Method and device for channel estimation based on artificial intelligence in wireless communication system

Abstract

The present disclosure proposes a method and a device in which an electronic device performs channel estimation for all antennas on the basis of partial CSI by using an artificial intelligence model. According to an embodiment of the present disclosure, a method of a base station in a wireless communication system comprises the operations of: grouping a plurality of transmission antenna ports into K groups, wherein K is a natural number of 2 or more; transmitting K channel state information-reference signals (CSI-RSs) for each of the K groups to a terminal; receiving at least one partial channel state information (CSI) for the K CSI-RSs; and determining a codebook for precoding of a transmission signal by using an artificial intelligence (AI) model on the basis of the at least one partial CSI.

Description

Artificial intelligence-based channel estimation method and device in a wireless communication system

[0001] The present disclosure relates to a method and apparatus for estimating channel state information based on artificial intelligence in a wireless communication system.

[0002] 전자 장치는 디지털 기술의 발달과 함께 스마트폰(smart phone), 태블릿 PC(tablet personal computer), 또는 PDA(personal digital assistant)와 같은 다양한 형태로 제공되고 있다.

[0003] As artificial intelligence technology advances, electronic devices can provide various artificial intelligence services by applying artificial intelligence technology. Based on artificial intelligence technology and voice recognition technology, electronic devices can provide artificial intelligence services that process tasks requested by the user and offer software configurations (e.g., services, functions, or programs) that provide services specialized for the user (e.g., customized information based on user voice commands).

[0004] Machine learning is a field related to artificial intelligence that develops algorithms and technologies enabling computers to learn. Deep learning refers to a set of machine learning algorithms that attempt a high level of abstraction (the task of extracting only the essential content from a large amount of complex data) through a combination of non-linear transformation techniques.

[0005] Meanwhile, MIMO (multiple-input multiple-output) technology continues to evolve even following the recent New Radio (NR) standard, a 5th-generation data transmission method. In the 3GPP (3rd generation partnership project) NR standard, various technologies related to MIMO, such as beam management, new types of codebooks, and associated CSI (channel state information) feedback techniques, are being standardized. Furthermore, codebook designs considering various transmission scenarios (coherent joint transmission, medium / high velocity, etc.) have been developed to transmit and receive more sophisticated CSI. In particular, the technology is evolving into techniques that utilize more antenna elements to achieve high beam-forming gain, such as Massive MIMO and Ultra-massive MIMO.

[0006] In NR standards, the standardization of a CSI framework supporting up to 128 antenna ports on a base station (BS) is currently underway. This trend of advancing the CSI framework is expected to continue in standards beyond 5G, as the advancement of the CSI framework can contribute to improvements in throughput performance by generating sophisticated beams. On the other hand, this is accompanied by issues such as CSI feedback overhead and increased complexity of codebook selection algorithms, requiring solutions and technological advancements to resolve these challenges.

[0007] The information described above may be provided as related art for the purpose of aiding understanding of this document. None of the foregoing is to be claimed as prior art related to this document, nor is it to be used to determine prior art.

[0008] The present disclosure proposes a method for estimating and learning CSI of a massive MIMO system using AI / ML. The present disclosure proposes a system in which base station antennas are grouped to transmit CSI-RS (channel state information reference signal) for each group, and a terminal (user equipment, UE) feeds back partial CSI for each antenna group, wherein the base station uses AI to combine partial CSIs to generate a codebook for the entire antenna.

[0009] A method of an electronic device in a wireless communication system according to one embodiment of the present disclosure comprises: an operation of grouping a plurality of transmitting antenna ports into K groups—wherein K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0010] A storage medium for storing at least one computer-readable instruction according to one embodiment of the present disclosure, wherein when the at least one instruction is executed by at least part of at least one processor (120) of an electronic device, the electronic device causes the electronic device to perform at least one operation, and the at least one operation includes: an operation of grouping a plurality of transmitting antenna ports into K groups—where K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0011] According to one embodiment of the present disclosure, an electronic device comprises at least one processor (120); and a memory (130) for storing at least one instruction, wherein the at least one instruction causes the electronic device to perform at least one operation when executed by at least part of the at least one processor (120), the at least one operation comprising: an operation of grouping a plurality of transmitting antenna ports into K groups—where K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0012] By the present disclosure, partial CSI information is combined to have optimal performance 포트 코드북을 결정하는 방법을 인공 지능 또는 머신 러닝 기술에 대한 솔루션으로 제공함에 따라 MIMO와 같은 다수의 안테나가 이용되는 통신 시스템에서 빔 형성(beam-forming) 성능을 향상시킬 수 있다.

[0013] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0014] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment of the present disclosure.

[0015] FIG. 2 illustrates a block diagram of an electronic device according to one embodiment of the present disclosure.

[0016] FIG. 3 is a diagram illustrating the CSI feedback operation of a closed-loop MIMO system according to one embodiment of the present disclosure.

[0017] FIG. 4 illustrates CSI feedback and precoding operations according to one embodiment of the present disclosure.

[0018] FIG. 5 illustrates a precoding operation based on partial CSI feedback and artificial intelligence (AI) according to one embodiment of the present disclosure.

[0019] FIG. 6 illustrates a framework for estimating a codebook for a full CSI using a partial CSI using an AI model of an electronic device according to one embodiment of the present disclosure.

[0020] FIG. 7 is a diagram illustrating the learning and inference operations of an AI-based codebook estimator using partial CSI of an electronic device according to one embodiment of the present disclosure.

