or a combination thereof. For 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), and/or one or more field programmable gate arrays (FPGAs) may be included in the one or more processors (102, 202). For example, the one or more processors (102, 202) may be configured by a set of a communication control processor, an application processor (AP), an electronic control unit (ECU), a central processing unit (CPU), a graphic processing unit (GPU), and a memory control processor.

One or more memories (104, 204) may be coupled to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and/or commands. The one or more memories (104, 204) may be configured as random access memory (RAM), dynamic RAM (DRAM), read-only memory (ROM), erasable programmable ROM (EPROM), flash memory, volatile memory, nonvolatile memory, hard drive, register, cache memory, computer-readable storage media, and/or combinations thereof. The one or more memories (104, 204) may be located internally and/or externally to the one or more processors (102, 202). Additionally, the one or more memories (104, 204) may be coupled to the one or more processors (102, 202) via various technologies, such as wired or wireless connections.

One or more transceivers (106, 206) can transmit user data, control information, wireless signals/channels, etc., referred to in the descriptions, functions, procedures, proposals, methods, and/or flowcharts disclosed herein to one or more other devices. One or more transceivers (106, 206) can receive user data, control information, wireless signals/channels, etc., referred to in the descriptions, functions, procedures, proposals, methods, and/or flowcharts disclosed herein from one or more other devices. For example, one or more transceivers (106, 206) can be coupled to one or more processors (102, 202) and can transmit and receive wireless signals. For example, one or more processors (102, 202) can control one or more transceivers (106, 206) to transmit user data, control information, wireless signals, etc., to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, wireless signals, etc. from one or more other devices.

One or more transceivers (106, 206) may be coupled to one or more antennas (108, 208). Additionally and/or alternatively, one or more transceivers (106, 206) may include one or more antennas (108, 208). One or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals/channels, etc., as described in the descriptions, functions, procedures, proposals, methods and/or operational flowcharts disclosed herein via one or more antennas (108, 208). In the present specification, one or more antennas (108, 208) may be multiple physical antennas or multiple logical antennas (e.g., antenna ports).

One or more transceivers (106, 206) may convert received user data, control information, wireless signals/channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals/channels, etc. using one or more processors (102, 202). One or more transceivers (106, 206) may convert processed user data, control information, wireless signals/channels, etc. from baseband signals to RF band signals using one or more processors (102, 202). For this purpose, one or more transceivers (106, 206) may include an (analog) oscillator and/or a filter. For example, one or more transceivers (106, 206) may up-convert an OFDM baseband signal to an OFDM signal via an (analog) oscillator and/or filter under the control of one or more processors (102, 202) and transmit the up-converted OFDM signal at a carrier frequency. One or more transceivers (106, 206) may receive an OFDM signal at a carrier frequency and down-convert the OFDM signal to an OFDM baseband signal via an (analog) oscillator and/or filter under the control of one or more processors (102, 202).

Although not illustrated in FIG. 2, the wireless device (100, 200) may further include additional components. The additional components (140) may be configured in various ways depending on the type of the wireless device (100, 200). For example, the additional components (140) may include at least one of a power unit/battery, an input/output (I/O) device (e.g., an audio I/O port, a video I/O port), a driving device, and a computing device. The additional components (140) may be connected to one or more processors (102, 202) via various technologies, such as a wired or wireless connection.

In the implementation of the present specification, a UE can operate as a transmitter in the uplink (UL) and as a receiver in the downlink (DL). In the implementation of the present specification, a base station can operate as a receiver in the UL and as a transmitter in the DL. For the sake of convenience of description, it is mainly assumed below that the first wireless device (100) operates as a UE and the second wireless device (200) operates as a base station. For example, a processor (102) connected to, mounted on, or released in the first wireless device (100) can be configured to perform UE operations according to the implementation of the present specification or to control a transceiver (106) to perform UE operations according to the implementation of the present specification. A processor (202) connected to, mounted on, or released in the second wireless device (200) can be configured to perform base station operations according to the implementation of the present specification or to control a transceiver (206) to perform base station operations according to the implementation of the present specification.

In this specification, a base station may be referred to as a Node B, an eNode B (eNB), or a gNB.

Figure 3 shows an example of a UE to which the implementation of this specification is applied.

Referring to FIG. 3, the UE (100) can correspond to the first wireless device (100) of FIG. 2.

The 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 SIM (Subscriber Identification Module) card (145), a speaker (146), and a microphone (147).

The processor (102) may be configured to implement the descriptions, functions, procedures, proposals, methods, and/or flowcharts disclosed herein. The processor (102) may be configured to control one or more other components of the UE (100) to implement the descriptions, functions, procedures, proposals, methods, and/or flowcharts disclosed herein. A layer of a radio interface protocol may be implemented in the processor (102). The processor (102) may include an ASIC, other chipset, logic circuit, and/or data processing device. The processor (102) may be an application processor. The processor (102) may include at least one of a DSP, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a modem (modulator and demodulator). Examples of processors (102) can be found in the SNAPDRAGON ^TM series processors made by Qualcomm®, the EXYNOS ^TM series processors made by Samsung®, the A series processors made by Apple®, the HELIO ^TM series processors made by MediaTek®, the ATOM ^TM series processors made by Intel®, or their corresponding next-generation processors.

Memory (104) is operatively coupled to the processor (102) and stores various information for operating the processor (102). Memory (104) may include ROM, RAM, flash memory, memory cards, storage media, and/or other storage devices. When the implementation is implemented in software, the techniques described herein may be implemented using modules (e.g., procedures, functions, etc.) that perform the descriptions, functions, procedures, suggestions, methods, and/or operational flowcharts disclosed herein. The modules may be stored in memory (104) and executed by the processor (102). Memory (104) may be implemented within the processor (102) or external to the processor (102), in which case it may be communicatively coupled to the processor (102) via various methods known in the art.

A transceiver (106) is operably coupled to the processor (102) and transmits and/or receives a radio signal. The transceiver (106) includes a transmitter and a receiver. The transceiver (106) may include a baseband circuit for processing a radio frequency signal. The transceiver (106) controls one or more antennas (108) to transmit and/or receive a radio signal.

The power management module (141) manages the power of the processor (102) and/or the transceiver (106). The battery (142) supplies power to the power management module (141).

The display (143) outputs the results processed by the processor (102). The keypad (144) receives input to be used by the processor (102). The keypad (144) can be displayed on the display (143).

A SIM card (145) is an integrated circuit that securely stores an International Mobile Subscriber Identity (IMSI) and associated keys, and is used to identify and authenticate subscribers in mobile devices such as mobile phones and computers. Additionally, many SIM cards can store contact information.

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).

<6G System General>

The 6G (wireless communication) system aims to achieve (i) very high data rates per device, (ii) a very large number of connected devices, (iii) global connectivity, (iv) very low latency, (v) low energy consumption for battery-free IoT devices, (vi) ultra-reliable connectivity, and (vii) connected intelligence with machine learning capabilities. The vision of the 6G system can be divided into four aspects: intelligent connectivity, deep connectivity, holographic connectivity, and ubiquitous connectivity, and the 6G system can satisfy the requirements as shown in Table 1 below. In other words, Table 1 is a table showing an example of the requirements of a 6G system.

