WO2024034707A1 - Device and method for performing online training with respect to receiver model in wireless communication system - Google Patents

Abstract

The objective of the present disclosure is to perform online training with respect to a receiver model in a wireless communication system, and an operation method of a user equipment (UE) may include the steps of: receiving broadcast information required for communication; transmitting capability information related to discontinuous reception (DRX); receiving configuration information related to the DRX; performing a sleep duration operation on the basis of the configuration information; and performing an on-duration operation on the basis of the configuration information, wherein the on-duration operation includes an operation of monitoring UE context used for configuring a receiver, and the sleep duration operation includes an operation of configuring the receiver by using channel data generated on the basis of the UE context.

Description

Apparatus and method for performing online learning of a receiver model in a wireless communication system

The following description relates to a wireless communication system and an apparatus and method for performing online learning of a receiver model in a wireless communication system.

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

In particular, as many communication devices require large communication capacity, enhanced mobile broadband (eMBB) communication technology is being proposed compared to the existing radio access technology (RAT). In addition, a communication system that takes into account reliability and latency-sensitive services/UE (user equipment) as well as mMTC (massive machine type communications), which connects multiple devices and objects to provide a variety of services anytime and anywhere, is being proposed. . Various technological configurations are being proposed for this purpose.

The present disclosure can provide an apparatus and method for effectively performing online learning of a receiver model in a wireless communication system.

The present disclosure can provide an apparatus and method for performing active learning on a receiver model in a wireless communication system.

The present disclosure can provide an apparatus and method for reducing the burden of separately updating different receiver models held by a plurality of terminals in a wireless communication system.

The present disclosure can provide an apparatus and method for performing training on receiver models using a common channel creation model for a plurality of receiver models for different tasks in a wireless communication system.

The present disclosure can provide an apparatus and method for controlling the output of a channel generation model according to the channel environment in a wireless communication system.

The present disclosure can provide an apparatus and method for operating a channel creation model based on a probability distribution corresponding to a channel environment in a wireless communication system.

The present disclosure can provide an apparatus and method for determining a probability distribution corresponding to a channel environment in a wireless communication system.

The present disclosure can provide an apparatus and method for controlling the output of a channel creation model according to the context of a terminal in a wireless communication system.

The present disclosure can provide an apparatus and method for controlling the output of a channel creation model according to uncertainty about a receiver model of a terminal in a wireless communication system.

The present disclosure can provide an apparatus and method for performing online training for a receiver model during DRX (discontinuous reception) operation of a terminal in a wireless communication system.

The present disclosure can provide an apparatus and method for performing online learning of a receiver model during a sleep period according to DRX operation of a terminal in a wireless communication system.

The present disclosure can provide an apparatus and method for determining the length of an online learning period based on measurement results during a wake-up period according to the DRX operation of a terminal in a wireless communication system.

The technical objectives sought to be achieved by the present disclosure are not limited to the matters mentioned above, and other technical tasks not mentioned are subject to common knowledge in the technical field to which the technical configuration of the present disclosure is applied from the embodiments of the present disclosure described below. Can be considered by those who have.

As an example of the present disclosure, a method of operating a user equipment (UE) in a wireless communication system includes receiving broadcast information necessary for communication, transmitting capability information related to DRX (discontinuous reception), and settings related to the DRX. Receiving (configuration) information, performing a sleep section operation based on the configuration information, and performing an on-duration operation based on the configuration information, The on-section operation includes monitoring the UE context used to set up the receiver, and the sleep section operation includes setting up the receiver using channel data generated based on the UE context. It can be included.

As an example of the present disclosure, a method of operating a base station in a wireless communication system includes transmitting broadcast information necessary for communication, receiving capability information related to DRX (discontinuous reception), and configuration information related to the DRX. Transmitting, receiving a message requesting information or signals necessary for setting up a receiver of a user equipment (UE), and transmitting the information or signals, wherein the setting information is DRX of the UE. Indicates a sleep period and on-duration for operation, and the on-duration is used to monitor the UE context used for setting the receiver in the UE, and the sleep period is , It can be used in the UE to set up the receiver using channel data generated based on the UE context.

As an example of the present disclosure, a user equipment (UE) in a wireless communication system includes a transceiver and a processor connected to the transceiver, where the processor receives broadcast information necessary for communication and performs a process related to discontinuous reception (DRX). Transmit capability information, receive configuration information related to the DRX, perform sleep section operation based on the configuration information, and on-duration operation based on the configuration information. Control to perform, wherein the on-section operation includes monitoring the UE context used for setting up the receiver, and the sleep section operation uses channel data generated based on the UE context to May include operations for setting up the receiver.

As an example of the present disclosure, a base station in a wireless communication system includes a transceiver and a processor connected to the transceiver, where the processor transmits broadcast information necessary for communication and receives capability information related to discontinuous reception (DRX). and transmitting configuration information related to the DRX, receiving a message requesting information or signals necessary for setting up a receiver of a UE (user equipment), controlling to transmit the information or signals, and performing the configuration. The information indicates a sleep period and on-duration for the DRX operation of the UE, and the on-duration monitors the UE context used for setting the receiver in the UE. The sleep period may be used by the UE to configure the receiver using channel data generated based on the UE context.

As an example of the present disclosure, a communication device includes at least one processor, 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. The operations include receiving broadcast information necessary for communication, transmitting capability information related to DRX (discontinuous reception), receiving configuration information related to the DRX, and based on the configuration information. It includes performing a sleep section operation, and performing an on-duration operation based on the configuration information, wherein the on-duration operation is performed by the UE used to configure the receiver. (user equipment) includes an operation of monitoring context, and the sleep period operation may include an operation of configuring the receiver using channel data generated based on the UE context.

As an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction includes the at least one instruction executable by a processor. Includes, wherein the at least one command causes the device to receive broadcast information necessary for communication, transmit capability information related to DRX (discontinuous reception), receive configuration information related to the DRX, and A sleep section operation is performed based on the setting information, and an on-duration operation is controlled based on the setting information. The on-duration operation is used for setting the receiver. It includes an operation of monitoring a user equipment (UE) context, and the sleep period operation may include an operation of configuring the receiver using channel data generated based on the UE context.

The above-described aspects of the present disclosure are only some of the preferred embodiments of the present disclosure, and various embodiments reflecting the technical features of the present disclosure will be described in detail by those skilled in the art. It can be derived and understood based on.

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

According to the present disclosure, online learning for a receiver model can be effectively performed.

The effects that can be obtained from the embodiments of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be found in the technical field to which the technical configuration of the present disclosure is applied from the description of the embodiments of the present disclosure below. It can be clearly derived and understood by those with ordinary knowledge. That is, unintended effects resulting from implementing the configuration described in this disclosure may also be derived by a person skilled in the art from the embodiments of this disclosure.

The drawings attached below are intended to aid understanding of the present disclosure and may provide embodiments of the present disclosure along with a detailed description. However, the technical features of the present disclosure are not limited to specific drawings, and the features disclosed in each drawing may be combined to form a new embodiment. Reference numerals in each drawing may refer to structural elements.

1 shows an example of a communication system applicable to the present disclosure.

Figure 2 shows an example of a wireless device applicable to the present disclosure.

Figure 3 shows another example of a wireless device applicable to the present disclosure.

Figure 4 shows an example of a portable device applicable to the present disclosure.

5 shows an example of a vehicle or autonomous vehicle applicable to the present disclosure.

Figure 6 shows an example of AI (Artificial Intelligence) applicable to the present disclosure.

Figure 7 shows a method of processing a transmission signal applicable to the present disclosure.

Figure 8 shows an example of a communication structure that can be provided in a 6G system applicable to the present disclosure.

9 shows an electromagnetic spectrum applicable to the present disclosure.

Figure 10 shows a THz communication method applicable to the present disclosure.

Figure 11 shows the structure of a perceptron included in an artificial neural network applicable to the present disclosure.

Figure 12 shows an artificial neural network structure applicable to the present disclosure.

13 shows a deep neural network applicable to this disclosure.

14 shows a convolutional neural network applicable to this disclosure.

15 shows a filter operation of a convolutional neural network applicable to this disclosure.

Figure 16 shows a neural network structure with a cyclic loop applicable to the present disclosure.

Figure 17 shows the operational structure of a recurrent neural network applicable to the present disclosure.

Figure 18 shows sampling methods for active learning according to an embodiment of the present disclosure.

19A to 19C show examples of results of active learning and passive learning according to an embodiment of the present disclosure.

Figure 20 shows functional structures of devices supporting active learning according to an embodiment of the present disclosure.

Figure 21 shows an example of areas divided according to latent distribution according to an embodiment of the present disclosure.

FIG. 22 shows an example of times when context monitoring is performed during a discontinuous reception (DRX) cycle according to an embodiment of the present disclosure.

Figure 23 shows an example of times when online learning is performed during a DRX cycle according to an embodiment of the present disclosure.

Figure 24 shows an example of a procedure for setting up a receiver while operating in DRX mode according to an embodiment of the present disclosure.

Figure 25 shows an example of a procedure corresponding to a change in context information according to an embodiment of the present disclosure.

Figure 26 shows an example of a procedure for responding to an increase in uncertainty according to an embodiment of the present invention.

Figure 27 shows an example of a procedure for supporting online learning according to an embodiment of the present invention.

Figure 28 shows an example of a procedure for exchanging competency information related to online learning according to an embodiment of the present invention.

Figure 29 shows an example of a procedure for updating latent distribution information according to an embodiment of the present invention.

Figure 30 shows an example of a procedure for controlling uncertainty in a receiver model according to an embodiment of the present invention.

Figure 31 shows examples of various neural networks for different tasks according to an embodiment of the present invention.

Figure 32 shows an example of times when context measurement and online learning are performed during a DRX cycle according to an embodiment of the present invention.

Figure 33 shows an example of context groups according to an embodiment of the present invention.

Figure 34 shows another example of context groups according to an embodiment of the present invention.

Figure 35 shows an example of terminals with different channel task networks according to an embodiment of the present invention.

The following embodiments combine the elements and features of the present disclosure in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. Additionally, some components and/or features may be combined to configure an embodiment of the present disclosure. The order of operations described in embodiments of the present disclosure may be changed. Some features or features of one embodiment may be included in another embodiment or may be replaced with corresponding features or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of the present disclosure are not described, and procedures or steps that can be understood by a person skilled in the art are not described.

Throughout the specification, when a part is said to “comprise or include” a certain element, this means that it does not exclude other elements but may further include other elements, unless specifically stated to the contrary. do. In addition, terms such as "... unit", "... unit", and "module" used in the specification refer to a unit that processes at least one function or operation, which refers to hardware, software, or a combination of hardware and software. It can be implemented as: Additionally, the terms “a or an,” “one,” “the,” and similar related terms may be used differently herein in the context of describing the present disclosure (particularly in the context of the claims below). It may be used in both singular and plural terms, unless indicated otherwise or clearly contradicted by context.

In this specification, embodiments of the present disclosure have been described focusing on the data transmission and reception relationship between the base station and the mobile station. Here, the base station is meant as a terminal node of the network that directly communicates with the mobile station. Certain operations described in this document as being performed by the base station may, in some cases, be performed by an upper node of the base station.

That is, in a network comprised of a plurality of 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. At this time, 'base station' is a term such as fixed station, Node B, eNB (eNode B), gNB (gNode B), ng-eNB, advanced base station (ABS), or access point. It can be replaced by .

Additionally, in embodiments of the present disclosure, a terminal may include a user equipment (UE), a mobile station (MS), a subscriber station (SS), a mobile subscriber station (MSS), It can be replaced with terms such as mobile terminal or advanced mobile station (AMS).

Additionally, the transmitting end refers to a fixed and/or mobile node that provides a data service or a voice service, and the receiving end refers to a fixed and/or mobile node that receives a data service or a voice service. Therefore, in the case of uplink, the mobile station can be the transmitting end and the base station can be the receiving end. Likewise, in the case of downlink, the mobile station can be the receiving end and the base station can be the transmitting end.

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

Additionally, embodiments of the present disclosure can be applied to other wireless access systems and are not limited to the above-described systems. As an example, it may be applicable to systems applied after the 3GPP 5G NR system and is not limited to a specific system.

That is, obvious steps or parts that are not described among the embodiments of the present disclosure can be explained with reference to the documents. Additionally, all terms disclosed in this document can be explained by the standard document.

Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the attached drawings. The detailed description to be disclosed below along with the accompanying drawings is intended to describe exemplary embodiments of the present disclosure, and is not intended to represent the only embodiments in which the technical features of the present disclosure may be practiced.

In addition, specific terms used in the embodiments of the present disclosure are provided to aid understanding of the present disclosure, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the present disclosure.

The following technologies include code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single carrier frequency division multiple access (SC-FDMA). It can be applied to various wireless access systems.