[0021] FIG. 8 is a diagram illustrating the learning and inference operations of an AI-based channel estimator using partial CSI of an electronic device according to one embodiment of the present disclosure.

[0022] 도 9는 본 개시의 일 실시예에 따른, 전자 장치의 부분(partial) CSI를 이용한 AI 기반 코드북 추정기의 학습 및 추론 동작을 구체화하여 설명하는 도면이다.

[0023] 도 10은 본 개시의 일 실시예에 따른, 전자 장치의 부분(partial) CSI를 이용한 AI 기반 채널 추정기의 학습 및 추론 동작을 구체화하여 설명하는 도면이다.

[0024] FIG. 11 is a flowchart illustrating an AI-based codebook estimation operation using partial CSI of a base station according to one embodiment of the present disclosure.

[0025] FIG. 12 is a flowchart illustrating an AI-based channel estimation operation using partial CSI of a base station according to one embodiment of the present disclosure.

[0026] Hereinafter, embodiments of the present disclosure are described in detail with reference to the drawings so that those skilled in the art can easily practice them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0027] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0028] The processor (120) can control at least one other component (e.g., hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., sensor module (176) or communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., central processing unit or application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., graphics processing unit, neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0029] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0030] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0031] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0032] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0033] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0034] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0035] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0036] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0037] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0038] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0039] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0040] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0041] The power management module (188) can manage the power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0042] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0043] A communication module (transmitter / receiver) (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of a processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0044] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0045] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0046] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0047] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0048] According to one embodiment, commands or data may be transmitted or received between an electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0049] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0050] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0051] As used in various embodiments of this document, the term “module” may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0052] Various embodiments of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0053] In the following description, the electronic device may include a receiving device that receives a signal (or data) from a transmitting device of a wireless communication system. For example, the electronic device may include a base station that receives a signal (or data) from a terminal. As an example, the base station may be at least one of a Node B, a BS (base station), an eNB (eNode B), or a gNB (gNode B). For example, the electronic device may include a terminal that receives a signal (or data) from a base station. As an example, the terminal may be at least one of a UE (user equipment), an MS (mobile station), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing communication functions.

[0054] FIG. 2 illustrates a block diagram of an electronic device according to one embodiment of the present disclosure.

[0055] FIG. 2 illustrates a block diagram of an electronic device according to one embodiment of the present disclosure.

[0056] According to one embodiment, the electronic device (101) may include, and / or execute a frontend module (210) and / or a service processing module (220). The frontend module (210) and / or the service processing module (220) may be executed, for example, by a processor (120) or may be included as at least part of the processor (120) or other entity. At least some of the operations performed by the frontend module (210) and / or the service processing module (220) in the present disclosure may be understood as being performed, for example, by the processor (120) and / or other entity under the control of the processor (120).

[0057] The frontend module (210) can perform at least one operation for exchanging data with, for example, an external electronic device (106a, 106b, 106c, ..., 106n). For example, the frontend module (210) can provide data that can configure a user interface (UI) for inputting user input from the external electronic device (106a, 106b, 106c, ..., 106n). The frontend module (210) can provide processing for user requests to the service processing module (220). The service processing module (220) can perform a service using the user request and may be named a backend module. The service processing module (220) can provide a response corresponding to the user request to the frontend module (210). The frontend module (210) can provide the response received from the service processing module (220) to an external electronic device (106a, 106b, 106c, ..., 106n).

[0058] 서비스 처리 모듈(220)은, 예를 들어 사용자 요청 확인 모듈(221), 최적화 모듈(222), AI 모델 관리 모듈(224), 정책 관리 모듈(226) 및 / 또는 서비스 수행 모듈(227)을 포함할 수 있다.

[0059] The user request verification module (221) can verify information associated with user requests provided by external electronic devices (106a, 106b, 106c, ..., 106n). Information associated with user requests may be expressed, for example, as the number of user requests and / or the size of user requests over a certain period, but there are no limitations. For example, the user request verification module (221) may count the number of user requests provided by external electronic devices (106a, 106b, 106c, ..., 106n) and / or monitor the size of content included in the user requests (e.g., text and / or graphic objects, but there are no limitations), but there are no limitations on the type of information associated with user requests and / or the verification method.

[0060] The optimization module (222) can provide at least one optimal number of instances for each of at least one AI model associated with the service.

[0061] AI 모델 관리 모듈(224)은, 서비스와 연계되는 AI 모델을 저장 및 / 또는 관리(예를 들어, 추가, 삭제, 및 / 또는 갱신을 포함할 수 있으나 제한이 없음)할 수 있다.

[0062] The policy management module (226) may, for example, store and / or manage allowable response times (e.g., may include, but is not limited to, adding, deleting, and / or updating). For example, the management device (104) may verify (e.g., receive or determine) at least one input for determining allowable response times and provide it to the electronic device (101). For example, an administrator may input information regarding allowable response times for the corresponding service into the management device (104), but this is exemplary and there is no limitation on the way allowable response times are verified.

[0063] The service execution module (227) can execute each of at least one instance group (231, 232, 233) corresponding to at least one AI model associated with the service, for example. The service execution module (227) can execute at least one instance group (231, 232, 233) corresponding to at least one AI model according to the optimal number of instances provided by the optimization module (222), for example. The service execution module (227) can process user requests based on the executed at least one instance group (231, 232, 233) and can provide a response according to the processing result to an external electronic device (106a, 106b, 106c, ..., 106n) through the frontend module (210). According to one embodiment, if there are multiple instances being executed, user requests can be distributed and processed by the multiple instances.