Per device peak data rate 1 Tbps E2E latency 1 ms Maximum spectral efficiency 100bps/Hz Mobility support Up to 1000km/hr Satellite integration Fully AI Fully Autonomous vehicle Fully XR Fully Haptic Communication Fully

6G systems can have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), massive machine-type communication (mMTC), AI integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security.

Figure 4 is a diagram showing an example of a communication structure that can be provided in a 6G system.

6G systems are expected to have 50 times the simultaneous wireless connectivity of 5G systems. URLLC, a key feature of 5G, will become even more crucial in 6G communications by providing end-to-end latency of less than 1 ms. 6G systems will have significantly higher volumetric spectral efficiency, compared to the commonly used area spectral efficiency. 6G systems can offer extremely long battery life and advanced battery technologies for energy harvesting, eliminating the need for separate charging for mobile devices in 6G systems. New network characteristics in 6G may include:

- Satellite integrated network: 6G is expected to integrate with satellites to provide a global mobile network. The integration of terrestrial, satellite, and airborne networks into a single wireless communications system is crucial for 6G.

- Connected intelligence: Unlike previous generations of wireless communication systems, 6G is revolutionary and will update the wireless evolution from “connected things” to “connected intelligence.” AI can be applied at each stage of the communication process (or at each stage of signal processing, as described below).

- Seamless integration of wireless information and energy transfer: 6G wireless networks will transfer power to charge the batteries of devices such as smartphones and sensors. Therefore, wireless information and energy transfer (WIET) will be integrated.

- Ubiquitous super 3D connectivity: Access to networks and core network functions of drones and very low Earth orbit satellites will create super 3D connectivity in 6G ubiquitous.

Some general requirements for the new network characteristics of 6G, such as the above, may be as follows:

- Small cell networks: The concept of small cell networks was introduced to improve received signal quality in cellular systems by increasing throughput, energy efficiency, and spectral efficiency. Consequently, small cell networks are essential for 5G and beyond-5G (5GB) communication systems. Accordingly, 6G communication systems also adopt the characteristics of small cell networks.

Ultra-dense heterogeneous networks: Ultra-dense heterogeneous networks will be another key feature of 6G communication systems. Multi-tier networks comprised of heterogeneous networks improve overall QoS and reduce costs.

High-capacity backhaul: Backhaul connections are characterized by high-capacity backhaul networks to support high-volume traffic. High-speed fiber optics and free-space optics (FSO) systems may be potential solutions to this problem.

- Radar technology integrated with mobile technology: High-precision localization (or location-based services) through communications is a key feature of 6G wireless communication systems. Therefore, radar systems will be integrated with 6G networks.

- Softwarization and virtualization: Softwarization and virtualization are two critical features that form the foundation of the design process for 5GB networks to ensure flexibility, reconfigurability, and programmability. Furthermore, billions of devices can be shared on a shared physical infrastructure.

<Key implementation technologies for 6G systems>

Artificial Intelligence

The most crucial and newly introduced technology for 6G systems is AI. 4G systems did not involve AI. 5G systems will support partial or very limited AI. However, 6G systems will fully support AI for automation. Advances in machine learning will create more intelligent networks for real-time communications in 6G. Incorporating AI into communications can streamline and improve real-time data transmission. AI can use numerous analyses to determine how complex target tasks should be performed. In other words, AI can increase efficiency and reduce processing delays.

Time-consuming tasks such as handover, network selection, and resource scheduling can be performed instantly using AI. AI can also play a crucial role in machine-to-machine (M2M), machine-to-human, and human-to-machine communications. Furthermore, AI can facilitate rapid communication in brain-computer interfaces (BCIs). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.

Recent attempts to integrate AI into wireless communication systems have focused on the application layer, network layer, and especially deep learning in wireless resource management and allocation. However, this research is increasingly evolving to the MAC layer and physical layer, with attempts to combine deep learning with wireless transmission, particularly at the physical layer. AI-based physical layer transmission refers to the application of AI-driven signal processing and communication mechanisms, rather than traditional communication frameworks, in the fundamental signal processing and communication mechanisms. Examples include deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO mechanisms, and AI-based resource scheduling and allocation.

Machine learning can be used for channel estimation and channel tracking, as well as for power allocation and interference cancellation in the physical layer of the downlink (DL). Furthermore, machine learning can be used for antenna selection, power control, and symbol detection in MIMO systems.

Machine learning refers to a series of operations that train machines to perform tasks that humans can or cannot perform. Machine learning requires data and a learning model. In machine learning, data learning methods can be broadly categorized into three types: supervised learning, unsupervised learning, and reinforcement learning.

Neural network training aims to minimize output errors. It involves repeatedly inputting training data into a neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error.

Supervised learning uses labeled training data, while unsupervised learning may not have labeled training data. For example, in the case of supervised learning for data classification, the training data may be data in which each training data category is labeled. Labeled training data is input to a neural network, and the error can be calculated by comparing the output (categories) of the neural network with the training data labels. The calculated error is backpropagated through the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated through backpropagation. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, in the early stages of training a neural network, a high learning rate can be used to quickly allow the network to achieve a certain level of performance, thereby increasing efficiency. In the later stages of training, a low learning rate can be used to increase accuracy.

Learning methods may vary depending on the characteristics of the data. For example, if the goal is to accurately predict data transmitted by a transmitter in a communication system, supervised learning is preferable to unsupervised learning or reinforcement learning.

The learning model corresponds to the human brain, and the most basic linear model can be thought of, but the machine learning paradigm that uses highly complex neural network structures, such as artificial neural networks, as learning models is called deep learning.

The neural network cores used in learning methods are mainly divided into deep neural networks (DNN), convolutional deep neural networks (CNN), recurrent Boltzmann machines (RNN), and spiking neural networks (SNN).

Terahertz Communication

Data rates can be increased by increasing bandwidth. This can be achieved by utilizing sub-THz communications with wide bandwidths and applying advanced massive MIMO technology. THz waves, also known as sub-millimeter waves, typically refer to the frequency range between 0.1 THz and 10 THz, with corresponding wavelengths ranging from 0.03 mm to 3 mm. The 100 GHz to 300 GHz band (sub-THz band) is considered a key part of the THz spectrum for cellular communications. Adding the sub-THz band to the mmWave band will increase 6G cellular communication capacity. Among the defined THz bands, 300 GHz to 3 THz lies in the far infrared (IR) frequency band. While part of the optical band, the 300 GHz to 3 THz band lies at the boundary of the optical band, immediately following the RF band. Therefore, this 300 GHz to 3 THz band exhibits similarities to RF.

Figure 5 shows an example of an electromagnetic spectrum.

Key characteristics of THz communications include (i) the widely available bandwidth to support very high data rates and (ii) the high path loss that occurs at high frequencies (requiring highly directional antennas). The narrow beamwidths generated by highly directional antennas reduce interference. The small wavelength of THz signals allows for a significantly larger number of antenna elements to be integrated into devices and base stations operating in this band. This enables the use of advanced adaptive array technologies to overcome range limitations.

Large-scale MIMO

One of the key technologies for improving spectral efficiency is the application of MIMO technology. As MIMO technology improves, spectral efficiency also improves. Therefore, massive MIMO technology will be crucial in 6G systems. Because MIMO technology utilizes multiple paths, multiplexing technology must be considered to ensure that data signals can be transmitted along more than one path, as well as beam generation and operation technologies suitable for the THz band.

