Device and method for performing online learning in a wireless communication system

Abstract

The present disclosure relates to performing online learning in a wireless communication system, wherein a method performed by a terminal may include the steps of: transmitting a first message requesting information about a neighboring region; receiving a second message containing information about said neighboring region; performing an evaluation of at least one neighboring region based on the information about said neighboring region; and performing online learning for a channel task model based on the result of said evaluation. The online learning may be performed for at least some regions among said at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for said channel task model.

Description

Technology Field

[0001] The following description relates to a wireless communication system and to an apparatus and method for performing online learning in a wireless communication system. Background Technology

[0002] Wireless access systems are being widely deployed to provide various types of communication services, such as voice and data. Generally, a wireless access system is a multiple access system capable of supporting communication with multiple users by sharing available system resources (bandwidth, transmission power, etc.). Examples of multiple access systems include CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access) systems.

[0003] In particular, as many communication devices require large communication capacities, enhanced mobile broadband (eMBB) communication technology is being proposed as an improvement over existing radio access technology (RAT). Furthermore, communication systems are being proposed that consider not only massive machine type communications (mmTC), which connects multiple devices and objects to provide various services anytime and anywhere, but also services and user equipment (UE) that are sensitive to reliability and latency. Various technical configurations are being proposed to support this. The problem to be solved

[0004] The present disclosure may provide an apparatus and method for effectively performing online learning in a wireless communication system.

[0005] The present disclosure may provide an apparatus and method for assisting online learning of a channel task model in a wireless communication system.

[0006] The present disclosure may provide an apparatus and method for reducing the occurrence of out-of-distribution (OOD) of a channel task model in a wireless communication system.

[0007] The present disclosure may provide an apparatus and method for evaluating the OOD probability of a channel task model in a wireless communication system.

[0008] The present disclosure may provide an apparatus and method for signaling information related to OOD evaluation for at least one neighboring area in a wireless communication system.

[0009] The present disclosure may provide an apparatus and method for providing information related to the probability distribution of a channel for neighboring regions of a terminal in a wireless communication system.

[0010] The present disclosure may provide an apparatus and method for limiting neighboring regions subject to OOD evaluation in a wireless communication system.

[0011] The present disclosure may provide an apparatus and method for obtaining information for learning about at least one neighboring channel in a wireless communication system.

[0012] The present disclosure may provide an apparatus and method for generating sample data for learning about at least one neighboring channel in a wireless communication system.

[0013] The present disclosure may provide an apparatus and method for reducing the cost of online learning based on the mobility of a terminal in a wireless communication system.

[0014] The technical objectives to be achieved in this disclosure are not limited to those mentioned above, and other unmentioned technical problems may be considered by those skilled in the art to which the technical configuration of this disclosure applies, based on the embodiments of this disclosure described below. means of solving the problem

[0015] As an example of the present disclosure, a method performed by a terminal in a wireless communication system may include the steps of: transmitting a first message requesting information about a neighboring region; receiving a second message containing information about the neighboring region; performing an evaluation of at least one neighboring region based on the information about the neighboring region; and performing online learning for a channel task model based on the result of the evaluation. The online learning may be performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model.

[0016] As an example of the present disclosure, a terminal in a wireless communication system comprises a transceiver and a processor connected to the transceiver, wherein the processor transmits a first message requesting information about a neighboring region and receives a second message containing information about the neighboring region, performs an evaluation of at least one neighboring region based on the information about the neighboring region, and controls the performance of online learning for a channel task model based on the result of the evaluation, wherein the online learning may be performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model.

[0017] As an example of the present disclosure, a communication device comprises at least one processor and at least one computer memory connected to the at least one processor and storing instructions that direct operations as executed by the at least one processor, wherein the operations may include: transmitting a first message requesting information about a neighboring region; receiving a second message containing information about the neighboring region; performing an evaluation of at least one neighboring region based on the information about the neighboring region; and performing online learning for a channel task model based on the result of the evaluation. The online learning may be performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model.

[0018] As an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction comprises said at least one instruction executable by a processor, said at least one instruction, said at least one instruction, said at least one instruction, said at least one instruction, said device transmits a first message requesting information about a neighbor region, receives a second message containing information about said neighbor region, and controls the device to perform an evaluation of at least one neighbor region based on the information about said neighbor region, and to perform online learning for a channel task model based on the result of said evaluation, said online learning may be performed for at least some of said at least one neighbor region that is evaluated to have an out-of-distribution probability greater than a threshold for said channel task model.

[0019] The embodiments of the present disclosure described above are merely some of the preferred embodiments of the present disclosure, and various embodiments reflecting the technical features of the present disclosure can be derived and understood by those skilled in the art based on the detailed description of the present disclosure set forth below. Effects of the invention

[0020] The following effects may be achieved by embodiments based on the present disclosure.

[0021] According to the present disclosure, online learning can be effectively performed.

[0022] The effects obtainable from the embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by a person skilled in the art to which the technical configuration of the present disclosure applies from the description of the embodiments of the present disclosure below. That is, unintended effects resulting from implementing the configuration described in the present disclosure can also be derived by a person skilled in the art from the embodiments of the present disclosure. Brief explanation of the drawing

[0023] The drawings attached below are intended to aid in understanding the present disclosure and may provide embodiments of the present disclosure together with the detailed description. However, the technical features of the present disclosure are not limited to specific drawings, and features disclosed in each drawing may be combined with one another to form new embodiments. Reference numerals in each drawing may denote structural elements. FIG. 1 illustrates an example of a communication system applicable to the present disclosure. FIG. 2 illustrates an example of a wireless device applicable to the present disclosure. FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure. FIG. 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure. FIG. 5 illustrates an example of a communication structure that can be provided in a 6G (6th generation) system applicable to the present disclosure. FIG. 6 illustrates an electromagnetic spectrum applicable to the present disclosure. FIG. 7 illustrates a THz wireless communication transceiver applicable to the present disclosure. FIG. 8 illustrates a THz signal generation method applicable to the present disclosure. FIG. 9 illustrates a wireless communication transceiver applicable to the present disclosure. FIG. 10 illustrates a transmitter structure applicable to the present disclosure. FIG. 11 illustrates a modulator structure applicable to the present disclosure. FIG. 12 illustrates the structure of a perceptron included in an artificial neural network applicable to the present disclosure. FIG. 13 illustrates an artificial neural network structure applicable to the present disclosure. FIG. 14 illustrates an example of a functional framework for the application of artificial intelligence technology applicable to the present disclosure. FIG. 15 illustrates an example of a procedure for utilizing an artificial intelligence model applicable to the present disclosure. FIG. 16 illustrates another example of a procedure for utilizing an artificial intelligence model applicable to the present disclosure. FIG. 17 illustrates another example of a procedure for utilizing an artificial intelligence model applicable to the present disclosure. FIG. 18 illustrates an AI technology-based communication procedure applicable to the present disclosure. FIG. 19 illustrates an example of the movement of a terminal between different channel environments in a wireless communication system. Figure 20 illustrates an example of an adversarial generative neural network model that processes channel information. FIG. 21 illustrates the functional structures of devices in a wireless communication system according to one embodiment of the present disclosure. FIG. 22 illustrates an example of a procedure for performing online learning in a wireless communication system according to one embodiment of the present disclosure. FIG. 23 illustrates an example of a procedure for providing information for online learning in a wireless communication system according to one embodiment of the present disclosure. FIG. 24 illustrates an example of a procedure for performing online learning in response to out-of-distribution detection in a wireless communication system according to one embodiment of the present disclosure. FIG. 25 illustrates an example of a channel point map in a wireless communication system according to one embodiment of the present disclosure. FIG. 26 illustrates examples of candidate channel points in a wireless communication system according to one embodiment of the present disclosure. Specific details for implementing the invention

[0024] The following embodiments are combinations of the components and features of the present disclosure in a predetermined form. Each component or feature may be considered optional unless otherwise explicitly stated. Each component or feature may be implemented in a form not combined with other components or features. Additionally, some components and / or features may be combined to form embodiments of the present disclosure. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of any embodiment may be included in other embodiments, or may be replaced with corresponding components or features of other embodiments.

[0025] In the description of the drawings, procedures or steps that could obscure the gist of the present disclosure have not been described, nor have procedures or steps that are understandable to those skilled in the art been described.

[0026] Throughout the specification, when a part is described as "comprising" or "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...unit," and "module" as used in the specification refer to a unit that performs at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software. Additionally, "one (a or an)," "one," "the," and similar related terms may be used in the context describing the present disclosure (particularly in the context of the following claims) in both singular and plural forms, unless otherwise indicated in the specification or clearly contradicted by the context.

[0027] In this specification, the embodiments of the present disclosure are described with a focus on the data transmission and reception relationship between a base station and a mobile station. Here, the base station refers to a terminal node of a network that communicates directly with a mobile station. Specific operations described in this document as being performed by a base station may, in some cases, be performed by an upper node of the base station.

[0028] That is, in a network consisting of multiple network nodes including a base station, various operations performed for communication with a mobile station may be performed by the base station or other network nodes other than the base station. In this case, 'base station' may be replaced by terms such as fixed station, Node B, eNB (eNode B), gNB (gNode B), ng-eNB, advanced base station (ABS), or access point.

[0029] Additionally, in embodiments of the present disclosure, the term terminal may be replaced with terms such as user equipment (UE), mobile station (MS), subscriber station (SS), mobile subscriber station (MSS), mobile terminal, or advanced mobile station (AMS).