In the following, for clarity of explanation, the description is based on the 3GPP communication system (e.g., LTE, NR, etc.), but the technical idea of the present invention is not limited thereto. LTE is 3GPP TS 36.xxx Release 8 and later. In detail, LTE technology after 3GPP TS 36.xxx Release 10 may be referred to as LTE-A, and LTE technology after 3GPP TS 36.xxx Release 13 may be referred to as LTE-A pro. 3GPP NR may refer to technology after TS 38.xxx Release 15. 3GPP 6G may refer to technology after TS Release 17 and/or Release 18. “xxx” refers to the standard document detail number. LTE/NR/6G can be collectively referred to as a 3GPP system.

Regarding background technology, terms, abbreviations, etc. used in the present disclosure, reference may be made to matters described in standard documents published prior to the present invention. As an example, you can refer to the 36.xxx and 38.xxx standard documents.

Communication systems applicable to this disclosure

Although not limited thereto, the various descriptions, functions, procedures, suggestions, methods, and/or operational flowcharts of the present disclosure disclosed in this document can be applied to various fields requiring wireless communication/connection (e.g., 5G) between devices. there is.

Hereinafter, a more detailed example will be provided with reference to the drawings. In the following drawings/descriptions, identical reference numerals may illustrate identical or corresponding hardware blocks, software blocks, or functional blocks, unless otherwise noted.

1 is a diagram illustrating an example of a communication system applied to the present disclosure.

Referring to FIG. 1, the communication system 100 applied to the present disclosure includes a wireless device, a base station, and a network. Here, a wireless device refers to a device that performs communication using wireless access technology (e.g., 5G NR, LTE) and may be referred to as a communication/wireless/5G device. Although not limited thereto, wireless devices include robots (100a), vehicles (100b-1, 100b-2), extended reality (XR) devices (100c), hand-held devices (100d), and home appliances (100d). appliance) (100e), IoT (Internet of Thing) device (100f), and AI (artificial intelligence) device/server (100g). For example, vehicles may include vehicles equipped with wireless communication functions, autonomous vehicles, vehicles capable of inter-vehicle communication, etc. Here, the vehicles 100b-1 and 100b-2 may include an unmanned aerial vehicle (UAV) (eg, a drone). The XR device 100c includes augmented reality (AR)/virtual reality (VR)/mixed reality (MR) devices, including a head-mounted device (HMD), a head-up display (HUD) installed in a vehicle, a television, It can be implemented in the form of smartphones, computers, wearable devices, home appliances, digital signage, vehicles, robots, etc. The mobile device 100d may include a smartphone, smart pad, wearable device (eg, smart watch, smart glasses), computer (eg, laptop, etc.), etc. Home appliances 100e may include a TV, refrigerator, washing machine, etc. IoT device 100f may include sensors, smart meters, etc. For example, the base station 120 and the network 130 may also be implemented as wireless devices, and a specific wireless device 120a may operate as a base station/network node for other wireless devices.

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

Wireless communication/connection (150a, 150b, 150c) may be established between the wireless devices (100a to 100f)/base station (120) and the base station (120)/base station (120). Here, wireless communication/connection includes various methods such as uplink/downlink communication (150a), sidelink communication (150b) (or D2D communication), and inter-base station communication (150c) (e.g., relay, integrated access backhaul (IAB)). This can be achieved through wireless access technology (e.g. 5G NR). Through wireless communication/connection (150a, 150b, 150c), a wireless device and a base station/wireless device, and a base station and a base station can transmit/receive wireless signals to each other. For example, wireless communication/connection 150a, 150b, and 150c may transmit/receive signals through various physical channels. To this end, based on the various proposals of the present disclosure, various configuration information setting processes for transmitting/receiving wireless signals, various signal processing processes (e.g., channel encoding/decoding, modulation/demodulation, resource mapping/demapping, etc.) , at least some of the resource allocation process, etc. may be performed.

Communication systems applicable to this disclosure

FIG. 2 is a diagram illustrating an example of a wireless device applicable to the present disclosure.

Referring to FIG. 2, the first wireless device 200a and the second wireless device 200b can transmit and receive wireless signals through various wireless access technologies (eg, LTE, NR). Here, {first wireless device 200a, second wireless device 200b} refers to {wireless device 100x, base station 120} and/or {wireless device 100x, wireless device 100x) in FIG. } can be responded to.

The first wireless device 200a includes one or more processors 202a and one or more memories 204a, and may further include one or more transceivers 206a and/or one or more antennas 208a. Processor 202a controls memory 204a and/or transceiver 206a and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the processor 202a may process information in the memory 204a to generate first information/signal and then transmit a wireless signal including the first information/signal through the transceiver 206a. Additionally, the processor 202a may receive a wireless signal including the second information/signal through the transceiver 206a and then store information obtained from signal processing of the second information/signal in the memory 204a. The memory 204a may be connected to the processor 202a and may store various information related to the operation of the processor 202a. For example, memory 204a may perform some or all of the processes controlled by processor 202a or instructions for performing the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. Software code containing them can be stored. Here, the processor 202a and the memory 204a may be part of a communication modem/circuit/chip designed to implement wireless communication technology (eg, LTE, NR). Transceiver 206a may be coupled to processor 202a and may transmit and/or receive wireless signals via one or more antennas 208a. Transceiver 206a may include a transmitter and/or receiver. The transceiver 206a may be used interchangeably with a radio frequency (RF) unit. In this disclosure, a wireless device may mean a communication modem/circuit/chip.

The second wireless device 200b includes one or more processors 202b, one or more memories 204b, and may further include one or more transceivers 206b and/or one or more antennas 208b. Processor 202b controls memory 204b and/or transceiver 206b and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. For example, the processor 202b may process information in the memory 204b to generate third information/signal and then transmit a wireless signal including the third information/signal through the transceiver 206b. Additionally, the processor 202b may receive a wireless signal including the fourth information/signal through the transceiver 206b and then store information obtained from signal processing of the fourth information/signal in the memory 204b. The memory 204b may be connected to the processor 202b and may store various information related to the operation of the processor 202b. For example, memory 204b may perform some or all of the processes controlled by processor 202b or instructions for performing the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein. Software code containing them can be stored. Here, the processor 202b and the memory 204b may be part of a communication modem/circuit/chip designed to implement wireless communication technology (eg, LTE, NR). Transceiver 206b may be coupled to processor 202b and may transmit and/or receive wireless signals via one or more antennas 208b. The transceiver 206b may include a transmitter and/or a receiver. The transceiver 206b may be used interchangeably with an RF unit. In this disclosure, a wireless device may mean a communication modem/circuit/chip.

Hereinafter, the hardware elements of the wireless devices 200a and 200b will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors 202a and 202b. For example, one or more processors 202a and 202b may operate on one or more layers (e.g., physical (PHY), media access control (MAC), radio link control (RLC), packet data convergence protocol (PDCP), and radio resource (RRC). control) and functional layers such as SDAP (service data adaptation protocol) can be implemented. One or more processors 202a, 202b may generate one or more Protocol Data Units (PDUs) and/or one or more service data units (SDUs) according to the descriptions, functions, procedures, suggestions, methods, and/or operational flowcharts disclosed in this document. can be created. One or more processors 202a and 202b may generate messages, control information, data or information according to the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed in this document. One or more processors 202a, 202b generate signals (e.g., baseband signals) containing PDUs, SDUs, messages, control information, data, or information according to the functions, procedures, proposals, and/or methods disclosed herein. , can be provided to one or more transceivers (206a, 206b). One or more processors 202a, 202b may receive signals (e.g., baseband signals) from one or more transceivers 206a, 206b, and the descriptions, functions, procedures, suggestions, methods, and/or operational flowcharts disclosed herein. Depending on the device, PDU, SDU, message, control information, data or information can be obtained.

One or more processors 202a, 202b may be referred to as a controller, microcontroller, microprocessor, or microcomputer. One or more processors 202a and 202b may be implemented by hardware, firmware, software, or a combination thereof. As an example, one or more application specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), or one or more field programmable gate arrays (FPGAs) May be included in one or more processors 202a and 202b. The descriptions, functions, procedures, suggestions, methods and/or operational flowcharts 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, suggestions, methods and/or operation flowcharts disclosed in this document may be included in one or more processors 202a and 202b or stored in one or more memories 204a and 204b. It may be driven by the above processors 202a and 202b. The descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed in this document may be implemented using firmware or software in the form of codes, instructions and/or sets of instructions.

One or more memories 204a and 204b may be connected to one or more processors 202a and 202b and may store various types of data, signals, messages, information, programs, codes, instructions and/or commands. One or more memories 204a, 204b may include read only memory (ROM), random access memory (RAM), erasable programmable read only memory (EPROM), flash memory, hard drives, registers, cache memory, computer readable storage media, and/or It may be composed of a combination of these. One or more memories 204a and 204b may be located internal to and/or external to one or more processors 202a and 202b. Additionally, one or more memories 204a and 204b may be connected to one or more processors 202a and 202b through various technologies, such as wired or wireless connections.

One or more transceivers (206a, 206b) may transmit user data, control information, wireless signals/channels, etc. mentioned in the methods and/or operation flowcharts of this document to one or more other devices. One or more transceivers 206a, 206b may receive user data, control information, wireless signals/channels, etc. referred to in the descriptions, functions, procedures, suggestions, methods and/or operational flowcharts disclosed herein, etc. from one or more other devices. there is. For example, one or more transceivers 206a and 206b may be connected to one or more processors 202a and 202b and may transmit and receive wireless signals. For example, one or more processors 202a, 202b may control one or more transceivers 206a, 206b to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors 202a and 202b may control one or more transceivers 206a and 206b to receive user data, control information, or wireless signals from one or more other devices. In addition, one or more transceivers (206a, 206b) may be connected to one or more antennas (208a, 208b), and one or more transceivers (206a, 206b) may be connected to the description and functions disclosed in this document through one or more antennas (208a, 208b). , may be set to transmit and receive user data, control information, wireless signals/channels, etc. mentioned in procedures, proposals, methods and/or operation flow charts, etc. In this document, one or more antennas may be multiple physical antennas or multiple logical antennas (eg, antenna ports). One or more transceivers (206a, 206b) process the received user data, control information, wireless signals/channels, etc. using one or more processors (202a, 202b), and convert the received wireless signals/channels, etc. from the RF band signal. It can be converted to a baseband signal. One or more transceivers (206a, 206b) may convert user data, control information, wireless signals/channels, etc. processed using one or more processors (202a, 202b) from a baseband signal to an RF band signal. To this end, one or more transceivers 206a, 206b may include (analog) oscillators and/or filters.

Wireless device structure applicable to this disclosure

FIG. 3 is a diagram illustrating another example of a wireless device applied to the present disclosure.

Referring to FIG. 3, the wireless device 300 corresponds to the wireless devices 200a and 200b of FIG. 2 and includes various elements, components, units/units, and/or modules. ) can be composed of. For example, the wireless device 300 may include a communication unit 310, a control unit 320, a memory unit 330, and an additional element 340. The communication unit may include communication circuitry 312 and transceiver(s) 314. For example, communication circuitry 312 may include one or more processors 202a and 202b and/or one or more memories 204a and 204b of FIG. 2 . For example, transceiver(s) 314 may include one or more transceivers 206a, 206b and/or one or more antennas 208a, 208b of FIG. 2. The control unit 320 is electrically connected to the communication unit 310, the memory unit 330, and the additional element 340 and controls overall operations of the wireless device. For example, the control unit 320 may control the electrical/mechanical operation of the wireless device based on the program/code/command/information stored in the memory unit 330. In addition, the control unit 320 transmits the information stored in the memory unit 330 to the outside (e.g., another communication device) through the communication unit 310 through a wireless/wired interface, or to the outside (e.g., to another communication device) through the communication unit 310. Information received through a wireless/wired interface from another communication device can be stored in the memory unit 330.

The additional element 340 may be configured in various ways depending on the type of wireless device. For example, the additional element 340 may include at least one of a power unit/battery, an input/output unit, a driving unit, and a computing unit. Although not limited thereto, the wireless device 300 includes robots (FIG. 1, 100a), vehicles (FIG. 1, 100b-1, 100b-2), XR devices (FIG. 1, 100c), and portable devices (FIG. 1, 100d). ), home appliances (Figure 1, 100e), IoT devices (Figure 1, 100f), digital broadcasting terminals, hologram devices, public safety devices, MTC devices, medical devices, fintech devices (or financial devices), security devices, climate/ It can be implemented in the form of an environmental device, AI server/device (FIG. 1, 140), base station (FIG. 1, 120), network node, etc. Wireless devices can be mobile or used in fixed locations depending on the usage/service.

