Method and apparatus for transmitting or receiving information for channel state information feedback based on artificial intelligence in wireless communication system

Abstract

A method by which a user equipment (UE) including an encoder transmits or receives information for artificial intelligence (AI)-based channel state information (CSI) feedback in a wireless communication system. The method may include receiving a CSI report configuration message from a base station (BS); and generating compressed CSI feedback data by the encoder based on the CSI report configuration information, and generating auxiliary information related to the compressed CSI feedback data, and transmitting the compressed CSI feedback data and the auxiliary information to the BS.

Description

Technical Field

[0001] The present disclosure relates to a wireless communication system, and more particularly, to a method and apparatus for transmitting or receiving auxiliary information for artificial intelligence (AI)-based channel state information (CSI) feedback in a multiple-input multiple-output (MIMO) system. Background Art

[0002] Looking back at the successive generations in the development of radio communications, the following technologies have been developed for services targeting humans: such as voice, multimedia, data, etc. The explosively increasing number of connected devices after the commercialization of the fifth generation (5G) communication system is expected to be connected to the communication network. As examples of things connected to the network, there can be cars, robots, dashboards, home appliances, displays, smart sensors installed in various infrastructures, construction machinery, factory equipment, etc. It is expected that mobile devices will develop into various form factors: such as augmented reality (AR) glasses, virtual reality (VR) headsets, holographic devices, etc. In order to provide various services by connecting hundreds of devices and things in the sixth generation (6G) era, efforts are being made to develop better 6G communication systems. For these reasons, 6G communication systems are called super-5G systems.

[0003] In the 6G communication system that is expected to become a reality around 2030, the maximum transmission rate is tera bits per second (bps), that is, 1000 gigabits per second, and the maximum wireless delay is 100 microseconds (μsec). In other words, compared with the 5G communication system, in the 6G communication system, the transmission rate becomes 50 times faster and the wireless delay is reduced to one tenth (1 / 10).

[0004] In order to obtain these high data transmission rates and ultra-low latency, 6G communication systems are considered to be implemented in the terahertz (THz) band (e.g., ranging from 95 gigahertz (GHz) to 3THz). Due to the more serious path loss and atmospheric absorption phenomena in the THz band compared to the millimeter wave (mmWave) band introduced in the 5G system, the importance of technologies for ensuring signal range (i.e., coverage) is expected to grow. As the main technologies for ensuring coverage, the following technologies need to be developed: radio frequency (RF) elements, antennas, new waveforms that are superior to orthogonal frequency division multiplexing (OFDM) in terms of coverage, beamforming and massive multiple input multiple output (massive MIMO), full-dimensional MIMO (FFD-MIMO), array antennas, multi-antenna transmission technologies such as massive antennas, etc. In addition, new technologies for increasing the coverage of terahertz (THz) band signals are also discussed, such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing technologies using orbital angular momentum (OAM), reconfigurable smart surfaces (RIS), etc.

[0005] In addition, in order to enhance frequency efficiency and system network, the following technologies are being developed in 6G communication systems: full-duplex technology that uses the same frequency resources for both uplink and downlink transmissions, network technology that uses satellites and high altitude platform stations (HAPS) etc. in combination, network structure innovation technology that supports mobile base stations and allows optimization and automation of network operations, dynamic spectrum sharing technology that avoids collisions based on spectrum usage prediction, AI-based communication technology that achieves system optimization by using artificial intelligence (AI) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology that achieves services with complexity that exceeds the computing power limit of terminals by using ultra-high performance communication and computing resources (e.g., mobile edge computing (MEC) cloud). In addition, by designing new protocols used in 6G communication systems, developing mechanisms for realizing hardware-based security environments and secure use of data, and developing technologies for protecting privacy, attempts are being made to strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase openness of wireless communications.

[0006] With such research and development of 6G communication systems, it is expected that through the ultra-connectivity of the 6G communication system (including not only connections between things but also connections between people and things), a new level of the next ultra-connected experience will become possible. Specifically, it can be predicted that services such as truly immersive extended reality (truly immersive XR), high-fidelity mobile holograms, digital replicas, etc. can be provided. In addition, services with enhanced security and reliability such as remote surgery, industrial automation, and emergency response can be provided through the 6G communication system for application in various fields such as industry, medical care, vehicles, appliances, etc. Summary of the invention

[0007] [Technical solution]

[0008] Embodiments of the present disclosure provide a technique for a user equipment (UE) to reduce the overhead of channel state information (CSI) feedback by sending auxiliary information to a base station (BS), and for the BS to increase accuracy when reconstructing compressed CSI data.

[0009] The technical purpose of the present disclosure is not limited thereto, and other technical purposes can be inferred from the following embodiments of the present disclosure.

[0010] Additional aspects will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the presented embodiments of the disclosure.

[0011] According to one aspect of the present disclosure, a method for a UE including an encoder in a wireless communication system to send or receive information for artificial intelligence (AI)-based CSI feedback includes: receiving CSI report configuration information from a base station (BS); generating compressed CSI feedback data through an encoder based on the CSI report configuration information, and generating auxiliary information related to the compressed CSI feedback data; and, sending the compressed CSI feedback data and the auxiliary information to the BS.

[0012] According to one aspect of the present disclosure, a UE for sending or receiving information for AI-based CSI feedback in a wireless communication system includes an encoder, a transceiver, and at least one processor. The at least one processor can be configured to receive CSI report configuration information from a BS through the transceiver, generate compressed CSI feedback data from the encoder based on the CSI report configuration information, generate auxiliary information related to the compressed CSI feedback data, and send the compressed CSI feedback data and the auxiliary information to the BS through the transceiver.

[0013] According to one aspect of the present disclosure, a method for sending or receiving information for AI-based CSI feedback by a BS including a decoder and a post-processor in a wireless communication system includes: sending CSI report configuration information to a UE; receiving compressed CSI feedback data and auxiliary information related to the compressed CSI feedback data determined based on the CSI report configuration information from the UE; reconstructing the compressed CSI feedback data through a decoder; and post-processing the reconstructed CSI feedback data through a post-processor based on the auxiliary information.

[0014] According to one aspect of the present disclosure, a BS for sending or receiving information for AI-based CSI feedback in a wireless communication system includes a decoder, a post-processor, a transceiver, and at least one processor. The at least one processor can be configured to send CSI report configuration information to a UE through a transceiver, receive compressed CSI feedback data and auxiliary information related to the compressed CSI feedback data determined based on the CSI report configuration information from the UE through the transceiver, reconstruct the compressed CSI feedback data through a decoder, and post-process the reconstructed CSI feedback data through a post-processor based on the auxiliary information.

[0015] According to an embodiment of the present disclosure, there is provided a computer-readable recording medium storing a program for executing a method in at least one embodiment of the present disclosure on a computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent from the following description in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A diagram for describing a communication network according to an embodiment of the present disclosure is illustrated;

[0018] Figure 2a A diagram for describing a data transmission path according to an embodiment of the present disclosure is illustrated;

[0019] Figure 2b A diagram for describing a data receiving path according to an embodiment of the present disclosure is illustrated;

[0020] Figure 3a A user equipment (UE) according to an embodiment of the present disclosure is illustrated;

[0021] Figure 3b A base station (BS) according to an embodiment of the present disclosure is illustrated;

[0022] Figure 4 A cross-polarized multiple-input multiple-output (MIMO) antenna system according to an embodiment of the present disclosure is illustrated;

[0023] Figure 5 A diagram for describing channel state information (CSI) reference signal (RS) (CSI-RS) resource mapping in an orthogonal frequency division multiple access (OFDM) time-frequency grid according to an embodiment of the present disclosure is illustrated;

[0024] Figure 6 A diagram for describing a precoder configuration in type IICSI according to an embodiment of the present disclosure is illustrated;

[0025] Figure 7a A diagram for describing a subband-based reporting precoding matrix according to an embodiment of the present disclosure is illustrated;

[0026] Figure 7b A diagram for describing a precoding matrix configuration for enhanced type IICSI according to an embodiment of the present disclosure is illustrated;

[0027] Figure 8 A diagram for describing CSI feedback based on an autoencoder (AE) according to an embodiment of the present disclosure is illustrated;

[0028] Fig. 9 A diagram for describing the operation of a pre-processor for transforming an estimated channel into a stacked eigenvector in AE-based CSI feedback according to an embodiment of the present disclosure is illustrated;

[0029] Fig.10 A diagram for describing an operation of a UE that transmits compressed CSI and auxiliary information to a BS according to an embodiment of the present disclosure is illustrated;

[0030] Fig.11 A diagram for describing a preprocessing operation according to an embodiment of the present disclosure is illustrated;

[0031] Fig.12 A diagram for describing an operation of a UE that transmits assistance information including quantization information to a BS according to an embodiment of the present disclosure is illustrated;

[0032] Fig.13 A diagram for describing signaling between a UE and a BS for AE-based CSI feedback according to an embodiment of the present disclosure is illustrated;

[0033] Fig.14a , 14b and 14c illustrate a diagram for describing an operation of a UE transmitting auxiliary information to a BS in AE-based CSI feedback according to an embodiment of the present disclosure;

[0034] Fig.15 A schematic block diagram of a BS according to an embodiment of the present disclosure is illustrated; and

[0035] Fig.16 A schematic block diagram of a UE according to an embodiment of the present disclosure is illustrated. DETAILED DESCRIPTION

[0036] Before proceeding to the following detailed description, it may be helpful to set forth definitions of certain words and phrases used throughout this patent document: the terms "include" and "comprising" and their derivatives are meant to include without limitation; the term "or" is inclusive, meaning and / or; the phrases "associated with" and "associated with" and their derivatives may mean to include, be included, interconnected with, contain, be contained within, connect to or be connected with, be connected to or be connected with, be communicative with, cooperate with, interleave, juxtapose, be adjacent to, be bound to or be bound with, have, have the property of, etc.; and the term "controller" means any device, system, or portion thereof that controls at least one operation, such device may be implemented in hardware, firmware, or software, or a combination of at least two thereof. It should be noted that the functionality associated with any particular controller may be centralized or distributed, whether locally or remotely.