[0030] Furthermore, the transmitting end refers to a fixed and / or mobile node that provides data or voice services, and the receiving end refers to a fixed and / or mobile node that receives data or voice services. Therefore, in the case of the uplink, a mobile station can be the transmitting end and a base station can be the receiving end. Similarly, in the case of the downlink, a mobile station can be the receiving end and a base station can be the transmitting end.

[0031] Embodiments of the present disclosure may be supported by standard documents disclosed in at least one of the wireless access systems, such as IEEE 802.xx systems, 3GPP (3rd Generation Partnership Project) systems, 3GPP LTE (Long Term Evolution) systems, 3GPP 5G (5th generation) NR (New Radio) systems and 3GPP2 systems, and in particular, embodiments of the present disclosure may be supported by 3GPP TS (technical specification) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents.

[0032] In addition, the embodiments of the present disclosure may be applied to other wireless access systems and are not limited to the systems described above. For example, they may be applicable to systems applied after the 3GPP 5G NR system and are not limited to specific systems.

[0033] That is, obvious steps or parts not described in the embodiments of the present disclosure may be described by referring to the aforementioned documents. Additionally, all terms disclosed in this document may be explained by the aforementioned standard documents.

[0034] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the technical configuration of the present disclosure can be implemented.

[0035] Additionally, specific terms used in the embodiments of the present disclosure are provided to aid in understanding the present disclosure, and the use of such specific terms may be modified in other forms without departing from the technical spirit of the present disclosure.

[0036] The following technology can be applied to various wireless access systems such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access).

[0037] For the sake of clarity, the following description is based on 3GPP communication systems (e.g., LTE, NR, etc.), but the technical scope of this disclosure is not limited thereto. LTE may refer to technology from 3GPP TS 36.xxx Release 8 onwards. Specifically, LTE technology from 3GPP TS 36.xxx Release 10 onwards is referred to as LTE-A, and LTE technology from 3GPP TS 36.xxx Release 13 onwards may be referred to as LTE-A pro. 3GPP NR may refer to technology from TS 38.xxx Release 15 onwards. 3GPP 6G may refer to technology from TS Release 17 and / or Release 18 onwards. "xxx" indicates a specific standard document number. LTE / NR / 6G may be collectively referred to as 3GPP systems.

[0038] Regarding the background technology, terms, abbreviations, etc. used in this disclosure, reference may be made to standard documents published prior to this disclosure. For example, reference may be made to standard documents 36.xxx and 38.xxx.

[0039] Communication systems applicable to the present disclosure

[0040] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods, and / or flowcharts of the disclosure disclosed in this document may be applied to various fields requiring wireless communication / connection (e.g., 5G) between devices.

[0041] Examples are provided in more detail below with reference to the drawings. In the following drawings and descriptions, the same reference numerals may represent the same or corresponding hardware blocks, software blocks, or function blocks unless otherwise described.

[0042] FIG. 1 illustrates an example of a communication system to which the present disclosure applies.

[0043] Referring to FIG. 1, the communication system (100) to which the present disclosure applies includes a wireless device, a base station, and a network. Here, the wireless device refers to a device that performs communication using wireless access technology (e.g., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, the wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (extended reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Thing) device (100f), and an AI (artificial intelligence) device / server (100g). For example, the vehicle may include a vehicle equipped with wireless communication capabilities, an autonomous vehicle, a vehicle capable of performing inter-vehicle communication, etc. Here, the vehicle (100b-1, 100b-2) may include an unmanned aerial vehicle (UAV) (e.g., a drone). The XR device (100c) includes an augmented reality (AR) / virtual reality (VR) / mixed reality (MR) device and may be implemented in the form of a head-mounted device (HMD), a head-up display (HUD) equipped in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, digital signage, a vehicle, a robot, etc. The portable device (100d) may include a smartphone, a smartpad, a wearable device (e.g., a smartwatch, smart glasses), a computer (e.g., a laptop, etc.). The home appliance (100e) may include a TV, a refrigerator, a washing machine, etc. The IoT device (100f) may include a sensor, a smart meter, etc.For example, the base station (120) and network (130) may also be implemented as wireless devices, and a specific wireless device (120a) may act as a base station / network node to other wireless devices.

[0044] Wireless devices (100a to 100f) can be connected to a network (130) through a base station (120). AI technology may be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (100g) through the network (130). The network (130) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, or a 6G network. The wireless devices (100a to 100f) may communicate with each other through the base station (120) / network (130), but may also communicate directly (e.g., sidelink communication) without going through the base station (120) / network (130). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle to vehicle) / V2X (vehicle to everything) communication). Also, an IoT device (100f) (e.g., a sensor) can communicate directly with another IoT device (e.g., a sensor) or other wireless devices (100a to 100f).

[0045] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a to 100f) / base station (120) and between base station (120) / base station (120). Here, wireless communication / connection can be established through various wireless access technologies such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D communication), and communication between base stations (150c) (e.g., relay, IAB (integrated access backhaul)). Through wireless communication / connection (150a, 150b, 150c), wireless devices and base stations / wireless devices, and base stations and base stations 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, based on the various proposals of the present disclosure, at least some of the following may be performed: a process for setting various configuration information for transmitting / receiving wireless signals, a process for various signal processing (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), a resource allocation process, etc.

[0046] Devices applicable to the present disclosure

[0047] FIG. 2 illustrates an example of a wireless device that can be applied to the present disclosure.

[0048] Referring to FIG. 2, the wireless device (200) can transmit and receive wireless signals through various wireless access technologies (e.g., LTE, LTE-A, LTE-A pro, NR, 5G, 5G-A, 6G). The wireless device (200) includes at least one processor (202) and at least one memory (204), and may additionally include at least one transceiver (206) and / or at least one antenna (208).

[0049] The processor (202) controls the memory (204) and / or the transceiver (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or sequences of operation disclosed in this document. For example, the processor (202) may process information within the memory (204) to generate a first information / signal and then transmit a wireless signal containing the first information / signal through the transceiver (206). Additionally, the processor (202) may receive a wireless signal containing a second information / signal through the transceiver (206) and then store information obtained from the signal processing of the second information / signal in the memory (204). The memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, memory (204) may store software code containing instructions for performing some or all of the processes controlled by the processor (202) or for performing the descriptions, functions, procedures, proposals, methods, and / or sequences of operations disclosed in this document. Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology. A transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals through at least one antenna (208). The transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeable with a radio frequency (RF) unit. In this disclosure, a wireless device may mean a communication modem / circuit / chip.

[0050] Hereinafter, hardware elements of the wireless device (200) will be described in more detail. Although not limited thereto, at least one protocol layer may be implemented by at least one processor (202). For example, at least one processor (202) may implement at least one layer (e.g., functional layers such as PHY (physical), MAC (media access control), RLC (radio link control), PDCP (packet data convergence protocol), RRC (radio resource control), and SDAP (service data adaptation protocol). At least one processor (202) may generate at least one PDU (Protocol Data Unit) and / or at least one SDU (service data unit) according to the descriptions, functions, procedures, proposals, methods and / or operation sequences disclosed in this document. At least one processor (202) may generate messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods and / or operation sequences disclosed in this document. At least one processor (202) may generate a signal (e.g., baseband signal) including a PDU, SDU, message, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this document and provide it to at least one transceiver (206). At least one processor (202) may receive a signal (e.g., baseband signal) from at least one transceiver (206) and may obtain a PDU, SDU, message, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this document.

[0051] At least one processor (202) may be referred to as a controller, microcontroller, microprocessor, or microcomputer. At least one processor (202) may be implemented by hardware, firmware, software, or a combination thereof. For example, at least one application-specific integrated circuit (ASIC), at least one digital signal processor (DSP), at least one digital signal processing device (DSPD), at least one programmable logic device (PLD), or at least one field programmable gate array (FPGA) may be included in at least one processor (202). The descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this document may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. Firmware or software configured to perform the descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this document may be included in at least one processor (202) or stored in at least one memory (204) and driven by at least one processor (202). The descriptions, functions, procedures, proposals, methods, and / or flowcharts disclosed in this document may be implemented using firmware or software in the form of code, instructions, and / or sets of instructions.

[0052] At least one memory (204) may be connected to at least one processor (202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. At least one memory (204) may be composed of ROM (read-only memory), RAM (random access memory), EPROM (erasable programmable read-only memory), flash memory, hard drive, registers, cache memory, computer read storage media, and / or combinations thereof. At least one memory (204) may be located inside and / or outside of at least one processor (202). Additionally, at least one memory (204) may be connected to at least one processor (202) via various technologies, such as wired or wireless connections.

[0053] At least one transceiver (206) may transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or operation flowcharts, etc. of this document to at least one other device. At least one transceiver (206) may receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or operation flowcharts, etc. disclosed in this document from at least one other device. For example, at least one transceiver (206) may be connected to at least one processor (202) and may transmit and receive wireless signals. For example, at least one processor (202) may control at least one transceiver (206) to transmit user data, control information, or wireless signals to at least one other device. Additionally, at least one processor (202) may control at least one transceiver (206) to receive user data, control information, or wireless signals from at least one other device. Additionally, at least one transceiver (206) may be connected to at least one antenna (208), and at least one transceiver (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 operation sequence diagrams disclosed in this document through at least one antenna (208). In this document, at least one antenna may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports). At least one transceiver (206) may convert the received 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 at least one processor (202). At least one transceiver (206) may convert the processed user data, control information, wireless signals / channels, etc., from baseband signals to RF band signals using at least one processor (202).To this end, at least one transceiver (206) may include an (analog) oscillator and / or filter.