In FIG. 3 , various elements, components, units/parts, and/or modules within the wireless device 300 may be entirely interconnected through a wired interface, or at least some of them may be wirelessly connected through the communication unit 310. For example, within the wireless device 300, the control unit 320 and the communication unit 310 are connected by wire, and the control unit 320 and the first unit (e.g., 130, 140) are connected wirelessly through the communication unit 310. can be connected Additionally, each element, component, unit/part, and/or module within the wireless device 300 may further include one or more elements. For example, the control unit 320 may be comprised of one or more processor sets. For example, the control unit 320 may be composed of a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphics processing processor, and a memory control processor. As another example, the memory unit 330 may be comprised of RAM, dynamic RAM (DRAM), ROM, flash memory, volatile memory, non-volatile memory, and/or a combination thereof. It can be configured.

Mobile devices to which this disclosure is applicable

FIG. 4 is a diagram illustrating an example of a portable device to which the present disclosure is applied.

Figure 4 illustrates a portable device to which the present disclosure is applied. Portable devices may include smartphones, smart pads, wearable devices (e.g., smart watches, smart glasses), and portable computers (e.g., laptops, etc.). A mobile device may be referred to as a mobile station (MS), user terminal (UT), mobile subscriber station (MSS), subscriber station (SS), advanced mobile station (AMS), or wireless terminal (WT).

Referring to FIG. 4, the portable device 400 includes an antenna unit 408, a communication unit 410, a control unit 420, a memory unit 430, a power supply unit 440a, an interface unit 440b, and an input/output unit 440c. ) may include. The antenna unit 408 may be configured as part of the communication unit 410. Blocks 410 to 430/440a to 440c correspond to blocks 310 to 330/340 in FIG. 3, respectively.

The communication unit 410 can transmit and receive signals (eg, data, control signals, etc.) with other wireless devices and base stations. The control unit 420 can control the components of the portable device 400 to perform various operations. The control unit 420 may include an application processor (AP). The memory unit 430 may store data/parameters/programs/codes/commands necessary for driving the portable device 400. Additionally, the memory unit 430 can store input/output data/information, etc. The power supply unit 440a supplies power to the portable device 400 and may include a wired/wireless charging circuit, a battery, etc. The interface unit 440b may support connection between the mobile device 400 and other external devices. The interface unit 440b may include various ports (eg, audio input/output ports, video input/output ports) for connection to external devices. The input/output unit 440c may input or output image information/signals, audio information/signals, data, and/or information input from the user. The input/output unit 440c may include a camera, a microphone, a user input unit, a display unit 440d, a speaker, and/or a haptic module.

For example, in the case of data communication, the input/output unit 440c acquires information/signals (e.g., touch, text, voice, image, video) input from the user, and the obtained information/signals are stored in the memory unit 430. It can be saved. The communication unit 410 can convert the information/signal stored in the memory into a wireless signal and transmit the converted wireless signal directly to another wireless device or to a base station. Additionally, the communication unit 410 may receive a wireless signal from another wireless device or a base station and then restore the received wireless signal to the original information/signal. The restored information/signal may be stored in the memory unit 430 and then output in various forms (eg, text, voice, image, video, haptic) through the input/output unit 440c.

Types of wireless devices to which this disclosure is applicable

FIG. 5 is a diagram illustrating an example of a vehicle or autonomous vehicle applied to the present disclosure.

5 illustrates a vehicle or autonomous vehicle to which the present disclosure is applied. A vehicle or autonomous vehicle can be implemented as a mobile robot, vehicle, train, aerial vehicle (AV), ship, etc., and is not limited to the form of a vehicle.

Referring to FIG. 5, the vehicle or autonomous vehicle 500 includes an antenna unit 508, a communication unit 510, a control unit 520, a drive unit 540a, a power supply unit 540b, a sensor unit 540c, and an autonomous driving unit. It may include a portion 540d. The antenna unit 550 may be configured as part of the communication unit 510. Blocks 510/530/540a to 540d correspond to blocks 410/430/440 in FIG. 4, respectively.

The communication unit 510 may transmit and receive signals (e.g., data, control signals, etc.) with external devices such as other vehicles, base stations (e.g., base stations, road side units, etc.), and servers. The control unit 520 may control elements of the vehicle or autonomous vehicle 500 to perform various operations. The control unit 520 may include an electronic control unit (ECU).

Figure 6 is a diagram showing an example of an AI device applied to the present disclosure. As an example, AI devices include fixed devices such as TVs, projectors, smartphones, PCs, laptops, digital broadcasting terminals, tablet PCs, wearable devices, set-top boxes (STBs), radios, washing machines, refrigerators, digital signage, robots, vehicles, etc. It can be implemented as a device or a movable device.

Referring to FIG. 6, the AI device 600 includes a communication unit 610, a control unit 620, a memory unit 630, an input/output unit (640a/640b), a learning processor unit 640c, and a sensor unit 640d. may include. Blocks 610 to 630/640a to 640d may correspond to blocks 310 to 330/340 of FIG. 3, respectively.

The communication unit 610 uses wired and wireless communication technology to communicate with wired and wireless signals (e.g., sensor information, user Input, learning model, control signal, etc.) can be transmitted and received. To this end, the communication unit 610 may transmit information in the memory unit 630 to an external device or transmit a signal received from an external device to the memory unit 630.

The control unit 620 may determine at least one executable operation of the AI device 600 based on information determined or generated using a data analysis algorithm or a machine learning algorithm. And, the control unit 620 can control the components of the AI device 600 to perform the determined operation. For example, the control unit 620 may request, search, receive, or utilize data from the learning processor unit 640c or the memory unit 630, and may select at least one operation that is predicted or determined to be desirable among the executable operations. Components of the AI device 600 can be controlled to execute operations. In addition, the control unit 620 collects history information including the operation content of the AI device 600 or user feedback on the operation, and stores it in the memory unit 630 or the learning processor unit 640c, or the AI server ( It can be transmitted to an external device such as Figure 1, 140). The collected historical information can be used to update the learning model.

The memory unit 630 can store data supporting various functions of the AI device 600. For example, the memory unit 630 may store data obtained from the input unit 640a, data obtained from the communication unit 610, output data from the learning processor unit 640c, and data obtained from the sensing unit 640. Additionally, the memory unit 630 may store control information and/or software codes necessary for operation/execution of the control unit 620.

The input unit 640a can obtain various types of data from outside the AI device 600. For example, the input unit 620 may obtain training data for model training and input data to which the learning model will be applied. The input unit 640a may include a camera, microphone, and/or a user input unit. The output unit 640b may generate output related to vision, hearing, or tactile sensation. The output unit 640b may include a display unit, a speaker, and/or a haptic module. The sensing unit 640 may obtain at least one of internal information of the AI device 600, surrounding environment information of the AI device 600, and user information using various sensors. The sensing unit 640 may include a proximity sensor, an illumination sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, an optical sensor, a microphone, and/or a radar. there is.

The learning processor unit 640c can train a model composed of an artificial neural network using training data. The learning processor unit 640c may perform AI processing together with the learning processor unit of the AI server (FIG. 1, 140). The learning processor unit 640c may process information received from an external device through the communication unit 610 and/or information stored in the memory unit 630. Additionally, the output value of the learning processor unit 640c may be transmitted to an external device through the communication unit 610 and/or stored in the memory unit 630.

Figure 7 is a diagram illustrating a method of processing a transmission signal applied to the present disclosure. As an example, the transmission signal may be processed by a signal processing circuit. At this time, the signal processing circuit 700 may include a scrambler 710, a modulator 720, a layer mapper 730, a precoder 740, a resource mapper 750, and a signal generator 760. At this time, as an example, the operation/function of FIG. 7 may be performed in the processors 202a and 202b and/or transceivers 206a and 206b of FIG. 2. Additionally, as an example, the hardware elements of FIG. 7 may be implemented in the processors 202a and 202b and/or transceivers 206a and 206b of FIG. 2. As an example, blocks 710 to 760 may be implemented in processors 202a and 202b of FIG. 2. Additionally, blocks 710 to 750 may be implemented in the processors 202a and 202b of FIG. 2, and block 760 may be implemented in the transceivers 206a and 206b of FIG. 2, and are not limited to the above-described embodiment.

The codeword can be converted into a wireless signal through the signal processing circuit 700 of FIG. 7. Here, a codeword is an encoded bit sequence of an information block. The information block may include a transport block (eg, UL-SCH transport block, DL-SCH transport block). Wireless signals may be transmitted through various physical channels (eg, PUSCH, PDSCH). Specifically, the codeword may be converted into a scrambled bit sequence by the scrambler 710. The scramble sequence used for scrambling is generated based on an initialization value, and the initialization value may include ID information of the wireless device. The scrambled bit sequence may be modulated into a modulation symbol sequence by the modulator 720. Modulation methods may include pi/2-binary phase shift keying (pi/2-BPSK), m-phase shift keying (m-PSK), and m-quadrature amplitude modulation (m-QAM).

The complex modulation symbol sequence may be mapped to one or more transport layers by the layer mapper 730. The modulation symbols of each transport layer may be mapped to corresponding antenna port(s) by the precoder 740 (precoding). The output z of the precoder 740 can be obtained by multiplying the output y of the layer mapper 730 with the precoding matrix W of N*M. Here, N is the number of antenna ports and M is the number of transport layers. Here, the precoder 740 may perform precoding after performing transform precoding (eg, discrete Fourier transform (DFT) transform) on complex modulation symbols. Additionally, the precoder 740 may perform precoding without performing transform precoding.

The resource mapper 750 can map the modulation symbols of each antenna port to time-frequency resources. A time-frequency resource may include a plurality of symbols (eg, CP-OFDMA symbol, DFT-s-OFDMA symbol) in the time domain and a plurality of subcarriers in the frequency domain. The signal generator 760 generates a wireless signal from the mapped modulation symbols, and the generated wireless signal can be transmitted to another device through each antenna. To this end, the signal generator 760 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. .

The signal processing process for the received signal in the wireless device may be configured as the reverse of the signal processing process (710 to 760) of FIG. 7. As an example, a wireless device (eg, 200a and 200b in FIG. 2) may 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. Afterwards, the baseband signal can be restored to a codeword through a resource de-mapper process, postcoding process, demodulation process, and de-scramble process. The codeword can be restored to the original information block through decoding. Accordingly, a signal processing circuit (not shown) for a received signal may include a signal restorer, resource de-mapper, postcoder, demodulator, de-scrambler, and decoder.

6G communication system

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

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

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

FIG. 10 is a diagram illustrating an example of a communication structure that can be provided in a 6G system applicable to the present disclosure.

Referring to Figure 10, the 6G system is expected to have simultaneous wireless communication connectivity 50 times higher than that of the 5G wireless communication system. URLLC, a key feature of 5G, is expected to become an even more mainstream technology in 6G communications by providing end-to-end delays of less than 1ms. At this time, the 6G system will have much better volume spectrum efficiency, unlike the frequently used area spectrum efficiency. 6G systems can provide very long battery life and advanced battery technologies for energy harvesting, so mobile devices in 6G systems may not need to be separately charged.

Core implementation technology of 6G system

- Artificial Intelligence (AI)

The most important and newly introduced technology in the 6G system is AI. AI was not involved in the 4G system. 5G systems will support partial or very limited AI. However, 6G systems will be AI-enabled for full automation. Advances in machine learning will create more intelligent networks for real-time communications in 6G. Introducing AI in communications can simplify and improve real-time data transmission. AI can use numerous analytics to determine how complex target tasks are performed. In other words, AI can increase efficiency and reduce processing delays.

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

Recently, attempts have been made to integrate AI with wireless communication systems, but these are focused on the application layer and network layer, and in particular, deep learning is focused on wireless resource management and allocation. come. However, this research is gradually advancing to the MAC layer and physical layer, and attempts are being made to combine deep learning with wireless transmission, especially in the physical layer. AI-based physical layer transmission means applying signal processing and communication mechanisms based on AI drivers, rather than traditional communication frameworks, in terms of fundamental signal processing and communication mechanisms. For example, deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO (multiple input multiple output) mechanism, It may include AI-based resource scheduling and allocation.

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

However, application of DNN for transmission in the physical layer may have the following problems.

Deep learning-based AI algorithms require a large amount of training data to optimize training parameters. However, due to limitations in acquiring data from a specific channel environment as training data, a lot of training data is used offline. This means that static training on training data in a specific channel environment may result in a contradiction between the dynamic characteristics and diversity of the wireless channel.

Additionally, current deep learning mainly targets real signals. However, signals of the physical layer of wireless communication are complex signals. In order to match the characteristics of wireless communication signals, more research is needed on neural networks that detect complex domain signals.

Below, we will look at machine learning in more detail.

Machine learning refers to a series of operations that train machines to create machines that can perform tasks that are difficult or difficult for humans to perform. Machine learning requires data and a learning model. In machine learning, data learning methods can be broadly divided into three types: supervised learning, unsupervised learning, and reinforcement learning.

