KR20240026441A - Method and device for transmitting and receiving signals in a wireless communication system - Google Patents

Abstract

The present disclosure can provide a terminal operation method in a wireless communication system. The terminal operation method includes transmitting first index information related to the IRS control value to the IRS, receiving a reference signal to which first beamforming is applied from the base station through the IRS, and compensating value information and channel based on the received reference signal. Obtaining at least one of state information, updating first index information to second index information through at least one of compensation value information and channel state information, and transmitting the updated second index information to IRS. It may include receiving a reference signal to which the second beamforming is applied from the base station based on the step and the updated second index information through the IRS.

Description

Method and device for transmitting and receiving signals in a wireless communication system

The following description is about a wireless communication system and a method and device for transmitting and receiving signals between a terminal and a base station in a wireless communication system.

In particular, terminals and base stations can provide methods and devices for transmitting and receiving signals by controlling the wireless channel environment through an intelligent reflective surface (IRS).

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, Massive MTC (Machine Type Communications), which connects multiple devices and objects to provide a variety of services anytime, anywhere, as well as communication systems that take reliability and latency-sensitive services/UE into consideration are being proposed. Various technological configurations are being proposed for this purpose.

The present disclosure can provide a method and device for transmitting and receiving signals in a wireless communication system.

The present disclosure can provide a method for a terminal and a base station to transmit and receive signals using an intelligent reflector in a wireless communication system.

The present disclosure can provide a method for a terminal and a base station to transmit and receive signals based on an intelligent radio channel environment (Smart Radio Environment, SRE) in a wireless communication system.

The present disclosure can provide a method of controlling a passive intelligent reflector based on an artificial intelligence system in a wireless communication system.

The present disclosure can provide a method for a terminal and a base station to transmit and receive signals by controlling a passive intelligent reflector 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, in a method of operating a terminal in a wireless communication system, transmitting first index information related to an intelligent reflector (Intelligent Reflect Surface, IRS) control value to the IRS, a reference to which first beamforming is applied from a base station Receiving a signal through IRS, obtaining at least one of compensation value information and channel state information based on the received reference signal, first index information through at least one of compensation value information and channel state information updating with second index information, transmitting the updated second index information to the IRS, and receiving a reference signal to which the second beamforming is applied from the base station based on the updated second index information through the IRS. It can be included.

In addition, according to an embodiment of the present disclosure, in a method of operating a base station in a wireless communication system, transmitting a reference signal to which first beamforming is applied to a terminal through IRS, the first signal updated in the first index information through IRS 2. Receiving index information and transmitting a reference signal to which second beamforming is applied to the terminal through IRS, wherein the terminal transmits first index information related to the IRS control value to IRS and performs first beamforming Obtain at least one of compensation value information and channel state information through this applied reference signal, update first index information to second index information through at least one of compensation value information and channel state information, and Index information can be transmitted to the IRS.

In addition, according to an embodiment of the present disclosure, a terminal of a wireless communication system includes a transceiver and a processor connected to the transceiver, and the processor transmits first index information related to the IRS control value to the IRS through the transceiver, Receive a reference signal to which first beamforming is applied from the base station through the transceiver through IRS, obtain at least one of compensation value information and channel state information based on the received reference signal, and obtain compensation value information and channel state information updating the first index information to the second index information through at least one of the following, transmitting the updated second index information to the IRS, and applying second beamforming from the base station based on the updated second index information. The signal can be received through IRS.

In addition, according to an embodiment of the present disclosure, a base station of a wireless communication system includes a transceiver and a processor connected to the transceiver, and the processor transmits a reference signal to which first beamforming is applied through the transceiver to the terminal through IRS. And, receive the second index information updated from the first index information through the IRS through the transceiver, and transmit a reference signal to which the second beamforming is applied through the transceiver to the terminal through the IRS, and the terminal receives the IRS control value and Transmit related first index information to IRS, obtain at least one of compensation value information and channel state information through a reference signal to which first beamforming is applied, and obtain at least one of compensation value information and channel state information through at least one of compensation value information and channel state information. The first index information can be updated with the second index information, and the second index information can be transmitted to the IRS.

In addition, according to an embodiment of the present disclosure, in a device including at least one memory and at least one processor functionally connected to the at least one memory, the at least one processor is configured to: Transmit related first index information to the IRS, receive a reference signal to which first beamforming is applied from the base station through the IRS, and obtain at least one of compensation value information and channel state information based on the received reference signal, and , updating the first index information with second index information through at least one of compensation value information and channel state information, transmitting the updated second index information to IRS, and base station based on the updated second index information. A reference signal to which the second beamforming is applied can be received through IRS.

Additionally, according to an embodiment of the present disclosure, in a non-transitory computer-readable medium storing at least one instruction, executable by a processor It includes at least one command, wherein the at least one command is such that the device transmits first index information related to the IRS control value to the IRS, receives a reference signal to which first beamforming is applied from the base station through the IRS, and receives the first index information related to the IRS control value. Obtain at least one of compensation value information and channel state information based on the reference signal, update first index information to second index information through at least one of compensation value information and channel state information, and update the first index information with second index information. 2 Index information can be transmitted to the IRS, and a reference signal to which the second beamforming is applied can be received from the base station based on the updated second index information through the IRS.

The following matters can be commonly applied to the above-described base stations, terminals, devices, and computer recording media.

Additionally, according to an embodiment of the present disclosure, the IRS control value may be determined based on index information, and each phase value within the IRS element may be determined based on the determined IRS control value.

In addition, according to an embodiment of the present disclosure, the index information is information generated through a codebook based on an IRS direction vector set, and the index information is composed of a first factor based on the IRS azimuth and a second factor based on the IRS elevation angle. You can.

In addition, according to an embodiment of the present disclosure, the terminal receives a reference signal for setting the initial value from the base station, and sends the channel state information and the location information of the terminal obtained through the received reference signal for setting the initial value to the base station. Feedback is provided, and the terminal can receive artificial intelligence initial value information derived from the base station based on the channel state information received by the base station and the location information of the terminal.

Additionally, according to an embodiment of the present disclosure, the terminal may further receive candidate set information related to index information from the base station.

Additionally, according to an embodiment of the present disclosure, the terminal may derive first index information based on the received artificial intelligence initial value information and candidate set information.

Additionally, according to an embodiment of the present disclosure, the base station may determine the first beamforming based on the location of the IRS when performing initial setup with the IRS.

In addition, according to an embodiment of the present disclosure, when the IRS updates the first index information with the second index information, the IRS transmits a wireless environment change completion signal including the second index information to the base station, and the base station 2 The second beamforming may be determined based on the index information.

In addition, according to an embodiment of the present disclosure, the terminal includes an artificial intelligence beam selector, and the artificial intelligence beam selector updates the first index information to the second index information through at least one of compensation value information and channel state information. can do.

In addition, according to an embodiment of the present disclosure, the artificial intelligence beam selector converts first index information into second index information based on either a multi-armed bandit (MAB) artificial intelligence (AI) learning model or a reinforcement learning learning model. You can update it with .

In addition, according to an embodiment of the present disclosure, when the artificial intelligence beam selector updates the first index information to the second index information based on the MAB AI learning model, the second index information is updated through learning based on compensation value information. It can be obtained.

In addition, according to an embodiment of the present disclosure, when the artificial intelligence beam selector updates the first index information with the second index information based on the reinforcement learning learning model, state information is set based on the first index information, Second index information can be obtained through learning based on state information and compensation value information.

Additionally, according to an embodiment of the present disclosure, the terminal includes an IRS performance meter, and the IRS performance meter may generate compensation value information using channel-related information obtained through a reference signal.

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 can be understood by those skilled in the art. It can be derived and understood based on explanation.

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

Embodiments based on the present disclosure can provide a method for a terminal and a base station to transmit and receive signals using an intelligent reflector.

Embodiments based on the present disclosure can provide a method for a terminal and a base station to transmit and receive signals based on an intelligent wireless channel environment.

Embodiments based on the present disclosure may provide a method for controlling a passive intelligent reflector based on an artificial intelligence system.

Embodiments based on the present disclosure can provide a method for a terminal and a base station to transmit and receive signals by controlling a passive intelligent reflector.

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 is a diagram showing an example of a communication system applicable to the present disclosure.
Figure 2 is a diagram showing an example of a wireless device applicable to the present disclosure.
Figure 3 is a diagram showing another example of a wireless device applicable to the present disclosure.
Figure 4 is a diagram showing an example of a portable device applicable to the present disclosure.
Figure 5 is a diagram showing an example of a vehicle or autonomous vehicle applicable to the present disclosure.
Figure 6 is a diagram showing an example of AI (Artificial Intelligence) applicable to the present disclosure.
Figure 7 is a diagram showing an example of a communication structure that can be provided in a 6G system applicable to the present disclosure.
Figure 8 is a diagram showing an electromagnetic spectrum applicable to the present disclosure.
Figure 9 is a diagram showing a wireless channel environment according to an embodiment of the present disclosure.
Figure 10 is a diagram showing an intelligent wireless environment according to an embodiment of the present disclosure.
Figure 11 is a diagram showing an existing wireless channel environment and an intelligent wireless channel environment, according to an embodiment of the present disclosure.
FIG. 12 is a diagram illustrating a method of performing optimization in an intelligent wireless channel environment according to an embodiment of the present disclosure.
Figure 13 is a diagram showing a confidence interval according to an embodiment of the present disclosure.
FIG. 14 is a diagram illustrating a method of performing optimization in a passive-based intelligent wireless channel environment according to an embodiment of the present disclosure.
FIG. 15 is a diagram illustrating signal flows between a base station, a terminal, and an IRS to set up an optimized intelligent wireless environment (SRE) according to an embodiment of the present disclosure.
FIG. 16 is a diagram illustrating the signal flow between the base station, IRS, and terminal when an artificial intelligence beam selector is implemented in the terminal according to an embodiment of the present disclosure.
FIG. 17 may be a flowchart showing a method of setting an optimized intelligent wireless environment according to an embodiment of the present disclosure.
Figure 18 is a diagram showing the structure of an SRE artificial intelligence system using reinforcement learning according to an embodiment of the present disclosure.
FIG. 19 may be a more detailed diagram of the components of the environment based on FIG. 18.
FIG. 20 is a diagram illustrating blocks used by a terminal and a base station among environmental components in an artificial intelligence beam selector according to an embodiment of the present disclosure.
Figure 21 is a diagram showing the structure of an artificial intelligence beam selector according to an embodiment of the present disclosure.
Figure 22 is a diagram showing a method of implementing an artificial intelligence beam selector through MAB AI according to an embodiment of the present disclosure.
Figure 23 is a diagram showing a method of implementing an artificial intelligence beam selector through reinforcement learning according to an embodiment of the present disclosure.
Figure 24 is a diagram showing total regret using the greedy method according to an embodiment of the present disclosure.
Figure 25 shows the structure of an IRS performance meter, according to an embodiment of the present disclosure.
Figure 26 is a diagram showing a method of setting the initial value of artificial intelligence according to an embodiment of the present disclosure.
Figure 27 may be a case where an artificial intelligence beam selector is implemented in a terminal according to an embodiment of the present disclosure.
Figure 28 is a diagram showing the structure of an SRE artificial intelligence system including an artificial intelligence initial value setter according to an embodiment of the present disclosure.
Figure 29 is a diagram showing an example of an artificial intelligence coding initial value setter applicable to the present disclosure.
Figure 30 is a diagram showing a method of performing wireless environment optimization based on an artificial intelligence system according to an embodiment of the present disclosure.