[0037] In addition, the various functions described below can be implemented or supported by one or more computer programs, each of which is formed by a computer-readable program code and embodied in a computer-readable medium. The terms "application" and "program" refer to one or more computer programs, software components, instruction sets, processes, functions, objects, classes, instances, related data, or parts thereof suitable for implementation in appropriate computer-readable program codes. The phrase "computer-readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer-readable medium" includes any type of medium that can be accessed by a computer, such as a read-only memory (ROM), a random access memory (RAM), a hard drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. "Non-transient" computer-readable media excludes wired, wireless, optical or other communication links that transmit transient electrical or other signals. A non-transient computer-readable medium includes a medium that can permanently store data, and a medium that can store data and then rewrite data, such as a rewritable optical disc or an erasable storage device.

[0038] Definitions for certain words and phrases are provided throughout this patent document, those of ordinary skill in the art should understand that in many, if not most instances, such definitions apply to prior, as well as future uses of such defined words and phrases.

[0039] Discussed below Figures 1 to 16 The various embodiments used to describe the principles of the present disclosure in this patent document are merely exemplary and should not be interpreted in any way as limiting the scope of the present disclosure. Those skilled in the art will appreciate that the principles of the present disclosure can be implemented in any appropriately arranged system or device.

[0040] Embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0041] The description of technical contents that are well known in the art or not directly related to the present disclosure will be omitted herein. By omitting contents that may make the subject matter of the present disclosure unclear, the subject matter will be more clearly understood. In addition, as will be mentioned later, the terms are defined by considering the functions in the present disclosure, but may vary according to the practice or intention of the user or operator. Therefore, the terms should be defined based on the description in the entire specification.

[0042] For the same reason, some parts in the drawings are exaggerated, omitted or schematically shown. The sizes of the corresponding elements may not fully reflect their actual sizes. In the entire drawings, the same reference numerals represent the same elements.

[0043] When reading the following embodiments with reference to the accompanying drawings, the advantages and features of the present disclosure and the methods for realizing them will be more clearly understood. However, the embodiments of the present disclosure can be embodied in many different forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments of the present disclosure are provided so that the present disclosure will be thorough and complete, and the scope of the embodiments of the present disclosure will be fully conveyed to those of ordinary skill in the art. Throughout the specification, the same reference numerals represent the same elements. In the description of the present disclosure, when it is determined that the detailed description of the relevant functions or configurations may unnecessarily obscure the subject matter of the present disclosure, the detailed description will be omitted. In addition, as will be mentioned later, the terms are defined by considering the functions in the present disclosure, but may vary according to the practice or intention of the user or operator. Therefore, the terms should be defined based on the descriptions in the entire specification.

[0044] Throughout the disclosure, the expression "at least one of a, b, or c" means only a, only b, only c, both a and b, both a and c, both b and c, all of a, b, and c, or variations thereof.

[0045] Throughout the specification, a layer may also be referred to as an entity.

[0046] A base station (BS) as used herein may refer to an entity for performing resource allocation for a user equipment (UE), and may be at least one of a gNode B, an eNode B, a Node B (or an xNode B, where x represents any letter including 'g' and 'e'), a radio access unit, a BS controller, a satellite, an airborne vehicle, or a node in a network. A UE may include a mobile station (MS), a vehicle, a satellite, an aircraft, a cellular phone, a smart phone, a computer, or a multimedia system with a communication function. In the present disclosure, a downlink (DL) may refer to a radio transmission path for a signal sent from a BS to a UE, and an uplink (UL) may refer to a radio transmission path for a signal sent from a UE to a BS. In addition, there may be a side link (SL), which refers to a radio transmission path for a signal sent from a UE to another UE.

[0047] Although the following embodiments of the present disclosure will focus on long term evolution (LTE), LTE-Advanced (LTE-A) or fifth generation (5G) systems as examples, they can be applied to other communication systems with similar technical backgrounds or channel types. For example, other communication systems may include 5G-Advanced, New Radio (NR)-Advanced or sixth generation (6G) mobile communication technology developed after 5G mobile communication technology (or NR), and the term 5G may be a concept that includes existing LTE, LTE-A and other similar services. In addition, the embodiments of the present disclosure will also be applied to different communication systems with some modifications to the extent that they do not significantly deviate from the scope of the present disclosure when judged by those skilled in the art.

[0048] Wireless communication is one of the most successful innovations in recent history. The number of wireless communication service subscribers exceeds 5 billion today and continues to grow rapidly. As various mobile data devices (e.g., smart phones, tablet computers, notepad computers, online books, e-book readers, etc.) become popular in the consumer and business world, the demand for mobile data services has risen sharply. In order to meet the high growth of mobile data services and support the distribution of new applications, it is important to enhance the coverage and efficiency of the radio interface.

[0049] Since the distribution of fourth generation (4G) communication systems, 5G communication systems have been developed and distributed to meet the growing demand for wireless data services and enable various vertical applications.

[0050] The 5G communication system has a 28 GHz or 60 GHz frequency band or a high frequency band above 6 GHz (e.g., a millimeter wave (mmwave) band) to obtain a high data rate, or is implemented in a low frequency band below 6 GHz to enable stable coverage and mobility support. The embodiments of the present disclosure can be applied to 5G communication systems, 6G, or further, to future versions using terahertz (THz) frequencies. In order to reduce the propagation loss of radio waves and increase the transmission range, beamforming, massive MIMO, full-dimensional (FD) MIMO, array antennas, analog beamforming, and massive antenna technology will be discussed in a wireless communication system according to an embodiment of the present disclosure.

[0051] In the 5G communication system, small cells, cloud radio access networks (RAN), ultra-dense networks, device-to-device (D2D) communications, wireless backhaul, mobile networks, cooperative communications, coordinated multi-point (CoMP), interference cancellation at the receiving end, etc. are being developed for network enhancement of the system. In addition, in the 5G communication system, advanced coding modulation (ACM) (such as hybrid frequency shift keying (FSK) and Fernandezha quadrature amplitude modulation (FQAM)) and sliding window superposition coding (SWSC) are being developed, as well as advanced access technologies (such as filter bank multi-carrier (FBMC), non-orthogonal multiple access (NOMA) and sparse code multiple access (SCMA)).

[0052] The Internet is a connectivity network for humans, where humans generate and consume information, and is developing into the Internet of Things (IoT), where distributed entities or things exchange information between them and process the information. The Internet of Everything (IoE) has emerged, which combines IoT technology and big data processing technology through connection with cloud servers. Since the realization of IoT requires technical elements such as sensing technology, wired / wireless communication and network infrastructure, service interface technology and security technology, sensor networks, machine-to-machine (M2M) communication, machine type communication (MTC), etc. are being studied. The IoT environment can provide intelligent Internet technology (IT) services that create new value for human life by collecting and analyzing data generated from connected things. IT can be applied to various fields such as smart homes, smart buildings, smart cities, smart cars or connected cars, smart grids, health care, smart home appliances, and advanced medical services through the integration and combination between existing information technology (IT) and various industrial applications.

[0053] 5G communication systems can be applied to IoT networks. For example, technologies such as sensor networks, MTC, and M2M communications can be implemented through beamforming, MIMO, and array antennas. Applying cloud radio access networks (RAN) as big data processing technology can be an example of the convergence between 5G technology and IOT technology.

[0054] It is understood that the corresponding blocks and combinations of blocks in the process flow chart will be performed by computer program instructions in the embodiments of the present disclosure. Computer program instructions can be loaded onto a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, and therefore they generate a device for performing the functions described in the blocks of the flow chart when executed by the processor of the computer or other programmable data processing device. Computer program instructions can also be stored in a computer-available or computer-readable memory for a computer or other programmable data processing device, so that a product containing an instruction device for performing the functions described in the box of the flow chart can be manufactured. Computer program instructions can also be loaded onto a computer or a programmable data processing device, so instructions can generate a process performed by a computer or other programmable data processing device to provide steps for performing the functions described in the box of the flow chart.

[0055] In addition, each block can represent a module, segment or a part of code including one or more executable instructions for performing (one or more) specific logic functions. It should be noted that in some alternative implementations, the functions described in the block can occur out of order. For example, two continuous blocks can be performed substantially simultaneously, or in reverse order according to the corresponding functions. For example, the series of operations shown can be various operations included in different figures, which can overlap each other, occur in parallel, occur in different orders, or occur several times. In addition, in some examples, operations can be omitted or replaced by other operations.

[0056] The term "module" (or sometimes "unit") used herein refers to a software or hardware component that performs some functions, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). However, modules are not limited to software or hardware. A module can be configured to be stored in an addressable storage medium, or to execute one or more processors. For example, a module can include components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcodes, circuits, data, databases, data structures, tables, arrays, and variables. The functions served by components and modules can be combined into a smaller number of components and modules, or further divided into a larger number of components and modules. In addition, components and modules can be implemented as one or more central processing units (CPUs) in an execution device or a secure multimedia card. In an embodiment of the present disclosure, a module can include one or more processors.

[0057] In the following description, for the sake of convenience of explanation, terms related to broadcast information, control information, state changes (e.g., events), network entities, messages, and components of devices, terms related to communication coverage, etc. are mentioned. The present disclosure is not limited to the terms to be used in the following description, and different terms having the same meaning in a technical sense may be used.

[0058] In the following description, for ease of explanation, the terms and definitions used in the latest standards in the current existing communication standards (i.e., LTE and NR standards defined in the 3rd Generation Partnership Project (3GPP)) will be used in the present disclosure. However, the present disclosure is not limited to the terms and definitions and can be equally applied to any system conforming to other standards.

[0059] In an embodiment of the present disclosure, a method and apparatus for sending or receiving information for artificial intelligence (AI)-based (or autoencoder (AE)-based) channel state information (CSI) feedback may be provided in a wireless communication system (or communication network).

[0060] Figure 1 A diagram for describing a communication network 100 according to an embodiment of the present disclosure is illustrated.