Neural network learning is intended to minimize errors in output. Neural network learning repeatedly inputs learning data into the neural network, calculates the output of the neural network and the error of the target for the learning data, and backpropagates the error of the neural network from the output layer of the neural network to the input layer to reduce the error. ) is the process of updating the weight of each node in the neural network.

Supervised learning uses training data in which the correct answer is labeled, while unsupervised learning may not have the correct answer labeled in the training data. That is, for example, in the case of supervised learning on data classification, the learning data may be data in which each training data is labeled with a category. Labeled learning data is input to a neural network, and error can be calculated by comparing the output (category) of the neural network with the label of the learning data. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to ensure that the neural network quickly achieves a certain level of performance to increase efficiency, and in the later stages of training, a low learning rate can be used to increase accuracy.

Learning methods may vary depending on the characteristics of the data. For example, in a communication system, when the goal is to accurately predict data transmitted from a transmitter at a receiver, it is preferable to perform learning using supervised learning rather than unsupervised learning or reinforcement learning.

The learning model corresponds to the human brain, and can be considered the most basic linear model. However, deep learning is a machine learning paradigm that uses a highly complex neural network structure, such as artificial neural networks, as a learning model. ).

Neural network cores used as learning methods are broadly divided into deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent neural networks (recurrent boltzmann machine). And this learning model can be applied.

Terahertz (THz) communications

THz communication can be applied in the 6G system. As an example, the data transfer rate can be increased by increasing the bandwidth. This can be accomplished by using sub-THz communications with wide bandwidth and applying advanced massive MIMO technology.

Figure 9 is a diagram showing an electromagnetic spectrum applicable to the present disclosure. As an example, referring to Figure 9, THz waves, also known as submillimeter radiation, typically represent a frequency band between 0.1 THz and 10 THz with a corresponding wavelength in the range of 0.03 mm-3 mm. The 100GHz-300GHz band range (Sub THz band) is considered the main part of the THz band for cellular communications. Adding the Sub-THz band to the mmWave band increases 6G cellular communication capacity. Among the defined THz bands, 300GHz-3THz is in the far infrared (IR) frequency band. The 300GHz-3THz band is part of the wideband, but it is at the border of the wideband and immediately behind the RF band. Therefore, this 300 GHz-3 THz band shows similarities to RF.

Key characteristics of THz communications include (i) widely available bandwidth to support very high data rates, (ii) high path loss occurring at high frequencies (highly directional antennas are indispensable). The narrow beamwidth produced by a highly directional antenna reduces interference. The small wavelength of THz signals allows a much larger number of antenna elements to be integrated into devices and BSs operating in this band. This enables the use of advanced adaptive array techniques that can overcome range limitations.

Terahertz (THz) wireless communication

Figure 10 is a diagram illustrating a THz communication method applicable to the present disclosure.

Referring to Figure 10, THz wireless communication uses wireless communication using THz waves with a frequency of approximately 0.1 to 10 THz (1 THz = 1012 Hz), and is a terahertz (THz) band wireless communication that uses a very high carrier frequency of 100 GHz or more. It can mean communication. THz waves are located between RF (Radio Frequency)/millimeter (mm) and infrared bands. (i) Compared to visible light/infrared, they penetrate non-metal/non-polarized materials better and have a shorter wavelength than RF/millimeter waves, so they have high straightness. Beam focusing may be possible.

Artificial Intelligence System

Figure 11 shows the structure of a perceptron included in an artificial neural network applicable to the present disclosure. Additionally, Figure 12 shows an artificial neural network structure applicable to the present disclosure.

As described above, an artificial intelligence system can be applied in the 6G system. At this time, as an example, the artificial intelligence system may operate based on a learning model corresponding to the human brain, as described above. At this time, the machine learning paradigm that uses a highly complex neural network structure, such as artificial neural networks, as a learning model can be called deep learning. In addition, the neural network core used as a learning method is largely divided into deep neural network (DNN), convolutional deep neural network (CNN), and recurrent neural network (RNN). There is a way. At this time, as an example, referring to FIG. 11, the artificial neural network may be composed of several perceptrons. At this time, the input vector x={x ₁ , x ₂ , … , x _d }, weights {W ₁ , W ₂ , … are assigned to each component. , W _d } are multiplied, the results are summed, and the entire process of applying the activation function σ(·) can be called a perceptron. If the large artificial neural network structure expands the simplified perceptron structure shown in FIG. 11, the input vector can be applied to different multi-dimensional perceptrons. For convenience of explanation, input or output values are referred to as nodes.

Meanwhile, the perceptron structure shown in FIG. 11 can be described as consisting of a total of three layers based on input and output values. An artificial neural network with H (d+1) dimensional perceptrons between ^{the 1st} layer and ^{the 2nd} layer, and K (H+1) dimensional perceptrons between the ^2nd layer and the ^3rd layer can be expressed as shown in Figure 12. You can.

At this time, the layer where the input vector is located is called the input layer, the layer where the final output value is located is called the output layer, and all layers located between the input layer and the output layer are called hidden layers. For example, three layers are shown in FIG. 12, but when counting the actual number of artificial neural network layers, the input layer is counted excluding the input layer, so the artificial neural network illustrated in FIG. 12 can be understood as having a total of two layers. An artificial neural network is constructed by two-dimensionally connecting perceptrons of basic blocks.

The above-described input layer, hidden layer, and output layer can be jointly applied not only to the multi-layer perceptron, but also to various artificial neural network structures such as CNN and RNN, which will be described later. As the number of hidden layers increases, the artificial neural network becomes deeper, and the machine learning paradigm that uses a sufficiently deep artificial neural network as a learning model can be called deep learning. Additionally, the artificial neural network used for deep learning can be called a deep neural network (DNN).

13 shows a deep neural network applicable to this disclosure.

Referring to Figure 13, the deep neural network may be a multi-layer perceptron consisting of 8 hidden layers and 8 output layers. At this time, the multi-layer perceptron structure can be expressed as a fully-connected neural network. In a fully connected neural network, no connection exists between nodes located on the same layer, and connections can only exist between nodes located on adjacent layers. DNN has a fully connected neural network structure and is composed of a combination of multiple hidden layers and activation functions, so it can be usefully applied to identify correlation characteristics between input and output. Here, the correlation characteristic may mean the joint probability of input and output.

14 shows a convolutional neural network applicable to this disclosure. Additionally, Figure 15 shows a filter operation of a convolutional neural network applicable to this disclosure.

For example, depending on how a plurality of perceptrons are connected to each other, various artificial neural network structures different from the above-described DNN can be formed. At this time, in DNN, nodes located inside one layer are arranged in a one-dimensional vertical direction. However, referring to FIG. 14, it can be assumed that the nodes are arranged two-dimensionally with w nodes horizontally and h nodes vertically. (Convolutional neural network structure in Figure 14). In this case, since a weight is added for each connection in the connection process from one input node to the hidden layer, a total of h × w weights must be considered. Since there are h×w nodes in the input layer, a total of h ² w ² weights may be required between two adjacent layers.

In addition, the convolutional neural network of Figure 14 has a problem in that the number of weights increases exponentially depending on the number of connections, so instead of considering all mode connections between adjacent layers, it is assumed that a small filter exists. You can. For example, as shown in FIG. 15, weighted sum and activation function calculations can be performed on areas where filters overlap.

At this time, one filter has a weight corresponding to the number of filters, and the weight can be learned so that a specific feature in the image can be extracted and output as a factor. In Figure 15, a 3×3 filter is applied to the upper leftmost 3×3 area of the input layer, and the output value as a result of performing the weighted sum and activation function calculation for the corresponding node can be stored at z ₂₂ .

At this time, the above-described filter scans the input layer and moves at regular intervals horizontally and vertically to perform weighted sum and activation function calculations, and the output value can be placed at the current filter position. Since this operation method is similar to the convolution operation on images in the field of computer vision, a deep neural network with this structure is called a convolutional neural network (CNN), and the The hidden layer may be called a convolutional layer. Additionally, a neural network with multiple convolutional layers may be referred to as a deep convolutional neural network (DCNN).

Additionally, in the convolutional layer, the number of weights can be reduced by calculating a weighted sum from the node where the current filter is located, including only the nodes located in the area covered by the filter. Because of this, one filter can be used to focus on features for a local area. Accordingly, CNN can be effectively applied to image data processing in which the physical distance in a two-dimensional area is an important decision criterion. Meanwhile, CNN may have multiple filters applied immediately before the convolution layer, and may generate multiple output results through the convolution operation of each filter.

Meanwhile, depending on the data properties, there may be data for which sequence characteristics are important. Considering the length variability and precedence relationship of these sequence data, elements in the data sequence are input one by one at each time step, and the output vector (hidden vector) of the hidden layer output at a specific time point is input together with the next element in the sequence. The structure that applies this method to an artificial neural network can be called a recurrent neural network structure.

Figure 16 shows a neural network structure with a cyclic loop applicable to the present disclosure. Figure 17 shows the operational structure of a recurrent neural network applicable to the present disclosure.

Referring to FIG. 16, a recurrent neural network (RNN) is a recurrent neural network (RNN) that uses elements of a certain line of sight t in a data sequence {x ₁ ^(t) , x ₂ ^(t) ,... ^In _{the process} ^of _inputting ^, , z _H ^(t-1) } can be input together to have a structure that applies a weighted sum and activation function. The reason for passing the hidden vector to the next time point like this is because the information in the input vector from previous time points is considered to be accumulated in the hidden vector at the current time point.

Additionally, referring to FIG. 17, the recurrent neural network can operate in a predetermined time point order with respect to the input data sequence. At this time, the input vector at time point 1 {x ₁ ^(t) , x ₂ ^(t) , … , x _d ^(t) } is the hidden vector {z ₁ ⁽¹⁾ , z ₂ ⁽¹⁾ , … when input to the recurrent neural network. , z _H ⁽¹⁾ } is the input vector at point 2 {x ₁ ⁽²⁾ , x ₂ ⁽²⁾ , … , x _d ⁽²⁾ }, and the vectors of the hidden layer {z ₁ ⁽²⁾ , z ₂ ⁽²⁾ , … , z _H ⁽²⁾ } is determined. This process progresses from time point 2, time point 3, … , is performed repeatedly until time T.

Meanwhile, when multiple hidden layers are placed within a recurrent neural network, it is called a deep recurrent neural network (DRNN). Recurrent neural networks are designed to be useful for sequence data (e.g., natural language processing).

As a neural network core used as a learning method, in addition to DNN, CNN, and RNN, it includes restricted Boltzmann machine (RBM), deep belief networks (DBN), deep Q-Network, and It includes various deep learning techniques, and can be applied to fields such as computer vision, speech recognition, natural language processing, and voice/signal processing.

Recently, attempts have been made to integrate AI with wireless communication systems, but this involves the application layer, network layer, and especially in the case of deep learning, wireless resource management and allocation. has been focused on the field. However, this research is gradually advancing to the MAC layer and physical layer, and in particular, attempts are being made to combine deep learning with wireless transmission in the physical layer. AI-based physical layer transmission means applying signal processing and communication mechanisms based on AI drivers, rather than traditional communication frameworks, in terms of fundamental signal processing and communication mechanisms. For example, deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO mechanism, AI-based resource scheduling ( It may include scheduling and allocation, etc.

Specific embodiments of the present invention

This disclosure is for performing learning on a receiver model in a wireless communication system and relates to technology for performing online learning. Hereinafter, the present disclosure describes various embodiments for supporting and performing online learning. Specifically, the present disclosure proposes an online learning technology for a physical layer receiver consisting of a machine learning model or a deep learning model in a wireless communication system.

Wireless communication systems can provide various types of communication services such as voice and data. Recently, with the great development of artificial intelligence technology, attempts to apply artificial intelligence technology to communication systems are rapidly increasing. The integration of artificial intelligence technology can be largely divided into C4AI (communications for AI), which develops communication technology to support artificial intelligence, and AI4C (AI for communications), which utilizes artificial intelligence technology to improve communication performance. In the case of AI4C, there is an attempt to increase design efficiency by replacing the channel encoder/decoder with an end-to-end auto-encoder. In the case of C4AI, federated learning, one of the distributed learning techniques, is used to determine the weight or gradient of the model without sharing the raw data of the device. By sharing only the gradient) with the server, a common prediction model can be updated while protecting personal information. Additionally, a method of distributing the load of the device, network edge, and cloud server has also been proposed using a split inference technique.

