Method and apparatus for reporting ai-based channel information for link adaptation in wireless communication system, and link adaptation method and apparatus using same

Abstract

The present disclosure relates to a method and an apparatus for reporting AI-based channel information for link adaptation in a wireless communication system, and a link adaptation method and apparatus using same. A method performed by a terminal for link adaptation in a wireless communication system, according to an embodiment of the present disclosure, comprises steps in which the terminal: receives, from a base station, configuration information for AI-based link adaptation; receives a PDSCH transmission from the base station; and performs a first update of an SINR model related to the AI-based link adaptation on the basis of a decoding result of the PDSCH transmission.

Description

Method and device for reporting AI-based channel information for link adaptation in a wireless communication system and method and device for link adaptation using the same

[0001] The present disclosure relates to a method and apparatus for link adaptation in a wireless communication system.

[0002] Looking back at the evolution of wireless communication over successive generations, technologies have primarily been developed for human-facing services such as voice, multimedia, and data. With the commercialization of 5G (5th-generation) communication systems, an explosive increase in connected devices is expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction equipment, and factory equipment. Mobile devices are expected to evolve into diverse form factors, including augmented reality glasses, virtual reality headsets, and holographic devices. In the 6th-generation (6G) era, efforts are being made to develop improved 6G communication systems to connect hundreds of billions of devices and objects and provide diverse services. For this reason, 6G communication systems are often referred to as "beyond 5G."

[0003] The 6G communication system, expected to be realized around 2030, will have a maximum transmission speed of terabytes per second (i.e., 1,000 gigabits per second) and a wireless latency of 100 microseconds (μsec). In other words, compared to 5G, the transmission speed in a 6G communication system will be 50 times faster, while the wireless latency will be reduced to one-tenth.

[0004] To achieve these high data rates and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz band (e.g., from 95 gigahertz (GHz) to 3 terahertz (THz)). Compared to the millimeter wave (mmWave) band introduced in 5G, the terahertz band is expected to experience more severe path loss and atmospheric absorption, making it more crucial to ensure signal reach, or coverage, in this band. Key technologies to ensure coverage include radio frequency (RF) components, antennas, new waveforms that offer better coverage than OFDM (orthogonal frequency division multiplexing), beamforming, and multiple antenna transmission technologies such as massive multiple-input and multiple-output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing using orbital angular momentum (OAM), and reconfigurable intelligent surfaces (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, in order to improve frequency efficiency and system network, 6G communication systems are developing full duplex technology that utilizes the same frequency resources for uplink and downlink at the same time; network technology that integrates satellites and high-altitude platform stations (HAPS); network structure innovation technology that supports mobile base stations and enables optimization and automation of network operation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes artificial intelligence (AI) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services with complexity that exceeds the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources (mobile edge computing (MEC), cloud, etc.). In addition, efforts are being made to further strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase the openness of wireless communications through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe use of data, and the development of technologies for maintaining privacy.

[0006] Research and development of these 6G communication systems are expected to enable a new level of hyper-connected experience through the hyper-connectivity of 6G communication systems, which encompass not only connections between things but also connections between people and things. Specifically, 6G communication systems are expected to enable services such as truly immersive extended reality (Truly Immersive XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems through enhanced security and reliability, will find application in diverse fields such as industry, medicine, automobiles, and home appliances.

[0007] The present disclosure provides a method and apparatus for reporting AI (artificial intelligence)-based channel information for link adaptation in a wireless communication system.

[0008] Additionally, the present disclosure provides a link adaptation method and device using AI-based channel information in a wireless communication system.

[0009] The present disclosure also provides a method and apparatus for supporting AI-based channel information reporting for link adaptation in at least one of a terminal and a base station in a wireless communication system.

[0010] According to an embodiment of the present disclosure, a method performed in a terminal for link adaptation in a wireless communication system includes a process in which the terminal receives configuration information for AI-based link adaptation from a base station, a process in which the terminal receives a physical downlink shared channel (PDSCH) transmission from the base station, and a process in which the terminal first updates a signal to noise and interference ratio (SINR) model related to the AI-based link adaptation based on a decoding result of the PDSCH transmission.

[0011] In addition, according to an embodiment of the present disclosure, in a wireless communication system, a terminal includes a transceiver, and a processor configured to receive, through the transceiver, configuration information for AI-based link adaptation from a base station, and to first update an SINR model related to the AI-based link adaptation based on a decoding result of the PDSCH transmission, through the transceiver.

[0012] In addition, according to an embodiment of the present disclosure, a method performed in a base station for link adaptation in a wireless communication system includes the steps of: transmitting configuration information for AI-based link adaptation to a terminal; transmitting at least one of a PDSCH signal and a CSI-RS to the terminal; receiving at least one of a first SINR difference and a second SINR difference related to an update of an SINR model related to the AI-based link adaptation from the terminal; and selecting an MCS to be applied to PDSCH transmission to the terminal based on the at least one of the first SINR difference and the second SINR difference.

[0013] In addition, according to an embodiment of the present disclosure, in a wireless communication system, a base station includes a transceiver, and a processor configured to transmit, through the transceiver, configuration information for AI-based link adaptation to a terminal, transmit, through the transceiver, at least one of a PDSCH signal and a CSI-RS to the terminal, receive, through the transceiver, from the terminal at least one of a first SINR difference and a second SINR difference related to an update of an SINR model related to the AI-based link adaptation, and select an MCS to be applied to PDSCH transmission to the terminal based on the at least one of the first SINR difference and the second SINR difference.

[0014] Figure 1 is a diagram illustrating an example of link adaptation in a wireless communication system.

[0015] Figure 2 is a diagram for explaining an example of a link adaptation method using SINR probability distribution in a wireless communication system.

[0016] FIG. 3 is a diagram conceptually illustrating a method for a terminal to estimate an SINR probability distribution in a wireless communication system according to an embodiment of the present disclosure;

[0017] FIG. 4a is a diagram illustrating a method for estimating an SINR probability distribution when a terminal successfully decodes a PDSCH according to an embodiment of the present disclosure;

[0018] FIG. 4b is a diagram illustrating a method for estimating an SINR probability distribution when decoding of a PDSCH fails in a terminal according to an embodiment of the present disclosure;

[0019] FIG. 5 is a diagram illustrating a method for updating an SINR model when decoding of a PDSCH retransmission signal fails in a terminal according to an embodiment of the present disclosure;

[0020] FIG. 6 is a diagram illustrating an example of an AI-based link adaptation method using a first SINR difference in a wireless communication system according to an embodiment of the present disclosure;

[0021] FIG. 7 is a diagram illustrating an example of an AI-based link adaptation method using a first SINR difference in a wireless communication system according to an embodiment of the present disclosure;

[0022] FIG. 8 is a diagram illustrating an example of an AI-based link adaptation method using a second SINR difference in a wireless communication system according to an embodiment of the present disclosure;

[0023] FIG. 9 is a diagram illustrating an example of an AI-based link adaptation method using a second SINR difference in a wireless communication system according to an embodiment of the present disclosure;

[0024] FIG. 10 is a diagram illustrating a SINR representative value selection method negotiation method performed between a terminal and a base station according to an embodiment of the present disclosure;

[0025] FIG. 11 is a diagram showing an example of an AI-based link adaptation method using a first SINR difference and a second SINR difference in a wireless communication system according to an embodiment of the present disclosure; and

[0026] FIG. 12 is a diagram showing an example configuration of a network entity in a wireless communication system according to an embodiment of the present disclosure.

