Method, base station, and user equipment for transmitting and receiving signals in wireless communication system

Abstract

A method and a device for transmitting and receiving signals in a wireless communication system are provided. The method and the device may comprise: training an artificial intelligence or machine learning-based model for channel estimation with a user equipment (UE); transmitting a plurality of parameters of the model to the UE; retraining the model on the basis that a predetermined condition related to life cycle management (LCM) of the model has been satisfied; and transmitting, to the UE, information on a parameter related to the retraining among the plurality of parameters.

Description

Method for transmitting and receiving signals in a wireless communication system, base station and user equipment

[0001] This specification relates to a wireless communication system, a method for transmitting and receiving signals, a base station, and user equipment.

[0002] As wireless communication technology advances, communication devices requiring high data rates are emerging and becoming widespread. As more communication devices demand greater capacity, the need for enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low latency communication (URLLC) is emerging.

[0003] Meanwhile, the introduction of artificial intelligence (AI) technology in wireless communication systems is expected to help support low-latency, low-complexity, and high-performance communication systems. To design communication systems that take into account latency-sensitive services and / or communication devices, AI-based communication technologies that achieve system optimization are key issues to consider in next-generation communications.

[0004] With the introduction of new wireless communication technologies, the amount of data and / or control information transmitted and received by communication devices is increasing. Since the amount of radio resources available for communication is finite, new methods are needed to enable base stations and / or user devices in wireless communication systems to efficiently utilize radio resources to transmit and receive data and / or control information.

[0005] The technical tasks to be achieved by this specification are not limited to the technical tasks mentioned above, and other technical tasks not mentioned will be clearly understood by those of ordinary skill in the art related to this specification from the detailed description below.

[0006] In one aspect of the present disclosure, a method for transmitting and receiving signals by a base station in a wireless communication system is provided. The method comprises: training an artificial intelligence or machine learning-based model for channel estimation with a user equipment (UE), transmitting a plurality of parameters of the model to the UE, retraining the model based on satisfying a predetermined condition related to Life Cycle Management (LCM) of the model, and transmitting parameter information related to the retraining among the plurality of parameters to the UE.

[0007] In another aspect of the present disclosure, a base station for transmitting and receiving signals in a wireless communication system is provided. The base station includes: at least one transceiver; at least one processor; and at least one computer memory operably connected to the at least one processor and storing instructions that, when executed, cause the at least one processor to perform operations. The operations include: training an artificial intelligence or machine learning-based model for channel estimation with a user equipment (UE), transmitting a plurality of parameters of the model to the UE, retraining the model based on satisfying a predetermined condition related to Life Cycle Management (LCM) of the model, and transmitting parameter information related to the retraining among the plurality of parameters to the UE.

[0008] In another aspect of the present disclosure, a method for a user equipment to transmit and receive signals in a wireless communication system is provided. The method comprises: determining an artificial intelligence or machine learning-based model for channel estimation with a base station, receiving a plurality of parameters of the model from the base station, and receiving parameter information related to retraining of the model among the plurality of parameters from the base station based on satisfying a predetermined condition related to Life Cycle Management (LCM) of the model.

[0009] In another aspect of the present disclosure, a user equipment for transmitting and receiving signals in a wireless communication system is provided. The user equipment includes: at least one transceiver; at least one processor; and at least one computer memory operably connected to the at least one processor and storing instructions that, when executed, cause the at least one processor to perform operations. The operations include: determining an artificial intelligence or machine learning-based model for channel estimation with a base station, receiving a plurality of parameters of the model from the base station, and receiving parameter information related to retraining of the model among the plurality of parameters based on satisfaction of a predetermined condition related to Life Cycle Management (LCM) of the model from the base station.

[0010] In each aspect of this specification, the predetermined condition associated with the LCM may include at least one of a beam change or a precoding change.

[0011] In each aspect of the present specification, retraining the model may be retraining a layer related to a predetermined condition that is satisfied among a plurality of layers of the model.

[0012] In each aspect of this specification, transmitting the parameter information may be performed based on receiving a request for the model from the UE.

[0013] Alternatively, transmitting the above parameter information may be performed based on a preset cycle.

[0014] In each aspect of the present specification, the parameter information may include index information for parameters related to the retraining based on a predetermined codebook for the plurality of parameters.

[0015] In each aspect of the present specification, storing the retrained model may be further included.

[0016] In each aspect of this specification, retraining the model may include receiving information that retrained the model from the UE or a UE other than the UE.