[0064] Meanwhile, recent 3GPP standards are standardizing methods for utilizing AI (artificial intelligence) and ML (machine learning) technologies in telecommunications. The application of AI and ML is being considered primarily in technical fields that allow for estimation based on actual data. Among these, AI and ML technologies related to CSI feedback are being discussed; specifically, CSI compression to reduce CSI overhead and CSI prediction for future channels are being debated as key topics. The trend is toward prioritizing standardization in areas where analysis is possible based on experimental data results, which are difficult to perform mathematically.

[0065] FIG. 3 is a diagram illustrating the CSI feedback operation of a closed-loop MIMO system according to one embodiment of the present disclosure.

[0066] 도 3을 참조하면, 폐루프 MIMO 시스템은 송신기(transmitter)(300), 수신기(receiver)(310)를 포함할 수 있다. 예를 들어, 도 3에서 송신기(300)는 기지국으로 구현되고, 수신기(310)는 단말로 구현될 수 있다.

[0067] Referring to FIG. 3, the number of transmitting antennas of the base station (300) , the number of receiving antennas of the terminal (310) When saying that, the actual downlink channel (320) × of The channel estimated at the terminal (310) is represented as a matrix. It can be written as.

[0068] 도 3에서 도시한 폐루프(closed-loop) MIMO 시스템에서 기지국(300)은 단말(310)로 CRS(cell-specific reference signal) 또는 CSI-RS(channel state information-reference signal)의 참조 신호를 전송하고, 단말(310)은 상기 참조 신호들을 이용해 하향 링크(downlink, DL) 채널 정보를 획득할 수 있다.

[0069] 이후, 단말(310)은 규격에 정의된 프리코딩(precoding) 코드북 중 추정된 DL 채널에 적합한 코드북을 결정하여 해당 코드북에 대한 정보를 기지국에 피드백 할 수 있다.

[0070] The terminal (310) obtains CQI (channel quality indicator) information from the received signal and estimates After deriving PMI (precoding matrix indicator) and RI (rank indicator) values ​​that maximize the capacity or SNR (signal-to-noise ratio) of the effective channel, the results can be transmitted to the base station (300) via a CSI report (330). For example, the formulas for finding the PMI and RI that maximize the capacity of the effective channel and the SNR can be expressed as Equation 1 and Equation 2, respectively.

[0071] [Mathematical Formula 1]

[0072]

[0073] [Mathematical Formula 2]

[0074]

[0075] Here, represents a codebook or precoding matrix mapped to a given PMI and RI, and represents the noise power added at the receiving end.

[0076] In this disclosure, without specifying a function to find PMI and RI If written as, It can be represented as follows. The base station (300) receives feedback Precoding codebook using information It can be selected and used for transmission (however, the base station (300) may select a precoding codebook different from the feedback information depending on the situation).

[0077] The base station (300) has a function for selecting a codebook If written as, It can be displayed as.

[0078] In 3GPP mobile communication systems (e.g., 4G and 5G standards), CSI feedback and codebook formats suitable for antenna shapes are standardized. In particular, the 5G NR standard standardizes various types of codebooks (Type-1, Type-2, Enhanced Type-2, etc.) and CSI feedback information and information transmission methods, taking into account up to 32 antenna ports of a base station.

[0079] In the NR standard, regarding the standardization of codebooks and CSI feedback information for antenna shapes larger than the existing 32 antennas, standardization for antenna shapes assuming up to 128 antenna ports is being considered. Furthermore, for standards such as 6G following 5G, there is a need for methods to utilize codebooks and CSI feedback that assume a larger number of antenna ports.

[0080] For CSI and codebooks in up to 128 antenna configurations, CSI-RS resources for existing 32 or fewer antenna ports when transmitting via 32 ports You can use dogs. For example, It supports up to 48, 64, and 128 ports, and the number of CSI-RS resources for each CSI-RS transmission and the number of ports for each resource It can be set as shown in Table 1 below. . corresponding The resources must be allocated within 1 slot or 2 consecutive slots.

[0081]

[0082] 도 4는 본 개시의 일 실시예에 따른 CSI 피드백과 프리코딩 동작을 도시한다. 도 4는 기지국(400)과 단말(410) 간 CSI 피드백과 코드북 결정 및 프리코딩 동작을 도시한다.

[0083] More specifically, in operation 420, the base station (400) is Port CSI-RS can be transmitted to the terminal (410).

[0084] In operation 425, the terminal (410) that receives this can report the CSI to the base station (400) (e.g., PMI and RI).

[0085] In operation 430, the base station (400) that receives the CSI can select a codebook, precode based on the codebook, and transmit.

[0086] In Fig. 4, since CQI is not required for codebook determination, CQI is omitted from the CSI reports below for convenience. For example, existing 의 안테나 포트에서는 단말(410)이 한 번에 CSI를 피드백 한 후에, 기지국(400)이 해당 피드백을 받아 코드북을 결정하고 프리코딩을 수행하는 형태로 동작했다. 그러나, If it is > 32, for example, =128 이면 128 포트에 대한 CSI-RS 자원의 할당이 필요하며, 이런 경우 데이터 전송에 사용하는 자원이 적어져서 전송률이 낮아지는 문제가 발생할 수 있다.