[0027] The operating principles of the present disclosure are described in detail below with reference to the attached drawings. In the following description of the present disclosure, detailed descriptions of related known functions or configurations will be omitted if they are deemed to unnecessarily obscure the gist of the present disclosure. Furthermore, the terms described below are defined based on the functions of the present disclosure and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the overall content of this specification.

[0028] For the same reason, some components in the attached drawings are omitted or schematically depicted. Furthermore, the dimensions of each component do not entirely reflect its actual size. Identical or corresponding components in each drawing are assigned the same reference numbers.

[0029] The advantages and features of the present disclosure, and methods for achieving them, will become clearer with reference to the embodiments described below in detail with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The various embodiments are provided to ensure that the present disclosure is complete and to fully convey the scope of the present disclosure to those skilled in the art, and the present disclosure is defined solely by the scope of the claims. Like reference numerals designate like elements throughout the specification.

[0030] At this time, it will be understood that each block of the processing flow diagrams and combinations of the flow diagrams can be performed by computer program instructions. These computer program instructions can be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flow diagram block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to implement the functions in a specific manner, so that the instructions stored in the computer-available or computer-readable memory can also produce a manufactured item that includes an instruction means for performing the functions described in the flow diagram block(s). Since the computer program instructions may be installed on a computer or other programmable data processing device, a series of operational steps may be performed on the computer or other programmable data processing device to create a computer-executable process, and the instructions that cause the computer or other programmable data processing device to perform the steps for performing the functions described in the flowchart block(s) may also provide steps for performing the functions described in the flowchart block(s).

[0031] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions.

[0032] The term "~unit" used in various embodiments of the present disclosure refers to a software or hardware component, and the "~unit" performs certain roles. However, the "~unit" is not limited to software or hardware. The "~unit" may be configured to reside on an addressable storage medium and may be configured to regenerate one or more processors. Thus, as an example, the "~unit" includes components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and "~units" may be combined into a smaller number of components and "~units" or further separated into additional components and "~units." In addition, the components and "~units" may be implemented to regenerate one or more CPUs within a device or a secure multimedia card. Additionally, in various embodiments of the present disclosure, '~bu' may include one or more processors.

[0033] In this disclosure, phrases such as "A and / or B", "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can each include any one of the items listed together in that phrase, or all possible combinations thereof. Terms such as "first", "second", or "first" or "second" may be used merely to distinguish the corresponding component from other corresponding components and do not limit the corresponding components in any other respect (e.g., importance or order).

[0034] In embodiments of the present disclosure, a user equipment (UE) may be a terminal, a mobile station (MS), a cellular phone, a smartphone, a computer, or any other electronic device capable of performing a communication function. In addition, a base station (BS) is a network entity that performs resource allocation to a terminal, and may be a Node B, an eNB (eNode B), a gNB (gNode B), a wireless access unit, a base station controller, or a node on a network.

[0035] Furthermore, the various embodiments of the present disclosure described below may be applied to other communication systems having similar technical backgrounds or channel configurations. Furthermore, the various embodiments of the present disclosure may be applied to other communication systems with some modifications, as determined by a person skilled in the art, without significantly departing from the scope of the present disclosure.

[0036] In specifically describing various embodiments of the present disclosure, the communication system may utilize a wireless communication system, and for example, may utilize a 5G communication system based on the 5G communication standard (NR (New RAN)) proposed by 3GPP (3rd generation partnership project long term evolution), a wireless communication standard standardization organization. In addition, it may be applied to other communication systems with similar technical backgrounds with slight modifications within a range that does not significantly deviate from the scope of the present disclosure, and this may be possible at the discretion of a person skilled in the technical field of the present disclosure. For the convenience of the following description, some terms and names defined in the 3GPP standard may be used. However, the present disclosure is not limited by the above terms and names, and may be equally applied to systems conforming to other standards.

[0037] The aforementioned 5G communication system must be able to freely reflect the diverse needs of service providers and users, and thus support services that simultaneously satisfy these requirements. Services being considered for 5G communication systems include enhanced Mobile Broadband (eMBB), massive Machine Type Communication (mNTC), and Ultra Reliability Low Latency Communication (URLLC).

[0038] The above eMBB aims to provide data transmission rates that are significantly higher than those supported by existing LTE, LTE-A, or LTE-Pro. For example, in a 5G communication system, eMBB must be able to provide a peak data rate of 20 Gbps in the downlink and a peak data rate of 10 Gbps in the uplink from the perspective of a single base station. In addition, the 5G communication system must provide the maximum transmission rate while also providing an increased user-perceived data rate for the terminal. To meet these requirements, improvements in various transmission and reception technologies, including further improved multi-antenna (multi-input multi-output: MIMO) transmission technology, are required. In addition, while the current LTE transmits signals using a maximum transmission bandwidth of 20 MHz in the 2 GHz band, the 5G communication system can satisfy the data transmission rates required by the 5G communication system by using a wider frequency bandwidth than 20 MHz in the 3-6 GHz or higher frequency band.

[0039] At the same time, mMTC is being considered to support application services such as the Internet of Things (IoT) in 5G communication systems. To efficiently provide the IoT, mMTC requires supporting large-scale terminal connections within a cell, improved terminal coverage, enhanced battery life, and reduced terminal costs. The IoT requires the ability to support a large number of terminals (e.g., 1,000,000 terminals / km2) within a cell, as it provides communication capabilities through the attachment of various sensors and devices. Furthermore, terminals supporting mMTC are likely to be located in shadow areas not covered by cells, such as basements, due to the nature of the service. This necessitates broader coverage compared to other services provided by 5G communication systems. Terminals supporting mMTC must be inexpensive, and since frequent battery replacement is difficult, a very long battery life, such as 10 to 15 years, is required.

[0040] Finally, URLLC refers to cellular-based wireless communication services used for specific mission-critical purposes. Examples include remote control of robots or machinery, industrial automation, unmanned aerial vehicles (UAVs), remote health care, and emergency alerts. Therefore, URLLC communications must offer extremely low latency and high reliability. For example, services supporting URLLC must meet air interface latency requirements of less than 0.5 milliseconds and a packet error rate (PER) of 10-5 or lower. Therefore, for services supporting URLLC, 5G communication systems must provide shorter Transmit Time Intervals (TTIs) than other services, while simultaneously allocating extensive resources in the frequency band to ensure communication link reliability.

[0041] In the present disclosure, link adaptation refers to a technology for selecting an MCS (Modulation and Coding Scheme) with an optimal transmission rate according to a changing wireless environment. For example, when the wireless environment is good, a base station can apply a high transmission rate of 256 QAM (Quadrature Amplitude Modulation) to downlink transmission, and when the wireless environment is bad, it can apply a low modulation scheme of BPSK (Binary Phase Shift Keying) and a low code rate to transmit downlink data. The base station can select an optimal MCS suitable for the wireless environment based on feedback information reported by the terminal (e.g., CQI (channel quality indicator), HARQ (Hybrid Automatic Repeat Request) feedback).

[0042] Figure 1 is a diagram illustrating an example of link adaptation in a wireless communication system.