Hologram Beam Forming (HBF)

Beamforming is a signal processing procedure that adjusts an antenna array to transmit a wireless signal in a specific direction. It is a subset of smart antennas or advanced antenna systems. Beamforming technology offers several advantages, including high signal-to-noise ratio, interference avoidance and rejection, and high network efficiency. Holographic beamforming (HBF) is a novel beamforming method that differs significantly from MIMO systems because it uses software-defined antennas. HBF will be a highly effective approach for efficient and flexible signal transmission and reception in multi-antenna communication devices in 6G.

Optical wireless technology

Optical wireless communication (OWC) is a form of optical communication that uses visible light, infrared (IR), or ultraviolet (UV) light to transmit signals. OWC operating in the visible light band (e.g., 390–750 nm) is commonly referred to as visible light communication (VLC). Light-emitting diodes (LEDs) can be utilized to implement VLC. VLC can be used in a variety of applications, including wireless local area networks (WLANs), wireless personal area networks (WPANs), and vehicular networks.

VLC offers the following advantages over RF-based technologies. First, the spectrum occupied by VLC is unlicensed and can provide a wide bandwidth (up to THz). Second, VLC causes minimal significant interference with other electromagnetic devices. Therefore, VLC can be applied to sensitive electromagnetic interference applications such as aircraft and hospitals. Third, VLC offers advantages in communication security and privacy. Visible light, the transmission medium of VLC-based networks, cannot penetrate walls and other opaque obstacles. Therefore, VLC's transmission range can be limited to indoor areas, protecting users' privacy and sensitive information. Fourth, VLC can utilize lighting sources as base stations, eliminating the need for expensive base stations.

Free-space optical communication (FSO) is an optical communication technology that uses light propagating in free space, such as air, outer space, or a vacuum, to wirelessly transmit data for communication or computer networking. FSO can be used as a point-to-point optical wireless communication (OWC) system on the ground. FSO can operate in the near-infrared frequency range (750-1600 nm). Laser transmitters can be used to implement FSO, and it offers high data rates (e.g., 10 Gbit/s), potentially offering a solution to backhaul bottlenecks.

These OWC technologies are designed for 6G communications, in addition to RF-based communications for all possible device-to-access networks. These networks connect to network-to-backhaul/fronthaul networks. OWC technologies have already been used since 4G communication systems, but they will be used more widely to meet the demands of 6G communication systems. OWC technologies such as light fidelity, visible light communication, optical camera communication, and optical band-based FSO communication are already well-known. Communications based on optical wireless technology can provide very high data rates, low latency, and secure communications.

LiDAR (Light Detection And Ranging) can also be used for ultra-high-resolution 3D mapping in 6G communications based on its wide bandwidth. LiDAR is a remote sensing method that illuminates a target using near-infrared, visible, and ultraviolet light, detecting the reflected light with a light sensor to measure distance. LiDAR can be used for fully autonomous driving in automobiles.

FSO Backhaul Network

The transmitter and receiver characteristics of an FSO system are similar to those of a fiber-optic network. Therefore, data transmission in an FSO system is similar to that of a fiber-optic system. Therefore, FSO can be a promising technology for providing backhaul connectivity in 6G systems, in conjunction with fiber-optic networks. Using FSO, ultra-long-distance communications are possible, even over distances exceeding 10,000 km. FSO supports high-capacity backhaul connectivity for remote and non-remote areas, such as the ocean, space, underwater, and isolated islands. FSO also supports cellular base station (BS) connections.

Non-Terrestrial Networks (NTN)

6G systems integrate terrestrial and airborne networks to support vertically expanded user communications. 3D BSs will be provided via low-Earth orbit satellites and UAVs. Adding a new dimension in altitude and associated degrees of freedom significantly differentiates 3D connectivity from existing 2D networks. NR considers Non-Terrestrial Networks (NTNs) as one approach to achieving this. NTNs are networks or network segments that utilize RF resources onboard satellites (or UAS platforms). Common NTN scenarios, which provide access to user equipment, include transparent payloads and regenerative payloads. The following are the basic elements of NTNs.

- One or more sat-gateways connecting the NTN to the public data network.

- GEO satellites are served by one or more satellite gateways deployed across the satellite's target coverage area (e.g., regional or continental coverage). We assume that a UE in a cell is served by only one sat-gateway.

Non-GEO satellites that provide continuous service from one or more satellite gateways at a time. The system ensures service and feeder link continuity between consecutively serving satellite gateways with sufficient time duration to allow for mobile anchoring and handover.

- Feeder link or wireless link between the satellite gateway and the satellite (or UAS platform).

- Service link or wireless link between user equipment and satellite (or UAS platform).

A satellite (or UAS platform) capable of implementing transparent or regenerative (including onboard processing) payloads. The satellite (or UAS platform) typically generates multiple beams for a designated service area, depending on its field of view. The beam's footprint is typically elliptical. The satellite's (or UAS platform's) field of view varies depending on the onboard antenna diagram and minimum elevation angle.

- Transparent payload: Radio frequency filtering, frequency conversion, and amplification. Therefore, the waveform signal repeated by the payload remains unchanged.

- Replay payload: radio frequency filtering, frequency conversion and amplification, demodulation/decoding, switching and/or routing, and coding/modulation. This is essentially equivalent to embedding all or part of a base station function (e.g., gNB) on a satellite (or UAS platform).

- Optionally, for satellite constellations, inter-satellite link (ISL) is available. This requires a regenerative payload on the satellite. ISL can operate in RF or wideband.

- User equipment is serviced by satellites (or UAS platforms) within the target service area.

Typically, GEO satellites and UAS are used to provide continental, regional or local services.

Typically, LEO and MEO constellations are used to provide services in both the Northern and Southern Hemispheres. In some cases, constellations can even provide global coverage, including polar regions. This requires appropriate orbital inclination, sufficient beam generation, and inter-satellite links.

Quantum Communication

Quantum communication is a next-generation communication technology that applies quantum mechanical properties to the field of information and communication, overcoming limitations of existing information and communication technologies, such as security and ultra-high-speed computation. Quantum communication provides a means to generate, transmit, process, and store information that cannot be expressed in the binary bits of 0 and 1 used in existing communication technologies, or that are difficult to express. Unlike existing communication technologies that use wavelength or amplitude to transmit information between a transmitter and a receiver, quantum communication utilizes photons, the smallest unit of light, to transmit information between the transmitter and receiver. In particular, quantum communication can utilize quantum uncertainty and quantum irreversibility regarding the polarization or phase difference of photons (light), enabling communication with perfect security. Furthermore, under certain conditions, quantum communication may also enable ultra-high-speed communication by exploiting quantum entanglement.

Cell-free Communication

Tight integration of multiple frequencies and heterogeneous communication technologies is crucial for 6G systems. As a result, users can seamlessly move from one network to another without requiring any manual configuration on their devices. The best network is automatically selected from available communication technologies. This will break the limitations of the cell concept in wireless communications. Currently, user movement from one cell to another in dense networks results in excessive handovers, resulting in handover failures, handover delays, data loss, and the ping-pong effect. 6G cell-free communications will overcome all of these challenges and provide improved QoS.