[0087] hereto, In the case where =128, the total number of antennas is 4 as shown in Table 1 above ( Divided into groups of =4) 32 ports ( =32) 씩 각 안테나 그룹을 시간 차이를 두어 CSI-RS를 전송할 수 있다. 이 경우, CSI 피드백도 안테나 그룹 단위로 제한되어 전송될 수 있다. 기지국(400)은 32 포트 CSI 4개를 결합하여 128 포트 코드북을 결정할 수 있다. 상기 전체 안테나가 그룹으로 나누어진 포트( )에 대해 수신한CSI를 부분(partial) CSI (예를 들어, 32 포트)로 지칭할 수 있으며, 부분(partial) CSI를 결합해 full CSI (eg, 128 포트)를 도출하는 방법은 향후 As this grows and CSI becomes more sophisticated, it is required to be advanced.

[0088] 기지국의 안테나 수가 128 포트로 증가함에 따라 CSI를 안테나 그룹 별로 나누어 피드백 하는 방법이 고려될 수 있고, partial CSI를 결합하여 full CSI를 생성하는 방법은 ultra-massive MIMO 기술 적용에 따라서 필요성이 향상되고 있다.

[0089] 따라서 본 개시는 AI / ML을 활용하여 부분(partial) CSI에서 전체(full) CSI를 도출하는 방법을 제안한다.본 개시에서는 AI / ML을 활용하여 부분(partial) CSI에서 전체(full) CSI를 도출하여 프리코더를 추정하는 방안과 프레임워크을 제안한다.

[0090] FIG. 5 illustrates a precoding operation based on partial CSI feedback and artificial intelligence (AI) according to one embodiment of the present disclosure.

[0091] FIG. 5 illustrates CSI feedback between a base station (500) and a terminal (510) and AI-based codebook determination and precoding operations of the base station (500).

[0092] The present disclosure is based on a base station After receiving all partial CSIs, use an AI model In addition to the method for determining the port codebook, a method for performing AI processing while receiving partial CSI each time as shown in Fig. 5 is proposed.

[0093] The terminal (510) provides CSI feedback to the PMI, RI pair It can be denoted as (k= 1,2,3, ..., ). In FIG. 3, index k was assigned in chronological order, but it can be assigned arbitrarily. Also, the base station (500) and the terminal (510) each Antenna group information regarding this may be shared in advance and not included in CSI feedback.

[0094] Referring to FIG. 5, in operation 520, the base station (500) for A1 Port CSI-RS can be transmitted to the terminal (510). In operation 525, the terminal (510) that receives it CSI It can be reported to the base station (500). In operation 527, the base station (500) that received the CSI receives the above-mentioned report AI processing can be performed on. The detailed operation of AI processing will be described later.

[0095] Subsequently, the base station [represents] the number of operations 520 to 527 grouped by CSI Considering, It can be repeated once. In operation 530, the base station (500) is A K for Port CSI-RS can be transmitted to the terminal (510). In operation 535, the terminal (510) that receives it CSI It can be reported to the base station (500). In operation 527, the base station (500) that received the CSI receives the above-mentioned report AI processing can be performed on. The detailed operation of AI processing will be described later.

[0096] In operation 520, the base station can perform AI-based codebook determination and precoding.

[0097] FIG. 6 illustrates a framework for estimating a codebook for a full CSI using a partial CSI with an AI model according to one embodiment of the present disclosure.

[0098] FIG. 6(a) shows a codebook by inputting a partial CSI (630) into an AI-based codebook predictor (610). Outputs the data x (625) to be transmitted from the precoder (620) to the output codebook Pre-code based on and output (640) Illustrates an example of a framework (600) of a modem DU (data unit).

[0099] FIG. 6(b) shows the channel value by inputting the partial CSI (680) into the AI-based channel predictor (660). Outputs, and the channel value in the codebook determiner (665) Codebook based on Redetermine and the data x (675) to be transmitted from the precoder (670) to the codebook Pre-code based on and output (690) Illustrates an example of a framework (650) of a DU (data unit).

[0100] 도 6의 (b)처럼 채널 정보를 출력하는 경우에는 추가적으로 코드북을 결정하는 알고리듬을 적용하여 최종 코드북을 획득하며, 이 때 상기 수학식 1 및상기 수학식 2를 이용할 수 있다.

[0101] Most neural networks used in supervised learning can be used as the AI ​​model of the present disclosure, for example, artificial neural networks (ANN), deep neural networks (DNN), convolutional neural networks (CNN), transformers, etc. Partial CSI, which is the input data of the AI ​​model, and codebook or channel data, which is the output data, can be used in SW or HW modules within the modem digital unit (DU). However, depending on the modem operation option, the functions performed by the precoder may be performed in the radio unit (RU).

[0102] 도 6에서, 본 개시의 프레임워크를 두 종류(코드북 추정, 채널 추정)로 도시하였는데, 각 프레임워크 내에서도 partial CSI의 정의에 따라 이하의 두 종류의 방식으로 구분할 수 있다.

[0103] Definition 1) Partial CSI 1: M' Port CSI Feedback

[0104] Definition 2) Partial CSI 2: Port CSI Feedback

[0105] In Definition 1, Partial CSI is a terminal After receiving Port CSI-RS It refers to determining and providing feedback on CSIs such as Port PMI, RI, and CQI, and in Definition 2, Partial CSI refers to the terminal After receiving Port CSI-RS It refers to determining and providing feedback on CSIs such as Port PMI, RI, and CQI. In Definition 2, Partial CSI is not this It refers to feeding back the CSI to the port.