[0061] Figure 1 The communication network 100 shown is only an example and is not limited to Figure 1 Various embodiments of the communication network 100 may be applied to the embodiments of the present disclosure.

[0062] The wireless communication system or the communication network 100 according to an embodiment of the present disclosure may include at least one of a 5G independent network, a 5G non-independent (NS) network, or a 6G network.

[0063] refer to Figure 1 , the communication network 100 may include a first BS, such as a gNB (or gNodeB), a second BS, and a third BS 103. The first BS 101 may communicate with the second BS 102 and the third BS 103. The first BS 101 may also communicate with at least one Internet Protocol (IP) network 130 (e.g., the Internet, a private IP network, or another data network).

[0064] In an embodiment of the present disclosure, based on the type of the communication network 100, a BS or gNB may refer to various components (or a collection of components) configured to provide a remote UE with radio access to the IP network 130, such as a base transceiver station, a wireless BS, a transmission point (TP), a transmission-reception point (TRP), a ground gateway, an airborne gNB, a satellite system, a mobile BS, a macro cell, a femto cell, a wireless fidelity (Wi-Fi) access point (AP), etc. In addition, based on the type of the communication network 100, various terms such as a mobile station, a subscriber station, a remote UE, a wireless UE, or a user device may be used to replace the term UE or user equipment. In the present disclosure, for ease of explanation, a device that wirelessly accesses a BS (or gNB) is now represented as a user device or UE. A UE may be a mobile device or a fixed device. For example, a UE may be a cellular phone, a smart phone, a monitoring device, an alarm device, a vehicle management device, an asset tracking device, a vehicle, a desktop computer, an entertainment device, an infotainment device, a vending machine, an electric meter, a water meter, a gas meter, a security device, a sensor device, a home appliance, etc.

[0065] Reference Figure 1 , the second BS 102 can provide wireless broadband access to the IP network 130 for multiple first UEs in the coverage area 120 of the second BS 102. The multiple first UEs may include a UE 111 that may be located in a small enterprise SB, a UE 112 that may be located in an enterprise E, a UE 113 that may be located in a Wi-Fi hotspot HS, a UE 114 that may be located in a first residence R, a UE 115 that may be located in a second residence R, and a mobile device M, such as a UE 116, which may be a cellular phone, a wireless laptop computer, a wireless personal digital assistant (PDA), etc. The third BS 103 can provide wireless broadband access to the IP network 130 for multiple second UEs in the coverage area 125 of the third BS 103. The multiple second UEs may include UE 115 and UE 116. In some embodiments of the present disclosure, one or more BSs 101, BS 102, and BS 103 may communicate with each other and with at least one UE 111 to UE 116 using 5G, LTE, LTE-A, WiMAX, or other wireless communication technologies.

[0066] Reference Figure 1 , dotted lines represent approximate ranges of coverage area 120 and coverage area 125, which are shown as circles for illustration and explanation. In an embodiment of the present disclosure, the coverage areas of BSs, such as coverage area 120 of second BS 102 and coverage area 125 of third BS 103, may have various forms, including irregular forms, depending on the configuration of each BS and changes in the wireless environment associated with natural or artificial obstacles.

[0067] As will be combined later Figure 4 As described, at least one of the first BS 101, the second BS 102, or the third BS 103 may include a two-dimensional (2D) antenna array. In an embodiment of the present disclosure, at least one of the first BS 101, the second BS 102, or the third BS 103 may support codebook design and structure for a system with a 2D antenna array.

[0068] Figure 1 An example of a communication network 100 is illustrated and may be used to Figure 1 Various modifications may be made. For example, the communication network 100 may include any number of gNBs and any number of UEs in various layouts. In addition, the first BS 101 may communicate directly with any number of UEs and provide the UEs with wireless broadband access to the IP network 130. Similarly, the second BS 102 and the third BS 103 may also communicate directly with the IP network 130 and provide the connected UEs with wireless broadband access to the IP network 130. In an embodiment of the present disclosure, the first BS 101, the second BS 102, and the third BS 103 may also provide access to additional external networks or different types of data networks.

[0069] Figure 2a A diagram for describing a data transmission path 200 according to an embodiment of the present disclosure is illustrated, and Figure 2b is a diagram for describing a data receiving path 250 according to an embodiment of the present disclosure.

[0070] In an embodiment of the present disclosure, the data transmission path 200 may be in a BS (eg, Figure 1 The data receiving path 250 may be implemented in a UE (eg, a second BS 102). Figure 1 In an embodiment, alternatively, the data receiving path 250 may be implemented in the BS and the data transmitting path 200 may be implemented in the UE. In an embodiment of the present disclosure, the data receiving path 250 may be configured to support a codebook design and structure for a system including a 2D antenna array as described above.

[0071] Reference Figure 2a , the data transmission path 200 may include a channel coding and modulation block 205, a serial to parallel (S-to-P) block 210, a size N inverse fast Fourier transform (IFFT) block 215, a parallel to serial (P-to-S) block 220, an add cyclic prefix block 225 and an up converter (UC) 230.

[0072] Reference Figure 2b, the data receive path 250 may include a down converter (DC) 255, a cyclic prefix removal block 260, a serial to parallel (S-to-P) block 265, a size N fast Fourier transform (FFT) block 270, a parallel to serial (P-to-S) block 275, and a channel decoding and demodulation block 280.

[0073] In the data transmission path 200, the channel coding and modulation block 205 can receive a set of information bits, apply coding (e.g., low-density parity check (LDPC) coding) and modulate (e.g., quadrature phase shift keying (QPSK) or quadrature amplitude modulation (QAM)) the input bits to produce a frequency domain modulation symbol sequence. The serial to parallel block 210 can convert (e.g., demultiplex) the serial modulated symbols into parallel data to produce N parallel symbol streams. N can be a number determined by the BS (e.g., Figure 1 The second BS 102) and the UE (eg, Figure 1 The size of the IFFT or FFT used by the UE 116 of the present invention. The size N IFFT block 215 can then perform an IFFT operation on the N parallel symbol streams to produce a time domain output signal. The parallel to serial block 220 can convert (e.g., multiplex) the serial time domain output symbols from the size N IFFT block 215 to produce a serial time domain signal. The add cyclic prefix block 225 can insert a cyclic prefix into the time domain signal. The UC 230 can convert the output of the add cyclic prefix block 225 to a radio frequency (RF) frequency (e.g., up-conversion) for data transmission in a radio channel. In an embodiment of the present disclosure, the signal can be filtered in the baseband before being converted to RF frequency.

[0074] In an embodiment of the present disclosure, when an RF signal transmitted from a BS reaches a UE through a radio channel, the UE may perform operations performed by the BS in a reverse order. Figure 2b , DC 255 can down-convert the received signal to baseband frequency, and remove cyclic prefix block 260 can remove the cyclic prefix to produce a serial time domain baseband signal. Serial to parallel block 265 can convert the time domain baseband signal into a parallel time domain signal. Size N FFT block 270 can perform an FFT algorithm to produce N parallel frequency domain signals. Parallel to serial block 275 can convert the parallel frequency domain signals into a modulated sequence of data symbols. Channel decoding and demodulation block 280 can demodulate and decode the modulated symbols to recover the original input data stream.

[0075] The BS may implement a data transmission path 200 to the UE in a DL scenario and a data reception path 250 from the UE in a UL scenario. In a similar manner, the UE may implement a data transmission path 200 to the BS in a UL scenario and a data reception path 250 from the BS in a DL scenario.

[0076] Figure 2a The corresponding blocks shown in or 2b can be implemented in hardware or a combination of hardware and software or firmware. In the embodiments of the present disclosure, Figure 2a At least some of the blocks in 2b may be implemented in software, while other blocks may be implemented in hardware or a combination of hardware and software. Figure 2b The FFT block 270 and Figure 2a The IFFT block 215 may be implemented using a software algorithm, where the value of the size N may be determined according to the embodiments of the present disclosure.

[0077] Although the reference Figure 2a and Figure 2b An embodiment using FFT and IFFT is described, but it is merely an illustrative example and should not be construed as limiting the scope of the present disclosure. In embodiments of the present disclosure, various types of transforms, such as discrete Fourier transform (DFT) and inverse discrete Fourier transform (IDFT) functions, may be used. For example, the variable N may have integer values ​​(e.g., 1, 2, 3, 4, ...) for DFT and IDFT functions, and may have power-of-two values ​​(e.g., 1, 2, 4, 8, 16, ...) for FFT and IFFT functions.

[0078] although Figure 2a and Figure 2b The wireless data transmission path 200 and the data reception path 250 are shown in the figure, but in the embodiment, the wireless data transmission path 200 and the data reception path 250 may be Figure 2a and Figure 2b Make various modifications. For example, Figure 2a and Figure 2b The various components of may be combined, subdivided, or omitted, and additional components may be added upon specific request. Figure 2a and Figure 2b Illustrative types for describing data transmission paths and data reception paths to be used in a wireless communication network. Various suitable configurations for supporting wireless communications in a wireless network according to embodiments of the present disclosure may be used.

[0079] Figure 3a A UE 116 according to an embodiment of the present disclosure is illustrated.

[0080] Figure 3a UE 116 may also be referred to as a terminal or user equipment. UE 116 may correspond to Figure 1 At least one of UE 111 to UE 116. The UE according to an embodiment of the present disclosure may be provided in various configurations and is not limited to the following. Figure 3a UE 116 is shown.

[0081] Reference Figure 3a , UE 116 may include at least one antenna 305, an RF transceiver 310, a transmit (TX) processing circuit 315, a microphone 320, and a receive (RX) processing circuit 325. UE 116 may also include a speaker 330, a controller or processor 340, an input / output (I / O) interface (IF) 345, an input device 350 such as a keypad, a display 355, and a memory 360. The memory 360 may store a basic operating system (OS) program 361 and at least one application 362.