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.

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 910 to 930/940a to 940d 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 920 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 930 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 940c may be transmitted to an external device through the communication unit 610 and/or stored in the memory unit 630.

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.

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. 7 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 7, 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 8 is a diagram showing an electromagnetic spectrum applicable to the present disclosure. As an example, referring to Figure 8, 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 to 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.

Below, we describe how to control the wireless channel environment using a passive Intelligent Reflect Surface (IRS). Here, the artificial intelligence system can be used to control the wireless channel environment using IRS, which will also be described later.

As an example, current wireless communication technology can be controlled through end-point optimization that adapts to the channel environment (H). For example, when performing optimization in the transmitter and receiver, the transmitter and receiver adjust at least one of beamforming, power control, and adaptive modulation to match the channel environment (H) between the transmitter and receiver to increase transmission efficiency. You can.

At this time, the channel environment may be random, uncontrolled, and naturally fixed. That is, in the existing communication system, each end point could be controlled to optimize the channel environment while the channel environment was fixed. Therefore, the transmitter and receiver have no choice but to perform optimization to adapt to the channel and transmit and receive data through this. At this time, in environments where signal loss is large and multipath is difficult to exist, such as NLOS (non-line of sight) in a shaded area or 6G THz, Shannon's capacity limit can be overcome by optimizing the end point alone. This may be difficult to do, and it may be difficult to expect throughput as desired.

In consideration of the above, in the new communication system, communication can be performed based on an intelligent radio environment (Smart Radio Environment). At this time, in an intelligent wireless environment, an intelligent reflector (IRS) can be used as a factor that can control the wireless channel like a transceiver.

That is, a factor for the wireless channel may be added as a factor used to optimize wireless communication transmission. Through this, it may be possible to reset the channel, which is a problem that cannot be solved in existing communication systems, or to overcome Shannon's channel capacity limitations. However, in an intelligent wireless environment, there is a need to optimize by simultaneously considering the measurement of channels added due to the intelligent reflector (IRS) and the intelligent reflector (IRS) as a transceiver, and this may complicate the optimization process.

For example, with the limitations of current wireless communication technology, there may be limitations in controlling IRS using the AO (Alternating Optimization) algorithm applied in an intelligent wireless environment. In the following, the limitations of channel information acquisition in a passive-based intelligent reflector are overcome. Describe how to do this.

More specifically, the existing communication system was able to operate in a fixed wireless channel environment by approaching Shannon's channel capacity limit through control of the transmitter and receiver. However, in poor NLOS environments such as shaded areas, transmission and reception may be nearly impossible due to limitations in channel capacity. For example, in an NLOS channel environment, the transmitter can improve the limitations of channel capacity by increasing power, but the size of noise and interference may also increase accordingly. At this time, in an environment where signal loss is large and multipath is difficult to exist, such as a 6G THz environment, there may be limitations in overcoming Shannon's channel capacity limitations only by optimizing the transmitter and receiver.

Here, as an example, in a new communication system (e.g. 6G), new services include MBRLLC (Mobile Broadband Reliable Low Latency Communication), mURLLC (Massive Ultra-Reliable, Low Latency communications), HCS (Human-Centric Services), and 3CLS (Convergence of There is a need to satisfy the requirements for providing services (Communications, Computing, Control, Localization, and Sensing), and for this, communication based on an intelligent wireless environment may be necessary.

Additionally, as an example, many relays are currently being used to increase coverage of base station cells and support shadow areas. However, the method of using a repeater can increase transmission efficiency, but may additionally generate interference signals for other users. Therefore, there may be limitations in overall communication resource efficiency. Additionally, the use of a relay also requires high additional costs and energy, and it may not be easy to manage complex and mixed interference signals. Additionally, as an example, using half duplex may reduce spectral efficiency and may also affect space utilization and aesthetics.

On the other hand, in an intelligent wireless environment, the wireless channel environment can be controlled using an intelligent reflector (IRS). At the same time, the transmitter and receiver can perform optimization together to provide a solution to overcome Shannon's channel capacity limitations in a smart radio environment, which will be described later.

However, in addition to the existing channels between the base station and the terminal, there is also a need to consider channels between the base station and IRS and IRS and the terminal. In addition, conventionally, it is sufficient to optimize only the transceiver to suit the environment, but in a smart radio environment, there is a need to control the intelligent reflector (IRS) as well.

Additionally, the value may depend on optimization of the transceiver, which may increase complexity. Here, the Alternating Optimization (AO) algorithm used for optimization may be performed repeatedly until convergence, which may impose the burden of having to measure all channels. In the following, taking the above-mentioned points into consideration, we describe a method of performing optimization in an intelligent wireless environment with a passive-based intelligent reflector and an artificial intelligence system.

Additionally, as an example, Table 2 may be a term considering the following and the above, and based on this, the following describes a method of performing optimization in an intelligent wireless environment with a passive-based intelligent reflector and an artificial intelligence system.

Figure 9 is a diagram showing a wireless channel environment according to an embodiment of the present disclosure. Referring to FIG. 9, in an existing communication system, the wireless channel environment (H) is naturally fixed and may be in a random state that cannot be controlled. Accordingly, the transmitter 910 and the receiver 920 can find an optimized transmission and reception method by adapting to the channel. The transmitter 910 and the receiver 920 may be controlled to measure the channel state through a signal (e.g. a reference signal) and perform optimization based on the measured channel state. However, as described above, there may be limitations in data transmission in cases where signal loss is large and multi-path application is difficult, such as in a terahertz environment, and in NLOS environments, such as shaded areas. As an example, Equation 1 below may represent Shannon's capacity limit. At this time, even if the transmission signal P in Equation 1 is increased by applying precoding and processing, there may be a limit to increasing the channel capacity if the size of the channel |H| is small.

When the wireless channel environment is fixed, there may be a limit to increasing channel capacity based on Equation 1. At this time, by using an intelligent reflector (IRS), multiple paths can be secured between the transmitter 910 and the receiver 920, and the above-mentioned channel |H| can be increased. That is, in an intelligent wireless environment, the wireless channel environment can be an adjustable factor based on the intelligent reflector, and through this, channel capacity can be increased.

As an example, FIG. 10 is a diagram illustrating an intelligent wireless environment according to an embodiment of the present disclosure. Referring to FIG. 10, in an intelligent wireless channel environment, the wireless channel |H| may be a factor for optimization. More specifically, in FIG. 9 described above, optimization can be performed in the transmitter 910 and the receiver 920 based on “max{f(Tx, Rx)}” as endpoint optimization, as described above. . However, in FIG. 10, optimization may be performed in the transmitter 1010 and the receiver 1020 based on “max{f(Tx, Rx, H)}” as end-point optimization. That is, in an intelligent wireless environment, channel |H| can be used as a factor for optimization based on an intelligent reflector.

Figure 11 is a diagram showing an existing wireless channel environment and an intelligent wireless channel environment, according to an embodiment of the present disclosure. For example, referring to FIG. 11(a), the existing wireless channel environment may be P1. Additionally, referring to FIG. 11(b), the intelligent wireless channel environment may be P2. At this time, when the x signal is transmitted from the transmitting end through a wireless channel in FIGS. 11(a) and 11(b), the receiving end can receive the y signal. At this time, in the existing wireless channel environment, the probability of P1 is fixed, and the receiving end (Decoder) can transmit feedback to the transmitting end through measurement of the transmitted signal. The transmitting end can perform optimization to adapt to the wireless channel environment through feedback from the receiving end. As a more specific example, the receiving end can measure the CQI (Channel Quality Indicator) for the transmitted signal based on the reference signal transmitted by the transmitting end and feed it back. The transmitting end can perform communication by adjusting the modulation coding scheme (MCS) based on the fed back information and providing information about this to the receiving end.

On the other hand, referring to FIG. 11(b), in the intelligent wireless channel environment, the wireless channel environment P2 is recognized, and the wireless channel environment can be changed through IRS control. At the same time, the receiving end can measure the received transmission signal and transmit feedback about it to the transmitting end. That is, the transmitting end can perform optimization by receiving feedback information based on IRS control and feedback information from the receiving end. At this time, the transmitting end can change the wireless channel environment by adjusting the IRS, and optimization considering the wireless channel environment and the transmitting end can be performed.