[0106] In FIGS. 7 and 8 below, the learning and inference operations of an AI-based codebook estimator using partial CSI and the learning and inference operations of an AI-based channel estimator are described. For convenience, the operations illustrated in FIGS. 7 and 8 describe the Partial CSI feedback corresponding to Definition 1 mentioned earlier, but they can also be applied to the Partial CSI feedback corresponding to Definition 2.

[0107] FIG. 7 is a diagram illustrating the learning and inference operations of an AI-based codebook estimator using partial CSI of an electronic device according to one embodiment of the present disclosure.

[0108] The electronic device illustrated in Fig. 7 can be implemented as a base station in a mobile communication system.

[0109] Referring to FIG. 7, an AI codebook estimator using partial CSI can perform a training operation and an inference operation. The training operation may include the operation of a partial CSI extraction unit (730), a full CSI extraction unit (735), and a loss calculation unit (760). The inference operation may include the operation of a preprocessing unit (700) and an AI-based codebook predictor (710).

[0110] The partial CSI definition of Definition 1 explained earlier is that the terminal After receiving Port CSI-RS It determines the port PMI and RI and provides feedback. In other words, the terminal [represents] the number of base station antennas There is no need to share the information It performs channel reception and CSI feedback for the port. Therefore, meaningful at the base station To obtain Port CSI It is possible to estimate after receiving all partial CSI feedback.

[0111] Referring to FIG. 7, the partial CSI 1 of Definition 1 and the partial CSI 2 of Definition 2 described earlier are denoted as X values ​​(1 and 2), Indicate as , and the corresponding antenna index group It can be denoted as (750). For example, in the case of partial CSI 1 of Definition 1 described above, Indicate as , and the corresponding antenna index group It can be denoted as. Here is a mutually disjoint set, and the union 을 만족할 수 있다. 본 개시에서는 편의를 위하여, 입력 정보로 PMI, RI 만을 표기하였으며, 필요에 따라 CQI 등 다른 CSI 정보들을 입력으로 사용할 수 있다.

[0112] 본 개시는 입력 데이터와 정답 데이터를 활용하여 학습시키는 지도 학습을 채용하기 때문에 사전에 AI 모델을 학습시킬 수 있다. 이 경우, 채널 데이터 The network operator may obtain channel data directly from commercial terminals, or generate and use channel data through computer simulation.

[0113] First, in the training process, channel data is used to generate the data necessary for training the AI ​​model. (720) may be needed. And the given channel (720) Antenna group Submatrix corresponding to (740) from It can be obtained and input into an AI model. However, before being input into the AI ​​model, depending on the type or configuration of the neural network of the model, preprocessing (700) may be required to adjust the range of values ​​or convert them into equivalent other data (e.g., quantized channels) instead of inputting the values ​​as they are. And, in the AI-based codebook predictor (710), the codebook It can output. In addition, provided as the correct answer of the AI ​​model output is in the full CSI extraction unit (735) It can be derived as.

[0114] In one embodiment, the loss calculation unit (760) outputs the AI ​​model Wow, the correct answer By defining the difference as the loss, the model can be trained using optimization techniques from the gradient descent family in the direction that minimizes the loss. Here, functions such as the Mean Square Error (MSE) or Codebook Distance can be used to calculate the loss. For example, using MSE or Codebook Distance functions, the parameters of the AI ​​model The equations for optimizing can be expressed as Equation 3 and Equation 4, respectively, and consequently, the AI ​​model parameters It can determine the weights and biases of the AI ​​model.

[0115] [Mathematical Formula 3]

[0116]

[0117] [Mathematical Formula 4]

[0118]

[0119] 학습이 충분히 된 후 모델을 사용할 때에는 기지국은 단말로부터 수신 받는 partial CSI 정보들을 전처리부(pre-processing)(700)와 AI 모델(AI 기반 코드북 예측부)(710)에 입력하고, 출력으로 생성되는 It can be used as a codebook.

[0120] FIG. 8 is a diagram illustrating the learning and inference operations of an AI-based channel estimator using partial CSI according to one embodiment of the present disclosure.

[0121] In Fig. 8, the process of acquiring the partial CSI that enters as input to the AI ​​model can be applied as described in Fig. 7. However, the AI ​​model output in Fig. 8 is a channel It becomes, and what is provided as the correct answer in the AI ​​model output is also a channel This can be applied. After this, in the loss calculation unit (860) and The model can be trained in a direction that minimizes the loss.

[0122] In this case, the estimated channel as explained earlier Based on An additional process is required to determine the port codebook. The framework described in Fig. 7 has the advantage that the codebook can be determined by an AI model when the algorithm for determining the codebook is fixed, and the framework described in Fig. 8 performs channel estimation by an AI model, and the codebook determination algorithm can be applied flexibly according to transmission scenarios or other conditions.

[0123] 앞서 도 7 및 도 8의 경우, 정의 1에 해당하는 partial CSI에 대한 동작을 예시로 하여 설명하였으나, 정의 2에 해당하는 M 포트에 대한 partial CSI 피드백에 대해서도 적용이 가능하다.