[0054] The components of the wireless device described with reference to FIG. 2 may be referred to by other terms in terms of their function. For example, the processor (202) may be referred to as the control unit, the transceiver (206) as the communication unit, and the memory (204) as the storage unit. In some cases, the communication unit may be used to mean at least a part of the processor (202) and the transceiver (206).

[0055] The structure of the wireless device described with reference to FIG. 2 can be understood as the structure of at least part of various devices. For example, the structure of the wireless device exemplified in FIG. 2 may be at least part of the various devices described with reference to FIG. 1 (e.g., robot (100a), vehicle (100b-1, 100b-2), XR device (100c), portable device (100d), home appliance (100e), IoT device (100f), AI device / server (100g)). Furthermore, according to various embodiments, the device may include other components in addition to the components exemplified in FIG. 2.

[0056] For example, the device may be a portable device such as a smartphone, smartpad, wearable device (e.g., smart watch, smart glasses), or portable computer (e.g., laptop, etc.). In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an interface unit that includes at least one port for connection with another device (e.g., audio input / output port, video input / output port), and an input / output unit for inputting and outputting video information / signals, audio information / signals, data, and / or information input by a user.

[0057] For example, the device may be a mobile device such as a mobile robot, vehicle, train, manned / unmanned aerial vehicle (AV), or ship. In this case, the device may further include at least one of a drive unit comprising at least one of an engine, motor, power train, wheel, brake, and steering device of the device; a power supply unit that supplies power and includes a wired / wireless charging circuit, battery, etc.; a sensor unit that senses state information, environmental information, and user information of the device or its surroundings; an autonomous driving unit that performs functions such as path maintenance, speed control, and destination setting; and a position measurement unit that acquires position information of the moving body through a GPS (global positioning system) and various sensors.

[0058] For example, the device may be an XR device such as an HMD, a HUD (head-up display) equipped in a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, digital signage, a vehicle, a robot, etc. In this case, the device may further include at least one of a power supply unit that supplies power and includes a wired / wireless charging circuit, a battery, etc., an input / output unit that acquires control information, data, etc. from the outside and outputs a generated XR object, and a sensor unit that senses state information, environment information, and user information of the device or the surroundings of the device.

[0059] For example, the device may be a robot that can be classified into industrial, medical, household, military, etc., depending on the purpose or field of use. In this case, the device may further include at least one of a sensor unit that senses state information, environmental information, and user information of the device or its surroundings, and a drive unit that performs various physical actions, such as moving robot joints.

[0060] For example, the device may be an AI device such as a TV, projector, smartphone, PC, laptop, digital broadcasting terminal, tablet PC, wearable device, set-top box (STB), radio, washing machine, refrigerator, digital signage, robot, vehicle, etc. In this case, the device may further include at least one of an input unit that acquires various types of data from the outside, an output unit that generates output related to sight, hearing, or touch, a sensor unit that senses state information, environmental information, and user information of the device or its surroundings, and a training unit that learns a model composed of an artificial neural network using training data.

[0061] The structure of the wireless device illustrated in FIG. 2 can be understood as part of a RAN node (e.g., base station, DU, RU, RRH, etc.). That is, the device illustrated in FIG. 2 may be a RAN node. In this case, the device may further include a wired transceiver for front haul and / or back haul communication. However, if the front haul and / or back haul communication is based on wireless communication, at least one transceiver (206) illustrated in FIG. 2 is used for front haul and / or back haul communication, and the wired transceiver may not be included.

[0062] FIG. 3 illustrates a method for processing a transmission signal applicable to the present disclosure. For example, the transmission signal may be processed by a signal processing circuit. In this case, the signal processing circuit (300) may include a scrambler (310), a modulator (320), a layer mapper (330), a precoder (340), a resource mapper (350), and a signal generator (360). In this case, for example, the operation / function of FIG. 3 may be performed in the processor (202) and / or transceiver (206) of FIG. 2. Also, for example, the hardware elements of FIG. 3 may be implemented in the processor (202) and / or transceiver (206) of FIG. 2. For example, blocks 310 to 360 may be implemented in the processor (202) of FIG. 2. Additionally, blocks 310 to 350 may be implemented in the processor (202) of FIG. 2, and block 360 may be implemented in the transceiver (206) of FIG. 2, and are not limited to the embodiments described above.

[0063] A codeword can be converted into a wireless signal through the signal processing circuit (300) of FIG. 3. Here, the codeword is an encoded bit sequence of an information block. The information block may include a transmission block (e.g., UL-SCH transmission block, DL-SCH transmission block). The wireless signal may be transmitted through various physical channels (e.g., PUSCH, PDSCH). Specifically, the codeword can be converted into a scrambled bit sequence by a scrambler (310). The scrambled sequence used for scrambling is generated based on an initialization value, which may include ID information of the wireless device, etc. The scrambled bit sequence may be modulated into a modulation symbol sequence by a modulator (320). The modulation method may include pi / 2-BPSK (pi / 2-binary phase shift keying), m-PSK (m-phase shift keying), m-QAM (m-quadrature amplitude modulation), etc.

[0064] A complex modulation symbol sequence can be mapped to at least one transmission layer by a layer mapper (330). The modulation symbols of each transmission layer can be mapped to the corresponding antenna port(s) by a precoder (340). The output z of the precoder (340) can be obtained by multiplying the output y of the layer mapper (330) by an N×M precoding matrix W, where N is the number of antenna ports and M is the number of transmission layers. Here, the precoder (340) can perform precoding after performing transform precoding (e.g., a discrete Fourier transform (DFT)) on the complex modulation symbols. Alternatively, the precoder (340) can perform precoding without performing transform precoding.

[0065] A resource mapper (350) can map the modulation symbols of each antenna port to a time-frequency resource. The time-frequency resource may include multiple symbols (e.g., CP-OFDMA symbols, DFT-s-OFDMA symbols) in the time domain and multiple subcarriers in the frequency domain. A signal generator (360) generates a radio signal from the mapped modulation symbols, and the generated radio signal can be transmitted to another device through each antenna. To this end, the signal generator (360) may include an inverse fast Fourier transform (IFFT) module, a cyclic prefix (CP) inserter, a digital-to-analog converter (DAC), a frequency uplink converter, etc.

[0066] The signal processing process for a received signal in a wireless device can be configured as the inverse of the signal processing process (310 to 360) of FIG. 3. For example, a wireless device (e.g., 200 in FIG. 2) can receive a wireless signal from the outside through an antenna port / transceiver. The received wireless signal can be converted into a baseband signal through a signal restorer. To this end, the signal restorer may include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Subsequently, the baseband signal can be restored into a codeword through a resource de-mapper process, a postcoding process, a demodulation process, and a de-scrambling process. The codeword can be restored into the original information block through decoding. Accordingly, a signal processing circuit (not shown) for a received signal may include a signal restorer, a resource de-mapper, a postcoder, a demodulator, a de-scrambler, and a decoder.

[0067] FIG. 4 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure. FIG. 4 illustrates the operation of a terminal (410) and a base station (420) transmitting and / or receiving data, and the operation performed prior to this.

[0068] Referring to FIG. 4, in step 401, the terminal (410) and the base station (420) perform synchronization. For example, the terminal (410) performs an initial cell search operation. Specifically, the terminal (410) can detect at least one synchronization signal transmitted from the base station (420) according to a predefined rule. Here, the synchronization signal may include a plurality of synchronization signals (e.g., primary synchronization signal, secondary synchronization signal) classified according to structure or use. Through this, the terminal (410) can identify the boundaries of the frame, subframe, slot, and / or symbol of the base station (420) and obtain information about the base station (420) (e.g., cell identifier).

[0069] In step 403, the terminal (410) obtains system information transmitted from the base station (420). The system information is information related to the attributes, characteristics, and / or capabilities of the base station (420) required to connect to the base station (420) and use the service, and can be classified according to content (e.g., whether it is essential for connection), transmission structure (e.g., channel used, whether it is provided on-demand), etc., and can be classified, for example, into a master information block (MIB) and a system information block (SIB). If necessary, the terminal (410) may transmit a signal requesting the system information prior to receiving the system information. However, the request and provision of the system information may be performed after the random access procedure described later.

[0070] In step 405, the terminal (410) and the base station (420) perform a random access procedure. The terminal (410) may transmit and / or receive at least one message for the random access procedure (e.g., random access preamble, RAR (random access response) message, etc.) based on information related to the random access channel of the base station (420) obtained through system information (e.g., channel location, channel structure, structure of supported preamble, etc.). For example, the terminal (410) may transmit a preamble (e.g., MSG1) through the random access channel, receive a RAR message (e.g., MSG2), transmit a message (e.g., MSG3) containing information related to the terminal (410) (e.g., identification information) to the base station (420) using scheduling information included in the RAR message, and receive a message (e.g., MSG4) for contention resolution and / or connection establishment. As another example, MSG1 and MSG3 can be transmitted and received as a single message, or MSG2 and MSG4 can be transmitted and received as a single message.

[0071] In step 407, the terminal (410) and the base station (420) perform signaling of control information. Here, the control information may be defined in various layers, such as a layer that controls the connection (e.g., a radio resource control (RRC) layer), a layer that handles mapping between logical channels and transmission channels (e.g., a media access control (MAC) layer), and a layer that handles physical channels (e.g., a physical (PHY) layer). For example, the terminal (410) and the base station (420) may perform at least one of signaling to establish a connection, signaling to determine settings related to communication, and signaling to indicate allocated resources.