Cell-free communication is defined as "a system in which multiple geographically distributed antennas (APs) cooperatively serve a small number of terminals using the same time/frequency resources, assisted by a fronthaul network and CPU." A single terminal is served by a collection of APs, called an AP cluster. There are several methods for forming AP clusters. Among them, a cluster composed of APs that can significantly improve terminal reception performance is called terminal-centric clustering, and this method dynamically updates the cluster configuration as the terminal moves. By introducing this terminal-centric AP clustering technique, the terminal is always located at the center of the AP cluster, thereby avoiding inter-cluster interference that can occur when the terminal is located at the edge of the AP cluster. This cell-free communication will be achieved through multi-connectivity and multi-tier hybrid technologies and heterogeneous radios in the devices.

Integration of Wireless Information and Energy Transfer (WIET)

WIET uses the same fields and waves as wireless communication systems. Specifically, sensors and smartphones will be charged using wireless power transfer during communication. WIET is a promising technology for extending the life of battery-powered wireless systems. Therefore, battery-less devices will be supported by 6G communications.

Integration of Wireless Communication and Sensing

Autonomous wireless networks are capable of continuously sensing dynamically changing environmental conditions and exchanging information between different nodes. In 6G, sensing will be tightly integrated with communications to support autonomous systems.

Integrated Access and Backhaul Network

In 6G, the density of access networks will be enormous. Each access network will be connected to backhaul connections, such as fiber optics and FSO networks. To accommodate the massive number of access networks, there will be tight integration between access and backhaul networks.

Big Data Analysis

Big data analytics is a complex process for analyzing diverse, large-scale data sets, or "big data." This process uncovers hidden data, unknown correlations, and customer trends, ensuring complete data management. Big data is collected from various sources, such as video, social networks, images, and sensors. This technology is widely used to process massive amounts of data in 6G systems.

Reconfigurable Intelligent Surface

Many studies have been conducted that consider the wireless environment as an optimization target variable along with the transmitter and receiver. The wireless environment created using this approach is called a Smart Radio Environment (SRE) or Intelligent Radio Environment (IRE) to emphasize its fundamental difference from past design and optimization standards. Various terms have been proposed for reconfigurable intelligent antenna (or intelligent reconfigurable antenna) technologies that enable SRE, including Reconfigurable Metasurfaces, Smart Large Intelligent Surfaces (SLIS), Large Intelligent Surfaces (LIS), Reconfigurable Intelligent Surface (RIS), and Intelligent Reflecting Surface (IRS).

THz band signals have strong linearity, which can create many shadow areas due to obstacles. RIS technology, which enables expanded communication coverage, enhanced communication stability, and additional value-added services by installing RIS near these shadow areas, is becoming increasingly important. RIS is an artificial surface made of electromagnetic materials that can alter the propagation of incoming and outgoing radio waves. While RIS may appear to be an extension of massive MIMO, it differs from massive MIMO in its array structure and operating mechanism. Furthermore, RIS operates as a reconfigurable reflector with passive elements, meaning it passively reflects signals without using active RF chains, which offers the advantage of low power consumption. Furthermore, because each passive reflector in RIS must independently adjust the phase shift of the incoming signal, this can be advantageous for wireless communication channels. By appropriately adjusting the phase shift via the RIS controller, the reflected signal can be collected at the target receiver to boost the received signal power.

In addition to reflecting wireless signals, RISs also exist that can control transmission and refraction characteristics. These RISs are primarily used for outdoor-to-indoor (O2I) applications. Recently, STAR-RIS (Simultaneous Transmission and Reflection RIS), which provides both reflection and transmission, has also been actively researched.

Metaverse

The metaverse is a portmanteau of "Meta," meaning "virtual" or "transcendent," and "Universe," meaning "universe." Generally, the metaverse is used to refer to a "three-dimensional virtual space where social and economic activities similar to those in the real world are facilitated."

Extended Reality (XR), a key technology enabling the metaverse, can expand real-world experiences and deliver exceptional immersion by merging the virtual and real. The high bandwidth and low latency of 6G networks enable users to experience even more immersive virtual reality (VR) and augmented reality (AR).

Autonomous Driving (Self-driving)

For fully autonomous driving, vehicles must communicate with each other to inform each other of dangerous situations, and vehicles must communicate with infrastructure such as parking lots and traffic lights to confirm information such as parking location and signal change times. V2X (Vehicle-to-Everything), a key element in building autonomous driving infrastructure, is a technology that allows cars to communicate and share with various elements on the road for autonomous driving, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) wireless communication.

To maximize autonomous driving performance and ensure high safety, fast transmission speeds and low-latency technologies are essential. Furthermore, as autonomous driving moves beyond simply providing warnings or guidance messages to drivers, actively intervening in driving and directly controlling the vehicle in dangerous situations requires a vast amount of information to be transmitted and received, 6G is expected to maximize autonomous driving with faster transmission speeds and lower latency than 5G.

Unmanned Aerial Vehicle (UAV)

Unmanned Aerial Vehicles (UAVs), or drones, will be a key element in 6G wireless communications. In most cases, high-speed wireless connections will be provided using UAV technology. BS entities are installed on UAVs to provide cellular connectivity. UAVs offer specific capabilities not found in fixed BS infrastructure, such as easy deployment, robust line-of-sight links, and controlled mobility. During emergencies such as natural disasters, deploying terrestrial communication infrastructure is not economically feasible, and sometimes, volatile environments make it impossible to provide services. UAVs can easily handle these situations. UAVs will become a new paradigm in wireless communications. This technology facilitates three fundamental requirements for wireless networks: enhanced mobile broadband (eMBB), URLLC, and mMTC. UAVs can also support various purposes, such as enhancing network connectivity, fire detection, disaster emergency services, security and surveillance, pollution monitoring, parking monitoring, and accident monitoring. Therefore, UAV technology is recognized as one of the most important technologies for 6G communications.

Blockchain

Blockchain will become a crucial technology for managing massive amounts of data in future communication systems. Blockchain is a form of distributed ledger technology. A distributed ledger is a database distributed across numerous nodes or computing devices. Each node replicates and stores an identical copy of the ledger. Blockchains are managed by a peer-to-peer network and can exist without being managed by a central authority or server. Data on a blockchain is collected and organized into blocks. Blocks are linked together and protected using cryptography. Blockchain perfectly complements large-scale IoT with its inherently enhanced interoperability, security, privacy, reliability, and scalability. Therefore, blockchain technology offers several features, such as interoperability between devices, traceability of large amounts of data, autonomous interaction with other IoT systems, and the massive connectivity stability of 6G communication systems.

Figure 6 illustrates an example of subframe types in NR.