[0017] The above problem solving methods are only some of the examples of this specification, and various examples reflecting the technical features of this specification can be derived and understood by a person having ordinary knowledge in the relevant technical field based on the detailed description below.

[0018] According to an implementation(s) of this specification, a method for transmitting and receiving an artificial intelligence (AI) or machine learning (ML) based model in a wireless communication system is provided.

[0019] According to the implementation(s) of this specification, wireless communication signals can be transmitted and received efficiently. Accordingly, the overall throughput of the wireless communication system can be increased.

[0020] According to implementation(s) of this specification, delay / latency occurring during wireless communication can be reduced.

[0021] The effects obtained from the present invention may not be limited to the effects described above. Furthermore, other effects not mentioned can be clearly understood by those skilled in the art from the following description.

[0022] The accompanying drawings, which are included as part of the detailed description to aid in understanding implementations of this specification, provide examples of implementations of this specification and, together with the detailed description, serve to illustrate implementations of this specification.

[0023] Figure 1 illustrates the structure of a system for 5th generation (5G) communication.

[0024] FIG. 2 is a block diagram illustrating examples of communication devices capable of performing a method according to the present specification.

[0025] FIG. 3 illustrates a wireless communication system to which some implementations of the present specification are applied.

[0026] Figure 4 illustrates a channel in wireless communication.

[0027] Figure 5 illustrates a flow of a signal transmission and reception method according to some implementations of this specification.

[0028] Figure 6 illustrates the structure of wireless communication based on deep learning (DL).

[0029] Figure 7 illustrates another structure of wireless communication based on deep learning (DL).

[0030] Hereinafter, implementations according to this specification will be described in detail with reference to the attached drawings. The detailed description provided below, together with the attached drawings, is intended to describe exemplary implementations of this specification and is not intended to represent the only possible implementations of this specification. The detailed description below includes specific details to provide a thorough understanding of this specification. However, one of ordinary skill in the art will appreciate that this specification may be practiced without these specific details.

[0031] In some cases, to avoid ambiguity in the concepts of this specification, known structures and devices may be omitted or illustrated in block diagram form focusing on the core functions of each structure and device. Throughout this specification, identical components are described using the same reference numerals.

[0032] The terms and words used in the following description and drawings should not be interpreted as limited to their conventional or dictionary meanings, but should be interpreted with meanings and concepts that conform to the technical idea of ​​this specification based on the principle that the inventor can appropriately define the concept of the term to best describe his or her invention. Therefore, the examples described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of this specification and do not represent all of the technical idea of ​​this specification. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of filing this application.

[0033] Additionally, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0034] The terminology used in this specification is only used to describe specific embodiments and is not intended to limit the features, components, etc. described in the specification. The singular expression includes plural expressions unless the context clearly indicates otherwise. It should be understood that the terms "comprises" or "has" described in this specification are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0035] Additionally, in various embodiments of the present specification, " / " and "," should be interpreted as indicating "and / or". For example, "A / B" can mean "A and / or B". Furthermore, "A, B" can mean "A and / or B". Furthermore, "A / B / C" can mean "at least one of A, B, and / or C". Furthermore, "A, B, C" can mean "at least one of A, B, and / or C".

[0036] Additionally, terms that include ordinal numbers, such as "first," "second," etc., are used to describe various components and are only used to distinguish one component from another, not to limit said components. For example, without exceeding the scope of this specification, a second component could be referred to as a first component, and similarly, a first component could also be referred to as a second component.

[0037] The techniques, devices, and systems described below can be applied to various wireless multiple access systems. Examples of multiple access systems include code division multiple access (CDMA) systems, frequency division multiple access (FDMA) systems, time division multiple access (TDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, and single carrier frequency division multiple access (SC-FDMA) systems. CDMA can be implemented in radio technologies such as Universal Terrestrial Radio Access (UTRA) or CDMA2000. TDMA can be implemented in radio technologies such as Global System for Mobile communications (GSM) / General Packet Radio Service (GPRS) / Enhanced Data Rates for GSM Evolution (EDGE). OFDMA can be implemented in wireless technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and Evolved UTRA (E-UTRA). UTRA is part of UMTS (Universal Mobile Telecommunications System), and 3GPP (3rd Generation Partnership Project) LTE (long term evolution) is part of E-UMTS (Evolved UMTS) that uses E-UTRA. 3GPP LTE adopts OFDMA for the downlink (DL) and SC-FDMA for the uplink (UL).LTE-A (Advanced) is an evolved form of 3GPP LTE, and 3GPP NR (New Radio or New Radio Access Technology) is an evolved form of 3GPP LTE / LTE-A.