[0072] In step 409, the terminal (410) and the base station (420) transmit and / or receive data. That is, the terminal (410) and the base station (420) can process, transmit and / or receive data based on the signaling of control information. For example, when transmitting data, the terminal (410) or the base station (420) may perform at least one of channel encoding, rate matching, scrambling, constellation mapping, layer mapping, waveform modulation, antenna mapping, and resource mapping on the information bits. Conversely, when receiving data, the terminal (410) or the base station (420) may perform at least one of signal extraction from resources, antenna-specific waveform demodulation, signal placement considering layer mapping, constellation demapping, descrambling, and channel decoding.

[0073] 6G communication systems and core implementation technologies of 6G systems

[0074] 5G systems define various operating bands within FR1 (frequency range 1), which includes 410 MHz to 7125 MHz, and FR2 (frequency range 2), which includes 24,250 MHz to 71,000 MHz. Various frequencies are being discussed as operating bands for subsequent 6G systems, and the use of frequencies higher than those of 5G systems is also being considered for wider bandwidth and higher transmission speeds. As one example, the use of the THz (Terahertz) frequency band, which includes approximately 100 GHz to 10 THz, is being discussed. The THz frequency band is a band that possesses both the penetrability of radio waves and the directivity of optical waves, and communication using the THz frequency band is expected to play a transitional role from existing radio-based communication to optical-based communication.

[0075] 6G systems utilizing the THz frequency band as described above aim for: i) very high data rates per device, ii) a very large number of connected devices, iii) global connectivity, iv) very low latency, v) reduced energy consumption of battery-free IoT devices, vi) ultra-reliable connectivity, and vii) connected intelligence with machine learning capabilities. The vision of 6G systems can be four aspects, such as "intelligent connectivity," "deep connectivity," "holographic connectivity," and "ubiquitous connectivity," and 6G systems can be designed to satisfy requirements such as those shown in [Table 1] below.

[0076] Per device peak data rate 1 Tbps E2E latency 1 ms Maximum spectral efficiency 100 bps / Hz Mobility support up to 1000 km / hr Satellite integration Fully AI Fully Autonomous vehicle Fully XR Fully Haptic Communication Fully

[0077] At this time, the 6G system may have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLC), massive machine type communications (mMTC), AI integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security. FIG. 5 illustrates an example of a communication structure that can be provided by a 6G system applicable to the present disclosure. Referring to FIG. 5, the 6G system is expected to have simultaneous wireless communication connectivity 50 times higher than that of a 5G wireless communication system. URLLC, a key feature of 5G, is expected to become an even more dominant technology in 6G communication by providing end-to-end latency of less than 1ms. In this case, 6G systems will have much better volumetric spectral efficiency than the frequently used area-spectral efficiency. 6G systems can provide very long battery life and advanced battery technology for energy harvesting, so mobile devices in 6G systems may not need to be charged separately.

[0078] As core implementation technologies for 6G systems, technologies such as artificial intelligence (AI), THz (Terahertz) communication, optical wireless technology, FSO backhaul network, massive MIMO technology, blockchain, 3D networking, quantum communication, unmanned aerial vehicles, cell-free communication, wireless information and energy transfer (WIET), integration of sensing and communication, integration of access backhaul networks, holographic beamforming, big data analysis, and large intelligent surface (LIS) can be adopted.

[0079] For example, THz communication is a communication that utilizes a spectrum in a frequency band between 0.1 THz and 10 THz with a corresponding wavelength in the range of 0.03 mm to 3 mm as shown in FIG. 6, and can be implemented using circuit elements with a structure as shown in FIG. 7. Additionally, optical wireless technology is a technology that generates and modulates THz signals using optical elements, and can be implemented based on a device with a structure as shown in FIG. 8, FIG. 9, FIG. 10, and FIG. 11.

[0080] In addition, AI can be implemented based on various models, such as neural networks and machine learning models. For example, an AI model with a neural network structure can be based on the structure of a perceptron as shown in Fig. 12. Referring to Fig. 12, an artificial neural network can be composed of multiple perceptrons. Depending on the structure of the perceptron, input vector x={x1, x2, If { , xd} is input, weights {W1, W2,} are assigned to each component. {Wd} is multiplied, and after the results are all summed, the activation function σ(·) is applied. If the large artificial neural network structure is an extension of the simplified perceptron structure shown in Fig. 12, the input vector can be applied to different multi-dimensional perceptrons. When perceptrons are stacked, a neural network having an input layer, a hidden layer, and an output layer as shown in Fig. 13 can be constructed.

[0081] AI technology utilizing the structure of a neural network as described above can be operated based on a functional framework such as that shown in FIG. 14. FIG. 14 illustrates an example of a functional framework for the application of AI technology applicable to the present disclosure. First, a data collection block (1410) generates training data (1411) and / or inference data (1411) containing processed input data by performing data preparation on input data collected from objects (e.g., UE, RAN node, network node, etc.). A model training block (1420) performs training on an AI model using the training data (1411) and provides information about the trained model to a model inference block (1430). A model inference block (1430) generates an output (1416) by performing inference and / or prediction using the inference data (1411). Additionally, the model inference block (1430) may provide model performance feedback (1414) to the model training block (1420). Here, the output (1416) refers to the inference output of the AI ​​model generated by the model inference block (1430), and the details of the inference output may vary depending on the use case. The actor block (1440) triggers or performs a specified task / action based on the output (1416). The actor block (1440) may trigger a task / action for another object (e.g., at least one UE, at least one RAN node, at least one network node, etc.) or for itself. Any one of the functions exemplified in FIG. 14 described above may be performed by two or more entities among the RAN, network node, network operator's OAM, or UE in collaboration. This may be referred to as a split AI operation.

[0082] FIG. 15 illustrates an example of a procedure for utilizing an AI model applicable to the present disclosure. FIG. 15 illustrates a case where a model training function (e.g., the function of the model training block (1420)) is included in a network node, and a model inference function (e.g., the function of the model inference block (1430)) is included in a RAN node. Referring to FIG. 15, in step 1, RAN node 1 and RAN node 2 transmit input data (e.g., training data) for training an AI model to a network node. Here, RAN node 1 and RAN node 2 may also transmit data collected from a UE (e.g., UE measurements related to RSRP, RSRQ, SINR of a serving cell and neighboring cells, UE location, velocity, etc.) to the network node. In step 2, the network node trains the AI ​​model using the received training data. In step 3, the network node distributes / updates the AI ​​model to RAN node 1 and / or RAN node 2. RAN Node 1 and / or RAN Node 2 may continue to perform model training based on the received AI model. In this procedure, it is assumed that the AI ​​model is distributed / updated only to RAN Node 1. In Step 4, RAN Node 1 receives input data (e.g., inference data) for AI model inference from the UE and RAN Node 2. In Step 5, RAN Node 1 generates output data (e.g., prediction or decision) by performing AI model-based inference using the received inference data. In Step 6, if applicable, RAN Node 1 may transmit model performance feedback to network nodes. In Step 7, RAN Node 1, RAN Node 2, and the UE (or 'RAN Node 1 and UE', or 'RAN Node 1 and RAN Node 2') perform an action based on the output data. For example, in the case of a load balancing action, the UE may move from RAN Node 1 to RAN Node 2.In step 8, RAN node 1 and RAN node 2 send feedback information to the network node.

[0083] FIG. 16 illustrates another example of a procedure for utilizing an AI model applicable to the present disclosure. FIG. 16 illustrates a case where a model training function (e.g., the function of the model training block (1420)) and a model inference function (e.g., the function of the model inference block (1430)) are included in a RAN node. Referring to FIG. 16, in step 1, the UE and RAN node 2 transmit input data (e.g., training data) for training an AI model to RAN node 1. In step 2, RAN node 1 trains the AI ​​model using the received training data. In step 3, RAN node 1 receives input data (e.g., inference data) for AI model-based inference from the UE and RAN node 2. In step 4, RAN node 1 generates output data (e.g., prediction or decision) by performing AI model-based inference using the received inference data. In step 5, RAN Node 1, RAN Node 2, and UE (or 'RAN Node 1 and UE', or 'RAN Node 1 and RAN Node 2') perform actions based on the output data. For example, in the case of a load balancing action, a UE may move from RAN Node 1 to RAN Node 2. In step 6, RAN Node 2 transmits feedback information to RAN Node 1.

[0084] FIG. 17 illustrates another example of a procedure for utilizing an AI model applicable to the present disclosure. FIG. 17 illustrates a case where a model training function (e.g., the function of the model training block (1420)) is included in a RAN node, and a model inference function (e.g., the function of the model inference block (1430)) is included in a UE. Referring to FIG. 17, in step 1, the UE transmits input data (e.g., training data) for training an AI model to a RAN node. Here, the RAN node may collect data from various UEs and / or other RAN nodes. In step 2, the RAN node trains the AI ​​model using the received training data. In step 3, the RAN node distributes / updates the AI ​​model to the UE. The UE may continue to perform model training based on the received AI model. In step 4, input data (e.g., inference data) for AI model-based inference is received from the UE, the RAN node, and / or other UEs. In Step 5, the UE generates output data (e.g., prediction or decision) by performing AI model-based inference using the received inference data. In Step 6, if applicable, the UE may transmit model performance feedback to the RAN node. In Step 7, the UE and the RAN node perform actions based on the output data. In Step 8, the UE transmits feedback information to the RAN node.