[0043] Referring to FIG. 1, a terminal (UE) (110) may receive downlink data from a base station (120) and transmit a well-known HARQ ACK / NACK as a reception response to the downlink data to the base station (120). In addition, the terminal (110) may receive a reference signal for measuring a channel state, such as a CSI-RS (Channel State Information Reference Signal), from the base station (120), and transmit a CQI indicating the channel state to the base station (120). The HARQ ACK / NACK, CQI, etc. may be used as feedback information for link adaptation. The base station (120) may select an optimal MCS suitable for the channel environment of the terminal (110) based on the feedback information, and provide the MCS information to the terminal (110). The base station (120) may transmit a PDSCH (Physical Downlink Shared Channel) signal to be transmitted to the terminal (110) according to the selected MCS.

[0044] Figure 1 illustrates a link adaptation that combines inner-loop link adaptation (ILLA) and outer-loop link adaptation (OLLA). ILLA (121) is a technology that selects an MCS based on CSI feedback (e.g., CQI) reported to the base station (120) from the terminal (110). CQI can be converted / calculated into SINR (signal to noise and interference ratio) using a known method (122). OLLA (123) is a technology that selects an SINR offset (hereinafter, Offset) based on HARQ feedback (e.g., ACK / NACK) reported to the base station (120) from the terminal (110). OLLA ) is a technology that controls.

[0045] Offset from the above OLLA(123) OLLAcan be adjusted in the same manner as 1) and 2) below whenever ACK or NACK is received from the terminal (110).

[0046] 1) When receiving ACK, Offset OLLA [t]←Offset OLLA [t-1]+△ ACK Update (adjust)

[0047] 2) When receiving NACK, Offset OLLA [t]←Offset OLLA [t-1]-△ NACK Update (adjust)

[0048] At this time △ ACK Wow △ NACK Silver BLER target =(1+△ NACK / △ ACK ) -1 It can be determined by the relationship between BLER target means the target BLER (for example, 10%) that the base station (120) is aiming for, and once the target BLER is determined, △ ACK Wow △ NACK can be determined according to the above relationship. The base station (120) obtains / calculates the SINR based on the CSI feedback. CQI SINR offset (Offset) obtained / calculated based on HARQ feedback at [t] OLLA SINR subtracting [t]) eff [t]←SINR CQI [t]-Offset OLLA Using the method of [t], the effective SINR (i.e. SINR) of the current time point (t) eff[t]) is estimated, and the base station (120) can select the highest MCS level that satisfies the target BLER using the BLER curve, or select the MCS corresponding to the effective SINR using table information indicating the mapping relationship between SINR and MCS. In the example of FIG. 1, the CQI may mean the maximum MCS that the terminal (110) recommends to the base station (120). That is, the CQI may mean the maximum acceptable MCS estimated based on the channel information measured by the terminal (110).

[0049] However, in the ILLA, the CQI is estimated in a state where the terminal (110) does not know the operation of the base station (120) (e.g., precoding, link adaptation algorithm), and is reported to the base station (120) in a quantized discrete level, so the base station (120) may not always trust the CQI reported by the terminal (110). In addition, since the CQI has a long reporting cycle, an outdated CQI problem may occur in which the CQI previously reported to the base station (120) is not valid for the current channel situation. In addition, in the OLLA, the CQI is estimated by Offset OLLA Even when corrected through OLLA, performance may deteriorate due to the difficulty in quickly converging and maintaining the optimal MCS value due to the nature of the rule-based algorithm.

[0050] FIG. 2 is a diagram for explaining an example of a link adaptation method using SINR probability distribution in a wireless communication system.

[0051] Referring to FIG. 2, a terminal transmits a HARQ ACK / NACK (201) to a base station (210) in response to receiving downlink data on a PDSCH. The base station (210) can estimate an SINR probability distribution (211) for the terminal based on the history of HARQ ACK / NACK (201) received from the terminal. The base station (210) can perform link adaptation to select an MCS (212) for the terminal based on the estimated SINR probability distribution (211). The estimation of the SINR probability distribution (211) and the selection of the MCS can utilize, for example, the well-known Thompson sampling method. However, in the case of the link adaptation method of Fig. 2, the SINR for the terminal cannot be accurately estimated with only HARQ ACK / NACK (201) for PDSCH retransmission, and since link adaptation is performed only based on HARQ ACK / NACK (201), it may be difficult to update the SINR probability distribution using the terminal's channel state information such as CQI.

[0052] In the following embodiments of the present disclosure, a method is proposed in which an SINR probability distribution is estimated / updated at one side of a terminal or at both sides of a terminal and a base station, and an optimal MCS for a terminal is selected at a base station based on the estimated / updated SINR probability distribution (i.e., an SINR representative value in the estimated / updated SINR probability distribution). An SINR representative value that estimates the channel status of the terminal can be determined from the SINR probability distribution. For example, the SINR representative value can use an average value in the SINR probability distribution. The SINR probability distribution can be estimated by using a method in which an artificial intelligence (AI)-based SINR model is updated whenever a terminal receives a PDSCH signal and / or a CSI-RS from a base station. In addition, the SINR probability distribution can be estimated by using a method in which an AI-based SINR model is updated whenever a base station receives a HARQ ACK / NACK and / or an SINR difference value, which will be described later, from a terminal. Based on the SINR probability distribution estimated at the terminal and / or the base station, the base station can select the highest MCS level that satisfies the target BLER as the optimal MCS level using the BLER curve, or can select the MCS corresponding to the effective SINR as the optimal MCS level using table information indicating the mapping relationship between SINR and MCS, and through this, the base station can improve link adaptation performance (e.g., user perceived throughput).

[0053] FIG. 3 is a diagram conceptually illustrating a method for a terminal to estimate an SINR probability distribution in a wireless communication system according to an embodiment of the present disclosure.

[0054] Referring to FIG. 3, the terminal can estimate the SINR probability distribution based on whether the decoding of the PDSCH signal (301) received from the base station is successful (303). As an optional embodiment, in the present disclosure, the terminal can calculate the difference value (SINR Diff. A) (hereinafter referred to as the first SINR difference) between the SINR value of the initially transmitted PDSCH signal and the SINR value of the retransmitted PDSCH signal, and estimate the SINR probability distribution based on the first SINR difference (303). The base station can receive information on the HARQ ACK / NACK and / or the first SINR difference for the PDSCH from the terminal, and select an MCS for the terminal based on the received information.

[0055] In addition, as an optional embodiment, in the present disclosure, the terminal can estimate the SINR probability distribution based on the CSI-RS (302) received from the base station (303). The terminal can transmit the SINR difference (SINR Diff. B) (hereinafter referred to as the second SINR difference) between the SINR representative value of the estimated SINR probability distribution and the effective SINR value calculated from the received CSI-RS to the base station (305). The SINR representative value can use, for example, a mean value, a median value, etc. A specific method for determining the SINR representative value from the SINR probability distribution (i.e., SINR sampling policy) will be described later. As an optional embodiment, in the present disclosure, the terminal can extract the SINR representative value from the estimated SINR probability distribution and transmit the CQI corresponding to the SINR representative value to the base station (304). Here, the CQI transmitted to the base station is not directly estimated from the CQI measured by the CSI-RS, but is estimated based on the SINR probability distribution obtained through AI-based SINR model learning, and thus can be understood as AI-based (enhanced) CQI. In the present disclosure, the base station receives HARQ ACK / NACK for PDSCH from the terminal, AI-based CQI received from the terminal, and / or information on the second SINR difference, and can select an MCS for the terminal based on the received information.