) 및 기지국(1210)과 단말(1230) 간 직접 무선 채널(

)이 존재할 수 있다. 여기서, IRS(1220)의 제어에 기초하여 기지국(1210)과 IRS(1220) 간 무선 채널(G) 및 IRS(1220)와 단말(1230) 간 무선 채널(

)이 변경될 수 있다. 따라서, 지능형 무선 채널 환경에서 최적화는 상술한 무선 채널 환경을 고려하여 최적화가 수행될 수 있다.More specifically, FIG. 12 is a diagram illustrating a method of performing optimization in an intelligent wireless channel environment according to an embodiment of the present disclosure. Referring to FIG. 12, an IRS 1220 may exist between the base station 1210 and the terminal 1230 in an intelligent wireless channel environment. For example, the signal transmitted by the base station 1210 may have a path directly transmitted to the terminal 1230 and a path reflected and transmitted to the IRS 1220. That is, in an intelligent wireless channel environment, the wireless channel (G) between the base station 1210 and the IRS (1220), the wireless channel (G) between the IRS (1220) and the terminal (1230)

) and a direct wireless channel between the base station 1210 and the terminal 1230 (

) may exist. Here, based on the control of the IRS (1220), the wireless channel (G) between the base station 1210 and the IRS (1220) and the wireless channel (G) between the IRS (1220) and the terminal 1230 (

) may change. Therefore, optimization in an intelligent wireless channel environment can be performed by considering the wireless channel environment described above.

, 단말 k(1230)에게 전송하는 신호는

및 수신 잡음이

일 수 있다. 이때, 단말 k(1230)가 IRS(1220)를 사용하는 환경에 기초하여 기지국(1210)으로부터 수신하는 신호는 하기 수학식 2와 같을 수 있으며, 각각의 채널에 대해서는 하기 표 3과 같을 수 있다.More specifically, when the base station 1210 transmits a signal to terminal k (1230), the base station transmission beamforming vector for terminal k (1230) is

, the signal transmitted to terminal k (1230) is

and reception noise

It can be. At this time, the signal that terminal k (1230) receives from the base station (1210) based on the environment in which it uses the IRS (1220) may be as shown in Equation 2 below, and may be as shown in Table 3 below for each channel.

Here, the signal-to-noise ratio (SNR) received by terminal k (1230) may be expressed as Equation 3 below.

Therefore, when configuring an intelligent radio environment (SRE) to optimize reception SNR, it may be a case of setting IRS control and transmit beamforming as shown in Equation 4 below.

는 하기 수학식 5와 같을 수 있다.At this time, transmit beamforming of terminal k (1230) considering maximum-rate transmit in MIMO

may be equal to Equation 5 below.

는 IRS에서 최대 전송 파워일 수 있고,

및 Φ 를 최적화하는 수식에

를 대입하면 최적화는 하기 수학식 6과 같을 수 있다.here,

may be the maximum transmission power in IRS,

and in the formula to optimize Φ

By substituting , optimization can be as shown in Equation 6 below.

를 연산에 의해 결정할 수 있다. 여기서, 상술한 최적화 문제를 해결하기 위한 AO(Alternating Optimization) 알고리즘이 사용될 수 있다. 일 예로, AO 알고리즘은 채널정보(

,

, G) 를 이용하여 IRS 요소 별로 신뢰 구간(Trust region)을 결정하는 방법일 수 있으며, 도 13과 같을 수 있다. 또한, 목적 함수의 값(Objective Value)이 수렴할 때까지 반복적으로 바이너리 결정(binary decision)을 수행하고, 이를 통해

을 구할 수 있다. 여기서, 수렴 값의 상위 한계 값(upper bound)은 이상적인 IRS(Ideal IRS)인 경우,

=1일 수 있다. 이때, 일 예로, 도 12에서 IRS는 상술한 IRS 요소별로 최적화된 값을 찾기 위해 상술한 동작을 반복할 수 있다.At this time, if the IRS control value Φ is determined,

can be determined by calculation. Here, an Alternating Optimization (AO) algorithm can be used to solve the above-described optimization problem. As an example, the AO algorithm uses channel information (

,

, G) may be used to determine a trust region for each IRS element, and may be as shown in FIG. 13. In addition, binary decisions are repeatedly made until the objective value of the objective function converges, and through this,

can be obtained. Here, the upper bound of the convergence value is the ideal IRS,

= It can be 1. At this time, as an example, in FIG. 12, the IRS may repeat the above-described operation to find an optimized value for each IRS element.

Here, the AO (Alternating Optimization) algorithm needs to be repeated until convergence. In addition, since each optimization value must be derived for each IRS element, complexity may increase and the amount of computation may increase. At this time, complexity and calculation amount may increase depending on the number of antennas M of the base station and the number of IRS elements N, and there may be limitations in calculating them. Additionally, when optimizing the AO (Alternating Optimization) algorithm, measurement values of all channels including IRS may be required, and considering the above, there may be limits to optimization.

FIG. 14 is a diagram illustrating a method of performing optimization in a passive-based intelligent wireless channel environment according to an embodiment of the present disclosure.

As described above, when channel optimization is performed based on IRS in an intelligent wireless channel environment, the amount of calculation may increase exponentially depending on the repeatability of the AO (Alternating Optimization) algorithm and the IRS element. Additionally, as an example, in an intelligent wireless channel environment, there is a need to measure all channel information including IRS, which may increase complexity.

The following describes how to use an IRS with a simple structure without an active sensor. For example, an IRS equipped with an active sensor can acquire channel information by sensing a signal transmitted from a base station. On the other hand, a passive IRS without an active sensor may only transmit signals transmitted from the base station to the terminal based on a reflector structure, but may not perform sensing. Therefore, a passive IRS without an active sensor may require less installation and cost than an IRS with an active sensor, and based on this, the possibility of its utilization may be high.

However, since passive-based IRS is not equipped with active sensors, there is a need to supplement insufficient channel information with artificial intelligence. In other words, channel information that can be measured by an active sensor needs to be acquired through artificial intelligence. As an example, the optimized IRS control value is not affected by the number of base station antennas M and the number of IRS elements N, and can be derived based on artificial intelligence, which will be described later.

를 사전에 인지하고 관리할 수 있다. 일 예로, 인공지능 빔 선택기(1440)는 최적화된 IRS 제어 값 Φ를 선택하고, 선택된 정보를 IRS 제어기(IRS Controller, 1450)로 전달하는 구성일 수 있다. 일 예로, 인공지능 빔 선택기(1440)는 SRE 인공지능 시스템에 기초하여 최적화된 빔을 선택하는 구성일 수 있다.As a specific example, referring to FIG. 14, channel G between the base station 1410 and the IRS 1420 may be a channel in which there is no change in location in a Line of Sight (LoS) environment. Therefore, the base station 1410 performs transmit beamforming for channel G.

can be recognized and managed in advance. As an example, the artificial intelligence beam selector 1440 may be configured to select an optimized IRS control value Φ and transmit the selected information to the IRS controller (IRS Controller, 1450). As an example, the artificial intelligence beam selector 1440 may be configured to select an optimized beam based on the SRE artificial intelligence system.

As an example, the artificial intelligence beam selector 1440 may be implemented in the base station 1410. That is, the artificial intelligence beam selector 1440 that operates based on the SRE artificial intelligence system can be implemented and operated in the base station 1410. As another example, the artificial intelligence beam selector 1440 may be implemented in conjunction with the IRS controller 1450. As another example, the artificial intelligence beam selector 1440 may be implemented and operated in the terminal 1430. As another example, the artificial intelligence beam selector 1440 may be implemented through a cloud or a separate device separately from the base station 1410, and may not be limited to a specific form.

That is, the artificial intelligence beam selector 1440 may be configured to perform optimized beam selection based on the SRE artificial intelligence system, and may be configured among the base station 1410, IRS controller 1450, terminal 1430, and separate device/cloud. It may be implemented based on at least one of them, and may not be limited to a specific form.

가 적용된 를 전송할 수 있다. 이때, 단말(1430)은 IRS(1420)를 통해 기지국(1410)이 전송하는 참조신호를 수신할 수 있다. 그 후, 단말(1430)은 참조신호에 기초하여 IRS 제어 값 Φ 로 인한 보상 값(Reward)을 획득하고, 채널 정보를 측정할 수 있다. 이때, 단말(1430)은 보상 값과 측정된 채널 정보(

)를 기지국(1410)으로 전달할 수 있다. 또 다른 일 예로, 단말(1430)은 IRS 제어 값 Φ 로 인한 보상 값(Reward)과 채널 정보를 간접적으로 나타내는 지표 정보(e.g. SNR,

)를 획득하고, 기지국(1410)으로 전달할 수 있다. 그 후, 기지국(1410)은 단말(1430)로부터 전달받은 피드백 정보에 기초하여 인공지능 시스템을 학습할 수 있다. 일 예로, 인공지능 빔 선택기(1450)가 기지국(1410)에 직접 구비된 경우, 기지국(1410)은 인공지능 빔 선택기(1450)를 통해 학습을 수행할 수 있다. 또 다른 일 예로, 인공지능 빔 선택기(1450)가 별도의 클라우드 또는 디바이스로 존재하는 경우, 기지국(1410)은 단말(1430)로부터 수신한 피드백 정보를 전달하여 학습을 수행하도록 할 수 있다. 또 다른 일 예로, 단말(1430)에 인공지능 빔 선택시(1450)가 구현된 경우, 단말(1430)은 참조신호를 통해 획득한 보상 값 및 채널 정보를 통해 직접 학습을 수행할 수 있다.When selecting an artificial intelligence beam (1440) selects the optimized IRS control value Φ as described above and transmits information about this to the IRS controller (1450), the IRS controller (1450) sets IRS ( 1420) can be controlled. At this time, the base station 1410 sends the IRS 1420 based on the IRS control value described above.

The applied can be transmitted. At this time, the terminal 1430 can receive the reference signal transmitted by the base station 1410 through the IRS 1420. Afterwards, the terminal 1430 can obtain a compensation value (Reward) due to the IRS control value Φ based on the reference signal and measure channel information. At this time, the terminal 1430 receives the compensation value and the measured channel information (

) can be transmitted to the base station 1410. As another example, the terminal 1430 displays a reward value due to the IRS control value Φ and indicator information (eg SNR,

) can be obtained and transmitted to the base station 1410. Afterwards, the base station 1410 can learn the artificial intelligence system based on the feedback information received from the terminal 1430. For example, when the artificial intelligence beam selector 1450 is directly provided in the base station 1410, the base station 1410 can perform learning through the artificial intelligence beam selector 1450. As another example, if the artificial intelligence beam selector 1450 exists as a separate cloud or device, the base station 1410 may transmit feedback information received from the terminal 1430 to perform learning. As another example, when artificial intelligence beam selection 1450 is implemented in the terminal 1430, the terminal 1430 can directly perform learning through the compensation value and channel information obtained through the reference signal.