[0038] For convenience of explanation, the following description assumes that this specification applies to 3GPP-based communication systems, such as LTE and NR. However, the technical features of this specification are not limited to this. For example, although the detailed description below is based on a mobile communication system corresponding to a 3GPP LTE / NR system, it can also be applied to any other mobile communication system, except for features specific to 3GPP LTE / NR.

[0039] For terms and technologies used in this specification that are not specifically explained, reference can be made to 3GPP-based standard documents.

[0040] In the examples of this specification described below, the expression "assumes" that a device "assumes" that the entity transmitting the channel transmits the channel in a manner consistent with the "assume." The entity receiving the channel may mean that, under the assumption that the channel was transmitted in a manner consistent with the "assume," the entity receiving the channel receives or decodes the channel in a manner consistent with the "assume."

[0041] In this specification, user equipment (UE) may be fixed or mobile, and includes various devices that communicate with a base station (BS) to transmit and / or receive user data and / or various control information. UE may be called Terminal Equipment (TE), Mobile Station (MS), Mobile Terminal (MT), User Terminal (UT), Subscriber Station (SS), wireless device, Personal Digital Assistant (PDA), wireless modem, handheld device, etc. In addition, in this specification, BS generally refers to a fixed station that communicates with UE and / or other BS, and exchanges various data and control information with UE and other BS. BS may be called by other terms such as Advanced Base Station (ABS), Node-B (NB), evolved-NodeB (eNB), Base Transceiver System (BTS), Access Point, and Processing Server (PS). In particular, the BS in UTRAN is called a Node-B, the BS in E-UTRAN is called an eNB, and the BS in a new radio access technology network is called a gNB. For convenience of explanation, the base station is referred to as a BS below, regardless of the type or version of communication technology.

[0042] Figure 1 illustrates the structure of a system for 5th generation (5G) communication.

[0043] Specifically, FIG. 1 illustrates the structure of a 5G communication system to which the method(s) described in FIG. 5 are applied.

[0044] Referring to FIG. 1, a next generation radio access network (NG-RAN) may include a BS (20) that provides user plane and control plane protocol termination to a UE (10).

[0045] The example of Fig. 1 illustrates a case including only gNB. BSs (20) can be connected to each other via Xn interfaces. BSs (20) can be connected to a 5th generation core network (5GC) via an NG interface. Specifically, BSs (20) can be connected to an access and mobility management function (AMF) (30) via an NG-C interface, and can be connected to a user plane function (UPF) (30) via an NG-U interface.

[0046] According to some implementations of this specification, the functions, procedures, and / or methods described in this specification may be performed via the AMF / UPF (30). For example, according to some implementations of this specification, the operation(s) performed by the BS (20) may be processed by the AMF / UPF (30) (rather than the BS (20)).

[0047] Meanwhile, the UE (10) and / or BS (20) of FIG. 1 may correspond to the wireless device illustrated in FIG. 2.

[0048] In a wireless communication system, a UE (10) performs beam management by transmitting feedback information through uplink control information (UCI) transmitted through a physical uplink control channel (PUCCH) and / or a physical uplink shared channel (PUSCH) for a beam transmitted by a BS (20). The UCI information transmitted through the uplink may include a rank indicator (RI), a layer indicator, a channel quality indicator, a channel state information reference signal (CSI-RS) resource indicator (CRI), etc.

[0049] Meanwhile, in the next generation communication system of 5G communication, the necessity of beam management and methods for efficiently performing beam management are being discussed.

[0050] This specification proposes a method for a UE (10) and / or a BS (20) to transmit and receive an artificial intelligence (AI) and / or machine learning (ML) based model (hereinafter, AI / ML model) for channel estimation (CE).

[0051] FIG. 2 is a block diagram illustrating examples of communication devices capable of performing a method according to the present specification.

[0052] Specifically, FIG. 2 illustrates an example of a communication device(s) that transmits and receives signals according to the method(s) described in FIG. 5.

[0053] Referring to FIG. 2, the first wireless device (100) and the second wireless device (200) can transmit and / or receive wireless signals via various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (100), the second wireless device (200)} can correspond to {UE, BS}.