[0056] In the present disclosure, the AI-based channel information reported by the terminal to the base station may include at least one of information regarding the first SINR difference and information regarding the second SINR difference. The information regarding the first SINR difference and the information regarding the second SINR difference may be values ​​representing the difference values ​​or predetermined indices corresponding to the difference values, respectively.

[0057] Additionally, in the present disclosure, the terminal transmits information on a preferred SINR representative value selection method to the base station, and the base station can determine the SINR representative value selection method (i.e., SINR sampling method).

[0058] FIG. 4a is a diagram illustrating a method for estimating an SINR probability distribution when decoding of a PDSCH is successful in a terminal according to an embodiment of the present disclosure, and FIG. 4b is a diagram illustrating a method for estimating an SINR probability distribution when decoding of a PDSCH is unsuccessful in a terminal according to an embodiment of the present disclosure.

[0059] In the present disclosure, a terminal can estimate an SINR probability distribution based on whether or not the decoding of a received PDSCH is successful. The SINR probability distribution has a probability value between [0, 1] for discrete SINR values, and means an array of values ​​where the sum of the probability values ​​is 1. The SINR probability distribution can be updated to a new SINR probability distribution by multiplying an existing probability distribution by a weight function (i.e., an array that can have different weights for each SINR bin).

[0060] In the present disclosure, the update of the SINR probability distribution may be referred to as the update of the SINR model. For example, the SINR probability distribution may be updated using Bayes' theorem, and at this time, the MCS level of the PDSCH and whether the decoding of the PDSCH is successful may be used as inputs for updating the SINR model, which is an AI model. Updating the SINR probability distribution using the Bayes' theorem may be expressed as in [Mathematical Formula 1] below. In [Mathematical Formula 1] below, "Prior" is the prior probability of the SINR probability distribution when the previously estimated SINR is θ=x, and "Likelihood" is the MCS level (a) of the PDSCH. t ) and PDSCH decoding result (y t) is a weight function that is an element-wise product of the above prior probability, and "Posterior" is the MCS level (a) of the PDSCH. t ) and PDSCH decoding result (y t ) represents the posterior probability of the SINR probability distribution updated according to [Mathematical Equation 1]. And "Marginal" is a term for normalization so that the sum of the probability values ​​of [Mathematical Equation 1] becomes 1.

[0061]

[0062] In the present disclosure, for example, if PDSCH decoding is successful, the weight function can be determined as a 1-BLER curve corresponding to the MCS of the received PDSCH, and an element-wise product can be performed with the SINR probability distribution of the previous time point to obtain a new SINR probability distribution of the current time point. If PDSCH decoding fails, the weight function can be determined as a BLER (block error rate) curve corresponding to the MCS of the received PDSCH, and an element-wise product can be performed with the existing SINR probability distribution to obtain a new, updated SINR probability distribution.

[0063] Specifically, referring to FIG. 4a, when the decoding of the PDSCH in the terminal is successful, the SINR probability distribution of the previous time point (t-1), SINR[t-1](401), may be multiplied by a weight (402) having, for example, a value of the (1-BLER) curve (element-wise product) to calculate the updated SINR probability distribution of the current time point (t), SINR[t](403). Referring to FIG. 4b, when the decoding of the PDSCH in the terminal is unsuccessful, the SINR probability distribution of the previous time point (t-1), SINR[t-1](411), may be multiplied by a weight (412) having, for example, a value of the BLER curve (element-wise product) to calculate the updated SINR probability distribution of the current time point (t), SINR[t](413). As shown in SINR[t](403, 413), which is an updated SINR probability distribution in FIGS. 4a and 4b, when PDSCH decoding is successful, the average of the SINR[t](403) curve shifts to the right where the SINR is higher than the average of the SINR probability distribution at the previous time point (t-1), and when PDSCH decoding fails, the average of the SINR[t](413) curve shifts to the left where the SINR is lower than the average of the SINR probability distribution at the previous time point (t-1).

[0064] In the examples of FIGS. 4A and 4B, "BLER" is a BLER curve corresponding to the MCS of the PDSCH received by the terminal, and BLER curves exist for each MCS level. For example, if there are A MCS levels, there are A BLER curves. Therefore, a (1-BLER) curve also exists for each MCS level. In addition, the BLER curve refers to a function having a BLER value with a real value in the range of [0, 1] for discrete SINR values, and the (1-BLER) curve refers to a function obtained by subtracting the BLER value for discrete SINR values ​​from 1. The BLER curve can be obtained through various methods, such as using a predefined BLER curve table stored in advance in the terminal, using a predefined BLER curve table received by the terminal from a base station, or using a BLER curve table generated by the terminal as a result of PDSCH decoding.

[0065] In the present disclosure, the terminal can extract SINR representative values ​​(e.g., average SINR, median SINR, etc.) from the updated SINR probability distribution based on the PDSCH decoding result (success or failure), and transmit the CQI derived from the extracted SINR representative value to the base station for link adaptation. In addition, in the present disclosure, the terminal can calculate the CQI from the learned SINR probability distribution to report a more accurate CQI, and can report the CQI using the decoding result when receiving the PDSCH regardless of the CSI-RS cycle, thereby solving the outdated CQI problem.

[0066] In addition, in the embodiment of the present disclosure, the SINR probability distribution (or SINR representative value) used for link adaptation can be updated / learned using not only the PDSCH decoding result, as in the embodiments of FIGS. 5 to 7 described later, but also the difference between the SINR at the time of the initial PDSCH transmission and the SINR at the time of the PDSCH retransmission, or the difference in the SINR between the PDSCH retransmissions.

[0067] In addition, in the embodiment of the present disclosure, the SINR probability distribution update (i.e., SINR model update) for link adaptation may be performed on one side of the terminal, as in the embodiments of FIGS. 6 to 9, or may be performed on both sides of the terminal and the base station, respectively. In the present disclosure, the SINR probability distribution update may be performed using the difference between the SINR value of the initially transmitted PDSCH signal and the SINR value of the retransmitted PDSCH signal (i.e., the first SINR difference) as described above, or may be performed using the SINR difference between the SINR representative value of the SINR probability distribution updated according to the PDSCH decoding result and the effective SINR value calculated from the CSI-RS received by the terminal (i.e., the second SINR difference).

[0068] FIG. 6 is a diagram illustrating an example of an AI-based link adaptation method utilizing a first SINR difference in a wireless communication system according to an embodiment of the present disclosure. FIG. 6 illustrates a case where the first SINR difference is utilized in link adaptation, but SINR probability distribution updates (SINR model updates) for the link adaptation are performed on both sides of the terminal and the base station.

[0069] Referring to FIG. 6, at step 600, negotiations may be performed between the terminal and the base station to determine a SINR representative value selection method. The SINR representative value may be, for example, the mean value, median value, or N-percentile value (e.g., N%) of the SINR probability distribution. The specific negotiation method will be described later. As an optional embodiment, if a predetermined method is used between the terminal and the base station as the SINR representative value selection method, step 600 may be omitted.