[0085] In accordance with the aforementioned framework and procedure, an AI model can be trained and utilized in a wireless communication system. In the aforementioned framework and procedure, various data such as input data, training data, and inference data have been introduced, and the specific details of the aforementioned data may vary depending on the task in which the AI ​​model is utilized. For example, information used in the various embodiments of the present disclosure described below may be included in the aforementioned data.

[0086] FIG. 18 illustrates an AI technology-based communication procedure applicable to the present disclosure. The detailed procedures illustrated in FIG. 18 may be combined with various embodiments of the present disclosure described below. For example, data generated according to various embodiments of the present disclosure may be used for operations (e.g., setup, training, inference, and / or data transmission / reception) in at least one of the detailed procedures illustrated in FIG. 18. As another example, the result of the inference illustrated in FIG. 18 may be used to transmit and / or receive data according to various embodiments of the present disclosure.

[0087] Referring to FIG. 18, in step 1801, at least one of the UE (1810), RAN node (1820), and network node (1830) performs an initial connection procedure. For example, in this step, at least one of an initial cell search operation, a system information acquisition operation, a random access operation, and a registration operation may be performed. In step 1803, at least one of the UE (1810), RAN node (1820), and network node (1830) performs a configuration procedure. Through the configuration procedure, parameters, resources, connections, and / or entities necessary to perform subsequent procedures at layers between the UE (1810) and the RAN node (1820) and / or at least one layer between the UE (1810) and the network node (1830) may be determined and / or created. At this time, the configuration procedure may be performed based on information, status, and / or characteristics of the AI ​​model used for subsequent training and inference.

[0088] In step 1805, at least one of the UE (1810), RAN node (1820), and network node (1830) performs a model training procedure. At least one of the UE (1810), RAN node (1820), and network node (1830) may collect training data and perform training using the training data. For example, the model training procedure may be performed as described with reference to FIG. 15, FIG. 16, or FIG. 17. If an offline trained model is used, this step may be omitted.

[0089] In step 1807, at least one of the UE (1810), RAN node (1820), and network node (1830) performs a task using a trained model. That is, the task may be performed by the result of inference and / or prediction using the trained model. For example, the task may be a procedure belonging to a communication protocol, a preliminary operation for subsequent data transmission and / or reception, related to data transmission and / or reception, or related to data processing (e.g., encoding, decoding, etc.).

[0090] In step 1809, at least one of the UE (1810), RAN node (1820), and network node (1830) transmits and / or receives data. At this time, the result of the task performed in step 1807 may be used. In some cases, the task performed in step 1807 may include the transmission and / or reception of data, in which case this step may be omitted as it is part of step 1807.

[0091] Specific embodiments of the present disclosure

[0092] The present disclosure relates to a method for performing online learning in a wireless communication system, specifically, to acquiring data for online learning by considering the probability of experiencing a new environment that has not been learned, and to performing learning on a channel task model.

[0093] task is input Output from mapping function to It learns and outputs. If this mapping is implemented as a machine learning model, the joint probability of the input and output data A dataset with is an AI / ML model Setting value based on Used for training, and AI / ML models It can provide an output for the input. The task is a loss function having It can be expressed as. Also, the two tasks are the same model Even if you use If the distribution changes, it can be distinguished as different tasks. A task can be defined by only one stationary distribution. The data distribution may change as time or certain steps continuously change. In this case, The task that changes by It can be expressed as.

[0094] In physical layer mobile communication, a set of channel-dependent transmit and receive operations can be defined as a "channel task"—an AI / ML term—from the perspective of data-driven machine learning. As mentioned above, channel tasks can be classified into regression and classification; tasks where a machine learning model infers continuous values ​​belong to regression, while tasks where it infers discrete values ​​belong to classification. For example, channel tasks related to regression may include channel estimation, synchronization capture and tracking, beam tracing, and CSI (channel state information) prediction. Additionally, channel tasks related to classification may include tasks that distinguish classes, such as the estimation of RI (rank indicator), CQI (channel quality indicator), and PMI (precoding matrix indicator), MCS (modulation and coding scheme) detection, and beam index detection. These aspects may vary slightly depending on the requirements and design of the communication core system. Channel Task , at, It may be at least one of physical layer signals such as a reference signal, a synchronization signal, and a data signal.

[0095] Unlike existing methods based on mathematical models, the approach to performing channel tasks using AI / ML models relies on data. That is, AI / ML models are trained and utilized based on large-scale training data. Physical layer tasks primarily involve operations to overcome the radio channel between the base station and the terminal. For example, when the base station transmits CSI-RS, the terminal receives it and can train and utilize a deep neural network based on the received CSI-RS data to characterize the radio channel.

[0096] However, if the terminal encounters an untrained communication channel environment as it moves, performance will degrade. In particular, terminals with limited memory and computational capacity have deep neural networks of limited complexity, so there is a high probability that they will encounter new channel distributions that have never been learned due to movement. When a deep neural network encounters such new channels, it may cause a degradation in communication quality, such as data truncation. This problem can be detected as a decrease in SNR (signal to noise ratio), BER (bit error rate), SER (symbol error rate), and BER (block error rate) while performing physical layer tasks. The aforementioned problem may occur in a situation such as that shown in Fig. 19.

[0097] FIG. 19 illustrates an example of a terminal moving between different channel environments in a wireless communication system. Referring to FIG. 19, the terminal (1910) moves within the coverage areas of base stations (1910-1 to 1910-5). Accordingly, the terminal (1910) moves sequentially through regions corresponding to the channel task T0 region to T4 region. In the example of FIG. 19, each region may have a probability distribution of a different channel. For example, the channel task is a physical layer task directly or indirectly related to the channel, and may deal with beam index prediction or classification problems. In the case of the beam index prediction problem, as a new beam index is added while moving from the T0 region to the T1 region, the channel environment changes due to the appearance of the new beam index, and this can be understood as a different task.

[0098] The problem of predicting the external distribution of channel tasks

[0099] Data distribution of the channel environment experienced by the terminal As the distribution continues to change, a phenomenon may occur where the AI / ML model forgets what it has learned or performs worse than a certain level in a new distribution. This phenomenon is called out-of-distribution (OOD). Conversely, when the AI / ML model learns the distribution well or does not forget it, it is called in-distribution (IND). The determination of out-of-distribution and in-distribution depends not only on changes in the channel environment distribution but also on how well the AI / ML model responds. In other words, the determination of out-of-distribution and in-distribution is dependent on the AI / ML model as well as the channel environment distribution. From this perspective, the out-of-distribution and in-distribution of the channel task should be considered to optimize the performance of physical layer communication. If the capacity of the terminal AI / ML model is finite and the channel has the characteristics of a heavy-tail distribution, the probability of out-of-distribution may increase. As shown in FIG. 19, when the terminal (1910) moves, if an out-of-distribution occurs at the boundary of the task, problems such as communication interruption will occur and performance will degrade.

[0100] Wireless channel modeling using a generative model

[0101] Unlike discriminative models, which make judgments or estimate values ​​regarding data, generative models can model data distributions. Given data x, a discriminative model obtains y from the conditional probability p(Y|X) that best fits the data distribution. Generative models are interested in the data distribution p(Y,X) itself and probabilistically sample values ​​within Y when x is provided. Due to the advancement of neural network technology, it has become possible to train neural networks to incorporate complex probability distributions related to images, voice, video, and text, and then generate data close to reality as the network output using probability distributions that are simple to generate. Types of such generative models include Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Normalizing Flow (NF), and Diffusion models.

[0102] FIG. 20 illustrates an example of an adversarial generative neural network that processes channel information. In FIG. 20, (i,j) is the index of a MIMO antenna, and z is a Gaussian distribution. When two input values ​​are input, they are converted into embedding values ​​by an embedding module (2012), and virtual channel samples are generated by a generative network G (2014). At this time, the virtual channel samples and the actual (ground truth, GT) channel samples are input to a discriminative network D (2024), and through training, the output of the generative network G (2014) and the distribution of the actual channel samples can become similar. Here, (i,j) applies additional information from a generative perspective and becomes a conditional embedding for neural network learning. The conditional information can extend beyond the MIMO index to a channel context, such as the actual terminal location environment. In this case, as actual data, channel context information as well as channel samples must be provided together.

[0103] The expansion of condition information can be applied not only to GANs but also to other generative models. There is an example where channel estimation, one of the channel tasks, can be utilized from the perspective of a generative network. In communication systems, when an instantaneous channel is provided, channel estimation is performed using techniques such as MMSE, taking into account the probabilistic characteristics of the instantaneous channel. In this case, rather than the probability distribution itself, the statistical characteristics of the probability distribution (e.g., covariance, noise power) are utilized. In contrast, channel estimation using a generative network can provide the result of channel estimation by applying a channel context, performing multiple channel samplings from the generative network probability distribution, and undergoing an optimization process that takes the best value among the selected samples.

[0104] Characteristics of the heavy tail distribution in the communication channel environment

[0105] In future communication systems such as 6G, communication channel characteristics may exhibit thick-tailed distributions because various channel distributions can coexist. This is because, as frequencies increase, such as with millimeter waves or terahertz waves, in addition to the directivity of radio waves, the radio waves combine with various local environments and diffraction, scattering, and reflection characteristics, so the channel environment can have a unique distribution depending on the region.