The transmission time interval (TTI) illustrated in FIG. 6 may be referred to as a subframe or slot for NR (or new RAT). The subframe (or slot) of FIG. 6 may be used in a TDD system of NR (or new RAT) to minimize data transmission delay. As illustrated in FIG. 4, the subframe (or slot) includes 14 symbols, similar to the current subframe. The symbols in the front of the subframe (or slot) may be used for a DL control channel, and the symbols in the back of the subframe (or slot) may be used for an UL control channel. The remaining symbols may be used for DL data transmission or UL data transmission. According to this subframe (or slot) structure, downlink transmission and uplink transmission may be sequentially performed in one subframe (or slot). Therefore, downlink data may be received within a subframe (or slot), and an uplink acknowledgment (ACK/NACK) may be transmitted within the subframe (or slot). This subframe (or slot) structure can be referred to as a self-contained subframe (or slot). Using this subframe (or slot) structure has the advantage of minimizing the final data transmission latency by reducing the time required to retransmit data with reception errors. In this self-contained subframe (or slot) structure, a time gap may be required during the transition from transmission mode to reception mode or from reception mode to transmission mode. To this end, some OFDM symbols during the transition from DL to UL in the subframe structure can be designated as a guard period (GP).

SS Block in NR

The SS block (SS/PBCH Block: SSB) includes the PBCH (Physical Broadcast Channel) containing the Master Information Block (MIB), which is the information required for the terminal to perform initial access in 5G NR, and the synchronization signal (SS) (including PSS and SSS).

Furthermore, multiple SSBs can be grouped together to define an SS burst, and multiple SS bursts can be grouped together to define an SS burst set. Each SSB is assumed to be beamformed in a specific direction, and the multiple SSBs within an SS burst set are designed to support terminals located in different directions.

Figure 7 is an example diagram showing an example of SSB in NR.

Referring to Figure 7, SS bursts are transmitted at predetermined periods. Accordingly, the terminal receives SSBs and performs cell detection and measurement.

Meanwhile, beam sweeping is performed for SSB in 5G NR. This will be described with reference to Fig. 8.

Figure 8 is an exemplary diagram showing an example of beam sweeping in NR.

The base station transmits each SSB within an SS burst by beam-sweeping it over time. At this time, multiple SSBs within an SS burst set are transmitted to support terminals located in different directions.

Poisoning

Positioning information may be requested from the network, LMF (Location Management Function), or other terminals in RRC INACTIVE mode or RRC CONNECTED mode. The required positioning accuracy may vary depending on various environments (e.g., industrial, indoor, automotive, emergency, etc.).

The LMF can control measurements related to positioning. The LMF can transmit scheduling information related to positioning measurements to the network (e.g., gNB) and/or the terminal. The network and/or the terminal can measure information necessary for positioning calculation (e.g., DL-RSTD, UL-RTOA, UE-Rx-Tx Time difference, gNB Rx-Tx Time difference, DL-AOD, UL-AoA, etc.) and report it to the LMF under the control of the LMF. At this time, the measurement of the corresponding information can be reported within a specified time and with a certain accuracy (e.g., RSRP accuracy ±3.5dB).

Based on information measured by the network and the terminal, the LMF can calculate the terminal's positioning. The LMF can also determine which positioning method to perform. Depending on the positioning method, the items measured by the terminal and/or the network (e.g., parameters, metrics, etc.) may vary. For example, if the LMF attempts to perform multi-cell RTT positioning, the terminal may measure the UE-Rx-Tx time difference, and the network may measure the gNB Rx-Tx time difference. As the operating scenarios for positioning information expand and scenarios require more precise positioning accuracy, positioning accuracy may be improved.

This positioning can also be applied to sidelink communications and operate similarly. If the LMF is out of control, a server UE can perform positioning calculations, acting as the LMF. In this regard, the terminal can perform the following measurement procedures and accuracy tests.

- RSTD measurement

- PRS-RSRP measurement

- Measurement of UE Rx-Tx time difference

The method for measuring the performance of the AI/ML model proposed in this specification may be a method performed by a terminal.

In this specification, a solution for a performance evaluation method of AI/ML, which is one of the major challenges related to 'AI/ML for NR air interface', one of the Rel-19 WIs, can be proposed.

By replacing existing functions with AI/ML methods, better performance can be expected. Furthermore, AI/ML can be applied to a variety of use cases.

Typical use cases include CSI feedback enhancement, beam management, and positioning accuracy enhancement.

The overall operation of AI/ML can be described as Life Cycle Management (LCM). AI/ML models are evaluated, and either the model can be replaced or additional model training can be performed. Alternatively, if performance falls short of expectations, a fallback to legacy methods can be implemented.

Because AI/ML models can be evaluated based on a benchmark value, a benchmark may be necessary to evaluate AI/ML models. For example, the accuracy of the inference results from an AI/ML model can be assessed using the benchmark value. However, if the benchmark value is known, there is no need to use AI/ML for inference, which can be a contradictory situation.

Therefore, this specification proposes a solution that can perform performance evaluation on AI/ML models for each use case.

Figure 9 shows an example of an AI/ML model.

Based on the performance evaluation of the AI/ML model, various actions can be performed in LCM.

For example, if the AI/ML model performance evaluation results are poor, the AI/ML model may be redesigned or fall back to a legacy method. These actions will be discussed later. This specification may describe and propose content/methods related to performance evaluation of AI/ML models.

Figure 10 shows an example of a network managing an AI/ML model.

From a signaling perspective, if the management operation of the LCM block diagram is performed in the network and the network triggers AI/ML operations, the UE can include metrics measured by the UE for AI/ML model evaluation in the assistance information and transmit them to the network.

I. Use Case 1: CSI Feedback Enhancement

Methods to improve CSI feedback through AI/ML models can be proposed.

Since the goal is to optimize T-put (throughput), performance evaluation of AI/ML models can be judged based on whether T-put optimization has been achieved.

At this time, the channel environment can also be considered.

For example, if the channel environment is poor, T-put may be low. However, if AI/ML model updates continue based solely on T-put (due to low T-put), terminals in poor channel environments may perform unnecessary AI/ML model updates.

Alternatively, performing AI/ML model updates solely based on channel conditions and T-put can be problematic. For example, if an AI/ML model update is performed in a good channel environment but T-put is low, the actual amount of data transmitted may not be large, resulting in unnecessary AI/ML model updates being performed even in good channel conditions and low T-put.

To address these issues, the following methods may be proposed:

- If the blur (BLER) performance is less than 10-a(%) or greater than 10+b(%), an AI/ML model update may be considered. For example, blur performance may be maintained between 10-a(%) and 10+b(%).

- Alternatively, if the blur (BLER) performance is less than x or greater than y, an AI/ML model update may be considered. For example, the blur performance may remain between x and y. x may be less than y.

Here, BLER may be the block error rate. For example, BLER may be the ratio of the number of received blocks with errors to the total number of sent blocks.

10-a and x may be lower boundaries. 10+b and y may be higher boundaries.

If the Channel State Information (CSI) is reported to be significantly better than the actual channel environment, a higher Modulation and Coding Scheme (MCS) than the actual channel environment may be set for data transmission and reception. In this case, blur performance may deteriorate (e.g., blur performance may be high).

If the CSI is reported to be significantly worse than the actual channel environment, data may be transmitted and received with an MCS lower than the MCS appropriate for the channel environment. In this case, blur performance may approach 0. A blur performance close to 0 can result in good blur performance but low T-put.

Therefore, it may be effective to determine whether to update the AI/ML model based on the range of blur performance.