[0070] In step 601, the terminal may receive configuration information (hereinafter, configuration information for AI-based link adaptation) related to the SINR probability distribution update (SINR model update), AI-based CQI transmission, acquisition method / reporting type / reporting cycle / reporting method of the first SINR difference and / or the second SINR difference for additional update of the SINR model, etc., from the base station. [Table 1] below shows an example of the configuration of information included in the configuration information, and at least one of the plurality of pieces of information exemplified in [Table 1] below may be included in the configuration information for AI-based link adaptation. When a predetermined method is used as the SINR representative value selection method in step 600, the "SINR Representative Selection Scheme" information in [Table 1] below may be omitted. In [Table 1] below, "SINR Bins" refer to, for example, bins at which probability distribution values ​​of SINR are displayed from a minimum of -10 dB to a maximum of 30 dB, as reference numeral 401 of FIG. 4a. As an optional embodiment, the configuration information for the AI-based link adaptation may be provided to the terminal through at least one combination of RRC information, MAC-CE (MAC Control Element), and DCI (Downlink Control Information).

[0071]

[0072] In step 602, the terminal receives a PDSCH transmission carrying downlink data from the base station, and in step 603, the terminal can update the SINR model based on the PDSCH decoding result, as described in FIGS. 3 to 4b. That is, the terminal can obtain an updated SINR probability distribution (i.e., an updated SINR model) at the current time by applying / multiplying a weight based on the PDSCH decoding result to the SINR probability distribution at the previous time. The SINR model corresponds to an AI model, and initial configuration information of the SINR model can be provided from the base station through configuration information for the AI-based link adaptation. The input of the SINR model is the decoding result of the PDSCH signal, and the output can be an updated SINR probability distribution (or an updated SINR representative value) for link adaptation according to the decoding result of the PDSCH signal.

[0073] In step 604, the terminal transmits a HARQ ACK / NACK to the base station as a reception response to the PDSCH transmission in step 602. In step 605, the base station can update the SINR model based on the received HARQ ACK / NACK. The SINR model update at the base station can also be performed by applying the method described in FIGS. 3 to 4b. In this case, reception of a HARQ ACK corresponds to successful PDSCH decoding, and reception of a HARQ NACK corresponds to a failure in PDSCH decoding. The terminal and the base station can initiate SINR model update using the same initial SINR model through initial configuration information, or can initiate SINR model update using different initial SINR models.

[0074] In the example of Fig. 6, it is assumed that the base station receives a HARQ NACK from the terminal in step 604. In this case, the base station performs a PDSCH retransmission to the terminal in step 606.

[0075] In step 607, the terminal that receives the PDSCH retransmission from the base station calculates / obtains the difference (i.e., the first SINR difference) between the SINR value of the PDSCH signal initially transmitted in step 602 and the SINR value of the PDSCH signal retransmitted in step 606. The first SINR difference may be, for example, (DMRS-SINR of the nth (re)transmitted PDSCH) - (DMRS-SINR of the initially transmitted PDSCH) or (DMRS-SINR of the initially transmitted PDSCH) - (DMRS-SINR of the nth (re)transmitted PDSCH) or (DMRS-SINR of the nth retransmitted PDSCH) - (DMRS-SINR of the n-1th PDSCH).

[0076] In step 608, the terminal can update the SINR model based on the decoding result of the PDSCH retransmission and / or the first SINR difference. The SINR model update operation in step 608 will be described with reference to FIG. 5.

[0077] FIG. 5 is a diagram illustrating a method for updating an SINR model when decoding of a PDSCH retransmission signal fails in a terminal according to an embodiment of the present disclosure. FIG. 5 compares, as an example, an SINR model (SINR probability distribution) update when decoding of a PDSCH initial transmission signal fails and an SINR model (SINR probability distribution) update when decoding of a PDSCH retransmission signal fails.

[0078] Referring to FIG. 5, when decoding of PDSCH initial transmission fails, the terminal may calculate SINR[t](503), which is an updated SINR probability distribution of the current time point (t), by multiplying SINR[t-1](501), which is an SINR probability distribution of the previous time point (t-1), by a weight (502) having a value of a BLER curve (element-wise product). Thereafter, when decoding of PDSCH retransmission fails, the terminal may calculate SINR[t](505), which is an updated SINR probability distribution of the current time point (t), by multiplying SINR[t-1](501), which is an SINR probability distribution of the previous time point (t-1), by a weight (504) having a value of a shifted BLER curve shifted to the left by a shifting offset (element-wise product). Here, the shifting offset may be determined based on the first SINR difference. The reason for multiplying (element-wise product) the weight (504) having the value of the shifted BLER curve shifted to the left by the shifting offset in the present disclosure is that the block error probability for the retransmitted TB (transport block) at the same SINR is lower than that of the initially transmitted TB by HARQ soft combining. Therefore, by shifting the weight (504) by the SINR gain used for soft combining of the retransmitted TB, over-estimation of the SINR probability distribution can be prevented, thereby improving the accuracy of the SINR probability distribution estimation. For example, if the first SINR difference between the initially transmitted PDSCH and the retransmitted PDSCH is 0 dB, the shifting offset can be calculated as 3 dB because the SINR gain is doubled.If decoding of a retransmitted TB fails as described above, the average of the SINR probability distribution can be shifted toward a faster decrease. Although not illustrated in Fig. 5, if decoding of a retransmitted TB is successful, the average of the SINR probability distribution can be shifted toward a slower increase, similar to the example of Fig. 4a, to prevent overestimation of the SINR probability distribution.

[0079] Thereafter, in step 609, the terminal transmits to the base station a HARQ ACK / NACK as a reception response to the PDSCH retransmission and the first SINR difference obtained in step 607. The first SINR difference may be transmitted using method 1-1 or method 1-2 below.

[0080] - Method 1-1: At least one of the following methods: a method of sending ACK / NACK simultaneously using the Long PUCCH format, a method of transmitting the SINR difference value at the discrete level, a static method, or a semi-static method (activation through RRC setting + DCI).

[0081] - Method 1-2: Method of transmitting using PUSCH allocated to the terminal

[0082] In step 610, the base station can update the SINR model based on the difference between the received HARQ ACK / NACK and the first SINR. The SINR model update at the base station can also be performed using the method described in step 608 and the example of FIG. 5 .

[0083] In step 611, the base station can select a representative SINR value from the SINR model (SINR probability distribution) updated in step 610 and select the maximum / optimal MCS that satisfies the target BLER. Then, in step 612, the base station can perform PDSCH transmission to the terminal based on the selected MCS for link adaptation. In the example of Fig. 6, a method of updating the SINR model based on AI is exemplified at both the terminal and the base station. However, as an optional embodiment, the base station can perform link adaptation using the existing method (non-AI method) described in Fig. 1 without updating the SINR model based on AI. In this case, the base station can perform link adaptation by receiving a CQI from the terminal.

[0084] FIG. 7 is a diagram illustrating an example of an AI-based link adaptation method utilizing a first SINR difference in a wireless communication system according to an embodiment of the present disclosure. FIG. 7 illustrates a case where the first SINR difference is utilized in link adaptation, but an SINR probability distribution update (SINR model update) for the link adaptation is performed on one terminal side.