[0106] It is possible to distinguish propagation environments where reference signals in the millimeter wave or terahertz band affect channel tasks. In the case of millimeter wave or terahertz bands, unlike the propagation characteristics of low-frequency bands, the signal exhibits greater directivity. Furthermore, these high-frequency propagation environments can have many variables depending on static buildings and terrain, as well as moving objects, antenna placement, and terminal movement. For example, the TR (technical report) 38.901 standard presents the following various propagation channels.

[0107] a) Urban microcells (UMi) with O2O (Outdoor-to-Outdoor) and O2I (Outdoor-to-Indoor) (e.g., streets and urban areas, open spaces)

[0108] b) UMa (urban macrocell) with O2O and I2I

[0109] c) Indoors: Environments, shopping malls. Typical office environments include open cubicle areas and walled spaces.

[0110] d) Backhaul, outdoor rooftop backhaul in urban areas, and street canyon scenarios with small cells

[0111] e) D2D / V2V. Device-to-device access in open spaces, street canyons, and indoor scenarios. V2V is communication between vehicles.

[0112] f) Other scenarios such as stadiums (e.g., open roofs) and gymnasiums (e.g., closed roofs).

[0113] g) Indoor industrial scenario

[0114] Locality refers to the fact that the probability distribution of a communication channel becomes more dependent on the region within the radio propagation environment in which a terminal is situated. The geographical distribution where a specific terminal is located and the terminal's dynamic state have the greatest influence on locality. This implies that regional characteristics can be associated with the channel probability distribution. Since this locality makes the channel probability distribution more diverse, the data distribution of AI / ML models can vary significantly.

[0115] A system according to various embodiments of the present disclosure may utilize a channel point map for continuous online learning. A channel point map may be defined as a set of channel distribution distance or similarity distance information between channel points at a specific time and a location x (x∈X) belonging to area X. A set of discontinuous channel measurement points in a continuous three-dimensional space may be constructed by a cooperative procedure of multiple base stations and terminals. The greater the channel measurement distance from one point to another, the higher the probability that the terminal has not experienced the channel distribution, and accordingly, the difficulty of performing online learning may increase. In this case, the probability of failure of the channel task may increase, but the terminal can reduce this probability by using the channel point map to recognize the channel point distance in advance and performing online learning. In the present disclosure, the channel point map may be referred to as a 'channel distance map', 'channel distribution map', 'channel distribution distance map', or other terms having an equivalent technical meaning.

[0116] According to various embodiments of the present disclosure, channel distribution distance may be considered for online learning. Channel distribution distance refers to the difference between channel measurement points. If p1 and p2 are the probability distributions of channel information y1 and y2 of two measurement points x1 and x2 in a channel point map, the channel distribution distance is the probability distance It can be expressed as. Here, It can be explained by one of the definitions as shown in [Table 2] below.

[0117] IE(information element) description Manhattan -distance Euclidean -distance Cosine similarity Dot product KL divergence Total variation distance p-Wasserstein distance JS (Jensen-Shannon) divergence

[0118] According to various embodiments of the present disclosure, for communication between a base station and a terminal or between terminals, the terminal may use a channel point map to evaluate the probability of an out-of-synchronization of expected channel points based on velocity and acceleration vectors, and perform online learning before encountering an out-of-synchronization point. Accordingly, it may be possible to minimize or reduce the probability of an out-of-synchronization of a channel task at the physical layer.

[0119] The structure of an AI / ML model according to various embodiments of the present disclosure is as shown in FIG. 21. FIG. 21 illustrates the functional structures of devices in a wireless communication system according to one embodiment of the present disclosure. FIG. 21 illustrates the structure of a channel task model of a base station or terminal.

[0120] Referring to FIG. 21, a first device (2110) operating as a transmitter includes a transmit entity (2112), a transmit model (2114), and a transmit signal processing unit (2116). A second device (2120) operating as a receiver includes a receive signal processing unit (2122), a receive model (2124a), an OOD detector (2124b), a channel model (2124c), and a receive entity (2126).

[0121] The transmitting entity (2112) performs overall control and processing for data transmission. In particular, according to various embodiments, the transmitting entity (2112) provides information necessary for the operation of the transmitting model (2114) and generates and provides input data for the task model. The transmitting model (2114), as part of the task model, generates output values ​​transmitted through a channel based on the input data. The transmitting signal processing unit (2116) performs physical layer processing for transmitting the output values ​​of the transmitting model (2114) through a wireless channel, including, for example, at least one of channel encoding, modulation, resource mapping, and frequency conversion. The function of the transmitting signal processing unit (2116) may vary depending on the function of the task model.

[0122] The receiving signal processing unit (2122) performs physical layer processing for interpreting a signal received through a wireless channel, including at least one of frequency conversion, resource demapping, demodulation, and channel decoding. The function of the receiving signal processing unit (2122) may vary depending on the function of the task model. The receiving model (2124a) is part of the task model and generates output data based on the output values ​​of the transmitting model (2114) received through the wireless channel, i.e., performs the task. The OOD detector (2124b) detects the external distribution. The channel model (2124c) generates channel information for online learning. The receiving entity (2126) performs overall control and processing for data reception. In particular, according to various embodiments, the receiving entity (2126) acquires the output data of the receiving model (2124a) and processes the acquired output data according to the task. Additionally, the receiving entity (2126) may provide information necessary for the operation of other blocks.

[0123] The transmission model (2114) is a set value A machine learning model or neural network model with and the receiver model (2124a) is the setting value A machine learning model or neural network model with The transmitting model (2112) acts as a kind of precoder and, taking into account the complexity of the transceiver, may have finite quantized setting values. For example, the transmitting model (2112) may be implemented as a multiplicator that multiplies beamforming vectors based on a DFT codebook or as a complex neural network model. The OOD detector (2124b) is a model that evaluates the external distribution probability. This is a model included in the OOD detector (2124b) according to various embodiments. The model Implemented with a neural network added to or a model It can be designed to take a portion of the same model output.

[0124] For example, model If is a neural network that classifies n CQIs, the output contains one of the n values. If it is designed to take n softmax values ​​immediately before the output, it is an OOD model (2124b). This can be implemented. It is possible to determine OOD by determining the variance for n values ​​and comparing it with a threshold value. When n is 15, if the CQI value is classified as 7 by normal operation, the softmax output will have a large value at 7. However, in an OOD situation, all n values ​​will have low values, and there is a high probability that the variance will be small. As another example, in the case of a channel estimation operation, an OOD model (2124b) is obtained by binary training an independent neural network that determines whether it is OOD using non-OOD data and OOD data. can be implemented.

[0125] The receiving model (2124a) and the OOD detector (2124b) are side information Use . Additional information The context information of the terminal may include sensor information including the terminal's location, acceleration, etc., or information signaled from the first device (2110).

[0126] The channel model (2124c) is a channel latent space an arbitrary element in Perform sampling on, and the model Using Channels with high similarity to It can generate. That is, the channel model (2124c) is a channel with large data dimensions. low-dimensional latent space It may be implemented as a dimension reduction inverse function model of a transformation mapping to or as a decoder of a generative model. The implementation of the channel model (2124c) may be determined by the capability of the terminal. If the channel model (2124c) is a dimension reduction inverse function model, the channel model (2124c) is a plurality of channel candidates that the second device (2120) may experience at a point corresponding to the terminal context of the point where the movement of the second device (2120) is expected. Creates and gives minimum loss to the current channel task Optimization of the path can be performed.

[0127] According to one embodiment, model If is a dimensionality reduction inverse function model, the first device (2110) has a plurality of latent spaces in the channel statistics database of the corresponding channel point. When the value of is transmitted to the second device (2120), the second device (2120) passes the received information through a dimensionality reduction inverse function model to obtain a channel candidate You can obtain. Here, is a low-dimensional vector that can be transmitted with small signaling overhead.

[0128] According to one embodiment, model If is a generative model, the first device (2110) transmits to the second device (2120) information on the potential spatial probability distribution of a point corresponding to the context of the point where the movement of the second device (2120) is expected. The second device (2120) transmits information on multiple channel candidates that the second device (2120) may experience. Generates through probability distribution sampling and gives the minimum loss to the current channel task Optimization can be performed on the channel latent space. That is, of an arbitrary element in When sampling is performed and input into a generative model, the second device (2120) Channels with high similarity to It can generate. The channel information generated in this way can be used for external distribution and online learning.

[0129] Additionally, the second device (2120) may include a channel point encoder for evaluating a channel point map when a channel is given, and when a channel and context are given at the current channel and target channel point, the corresponding elements of the latent space can decide.

[0130] Evaluation of external distribution predictions and online learning methods for a k-candidate set

[0131] According to various embodiments, an external distribution prediction evaluation and online learning for a k-candidate set may be performed. A candidate channel point is a channel point at a point where the terminal is expected to move. The greater the channel distribution distance between the current point and the candidate channel point, or the smaller the similarity in the channel latent space, the higher the probability that the external distribution probability of the candidate channel point will be very large. Considering terminal complexity and signaling burden, k candidates are selected from the current location. The terminal determines a k-candidate set in a certain space in the direction of the movement speed and acceleration vector. At this time, according to one embodiment, adaptive control may be performed such that the size k of the k-candidate set increases as the speed or acceleration increases, and the size k of the k-candidate set decreases as the speed or acceleration decreases.

[0132] Next, an external distribution evaluation and online learning for channel points are performed. In this disclosure, for convenience of explanation, the distance in channel distribution distance or channel latent space is referred to as 'channel distance'. The external distribution evaluation and online learning may be performed as follows.

[0133] Step-1) Channel distribution distance in k-candidate sets based on mobility is a threshold Select a larger channel point.