[0082] RF transceiver 310 may receive an input RF signal transmitted by a BS of a communication network from antenna 305. RF transceiver 310 may down-convert the input RF signal to produce an intermediate frequency (IF) or baseband signal. The IF or baseband signal may be sent to RX processing circuitry 325, which in turn may generate a processed baseband signal by filtering, decoding, or digitizing the baseband or IF signal. RX processing circuitry 325 may send the processed baseband signal to speaker 330 (for voice data) or processor 340 for additional processing (regarding web browsing data).

[0083] The TX processing circuit 315 may receive analog or digital voice data from the microphone 320 or other outgoing baseband data (e.g., web data, email, or interactive video game data) from the processor 340. The TX processing circuit 315 may encode, multiplex, or digitize the outgoing baseband data to produce a processed baseband or IF signal. The RF transceiver 310 may receive the outgoing processed baseband or IF signal from the TX processing circuit 315 and up-convert the baseband or IF signal to an RF signal for transmission via the antenna 305.

[0084] The processor 340 may include at least one processor or processing device and executes the OS program 361 stored in the memory 360 to control the overall operation of the UE 116. For example, the processor 340 may control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceiver 310, the RX processing circuit 325, and the TX processing circuit 315. In an embodiment of the present disclosure, the processor 340 may include at least one microprocessor or microcontroller.

[0085] The processor 340 may execute a program stored in the memory 360 or another processor included in the memory 360 for operations such as channel quality measurement and reporting on a system with a 2D antenna array. The processor 340 may move data into or out of the memory 360. In an embodiment of the present disclosure, the processor 340 may run an application 362 based on an OS program 361 or in response to a signal received from a BS. The processor 340 may be coupled to an I / O interface 345 that allows the UE 116 to access another device such as a laptop computer, a portable computer, etc. The I / O interface 345 may be a communication path between various accessories and the processor 340.

[0086] The processor 340 may be coupled to an input device 350 or a display 355. The UE 116 may receive data through various input devices 350. The display 355 may include various types of display devices, such as a liquid crystal display (LCD) capable of rendering text or graphics from a website. The memory 360 may be coupled to the processor 340. The memory 360 may include at least one of a random access memory (RAM), a flash memory, or a read-only memory (ROM).

[0087] like Figure 3a The UE 116 shown is only an example, and the UE 116 may be Figure 3a Various modifications of the illustrated configurations. For example, the Figure 3a The various components shown are shown, and additional components may be added upon specific request. For example, the processor 340 included in the UE 116 may include multiple processors, such as at least one central processing unit (CPU), at least one graphics processing unit (GPU), etc. Figure 3a The illustrated UE 116 may be implemented as a mobile phone or a smart phone, but it is not limited thereto and may be implemented as various types of mobile or stationary devices.

[0088] Figure 3b A BS 102 according to an embodiment of the present disclosure is illustrated.

[0089] Figure 3b The BS 102 may also be referred to as a gNB. The BS 102 may correspond to Figure 1 At least one of the first BS 101, the second BS 102 or the third BS 103. The UE according to the embodiment of the present disclosure may be provided in various configurations and is not limited to the following. Figure 3b BS102 shown.

[0090] Reference Figure 3b, BS102 may include at least one antenna 370a, 370b, ... 370n, at least one RF transceiver 372a, 372b, ... 372n, TX processing circuit 374, and RX processing circuit 376. In an embodiment of the present disclosure, at least one antenna 370a, 370b, ... 370n may include a 2D antenna array. BS102 may also include a controller or processor 378, a memory 380, and a backhaul or network interface 382.

[0091] At least one RF transceiver 372a, 372b, ... 372n can receive an input RF signal, such as a signal transmitted by a UE or another BS, from at least one antenna 370a, 370b, ... 370n. The RF transceiver 372a, 372b, ..., or 372n can down-convert the input RF signal to produce an IF or baseband signal. The IF or baseband signal can be sent to the RX processing circuit 376, which can generate a processed baseband signal by filtering, decoding or digitizing the baseband or IF signal. The RX processing circuit 376 can send the processed baseband signal to the processor 378 for further processing.

[0092] The TX processing circuit 374 may receive analog or digital data (e.g., voice data, web data, email, or interactive video game data) from the processor 378. The TX processing circuit 374 may encode, multiplex, and / or digitize the outgoing baseband data to produce a processed baseband or IF signal. The RF transceiver 372a, 372b, ..., or 372n may receive the outgoing processed baseband or IF signal from the TX processing circuit 374 and up-convert the baseband or IF signal to an RF signal that is transmitted via the antenna 370a, 370b, ..., or 370n.

[0093] The processor 378 may include at least one processor or processing device for controlling the general operation of the BS 102. For example, the processor 378 may control the reception of the forward channel signal and the transmission of the reverse channel signal through the RF transceiver 372a, 372b, ..., or 372n, the RX processing circuit 376 and the TX processing circuit 374. In an embodiment of the present disclosure, the processor 378 may support additional functions, such as advanced wireless communication functions. For example, the processor 378 may perform a BIS process by using a blind interference sensing (BIS) algorithm, and decode the received signal offset by an interference signal. The processor 378 in the BS 102 may support various other functions. In an embodiment, the processor 378 may include at least one microprocessor or microcontroller.

[0094] The processor 378 may also execute programs stored in the memory 380, such as an OS or other operations. The processor 378 may support operations such as channel quality measurement and reporting on a system with a 2D antenna array. In an embodiment of the present disclosure, the processor 378 may support communications between network entities, such as web real-time communications. The processor 378 may move data into or out of the memory 380.

[0095] Processor 378 may be connected to a backhaul or network interface 382. Backhaul or network interface 382 may allow BS 102 to communicate with other devices via a backhaul connection or via a network. Backhaul or network interface 382 may support communication via various types of wired or wireless connections. For example, when BS 102 is implemented as part of a wireless communication system (e.g., 5G, LTE, or LTE-A), backhaul or network interface 382 may allow BS 102 to communicate with another BS via a wired or wireless backhaul connection. When BS 102 is implemented as an access point (AP), backhaul or network interface 382 may allow BS 102 to perform communication via a wired or wireless local area network (LAN) or via a wired or wireless connection to a larger network (e.g., the Internet). Backhaul or network interface 382 may include various configurations that support communication via a wired or wireless connection (e.g., Ethernet or RF transceiver).

[0096] The memory 380 may be coupled to the processor 378. The memory 380 may include at least one of a RAM, a flash memory, or a ROM. In an embodiment of the present disclosure, instructions such as a BIS algorithm may be stored in the memory 380. The instructions stored in the memory 380 may be configured for the processor 378 to perform BIS processing and decode the received signal after offsetting at least one interference signal determined by the BIS algorithm.

[0097] As will be described in detail, the data transmission path and the data reception path of BS102 can support communication with the aggregation of frequency division duplex (FDD) cells and time division duplex (TDD) cells. The data transmission path and the data reception path of BS102 can be implemented by RF transceivers 372a, 372b, ..., or 372n, TX processing circuit 374 and RX processing circuit 376.

[0098] like Figure 3b The BS 102 shown is only an example, and the BS 102 may be Figure 3b Various modifications of the illustrated configurations. For example, the Figure 3bThe various components of the BS 102 may include a plurality of backhaul or network interfaces 382, ​​and the processor 378 may support routing functions for routing data between different network addresses. Figure 3b , each of the TX processing circuit 374 and the RX processing circuit 376 is shown as configured as a single instance, but BS 102 may include TX processing circuits 374 and RX processing circuits 376, each of which is provided as multiple instances (e.g., one TX processing circuit 374 and one RX processing circuit 376 for each RF transceiver).

[0099] Figure 4 A cross-polarized MIMO antenna system according to an embodiment of the present disclosure is illustrated.

[0100] In a MIMO antenna system, a BS or a UE may each include multiple antennas. Due to the advantages of spatial multiplexing, diversity gain, and array gain, a wireless communication system may adopt a MIMO antenna system.

[0101] Reference Figure 4 , a MIMO antenna system may include, for example, 48 antenna elements. Figure 4 , four cross-polarized antenna elements 401 may form a 4×1 subarray 402. Twelve subarrays 402 may form a 2V3H MIMO antenna configuration consisting of two subarrays 402 in the vertical dimension and three subarrays 402 in the horizontal dimension. Figure 4 An example of a MIMO antenna configuration is illustrated, and various configurations may be applied to the antenna configuration according to the embodiment of the present disclosure.

[0102] In a MIMO antenna system, when the BS requests channel state information (CSI), the UE can receive signals from the BS with the maximum possible received power and the minimum possible interference. The BS can obtain CSI by measuring the UL reference signal (RS) in the BS or by measuring and feeding back the DL RS by the UE for the corresponding TDD system and FDD system. For example, in the FDD system of the 5G network, the CSI-RS can be the main RS used by the UE in the operation of measuring and reporting CSI.

[0103] Figure 5 A diagram for describing CSI-RS resource mapping in an Orthogonal Frequency Division Multiple Access (OFDM) time-frequency grid according to an embodiment of the present disclosure is illustrated.

[0104] In an embodiment, the UE may receive signaling of the configuration of the CSI-RS that may be used in the CSI measurement from the BS. Figure 5 An implementation of CSI-RS configuration is shown in FIG.

[0105] Reference Figure 5 , 12 antenna ports (CSI-RS ports) can be mapped to CSI-RS with three code domain multiplexing (CDM) groups. CDM groups (CDM group 0, CDM group 1, and CDM group 2) can each be mapped to 4 resource elements (REs) in the OFDM time-frequency grid. Antenna ports mapped to the same CDM group can be orthogonalized in the code domain by using orthogonal cover codes.

[0106] Reference Figure 5 By mapping a CSI-RS port to one of the cross-polarized antenna elements in a subarray, the CSI-RS configuration can be combined with Figure 4 In the 5G NR standard, there can be three types of time domain CSI-RS resource configurations, namely periodic, semi-persistent, and aperiodic configurations. Figure 5 , illustrating a configuration with a cycle of 4 time slots.