[0085] In the example of FIG. 7, the operations of steps 700 to 703, in which the terminal receives the PDSCH initial transmission from the base station and updates the SINR model, are identical to the operations of steps 600 to 603 in the example of FIG. 6, and therefore a detailed description thereof will be omitted. In the example of FIG. 7, it is assumed that the base station receives a HARQ NACK for the PDSCH initial transmission from the terminal. In this case, in step 704, the base station performs a PDSCH retransmission to the terminal. Thereafter, the operations of steps 705 and 706, in which the terminal obtains the aforementioned first SINR difference and updates the SINR model based on the decoding result for the PDSCH retransmission and the first SINR difference, are identical to the operations of steps 607 and 608 in the example of FIG. 6, and therefore a detailed description thereof will be omitted.

[0086] In step 707, the terminal selects a CQI corresponding to the SINR representative value of the SINR probability distribution (SINR model) updated in step 706, and transmits the selected CQI to the base station as an AI-based (enhanced) CQI in step 708. The CQI selected in step 707 is not a CQI estimated from the measurement result of the CSI-RS as in the conventional method, but is selected based on the SINR probability distribution obtained according to AI-based SINR model learning. In step 709, the base station may select the highest MCS level that satisfies the target BLER using the BLER curve, or may select an MCS corresponding to the effective SINR using table information indicating the mapping relationship between SINRs and MCSs. In step 710, the base station may perform PDSCH transmission to the terminal based on the selected MCS for link adaptation.

[0087] In the embodiments of FIGS. 6 and 7, for convenience, a method for performing SINR model update is described by exemplifying a single PDSCH retransmission, but multiple PDSCH retransmissions may be performed depending on the channel status of the terminal, and SINR model update may be performed for each PDSCH retransmission according to the method described in the embodiments of FIGS. 6 and 7.

[0088] FIG. 8 is a diagram illustrating an example of an AI-based link adaptation method using a second SINR difference in a wireless communication system according to an embodiment of the present disclosure. FIG. 8 illustrates a case where a second SINR difference is used in link adaptation, and an SINR probability distribution update (SINR model update) for the link adaptation is performed on both sides of a terminal and a base station. The second SINR refers to the SINR difference between the SINR representative value of the SINR probability distribution updated at the terminal according to the PDSCH decoding result as described above and the effective SINR value calculated from the CSI-RS received by the terminal.

[0089] In the example of FIG. 8, the operations of steps 800 to 805, in which the terminal updates the SINR model by receiving the PDSCH initial transmission from the base station, and the base station updates the SINR model by receiving the HARQ-ACK / NACK for the PDSCH initial transmission from the terminal, are identical to the operations of steps 600 to 605 in the example of FIG. 6, and therefore, a detailed description thereof will be omitted.

[0090] Thereafter, in step 806, the terminal can receive CSI-RS from the base station periodically or aperiodically. In step 807, the terminal that received the CSI-RS can obtain a second SINR difference based on the CSI-RS measurement result. The second SINR difference refers to the SINR difference between the SINR representative value of the SINR probability distribution updated in step 803 and the effective SINR value calculated / measured from the CSI-RS received by the terminal in step 806. The second SINR difference can be, for example, (average SINR calculated from the SINR probability distribution of the terminal) - (effective SINR calculated from the CSI-RS) or (effective SINR calculated from the CSI-RS) - (average SINR calculated from the SINR probability distribution of the terminal). In this case, the effective SINR value calculated from the CSI-RS can be obtained through a post-processing process using a Precoding Matrix Indicator (PMI), a Rank Indicator (RI), etc. from the SINR measured by the CSI-RS.

[0091] In step 808, the terminal can update the SINR probability distribution (SINR model) based on the second SINR difference. For example, the terminal can update the SINR probability distribution by shifting the SINR probability distribution by the second SINR difference. In this case, the shifting method shifts the SINR probability distribution to the right by the second SINR difference when the effective SINR calculated from the CSI-RS is greater than (or greater than or equal to) the average SINR calculated from the SINR probability distribution of the terminal, and shifts the SINR probability distribution to the left by the second SINR difference when the effective SINR calculated from the CSI-RS is less than (or less than or equal to) the average SINR calculated from the SINR probability distribution of the terminal. Through this, the terminal can update the SINR probability distribution through periodic / aperiodic CSI-RS even when there is no PDSCH data reception.

[0092] Thereafter, in step 809, the terminal transmits the second SINR difference obtained in step 807 to the base station. The second SINR difference can be transmitted using method 2-1 or method 2-2 below.

[0093] - Method 2-1: Transmitting the SINR difference B by including it in the existing CSI report (PUCCH or PUSCH)

[0094] - Method 2-2: It can be defined as a new field in reportQuantity of CSI-ReportConfig in 3GPP standard, it can be defined as when only the second SINR difference is transmitted (ex. cri-RI-PMI-DiffB, cri-RI-i1-DiffB, cri-RI-DiffB, cri-RI-LI-PMI-DiffB), and it can be defined as when CQI and the second SINR difference are transmitted simultaneously (ex. cri-RI-PMI-CQI-DiffB, cri-RI-i1-CQI-DiffB, cri-RI-CQI-DiffB, cri-RI-LI-PMI-CQI-DiffB), where DiffB means the second SINR difference.

[0095] In step 810, the base station can update the SINR model based on the received second SINR difference. The SINR model update (shift) at the base station can also be performed by applying the method described in step 808. In step 811, the base station can select an SINR representative value from the SINR model (SINR probability distribution) updated (shifted) in step 810 and select the maximum / optimal MCS that satisfies the target BLER. Then, in step 812, the base station can perform PDSCH transmission to the terminal based on the selected MCS for link adaptation.

[0096] FIG. 9 is a diagram illustrating an example of an AI-based link adaptation method utilizing a second SINR difference in a wireless communication system according to an embodiment of the present disclosure. FIG. 9 illustrates a case where the second SINR difference is utilized in link adaptation, but an SINR probability distribution update (SINR model update) for the link adaptation is performed on one terminal side.

[0097] In the example of FIG. 9, the operations of steps 900 to 903, in which the terminal receives a PDSCH initial transmission from the base station and updates the SINR model, are identical to the operations of steps 800 to 803 in the example of FIG. 8, and thus a detailed description thereof will be omitted. In addition, in the example of FIG. 9, the operations of steps 904 to 906, in which the terminal receives a CSI-RS from the base station and obtains a second SINR difference and updates the SINR model, are identical to the operations of steps 806 to 808 in the example of FIG. 8, and thus a detailed description thereof will be omitted.

[0098] In step 907, the terminal selects a CQI corresponding to the SINR representative value of the SINR probability distribution (SINR model) updated (shifted) in step 906, and transmits the selected CQI to the base station as an AI-based (enhanced) CQI in step 908. The CQI selected in step 907 is not a CQI directly estimated from the measurement result of the CSI-RS as in the conventional method, but is a CQI selected based on the updated (shifted) SINR probability distribution according to AI-based SINR model learning. In step 909, the base station may select the highest MCS level that satisfies the target BLER using the BLER curve, or may select an MCS corresponding to the effective SINR using table information indicating the mapping relationship between SINRs and MCSs. In step 910, the base station may perform PDSCH transmission to the terminal based on the selected MCS for link adaptation. The embodiments of FIGS. 8 and 9 described above can be performed, for example, when the traffic transmitted to the terminal is small and PDSCH decoding is not frequently performed at the terminal.