This disclosure addresses the problem of online learning using reference signals in a wireless communication system that delivers end-to-end messages using a transmitter and receiver configured with machine learning models. Here, the machine learning model may include a neural network model. A neural network-based wireless communication system utilizes the characteristic of neural networks to approximate arbitrary or nonlinear functions well. In a situation where a message passes through a wireless channel in a transmission neural network and is then received by a reception neural network, good transmission and reception performance can be obtained by making good use of the above-described characteristics of the neural network. However, to obtain good performance, neural network training is required during actual operation. As the complexity of the model used in the terminal increases, all complex wireless channels can be covered, but the increase in complexity will act as a burden on implementation. The model used in the terminal must be designed with appropriate complexity. Meanwhile, when the terminal moves, the channel environment continues to change over time, so there is a high probability that the terminal's neural network will not sufficiently reflect the channel characteristics. Therefore, online learning is necessary.

Operating states allowed for the terminal include a connected state, which is a state in which data can be transmitted or received, and an idle state, which does not transmit or receive data and minimizes power consumption. When the terminal operates in an idle state, it is difficult to perform online learning while the terminal performs a sleep operation. In the idle state, the terminal wakes up from sleep at a DRX cycle (discontinuous reception cycle) and checks a paging message that has arrived at it or measures nearby cells. Specifically, the terminal may enter a wake-up state by activating the receiver in a DRX cycle period and attempt to receive data or perform measurement. Therefore, only in the wake-up period, the terminal can receive the reference signal and perform online learning. However, if the terminal moves significantly during the sleep state, the channel changes significantly, and a problem may arise in which online learning cannot be performed efficiently due to late updates. Furthermore, the terminal may be one of various types of devices, ranging from IoT devices to high-end smartphones. As there are various types of devices, various neural network models may exist. In this situation, if online learning is performed by replacing the neural network model for the receiver of each terminal through the network, a problem of greatly increasing complexity will occur.

In order to solve the above-mentioned problems, the present disclosure uses a generative neural network to easily learn various channel propagation environments such as below 6GHz communication, mmWave communication, and THz communication, and provides online learning. We propose a technology that can effectively perform and at the same time minimize power.

According to the proposed technology, even if the receiver of the physical layer enters sleep mode while operating in an idle state, online learning for the physical layer neural network can be performed based on the channel data generated by the channel generation network in the sleep period. . Additionally, the proposed technology evaluates the uncertainty of channel creation data and performs active learning based on the uncertainty, thereby preventing unnecessary learning in sleep mode.

Active learning is a type of machine learning, and is a technique that performs labeling of data for learning based on user interaction. Conversely, passive learning can be understood as supervised learning that uses already labeled training data.

In [Equation 1], x means data, y means label, D means data set, and p(D) means distribution of data set.

In the case of manual learning, the label y for x in the data set D is added, and the samples (x, y) in the training data set D that follow the distribution p(D) can all be given in advance. In the case of active learning, when training, Here, the labeling task in active learning is called 'annotation'. In active learning, given x, the entity that provides information about label y may be referred to as 'user', 'oracle', 'annotator', etc.

Figure 18 shows sampling methods for active learning according to an embodiment of the present disclosure. Figure 18 illustrates three representative methods of active learning. The three methods involve sampling data x from an input distribution 1810. Here, the input distribution 1810 may be referred to as an instance space. In the membership query synthesis method 1820-1, the model synthesizes samples x belonging to the input distribution 1810 for learning, and requests labeling y for the sample x from the oracle. That is, the model synthesizes the sample x and queries the oracle (1830). Stream-based selective sampling (1820-2) selectively separates data x that is continuously extracted from the input distribution (1810) and sends the label y for the separated data x to the oracle (1830). request. Pool-based sampling (1820-3) includes all data Request to the Oracle (1830). In this way, by actively participating in the data collection process, the model can reduce the number of samples required for training and improve performance.

In other words, active learning can be used to reduce the cost of obtaining training data. In data-based machine learning, securing data requires a lot of cost. To save these large costs, active learning can be used to improve learning ability even with small amounts of data. Additionally, active learning can improve the speed and performance of learning.

Active sampling in active learning can be broadly divided into two types: uncertainty sampling and diversity sampling. Uncertainty sampling is a method of increasing effectiveness by learning the most ambiguous data first during learning, and diversity sampling is a method of quickly learning the entire distribution by sampling representative data evenly from the entire data distribution.

The effect of uncertainty sampling can be confirmed in an example of a simple binary classification task, an example of which is shown in FIGS. 19A to 19C. 19A to 19C show examples of results of active learning and passive learning according to an embodiment of the present disclosure. Figure 19a illustrates the overall distribution of sampling data. As shown in Figure 19a, learning begins with all data acquired through pull-based learning. Figure 19b illustrates the results of passive learning. Because random sampling is performed, input values are picked evenly from the entire distribution, and the boundary line is learned inaccurately. Figure 19c illustrates the results of active learning sampling centered on an area with high uncertainty near the boundary line. Referring to Figure 19c, it is confirmed that good results are obtained even when using a small amount of samples. Active learning can be applied not only to the classification task illustrated in FIGS. 19A to 19C, but also to a regression task.

의 샘플 복잡도를 가지는데 비해, 다수 모델의 결정 결과를 기반으로 결정하는 위원회 기반 질의(query-by-committee) 방식의 능동 학습은

복잡도의 데이터를 수신한 후,

복잡도의 데이터를 레이블링 학습할 수 있다. 여기서,

는 학습 모델의 에러 성능을 나타내는 값이다.The effectiveness of active learning in uncertainty sampling has been theoretically proven for some analyzable cases. Compared to passive learning, active learning is known to be able to reduce the number of samples required for training to the logarithmic complexity level. Assuming an ideal case and considering a simple binary classifier, it is easily expected that a complexity reduction of the logarithmic complexity level can be achieved by applying sampling of active learning based on binary search rather than exhaustive search. As a more specific example, considering the learning problem of data uniformly sampled from a unit sphere plane in d-dimensional space, for a homogeneous linear separator, manual learning is

Compared to the sample complexity of

After receiving data of complexity,

You can learn to label data of any complexity. here,

is a value representing the error performance of the learning model.

In the present disclosure, a Bayesian model that can quantify uncertainty can be used to evaluate uncertainty for samples in a model. At this time, the model parameter ϕ, which is the subject of evaluation of the uncertainty of the transceiver model, is not a deterministic value but a random variable. Learning the Bayesian model aims to find the posterior probability for data as shown in [Equation 2] below.

In [Equation 2], ϕ is the model parameter, D is the training data set, p(ϕ|D) is the prior distribution of the model parameter containing prior information about the model, x is the data, y is the output of the model, p (y|x,ϕ) is the probability of y given x and ϕ, and p(ϕ) is the prior distribution of ϕ. In [Equation 2], the denominator is the probability of the training data, called evidence, and is equal to p(D).

The predicted probability distribution p(y'|x',D) for new data x' can be calculated by marginalizing the model conditional probability and the posterior probability of ϕ and the model conditional probability as follows.

In [Equation 3], y' is the output of the new model, x' is new data, D is the training data set, and p(y|) means the probability distribution of the output given the training data.

Once the predicted probability distribution is obtained, the mean and variance can be determined using the predicted probability distribution. Since the model parameter ϕ is a random variable, the uncertainty of the model is reflected. Additionally, using [Equation 3], the variance of the prediction can be determined. Variance can be used for uncertainty assessment.

Except for linear models, closed form derivation of the posterior probability of ϕ during training is very difficult, and several methods have been proposed to solve this problem. In particular, approximate methods and sampling methods to obtain the posterior probability can be applied.

는 베이지안 예측 분포 p(y|x,θ)를 내포하는 범함수(functional)이다. 이하 [수학식 4]의 예와 같이, 획득 함수는 함수에 사전 분포의 주변화를 수행하는 범함수일 수 있다. 예를 들면, 섀넌 엔트로피가 이용될 수 있다. 이 경우, 불확실성은 주어진 기준 신호의 모델 추정 값의 최대 엔트로피 기준으로 평가될 수 있다.The acquisition function for estimating uncertainty can also be obtained by applying Bayesian assumptions. For example, the acquisition function can be obtained by reflecting the model's prior distribution for several possible acquisition functions and then integrating. In this case, the acquisition function

is a functional that implies the Bayesian prediction distribution p(y|x,θ). As in the example in [Equation 4] below, the acquisition function may be a functional function that performs marginalization of the prior distribution on the function. For example, Shannon entropy may be used. In this case, uncertainty can be evaluated based on the maximum entropy of the model estimate of a given reference signal.

In [Equation 4], x is the input of the model, D _train is training data, y is the output of the model, and H(y|x,D _train ) means the entropy of y under the conditions given x and D _train .

According to another embodiment, uncertainty may be evaluated based on the model's prediction and the mutual information amount of the model ϕ, as shown in [Equation 5] below.

In [Equation 5], y is the output of the model, x is the input of the model, ϕ is the model parameter, D _train is training data, and I(y|x,ϕ,D _train ) is the amount of mutual information given the input of the model. , E _p(ϕ|Dtrain) {H(y|x,ϕ)} means the average of the entropy for the model posterior distribution.

According to another embodiment, uncertainty may be evaluated based on the variance ratio of the model output, as shown in Equation 6 below.

In [Equation 6], variatioin _ratio is the variance ratio, x is the input of the model, D _train is training data, y is the output of the model, and max p(y|x,D _train ) is the output when a random variable input x is given. It refers to the maximum value of the conditional probability for a variable.

According to another embodiment, the acquisition function may determine the variance or standard deviation for the estimate from the Bayesian prediction distribution and estimate uncertainty based on the determined variance or standard deviation.

In various embodiments of the present disclosure, a generative network that outputs channel data for online learning may be used. A generative network is a neural network that models probability distributions, and can generate output samples by combining features obtained from training data with input values sampled according to a specific probability distribution. In various embodiments of the present disclosure, the terminal has a generation network for channel creation, and can obtain the terminal's own latent probability distribution from a base station or another terminal to obtain a latent vector value.

Figure 20 shows functional structures of devices supporting active learning according to an embodiment of the present disclosure. FIG. 20 illustrates a transmission and reception model in which the first device 2010 functions as a transmitter and the second device 2020 functions as a receiver among two devices 2010 and 2020 that perform communication according to an embodiment. In the case of downlink communication, the first device 2010 can be understood as a base station and the second device 2020 can be understood as a UE. In the case of uplink communication, the first device 2010 can be understood as a UE and the second device 2020 can be understood as a base station.

Referring to FIG. 20, the first device 2010 includes a transmit entity 2012 and a transmitter model 2014. The transmitting entity 2012 performs overall control and processing for data transmission. For example, the transmitting entity 2012 may generate transmission data and provide information necessary for the operation of the transmitter model 2014. The transmitter model (2014) is a data and reference signal processing block implemented with a neural network. The transmitter model 2014 generates a signal including at least one of data and a reference signal.

The second device 2020 includes a receive entity 2022, a receiver model 2024, an evaluation unit 2026, and a channel creation unit 2028. The receiving entity 2022 performs overall control and processing for data reception. For example, the transmitting entity 2012 processes the information output from the receiver model 2024, controls the learning procedure based on the uncertainty information output from the evaluation unit 2026, and provides a channel to the channel creation unit 2028. It can provide potential vectors for generating data. In addition, although not shown in FIG. 20, the receiving entity 2022 may generate feedback information or control information necessary for online learning and control the feedback information or control information to be transmitted to the first device 2010.

(k=0, 1, …, N)를 가지는 복수의 신경망들을 포함할 수 있다.The receiver model (2024) is a data processing block implemented with a neural network. The receiver model 2024 may include at least one neural network for performing at least one task related to the reference signal. Accordingly, the receiver model 2024 can selectively perform one of a plurality of tasks using reference signals received from the first device 2010. For example, receiver model 2024 may include deep neural networks (DNNs) for channel tasks. Each task has an index k, and the receiver model (2024) is a model parameter

It may include multiple neural networks with (k=0, 1, …, N).

는 모델 고유 파라미터 혹은 사전 학습된 메타 파라미터를 의미한다.

는 송신기 신경망 모델의 매개 변수로서, 능동 학습 기준 신호 k 및 데이터 전송 신호의 일종의 프리코딩(precoding)의 역할을 수행할 수 있다.

는 수신기 신경망의 매개 변수이다. 수신기는 송신기에서 송신된 능동 학습 기준 신호 k를 알고 있다.

및

은 기존 능동 학습 기준 신호 데이터 셋 D_RS를 이용하여 송신 및 수신기의 결합(joint) 손실 함수의 최적화

를 확률경사법(stochastic gradient decent method) 등을 수행함으로써 훈련될 수 있다. 구체적으로, 송신기

를 고정한 상태에서 기준 신호를 송신하고, 수신기

에 대해 확률 경사법을 이용하여 훈련을 수행한 후, 다시 수신기

을 고정한 상태에서 송신기

를 훈련하는 절차가 진행될 수 있다. 이러한 절차가 반복적으로 수행될 수 있다. 송신기를 훈련하는 경우, 수신기로부터 송신기로 손실(loss)이 전달될 수 있다. 이때, 수신기를 포함하는 장치는

를 알고 있을 수 있다.model parameters

refers to model-specific parameters or pre-learned meta parameters.

is a parameter of the transmitter neural network model and can serve as a kind of precoding of the active learning reference signal k and the data transmission signal.

are the parameters of the receiver neural network. The receiver knows the active learning reference signal k transmitted from the transmitter.

and

Optimization of the joint loss function of the transmitter and receiver using the existing active learning reference signal data set D _RS .