[0054] A first wireless device (100) includes one or more processors (102) and one or more memories (104), and may further include one or more transceivers (106) and / or one or more antennas (108). The processor(s) (102) controls the memories (104) and / or the transceivers (106), and may be configured to implement the functions, procedures, and / or methods described / proposed above. For example, the processor(s) (102) may process information in the memories (104) to generate first information / signals, and then transmit a wireless signal including the first information / signals via the transceivers (106). In addition, the processor(s) (102) may receive a wireless signal including second information / signal through the transceiver(s) (106), and then store information obtained from signal processing of the second information / signal in the memory(s) (104). The memory(s) (104) may be connected to the processor(s) (102) and may store various information related to the operation of the processor(s) (102). For example, the memory(s) (104) may perform some or all of the processes controlled by the processor(s) (102), or store software code including instructions for performing the procedures and / or methods described / proposed above. Here, the processor(s) (102) and the memory(s) (104) may be part of a communication modem / circuit / chip designed to implement a wireless communication technology (e.g., LTE, NR). The transceiver(s) (106) may be connected to the processor(s) (102) and may transmit and / or receive wireless signals via one or more antennas (108). The transceiver(s) (106) may include a transmitter and / or a receiver. The transceiver(s) (106) may be used interchangeably with an RF (Radio Frequency) unit. In this specification, a wireless device may also mean a communication modem / circuit / chip.

[0055] The second wireless device (200) includes one or more processors (202), one or more memories (204), and may further include one or more transceivers (206) and / or one or more antennas (208). The processor(s) (202) controls the memories (204) and / or the transceivers (206), and may be configured to implement the functions, procedures, and / or methods described / proposed above. For example, the processor(s) (202) may process information in the memories (204) to generate third information / signals, and then transmit a wireless signal including the third information / signals via the transceivers (206). In addition, the processor(s) (202) may receive a wireless signal including the fourth information / signal through the transceiver(s) (206), and then store information obtained from signal processing of the fourth information / signal in the memory(s) (204). The memory(s) (204) may be connected to the processor(s) (202) and may store various information related to the operation of the processor(s) (202). For example, the memory(s) (204) may perform some or all of the processes controlled by the processor(s) (202), or store software code including instructions for performing the procedures and / or methods described / proposed above. Here, the processor(s) (202) and the memory(s) (204) may be part of a communication modem / circuit / chip designed to implement a wireless communication technology (e.g., LTE, NR). The transceiver(s) (206) may be connected to the processor(s) (202) and may transmit and / or receive wireless signals via one or more antennas (208). The transceiver(s) (206) may include a transmitter and / or a receiver. The transceiver(s) (206) may be used interchangeably with an RF unit. In this specification, a wireless device may also mean a communication modem / circuit / chip.

[0056] Hereinafter, the hardware elements of the device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as a physical (PHY) layer, a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, and a service data adaptation protocol (SDAP) layer). One or more processors (102, 202) may generate one or more protocol data units (PDUs) and / or one or more service data units (SDUs) according to the functions, procedures, proposals, and / or methods disclosed in this specification. One or more processors (102, 202) may generate messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed in this specification. One or more processors (102, 202) may generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed in this specification, and provide the signals to one or more transceivers (106, 206). One or more processors (102, 202) may receive signals (e.g., baseband signals) from one or more transceivers (106, 206) and obtain PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed in this specification.

[0057] One or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), or one or more Field Programmable Gate Arrays (FPGAs) may be included in one or more processors (102, 202). The functions, procedures, proposals, and / or methods disclosed in this specification may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. Firmware or software configured to perform the functions, procedures, suggestions and / or methods disclosed in this specification may be included in one or more processors (102, 202) or stored in one or more memories (104, 204) and executed by one or more processors (102, 202). The functions, procedures, suggestions and / or methods disclosed in this specification may be implemented using firmware or software in the form of codes, instructions and / or sets of instructions.

[0058] The processor(s) (102, 202) may perform the method(s) and / or procedure(s) according to the present specification. For example, the processor(s) (102, 202) may train and / or retrain an AI / ML model. In another example, the processor(s) (102, 202) may transmit and receive an AI / ML model and / or parameter(s) of the AI / ML model via the transceiver(s) (106, 206).

[0059] One or more memories (104, 204) may be coupled to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. The one or more memories (104, 204) may be configured as ROM, RAM, EPROM, flash memory, hard drives, registers, cache memory, computer-readable storage media, and / or combinations thereof. The one or more memories (104, 204) may be located internally and / or externally to the one or more processors (102, 202). Additionally, the one or more memories (104, 204) may be coupled to the one or more processors (102, 202) via various technologies, such as wired or wireless connections.