[0099] FIG. 10 is a diagram illustrating a SINR representative value selection method negotiation method performed between a terminal and a base station according to an embodiment of the present disclosure. The method of FIG. 10 may be performed at reference numbers 600, 700, 800, and 900 in the embodiments of FIGS. 6 to 9. However, the SINR representative value selection method negotiation method of FIG. 10 is not limited to the above reference numbers 600, 700, 800, and 900, and may be performed at any step among the steps of the AI-based link adaptation method of FIGS. 6 to 9.

[0100] Referring to FIG. 10, in step 1001, the base station may provide the terminal with configuration information (e.g., RRC information) on a SINR representative value selection method. The configuration information may include, for example, at least one of information on a mean method that selects an average value from an SINR probability distribution as an SINR representative value, and an N-percentile method (e.g., 35%, 40%, 45%, 50% (=median), 55%, 60%, 65%) that selects a value corresponding to a specified percentage from an SINR probability distribution as an SINR representative value. Here, the mean is the expected value of the probability distribution. N-percentile means an N% quantile, so that 50% corresponds to the median of the probability distribution. In step 1002, the terminal may identify a preferred method among the SINR representative value selection methods(s) identified in the configuration information, and transmit information on the preferred SINR representative value selection method to the base station in step 1003. At this time, the terminal can determine a preferred SINR representative value selection method based on context information and transmit it to the base station. In the present disclosure, since the terminal learns the SINR probability distribution, it must be able to select one SINR representative value from the learned SINR probability distribution in order to report channel information based on this. In the present disclosure, SINR sampling refers to selecting a representative value from the SINR probability distribution. As an optional embodiment, information on the preferred SINR representative value selection method in step 1003 may be included in UEAssistanceInformation that the terminal transmits to the base station in the 3GPP standard.

[0101] In step 1004, the base station may determine an SINR representative value selection method to be applied to the terminal by considering the SINR representative value selection method preferred by the terminal, and may provide the terminal with configuration information (e.g., RRC information) regarding the determined SINR representative value selection method in step 1005. As an optional embodiment, in step 1004, the base station may determine the SINR representative value selection method preferred by the terminal as the SINR representative value selection method to be applied to the terminal, or the base station may arbitrarily determine one of the SINR representative value selection methods included in the configuration information in step 1001.

[0102] In actual wireless communication systems, the preferred SINR representative value selection method may vary depending on the application characteristics of the terminal. Since this is a context difficult for the base station to understand, the terminal's preferred SINR representative value selection method can be recommended, as shown in the example of Figure 10. For example, the following cases recommend an aggressive SINR representative value selection method: For latency-insensitive traffic, selecting a high SINR representative value may be advantageous in determining a high MCS. Furthermore, selecting a high SINR representative value may also be advantageous in cases where inter-cell interference fluctuates significantly. In this case, the terminal may recommend an N-percentile method of 50% or higher to the base station. The following cases recommend a conservative SINR representative value selection method: For latency-critical traffic, selecting a low SINR representative value may be advantageous in determining a low MCS. In this case, the terminal may recommend an N-percentile method of 50% or less to the base station.

[0103] FIG. 11 is a diagram illustrating an example of an AI-based link adaptation method using a first SINR difference and a second SINR difference in a wireless communication system according to an embodiment of the present disclosure.

[0104] Referring to FIG. 11, negotiations may be performed between a terminal and a base station at step 1101 to determine a SINR representative value selection method. Step 1101 may be performed in the same manner as the method of FIG. 10. As an optional embodiment, step 1101 may be omitted when a predetermined method is used between the terminal and the base station as the SINR representative value selection method.

[0105] In step 1102, an SINR model update procedure using the first SINR difference described above may be performed on both terminal and base station sides or on one terminal side. The SINR model update procedure in step 1102 may be performed using the embodiment of FIG. 6 or FIG. 7.

[0106] In step 1103, an SINR model update procedure utilizing the aforementioned second SINR difference may be performed on both the terminal and the base station or on one side of the terminal. The SINR model update procedure in step 1103 may be performed using the embodiment of FIG. 8 or FIG. 9.

[0107] In step 1104, the base station may select a representative SINR value and use the BLER curve to select the highest MCS level that satisfies the target BLER, or may use table information indicating the mapping relationship between SINR and MCS to select an MCS corresponding to the effective SINR. In step 1105, the base station may perform PDSCH transmission to the terminal based on the selected MCS for link adaptation.

[0108] According to the embodiments of the present disclosure described above, the terminal can estimate the SINR probability distribution based on AI, and the base station can select the optimal MCS based on the SINR probability distribution, thereby improving link adaptation performance.

[0109] FIG. 12 is a diagram showing an example configuration of a network entity in a wireless communication system according to an embodiment of the present disclosure.

[0110] The network entity of FIG. 12 may be one of the terminals and base stations described in the embodiments of FIGS. 1 to 11 described above. The network entity of FIG. 12 may include a processor (1201), a transceiver (1203), and a memory (1205). The processor (1201), the transceiver (1203), and the memory (1205) of the network entity may operate according to the communication methods described in the embodiments of FIGS. 1 to 11. However, the components of the network entity are not limited to the examples described above. For example, the network entity may include more or fewer components than the components described above. In addition, the processor (1201), the transceiver (1203), and the memory (1205) may be implemented in the form of a single chip.

[0111] The transceiver (1203) is a general term for a network entity's receiver and a network entity's transmitter, and can transmit and receive signals with a counterpart network entity. At this time, the transmitted and received signals may include at least one of control information and data. In addition, the transceiver (1203) may receive a signal, output it to the processor (1201), and transmit the signal output from the processor (1201). In addition, the transceiver (1203) of FIG. 12 may include an RF transmitter that up-converts and amplifies the frequency of a transmitted signal, and an RF receiver that low-noise amplifies and frequency-downconverts the received signal. In addition, the transceiver (1203) may receive a signal, output it to the processor (1201), and transmit the signal output from the processor (1201) to the counterpart network entity through the network. The memory (1205) can store programs and data required for the operation of a network entity according to at least one of the embodiments of FIGS. 1 to 11. In addition, the memory (1205) can store control information or data included in a signal acquired from the network entity. The memory (1205) can be configured as a storage medium or a combination of storage media, such as a ROM, a RAM, a hard disk, a CD-ROM, and a DVD.

[0112] In addition, the processor (1201) may control a series of processes so that the network entity can operate according to at least one of the embodiments of FIGS. 1 to 11. The processor (1201) may include at least one processor. The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software. In the case of software implementation, a computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors in an electronic device. The one or more programs include instructions that cause the electronic device to execute the methods according to the embodiments described in the claims or specification of the present disclosure.

[0113] These programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic disc storage devices, compact disc-ROMs (CD-ROMs), digital versatile discs (DVDs) or other forms of optical storage devices, magnetic cassettes, or may be stored in memories formed by a combination of some or all of these. In addition, each configuration memory may include multiple copies. The above program may be stored on an attachable storage device that is accessible via a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a storage area network (SAN), or a combination thereof. This storage device may be connected to a device performing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device performing an embodiment of the present disclosure.