[0134] Step-2) Perform an external distribution evaluation for all channel points in the previous step. To evaluate the external distribution, the terminal obtains representative sample data X for the corresponding channel point from a base station or a master terminal for V2X communication and may use an external distribution detector (OOD detector).

[0135] Step-3) If an external distribution occurs, the terminal performs online learning for the corresponding channel point using representative sample data or representative sample data generated by a generative model in the channel point space.

[0136] The operation of devices for online learning according to various embodiments of the present disclosure is described below. In the following description, it is described that a base station operates as a transmitter and a terminal operates as a receiver. However, the embodiments described below may be applied not only to base stations and terminals, but also to terminals and terminals performing side-link communication. In this case, at least some of the operations performed by the base station in the embodiments described below may be understood as the operations of the master terminal of V2X.

[0137] FIG. 22 illustrates an example of a procedure for performing online learning in a wireless communication system according to one embodiment of the present disclosure. FIG. 22 illustrates an example of a method performed by a terminal.

[0138] Referring to FIG. 22, in step S2201, the terminal transmits a message requesting information about a neighboring area. For example, the terminal may request the base station to transmit a broadcast message (e.g., system information) or a unicast message containing information about a neighboring area. Here, the neighboring area is an area adjacent to the geographical area where the terminal is currently located, and can be understood as an area that is physically adjacent or adjacent in terms of channel distribution.

[0139] In step S2203, the terminal receives a message containing information about a neighboring area. The terminal receives a message transmitted in response to the request in step S2201. The message may include a broadcast message (e.g., system information) or a unicast message. The information about the neighboring area includes information for evaluating or measuring at least one neighboring area. According to one embodiment, the information about the neighboring area may include at least one of information related to the evaluation of an external distribution and information related to channel distribution.

[0140] In step S2205, the terminal performs an evaluation of at least one neighboring region. Through this, the terminal can obtain information about the channel associated with at least one neighboring region. According to various embodiments, the terminal determines whether the region (e.g., a candidate channel point) is an area that generates an out-of-distribution, that is, whether it is an area that has a channel distribution that differs from the training data used to train a model for a task by a certain level or more. To this end, the terminal determines the channel distribution distance between the current location and the candidate channel points, obtains sample data for the channel of the candidate channel point that has a channel distribution distance greater than a threshold, and uses the sample data to determine whether there is an out-of-distribution.

[0141] In step S2207, the terminal performs online learning based on the evaluation. In other words, the terminal performs online learning for the channel task model using the results of the evaluation. Specifically, if at least one neighboring region (e.g., a channel point) is identified where the probability of an out-of-distribution occurrence is greater than or equal to a threshold, the terminal acquires representative sample data for the identified at least one neighboring region and performs learning for the task model using the acquired representative sample data. That is, online learning may be performed on at least some of the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model.

[0142] FIG. 23 illustrates an example of a procedure for providing information for online learning in a wireless communication system according to one embodiment of the present disclosure. FIG. 23 illustrates an example of a method performed by a base station.

[0143] Referring to FIG. 23, in step S2301, the base station receives a message requesting information about a neighboring area. For example, the terminal may request the base station to transmit a broadcast message (e.g., system information) or a unicast message containing information about a neighboring area. Here, the neighboring area is an area adjacent to the geographical area where the terminal is currently located, and can be understood as an area that is physically adjacent or adjacent in terms of channel distribution.

[0144] In step S2303, a message containing information about a base station neighbor area is transmitted. The base station transmits the message in response to the request in step S2301. The message may include a broadcast message (e.g., system information) or a unicast message. The information about the neighbor area includes information for evaluating or measuring at least one neighbor area. According to one embodiment, the information about the neighbor area may include at least one of information related to the evaluation of the external distribution and information related to the channel distribution.

[0145] FIG. 24 illustrates an example of a procedure for performing online learning in response to external distribution detection in a wireless communication system according to one embodiment of the present disclosure. FIG. 24 illustrates an example of a method performed by a terminal.

[0146] Referring to FIG. 24, in step S2401, the terminal performs a procedure to generate a channel point map. The channel point map is information related to the channel distribution for regions within the coverage area, which is stored and managed by the base station and can be provided to the terminals. The channel point map is generated based on measurements by the terminals, and the terminal can perform measurements under the control of the base station and report the measurement results.

[0147] In step S2403, the terminal performs an external distribution evaluation for candidate channel points. For example, the terminal may acquire a channel point map at the current location and perform an external distribution evaluation based on the channel point map. To do this, the terminal may request and receive information related to the channel point map from a base station or another terminal. Then, the terminal determines multiple candidate channel points that are movable from the current location and estimates the probability of an external distribution based on the channel distribution for the determined multiple candidate channel points. The probability of an external distribution can be estimated using a model for external distribution evaluation.

[0148] In step S2405, the terminal obtains sample data for channel points where an out-of-distribution occurs. An out-of-distribution occurs when the probability of the out-of-distribution is greater than or equal to a threshold. That is, the terminal obtains sample data for at least one channel point among the candidate channel points that has an out-of-distribution probability greater than or equal to the threshold. Here, the sample data is information related to the channel generated based on the channel distribution. The sample data may be received from a base station or generated by the terminal's generation model.

[0149] In step S2407, the terminal performs training using sample data. In other words, the terminal trains a channel task model using sample data. Accordingly, the channel task model can be trained to operate even in a channel distribution at at least one channel point where an out-of-distribution is expected to occur, and consequently, the occurrence of an out-of-distribution at said at least one channel point can be prevented.

[0150] According to the embodiments described above, online training for a channel task model for learning the channel distribution of channel points where movement of the terminal is expected can be performed. Here, the specific operation of the external distribution evaluation and online training may vary depending on the operating mode of the terminal. The operation of the external distribution evaluation and online training according to the operating mode of the terminal (e.g., idle mode, connection mode, etc.) is as follows.

[0151] In idle mode, the terminal wakes up from low-power mode every n-DRX (discoutinuos reception) cycle and performs an evaluation of channel distance and out-of-range distribution. This is intended to prevent out-of-range distribution in advance and minimize in-sync time during radio link setup based on paging messages via the paging channel. Since it wakes up every n-DRX cycle, power consumption can be minimized. The terminal can receive information related to channel points and distribution distances in the current cell through the SIB (system information block).

[0152] The terminal analyzes the current mobility vector to obtain a channel distribution map corresponding to the current cell location, selects k candidate channel points based on the mobility vector, and requests the base station for the channel distribution map or channel latent spatial information of the current point based on the current location. Here, the request to the base station can be performed according to the SIB acquisition procedure, that is, according to the on-demand system information request procedure. Subsequently, the base station transmits information related to the channel point map corresponding to the current location to the terminal via the SIB. Then, the terminal performs external distribution evaluation and online learning for the target k candidate channel points at every n-DRX period.

[0153] Here, the information transmitted from the base station to the terminal via the SIB may include at least one of the items listed in [Table 3] below.

[0154] IE(information element) description Measurement period n-DRX(evaluate k candidate channel points every n-times DRX cycle). Reference signal Reference signal for channel measurement. At least one of all available reference signals, such as CSI-RS, DM-RS, PT-RS, etc. Channel distance metric type Distance metric types. Channel model ID Channel Model Identifier of. Creates channel distribution. OOD evaluation model ID OOD model Identifier of. Evaluates external distribution. OOD evaluation criteria OOD determination criteria. It is the threshold of the OOD model, and if it is smaller than the threshold, it is determined to be OOD. Number of k-candidates Number of channel point candidates. Channel map type Type of channel point map (e.g., generative or low-dimensional inverse transform).

[0155] As information transmitted from a base station to a terminal, when the channel model is a low-dimensional back-turn model, information related to the channel point may include at least one of the items listed in [Table 4] below.

[0156] IE(information element) description Reference channel point ID Reference channel point identifier. Reference channel context Context information including reference channel point location information. Set of channel point z vector Multiple vector values ​​for generating channel candidates of a reference channel point.

[0157] Information related to channel point distances can be transmitted for each of the k candidates surrounding the reference channel point. If the channel model is a low-dimensional back-turn model, the information related to each channel point distance may include at least one of the items listed in [Table 5] below.

[0158] IE(information element) description Candidate ID Identifier for distinguishing between k candidates. Candidate point distance vector Distance vector from the reference channel point to the corresponding sign point Set of channel point z vector Multiple vector values ​​for generating channel candidates of k-candidate channel points.

[0159] As information transmitted from a base station to a terminal, if the channel model is a generative model, the information related to the channel point may include at least one of the items listed in [Table 6] below.

[0160] IE(information element) description Reference channel point ID Reference channel point identifier. Reference channel context Context information including reference channel point location information. Set of channel point z vector Probability distribution information for generating channel candidates of a reference channel point. Includes at least one of the probability distribution information, mean, and variance.

[0161] Information regarding channel point distances can be transmitted for each of the k candidates surrounding the reference channel point. If the channel model is a generative model, information regarding each channel point distance may include at least one of the items listed in [Table 7] below.

[0162] IE(information element) description Candidate ID Identifier for distinguishing between k candidates. Candidate point distance vector Distance vector from the reference channel point to the corresponding sign point Set of channel point z vector Probability distribution information for generating channel candidates of a reference channel point. Includes at least one of the probability distribution information, mean, and variance.

[0163] In connected mode, the terminal can perform external distribution evaluation on k channel point candidates and perform online learning. For example, the terminal can obtain channel point information by cell list during handover or by beam associated with CSI-RS.