It can be trained by performing a stochastic gradient decent method, etc. Specifically, the transmitter

Transmit the reference signal with fixed, and the receiver

After performing training using the probability gradient method, the receiver again

With the transmitter fixed

Training procedures may proceed. This procedure can be performed repeatedly. When training a transmitter, loss may be transmitted from the receiver to the transmitter. At this time, the device including the receiver is

You may know.

The evaluation unit 2026 evaluates the signal received from the first device 2010. The evaluation results may include information indicating the uncertainty used for uncertainty sampling. For example, the evaluation unit 2026 may include a deep neural network (DNN for uncertainty measurement). The evaluation unit 2026 may generate a result of the acquisition function f _acq (x) and provide it to the receiving entity 2022.

및 및 수신기 모델

을 모두 이용할 수 있다. 도 20의 예에서, f_acq(x)는 수신기로 동작하는 제2 장치(2020)에 포함되지만, 송신기로 동작하는 제1 장치(2010)도 f_acq(x)를 포함할 수 있다. 송신기 및 수신기를 훈련하는 절차와 유사하게,

를 고정한 상태에서

이 기여하는 획득 값을 결정하고,

을 고정한 상태에서

가 기여하는 획득 값을 결정하는 반복적 절차를 통해, 획득 값들이 교대로 결정될 수 있다. 특히,

가 기여하는 획득 값을 결정하는 경우, 수신기로 동작하는 제2 장치(2020)는 제1 장치(2010)로부터

가 기여하는 획득 값을 획득할 수 있다. 평가의 출력은 확률 분포 혹은 확률 값을 포함할 수 있다.f _acq (x) is an acquisition function that evaluates uncertainty and evaluates data acquired from the generating network channel based on the transmitter model and receiver model. f _acq (x) is the transmitter model

and and receiver model

are all available. In the example of FIG. 20 , f _acq (x) is included in the second device 2020 operating as a receiver, but the first device 2010 operating as a transmitter may also include f _acq (x). Similar to the procedure for training transmitters and receivers,

With fixed

Determine the acquisition value to which this contributes,

With fixed

Through an iterative procedure of determining the acquisition value contributed by , the acquisition values can be determined alternately. especially,

When determining the acquired value contributed, the second device 2020, operating as a receiver, receives from the first device 2010

The acquisition value contributed by can be obtained. The output of the evaluation may include probability distributions or probability values.

The channel generator 2028 generates channel data. The channel generator 2028 may receive a latent vector representing channel characteristics from the receiving entity 2022 and generate channel data as learning data for training the receiver model 2024 based on the latent vector. The latent vector is used as an input to the channel creation network constituting the channel creation unit 2028, and represents the probability distribution of the channel to be created. Channel data may include at least one of channel information based on a potential vector (e.g., channel matrix, Doppler value, power value, etc.), reference signals passing through a channel specified by the channel information, and a reference signal pattern. For example, the channel generator 2028 may include a common channel generative deep neural network (DNN).

및 수신기의 모델 파라미터

를 포함한다. 여기서, k는 지원되는 N개의 채널 관련 태스크들 중 하나를 지시하는 인덱스로서, 채널 판별 신경망(예: 수신기 모델(2024))은 채널 관련된 태스크 개수 N 만큼 존재할 수 있다. 채널 관련된 기준 신호(reference signal) 종류 인덱스 k에 대응하는 송신기의 모델

및 수신기의 모델

가 태스크 k를 수행하는 모델들로 이해될 수 있다. k는 송신기 및 수신기가 운용하는 기준 신호 종류 수만큼 정의되며, 모두 하나의 신호 처리 태스크(signal processing task)이다. 예를 들어, 5G NR의 CSI-RS의 경우, 빔 추적 CSI-RS, 링크 상태 평가를 위한 CSI-RS, 타이밍 동기를 맞추기 위한 CSI-RS 등 적어도 3개의 태스크들이 정의될 수 있다.The transmission and reception model in Figure 20 is the model parameters of the transmitter for task k

and model parameters of the receiver.

Includes. Here, k is an index indicating one of N supported channel-related tasks, and a channel discrimination neural network (e.g., receiver model 2024) may exist as many as N channel-related tasks. Transmitter model corresponding to channel-related reference signal type index k

and the model of the receiver

can be understood as models that perform task k. k is defined as the number of reference signal types operated by the transmitter and receiver, all of which are one signal processing task. For example, in the case of CSI-RS in 5G NR, at least three tasks can be defined, including beam tracking CSI-RS, CSI-RS for link state evaluation, and CSI-RS for timing synchronization.

The channel creation neural network included in the channel creation unit 2028 may include M neural networks that are always less than or equal to the number of channel discrimination neural networks (e.g., receiver model 2024). Even though the number of tasks using a channel discrimination neural network is large, a channel ultimately has one characteristic. Therefore, it is possible to train a discriminative neural network (eg, receiver model) online using a channel generation neural network common to all terminals. The channel generation neural network takes the value z of the latent vector as input and can generate the training data channel required for the channel discriminant network as output. The value z of the latent vector can be obtained by sampling from a probability distribution corresponding to the context of the terminal. The probability distribution p(z) can be treated as a UE context latent distribution.

Terminal context can be understood as a set of all factors that affect a channel. For example, the factors that determine the context are the location information of the terminal, the acceleration of the terminal, the speed information of the terminal, the angular velocity of the terminal and posture information including angular acceleration, the movement state of external objects, the shape of the antenna, and sensing data. It may include at least one of (e.g., information acquired through sound and vision sensors). The aforementioned factors can be expressed as numerical vectors. Numerous terminal contexts can be derived by combining various factors. Systems according to various embodiments may define terminal contexts as a finite number of terminal context groups. The UE context group may be defined as an area that can share the potential distribution p(z), and may be referred to as a 'UE context group'. Examples of terminal context groups are shown in FIG. 21 below.

Figure 21 shows an example of areas divided according to latent distribution according to an embodiment of the present disclosure. Figure 21 illustrates a situation where at least one terminal context group is assigned to a geographic area. Referring to FIG. 21, the first base station 2120-1 provides cell A, the second base station 2120-2 provides cell B, the third base station 2120-3 provides cell C, and the UE 2110 ) is located in cell A. Three terminal context groups each having latent distributions p _A1 (z), p _A2 (z), and p _A3 (z) can be assigned to each of the three areas included in cell A. Additionally, one terminal context group with latent distribution p _B (z) may be assigned to cell B. Additionally, three terminal context groups each having latent distributions p _C1 (z), p _C2 (z), and p _C3 (z) can be assigned to the entire area of cell C. In other words, in the case of cell C, terminal context groups can be allocated in three overlapping areas. As a specific example, terminal context groups may be allocated for three classifications according to the moving speed of the terminal in the same terrain, or terminal context groups may be allocated for three classifications according to each speed distribution. Figure 21 illustrates a base station and a terminal to aid understanding, but the terminal context group can also be applied to a sidelink for communication between terminals.

The example in FIG. 21 shows the combination of a specific area or region and the movement properties of the terminal. The simplest example of assigning a terminal context group based on region is to distinguish cells or smaller areas with similar terrain based on location information. Areas with different potential distributions are determined by decomposing the propagation environment affecting the reference signal task in the mmWave or THz band and can serve as a basis for applying artificial intelligence models. Unlike the propagation characteristics of the low-frequency band, signals in the millimeter wave (mmWave) or THz band have greater straightness. Therefore, in a millimeter wave (mmWave) or THz band environment, the high-frequency propagation path distribution specified by reflection, diffraction, and refraction is affected not only by buildings and terrain in a static state, but also by moving objects, antenna placement, and terminal movement. Depending on the number of cases, there may be many. The geographical distribution where the terminal is located and the dynamic state of the terminal have the greatest influence in determining the potential distribution for the terminal. This means that the latent distribution p(z) according to the terminal context can be locally related to the distribution.

When the terminal is turned on, the terminal can perform cell search and base station communication. At this time, once network registration is completed, the terminal operates in idle mode. The section operating in idle mode can be divided into a wake-up section and a sleep section. The distribution of the wake-up section and sleep section depends on the setting of the DRX (discontinuous reception) cycle. At this time, according to various embodiments, a monitoring operation for the context of the terminal may be performed based on the DRX cycle.

Figure 22 shows an example of times when context monitoring is performed during a DRX cycle according to an embodiment of the present disclosure. Referring to FIG. 22, one DRX cycle includes a wake-up section 2202 and a sleep section 2204. Here, the wake-up period 2202 may be referred to as an on-duration. At this time, terminal context monitoring may be performed in the wake-up period 2202. For each wake-up section 2202 that appears repeatedly according to the DRX cycle, the terminal can determine whether the terminal context changes due to movement of the terminal or changes in the external environment. If the changed terminal context does not satisfy the latent distribution p(z) for sampling the current channel, the terminal may update the latent distribution through signaling from the base station or another terminal.

According to one embodiment, the need to update p(z) according to a change in terminal context may be determined by an uncertainty measurement network (e.g., evaluation unit 2026). If the probability of not satisfying the current environment p(z) exceeds a certain threshold Q _thresh , that is, the uncertainty evaluated based on the signal passing through the actual channel in the wake-up section 2202 exceeds the threshold Q _thresh If exceeded, an operation to update p(z) may be performed. This is because, if the terminal context changes due to a change in the environment, but p(z) that does not match the changed terminal context is used, uncertainty increases. Here, the threshold Q _thresh can be configured by the network. Based on the uncertainty measurement results and the threshold Q _thresh , active learning can be performed. The threshold Q _thresh may include an out-of-distribution threshold and an in-distribution threshold.

In the sleep period, all components within the terminal corresponding to the physical layer may be deactivated (eg, powered off). Therefore, since the reference signal cannot be received during the sleep period, the discriminant neural network that requires online learning (e.g., receiver model 2024) can be trained using the output of the channel generation neural network (e.g., channel generator 2028). there is. An example of online learning in a sleep section is shown in Figure 23 below.

Figure 23 shows an example of times when online learning is performed during a DRX cycle according to an embodiment of the present disclosure. Referring to FIG. 23, one DRX cycle includes a wake-up section 2302 and a sleep section 2304. As shown in Figure 23, online learning in idle mode can be performed during the online learning period D(t). D(t) is always shorter than or equal to the DRX period. The length of D(t) can be determined by an uncertainty measurement network (e.g., Evaluation Department (2026)). For example, the greater the uncertainty, the more learning is required, so the greater the uncertainty, the longer the length of D(t) can be. The receiver can adaptively determine D(t) such that the uncertainty does not exceed Q _thresh . To determine D(t), in the wake-up section 2302, uncertainty is based on reference signals received through the actual channel, rather than signals generated by the generation network (e.g., channel generator 2028). The output of a neural network (e.g., evaluation unit 2026) may be determined. The channel creation neural network (e.g., channel creation unit 2028) may be trained by offline learning or joint learning between other terminals and base stations.

Figure 24 shows an example of a procedure for setting up a receiver while operating in DRX mode according to an embodiment of the present disclosure. FIG. 24 illustrates a method of operating a UE, and the illustrated operations may be understood as operations of the second device 2020 of FIG. 20.

Referring to FIG. 24, in step S2401, the UE transmits capability information related to DRX. For example, capability information related to DRX includes whether DRX operation is supported, information related to DRX cycles (e.g. inactivity timer, long cycle length, short cycle length, short cycle timer, etc.), DRX preferred by the UE. It may contain at least one of the related parameters. According to one embodiment, for example, capability information related to DRX may include information indicating whether online learning can be performed during DRX operation, information indicating whether channel data can be generated, and at least one supportable It may include at least one piece of information indicating a terminal context item. In addition to capability information related to DRX, the UE may provide other types of capability information, for example, information related to supportable radio access technology (RAT), information related to duplex method, and parameters used in the layer. At least one of related information and information related to operation mode/state may be further transmitted. According to one embodiment, capability information related to DRX may be transmitted in response to an inquiry from a base station.

In step S2403, the UE receives configuration information related to DRX. Setting information related to DRX includes control information necessary for DRX operation. For example, configuration information related to DRX may include at least one of the length of each section within the DRX cycle, a timer value related to DRX operation, DRX cycle length, and HARQ-related parameters. Additionally, configuration information related to DRX may include information instructing DRX operation. According to one embodiment, the setting information includes information instructing to perform online learning during DRX operation, functions supportable for online learning (e.g., providing latent distribution information, transmitting a reference signal for online learning, uncertainty about the reference signal) sampling, etc.).