[0114] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed in the singular or plural form, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in the plural form may be composed of singular elements, or components expressed in the singular form may be composed of plural elements.

[0115] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims described below, but also by equivalents thereof.

Claims

1. A method performed at a terminal for link adaptation in a wireless communication system, A process in which a terminal receives configuration information for AI (artificial intelligence)-based link adaptation from a base station; A process in which the terminal receives a PDSCH (physical downlink shared channel) transmission from the base station; and A method including a process of first updating a SINR (signal to noise and interference ratio) model related to the AI-based link adaptation based on the decoding result of the PDSCH transmission by the terminal.

2. In paragraph 1, A method for updating the SINR model, the method including the first process of updating the SINR model with the updated SINR probability distribution at the current time by applying a weight based on the PDSCH decoding result to the SINR probability distribution at the previous time.

3. In paragraph 1, The above setting information is, Method for setting SINR representative value of SINR probability distribution corresponding to the above SINR model, Information on at least one of the acquisition method, reporting type, reporting cycle, and reporting method of at least one SINR difference for additional update of the above SINR model, Information about the update-related weights of the above SINR model, A method including at least one piece of information indicating whether to report a channel quality indicator (CQI) based on the SINR model.

4. In paragraph 1, A process of receiving a PDSCH retransmission from the base station when the decoding result of the above PDSCH transmission is a failure; A process of obtaining a first SINR difference representing the difference between the SINR value of the received PDSCH transmission and the SINR value of the received PDSCH retransmission; A process of updating the SINR model a second time using weights applied with a shifted BLER (block error rate) curve based on the first SINR difference; The process of transmitting the first SINR difference to the base station; and A method further comprising the step of receiving a PDSCH transmission to which a modulation and coding scheme (MCS) for AI-based link adaptation is applied based on the first SINR difference from the base station.

5. In paragraph 1, A process of receiving a CSI-RS (channel state information-reference signal) from the above base station; A process of obtaining a second SINR difference representing the difference between the SINR representative value of the updated SINR probability distribution according to the PDSCH decoding result of the received PDSCH transmission and the effective SINR value calculated from the received CSI-RS; A process of updating the SINR model a second time by shifting the SINR probability distribution to the right by the second SINR difference when the effective SINR value is greater than the SINR representative value; A process of updating the SINR model a second time by shifting the SINR probability distribution to the left by the second SINR difference when the effective SINR value is smaller than the SINR representative value; The process of transmitting the second SINR difference to the base station; and A method further comprising the step of receiving a PDSCH transmission to which a modulation and coding scheme (MCS) for AI-based link adaptation is applied based on the second SINR difference from the base station.

6. In paragraph 1, A process of receiving setting information for at least one SINR representative value selection method from the above base station; A process of transmitting information about a preferred method among the above at least one SINR representative value selection method to the base station; and A method further comprising the step of receiving information on a method for selecting a SINR representative value to be applied to the terminal from the base station.

7. In a wireless communication system, at the terminal, Transmitter and receiver; and Through the above transceiver, setting information for AI (artificial intelligence)-based link adaptation is received from the base station, Through the above transceiver, the terminal receives a PDSCH (physical downlink shared channel) transmission from the base station, A terminal including a processor configured to first update a signal to noise and interference ratio (SINR) model related to the AI-based link adaptation based on a decoding result of the PDSCH transmission.

8. In paragraph 7, The above processor is a terminal configured to first update the SINR model by applying a weight based on the PDSCH decoding result to the SINR probability distribution of the previous point in time.

9. In paragraph 7, The above setting information is, Method for setting SINR representative value of SINR probability distribution corresponding to the above SINR model, Information on at least one of the acquisition method, reporting type, reporting cycle, and reporting method of at least one SINR difference for the second update of the above SINR model, Information about the update-related weights of the above SINR model, A terminal including at least one piece of information indicating whether to report a CQI (channel quality indicator) based on the above SINR model.

10. In paragraph 7, The above processor, If the decoding result of the above PDSCH transmission is a failure, a PDSCH retransmission is received from the base station through the transceiver, Obtaining a first SINR difference representing the difference between the SINR value of the received PDSCH transmission and the SINR value of the received PDSCH retransmission, The SINR model is updated a second time using weights applied with a shifted BLER (block error rate) curve based on the first SINR difference, Through the above transceiver, the first SINR difference is transmitted to the base station, A terminal further configured to receive a PDSCH transmission to which a modulation and coding scheme (MCS) for AI-based link adaptation is applied based on the first SINR difference from the base station through the transceiver.

11. In paragraph 7, The above processor, Receive CSI-RS (channel state information-reference signal) from the above base station through the above transceiver, Obtain a second SINR difference representing the difference between the SINR representative value of the updated SINR probability distribution according to the PDSCH decoding result of the received PDSCH transmission and the effective SINR value calculated from the received CSI-RS, If the effective SINR value is greater than the SINR representative value, the SINR probability distribution is shifted to the right by the second SINR difference to update the SINR model for the second time. If the effective SINR value is smaller than the SINR representative value, the SINR probability distribution is shifted to the left by the second SINR difference to update the SINR model a second time. Through the above transceiver, the second SINR difference is transmitted to the base station, A terminal further configured to receive a PDSCH transmission to which a modulation and coding scheme (MCS) for AI-based link adaptation is applied based on the second SINR difference from the base station through the transceiver.

12. In paragraph 7, The above processor, Receive setting information for at least one SINR representative value selection method from the above base station through the above transceiver, Through the above transceiver, information on a preferred method among the at least one SINR representative value selection method is transmitted to the base station, A terminal further configured to receive information about a SINR representative value selection method to be applied to the terminal from the base station through the transceiver.

13. A method performed at a base station for link adaptation in a wireless communication system, A process of transmitting configuration information for AI (artificial intelligence)-based link adaptation to a terminal; A process of transmitting at least one of a PDSCH (physical downlink shared channel) signal and a CSI-RS (channel state information-reference signal) to the terminal; A process of receiving at least one of a first SINR difference and a second SINR difference related to an update of a SINR (signal to noise and interference ratio) model related to the AI-based link adaptation from the terminal; and A method including a process of selecting an MCS (modulation and coding scheme) to be applied to a PDSCH (physical downlink shared channel) transmission to the terminal based on at least one of the first SINR difference and the second SINR difference.

14. In paragraph 13, The above first SINR difference represents the difference between the SINR value of the initial PDSCH transmission to the terminal and the SINR value of the PDSCH retransmission, The above second SINR difference is a method of representing the difference between the SINR representative value of the SINR probability distribution updated according to the PDSCH decoding result of the PDSCH signal and the SINR value based on the CSI-RS.

15. In a base station in a wireless communication system, Transmitter and receiver; and Through the above transceiver, setting information for AI (artificial intelligence)-based link adaptation is transmitted to the terminal, Through the above transceiver, at least one of a PDSCH (physical downlink shared channel) signal and a CSI-RS (channel state information-reference signal) is transmitted to the terminal, Receive at least one of a first SINR difference and a second SINR difference related to an update of a SINR (signal to noise and interference ratio) model related to the AI-based link adaptation from the terminal through the transceiver, A base station including a processor configured to select an MCS (modulation and coding scheme) to be applied to a PDSCH (physical downlink shared channel) transmission to the terminal based on at least one of the first SINR difference and the second SINR difference.

Images