[0060] One or more transceivers (106, 206) may transmit user data, control information, wireless signals / channels, etc., as described in the methods and / or flowcharts according to some implementations of this specification to one or more other devices. One or more transceivers (106, 206) may receive user data, control information, wireless signals / channels, etc., as described in the functions, procedures, proposals, methods and / or flowcharts disclosed in this specification from one or more other devices. For example, one or more transceivers (106, 206) may be coupled to one or more processors (102, 202) and may transmit and / or receive wireless signals. For example, one or more processors (102, 202) may control one or more transceivers (106, 206) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (106, 206) may be coupled to one or more antennas (108, 208), and one or more transceivers (106, 206) may be configured to transmit and / or receive user data, control information, wireless signals / channels, or the like, as referred to in the functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this specification, via one or more antennas (108, 208). In this specification, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (106, 206) may convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals for processing using one or more processors (102, 202).One or more transceivers (106, 206) may convert user data, control information, wireless signals / channels, etc. processed by one or more processors (102, 202) from baseband signals to RF band signals. For this purpose, one or more transceivers (106, 206) may include an (analog) oscillator and / or filter.

[0061] FIG. 3 illustrates a wireless communication system to which some implementations of the present specification are applied.

[0062] Referring to FIG. 3, a wireless communication system may include one or more BSs and one or more UEs. With the introduction of new wireless communication technologies, the amount of data and control information transmitted and received by the BSs and / or UEs is increasing. The introduction of AI technology in wireless communication systems provides enhanced wireless communication systems by enabling system optimization. AI technology overcomes problems arising from modeling issues, implementation complexity, and / or signal distortion / interference of wireless communication system configurations, thereby supporting low-latency, low-complexity, and high-performance communication systems. For example, AI technology can determine appropriate representations for problems that are difficult to model in wireless communication system configurations. For another example, an improved AI-based wireless communication system can reduce implementation complexity by finding an ideal and computationally feasible solution, or can optimize modem parameters. As another example, improved wireless communication systems based on AI can solve the non-linearity problem of existing wireless communication through non-linear function modeling.

[0063] In particular, this specification proposes a method for transmitting and receiving wireless communication signals based on such AI. Specifically, according to some implementations of this specification, a BS and / or a UE can (re)train an AI / ML model, transmit and receive the (re)trained AI / ML model, and transmit and receive wireless communication signals using the AI / ML model. For example, according to some implementations of this specification, the BS and / or the UE can (re)train an AI / ML model, transmit and receive parameter(s) of the model related to the (re)training, and perform channel estimation (CE) using the AI / ML model based on the transmitted and received parameter(s).

[0064] Figure 4 illustrates a channel in wireless communication.

[0065] Specifically, the devices / devices shown in FIGS. 1 and 2 illustrate channels that are transmitted and received and / or estimated according to some implementations of the present specification.

[0066] In wireless communications, a channel can be represented as an image in the subcarrier and time domains. Referring to Figure 4, channel elements in wireless communications are highly correlated in the spatial, temporal, and / or frequency domains. Deep learning (DL), which is powerful for image-related tasks, can efficiently process these channel elements. For example, convolutional neural networks (CNNs) have the potential to exploit correlations between adjacent channel elements in the spatial, temporal, and / or frequency domains. In particular, DL-based channel estimation methods can improve channel estimation performance in extreme environments. For example, in cases where pilots are scarce and / or nonlinear distortions exist, DL can be utilized to implement nonlinear filters for channel estimation.

[0067] Channel estimation according to some implementations of this specification may differ from CSI feedback enhancement, beam management, and / or positioning accuracy enhancement in the following respects: In time division duplexing (TDD) mode, the UE-side AI / ML model and the network-side AI / ML model may be the same due to channel reciprocity. When the UE-side AI / ML model and the network-side AI / ML model are the same, there is an advantage in that there is no need to train the AI / ML model of either the UE or the network while training the AI / ML model of the other. For example, the BS can train the AI / ML model, transmit / forward the trained AI / ML model to the UE, and the UE can use the received / forwarded AI / ML model for channel estimation. The opposite is also possible. For example, the UE can train the AI / ML model, transmit / forward the trained AI / ML model to the BS, and the BS can use the received / forwarded AI / ML model for channel estimation. In this way, when one side trains an AI / ML model and the other side does not train an AI / ML model, it is called offline learning. However, offline learning is not limited to the fact that the UE-side AI / ML model and the network-side AI / ML model are the same. For example, the UE can receive an AI / ML model trained from the BS and additionally train the AI / ML model based on the AI / ML model received from the BS. In this way, (re)training the AI / ML model on the other side that received the AI / ML model is called online learning. In this specification, offline / online learning can also be referred to as offline / online training.