[0124] 정의 2에 해당하는 M 포트에 대한 partial CSI 피드백의 경우에는 단말에서 After receiving the port CSI-RS, the corresponding channel 포트로 확장하기 위해 기지국에서 CSI-RS 전송 시 어떤 안테나 그룹을 사용하여 전송한 것인지에 대한 정보가 사전 공유 혹은 규격화되는 것이 필요하다. 예를 들어, Assuming that = 128 and that CSI-RS transmission samples at intervals of 4 starting from the first antenna index, the antenna indices used are 1, 5, 9, ..., 125. If the terminal knows this antenna index information, zero padding is applied to antennas without channel information to form a channel matrix as shown in Equation 5 below. It can be composed.

[0125] [Mathematical Formula 5]

[0126]

[0127] 상기 설명한 제로 패딩(zero padding)은 하나의 예시이며, 채널의 특성을 고려하여 다른 기법들이 적용될 수 있다. 정의 2에 해당하는 M 포트에 대한 partial CSI 피드백을 If denoted as such, the terminal is 을 적용하여 획득하는 CSI를 기지국으로 피드백 할 수 있다. 정의 2에 해당하는 M 포트에 대한 partial CSI 피드백를 이용한 AI 기반의 코드북 추정 모델에 대한 학습, 추론 과정 은 도 7 및 도 8에서 AI 모델의 입력으로 instead It can be used by entering.

[0128] Figures 9 and 10 below illustrate the AI ​​model (preprocessing unit and AI-based code predictor or AI-based channel predictor) described in Figures 7 and 8.

[0129] Figures 9 and 10 use an ANN as an example, but it can be replaced with other networks.

[0130] 도 9는 본 개시의 일 실시예에 따른, 전자 장치는 부분(partial) CSI를 이용한 AI 기반 코드북 추정기의 학습 및 추론 동작을 구체화하여 설명하는 도면이다.

[0131] More specifically, FIG. 9 illustrates the training and inference operations of an AI-based codebook estimator using partial CSI as described in FIG. 7. 의 입력(750), 전처리부(700), AI 기반 코드북 예측부(710)의 동작을 AI 모델 계층의 동작으로 구체화하여 도시한 도면이다. 도 9에서는 도7과 중복되는 구성에 대한 설명을 생략할 수 있으며, 도 7에서 설명된 바가 적용될 수 있다.

[0132] Referring to FIG. 9, the AI ​​model of the electronic device includes an AI network (ANN1, ANN2, ANNK) (910, 913, ..., 915) for each partial CSI input, and has a structure in which the output of ANNk becomes the input of ANNk+1, allowing for pre-processing of previously received partial CSIs before receiving the next partial CSI report. In one embodiment, the AI ​​model of the electronic device may optionally further include a preprocessing unit (900, 903, ..., 905).

[0133] In addition, the AI ​​model of the electronic device has a structure that processes sequentially in an AI network (ANN1, ANN2, ANNK) (910, 913, ..., 915), so repetitive operations can be used in the form of reusing (repeating) a single operation network, and as input is received and processed, the effect of the result becoming closer to an ideal result can also be expected. In one embodiment, the AI ​​model of the present disclosure may require updating the weights used in the neural network according to changes in the line of sight characteristics and Doppler characteristics of the channel.

[0134] For example, 3GPP has proposed a total of three types of training models related to CSI compression. In the present disclosure, in a manner similar to one of them, since the terminal knows downlink channel information and also has all information regarding partial CSI, the terminal can perform joint training and pass the learned weights to the base station.

[0135] FIG. 10 is a diagram that specifically illustrates the learning and inference operations of an AI-based channel estimator using partial CSI according to one embodiment of the present disclosure.

[0136] More specifically, FIG. 10 illustrates the training and inference operations of an AI-based channel estimator using partial CSI as described in FIG. 8. 의 입력(850), 전처리부(800), AI 기반 코드북 예측부(810)의 동작을 AI 모델 계층의 동작으로 구체화하여 도시한 도면이다. 도 10에서는 도8과 중복되는 구성에 대한 설명을 생략할 수 있으며, 도 8에서 설명된 바가 적용될 수 있다.

[0137] Referring to FIG. 10, the AI ​​model of the electronic device includes an AI network (ANN1, ANN2, ANNK) (1010, 1013, ..., 1015) for each partial CSI input, and is structured so that the output of ANNk becomes the input of ANNk+1, allowing for pre-processing of previously received partial CSIs before receiving the next partial CSI report. In one embodiment, the AI ​​model of the electronic device may optionally further include a preprocessing unit (1000, 1003, ..., 1005). The description of the AI ​​network (ANN1, ANN2, ANNK) (1010, 1013, ..., 1015) included in the AI ​​model of the electronic device of FIG. 10 may be applied as described in FIG. 9.

[0138] FIG. 11 is a flowchart illustrating an AI-based codebook estimation operation using partial CSI of a base station according to one embodiment of the present disclosure.

[0139] Figure 11 illustrates the operation of a base station corresponding to the AI-based codebook estimation procedure described in Figure 7 above.

[0140] In step 1100, the base station can initialize the variable K value to '0'.

[0141] In step 1110, the base station can assign a value of K+1 to the K value. For example, if the current K value is '0', it can assign '1' to the K value.

[0142] In step 1120, the base station can transmit the CSI-RS of the M'-port to the terminal using the antenna port that is AK. The M'-port is the number of transmitting antennas transmitted by the base station and the number of transmitting CSI-RS resources is multiple ( In the case of ), the number of antennas corresponding to one CSI-RS resource It can refer to the antenna port.