를 사용할 수 있다. 인공지능 빔 선택기(1450)가 최적화된 IRS 제어 값 Φ에 대한 설정을 완료한 경우, 기지국(1410)은 최적화된 IRS 제어 값 Φ를 통해 새로운 무선환경에서 최적화된 전송 빔포밍(Transmit Beamforming)

를 연산하고, 적용할 수 있다.

는 인공지능을 활용하여 연산되거나 5G NR에서 사용하고 있는 빔 관리 방식이 적용될 수 있으며, 특정 형태로 한정되는 것은 아닐 수 있다.Here, when the artificial intelligence beam selector 1450 is implemented using reinforcement learning using state information, the artificial intelligence beam selector 1450 uses the state information to control the current IRS 1420 and channel information.

can be used. When the artificial intelligence beam selector 1450 completes the settings for the optimized IRS control value Φ, the base station 1410 performs optimized transmit beamforming in a new wireless environment through the optimized IRS control value Φ.

can be calculated and applied.

may be calculated using artificial intelligence or the beam management method used in 5G NR may be applied, and may not be limited to a specific form.

FIG. 15 is a diagram illustrating signal flows between a base station, a terminal, and an IRS to set up an optimized intelligent wireless environment (SRE) according to an embodiment of the present disclosure.

를 사전에 인지하고, 관리할 수 있다. 보다 구체적인 일 예로, 기지국(1510)과 IRS(1520)가 초기 설정을 수행하는 경우,

는 측정 장비나 이동성이 가능한 장치를 통해 측정될 수 있으며, 측정 값으로 기 설정될 수 있다. 또 다른 일 예로, 기지국(1510)과 IRS(1520)는 저전력/저비용 센서를 통해 주기적으로

를 측정할 수 있으며, 측정된 값에 기초하여

를 주기적으로 업데이트할 수 있다. 일 예로, MRT(Maximum Transmit Rate)를 위한

는 하기 수학식 7과 같이 도출될 수 있다.As an example, referring to FIG. 15, the base station 1510 performs transmit beamforming for channel G as described above.

can be recognized and managed in advance. As a more specific example, when the base station 1510 and IRS 1520 perform initial setup,

Can be measured using measuring equipment or a portable device, and can be preset as a measured value. As another example, the base station 1510 and IRS 1520 periodically use low-power/low-cost sensors.

can be measured, and based on the measured value

can be updated periodically. As an example, for MRT (Maximum Transmit Rate)

Can be derived as shown in Equation 7 below.

를 지원할 수 있다. 일 예로,

는 무선 통신 시스템(e.g. NR)에서 사용되는 빔 관리 또는 빔 스위핑에 기초하여 지원되는 값 중 어느 하나로 결정될 수 있다. 일 예로, IRS(1520)는 기지국(1510)으로 CSI(channel status information) 피드백을 제공할 수 있으며, 이를 통해

값이 결정될 수 있다. 그 후, 기지국(1510)은

가 적용된 참조신호를 IRS(1520)로 전송할 수 있다. 여기서, IRS의 제어 값은 인공지능 빔 선택기에 기초하여 결정될 수 있다. 일 예로, 도 15에서는 인공지능 빔 선택기가 IRS 제어기와 연계된 경우일 수 있으나, 이에 한정되는 것은 아닐 수 있다. 일 예로, 인공지능 빔 선택기가 기지국(1510)이나 단말(1520) 또는 다른 디바이스/클라우드에 위치하는 경우, IRS(1520)는 IRS 제어 값 관련 정보를 별도로 수신할 수 있으며, 이에 대해서는 후술한다.As another example, the base station 1510 and IRS 1520 do not measure channel G,

can support. As an example,

may be determined to be one of the values supported based on beam management or beam sweeping used in a wireless communication system (eg NR). As an example, the IRS 1520 may provide channel status information (CSI) feedback to the base station 1510, through which

The value can be determined. Afterwards, the base station 1510

The applied reference signal can be transmitted to the IRS (1520). Here, the control value of IRS can be determined based on an artificial intelligence beam selector. As an example, in Figure 15, the artificial intelligence beam selector may be linked to the IRS controller, but the case may not be limited to this. For example, if the artificial intelligence beam selector is located in the base station 1510, the terminal 1520, or another device/cloud, the IRS 1520 may separately receive information related to the IRS control value, which will be described later.

를 선택할 수 있다. 일 예로, 인공지능 빔 선택기가 상태정보를 이용하는 강화학습인 경우, 상태정보는 현재 IRS(1520)의 제어 값과 채널정보

를 포함할 수 있다. 그 후, IRS(1520)는 인공지능 빔 선택기에서 예측한 위상 값으로 설정될 수 있다. 기지국(1510)은

가 적용된 참조신호(

)를 IRS(1520)로 전달하고, 단말(1530)은 IRS(1520)를 경유한 참조신호

를 수신할 수 있다. 그 후, 단말(1530)은 참조신호

에 기초하여 보상 값(reward)를 측정할 수 있다. 일 예로, 단말(1530)은 IRS 성능 측정기를 구비할 수 있으며, 이를 통해 보상 값을 측정할 수 있다. 보상 값은 IRS 채널의 신호대 잡음비

나 평균제곱에러

일 수 있으나, 다른 형태의 채널 관련 정보도 포함할 수 있다. 또한, 단말(1530)은 참조신호에 대한 측정을 수행하여 채널 상태 정보를 획득할 수 있다. 그 후, 단말(1530)은 보상 값 및 채널 상태 정보를 피드백 할 수 있다. 여기서, 인공지능 빔 선택기는 IRS 위상 값과 보상 값(reward) 및 측정한 채널정보를 통해 학습될 수 있다. 일 예로, 보상 값(reward)이나 예측된 위상 값의 수렴여부에 따라 학습이 반복될 수 있다. 이때, 인공지능 빔 선택기는 초기 전이학습을 통해 학습된 모델을 사용함으로써 반복성을 제거할 수 있다.Here, the artificial intelligence beam selector uses the phase change value for each element of the IRS.

You can select . For example, if the artificial intelligence beam selector is reinforcement learning using state information, the state information is the control value and channel information of the current IRS (1520).

may include. Afterwards, IRS 1520 can be set to the phase value predicted by the artificial intelligence beam selector. Base station 1510 is

The applied reference signal (

) is transmitted to the IRS (1520), and the terminal (1530) receives the reference signal via the IRS (1520)

can receive. Afterwards, the terminal 1530 receives the reference signal

Based on this, the reward value can be measured. As an example, the terminal 1530 may be equipped with an IRS performance meter, through which the compensation value can be measured. The compensation value is the signal-to-noise ratio of the IRS channel.

I mean square error

However, it may also include other types of channel-related information. Additionally, the terminal 1530 can obtain channel state information by performing measurement on the reference signal. Afterwards, the terminal 1530 can feed back the compensation value and channel state information. Here, the artificial intelligence beam selector can be learned through the IRS phase value, compensation value, and measured channel information. As an example, learning may be repeated depending on whether the reward or predicted phase value converges. At this time, the artificial intelligence beam selector can eliminate repeatability by using a model learned through initial transfer learning.

Afterwards, the IRS 1520 may transmit an environment change completion signal to the base station 1510 based on the learning of the artificial intelligence beam selector. Afterwards, the base station 1510 sends a reference signal to the terminal 1530 to obtain channel state information, determines and applies optimized transmit beamforming in the newly changed environment, and performs communication with the terminal 1530. You can.

FIG. 16 is a diagram illustrating the signal flow between the base station, IRS, and terminal when an artificial intelligence beam selector is implemented in the terminal according to an embodiment of the present disclosure.

를 결정할 수 있다. 이때, 단말(1630)은 결정된 인덱스 정보를 IRS(1620)로 전달할 수 있다. IRS(1620)는 수신한 인덱스 정보(

)를 통해 상술한 위상 값을 결정할 수 있다. 그 후, 기지국(1610)은

가 적용된 참조신호(

)를 IRS(1620)로 전달하고, 단말(1630)은 IRS(1620)를 경유한 참조신호

를 수신할 수 있다. 그 후, 단말(1630)은 참조신호

에 기초하여 보상 값(reward)를 측정할 수 있다. 일 예로, 단말(1630)은 IRS 성능 측정기를 구비할 수 있으며, 이를 통해 보상 값을 측정할 수 있다. 보상 값은 IRS 채널의 신호대 잡음비

나 평균제곱에러

일 수 있으나, 다른 형태의 채널 관련 정보도 포함할 수 있다. 또한, 단말(1630)은 참조신호에 대한 측정을 수행하여 채널 상태 정보를 획득할 수 있다. 그 후, 단말(1630)의 인공지능 빔 선택기는 보상 값 및 채널 상태 정보에 기초하여 학습을 수행할 수 있다. 여기서, 학습은 수렴할 때까지 반복될 수 있다. 이를 통해, 인공지능 빔 선택기는 IRS 제어 값을 업데이트할 수 있으며, 보상 값과 채널 상태 정보 및 현재 IRS 제어 값을 기반으로 IRS 제어의 빔 방향의 고도각, 방위각을 나타내는 인덱스

가 업데이트될 수 있다. 그 후, 단말(1630)은 업데이트된 인덱스 정보를 IRS(1620)로 전달할 수 있다. IRS는 IRS 제어 값에 기초하여 환경변경 완료 신호를 기지국(1610)으로 전송하고, 기지국(1610)은 단말(1630)에 참조신호를 보내서 채널 상태 정보를 획득할 수 있다. 이를 통해, 기지국(1610)은 새롭게 변경된 환경에서 최적화된 전달 빔포밍(transmit beamforming)을 결정하고 적용하여 단말(1630)과 통신을 수행할 수 있다.Referring to FIG. 16, the artificial intelligence beam selector may be implemented in the terminal 1630. That is, as described above, the artificial intelligence beam selector can be implemented not only in the base station 1610, IRS 1620, and a separate cloud/device, but also in the terminal 1630. As an example, the artificial intelligence beam selector implemented in the terminal 1630 can determine the IRS control value. As an example, the terminal 1630 is an index indicating the elevation angle and azimuth of the beam direction of the IRS control based on the channel information measured through the artificial intelligence beam selector and the current IRS control value (or initial value).

can be decided. At this time, the terminal 1630 may transmit the determined index information to the IRS 1620. IRS (1620) receives the index information (

), the above-described phase value can be determined. Afterwards, the base station 1610

The applied reference signal (

) is transmitted to the IRS (1620), and the terminal (1630) receives the reference signal via the IRS (1620)

can receive. Afterwards, the terminal 1630 receives the reference signal

Based on this, the reward value can be measured. As an example, the terminal 1630 may be equipped with an IRS performance meter, through which the compensation value can be measured. The compensation value is the signal-to-noise ratio of the IRS channel.