[0068] According to some implementations of this specification, a BS can train AI / ML model(s) and transmit the AI / ML model(s) to a UE, and the UE can transmit and receive wireless communication signals with the BS based on the AI / ML model(s) received from the BS. Furthermore, according to some implementations of this specification, the UE can (re)train the AI / ML model received from the BS and transmit feedback information including information related to the (re)training to the BS. The reverse is also true. That is, according to some implementations of this specification, both offline learning and / or online learning can be performed.

[0069] According to some implementations of this specification, the BS and the UE may determine an AI / ML model, wherein the AI / ML model of the BS and the AI / ML model of the UE may be models having a structure known to the BS and the UE. For example, the BS and / or the UE may determine an AI / ML model for channel estimation with the UE and / or the BS, receive parameter(s) corresponding to the AI / ML model from the UE and / or the BS, and perform channel estimation based on the AI / ML model based on the received parameter(s). In addition, the BS and / or the UE may determine the AI / ML model based on a model identifier (ID).

[0070] In this specification, transmitting and receiving an AI / ML model may refer to transmitting and receiving parameter(s) of the AI / ML model, information about the parameter(s), and / or information related to (re)training the AI / ML model. For example, one of the BS and the UE may train an AI / ML model, and transmit parameter(s) of the AI / ML model and / or information related to (re)training among the parameters to the other.

[0071] Below, we specifically describe how to transmit and receive signals according to some implementations of this specification.

[0072] Figure 5 illustrates a flow of a signal transmission and reception method according to some implementations of this specification.

[0073] Specifically, FIG. 5 illustrates a flow of a method in which the devices / devices shown in FIGS. 1 and 2 transmit and receive an AI / ML model.

[0074] Referring to FIG. 5, the BS may train AI / ML model(s) (S510), transmit the trained AI / ML model(s) to the UE (S520), update the AI / ML model(s) (S530), and transmit information related to the update to the UE (S540). Here, updating the AI / ML model(s) may mean retraining the (trained) AI / ML model(s), and the information related to the update may mean information about parameter(s) related to the retraining. For example, the BS may train an AI / ML model for channel estimation with the UE, transmit information about multiple parameter(s) of the AI / ML model to the UE, retrain the AI / ML model based on satisfaction of a predetermined condition, and transmit information about parameter(s) related to the retraining among the multiple parameter(s) of the AI / ML model to the UE.

[0075] The UE may determine an AI / ML model, receive a plurality of parameters of the AI / ML model from the BS (S520), and receive information on parameter(s) related to retraining among the plurality of parameters of the AI / ML model retrained at the BS (S540). For example, the UE may determine an AI / ML model for channel estimation with the BS, receive a plurality of parameters of an AI / ML model corresponding to the AI / ML model and trained at the BS, and, based on satisfying a predetermined condition, receive parameter(s) related to retraining performed at the BS corresponding to the AI / ML model of the UE, and reflect the plurality of parameter(s) and / or parameter(s) related to retraining in the AI / ML model of the UE.

[0076] As described above, in the case of channel estimation, there may be an advantage that there is no performance impact in determining an AI / ML model in the UE by the reciprocity of the channel, (re)training the model, transmitting parameter(s) of the model and / or information about the parameter(s) related to the (re)training to the BS, and reflecting this in the AI / ML model of the BS. As in the embodiment described above, it is also possible for the BS to transmit parameter(s) for the AI / ML model of the UE, but in other embodiments of the present specification, the UE may also transmit parameter(s) and / or information about the parameter(s) for the AI / ML model of the BS, depending on the case. For example, the UE may train an AI / ML model for channel estimation with the BS, transmit multiple parameter(s) of the AI / ML model to the BS, retrain the AI / ML model, and transmit parameter(s) related to the retraining to the BS.

[0077] Additionally, the BS and / or UE that transmitted and received the parameter(s) may perform channel estimation based on the (re)trained AI / ML model and transmit the channel estimation information to the UE and / or BS. The BS and / or UE may also receive channel estimation information from the UE and / or BS based on the AI / ML model that reflects the transmitted and received parameter(s).