Additionally, it may be considered whether the DL signal is transmitted with an MCS lower than the MCS appropriate for the CSI reported by the UE. For example, if there is little DL data, the DL data may be transmitted with an MCS lower than the MCS appropriate for the channel environment reported by the UE. In this case, the blur performance may be close to 0 and T-put degradation may occur. However, the T-put degradation may not be caused by the UE reporting a worse channel environment than the actual environment, as described above. Therefore, the T-put degradation may be unrelated to the performance of the AI/ML model for CSI prediction. Therefore, in this case, the lower boundary of the blur performance may be set to 0%.

Blur performance can be achieved by:

- Blur measurement method 1: The measurement period of blur performance can be the most recent A slot or t time.

- Blur measurement method 2: Measurement of blur performance can be performed in A slots or t time periods.

Blur measurement method 1 may have the disadvantage of requiring memory for the corresponding period, but may have the advantage of being able to quickly determine whether the AI/ML model needs to be updated.

Blur measurement method 2 may have the advantage of not requiring a large memory, but may have the disadvantage of judging whether to update the AI/ML model by the corresponding cycle (A slot or t time) later.

Fig. 11 shows an example of a blur measurement method 1 according to an embodiment of the present specification.

The terminal can perform a blur check for each slot by sliding one slot at a time.

Fig. 12 shows an example of a blur measurement method 2 according to an embodiment of the present specification.

The terminal can perform a blur check every A slot cycle.

Based on the blur performance checked in this way, the terminal can decide whether to update the AI/ML model currently in use.

Alternatively, based on the blur performance checked in this way, the terminal can decide whether to use the current AI/ML model and replace it with the existing method (fallback to the legacy method).

To improve CSI feedback through AI/ML, the following methods can be implemented:

- Method and procedure for using blur performance as a performance evaluation KPI (Key Performance Indicator) for AI/ML models

- When blur performance is used as a performance evaluation KPI of an AI/ML model, a method and procedure for setting an upper limit (upper threshold) and/or a lower limit (lower threshold) of blur performance.

- Method and procedure for performing blur performance in a specific time cycle

- Method and procedure for performing blur performance by sliding the measurement time interval

- Method and procedure for determining whether to update the AI/ML model (or fall back to the legacy method) by considering whether the DL signal is transmitted with the MCS set based on a CSI lower than the CSI reported by the terminal.

II. Use Case 2: Beam Management

A method to improve the performance of beam management through AI/ML models can be proposed.

The terminal can perform beam management using an AI/ML model. Based on the performed beam management, the terminal can select a specific beam (Tx beam) for downlink reception and perform communication (receiving downlink data) through the specific beam.

In this specification, beam management may include a procedure for a terminal to select an optimal Tx beam of a base station for downlink reception.

The terminal can measure the quality of communication using the specific beam (e.g., the quality of the channel by the specific beam).

If the communication quality using the above-mentioned specific beam is maintained at a certain level or higher, there may not be a major problem even if the above-mentioned specific beam is not the optimal beam.

However, if the communication quality using the above-mentioned specific beam is below a certain level, it may be necessary to check whether beam management using the AI/ML model is being performed properly.

The terminal can periodically perform legacy beam management and perform performance evaluation of beam management using AI/ML models based on the results of legacy beam management.

In addition, if the distance moved by the terminal is greater than a certain level depending on whether the positioning of the terminal moves, a performance evaluation of beam management using the AI/ML model through the legacy beam management described above can be performed. If the performance evaluation of beam management using the AI/ML model through the legacy beam management is performed periodically according to a specific cycle, and if the distance moved by the terminal is greater than a certain level depending on whether the positioning of the terminal moves, a performance evaluation of beam management using the AI/ML model through the legacy beam management can be performed regardless of the cycle.

Performance evaluation of beam management using an AI/ML model through the aforementioned legacy beam management can be performed by comparing the results of the legacy beam management and the results of beam management using an AI/ML model.

Based on the signal-to-noise ratio (SNR), performance evaluation of beam management using AI/ML models can begin with the aforementioned legacy beam management. SNR can refer to the ratio of signal power to noise power. A higher SNR may indicate better signal quality.

If the SNR satisfies certain conditions, a performance evaluation of beam management using an AI/ML model through the aforementioned legacy beam management can be performed. For example, if an SNR-based evaluation is performed and certain conditions are met, a performance evaluation of beam management using an AI/ML model through legacy beam management can be performed.

The SNR-based evaluation related to the specific conditions of the aforementioned SNR is described below.

1. SNR-based evaluation

The terminal can perform beam management using an AI/ML model. Based on the performed beam management, the terminal can select a specific beam and perform communication using that specific beam. The terminal can measure the quality of communication using that specific beam (e.g., the quality of the channel through that specific beam). The quality may be SNR.

The terminal can measure the quality of the channel by the above specific beam multiple times.

If the SNR is above the threshold x, the current state can be maintained (no AI/ML model update (or fallback to legacy beam management)).

If the SNR is below the threshold x, the terminal can decide whether to update the AI/ML model (or fall back to legacy beam management) by:

- When the SNR becomes less than the threshold x (when the SNR measured by the terminal at time t#1 is less than the threshold x), the terminal can set the timer to T ₀ (initialize the timer to T ₀ ) and start running (counting down). The timer can continue to run (count down) only while the state in which the SNR is less than the threshold x continues.

- When the SNR is greater than or equal to the threshold x (when the SNR measured by the terminal at time t#2 after time t#1 is greater than or equal to the threshold x), the timer can be held without counting down with the timer initialized to T ₀ .

- If the SNR remains below the threshold x and the timer expires (all SNRs measured by the terminal while the timer is running are less than the threshold x), a performance evaluation can be performed. For example, if the SNR remains below the threshold x and the timer expires (all SNRs measured by the terminal while the timer is running are less than the threshold x), legacy beam management can be performed to determine whether to update the AI/ML model (or fall back to legacy beam management).

- Even while the above timer is running (counting down) (e.g., before the timer expires), if the terminal is located further than a distance threshold from the terminal's position at the time the timer is started, the terminal can determine whether to update the AI/ML model (or fall back to legacy beam management). For example, regardless of whether the timer is running, if the terminal's position is further than a distance threshold from the terminal's position at the time the timer is started, the terminal can determine whether to update the AI/ML model (or fall back to legacy beam management).

Here, the time T ₀ of the timer can be 0. In this case, if the SNR measured by the terminal is less than the threshold x (for example, if the SNR measured at least once among multiple measurements is less than the threshold x), the terminal can perform performance evaluation for the AI/ML model through legacy beam management described below without additional SNR measurement.

As mentioned above, if certain conditions are satisfied (all measured SNRs while the timer is running are less than the threshold x), a performance evaluation of beam management using an AI/ML model through legacy beam management can be performed. The performance evaluation of beam management using an AI/ML model through legacy beam management is described below.

2. Performance Evaluation of AI/ML Models through Legacy Beam Management

Executing legacy beam management may be used to determine whether to update the AI/ML model (or fall back to legacy beam management). For example, the performance of the current AI/ML model (whether it is functioning properly) can be evaluated based on the results of legacy beam management.

If the performance evaluation results of the AI/ML model determine that the current AI/ML model is poor (below a certain level) (if the current AI/ML model is determined to not work well), the terminal can determine whether to update the AI/ML model (or fall back to legacy beam management).