I mean square error

However, it may also include other types of channel-related information. Additionally, the terminal 1630 can obtain channel state information by performing measurement on the reference signal. Afterwards, the artificial intelligence beam selector of the terminal 1630 may perform learning based on the compensation value and channel state information. Here, learning can be repeated until convergence. Through this, the artificial intelligence beam selector can update the IRS control value, and the index indicating the elevation angle and azimuth of the beam direction of the IRS control based on the compensation value, channel status information, and current IRS control value.

can be updated. Afterwards, the terminal 1630 may transmit the updated index information to the IRS 1620. The IRS transmits an environment change completion signal to the base station 1610 based on the IRS control value, and the base station 1610 can obtain channel state information by sending a reference signal to the terminal 1630. Through this, the base station 1610 can perform communication with the terminal 1630 by determining and applying optimized transmit beamforming in the newly changed environment.

FIG. 17 may be a flowchart showing a method of setting an optimized intelligent wireless environment according to an embodiment of the present disclosure.

를 설정하는 동작일 수 있다.(S1710) 일 예로, 상술한 바와 같이, 기지국과 IRS가 초기 설정을 수행하는 경우, 기지국과 IRS는 IRS의 위치에 기초하여 채널 G에 대한 초기 설정을 수행할 있다. 또 다른 일 예로, 기지국과 IRS는 채널 측정없이 인공지능을 통해 전송 빔포밍(transmit beamforming)

를 결정할 수 있다. 또한, 일 예로, 저전력 센서에 기초하여 주기적으로 채널 G가 확인될 수 있으며, 이는 상술한 바와 같다. 즉, 기지국은 IRS로 전송하는 전송 빔포밍(transmit beamforming)

를 사전에 인지하고, 관리할 수 있다. 이때, 단말이 IRS 성능 측정기를 통해 상술한 보상 값 및 채널 추정 정보를 획득하기 위해서 단말은 기지국으로부터 신호를 수신할 수 있다. 기지국은 신호를 IRS로 전달하여 단말로 전송할 수 있으며, 이를 위해 빔포밍이 필수적일 수 있다.Referring to Figure 17, this may be a method of setting an optimized intelligent wireless environment based on Figures 15 and 16 described above. Here, the channel estimation step is a beamforming vector transmitted from the base station to the IRS based on the channel information G of the base station-IRS (BS-IRS).

It may be an operation to set. (S1710) As an example, as described above, when the base station and IRS perform initial setup, the base station and IRS may perform initial setup for channel G based on the location of the IRS. . As another example, the base station and IRS perform transmit beamforming through artificial intelligence without channel measurement.

can be decided. Additionally, as an example, channel G may be periodically checked based on a low-power sensor, as described above. In other words, the base station transmits beamforming to the IRS.

can be recognized and managed in advance. At this time, in order for the terminal to obtain the above-described compensation value and channel estimation information through the IRS performance meter, the terminal may receive a signal from the base station. The base station can transmit the signal to the IRS and transmit it to the terminal, and beamforming may be essential for this.

를 적용한 참조신호를 IRS로 전달할 수 있다. 일 예로, 기지국과 IRS간 신호가

를 적용하지 않아도 충분히 큰 경우라면 상술한 과정없이 신호가 전달될 수 있다.Additionally, the environment change step may be a step of finding and applying the optimal IRS control value using an artificial intelligence beam selector. Here, the base station calculates the transfer beamforming vector through the channel estimation step described above.

The applied reference signal can be transmitted to IRS. As an example, the signal between the base station and IRS is

If it is large enough without applying , the signal can be transmitted without the above-described process.

를 생성하여(S1720), IRS에 제어 값을 적용할 수 있다.(S1730) 이때, 인공지능 빔 선택기는 지도학습(supervisor learning)으로써 AO(alternating optimization) 최적화나 SDR(software Defined Radio)과 같은 최적화 알고리즘을 통해 획득한 제어 값으로 학습을 수행할 수 있다. 다만, 인공지능 빔 선택기는 사용한 알고리즘의 성능을 넘지 못할 수 있다. 또 다른 일 예로, 인공지능 빔 선택기는 기 학습된 학습 모델을 통해서 빠르게 예측 값을 추정할 수 있다.Afterwards, the artificial intelligence beam selector, which operates based on the SRE artificial intelligence system, provides control values for each element of the passive intelligent judge board (IRS).

By generating (S1720), the control value can be applied to the IRS (S1730). At this time, the artificial intelligence beam selector uses supervised learning to perform optimization such as AO (alternate optimization) optimization or SDR (software defined radio). Learning can be performed with control values obtained through an algorithm. However, the artificial intelligence beam selector may not exceed the performance of the algorithm used. As another example, an artificial intelligence beam selector can quickly estimate a prediction value through a pre-trained learning model.

As another example, an artificial intelligence beam selector can acquire a prediction value through reinforcement learning, which is unsupervised learning, and acquire a reward value accordingly to continuously update the learning model through learning. As an example, an artificial intelligence beam selector may repeat learning until the reward value or prediction value converges. Here, the artificial intelligence beam selector can reduce the number of iterations through transfer learning or by continuously updating the model. Afterwards, the environment change step may be terminated when the base station receives an environment change completion signal.

를 찾는 과정일 수 있다. 일 예로, 기지국은 전송 빔포밍

를 적용하여 참조신호를 생성하고(S1740), 이를 IRS를 통해 단말로 전송할 수 있다. 단말은 참조신호를 통해 측정한 실제 채널상태정보(effective channel state information)인

ΦG+

및 보상 값 R을 인공지능 빔 선택기에 전달할 수 있다. 여기서, 일 예로, 인공지능 빔 선택기는 상술한 바와 같이, 기지국, IRS, 단말 또는 클라우드/디바이스에 구비될 수 있다. 일 예로, 인공지능 빔 선택기가 단말에 구현된 경우, 단말은 보상 값 및 채널상태 정보를 적용하여 IRS를 제어하기 위한 인덱스 값을 IRS로 전송할 수 있으며, 이는 상술한 바와 같다. 또 다른 일 예로, 인공지능 빔 선택기가 기지국에 구현된 경우, 단말은 보상 값 및 채널상태 정보를 기지국으로 전달할 수 있다. 이때, 인공지능 빔 선택기는 단말로부터 수신한 보상 값 및 채널상태 정보에 기초하여 학습을 수행할 수 있다.(S1750) 여기서, 학습은 수렴될 때까지 지속적으로 수행될 수 있으며(S1756), 수렴된 값에 기초하여 기지국은 환경변경 완료 정보를 획득할 수 있다.(S1770)그 후, 기지국은 전달받은 환경변경 완료 정보에 기초하여 주어진 환경을 최적화하는

를 결정하고 통신을 수행할 수 있다.(S1780) 일 예로, 기지국이 환경을 최적화하는

를 결정하는 경우, 기지국은 무선 통신 시스템(e.g. NR)에서 사용하는 빔 관리 또는 빔 스위핑 방식에 기초하여

=

와 같은 방법을 사용할 수 있다.As a specific example, the environmental adaptation stage is when the base station transmits a reference signal to the terminal to optimize the environment in the new environment.

It may be a process of finding . As an example, the base station transmits beamforming

A reference signal can be generated by applying (S1740) and transmitted to the terminal through IRS. The terminal is the actual channel state information measured through the reference signal.

ΦG+

And the compensation value R can be transmitted to the artificial intelligence beam selector. Here, as an example, the artificial intelligence beam selector may be provided in a base station, IRS, terminal, or cloud/device, as described above. For example, when an artificial intelligence beam selector is implemented in the terminal, the terminal can transmit an index value for controlling the IRS by applying compensation values and channel state information to the IRS, as described above. As another example, when an artificial intelligence beam selector is implemented in a base station, the terminal can transmit compensation values and channel state information to the base station. At this time, the artificial intelligence beam selector may perform learning based on the compensation value and channel state information received from the terminal (S1750). Here, learning may be continuously performed until convergence (S1756), and convergence occurs. Based on the value, the base station can obtain environment change completion information. (S1770) After that, the base station optimizes the given environment based on the received environment change completion information.

can be determined and communication can be performed. (S1780) As an example, the base station optimizes the environment.

When determining , the base station bases the beam management or beam sweeping method used in the wireless communication system (eg NR).

=

You can use the same method.

As a specific example, the artificial intelligence beam selector can express the beam to be set in the form of a codebook and simplify the artificial intelligence model. Here, the direction vector function representing the array response vector in the receiving direction can be expressed as Equation 8 below.

In Equation 8, N is the size of the array (antenna or IRS element), and w may be the phase difference between the antenna or IRS element.

는 하기 수학식 9와 같이 방향벡터 함수 u(ω,N)으로 표현이 가능할 수 있다.As an example, the received response vector for the signal received by the IRS from the base station based on beamforming

Can be expressed as a direction vector function u(ω,N) as shown in Equation 9 below.

는 IRS의 방위각,

은 고도각이며,

와

는 각각 IRS 요소의 가로 및 세로의 개수일 수 있고,

는 크로네커 곱을 나타낼 수 있다. 또한, IRS의 송신 응답벡터

도 방향벡터 함수 u(ω,N)로 표현될 수 있으며, 하기 수학식 10과 같을 수 있다.In equation 9:

is the azimuth of IRS,

is the elevation angle,

and

may be the horizontal and vertical numbers of IRS elements, respectively,

can represent the Kronecker product. Additionally, the IRS's transmission response vector

It can also be expressed as a direction vector function u(ω,N), and can be expressed as Equation 10 below.