[0078] Updating / retraining a (trained) AI / ML model in S530 may be performed based on satisfying certain conditions related to the model's Life Cycle Management (LCM). The certain conditions related to LCM may include at least one of a beam change or a precoding change, but are not limited thereto. For example, the BS and / or UE may update / retrain the model based on handover, requests from the UE and / or BS, etc.

[0079] Additionally, the S530 can retrain all or part of an AI / ML model. For example, among the multiple layers (or strata) of the model, a layer related to a predetermined condition that has been satisfied can be retrained.

[0080] Additionally, updating / retraining the (trained) AI / ML model in S530 may include receiving information from the UE and / or BS that received the parameter(s), or from another UE and / or BS that retrained the model.

[0081] Information related to updates transmitted and received by the BS and / or UE in S540 may be information about some parameter(s) related to the update / retraining performed in S530.

[0082] Additionally, in S540, the BS and / or UE transmitting information about the parameter(s) may be performed based on receiving a request for the corresponding model from the UE and / or BS.

[0083] Additionally, in S540, the BS and / or UE may transmit information about the parameter(s) periodically based on a preset cycle.

[0084] Additionally, information related to updates transmitted and received by the BS and / or UE in S540 may include codebook index information for parameters related to updates based on a predetermined codebook for multiple parameters of the corresponding AI / ML model.

[0085] Additionally, the BS and / or UE may further include storing the AI / ML model, the trained AI / ML model, and / or the retrained AI / ML model.

[0086] According to some implementations of this specification, a method for transmitting and receiving a (re)trained AI / ML-based model in a wireless communication system is provided. This allows a BS and / or UE to efficiently transmit and receive wireless communication signals. For example, according to some implementations of this specification, a BS and / or UE that transmits and receives an AI / ML model can reduce implementation complexity, computational load, and time delay when performing channel estimation based on the AI / ML model.

[0087] Therefore, the overall throughput of a wireless communication system can be increased and the delay / latency occurring during wireless communication can be reduced through the AI / ML model transmission / reception method according to this specification.

[0088] Figure 6 illustrates the structure of wireless communication based on deep learning (DL).

[0089] Specifically, FIG. 6 is an example of the structure of a DL-based wireless communication system to which the method(s) described in FIG. 5 are applied.

[0090] Referring to FIG. 6, a communication system can be designed block-by-block. A DL-based block-structured communication system can be composed of multiple blocks to partition signal processing. For example, a DL-based block-structured communication system can be composed of a channel encoding / decoding block (602), a modulation / demodulation block (604), a radio frequency (RF) transceiver (606), a channel estimation block (608), and a signal detection block (610). Here, each block(s) can be a processing block(s) individually / independently optimized based on DL for stable communication according to some implementations of the present specification.

[0091] In particular, the channel estimation block (608) may perform channel state information (CSI) estimation and / or direction of arrival (DOA) estimation according to some implementations of the present specification to improve the wireless communication environment. For example, according to some implementations of the present specification, the channel estimation block (608) may perform AI / ML model (re)training and / or AI / ML model transmission / reception (having multiple model structures), and may perform CSI estimation, DOA estimation, etc. based on the AI / ML model, thereby improving the implementation complexity and the performance of the wireless communication system for a small number of pilot symbols.

[0092] Figure 7 illustrates another structure of wireless communication based on deep learning (DL).

[0093] Specifically, FIG. 7 is an example of the structure of a DL-based wireless communication system to which the method(s) described in FIG. 5 are applied.

[0094] Block-structured communication systems allow for individual / independent optimization of blocks, but do not guarantee overall system performance. As an alternative to such block-structured communication systems, the DL-based end-to-end communication system illustrated in Figure 8 is trained based on DL, enabling optimization of the entire system.

[0095] Some implementations of this specification are applicable to DL-based end-to-end communication systems, depending on their embodiment.

[0096] Below, we specifically describe methods(s) for (re)training an AI / ML model and / or methods(s) for transmitting and receiving a (re)trained AI / ML model.

[0097] According to some implementations of this specification, a BS and / or UE may train AI / ML models(s) for channel estimation, transmit and receive the models, and perform channel estimation based on the models. When estimating a channel using an AI / ML model, maintaining the robustness of the AI / ML model under changing channel conditions is also one of the factors to be considered. The following robustness issues of the AI / ML model may be discussed in a changing channel environment. The performance of a fixed AI / ML model may degrade due to changes in the channel environment. For example, the performance of the AI / ML model may degrade depending on beam changes, received signal-to-noise ratio (SNR), handover, scenarios based on indoor / outdoor coverage / environment, and (user) mobility. Therefore, it may be necessary to update / (re)train the AI / ML model based on beam changes, received SNR, hand-over, indoor / outdoor coverage / environment-based scenarios, mobility and / or reference signal received power (RSRP) / reference signal strength indicator (RSSI).