Evaluating the performance of an AI/ML model (checking whether the AI/ML model is working well) can be done as follows:

- Method #1: If the difference between the highest value (e.g., reception metric value of the best beam) among all DL Tx beams of the base station measured through legacy beam management (e.g., RSRP, RSRQ) and the reception metric value of the beam selected through the AI/ML model is less than or equal to a threshold value (T), the current AI/ML model may be determined to be operating normally (well-operating or not performing poorly). Conversely, if the difference exceeds the threshold value (T), the current AI/ML model may be determined to be not operating normally (not performing poorly). In this case, the terminal may update the AI/ML model for beam management or fallback to legacy beam management.

- Method #2: The terminal can determine N beams among all DL Tx beams of the base station measured through legacy beam management, which have good (or high) reception metrics (e.g., RSRP, RSRQ). If a specific beam of the base station selected through the current AI/ML model is one of the N beams, the current AI/ML model can be determined to be operating normally (well-operating or not poorly performing). Conversely, if a specific beam of the base station selected through the current AI/ML model does not belong to the N beams, the current AI/ML model can be determined to not be operating normally (poorly performing). In this case, the terminal can update the AI/ML model for beam management or fallback to legacy beam management.

If there is another way to evaluate the performance of the AI/ML model, that method can be applied.

The following drawings are intended to illustrate specific examples of the present specification. The names of specific devices and the names of specific signals, messages, and fields depicted in the drawings are provided for illustrative purposes only, and the technical features of this specification are not limited to the specific names used in the drawings.

FIG. 13 illustrates an example of a beam management related procedure based on channel quality according to the disclosure of the present specification.

Regarding the channel quality represented in Figure 13, the aforementioned SNR can be applied. Alternatively, other methods for channel quality can be applied. For example, RSRP or RSRQ can be used as a metric for channel quality.

The terminal can perform action A.

- Action A: The terminal can measure the quality of the channel through the beam it is currently using. The current timer can be set to T _0. If the measurement result is below the threshold, the new T ₀ is obtained by subtracting 1 from T ₀ .

Until T ₀ becomes 0, the terminal can repeatedly perform the above operation A.

When T ₀ becomes 0, the terminal can perform legacy beam management to perform performance evaluation for the current AI/ML model.

With regard to performance evaluation, the ‘Performance evaluation of AI/ML models through legacy beam management’ in Section 2 mentioned above can be applied.

As a result of the performance evaluation, if the performance is below a certain level, the terminal can update the current AI/ML model or fall back to legacy beam management.

The following drawings are intended to illustrate specific examples of the present specification. The names of specific devices and the names of specific signals, messages, and fields depicted in the drawings are provided for illustrative purposes only, and the technical features of this specification are not limited to the specific names used in the drawings.

FIG. 14 illustrates an example of a beam management related procedure based on terminal location according to the disclosure of this specification.

The contents of Fig. 14 can be performed in combination with the contents of Fig. 13.

The terminal can measure its own location. At this time, the measured location is A.

The terminal can measure its own position after a period T has elapsed. At this time, the measured position is B.

If the distance between A and B does not exceed the distance threshold, the terminal can measure its position after another period T. At this time, the measured position is C. After this, the terminal can determine whether the distance between C and B exceeds the distance threshold.

The terminal can measure its own position and determine whether its position change over the last period T exceeds a distance threshold.

If the change in its position during the last period T exceeds the distance threshold, the terminal can perform legacy beam management to perform performance evaluation for the current AI/ML model.

With regard to performance evaluation, the ‘Performance evaluation of AI/ML models through legacy beam management’ in Section 2 mentioned above can be applied.

As a result of the performance evaluation, if the performance is below a certain level, the terminal can update the current AI/ML model or fall back to legacy beam management.

To improve beam management through AI/ML, the following methods can be implemented:

- Methods and procedures for evaluating AI/ML model performance differently depending on the SNR environment

- Method and procedure for evaluating AI/ML model performance only when SNR is below a certain threshold.

- Method and procedure for utilizing positioning information when evaluating AI/ML model performance only when the SNR is below a certain threshold.

- Method and procedure for utilizing a timer when evaluating AI/ML model performance only when the SNR is below a certain threshold.

- Metrics for channel quality may include not only SNR but also RSRP or RSRQ.

III. Use Case 3: Positioning Accuracy Enhancement

A method to improve the accuracy of positioning through AI/ML models can be proposed.

The following drawings are intended to illustrate specific examples of the present specification. The names of specific devices and the names of specific signals, messages, and fields depicted in the drawings are provided for illustrative purposes only, and the technical features of this specification are not limited to the specific names used in the drawings.

FIG. 15 illustrates an example of a positioning accuracy evaluation procedure according to the disclosure of the present specification.

If the results of positioning through the AI/ML model are compared with those of legacy positioning techniques to ensure that they work well, positioning through the AI/ML model may not be necessary.

The terminal can evaluate the accuracy of positioning using the AI/ML model by performing a range measurement operation (ranging operation) between the terminal's position estimated through positioning using the AI/ML model and a known positioning unit, thereby verifying whether the measured distance is within an expected error level. This method allows the terminal to avoid using legacy positioning methods.

In the above-described range measurement operation (ranging operation), the terminal can determine whether it is in line of sight (LOS) with the known positioning unit. Only when the known positioning unit is in line of sight with the terminal, the terminal can evaluate the accuracy of positioning using the AI/ML model through the range measurement operation with the known positioning unit.

For example, the terminal can measure the distance (D1) by performing a ranging operation with a known positioning unit corresponding to LOS. The terminal can determine/calculate the distance (D2) between the terminal's location estimated through positioning using an AI/ML model and the known location of the known positioning unit. The terminal can evaluate the accuracy of the positioning using the AI/ML model by determining whether the difference between D1 and D2 (the absolute value of the value obtained by subtracting D2 from D1) is within the expected level of error.

If the difference between D1 and D2 is within the expected error level, the terminal can determine/determine that the AI/ML model has high accuracy (is functioning well). If the difference between D1 and D2 is greater than the expected error level, the terminal can determine/determine that the AI/ML model has low accuracy (is not functioning well).

The terminal can determine whether it is in line-of-sight (LOS) with the known positioning unit. If it is not in LOS, the terminal can perform the aforementioned operation (evaluating the accuracy of the AI/ML model through distance measurement) with another known positioning unit.

To improve the accuracy of positioning using AI/ML models, the following methods can be implemented:

- Methods and procedures for using distance measurement information as AI/ML model performance evaluation KPIs (Key Performance Indicators)

- Methods and procedures for utilizing LOS indicators when using distance measurement information as AI/ML model performance evaluation KPIs.

The following drawings are intended to illustrate specific examples of the present specification. The names of specific devices and the names of specific signals, messages, and fields depicted in the drawings are provided for illustrative purposes only, and the technical features of this specification are not limited to the specific names used in the drawings.

Figure 16 illustrates the UE's procedure for disclosure of this specification.

1. The UE (User Equipment) can perform AI beam management through an AI (Artificial Intelligence) model to select a specific beam of the base station for downlink reception.

2. The UE can measure the quality of the channel through the specific beam.

3. The UE can determine whether the result of the measurement is below a quality threshold.

4. Based on the result of the above measurement being below the quality threshold, the UE can perform legacy beam management.

5. Based on the results of the above legacy beam management, the UE can evaluate the performance of the AI beam management.