In step S2405, the UE checks context information during the on-section of the DRX cycle. The UE may activate the physical layer hardware during the on-period, obtain at least one of a signal, measurement information, and sensing information received from the base station, and determine the context based on the obtained information. According to one embodiment, the UE can check location information and check context information corresponding to the location information.

In step S2407, the UE sets up the receiver during the sleep-period of the DRX cycle. According to one embodiment, the receiver may include at least one neural network model. In this case, the UE may perform training on a neural network model during the sleep-interval. Specifically, the UE may generate channel data corresponding to context information and perform training on at least one neural network model based on the generated channel data. That is, the UE can perform training for one neural network model using the generated channel data as learning data. At this time, according to one embodiment, uncertainty sampling may be performed for active learning. Accordingly, the UE can perform online learning for the neural network model forming the receiver while reducing power consumption by disabling at least one physical layer hardware.

Figure 25 shows an example of a procedure corresponding to a change in context information according to an embodiment of the present disclosure. FIG. 25 illustrates a method of operating a UE, and the illustrated operations may be understood as operations of the second device 2020 of FIG. 20.

Referring to FIG. 25, in step S2501, the UE checks the context group during the on-section of the DRX cycle. The UE may activate physical layer hardware during the on-period, obtain at least one of a signal, measurement information, and sensing information received from the base station, and determine a context group based on the obtained information. To this end, although not shown in FIG. 25, the UE may receive information related to conditions for selecting each of the context groups. In this case, the UE can confirm the context group of the UE by checking which conditions the obtained information meets. For example, the UE may check which condition is satisfied by the acquired information among at least one condition for each context group and check the context group corresponding to the confirmed condition. According to one embodiment, the UE can check location information and check context information corresponding to the location information.

In step S2503, the UE determines whether the context group has changed. That is, the UE compares the context group applied to generate current channel data and the context group confirmed in step S2501. In other words, the UE checks whether the context group identified in step S2501 is different from the context group applied to generate the current channel data.

If the context has changed, in step S2505, the UE requests information necessary for channel creation. In other words, the UE transmits a message requesting information necessary to generate channel data, that is, probability distribution information related to the channel corresponding to the confirmed context group. For example, probability distribution information may include a latent distribution. To this end, the UE may at least temporarily suspend DRX operation. According to one embodiment, the UE may perform this step when it does not possess probability distribution information for the changed context group.

In step S2507, the UE receives information necessary for channel creation. In other words, the UE receives a message containing information necessary to generate channel data, that is, probability distribution information related to the channel corresponding to the identified context group. For example, probability distribution information may include a latent distribution. Accordingly, the UE may generate channel data corresponding to the changed context group.

In the embodiment described with reference to FIG. 25, the UE checks the current context group and determines a change in the context group. According to another embodiment, the UE may determine a change in the context group and then confirm the changed context group. A change in the context group is confirmed, but a situation may arise where it is not confirmed which context group the change was made to. For example, the UE may determine uncertainty about the receiver model based on the signal passing through the channel, and if the uncertainty exceeds a threshold, determine a change in context group. In this case, the UE may not be able to confirm which context group it has changed to. Therefore, additionally, the UE can collect information to confirm the changed context group (e.g., signal passing through the channel, measurement information, sensing information, etc.) and confirm the changed context group.

Figure 26 shows an example of a procedure for responding to an increase in uncertainty according to an embodiment of the present invention. FIG. 26 illustrates a method of operating a UE, and the illustrated operations may be understood as operations of the second device 2020 of FIG. 20.

Referring to FIG. 26, in step S2601, the UE determines uncertainty about channel data. The UE can determine uncertainty about channel data generated by the channel generation model using an acquisition function. Uncertainty may be determined based on channel data, receiver model, etc. Here, uncertainty refers to the degree of reliability of the output when a task using a receiver model is performed on channel data.

In step S2603, the UE checks whether the uncertainty exceeds the threshold. In other words, the UE compares uncertainty and threshold. Here, the threshold may be configured in advance by the base station. According to one embodiment, the threshold may be provided as one of the parameters included in setting information related to DRX operation.

If the uncertainty exceeds the threshold, in step S2605, the UE requests transmission of a reference signal. That is, the UE transmits a message requesting transmission of a reference signal to the base station. Here, the message may include at least one of information related to the context group of the UE, information related to the channel creation model, information related to uncertainty, and information related to the reference signal pattern.

In step S2607, the UE receives at least one reference signal. To this end, the UE may receive information on the setting (e.g. resource location, etc.) of at least one reference signal from the base station and measure at least one reference signal. According to one embodiment, at least one reference signal may be transmitted according to a reference signal pattern indicated by the UE. Accordingly, the UE can perform training on the receiver model and channel creation model using reference signals that passed through the actual channel.

As explained with reference to FIG. 26, as uncertainty exceeds a threshold, transmission of a reference signal may be requested. In addition, if the uncertainty falls below another threshold, an interruption in the transmission of the reference signal may be requested. That is, when uncertainty is lowered through training using reference signals that actually passed through the channel, the UE may transmit a message requesting to stop transmitting the reference signal. Afterwards, if additional training is needed, the UE can perform training using channel data generated by the channel creation model.

Figure 27 shows an example of a procedure for supporting online learning according to an embodiment of the present invention. FIG. 27 illustrates a method of operating a base station, and the illustrated operations may be understood as operations of the first device 2010 of FIG. 20.

Referring to Figure 27, in step S2701, the base station receives capability information related to DRX. For example, capability information related to DRX includes whether DRX operation is supported, information related to DRX cycles (e.g. inactivity timer, long cycle length, short cycle length, short cycle timer, etc.), and the UE's preferred It may contain at least one of the DRX-related parameters. According to one embodiment, for example, capability information related to DRX includes information indicating whether online learning can be performed during DRX operation, information indicating whether channel data can be generated, and supportable terminal context information. It may include at least one of the information indicating. In addition to capability information related to DRX, the UE may provide other types of capability information, for example, information related to supportable radio access technology (RAT), information related to duplex method, and parameters used in the layer. At least one of related information and information related to the operating state may be further transmitted. According to one embodiment, the base station may transmit a message requesting capability information to the UE and receive capability information as a response.

In step S2703, the base station transmits configuration information related to DRX. Setting information related to DRX includes control information necessary for DRX operation. For example, configuration information related to DRX may include at least one of the length of each section within the DRX cycle, a timer value related to DRX operation, DRX cycle length, and HARQ-related parameters. Additionally, configuration information related to DRX may include information instructing DRX operation. According to one embodiment, the setting information includes information instructing to perform online learning during DRX operation, functions supportable for online learning (e.g., providing latent distribution information, transmitting a reference signal for online learning, uncertainty about the reference signal) sampling, etc.).

In step S2705, the base station checks whether information or signals necessary for setting up the receiver are requested. That is, the base station checks whether information or signals required for training on a receiver model included in the UE's receiver are requested from the UE. A request for information or a signal is performed through a message, and the message may include at least one of information about the context group of the UE, information related to the task of the receiver model to be trained, and information related to uncertainty.

If information or signals necessary for setting up the receiver are requested, in step S2707, the base station transmits the requested information or signals. That is, the base station may transmit a message or signal containing information necessary for training in response to the UE's request. For example, the signal may include at least one reference signal.

The embodiments described with reference to FIGS. 24 to 27 may be implemented for training a UE receiver model for downlink communication. To support tasks for the uplink channel, a receiver model of a base station for uplink communication can also be trained through a similar procedure. In this case, since the base station has a receiver model and the UE has a transmitter model, the base station can generate channel data and train the receiver model using the generated channel data. And, if necessary, the base station may request the UE to transmit an uplink reference signal.

Figure 28 shows an example of a procedure for exchanging competency information related to online learning according to an embodiment of the present invention. FIG. 28 illustrates signaling to confirm whether idle mode learning is supported between the base station 2810 and the UE 2820.

Referring to FIG. 28, in step S2801, the base station 2810 transmits an idle mode learning capability request message to the UE 2820. The idle mode learning capability request message may be referred to as a capability inquiry message.

In step S2803, the UE 2820 transmits an idle mode learning capability response message to the base station 2810. Through this, the base station 2810 can obtain information to support idle mode learning of the UE 2820. The idle mode learning capability response message may be referred to as a UE capability message. For example, the idle mode learning capability response message may include at least one of the items listed in Table 2 below.

Information element Description Support of generative model sets Identifier of a model set or set that the UE can support from a common generation model set that can support idle state learning UE context capabilities Supportable terminal context information (e.g., location information, acceleration and speed information, posture information including angular velocity and angular acceleration, movement state of external objects, shape of transmitting and receiving antennas, information acquired using sound and vision sensors) )

Figure 29 shows an example of a procedure for updating latent distribution information according to an embodiment of the present invention. Figure 29 illustrates signaling for updating the latent distribution according to a change in context between the base station 2910 and the UE 2920.

Referring to FIG. 29, in step S2901, the base station 2910 transmits information related to the potential distribution for the UE context group to the UE 2920. For example, information related to a latent distribution for a UE context group may include information defining a mapping relationship between the context group and the latent distribution. Here, the context group can be specified as a set of factors affecting the channel.

In step S2903, the UE 2920 performs an idle operation. Specifically, the UE 2920 operates a wake-up period and a sleep period according to the DRX cycle. At this time, according to various embodiments, the UE 2920 may perform context monitoring during the wake-up period and perform online learning using a channel generation network during at least part of the sleep period.

In step S2905, the UE 2920 updates the UE context. The UE 2920 may update the UE context based on the context monitoring results during the wake-up period. Specifically, the UE 2920 may obtain at least one of a signal, measurement information, sensing information, and hardware information received from the base station 2910, and determine the context based on the obtained information.

In step S2907, the UE 2920 transmits a latent distribution request for the UE context to the base station 2910. In other words, the UE 2920 announces the changed context or the context group corresponding to the changed context, and requests information related to the potential distribution needed to generate channel data corresponding to the changed context or context group. According to one embodiment, the UE 2920 may end the DRX operation and transmit a request for latent distribution. According to another embodiment, the UE 2920 may temporarily terminate the DRX operation and transmit a request for latent distribution. According to another embodiment, the UE 2920 may transmit a request for latent distribution while maintaining DRX operation.

In step S2909, the base station 2910 finds a potential distribution for the UE context. That is, the base station 2910 searches for a potential distribution for a changed context or context group in response to a request from the UE 2920. For example, the base station 2910 may search for a latent distribution corresponding to the context received from the UE 2920 in a table defining a mapping relationship between context and latent distribution.

In step S2911, the base station 2910 transmits a latent distribution response to the UE 2920. That is, the base station 2910 transmits information related to the latent distribution corresponding to the changed context of the UE 2920. According to one embodiment, the base station 2910 may transmit information related to the potential distribution as part of configuration information related to DRX.

In step S2913, the UE 2920 updates the potential distribution. The UE 2920 replaces the existing latent distribution with a latent distribution corresponding to the changed context. Accordingly, the UE 2920 may generate channel data according to the changed context.

The example procedure described with reference to FIG. 29 may be performed when it is confirmed that the context of the UE has changed through measurement. For training in the idle state transmitted in step S2901, information about the context group according to the context may be provided to the UE using broadcasting, multicasting, or dedicated signaling. Here, the potential distribution information can be delivered in advance using at least one of the items shown in [Table 3] below.

Information element Description UE context group ID Context group identifier UE context conditions Conditions for inclusion in a context group Generative model ID Channel creation model for idle state learning or identifier related thereto Latent distribution ID Channel generation latent distribution for idle learning or an identifier associated with it. Uncertainty threshold Thresholds for uncertainty, including Q _{out_thresh} (out-of-distribution) and Q _{in_thresh} (in-distribution)

The UE receives information related to the latent distribution and identifies a context group corresponding to its context. The UE can perform online learning using a channel generation network while performing idle mode operation, and at the same time minimize UE power consumption. At this time, the UE can adaptively adjust the online learning section so that the uncertainty does not fall below the threshold.

If the context of the UE has changed, but the potential distribution information delivered in advance does not include information about the context group corresponding to the changed context, the UE may transmit a latent distribution request, as in step S2907. At this time, the latent distribution request may include at least one of the items shown in [Table 4] below.

Information element description UE context group ID Current context group identifier UE context updated context

The base station can deliver updated potential distribution information for each group to the UE based on the information shown in [Table 4].

Figure 30 shows an example of a procedure for controlling uncertainty in a receiver model according to an embodiment of the present invention. Figure 30 illustrates signaling for performing training based on uncertainty between the base station 3010 and the UE 3020.