[0143] In step 1130, the base station may receive a partial CSI for the CSI-RS of the M'-port from the terminal. In one embodiment, if the partial CSI is partial CSI feedback for the M-port of Definition 2 described above, the partial CSI may be derived by the terminal augmenting the channel matrix using zero padding or interpolation.

[0144] In step 1140, the base station AI processing can be performed on partial CSI including.

[0145] 단계 1150에서, 기지국은 모든 부분(partial) CSI를 수신하였는지 여부를 결정할 수 있다. 기지국이 모든 부분(partial) CSI를 수신한 것으로 결정한 경우, 단계 1160에서 기지국은 모든 부분(partial) CSI를 사용하여 AI 기반의 코드북 예측을 수행할 수 있다.

[0146] 반면, 기지국이 모든 부분(partial) CSI를 수신하지 않은 것으로 결정한 경우, 단계 1110으로 회귀하여 K 값에 K+1값을 대입하여 단계 1120 내지 단계 1150을 수행할 수 있다.

[0147] FIG. 12 is a flowchart illustrating an AI-based channel estimation operation using partial CSI of a base station according to one embodiment of the present disclosure.

[0148] Figure 11 illustrates the operation of a base station corresponding to the AI-based channel estimation procedure described in Figure 8 above.

[0149] In step 1200, the base station can initialize the variable K value to '0'.

[0150] In step 1210, the base station can assign a value of K+1 to the K value. For example, if the current K value is '0', it can assign '1' to the K value.

[0151] In step 1220, the base station can transmit the CSI-RS of the M'-port to the terminal using the antenna port that is AK. The M'-port is the number of transmitting antennas that the base station transmits. and the number of transmitting CSI-RS resources is multiple ( In the case of ), the number of antennas corresponding to one CSI-RS resource It can refer to the antenna port.

[0152] In step 1230, the base station may receive a partial CSI for the CSI-RS of the M'-port from the terminal. In one embodiment, if the partial CSI is partial CSI feedback for the M-port for Definition 2 described above, the partial CSI may be derived by the terminal augmenting the channel matrix using zero padding or interpolation.

[0153] In step 1240, the base station AI processing can be performed on partial CSI including.

[0154] 단계 1250에서, 기지국은 모든 부분(partial) CSI를 수신하였는지 여부를 결정할 수 있다. 기지국이 모든 부분(partial) CSI를 수신한 것으로 결정한 경우, 단계 1260에서 기지국은 모든 부분(partial) CSI를 사용하여 AI 기반의 채널 예측을 수행할 수 있다.

[0155] In step 1270, the base station can determine the codebook based on the predicted channel.

[0156] In step 1280, the base station can select a precoding codebook.

[0157] 반면, 단계 150에서 기지국이 모든 부분(partial) CSI를 수신하지 않은 것으로 결정한 경우, 단계 1210으로 회귀하여 K 값에 K+1값을 대입하여 단계 1220 내지 단계 1250을 수행할 수 있다.

[0158] The use for explanation in the above Figures 11 and 12 , , Variable values ​​such as the above are examples and may be set and used with different values ​​depending on the standards or system operations to which this disclosure applies.

[0159] A method of an electronic device in a wireless communication system according to one embodiment of the present disclosure comprises: an operation of grouping a plurality of transmitting antenna ports into K groups—wherein K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0160] 일 실시예로, 상기 AI 모델을 이용하여 전송 신호의 프리코딩에 대한 코드북을 결정하는 동작;은, 상기 적어도 하나의 부분 CSI을 입력으로 하고, 코드북을 출력으로 하는 상기 AI 모델을 학습하는 동작;을 포함할 수 있다.

[0161] In one embodiment, the operation of training the AI ​​model may include the operation of determining at least one parameter of the AI ​​model such that the difference between the first codebook, which is the output of the AI ​​model, and the second codebook, which is determined based on the total CSI for a plurality of transmitting antenna ports, is reduced by taking the at least one partial CSI as input.

[0162] 일 실시예로, 상기 코드북을 결정하는 동작은, 상기 적어도 하나의 부분(partial) CSI에 기반하여 인공 지능(artificial intelligence, AI) 모델을 이용하여 채널 상태를 추정하는 동작; 및 상기 추정된 채널 상태에 기반하여 상기 코드북을 결정하는 동작;을 포함할 수 있다.

[0163] 일 실시예로, 상기 적어도 하나의 부분(partial) CSI는, PMI(precoding matrix indicator) 및 RI(rank indicator)를 포함할 수 있다. 일 실시예로, 상기 전자 장치는 기지국으로 구현될 수 있다.

[0164] 일 실시예로, 상기 적어도 하나의 부분(partial) CSI는, 상기 K 개의 그룹 중 하나의 그룹에 포함되는 적어도 하나의 송신 안테나 포트에 대한CSI를 포함하고, 또는 복수의 송신 안테나 포트들에 대한 CSI를 포함할 수 있다.

[0165] In one embodiment, the operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI may include, when the at least one partial CSI includes a CSI for at least one transmitting antenna port included in one of the K groups, the operation of determining a codebook for precoding a transmission signal using the AI ​​model based on K CSIs for the K groups.