에 대해 IRS를 통한 신호는 하기 수학식 11과 같이 표현될 수 있다.In addition, the transmission signal to which transmission beamforming is applied

The signal through IRS can be expressed as Equation 11 below.

는 BS-IRS 채널의 패스 게인이고,

는 IRS-UE 채널의 패스 게인일 수 있다. 또한, Φ는 IRS 소자의 위상 값 행렬로써 Φ=diag(v),

로 표현될 수 있다. 또한,

로서 ⊙는 아르마르 곱으로 행렬의 소자 간 곱을 나타낼 수 있으며, 수학식 12와 같을 수 있다.In equation 11,

is the pass gain of the BS-IRS channel,

May be the pass gain of the IRS-UE channel. In addition, Φ is the phase value matrix of the IRS element, Φ=diag(v),

It can be expressed as also,

As ⊙ can represent the product between elements of the matrix as the Armard product, and can be the same as Equation 12.

로 표현이 가능할 수 있으며,

로 표현될 수 있다.In Equation 12, u(ω,N) is a function with a period of 2.

It can be expressed as,

It can be expressed as

이며 방위각과 고도각의 방향벡터 함수 u(ω,N) 의 크로네커 곱으로 표현할 수 있다.In addition, the optimal beamforming vector v of IRS that maximizes the received signal SNR is

It can be expressed as the Kronecker product of the direction vector function u(ω,N) of the azimuth and elevation angles.

은 IRS 방향벡터의 집합이며, 가로 및 세로 방향에서 각각

의 크기를 가질 수 있다. 또한, j ∈J 로 방향벡터의 인덱스이며, J는 총 나타낼 수 있는 방향 벡터일 수 있다. 일 예로, J는 가로 세로 방향의 사용하는 빔의 개수를 표현하는 값으로, 가로 및 세로 방향으로 각각

으로 다르게 표현이 가능할 수 있다.That is, IRS control values can be managed in the form of azimuth and elevation angles, and control values for each direction can be managed in a codebook. As an example, codebook

is a set of IRS direction vectors, in the horizontal and vertical directions, respectively.

It can have a size of . Additionally, j ∈ J is the index of the direction vector, and J may be the total number of direction vectors that can be represented. As an example, J is a value representing the number of beams used in the horizontal and vertical directions, respectively.

It may be expressed differently.

Here, the beam set in the final artificial intelligence beam selector may be equal to Equation 14 based on Equation 13 below.

In other words, the artificial intelligence beam selector can express the beam through a codebook as described above, and through this, the artificial intelligence model can be simplified.

Additionally, as an example, FIG. 18 is a diagram showing the structure of an SRE artificial intelligence system using reinforcement learning according to an embodiment of the present disclosure, and FIG. 19 further subdivides the components of the environment based on FIG. 18. It could be one drawing.

More specifically, referring to FIG. 18, based on the SRE artificial intelligence system, the artificial intelligence beam selector can perform learning based on reinforcement learning. At this time, as an example, reinforcement learning may consist of two inputs and one output. State information (state) and reward value (reward) can be used as input, and agent action (action) can be selected as output. Here, as an example, reinforcement learning may be MAB (multi-armed bandit), and in the case of MAB, state information may not be used, but it is not limited to this. Additionally, an action as an output may be an action in which the IRS controller operates to select a beam that provides the optimal communication environment to the terminal. As an example, an artificial intelligence beam selector can obtain reward values for actions and changed state information from the environment and use them for learning. In addition, the artificial intelligence beam selector can repeat the operation of selecting an action again based on the input after learning.

)를 사용할 수 있다. 또한, 일 예로, IRS 제어 값에 대한 환경의 변화를 상태(State)에 반영하기 위해서 단말은 측정한 채널 정보(

)를 상태(State)에 추가할 수 있다. 여기서, 채널정보는 측정된 값이거나 채널을 나타내는 간접적인 지표(CQI, SNR,

)로 대체 될 수 있으며, 상태는 하기 수학식 15와 같을 수 있다.Here, referring to FIG. 19, the artificial intelligence beam selector may be a method of determining each state, reward, and action by considering components of the environment. Here, as an example, the environment may be considered not only the channel environment through which signals are transmitted, but also the environment between the base station, terminal, and IRS for measuring compensation and channel status. As a specific example, the state is a factor received from the environment and the horizontal and vertical indices of the beam selector selected just before (

) can be used. In addition, as an example, in order to reflect environmental changes to the IRS control value in the state, the terminal measures the channel information (

) can be added to the state. Here, the channel information is a measured value or an indirect indicator (CQI, SNR,

), and the state may be as shown in Equation 15 below.

Additionally, the action is to select the index of the codebook representing the beam direction vector of the IRS, and ultimately the phase shift values of each IRS element can be applied. Based on the above, the action of the artificial intelligence beam selector may be as shown in Equation 16 below.

Here, the action value is a value constructed based on a codebook through the IRS direction vector generator, and what is actually selected by the selection artificial intelligence may be the index of the azimuth and elevation angles of the direction vector. Additionally, as an example, the reward value is a value measured by the terminal and may be the result of a control value selected by the IRS. For example, if you add a block received from a terminal to the IRS, you can receive it directly, but the cost of the IRS may increase. Accordingly, the IRS may obtain a compensation value from the base station based on the information transmitted from the terminal to the base station, but may not be limited to this. Additionally, as an example, the reward value (Reward) may be determined considering other purposes of use. Additionally, as an example, the terminal may include an IRS performance meter, as described above. However, as an example, when it does not go through the IRS performance meter, the compensation value may be channel-related information measured by the terminal based on the reference signal, as shown in Equation 17.

Additionally, as an example, FIG. 20 is a diagram illustrating usage blocks of a terminal and a base station among environmental components in an artificial intelligence beam selector according to an embodiment of the present disclosure. As an example, referring to FIG. 20, a base station can generate and transmit a reference signal through a wireless channel. Additionally, the terminal can obtain a reference signal generated from the base station through IRS, measure the reference signal, and determine channel state information and compensation value information. As an example, channel state information may include information about the results of direct channel measurement and indirect channel-related information, and may not be limited to a specific form. Here, the environmental components may be considered not only the IRS but also the operations of the base station and the terminal, and are not limited to the above-described embodiment.

Additionally, as an example, FIG. 21 is a diagram showing the structure of an artificial intelligence beam selector according to an embodiment of the present disclosure. As an example, the artificial intelligence beam selector can be divided into a selection artificial intelligence and an IRS generator. As an example, the artificial intelligence beam selector can derive a value such as Equation 18 below through state information and compensation values based on reinforcement learning, and derive the above-described action value based on this.

More specifically, selective artificial intelligence can perform the role of learning and predicting IRS control values to configure the optimal wireless environment. Here, selective artificial intelligence may be implemented through reinforcement learning or MAB as described above, but may not be limited thereto. Additionally, the IRS direction vector generator can generate control values for each element based on the codebook. In other words, because selective artificial intelligence is learned in the form of an index of a codebook, the dimensions of state information (state) and action (action) can be reduced. Therefore, it may be advantageous in terms of model size, complexity, and convergence speed compared to each device-specific learning method. Based on the above, the number of base station antennas M and the number of IRS elements N are not significantly affected and an optimized IRS control value can be generated.

Additionally, as an example, FIG. 22 is a diagram showing a method of implementing an artificial intelligence beam selector through MAB AI according to an embodiment of the present disclosure. As an example, referring to FIG. 22, selection artificial intelligence (artificial intelligence beam selector) using MAB AI using Thompson sampling can be largely divided into a learning unit and a selection unit. At this time, the learning unit may update the Thompson sampling parameters (α, β) for the previous action i based on the reward value. Here, learning α and β according to the reward value may be as shown in Equation 19 below.

는 기준이 되는 보상 값으로써, 단말의 IRS 성능 측정기의 보상 형태에 따라 상이하게 설정될 수 있다. 또한, 선택부는 누적된 톰슨 샘플링 파라미터 α, β를 베타 분포(beta distribution)에 적용하여 샘플링한 값 중 가장 큰 값을 가지는 빔 방향의 인덱스를 선택하도록 할 수 있다. 일 예로, 도 22에서 선택된 {

는 IRS 방향벡터 생성기에 전달될 수 있다. IRS 방향벡터 생성기는 상술한 값에 기초하여 방위각과 고도각에 대한 방향을 나타내는 인덱스(

)를 개별적으로 선택하는 방식을 사용할 수 있다. 또 다른 일 예로, IRS 방향벡터 생성기는

=(

)와 같이 고도각과 방위각을 합쳐서 새로운 인덱스

를 사용하여 선택하는 방식을 통해 선택을 수행할 수 있다. 일 예로, 베타 분포에 대한 수학식은 하기 수학식 20과 같을 수 있다.here,

is a standard compensation value and can be set differently depending on the compensation type of the terminal's IRS performance meter. Additionally, the selection unit may apply the accumulated Thompson sampling parameters α and β to a beta distribution to select the index of the beam direction with the largest value among the sampled values. As an example, the { selected in Figure 22

Can be passed to the IRS direction vector generator. The IRS direction vector generator is an index indicating the direction for azimuth and elevation angles based on the above-mentioned values (

) can be selected individually. As another example, the IRS direction vector generator is

=(

) to create a new index by combining the elevation angle and azimuth angle

You can make a selection by selecting using . As an example, the equation for the beta distribution may be as shown in Equation 20 below.