Referring to FIG. 30, in step S3001, the base station 3010 transmits information related to the potential distribution for the UE context group to the UE 3020. For example, information related to a latent distribution for a UE context group may include information defining a mapping relationship between the context group and the latent distribution. Here, the context group can be specified as a set of factors affecting the channel.

In step S3003, the UE 3020 performs an idle operation. Specifically, the UE (3020) operates a wake-up section and a sleep section according to the DRX cycle. At this time, according to various embodiments, the UE 3020 may perform context monitoring during the wake-up period and perform online learning using a channel generation network during at least part of the sleep period.

In step S3005, the UE 3020 determines that the uncertainty exceeds the threshold. Specifically, the UE 3020 determines the uncertainty using an acquisition function and compares the uncertainty with the threshold. In step S3007, the UE 3020 transmits a report notifying the occurrence of an event whose uncertainty exceeds the threshold to the base station 3010.

In steps S3009-1 to S3009-4, the base station 3010 transmits reference signals for training. The reference signals may be used for training a receiver model of UE 3020. According to one embodiment, the reference signals are samples for active learning and may follow at least one pattern selected by uncertainty sampling.

In step S3011, the UE (3020) determines that the uncertainty is lower than the threshold. Specifically, the UE 3020 determines the uncertainty using an acquisition function and compares the uncertainty with the threshold. In step S3013, the UE 3020 transmits to the base station 3010 a report notifying the occurrence of an event in which uncertainty becomes lower than the threshold.

The example procedure described with reference to FIG. 30 may be performed to online train the channel generation network and the discriminator network when the context of the UE is not changed but the uncertainty exceeds a threshold. The UE may receive potential distribution information from the base station and perform idle state operation. The UE measures the uncertainty, detects that the measured uncertainty exceeds the threshold Q _{out_thresh} , and reports this to the base station. The base station transmits reference signals related to the channel task in response to the event. Based on one transmission of reference signals, the channel generation neural network and all discriminative neural networks related to the channel task can be trained. As training is performed, the uncertainty becomes less than Q _{in_thresh} and the UE sends a report about this event to the base station. The report may include at least one of the items shown in [Table 5] below.

Information element description UE context group ID Current context group identifier UE context updated context Channel generative model Parameters of the updated channel generation model

According to the various embodiments described above, online learning may be performed during DRX operation. The above-described embodiments have been described assuming DRX operation in an idle state. However, various embodiments may also be implemented during DRX operation in a connected state, that is, connected-DRX (C-DRX) operation.

Hereinafter, this disclosure describes a specific scenario of performing online learning using the proposed technology. According to one embodiment, the channel-related tasks of the UE are divided into three categories: channel state information (CSI) measurement such as rank indicator (RI), channel quality indicator (CQI), and precoding matrix indicator (PMI), channel estimator, and beam measurement. It can be. The discriminant neural networks corresponding to the tasks are shown in Figure 31 below.

Figure 31 shows examples of various neural networks for different tasks according to an embodiment of the present invention. Referring to FIG. 31, the channel creation network 3110 is commonly shared by a plurality of receiver models 3121 to 3123 in the terminal. The channel generation network 3110 may provide training samples for three tasks corresponding to a plurality of receiver models 3121 to 3123. The input to the channel generation network 3110 is sample z sampled from the latent distribution p(z) according to the terminal context. Uncertainty neural network 3130 measures uncertainty for online training samples and three receiver models 3121-3123.

Figure 32 shows an example of times when context measurement and online learning are performed during a DRX cycle according to an embodiment of the present invention. In the example of Figure 32, the DRX cycle is 1.28 seconds long. Referring to FIG. 32, monitoring of the terminal context is periodically performed in each wake-up section (3202-1, 3202-2). When the context changes, the latent distribution is updated through the proposed signaling. And, during the sleep sections 3204-1 and 3204-2, online learning is performed.

When three tasks exist, the terminal evaluates the uncertainty about the three given tasks and determines the length of the online learning interval D(t) and D(t+1) based on the uncertainty. For example, if the uncertainty threshold transmitted through signaling is set to Q _{out_thresh} of 10%, an online learning section of an appropriate length may be determined so that the uncertainty does not exceed 10%.

Figure 33 shows an example of context groups according to an embodiment of the present invention. Figure 33 illustrates three different terminal context groups. Referring to FIG. 33, three areas 3301 to 3303 with latent distributions p ₁ (z), p ₂ (z), and p ₃ (z) are context groups that occur due to differences in propagation characteristics. The context group assigned to the first area 3301 has a line-of-sight (LOS) environment between the base station 3320 and the terminal 3310-1, and the third area 3303 is a channel area due to diffraction and reflection. , and the second area 3302 is an area that has the probabilities of both the characteristics of the first area 3301 and the third area 3303. When the terminal 3310-2 located in the third area 3303 moves to the second area 3302, the terminal 3310-2 determines a context change and creates a new potential distribution through signaling according to the above-described embodiment. p ₂ (z) will be received from the base station 3320.

Figure 34 shows another example of context groups according to an embodiment of the present invention. Figure 34 illustrates two terminal context groups 3401 and 3402 assigned to the same area. The two terminal context groups 3401 and 3402 are both assigned to the cell of the base station 3420. Here, the terminal context is classified with mobility as the main factor. The first terminal 3410-1 with high mobility and the second terminal 3410-2 with low mobility and a probability distribution whose posture changes frequently have different contexts. Accordingly, the first terminal 3410-1 and the second terminal 3410-2 have different potential distributions p ₁ (z) and p ₂ (z).

According to the various embodiments described above, online learning performance degradation in an idle state can be minimized in a physical layer terminal composed of a neural network. This is because, while entering the power saving mode, training samples can be provided to the neural network responsible for channel-related tasks even if the terminal moves. Additionally, the online learning period can be adjusted through uncertainty measurement. Additionally, the proposed technique provides a trade-off between reduced power consumption and neural network performance. In particular, according to various embodiments, since latent distribution information, which occupies a small amount of information in the channel generation network compared to the method of updating the discriminant neural network, is transmitted, wireless resource consumption for online learning can be minimized.

By operating a common channel generation network for a plurality of receiver models, a simpler operating mechanism can be provided compared to a method in which various types of terminals have different neural network models and the network updates the neural network models. Figure 35 shows an example of terminals with different channel task networks according to an embodiment of the present invention. Referring to Figure 35, when N UEs all have different channel task networks (3521a, 3521b, 3522a, 3522b, 3523a, 3523b), updating all neural network models according to movement causes a large waste of radio resources. can do. However, if only the latent distribution for the channel generation networks 3510a and 3510b is updated, as in the proposed technology, this waste of resources will be minimized.

It is clear that examples of the proposed methods described above can also be included as one of the implementation methods of the present disclosure, and thus can be regarded as a type of proposed methods. Additionally, the proposed methods described above may be implemented independently, but may also be implemented in the form of a combination (or merge) of some of the proposed methods. A rule may be defined so that the base station informs the terminal of the application of the proposed methods (or information about the rules of the proposed methods) through a predefined signal (e.g., a physical layer signal or a higher layer signal). .

The present disclosure may be embodied in other specific forms without departing from the technical ideas and essential features described in the present disclosure. Accordingly, the above detailed description should not be construed as restrictive in all respects and should be considered illustrative. The scope of this disclosure should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this disclosure are included in the scope of this disclosure. In addition, claims that do not have an explicit reference relationship in the patent claims can be combined to form an embodiment or included as a new claim through amendment after filing.

Embodiments of the present disclosure can be applied to various wireless access systems. Examples of various wireless access systems include the 3rd Generation Partnership Project (3GPP) or 3GPP2 system.

Embodiments of the present disclosure can be applied not only to the various wireless access systems, but also to all technical fields that apply the various wireless access systems. Furthermore, the proposed method can also be applied to mmWave and THz communication systems using ultra-high frequency bands.

Additionally, embodiments of the present disclosure can be applied to various applications such as free-running vehicles and drones.

Claims (18)

In a method of operating a UE (user equipment) in a wireless communication system, Receiving broadcast information necessary for communication; Transmitting capability information related to discontinuous reception (DRX); Receiving configuration information related to the DRX; performing a sleep section operation based on the setting information; and It includes performing an on-duration operation based on the setting information, The on-interval operation includes monitoring the UE context used for setting up the receiver, The sleep period operation includes configuring the receiver using channel data generated based on the UE context. In claim 1, The capability information includes at least one of information indicating whether online learning can be performed during DRX operation, information indicating whether channel data can be generated, and information indicating at least one supportable terminal context item. How to include it. In claim 1, The receiver includes at least one neural network model for performing at least one task related to the reference signal, Setting up the receiver includes training for the at least one neural network model, using the channel data as learning data. In claim 1, Further comprising generating the channel data based on a latent distribution corresponding to the UE context, The channel data includes at least one of channel information based on a latent vector corresponding to the UE context, reference signals passing through a channel specified by the channel information, and a pattern of the reference signals. In claim 4, The step of performing the sleep section operation is, disabling at least one physical layer hardware; and A method comprising performing online learning for at least one neural network model included in the receiver using the channel data, without receiving an external signal. In claim 4, The potential distribution is determined based on the broadcast information, The broadcast information includes information related to conditions for selecting each of the context groups. In claim 1, Transmitting a first message requesting probability distribution information used to generate channel data for a context group corresponding to the UE context; and The method further comprising receiving a second message including the probability distribution information. In claim 1, If uncertainty about the channel data exceeds a threshold, transmitting a message requesting transmission of reference signals to the base station; receiving the reference signals; and The method further includes performing training on at least one neural network model included in the receiver based on the reference signals. In claim 1, determining uncertainty about the channel data; and The method further comprising determining a training period for at least one neural network model included in the receiver based on the uncertainty. In a method of operating a base station in a wireless communication system, Transmitting broadcast information necessary for communication; Receiving capability information related to discontinuous reception (DRX); Transmitting configuration information related to the DRX; Receiving a message requesting information or signals necessary for setting up a receiver of a user equipment (UE); Transmitting the information or signal, The configuration information indicates a sleep period and on-duration for the DRX operation of the UE, The on-interval is used to monitor the UE context used for setting the receiver in the UE, The sleep period is used by the UE to configure the receiver using channel data generated based on the UE context. In claim 10, The message includes information related to the UE context of the UE, information related to the context group of the UE, information related to the task of the receiver model to be trained, information related to uncertainty, and information related to the channel creation model of the UE. It may include at least one of: In claim 10, The capability information includes at least one of information indicating whether online learning can be performed during DRX operation, information indicating whether channel data can be generated, and information indicating at least one supportable terminal context item. How to include it. In claim 10, The step of transmitting the information or the signal includes: A method comprising transmitting information related to a latent distribution corresponding to a changed UE context or a changed context group of the UE. In claim 10, The step of transmitting the information or the signal includes: A method comprising transmitting reference signals having a pattern selected according to uncertainty sampling. In UE (user equipment) in a wireless communication system, transceiver; and Includes a processor connected to the transceiver, The processor, Receive broadcast information necessary for communication, Transmit capability information related to DRX (discontinuous reception), Receive configuration information related to the DRX, Perform a sleep section operation based on the setting information, Controls to perform on-duration operation based on the setting information, The on-interval operation includes monitoring the UE context used for setting up the receiver, The sleep period operation includes configuring the receiver using channel data generated based on the UE context. In a base station in a wireless communication system, transceiver; and Includes a processor connected to the transceiver, The processor, Transmits broadcast information necessary for communication, Receive capability information related to discontinuous reception (DRX), Transmit configuration information related to the DRX, Receive a message requesting information or signals necessary for setting up a receiver of UE (user equipment), Controls to transmit the information or signal, The configuration information indicates a sleep period and on-duration for the DRX operation of the UE, The on-interval is used to monitor the UE context used for configuration of the receiver in the UE, The sleep period is used by the UE to configure the receiver using channel data generated based on the UE context. In a communication device, at least one processor; 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, The above operations are: Receiving broadcast information necessary for communication; Transmitting capability information related to discontinuous reception (DRX); Receiving configuration information related to the DRX; performing a sleep section operation based on the setting information; and It includes performing an on-duration operation based on the setting information, The on-section operation includes monitoring the UE (user equipment) context used for setting up the receiver, The sleep period operation includes configuring the receiver using channel data generated based on the UE context. A non-transitory computer-readable medium storing at least one instruction, comprising: Contains the at least one instruction executable by a processor, The at least one command may cause the device to: Receive broadcast information necessary for communication, Transmit capability information related to DRX (discontinuous reception), Receive configuration information related to the DRX, Perform a sleep section operation based on the setting information, Controls to perform on-duration operation based on the setting information, The on-section operation includes monitoring the UE (user equipment) context used for setting up the receiver, The sleep period operation includes configuring the receiver using channel data generated based on the UE context.

Images