Based on the results of the above evaluation, the UE can update the AI model.

Based on the results of the above evaluation, the UE can perform fallback to the legacy beam management.

The steps by which the UE performs the legacy beam management are:

A step of the UE starting a timer based on the result of the above measurement being below the quality threshold;

While the timer is running, the UE measures the quality of the channel by the specific beam at least once;

The method may include a step of the UE performing the legacy beam management based on the result measured more than once being below the quality threshold.

The UE can determine the location of the UE at time point T1.

The UE can determine the location of the UE at time point T2.

The step of the UE performing the legacy beam management may be performed based on the location of the UE determined in the T1 and the location of the UE determined in the T2 being greater than or equal to a distance threshold.

The step of the UE performing the legacy beam management may be performed regardless of whether the result of the measurement is below the quality threshold.

The quality of the above channel and the quality threshold may be in terms of SNR (Signal-to-noise ratio).

The quality of the above channel and the quality threshold may be for Reference Signal Received Power (RSRP) or Reference Signal Received Quality (RSRQ).

Hereinafter, a device for performing communication according to some embodiments of the present specification will be described.

For example, a device may include a processor, a transceiver, and memory.

For example, a processor may be configured to be operatively coupled with memory and a processor.

The operations performed by the processor may include: a step in which a UE (User Equipment) performs AI beam management through an AI (Artificial Intelligence) model to select a specific beam of a base station for downlink reception; a step in which the UE measures the quality of a channel by the specific beam; a step in which the UE determines whether a result of the measurement is less than or equal to a quality threshold; a step in which the UE performs legacy beam management based on the result of the measurement being less than or equal to the quality threshold; and a step in which the UE evaluates the performance of the AI beam management based on a result of the legacy beam management.

Below, a processor of a device for providing communication according to some embodiments of the present specification is described.

The operations performed by the processor may include: a step in which a UE (User Equipment) performs AI beam management through an AI (Artificial Intelligence) model to select a specific beam of a base station for downlink reception; a step in which the UE measures the quality of a channel by the specific beam; a step in which the UE determines whether a result of the measurement is less than or equal to a quality threshold; a step in which the UE performs legacy beam management based on the result of the measurement being less than or equal to the quality threshold; and a step in which the UE evaluates the performance of the AI beam management based on a result of the legacy beam management.

Hereinafter, a non-volatile computer-readable medium storing one or more commands for providing mobile communication according to some embodiments of the present specification is described.

According to some embodiments of the present disclosure, the technical features of the present disclosure may be implemented directly in hardware, software executed by a processor, or a combination of the two. For example, a method performed by a wireless device in wireless communication may be implemented in hardware, software, firmware, or any combination thereof. For example, the software may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or other storage media.

Some examples of storage media are coupled to the processor, allowing the processor to read information from the storage media. Alternatively, the storage media may be integrated into the processor. The processor and storage media may reside in an ASIC. In other examples, the processor and storage media may reside as separate components.

Computer-readable media may include tangible and non-volatile computer-readable storage media.

For example, nonvolatile computer-readable media may include random access memory (RAM), such as synchronized dynamic random access memory (SDRAM), read-only memory (ROM), non-volatile random access memory (NVRAM), read-only memory (EEPROM), flash memory, magnetic or optical data storage media, or any other media that can be used to store instructions or data structures. Nonvolatile computer-readable media may also include combinations of the above.

Additionally, the methods described herein can be realized at least in part by a computer-readable communication medium that carries or transmits code in the form of instructions or data structures and that can be accessed, read, and/or executed by a computer.

According to some embodiments of the present disclosure, a non-transitory computer-readable medium has one or more instructions stored thereon. The one or more stored instructions can be executed by a processor of a base station.

The one or more stored commands may include: a step for a UE (User Equipment) to perform AI beam management through an AI (Artificial Intelligence) model to select a specific beam of a base station for downlink reception; a step for the UE to measure a quality of a channel by the specific beam; a step for the UE to determine whether a result of the measurement is less than or equal to a quality threshold; a step for the UE to perform legacy beam management based on the result of the measurement being less than or equal to the quality threshold; and a step for the UE to evaluate performance of the AI beam management based on a result of the legacy beam management.

Specifications can have a variety of effects.

For example, according to the disclosure of this specification, performance of AI/ML models may be improved.

The effects that can be achieved through specific examples of this specification are not limited to the effects listed above. For example, a person with ordinary skill in the relevant technical field may understand or derive various technical effects from this specification. Accordingly, the specific effects of this specification are not limited to those explicitly described herein, but may include various effects that can be understood or derived from the technical features of this specification.

The claims set forth in this specification may be combined in various ways. For example, the technical features of the method claims of this specification may be combined to implement a device, and the technical features of the device claims of this specification may be combined to implement a method. Furthermore, the technical features of the method claims and the technical features of the device claims of this specification may be combined to implement a device, and the technical features of the method claims and the technical features of the device claims of this specification may be combined to implement a method. Other implementations are within the scope of the claims.

Claims (11)

As a method, A step in which a UE (User Equipment) performs AI beam management through an AI (Artificial Intelligence) model to select a specific beam of a base station for downlink reception; A step in which the UE measures the quality of a channel by the specific beam; A step in which the UE determines whether the result of the measurement is below a quality threshold; A step in which the UE performs legacy beam management based on the result of the above measurement being below the quality threshold; A method comprising a step of the UE evaluating the performance of the AI beam management based on the results of the legacy beam management. In the first paragraph, A method further comprising a step of updating the AI model by the UE based on the results of the evaluation. In the first paragraph, A method further comprising a step of the UE performing fallback to the legacy beam management based on the results of the above evaluation. In any one of the first to third clauses, The steps by which the UE performs the legacy beam management are: A step of the UE starting a timer based on the result of the above measurement being below the quality threshold; While the timer is running, the UE measures the quality of the channel by the specific beam at least once; A method comprising a step of the UE performing the legacy beam management based on the result measured at least once being below the quality threshold. In any one of the claims 1 to 4, A step in which the UE determines the location of the UE at time point T1; The UE further comprises a step of determining the location of the UE at time point T2, The step of the UE performing the legacy beam management is: a method performed based on the location of the UE determined in the T1 and the location of the UE determined in the T2 being greater than or equal to a distance threshold. In paragraph 5, The step of the UE performing the legacy beam management is: a method performed regardless of whether the result of the measurement is below the quality threshold. In any one of claims 1 to 6, A method wherein the quality of the above channel and the quality threshold are for a signal-to-noise ratio (SNR). In any one of claims 1 to 6, The quality of the above channel and the quality threshold are for RSRP (Reference Signal Received Power) or RSRQ (Reference Signal Received Quality). As a UE (User Equipment), At least one transmitter and receiver; Contains at least one processor, The UE wherein the operation performed by at least one processor is a method according to any one of claims 1 to 8. As an apparatus in mobile communication, at least one processor; and At least one memory storing instructions and being operably electrically connected to at least one processor, A device wherein the operation performed based on the command being executed by at least one processor is a method according to any one of claims 1 to 8. A non-volatile computer-readable storage medium that records commands, A non-volatile computer-readable storage medium, wherein the instructions, when executed by one or more processors, cause the one or more processors to perform a method according to any one of claims 1 to 8.