[0107] In an embodiment of the present disclosure, the BS may configure the UE through high-layer signaling by using information for CSI feedback, and the CSI feedback includes a spatial channel information indicator and other auxiliary information to help the BS obtain accurate CSI. The spatial channel indicator reported in the precoding matrix indicator (PMI) in the 4G or 5G standard may include a single or multiple channel matrices, channel covariance matrices, eigenvectors, or spatial sampling basis vectors. In particular, in the 4G or 5G standard, the spatial channel information may be given as a single or multiple DFT basis vectors.

[0108] Figure 6 A diagram for describing a precoder configuration in Type IICSI according to an embodiment of the present disclosure is illustrated.

[0109] exist Figure 6 , an example of CSI feedback based on multiple DFT basis vectors for type IICSI in a 5G network is illustrated. The spatial information of the channel can be obtained by using L=4 DFT basis vectors {b 0 ,b 1 ,b 2 ,b 3}602. In addition, amplitude information {p 1 ,p 2 ,p 3 ,p 4}603 and in-phase information Therefore, in type IICSI, the two-stage precoding matrix can be given as W = W 1 W 2 , where W 1is the matrix used to select the DFT basis vectors, W 2 is a matrix for allocating amplitude and in-phase information. In addition, the codebook may be represented by a superset of candidate amplitude and phase coefficients and candidate DFT basis vectors 601. In this case, the reported PMI may include an indicator that may indicate a codebook element of the estimated channel.

[0110] In an embodiment of the present disclosure, amplitude and phase information may be reported such that a linear combination of basis vectors determined according to the following equation 1 matches the eigenvector direction of the channel.

[0111] [Equation 1]

[0112]

[0113] For example, in the (s,u)th element h having the channel gain between the sth transmit antenna and the uth receive antenna s,u In the case of a channel matrix H, we can consider the covariance matrix H H The eigenvector of H. When e 1 When one of the eigenvectors is indicated, the UE may select the PMI to maximize the value of the following equation:

[0114]

[0115] Figure 7a A diagram for describing reporting of a precoding matrix in a subband 702 manner according to an embodiment of the present disclosure is illustrated.

[0116] In an embodiment of the present disclosure, the UE may be configured in various ways to report DFT basis vectors, amplitude coefficients, and phase coefficients according to a polarization-common or polarization-specific method. For example, with reference to the 5G NR standard, the DFT basis vectors may be reported in a polarization-common method, and the phase coefficients and amplitude coefficients may be reported in a polarization-specific method, i.e., for each polarization beam. A MIMO system may allow spatial multiplexing, i.e., data transmission in multiple transmission layers. In this sense, type IICSI in 5G NR may allow DFT basis vectors to be reported in a layer-common method, i.e., common to all layers, but phase and amplitude coefficients to be reported in a layer-specific method.

[0117] In order to handle the frequency selectivity of the wideband channel, in an embodiment of the present disclosure, various components of the precoding matrix (i.e., components of the PMI) may be reported for each frequency range. In an embodiment of the present disclosure, the frequency band for CSI reporting of the UE may be divided into a set of subbands 702, and an amplitude coefficient or a phase coefficient may be reported for each of the divided subbands 702. The DL bandwidth part (BWP) may be divided into large and small In this case, the selected DFT basis vectors 701 may be linearly combined with different weights, and the vector 703 generated by the linear combination may be arranged in the eigenvector of the channel in the corresponding subband 702. Assume that the set of subcarriers of the kth subband is F k , we can consider the average covariance matrix C k The eigenvector of . The average covariance matrix C k It can be expressed in the following equation 2:

[0118] [Equation 2]

[0119]

[0120] where f∈F k is the subcarrier of the kth subband, and H f,k is the corresponding channel matrix.

[0121] Reference Figure 7a , shows that for K pieces of size 703 of a frequency selective linear combination 703 of DFT basis vectors 701 of a subband 702.

[0122] Figure 7b A diagram for describing a precoding matrix configuration of enhanced type IICSI according to an embodiment of the present disclosure is illustrated.

[0123] In the 5G NR standard, another configuration called enhanced type IICSI (e-type IICSI) allows reporting the amplitude and phase coefficients in the delay domain instead of in the frequency domain for each subband. This configuration can reduce feedback overhead because the delay components are typically much smaller in number than the equivalent number of subbands. Figure 7b In an enhanced type II codebook (e-type IICB), the precoding matrix is ​​reported in the delay domain by applying frequency domain DFT, instead of reporting in the frequency domain through type IICSI (reporting for each subband or each wideband).

[0124] refer to Figure 7b , illustrates an exemplary configuration of type e IICSI. In particular, the precoding matrix can be as follows 706 is represented in three steps. The spatial domain selection matrix W 1 From P = 2N 1 N 2 Select L DFT vectors from each CSI-RS port and have 2L rows of cross-polarized antennas. v ×N 3 matrix Corresponding to M vDFT basis vectors, which can be used in the delay domain for M v The precoding matrix reported by the delayed components is transformed into N 3 frequency domain points (bins). In particular, the t∈{1, 2, ..., N}th vector of the fth vector 3 The} elements can be given by the following equation 3:

[0125] [Equation 3]

[0126]

[0127] Finally, the matrix W 2 Carrying amplitude and phase information, the i-th and j-th elements w i,j It carries the amplitude information 707 and phase information 708 of the i-th 2D DFT beam and the j-th delay component.

[0128] To further reduce CSI overhead, the system can use angular delay reciprocity and measure the dominant angle and delay components of the channel from a UL RS such as a sounding reference signal (SRS). In this case, precoded CSI-RS can be considered for DL ​​CSI measurement, and the CSI-RS ports can be mapped to the angular delay components of the channel. In addition, delay precompensation can be applied to the CSI ports, allowing the UE to measure CSI for a smaller number of delay components (i.e., for extreme cases such as a single delay component).

[0129] Figure 8 A diagram for describing CSI feedback based on AE 800 according to an embodiment of the present disclosure is illustrated.

[0130] In the wireless communication system according to the embodiment of the present disclosure, artificial intelligence (AI)-based CSI feedback or AE-based CSI feedback may be applied. Figure 8 , AE 800 may generate compressed CSI feedback through encoder 801 on the UE 803 side, and may reconstruct the CSI feedback through decoder 802 on the gNB 804 side. From the perspective of feedback overhead, CSI feedback based on AE 800 may find the best representation of CSI. In the CSI feedback operation based on AE 800, compressed CSI feedback is sent from UE 803 to BS 804, thereby reducing CSI feedback overhead.

[0131] The ultra-LTE communication system can utilize support for services that can freely reflect the various needs of users and service providers. Services considered for the ultra-5G communication system may include enhanced mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliability low latency communication (URLLC), etc. To meet various services, beam management or support for various frequency bands may be used. In this case, different channel conditions may exist for each frequency band or beam, and a large amount of resources may be consumed in the process of UE803 estimating and reporting the channel status to BS 804. Therefore, in order to reduce resource consumption in the CSI feedback process, CSI compression technology, that is, a method for compressing CSI and sending compressed CSI, can be used.

[0132] The CSI reconstructed by the codebook-based CSI feedback may cause information loss due to the quantization problem of the codebook in the process of transmitting the estimated channel H. For example, when the BS 804 sends an RS to the UE 803, the UE 803 can estimate the channel state (channel estimation) based on the received RS to obtain the channel H. and is obtained in methods such as eigenvalue decomposition (EVD) or singular value decomposition When the value of V is known from the obtained relationship, the channel Therefore, in the codebook-based CSI feedback, the UE 803 transmits the PMI, that is, the index of the codebook most similar to the V value, to the BS 804. In the case where the index of the codebook most similar to the V value is transmitted to the BS instead of the V value, there may be an error caused by the difference between the preset codebook and the actual value of V. In addition, when the codebook is more variously configured to reduce the information loss caused by the difference between the preset codebook and the actual value of V, the amount of data to be transmitted may increase accordingly.

[0133] In the case of CSI feedback based on the CSI compression technology in the embodiment of the present disclosure, the UE (transmitter) 803 can compress the CSI data (V data) through the encoder 801 and send the compressed CSI data, and the BS 804 can decode or reconstruct the received compressed CSI data (z data) through the decoder 802 to obtain the reconstructed CSI data ( data).

[0134] In an embodiment of the present disclosure, the AE 800 for CSI compression includes an encoder 801 on the UE 803 side and a decoder 802 on the BS 804 side. Each of the encoder 801 and the decoder 802 may include an AI model. For example, the encoder AI model included in the encoder 801 may be used to compress CSI data (V data) to generate compressed data (feedback data or z data). The decoder AI model included in the decoder 802 may be used to decode or reconstruct the compressed data received from the UE 803 to generate reconstructed CSI data ( data).

[0135] When the characteristics of the task or input data are different from the training data set and environment, the performance of the AI ​​model will deteriorate. When the performance of the AI ​​model deteriorates, the AI ​​model can be replaced by another AI model that is suitable for the characteristics of the input data or environment, the AI ​​model can be retrained, or fine-tuning can be performed on some layers of the AI ​​model.

[0136] Fine-tuning of an AI model may refer to the operation of further retraining an AI model according to the characteristics of a data set or changes in the environment in which the AI ​​model is deployed. For example, fine-tuning may include the operation of further training an AI model by using the minimum number of weights for downstream tasks in addition to all weights used for pre-training of the AI ​​model. Downstream tasks may refer to tasks that are ultimately completed by the AI ​​model.

[0137] In order to decode the compressed data (z data) generated by compressing (encoding) the data before (V data), the data before compression (V data) is obtained. Therefore, the fine-tuning of the AI ​​model in the embodiment of the present disclosure can be performed by converting the reconstructed CSI data ( data) is performed by comparing the CSI data (V data) before compression.

[0138] The data input to AE 800 may have various formats. In an embodiment of the present disclosure, the input to AE 800 may be a feature vector corresponding to a channel. H H gives N t ×N r The covariance matrix of the channel matrix H can be calculated by UE803. H H) = the dominant eigenvector of V∑Λ (expressed as V = [v 1 ..v r ]) can be considered the input of the AE 800. This Fig. 9 As shown in the figure.