[0166] A storage medium for storing at least one computer-readable instruction according to one embodiment of the present disclosure, wherein when the at least one instruction is executed by at least part of at least one processor (120) of an electronic device, the electronic device causes the electronic device to perform at least one operation, and the at least one operation includes: an operation of grouping a plurality of transmitting antenna ports into K groups—where K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0167] According to one embodiment of the present disclosure, an electronic device comprises at least one processor (120); and a memory (130) for storing at least one instruction, wherein the at least one instruction causes the electronic device to perform at least one operation when executed by at least part of the at least one processor (120), the at least one operation comprising: an operation of grouping a plurality of transmitting antenna ports into K groups—where K is a natural number greater than or equal to 2—; an operation of transmitting K CSI-RS (channel state information - reference signals) for each of the K groups to a terminal; an operation of receiving at least one partial CSI (channel state information) for the K CSI-RS from the terminal; and an operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on the at least one partial CSI.

[0168] According to one embodiment, the method according to the embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0169] According to one embodiment, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to one embodiment, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device, At least one processor (120); and It includes a memory (130) that stores at least one instruction, and When the above at least one instruction is executed by at least part of the above at least one processor (120), it causes the electronic device to perform at least one operation, and The above at least one operation is: An operation of grouping multiple transmitting antenna ports into K groups—wherein K is a natural number greater than or equal to 2—; The operation of transmitting K CSI-RS (channel state information - reference signals) for each of the above K groups to a terminal; The operation of receiving at least one partial CSI (channel state information) for the K CSI-RSs from the terminal; and An electronic device characterized by including the operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI.

2. In claim 1, the operation of determining a codebook for the precoding of a transmission signal using the artificial intelligence (AI) model; is, An electronic device characterized by including the operation of learning the AI ​​model, which takes at least one partial CSI as input and a codebook as output.

3. In paragraph 1, the operation of training the AI ​​model; is, An electronic device characterized by including: an operation of determining at least one parameter of the AI ​​model such that the difference between the first codebook, which is the output of the AI ​​model, and the second codebook, which is determined based on the total CSI for a plurality of transmitting antenna ports, is reduced by taking at least one partial CSI as input.

4. In paragraph 1, the operation of determining the codebook is, An operation to estimate the channel state using an artificial intelligence (AI) model based on at least one partial CSI; and An electronic device characterized by including an operation to determine the codebook based on the estimated channel state.

5. In Paragraph 1, The above at least one partial CSI includes a PMI (precoding matrix indicator) and an RI (rank indicator), and The above electronic device is characterized by being implemented as a base station.

6. In paragraph 1, the at least one partial CSI is, Includes a CSI for at least one transmitting antenna port included in one of the K groups mentioned above, or An electronic device characterized by including CSI for multiple transmitting antenna ports.

7. In paragraph 6, the operation of determining a codebook for the precoding of a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI; is, An electronic device characterized by including: an operation of determining a codebook for precoding a transmission signal using the AI ​​model based on the K CSIs for the K groups, wherein the above at least one partial CSI includes a CSI for at least one transmitting antenna port included in one of the K groups.

8. In a method of an electronic device in a wireless communication system, An operation of grouping multiple transmitting antenna ports into K groups—wherein K is a natural number greater than or equal to 2—; The operation of transmitting K CSI-RS (channel state information - reference signals) for each of the above K groups to a terminal; The operation of receiving at least one partial CSI (channel state information) for the K CSI-RSs from the terminal; and A method characterized by including the operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI.

9. In claim 8, the operation of determining a codebook for the precoding of a transmission signal using the artificial intelligence (AI) model; is, A method characterized by including the operation of training the AI ​​model, which takes at least one partial CSI as input and a codebook as output.

10. In paragraph 8, the operation of training the AI ​​model; is, A method characterized by including: determining at least one parameter of the AI ​​model such that the difference between the first codebook, which is the output of the AI ​​model, and the second codebook, which is determined based on the total CSI for a plurality of transmitting antenna ports, is reduced by taking at least one partial CSI as input.

11. In paragraph 8, the operation of determining the codebook is, An operation to estimate the channel state using an artificial intelligence (AI) model based on at least one partial CSI; and A method characterized by including the operation of determining the codebook based on the estimated channel state.

12. In paragraph 8, the above-mentioned at least one partial CSI is, Includes PMI (precoding matrix indicator) and RI (rank indicator), and A method characterized in that the above electronic device is implemented as a base station.

13. In paragraph 8, the above-mentioned at least one partial CSI is, Includes a CSI for at least one transmitting antenna port included in one of the K groups mentioned above, or A method characterized by including CSI for multiple transmitting antenna ports.

14. In paragraph 13, the operation of determining a codebook for the precoding of a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI; is, A method characterized by including the operation of determining a codebook for precoding a transmission signal using the AI ​​model based on the K CSIs for the K groups, wherein the above at least one partial CSI includes a CSI for at least one transmitting antenna port included in one of the K groups.

15. A storage medium storing at least one instruction readable by a computer, wherein the at least one instruction causes the electronic device to perform at least one operation when executed by at least a part of at least one processor (120) of the electronic device, and The above at least one operation is: An operation of grouping multiple transmitting antenna ports into K groups—wherein K is a natural number greater than or equal to 2—; The operation of transmitting K CSI-RS (channel state information - reference signals) for each of the above K groups to a terminal; The operation of receiving at least one partial CSI (channel state information) for the K CSI-RSs from the terminal; and A storage medium characterized by including the operation of determining a codebook for precoding a transmission signal using an artificial intelligence (AI) model based on at least one partial CSI.

Images