)}을 선택하도록 하지 않고, 각 방위각 및 고도각 방향별로 {±

,±

}를 선택하도록 구성될 수 있다. 다만, 일 예로, 강화학습에 기초한 선택인공지능(인공지능 빔 선택기)은 충분한 하드웨어 사양을 구비한 경우를 고려하여 직접 빔 방향 {

}를 선택하도록 하는 것도 가능할 수 있으며, 상술한 실시예로 한정되지 않는다. 또 다른 일 예로, 빔 방향 조정기에서 이전 방향 값 인덱스

,

에 강화학습 모델이 선택한 {±

,±

}를 적용하여

,

를 생성하고, 최종적으로

를 생성하여 지능형반사표면 생성기에 전달하는 것도 가능할 수 있으며, 특정 형태로 한정되는 것은 아닐 수 있다.Additionally, as an example, FIG. 23 is a diagram showing a method of implementing an artificial intelligence beam selector through reinforcement learning according to an embodiment of the present disclosure. As an example, artificial intelligence selection (artificial intelligence beam selector) using reinforcement learning may be composed of a reinforcement learning model and a beam direction adjuster that adjusts the beam direction with a selected action. Here, in the selection artificial intelligence based on the MAB AI described above, learning is performed based on reward values without state information, but the reinforcement learning model can perform learning through reward values and state information. At this time, the calculation of the learning model may increase because more state information is used compared to MAB AI. Considering the above, the selection artificial intelligence (artificial intelligence beam selector) directly determines the beam direction {

)}, but {± for each azimuth and elevation direction.

,±

} can be configured to select. However, as an example, selection artificial intelligence (artificial intelligence beam selector) based on reinforcement learning directly beam direction {

} may also be possible to select, and is not limited to the above-described embodiment. As another example, the previous direction value index in the beam direction steerer

,

{±

,±

} by applying

,

and finally

It may also be possible to generate and transmit to the intelligent reflective surface generator, and may not be limited to a specific form.

에서 가장 큰 행동 값(action-value)를 가지는 행동은 하기 수학식 22와 같을 수 있다.Here, the reinforcement learning model consists of a learning unit and a selection unit, similar to the selection artificial intelligence (or artificial intelligence beam selector) using MAB AI, and can predict the next action at the same time as learning. At this time, as an example, during reinforcement learning, learning may be performed through Q-Learning based on Equation 21 below, and the specific action-value may be as shown in Equation 21 below. Additionally, the policy selected in Q-Learning is the current state.

The action with the largest action-value may be expressed as Equation 22 below.

Additionally, as an example, issues regarding control of Exploration and Exploitation may arise in reinforcement learning. At this time, Exploration can utilize actions sampled from multiple actions to obtain better reward values. On the other hand, Exploitation can utilize information that is already known based on repetitive actions. At this time, as an example, in reinforcement learning, appropriate adjustment of Exploration and Exploitation may be necessary to achieve optimal performance, and the e-greedy method may be performed, which may be shown in FIG. 24. At this time, e-greedy may be a method of executing exploration with a set probability. As an example, referring to FIG. 24, Total Regret can be improved by e-greedy over the greedy method that only performs exploitation. Additionally, decaying e-greedy can be used as a method of approximating Total Regret logarithm over time, but may not be limited to a specific form.

는 시간에 따른 e-greedy로서 시간에 따라 그리고 최소 Regret의 제곱에 반비례하여 감소되어질 수 있다.As an example, Equation 23 below is an equation representing decaying e-greedy, where c is a constant and |A| is the size of Action Space,

is e-greedy over time and can be decreased over time and inversely proportional to the square of the minimum Regret.

Additionally, as an example, control of Exploration and Exploitation can be further optimized using MAB (Multi Arm Bandit). For example, Upper Confidence Bound (UCB) or Thompson Sampling (TS) may be applied and may not be limited to a specific form.

와 반비례하도록 설정되어 선택되지 못한 행동들에 대해서 더 많은 기회가 주어지도록 할 수 있다. 상술한 바에 기초하여 기회는 시간에 따라 반감될 수 있다.At this time, Equation 24 below may be an equation for behavior based on UCB, and Equation 15 may be Upper Confidence. At this time, Upper Confidence is the number of actions taken.

It can be set to be inversely proportional to so that more opportunities are given for actions that were not selected. Based on the above, the opportunity may be halved over time.

For example, Thompson Sampling is implemented through a beta distribution based on the above-mentioned information, and is simpler than UCB, and exploration and exploitation can be easily controlled.

As another example, Figure 25 shows the structure of an IRS performance meter according to an embodiment of the present invention. As an example, the IRS performance measurer may perform at least one of standardization/normalization, batching, and weight applicator functions. At this time, the IRS performance meter not only calculates SNR, Channel Gain, MSE, and Spectral Efficiency based on the reference signal from the base station, but can also measure energy charging, etc. using other monitoring systems. Here, each piece of measurement information may be in the range of various values.

Therefore, the standardization/normalization block can standardize or normalize the values of various areas of measurement information by considering each weight. In addition, the Batching block plays the role of accumulating such measurement information at regular intervals and can also perform normalization for each accumulation. Additionally, as an example, the weight application block may express the best output value by applying weights to each measurement index. For example, in a receiver where spectral efficiency is important, the weight of the spectral efficiency measurement can be set high. At this time, the IRS performance measuring device can generate compensation values in the form of processing and integrating the measurement information. As another example, the IRS performance meter may generate compensation values by separately separating measurement information, and may not be limited to a specific embodiment.

Figure 26 is a diagram showing a method of setting the initial value of artificial intelligence according to an embodiment of the present disclosure.

Referring to FIG. 26, an artificial intelligence initial value may be set based on the operation of the artificial intelligence beam selector. As an example, the base station 2610 may transmit a reference signal to the terminal 2630. The terminal 2630 may perform measurement using a reference signal and obtain channel state information between the base station 2610 and the terminal 2630 based on the measurement. Afterwards, the terminal 2630 can transmit the channel state information and the location information of the terminal to the base station 2610. At this time, the base station 2610 can set the artificial intelligence initial value through the artificial intelligence initial value setter based on the received channel state information and the location information of the terminal.

,

)을 포함할 수 있다. 또한, 일 예로, 학습모델이 강화학습인 경우, 인공지능 초기 값 정보는 상술한 톰슨 샘플링 파라미터 및 상태 정보(

)를 더 포함할 수 있으며, 상술한 실시예로 한정되지 않는다.As another example, the artificial intelligence initial value setter may be implemented in a device other than the base station 2610 or in the cloud. At this time, the base station 2610 may transmit the channel state information and location information received from the terminal 2630 to the artificial intelligence initial value setter and obtain artificial intelligence initial value information from the artificial intelligence initial value setter. Here, the artificial intelligence initial value information is the initial value of the selection artificial intelligence used in the artificial intelligence beam selector (Thompson Sampling:

,

) may include. In addition, as an example, when the learning model is reinforcement learning, the artificial intelligence initial value information is the above-described Thompson sampling parameters and state information (

) may further include, and is not limited to the above-described embodiments.

Afterwards, the base station 2610 may transmit artificial intelligence initial value information and candidate set information to the IRS 2620. At this time, as an example, the candidate set information may be index set information of a defined beam direction codebook. As another example, the candidate set information may be information about the codebook itself. As an example, the codebook may be a set of beam direction vectors used differently from the precoding matrix codebook used in multi input multi output (MIMO). In other words, the beam direction vector used in the candidate set (candidates) may be the size (space) of the action (action) selected in the artificial intelligence model. At this time, through the candidate set, reinforcement learning or MAB AI can quickly converge on learning and reduce the amount of computation.

In Figure 26, the artificial intelligence beam selector may be connected to the IRS controller. At this time, the IRS controller or AI server can initialize an artificial intelligence beam selector that operates through MAB AI (Thompson Sampling) or reinforcement learning through the above-described information received. The subsequent operation may be the same as Figure 15 described above.

As another example, a case where an artificial intelligence beam selector is implemented in the base station 2610 can be considered. At this time, the base station 2610 can transmit a reference signal to the terminal 2630 as described above, and obtain artificial intelligence initial value information through an artificial intelligence initial value setter through channel state information and location information of the terminal. Thereafter, the base station 2610 may operate as described above after reflecting the above-described artificial intelligence initial value information in the artificial intelligence beam selector.

As another example, Figure 27 may be a case where an artificial intelligence beam selector is implemented in a terminal according to an embodiment of the present disclosure. As an example, the base station 2710 can obtain channel state information and location information from the terminal 2730 through the reference signal in the same way as in FIG. 26, and obtain artificial intelligence initial value information based on this, which is shown in FIG. 26 and may be the same. At this time, as an example, the base station may transmit the artificial intelligence initial value information and candidate set information described above in FIG. 26 to the terminal 2730 in which the artificial intelligence beam selector is implemented. Afterwards, the terminal 2730 can apply the information received from the base station 2710 to the artificial intelligence beam selector, and subsequent operations may be as shown in FIG. 16 described above.

Additionally, as an example, FIG. 28 is a diagram showing the structure of an SRE artificial intelligence system including an artificial intelligence initial value setter according to an embodiment of the present disclosure. Referring to Figure 28, the artificial intelligence initial value setter can set the initial weight value of the selected artificial intelligence within the artificial intelligence beam selector as shown in Figures 26 and 27 described above. Additionally, as an example, the artificial intelligence initial value setter may update the weights of the model that has completed operation. As an example, the updated weight value may be used as the initial value of MAB AI or the initial state of reinforcement learning, and may not be limited to a specific form.

,

을 설정하여 인공지능 빔 선택기에 전송할 수 있다. 이때, 채널환경(e.g. SNR)과 단말의 위치정보를 고려해서 예측이 수행될 수 있다. 또한, 통신 종료 후

,

, BLER,

,

, 위치정보 및 채널정보를 저장하고, 인공지능 초기값 설정기의 전이학습시 학습 데이터로 사용할 수 있다.Additionally, as an example, the artificial intelligence initial value setter may be designed in the form of a predictor in the form of supervised learning. As an example, in the case of Thompson sampling, the initial value

,

You can set and transmit it to the artificial intelligence beam selector. At this time, prediction can be performed considering the channel environment (eg SNR) and the location information of the terminal. Also, after communication ends

,

, BLER,

,

, location information and channel information can be stored and used as learning data during transfer learning of the artificial intelligence initial value setter.

Figure 29 is a diagram showing an example of an artificial intelligence coding initial value setter applicable to the present disclosure. Referring to Figure 29, the artificial intelligence coding initial value setter can set the initial value by considering the location information of the transmitter and the channel environment (signal-to-noise ratio, SNR).