[0139] Fig. 9A diagram for describing an operation of the pre-processor 903 transforming an estimated channel into a stacked eigenvector in CSI feedback based on the AE 900 according to an embodiment of the present disclosure is illustrated.

[0140] Fig. 9 The AE 900 can correspond to Figure 8 The aforementioned AE 800. Fig. 9 The encoder 901 and decoder 902 may correspond to Figure 8 The above-mentioned encoder 801 and decoder 802.

[0141] refer to Fig. 9 , the CSI feedback may be pre-processed by the pre-processor 903 before being input to the AE 900. For example, s N of the subbands s The set of channel matrices It can be the input 906 of the preprocessor 903, but not directly input to the encoder 901 of the AE 900. The preprocessor 903 can s The eigenvectors are operated on and the configuration matrix V stack , so that the feature vector corresponds to a column. The output V of the preprocessor 903 stack It can be an input 907 of the encoder 901. The encoder 901 can compress the input 907 to generate a bit stream s 905 for CSI feedback. The decoder 902 included in the AE 900 can obtain the compressed CSI feedback 905 from the encoder 901, and reconstruct the stacked feature vector V by decoding the compressed CSI feedback 905. stack The decoder 902 may be included on the BS side, and the BS may use the reconstructed stacked eigenvectors as a precoder.

[0142] At the same time, the AE900-based CSI feedback operation has limitations in generalizing various channel scenarios such as indoor, outdoor, urban macrocell (UMa), urban microcell (UMi), etc. This limitation may occur when the various scenarios involve different levels of channel scattering richness. Another factor may be the difference in the domain to be considered by the AE900 when compressing the CSI data. For example, when the number of subbands is N s And the number of CSI-RS ports is N t When the input to the AE 900 can be N s XN t .

[0143] [Table 1]

[0144]

[0145] Table 1 shows the output feature vector of the s-th subband and input 907v s Illustrative results of the hierarchical cosine similarity (GCS) between . The cosine similarity between feature vectors can be determined according to the following equation 4:

[0146] [Equation 4]

[0147]

[0148] The AE 900 for compressing CSI feedback includes an AI model at each end of the encoder 901 and the decoder 902. The AI ​​model uses a data set to train the model. Referring to Table 1, it can be seen that the AE 900 trained with an outdoor data set can have a high accuracy of about 91% when applied to an outdoor data set, and may have a low accuracy of about 82% when applied to an indoor data set. In order to enhance the performance of the AE 900 for various scenarios, a method of training the AE 900 using a combined data set including 50% outdoor data and 50% indoor data may be considered. It can be seen that the AE 900 trained with the combined data set has enhanced inter-scene accuracy, but has reduced intra-scene reasoning performance compared to training for one scene.

[0149] In an embodiment of the present disclosure, the generalization problem in AE-based CSI compression can be alleviated by the UE sending auxiliary information to the BS.

[0150] Fig.10 A diagram for describing an operation of a UE transmitting compressed CSI 1005 and auxiliary information 1009 to a BS according to an embodiment of the present disclosure is illustrated.

[0151] Fig.10 The AE 1000 can correspond to Figure 8 AE 800 or Fig. 9 AE900. Fig.10 The encoder 1001 may correspond to Figure 8 Encoder 801 or Fig. 9 The encoder 901, and Fig.10 The decoder 1002 may correspond to Figure 8 The decoder 802 or Fig. 9 Decoder 902. In addition, Fig.10 The preprocessor 1003 may correspond to Fig. 9 Preprocessor 903.

[0152] Upon receiving a CSI report request message (e.g., a configuration message) from the BS, the UE may send information for CSI reporting to the BS. The CSI report request message sent by the BS to the UE may include configuration information about AE-based CSI reporting. The information sent by the UE to the BS may include compressed CSI 1005 and auxiliary information 1009 for decompressing or reconstructing the compressed CSI 1005.

[0153] In an embodiment of the present disclosure, the CSI configuration information may be configured in the UE. In this case, the BS may obtain the CSI configuration information from the UE.

[0154] Reference Fig.10 , the UE sends the compressed CSI s 1005 and the auxiliary information s' 1009 to the BS. The compressed CSI s 1005 and the auxiliary information s' 1009 may constitute the CSI feedback information.

[0155] In an embodiment of the present disclosure, the pre-processor 1003 may perform dimensionality reduction of the input information 1006 .

[0156] For example, the pre-processor 1003 may identify L 2D DFT beams and transform N t XN s dimensional frequency domain channel Convert to 2L XM v Delay Domain Channel In this case, 2L is equal to or less than N t , and M v Equal to or less than N s As part of the auxiliary information s', the UE may feed back the indices of the L 2D DFT beams.

[0157] Table 2 below shows an example of the auxiliary information s'.

[0158] [Table 2]

[0159]

[0160] Referring to Table 2, the number of 2D DFT basis vectors L can be represented by the indicator i s1,1 Indicator i s1,1 The BS can be instructed to select from a maximum number N L The number of configured 2D DFT vectors. The configuration of the BS may be performed, for example, by Radio Resource Control (RRC) as part of the CSI configuration.

[0161] Table 3 below represents illustrative higher-level variables in the AE 1000 based CSI feedback method.

[0162] [Table 3]

[0163]

[0164] Referring to Table 3, CSI feedback based on AE 1000 can be configured as part of the codebook. Maximum number of 2D DFT beams N L It can be represented by the maximum number of DFT-beams (maxNumberOfDFT). The maximum number of delay components It can be indicated by the maximum number of delay components (maxNumberOfDelayComponents) that can be configured by the BS. The UE can then indicate the maximum number of delay components (maxNumberOfDelayComponents) by the indicator i s1,1 and i s2,1 represents the number of DFT beams L and the number of delayed components M v , as part of the CSI feedback.

[0165] For example, the parameters L and M v It can be configured by the BS as part of a parameter combination (paramCombination). In this case, the UE can add the index i s1,2 or s2,2 At least one of them is used as a part of the auxiliary information s'1009 to be sent to the BS.

[0166] When L and M v When determined by RRC configuration or as part of the UE's CSI report, the L DFT beams and M may be reported to the BS in the assistance information s'1009. v Indicator (index) of the delayed component.

[0167] Fig.11 A diagram for describing a preprocessing operation according to an embodiment of the present disclosure is illustrated.

[0168] Fig.11 The preprocessing operation can be done by Fig. 9 Preprocessor 903 or Fig.10 The preprocessor 1003 executes.

[0169] Reference Fig.11 , the AE may consider various domains (dimensions) for CSI compression. For example, the AE may perform CSI compression on the un-preprocessed spatial frequency domain 1100. In this case, the data domain used to perform compression, i.e., the input to the AE, has a dimension N t XN s .

[0170] For example, the spatial frequency domain 1100 may be preprocessed into the angular frequency domain 1101. In other words, the preprocessor may convert the Nt The data is converted into the angular frequency domain by converting L samples into the angular domain 1101. In this case, the data input to the AE is reduced to L x N after the pre-processing operation. s Dimension.

[0171] For example, the spatial frequency domain 1100 may be preprocessed into the spatial delay domain 1102. In other words, the preprocessor may convert the N s The samples (subbands) are converted into M in the delay domain v samples to convert the data into the spatial delay domain 1102. In this case, the data input to the AE is reduced to N samples after the pre-processing operation. t XM v Dimension.

[0172] For example, the spatial frequency domain 1100 may be preprocessed into the angular delay domain 1103. In other words, the preprocessor may convert the N t samples into L samples in the angle domain and N samples in the frequency domain s The samples (subbands) are converted into M in the delay domain v samples to convert the data into the angular delay domain 1103. In this case, the data input to the AE is reduced to LXM after the pre-processing operation. v Dimension.

[0173] In this way, when preprocessing for reducing the data dimension of the data signal before the data signal is input into the AE is performed in a method of identifying specific angles and specific delay components (for example, when selecting data to be compressed from all CSI feedback data), the dimension of the target data to be compressed is reduced through the AI ​​model, the number of times the AE performs compression is reduced, and the sensitivity of the AE to various environments and scenarios is thereby reduced.

[0174] Table 4 below represents dimensions of data input to the AE after the preprocessing operation and corresponding information included in the auxiliary information s'.

[0175] [Table 4]

[0176]

[0177] Fig.12 A diagram for describing an operation of a UE sending auxiliary information s'1206 including quantization information to a gNB according to an embodiment of the present disclosure is illustrated.

[0178] refer to Fig.12In an embodiment of the present disclosure, the UE may include a quantizer 1201. The quantizer 1201 may be configured in the encoder 1200 or may be implemented as a separate component. The UE may quantize the CSI compressed by the encoder 1200 before sending the compressed CSI to the gNB. The quantizer 1201 included in the UE may quantize the compressed CSI output from the encoder 1200. In an embodiment of the present disclosure, the UE may send the quantized compressed CSI S1205 to the gNB. The quantized compressed CSI S1205 may be sent to the gNB as CSI feedback. In the case where the quantized compressed CSI S1205 is sent from the UE to the gNB, the auxiliary information S'1206 may include information about the quantizer 1201 and may be sent to the gNB together with the quantized compressed CSI bits S1205 or separately from the quantized compressed CSI bits S1205.

[0179] In an embodiment of the present disclosure, the auxiliary information S'1206 determined based on the information about the quantizer 1201 may include information about, for example, the number of bits in each dimension of the encoder 1200, the total number of bits of the quantized compressed CSI S1205, etc. For example, the auxiliary information S'1206 determined based on the information about the quantizer 1201 may include information about a rule used by the quantizer 1201 to quantize the compressed CSI output from the encoder 1200, or other various information that allows the gNB to inversely convert and reconstruct the quantized data. Upon receiving the auxiliary information S'1206 from the UE, the gNB may configure the decoder 1202 or a post-processor to reconstruct the received quantized compressed CSI S1205 based on the auxiliary information S'1206.