[0164] The terminal requests information related to the channel point map from the base station by transmitting a message requesting channel point information (e.g., CP_INFO_REQ message). Specifically, the terminal analyzes the current mobility vector to obtain a channel distribution map corresponding to the current cell location, selects k candidate channel points based on the mobility vector, and requests the channel distribution map or channel latent space information of the current location from the base station based on the current location. This operation can be performed when moving from the current reference channel point to another channel point area. Subsequently, the base station transmits a message (e.g., CP_INFO_RES message) containing information related to the channel point map corresponding to the current location to the terminal. Then, the terminal performs external distribution evaluation and online learning for the target k candidate channel points.

[0165] Here, the information transmitted from the base station to the terminal via a message may include at least one of the items listed in [Table 8] below.

[0166] IE(information element) description Measurement period n-slots (evaluate k-candidate channel points for each n slot) Reference signal Reference signal for channel measurement. At least one of all available reference signals, such as CSI-RS, DM-RS, PT-RS, etc. Channel distance metric type Distance metric types. Channel model ID Channel Model Identifier of. Creates channel distribution. OOD evaluation model ID OOD model Identifier of. Evaluates external distribution. OOD evaluation criteria OOD determination criteria. It is the threshold of the OOD model, and if it is smaller than the threshold, it is determined to be OOD. Number of k-candidates Number of channel point candidates. Channel map type Type of channel point map (e.g., generative or low-dimensional inverse transform).

[0167] As information transmitted from a base station to a terminal, if the channel model is a low-dimensional back-turn model, the information related to the channel point may include at least one of the items listed in [Table 9] below.

[0168] IE(information element) description Reference channel point ID Reference channel point identifier. Reference channel context Context information including reference channel point location information. Set of channel point z vector Multiple vector values ​​for generating channel candidates of a reference channel point.

[0169] Information related to channel point distances can be transmitted for each of the k candidates surrounding the reference channel point. If the channel model is a low-dimensional back-turn model, the information related to each channel point distance may include at least one of the items listed in [Table 10] below.

[0170] IE(information element) description Candidate ID Identifier for distinguishing between k candidates. Candidate point distance vector Distance vector from the reference channel point to the corresponding sign point Set of channel point z vector Multiple vector values ​​for generating channel candidates of k-candidate channel points.

[0171] As information transmitted from a base station to a terminal, if the channel model is a generative model, the information related to the channel point may include at least one of the items listed in [Table 11] below.

[0172] IE(information element) description Reference channel point ID Reference channel point identifier. Reference channel context Context information including reference channel point location information. Set of channel point z vector Probability distribution information for generating channel candidates of a reference channel point. Includes at least one of the probability distribution information, mean, and variance.

[0173] Information regarding channel point distances can be transmitted for each of the k candidates surrounding the reference channel point. If the channel model is a generative model, information regarding each channel point distance may include at least one of the items listed in [Table 12] below.

[0174] IE(information element) description Candidate ID Identifier for distinguishing between k candidates. Candidate point distance vector Distance vector from the reference channel point to the corresponding sign point Set of channel point z vector Probability distribution information for generating channel candidates of a reference channel point. Includes at least one of the probability distribution information, mean, and variance.

[0175] FIG. 25 illustrates an example of a channel point map in a wireless communication system according to one embodiment of the present disclosure. FIG. 25 illustrates a situation in which a database (2502) of reference channel point locations in a potential space based on a channel distribution map or channel similarity is stored in a base station. Accordingly, the base station can provide training data related to a designated reference channel point to a terminal.

[0176] FIG. 26 illustrates examples of candidate channel points in a wireless communication system according to one embodiment of the present disclosure. FIG. 26 illustrates candidate channel points according to the direction of the mobility vector of each terminal. Based on the current location, an out-distribution evaluation and online learning may be performed only when the channel distribution distance for a candidate channel point is large. For the out-distribution evaluation and online learning, a base station may provide representative online training data.

[0177] When a terminal encounters a new channel environment it has not experienced while performing online continuous learning, communication interruption may occur due to delay caused by learning. However, as with the various embodiments described above, the out-of-sync probability of channel tasks can be reduced by evaluating the out-of-distribution of k-candidate channel points based on the channel distribution map and the terminal's mobility information in advance and performing online learning.

[0178] In the k-candidate distribution, the value of k can be adaptively determined in proportion to mobility. This minimizes the cost of evaluating unnecessary exclaves. In what dimension is the density of the channel point map Satisfying geometric probability having a Poisson distribution, the terminal speed in one direction When moving to, the terminal visits a new channel point at time intervals of an exponential distribution, and the time interval is It is proportional to. Evaluating the external distribution and the exponential distribution mean time to complete online learning Assuming it takes a certain amount of time, the approximate probability that k-candidates cannot handle online learning is as follows [Equation 1].

[0179]

[0180] In [Mathematical Formula 1], is the approximate probability that k-candidates cannot handle online learning, is the density of the Poisson distribution of geometric probability satisfied by the channel point map, represents the terminal's movement speed, and K represents the number of candidate channel points.

[0181] Referring to [Mathematical Formula 1], if the probability is the same, the smaller the speed, the A trade-off relationship is confirmed in which the value decreases. In addition, since the external distribution evaluation requires representative training data for candidate channels, the transmission of unnecessary representative training data can be prevented by pre-selecting the targets for the external distribution evaluation using a channel distribution map before the external distribution evaluation.

[0182] The proposed methods described above may be implemented independently, but they may also be implemented in the form of a combination (or merger) of some of the proposed methods. Rules may be defined so that the base station informs the terminal of the application status of the proposed methods (or information regarding the rules of the proposed methods) through a predefined signal (e.g., a physical layer signal or an upper layer signal).

[0183] The present disclosure may be embodied in other specific forms without departing from the technical ideas and essential features described herein. Accordingly, the above detailed description should not be interpreted restrictively in all respects and should be considered illustrative. The scope of the present disclosure shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present disclosure are included within the scope of the present disclosure. Furthermore, embodiments may be constructed by combining claims that are not explicitly related in the claims, or new claims may be included by amendments made after filing. Industrial applicability

[0184] The embodiments of the present disclosure can be applied to various wireless access systems. Examples of various wireless access systems include the 3GPP (3rd Generation Partnership Project) or 3GPP2 systems.

[0185] The embodiments of the present disclosure can be applied not only to the various wireless access systems mentioned above but also to all technical fields utilizing the various wireless access systems. Furthermore, the proposed method can also be applied to mmWave and THz communication systems utilizing the ultra-high frequency band.

[0186] Additionally, the embodiments of the present disclosure may also be applied to various applications, such as autonomous vehicles and drones.

Claims

Claim 1 A method performed by a terminal in a wireless communication system comprises: transmitting a first message requesting information about a neighboring region; receiving a second message containing information about the neighboring region; performing an evaluation of at least one neighboring region based on the information about the neighboring region; and performing online learning for a channel task model based on the result of the evaluation, wherein the online learning is performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model. Claim 2 A method according to claim 1, wherein the information regarding the neighboring region comprises a channel point map representing information related to the probability distribution of a channel of a plurality of points. Claim 3 A method according to claim 2, wherein the at least one neighboring region comprises at least one point among the plurality of points having a probability distribution distance greater than or equal to a threshold with respect to the current point of the terminal. Claim 4 A method according to claim 1, wherein the step of performing the online learning comprises: receiving representative sample data for the channel of at least some regions from a base station; and performing learning for the channel task model using the representative sample data. Claim 5 A method according to claim 1, wherein the step of performing online learning comprises: generating representative sample data for the channel of at least some regions; and performing learning for the channel task model using the representative sample data. Claim 6 The method of claim 1, wherein information about the neighboring region is included in system information or a unicast message. Claim 7 A method according to claim 1, wherein the information regarding the neighboring region comprises at least one of the following: the execution cycle of the evaluation, the number of at least one neighboring region, the type of channel point map, the distance metric used in the channel point map, the identifier of the model for the evaluation, the identifier of the channel point, and the distance to the channel point. Claim 8 A terminal in a wireless communication system comprises: a transceiver; and a processor connected to the transceiver, wherein the processor transmits a first message requesting information about a neighboring region and receives a second message containing information about the neighboring region, performs an evaluation of at least one neighboring region based on the information about the neighboring region, and controls the performance of online learning for a channel task model based on the result of the evaluation, wherein the online learning is performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model. Claim 9 A communication device comprising: at least one processor; and at least one computer memory connected to the at least one processor and storing instructions that direct operations as executed by the at least one processor, wherein the operations include: transmitting a first message requesting information about a neighboring region; receiving a second message containing information about the neighboring region; performing an evaluation of at least one neighboring region based on the information about the neighboring region; and performing online learning for a channel task model based on the result of the evaluation, wherein the online learning is performed for at least some regions among the at least one neighboring region that are evaluated to have an out-of-distribution probability greater than or equal to a threshold for the channel task model. Claim 10 A non-transitory computer-readable medium storing at least one instruction, comprising said at least one instruction executable by a processor, said at least one instruction, said at least one instruction, said at least one instruction, said at least one instruction, said device transmits a first message requesting information about a neighbor region, receives a second message containing information about said neighbor region, and controls to perform an evaluation of at least one neighbor region based on the information about said neighbor region, and to perform online learning for a channel task model based on the result of said evaluation, said online learning is performed for at least some regions among said at least one neighbor region that are evaluated to have an out-of-distribution probability greater than a threshold for said channel task model.

Images