,

를 확보함으로써, 로드가 감소될 수 있다. 일 예로, 성능은 하기 수학식 26과 같을 수 있다.Since there are many combinations of generation matrices when the size of the linear block code is large, considering too many generation matrices may cause excessive load on the terminal/base station, and it may take a lot of time for stabilization. However, depending on the communication channel environment, pre-training is performed on all generation matrices to determine the initial value.

,

By securing , the load can be reduced. As an example, the performance may be expressed as Equation 26 below.

At this time, the artificial intelligence coding initial value setter can create candidate sets for the generation matrix in order of high performance. Candidate sets may be generated differently depending on the channel environment. These candidate sets can be defined in the form of codebooks. The receiver can transmit the codebook set to be used by the transmitter in index form. Additionally, the receiver may directly transmit the codebook to be used by the transmitter.

,

을 설정하여 수신기로 전송할 수 있다. 이 때, 채널환경과 단말의 위치정보를 고려해서 예측할 수 있다. 통신 종료 후,

,

, BLER,

,

, 위치정보, 채널정보를 저장하여 인공지능 코딩 초기값 설정기를 다시 트레이닝(re-training)할 때, 학습 데이터로 사용할 수 있다.Artificial intelligence coding initial value setter is not only a candidate set but also an initial value

,

You can set and transmit to the receiver. At this time, prediction can be made taking into account the channel environment and location information of the terminal. After communication ends,

,

, BLER,

,

, location information, and channel information can be stored and used as learning data when re-training the artificial intelligence coding initial value setter.

Figure 30 is a diagram showing a method of performing wireless environment optimization based on an artificial intelligence system according to an embodiment of the present disclosure.

Referring to FIG. 30, the terminal may transmit first index information related to the IRS control value to the IRS (S3010). At this time, as an example, the IRS control value may be determined based on the first index information. Here, each phase value within the IRS element can be determined based on the IRS control value determined as described above. Additionally, as an example, the above-described first index information may be information generated through a codebook based on an IRS direction vector set. As an example, the first index information may be composed of a first factor based on the IRS azimuth angle and a second factor based on the IRS elevation angle, as described above.

At this time, the artificial intelligence beam selector may be included in the terminal. As an example, the above-described first index information may be determined based on the artificial intelligence beam selector of the terminal, and the determined first index information may be transmitted to the IRS.

Here, as an example, the terminal and the base station can set the initial value applied to the artificial intelligence beam selector. More specifically, the terminal can receive a reference signal for setting the initial value from the base station. Afterwards, the terminal can obtain channel state information through a reference signal for setting the initial value. The terminal can feed back the acquired channel state information and location information of the terminal to the base station. At this time, the base station may include an artificial intelligence initial value setter. The base station can derive the artificial intelligence initial value based on the artificial intelligence initial value setter and transmit information about it to the terminal. Additionally, as an example, the terminal may further receive candidate set information related to the index information transmitted to the IRS, as described above. The terminal can derive the above-described first index information through learning based on the received artificial intelligence initial value information and candidate set information.

Afterwards, the terminal may receive a reference signal to which the first beamforming has been applied from the base station through the IRS. (S3020) At this time, as an example, the base station may receive the first beamforming signal based on the location of the IRS when performing initial setup with the IRS. Beamforming can be determined. That is, information about the first beamforming may be information that the base station recognizes and manages in advance.

Next, the terminal can obtain at least one of compensation value information and channel state information through a reference signal transmitted by applying first beamforming from the base station. Next, the terminal may update the first index information to the second index information through at least one of compensation value information and channel state information (S3040). After that, the terminal sends the updated second index information to the IRS. Can be transmitted. (S3050) As an example, the terminal may include an artificial intelligence beam selector, as described above. Here, the artificial intelligence beam selector may update the above-described first index information to the second index information through at least one of compensation value information and channel state information. As an example, the artificial intelligence beam selector may update the first index information to the second index information based on either the MAB AI learning model or the reinforcement learning learning model described above. For example, when the artificial intelligence beam selector updates the first index information to the second index information based on the MAB AI learning model, the second index information may be obtained through learning based on compensation value information.

As another example, when the artificial intelligence beam selector updates first index information with second index information based on a reinforcement learning learning model, state information is set based on the first index information, and state information and compensation value information Second index information can be obtained through learning based on .

Here, the above-described compensation value can be obtained through the IRS performance meter. As an example, the terminal includes an IRS performance meter, and the IRS performance meter can generate compensation value information using channel-related information obtained through a reference signal, as described above.

Next, the terminal may receive a reference signal to which the second beamforming is applied from the base station based on the updated second index information through the IRS. (S3060) At this time, the IRS converts the first index information into the second index information. When updating, the IRS may transmit a wireless environment change completion signal including second index information to the base station. The base station may determine the above-described second beamforming based on the second index information and apply it to reference signal transmission.

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. Information on whether the proposed methods are applicable (or information on the rules of the proposed methods) can be defined so that the base station informs the terminal through a predefined signal (e.g., a physical layer signal or a higher layer signal). there is.

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 terminal operation method in a wireless communication system,
Transmitting first index information related to an Intelligent Reflect Surface (IRS) control value to the IRS;
Receiving a reference signal to which first beamforming is applied from a base station through the IRS;
Obtaining at least one of compensation value information and channel state information based on the received reference signal;
updating the first index information to second index information through at least one of the compensation value information and the channel state information;
transmitting the updated second index information to the IRS; and
Receiving a reference signal to which second beamforming is applied from the base station based on the updated second index information through the IRS. According to claim 1,
The IRS control value is determined based on index information,
A terminal operating method in which each phase value in an IRS element is determined based on the determined IRS control value. According to claim 2,
The index information is information generated through a codebook based on the IRS direction vector set,
The index information consists of a first factor based on the IRS azimuth angle and a second factor based on the IRS elevation angle. According to claim 1,
The terminal receives a reference signal for setting an initial value from the base station, and feeds back channel state information and location information of the terminal obtained through the received reference signal for setting an initial value to the base station,
A method of operating a terminal, wherein the terminal receives artificial intelligence initial value information derived from the base station based on the received channel state information and location information of the terminal. According to claim 4,
The terminal further receives candidate set information related to index information from the base station. According to claim 5,
A terminal operating method wherein the terminal derives the first index information based on the received artificial intelligence initial value information and the candidate set information. According to claim 1,
The base station determines the first beamforming based on the location of the IRS when performing initial setup with the IRS. According to claim 7,
When the IRS updates the first index information with the second index information, the IRS transmits a wireless environment change completion signal including the second index information to the base station,
The base station determines the second beamforming based on the second index information. According to claim 1,
The terminal includes an artificial intelligence beam selector,
The artificial intelligence beam selector updates the first index information to the second index information through at least one of the compensation value information and the channel state information. According to clause 9,
The artificial intelligence beam selector updates the first index information with the second index information based on either a multi-armed bandit (MAB) artificial intelligence (AI) learning model or a reinforcement learning learning model. According to claim 10,
When the artificial intelligence beam selector updates the first index information to the second index information based on the MAB AI learning model, a terminal operation of acquiring the second index information through learning based on the compensation value information. method. According to claim 10,
When the artificial intelligence beam selector updates the first index information with the second index information based on the reinforcement learning learning model, state information is set based on the first index information, and the state information and the compensation A terminal operation method of acquiring the second index information through learning based on value information. According to claim 1,
The terminal includes an IRS performance meter,
The IRS performance measurer generates the compensation value information using channel-related information obtained through a reference signal. In a method of operating a base station in a wireless communication system,
Transmitting a reference signal to which first beamforming has been applied to the terminal through IRS;
Receiving second index information updated from first index information through the IRS; and
Transmitting a reference signal to which second beamforming is applied to the terminal through the IRS; including,
The terminal transmits first index information related to the IRS control value to the IRS, obtains at least one of compensation value information and channel state information through the reference signal to which the first beamforming is applied, and obtains the compensation value information and updating the first index information with the second index information through at least one of the channel state information and transmitting the second index information to the IRS. In the terminal of a wireless communication system,
transceiver; and
Including a processor connected to the transceiver,
The processor,
Transmitting first index information related to the IRS control value to the IRS through the transceiver,
Receiving a reference signal to which first beamforming is applied from a base station through the transceiver through the IRS,
Obtaining at least one of compensation value information and channel state information based on the received reference signal,
Updating the first index information to second index information through at least one of the compensation value information and the channel state information,
transmitting the updated second index information to the IRS, and
A terminal receiving a reference signal to which second beamforming is applied from the base station based on the updated second index information through the IRS. In the base station of a wireless communication system,
transceiver; and
Including a processor connected to the transceiver,
The processor,
Transmitting a reference signal to which first beamforming is applied through the transceiver to the terminal through IRS,
Receive second index information updated from the first index information through the IRS through the transceiver, and
A reference signal to which second beamforming is applied is transmitted through the transceiver to the terminal through the IRS,
The terminal transmits first index information related to the IRS control value to the IRS, obtains at least one of compensation value information and channel state information through the reference signal to which the first beamforming is applied, and obtains the compensation value information and a base station updating the first index information with the second index information through at least one of the channel state information and transmitting the second index information to the IRS. A device comprising at least one memory and at least one processor functionally connected to the at least one memory,
The at least one processor is configured to:
transmitting first index information related to IRS control values to the IRS;
Receiving a reference signal to which first beamforming is applied from a base station through the IRS,
Obtaining at least one of compensation value information and channel state information based on the received reference signal,
Updating the first index information to second index information through at least one of the compensation value information and the channel state information,
transmitting the updated second index information to the IRS, and
A device that receives a reference signal to which second beamforming is applied from the base station based on the updated second index information through the IRS. 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 is:
The device transmits first index information related to the IRS control value to the IRS,
Receiving a reference signal to which first beamforming is applied from a base station through the IRS,
Obtaining at least one of compensation value information and channel state information based on the received reference signal,
Updating the first index information to second index information through at least one of the compensation value information and the channel state information,
transmitting the updated second index information to the IRS, and
A computer-readable medium that receives a reference signal to which second beamforming is applied from the base station based on the updated second index information through the IRS.

Images