[0180] Reference Fig.12 , the UE may include a preprocessor 1203 and a quantizer 1201. In this case, the UE may perform the above combined Fig.11 The preprocessing operation compresses the preprocessed CSI feedback data by the encoder 1200, and quantizes the compressed CSI feedback data by the quantizer 1201 to generate quantized compressed CSI feedback data S1205. In the case where the CSI feedback to be sent by the UE to the gNB corresponds to the preprocessed, compressed and quantized data, the additional data to be sent by the UE to the gNB may be configured with information from one of the preprocessor 1203 or the quantizer 1201.

[0181] Fig.12 The encoder 1200 may correspond to Figure 8 Encoder 801, Fig. 9 Encoder 901 or Fig.10 The encoder 1001, and Fig.12 The decoder 1202 may correspond to Figure 8 Decoder 802, Fig. 9 The decoder or Fig.10 Decoder 1002. In addition, Fig.12 The preprocessor 1203 may correspond to Fig. 9 Preprocessor 903 or Fig.10 The preprocessor 1003, and Fig.12 The postprocessor can correspond to Fig.10 A post-processor 1004 is provided.

[0182] Reference Fig.12 , shows that the CSI feedback sent by the UE to the gNB is pre-processed, compressed and quantized data, but in an embodiment of the present disclosure, the CSI feedback sent by the UE to the gNB may also be compressed and quantized non-pre-processed data. In this case, the additional data sent by the UE to the gNB may be configured using information from the quantizer 1201.

[0183] Fig.13 A diagram for describing signaling between a UE and a gNB for AE-based CSI feedback according to an embodiment of the present disclosure is illustrated.

[0184] Fig.13 The UE may correspond to Figure 1 , Figure 3a , Figure 8 or Fig.12 The aforementioned UE shown in FIG. Fig.13 The gNB can correspond to Figure 1 , Figure 3b , Figure 8 or Fig.12 The aforementioned BS or gNB.

[0185] Reference Fig.13 In operation 1300, the UE may send information about the capability of the UE to perform AI-based CSI feedback to the gNB. For example, the UE may send information indicating that the UE is capable of performing AI-based CSI feedback to the gNB through UE capability signaling.

[0186] In an embodiment of the present disclosure, the UE capability signaling may include at least one of information about a rule for a preprocessor included in the UE to perform preprocessing on data or information about a rule for a quantizer included in the UE to perform quantization on data. For example, the operation of the preprocessor included in the UE to perform preprocessing on data may correspond to the above combined Fig.11 The operation described above, and the operation of the quantizer included in the UE to perform quantization on the data may correspond to the above combined Fig.12 Describes the operation.

[0187] Subsequently, in operation 1301, the gNB may send CSI report configuration information to the UE through RRC signaling. The CSI report configuration information may include at least one of information related to a preprocessor included in the UE, information related to an AI model of an AE, or information related to a quantizer. In addition, the CSI report configuration information may include information about the size of the compressed CSI S or auxiliary information S', or the report format.

[0188] In operation 1302, the UE may receive CSI report configuration information from the gNB, and send AE-based CSI feedback including compressed CSI S and auxiliary information S'. In an embodiment of the present disclosure, the compressed CSI S sent by the UE to the gNB may be compressed CSI feedback data without preprocessing, CSI feedback data preprocessed by a preprocessor and then compressed by an encoder, CSI feedback data compressed by an encoder without preprocessing and then quantized by a quantizer, or CSI feedback data preprocessed by a preprocessor, compressed by an encoder, and quantized by a quantizer. In addition, the auxiliary information S' sent by the UE to the gNB may include at least one of information about a data compression rule of the encoder, information about a data preprocessing rule of the preprocessor, or information about a data quantization rule of the quantizer.

[0189] In an embodiment of the present disclosure, the gNB and the UE may pre-share the data compression rule of the encoder, the data preprocessing rule of the preprocessor, or the data quantization rule of the quantizer. In this case, the auxiliary information S' may include the minimum parameters for executing the rule.

[0190] In an embodiment of the present disclosure, the gNB may not know information about an encoder, a preprocessor, or a quantizer included in the UE. In this case, the auxiliary information S' sent by the UE to the gNB may include: at least one of a data compression rule of the encoder, a data preprocessing rule of the preprocessor, or a data quantization rule of the quantizer, and a parameter for implementing a specific rule.

[0191] In an embodiment of the present disclosure, the gNB and the UE may not share exact information about the data compression rule of the encoder, the data preprocessing rule of the preprocessor, or the data quantization rule of the quantizer in advance, but may share various rules as candidates. In this case, the auxiliary information S' may include an indicator for indicating a rule actually applied among the candidate rules and a parameter for implementing the rule.

[0192] In operation 1302, upon receiving compressed CSI feedback S and auxiliary information S' from the UE, the gNB may reconstruct the CSI feedback through a decoder and a post-processor based on the received auxiliary information S'. The CSI feedback reconstruction operation may be implemented by performing operations performed by the UE in reverse order based on the compressed CSI feedback S and the auxiliary information S'. The gNB may identify the CSI through the reconstructed CSI feedback.

[0193] Then, in operation 1303, upon receiving the CSI feedback based on the AE, the UE may transmit DL data on a physical downlink shared channel (PDSCH) based on the identified CSI.

[0194] Fig.14a , 14b 14c illustrate diagrams for describing operations of a UE transmitting assistance information to a BS in AE-based CSI feedback according to an embodiment of the present disclosure.

[0195] exist Fig.14a In FIG. 1 , data transmitted in the time domain is shown. In an embodiment of the present disclosure, CSI feedback may be reported periodically or non-permanently. In this case, the BS may establish a cycle for the UE to report auxiliary information and compressed CSI.

[0196] Reference Fig.14b , whenever the UE sends compressed CSI feedback to the BS (1400, 1401 and 1402), the UE may send auxiliary information. In this case, even when the channel state changes over time, the reconstruction accuracy of the compressed CSI feedback may be increased.

[0197] Reference Fig.14c , whenever the UE sends compressed CSI feedback to the BS, the UE may not send auxiliary information. For example, there may be a connection between channels in the time domain. Specifically, when the channel state does not change significantly or even if the condition changes slightly after a period of time, the auxiliary information (e.g., the angle delay component) of a certain channel may remain the same at multiple times of CSI feedback 1403, 1404, and 1405. In this case, when the auxiliary information is sent to the BS in a specific CSI feedback 1403, the auxiliary information may not be sent to the BS during a certain number of subsequent CSI feedback operations 1404 and 1405, but the auxiliary information that has been sent may be applied to the CSI feedback in which the auxiliary information is not reported.

[0198] For example, in Fig.14cIn the illustrated embodiment of the present disclosure, the assistance information sent in the CSI feedback 1403 may include timer information of the assistance information. In addition, the UE may send an indicator including information about whether it is capable of performing time-correlated CSI measurement and reporting to the BS in the assistance information, and the BS may then provide the UE with configuration information for time-correlated CSI measurement and reporting based on the indicator received from the UE.

[0199] Fig.15 A schematic block diagram of a BS 1500 according to an embodiment of the present disclosure is illustrated.

[0200] Reference Fig.15 , BS1500 may include a transceiver 1510, a processor 1520, and a memory 1530. The transceiver 1510, the processor 1520, and the memory 1530 of BS1500 may operate according to the above-mentioned communication method of BS1500. However, the elements of BS1500 are not limited thereto. For example, base station 1500 may include more or less elements than those described above. In addition, transceiver 1510, processor 1520, and memory 1530 may be implemented in a single chip. Processor 1520 may include one or more processors.

[0201] The receiver and transmitter of BS1500 are collectively referred to as transceiver 1510, and transceiver 1510 can send signals to UE or network entity or receive signals from UE or network entity. The signal to be sent to UE or network entity or received from UE or network entity may include control information and data. To this end, transceiver 1510 may include an RF transmitter for up-converting the signal to be sent and amplifying the signal, and an RF receiver for low-noise amplification of the received signal and down-converting the received signal. This is just an example of transceiver 1510, and the elements of transceiver 1510 are not limited to RF transmitter and RF receiver.

[0202] The transceiver 1510 may perform a function for transmitting and receiving a signal on a wireless channel. For example, the transceiver 1510 may receive a signal on a wireless channel and output the signal to the processor 1520, and transmit a signal output from the processor 1520 on a wireless channel.

[0203] The memory 1530 may store programs and data for the operation of the base station 1500. In addition, the memory 1530 may store control information or data included in the signal obtained by the BS. The memory 1530 may include a storage medium such as a read-only memory (ROM), a random access memory (RAM), a hard disk, a compact disk ROM (CD-ROM) and a digital versatile disk (DVD), or a combination of storage media. Alternatively, the memory 1530 may not exist alone but be integrated into the processor 1520. The memory 1530 may include a volatile memory, a non-volatile memory, or a combination of a volatile memory and a non-volatile memory. The memory 1530 may also provide the stored data at the request of the processor 1520.

[0204] The processor 1520 may control a series of processes of the BS 1500 for operating according to an embodiment of the present disclosure. For example, the processor 1520 may receive a control signal and a data signal through the transceiver 1510, and process the received control signal and data signal. The processor 1520 may send the processed control signal and data signal through the transceiver 1510. The processor 1520 may record data to the memory 1530 or read data from the memory 1330. The processor 1520 may perform the functions of the protocol stack requested by the communication standard. To this end, the processor 1520 may include at least one processor or microprocessor. In an embodiment of the present disclosure, a part of the transceiver 1510 and the processor 1520 may be referred to as a communication processor (CP).

[0205] Processor 1520 may include one or more processors. The one or more processors may include a general-purpose processor (e.g., CPU, AP, digital signal processor (DSP), etc.), a GPU, a visual processing unit (VPU), etc., or a dedicated AI processor (e.g., a neural processing unit (NPU)). For example, when one or more processors are dedicated AI processors, the dedicated AI processor may be designed as a hardware structure dedicated to processing a specific AI model.

[0206] Fig.16 A schematic block diagram of a UE 1600 according to an embodiment of the present disclosure is illustrated.

[0207] Reference Fig.16 , UE 1600 may include a transceiver 1610, a processor 1620, and a memory 1630. However, the elements of UE 1600 are not limited thereto. For example, UE 1600 may include more or fewer elements than those described above. In an embodiment of the present disclosure, transceiver 1610, processor 1620, and memory 1630 may be implemented in a single chip.

[0208] Processor 1620 may include one or more processors. The one or more processors may include a general-purpose processor (e.g., CPU, AP, digital signal processor (DSP), etc.), a GPU, a visual processing unit (VPU), etc., or a dedicated AI processor (e.g., a neural processing unit (NPU)). For example, when one or more processors are dedicated AI processors, the dedicated AI processor may be designed as a hardware structure dedicated to processing a specific AI model.

[0209] The processor 1620 may control a series of processes for the UE 1600 to operate according to the aforementioned embodiments of the present disclosure. For example, the processor 1620 may receive a control signal and a data signal through the transceiver 1610, and process the received control signal and data signal. The processor 1620 may send the processed control signal and data signal through the transceiver 1610. In addition, the processor 1620 may control the input data derived from the received control signal and the data signal to be processed according to a predetermined operation rule or AI model stored in the memory 1630. The processor 1620 may record data to the memory 1630 or read data from the memory 1430. The processor 1620 may also perform the functions of the protocol stack requested by the communication standard. In an embodiment, the processor 1620 may include at least one processor. In an embodiment of the present disclosure, a part of the transceiver 1610 or the processor 1620 may be referred to as a CP.

[0210] The memory 1630 may store programs and data for the operation of the UE 1600. In addition, the memory 1630 may store control information or data included in the signal obtained by the UE 1600. In addition, the memory 1630 may store predetermined operating rules or an AI model used by the UE 1600. The memory 1630 may include a storage medium (such as ROM, RAM, hard disk, CD-ROM and DVD) or a combination of storage media. Alternatively, the memory 1630 may not exist alone but be integrated into the processor 1620. The memory 1630 may include a volatile memory, a non-volatile memory, or a combination of a volatile memory and a non-volatile memory. The memory 1630 may also provide stored data at the request of the processor 1620.

[0211] The transceiver 1610 may refer to a transmitter and a receiver, and the transceiver 1610 of the UE 1600 may send a signal to a BS or a network entity or receive a signal from a BS or a network entity. The signal may include control information and data. To this end, the transceiver 1610 may include an RF transmitter for up-converting a signal to be sent and amplifying the signal, and an RF receiver for low-noise amplifying a received signal and down-converting the received signal. This is merely an example of the transceiver 1610, and the elements of the transceiver 1610 are not limited to an RF transmitter and an RF receiver. In addition, the transceiver 1610 may receive a signal on a wireless channel, output the signal to the processor 1620, and transmit a signal output from the processor 1620 on a wireless channel.

[0212] The AI-related functions according to the embodiments of the present disclosure are operated by a processor and a memory. There may be one or more processors. One or more processors may include a general-purpose processor (e.g., CPU, AP, digital signal processor (DSP), etc.), a GPU, a visual processing unit (VPU), etc., or a dedicated AI processor (e.g., a neural processing unit (NPU)). One or more processors may control the processing of input data according to predetermined operating rules or AI models stored in the memory. When one or more processors are dedicated AI processors, they may be designed as a hardware structure dedicated to processing a specific AI model.

[0213] Predefined operating rules or AI models can be formed by learning. Specifically, the predetermined operating rules or AI models formed by learning refer to the predetermined operating rules or AI models established to execute the desired features (or objects) when the basic AI model (or deep learning model) is trained by the learning algorithm using a large amount of training data. Such learning can be performed by the device itself that performs AI according to the present disclosure, or by a separate server and / or system. Examples of learning algorithms may include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited thereto.

[0214] The AI ​​model (or deep learning model) may be composed of multiple neural network layers. Each of the multiple neural network layers may have multiple weight values, and the neural network operation is performed by operating between the operation result of the previous layer and the multiple weight values. The multiple weight values ​​owned by the multiple neural network layers can be optimized by learning the results of the AI ​​model. For example, multiple weight values ​​can be updated to reduce or minimize the loss value or cost value obtained by the AI ​​model during the training process. The artificial neural network may include a deep neural network (DNN), such as a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep confidence network (DBN), a bidirectional recurrent deep neural network (BRDNN) or a deep Q network, but is not limited thereto.

[0215] Various embodiments of the present disclosure can be implemented or supported by one or more computer programs, which are formed by computer-readable program code and can be implemented on computer-readable media. Throughout the specification, the terms "application" and "program" can refer to one or more computer programs, software components, instruction sets, processes, functions, objects, classes, examples, associated data or parts thereof, which are suitably implemented in computer-readable program code. Computer-readable program code can include various types of computer code, including source code, object code and executable code. Computer-readable media can include computer-accessible various types of media, such as ROM, RAM, hard disk drive (HDD), compact disc (CD), digital video disc (DVD) or other various types of memory.

[0216] Computer-readable storage media may be provided in the form of non-transitory storage media. Non-transitory storage media are tangible devices that may exclude wired, wireless, optical or other communication links for sending transient electrical or other signals. Non-transitory storage media do not distinguish between situations where data is semi-permanently stored and situations where data is temporarily stored in storage media. For example, non-transitory storage media may include a buffer for temporarily storing data. Computer-readable media may be any available media that can be accessed by a computer, including volatile, non-volatile, removable and non-removable media. Computer-readable media include media for permanently storing data, as well as media for storing data that can be rewritten later, i.e., rewritable optical disks or erasable storage devices.

[0217] In an embodiment of the present disclosure, the above method according to various embodiments of the present disclosure may be provided in a computer program product. A computer program product may be a commercial product that can be traded between a seller and a buyer. The computer program product may be distributed in the form of a storage medium (e.g., a compact disc read-only memory (CD-ROM)), distributed through an application store, distributed directly between two user devices (e.g., smart phones), or distributed online (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable application) may be at least temporarily stored or arbitrarily created in a storage medium that may be readable by a device such as a manufacturer's server, a server of an application memory, or a relay server.

[0218] Several embodiments have been described, but those of ordinary skill in the art will understand and accept that various modifications may be made without departing from the scope of the present disclosure. For example, the above methods may be performed in a different order, and / or the above systems, structures, devices, circuits, etc. may be combined in different combinations than those described above, or replaced or substituted by other components or their equivalents to obtain appropriate results. Therefore, those of ordinary skill in the art will understand that the present disclosure is not limited to the described embodiments, but may include not only the attached claims, but also equivalents. For example, elements described in singular form may be implemented as distributed, and elements described in distributed form may be implemented as combined.

[0219] The scope of the present disclosure is defined by the appended claims, and it will be understood by those skilled in the art that various changes in form and details may be made without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents.

[0220] Although the present disclosure has been described with various embodiments, various changes and modifications may be suggested to one skilled in the art. The present disclosure is intended to encompass such changes and modifications as fall within the scope of the appended claims.

Claims

1. A method for a user equipment UE in a wireless communication system, the method comprising: Receiving channel state information CSI report configuration information from a base station BS; generating compressed CSI feedback data through an encoder included in the UE based on the CSI report configuration information, and generating auxiliary information related to the compressed CSI feedback data; as well as The compressed CSI feedback data and the auxiliary information are sent to the BS.

2. The method according to claim 1, wherein: The CSI report configuration information is received through radio resource control RRC signaling.

3. The method according to claim 1, wherein: The UE further includes a pre-processor, and The compressed CSI feedback data is generated by preprocessing the CSI data by the preprocessor and compressing the CSI data by the encoder.

4. The method according to claim 3, wherein: The auxiliary information includes at least one of information related to the pre-processor or information related to the encoder.

5. The method according to claim 3, wherein: The pre-processor is configured to reduce the dimension of input CSI data and output resulting CSI data.

6. The method according to claim 1, wherein: The UE further includes a quantizer, and The compressed CSI feedback data is generated by compressing the CSI data by the encoder and quantizing the CSI data by the quantizer.

7. The method according to claim 6, wherein: The auxiliary information includes at least one of information related to the quantizer or information related to the encoder.

8. The method according to claim 6, wherein: The UE further includes a pre-processor, and The compressed CSI feedback data is obtained by: preprocessing the CSI data by the preprocessor before compressing the CSI data by the encoder.

9. The method according to claim 1, wherein: The auxiliary information corresponds to a plurality of the compressed CSI feedback data and includes a timer.

10. A user equipment UE of a wireless communication system, the UE comprising: Encoder; Transceiver; as well as at least one processor, Wherein, the at least one processor is configured to: Receiving channel state information CSI report configuration information from a base station BS through the transceiver; generating compressed CSI feedback data through the encoder based on the CSI report configuration information, and generating auxiliary information related to the compressed CSI feedback data; as well as The compressed CSI feedback data and the auxiliary information are transmitted to the BS through the transceiver.

11. The UE according to claim 10, further comprising a preprocessor, wherein: The at least one processor is configured to: The CSI data is preprocessed by the preprocessor, and the preprocessed CSI data is compressed by the encoder, thereby generating the compressed CSI feedback data.

12. The UE according to claim 11, wherein: The at least one processor is configured to: The CSI data is preprocessed by reducing the dimension of the CSI data through the preprocessor.

13. The UE according to claim 10, further comprising a quantizer, wherein: The at least one processor is configured to: The CSI data is compressed by the encoder, and the compressed CSI data is quantized by the quantizer to generate the compressed CSI feedback data.

14. The UE according to claim 13, further comprising a preprocessor, wherein: The at least one processor is configured to: Before compressing the CSI data by the encoder, the CSI data is preprocessed by the preprocessor.

15. A method for a base station BS in a wireless communication system, the method comprising: Sending channel state information CSI report configuration information to user equipment UE; receiving, from the UE, compressed CSI feedback data determined based on the CSI report configuration information and auxiliary information related to the compressed CSI feedback data; Reconstructing the compressed CSI feedback data by a decoder included in the BS; as well as The reconstructed CSI feedback data is post-processed by a post-processor included in the BS based on the auxiliary information.

Images