[0098] According to some implementations of this specification, the BS and / or UE can compensate for the model robustness issue by performing offline learning (e.g., learning a model at the gNB and transmitting / forwarding it to the UE) and online learning (e.g., learning at the UE that receives the learned model from the gNB). In other words, the BS and / or UE that trains and / or transmits / receives an AI / ML model for channel estimation according to some implementations of this specification can maintain the model's robustness under changing channel environments by performing online learning together with offline learning. However, even in this case, if there is a significant change in the channel environment, the AI / ML model may need to be updated / retrained according to the change in the channel environment.

[0099] This specification proposes methods for updating / retraining AI / ML models based on changing channel conditions and transmitting / receiving the updated / retrained AI / ML models. For example, a BS and / or UE can retrain an AI / ML model based on satisfying certain conditions related to the AI / ML model's Life Cycle Management (LCM).

[0100] In this specification, LCM of an AI / ML model may include model training, model deployment, model inference, model monitoring, and / or model updating.

[0101] Additionally, the following aspects can be studied in LCM, including the definition and necessity of components:

[0102] - Data collection

[0103] This may include assistance information, if applicable.

[0104] - Model training

[0105] - Functionality / Model Identification

[0106] - Model delivery / transfer

[0107] - Model inference operation

[0108] - Function / model selection, activation, deactivation, switching, and fallback operations

[0109] To this end, decisions by the network (network-initiated, UE-initiated, or requested to the network), decisions by the UE (i) Event-triggered as configured by the network and reporting the UE's decision to the network, ii) UE-autonomous and reporting the UE's decision to the network, or iii) UE-autonomous and not reporting the UE's decision to the network) can be studied.

[0110] - Function / Model Monitoring

[0111] - Model update

[0112] - UE performance (capability)

[0113] Some of the aspects listed may not affect the specification.

[0114] This specification proposes a method(s) for (re)training an AI / ML model and transmitting / receiving the (re)trained AI / ML model by considering changes in the channel environment associated with the LCM of such an AI / ML model.

[0115] For example, the effective channel (in the frequency domain and / or spatial domain) may change depending on beam changes or precoding changes. In such changing channel environments, the BS and / or UE can maintain the robustness of the AI / ML model for channel estimation according to the proposed method(s) described below.

[0116] - Proposal 1

[0117] BS and / or UE may store (re)trained AI / ML models per beam and / or per precoding.

[0118] The BS and / or UE may store the (re)trained AI / ML model by beam and / or precoding, and transfer / deliver all parameters of the trained AI / ML model. Here, the AI / ML model transmitted and received may be an AI / ML model updated / retrained based on the changed environment at the BS and / or UE. Although transferring all parameters of the AI / ML model is simple and low in complexity, the overhead for transmission / delivery and / or memory at the BS and / or UE may be high.

[0119] Alternatively, the BS and / or UE may transmit some of the parameters of the (re)trained AI / ML model to the UE and / or BS. For example, the parameter(s) of some layer(s) of one or more layers of the AI / ML model may be transmitted. Here, the AI / ML model is an AI / ML model that has been updated / retrained based on a changing environment in the BS and / or UE, and some of the transmitted parameter(s) may refer to parameter(s) associated with the update / retraining.

[0120] In diverse channel environments, not all channel characteristics may change even when the environment changes. For example, when there is a beam change and / or a precoding change, the channel characteristics(s) may change in the spatial domain associated with the beam and / or precoding. According to some implementations of the present specification, a BS and / or a UE may fine-tune a previously trained AI / ML model by (re)training some layer(s)(or layers) of the AI / ML model. The BS and / or the UE may perform fine-tuning and / or transfer learning on the AI / ML model for fine control.

[0121] According to some implementations of this specification, the layer(s) (of the AI / ML model) to be updated / retrained may be determined / indicated via downlink control information (DCI) or radio resource control (RRC) signaling.

[0122] Additionally, according to some implementations of this specification, the layer(s) to be updated / retrained may be determined / indicated via pre-defined tables and / or implicit information.

[0123] For example, if the beam is changed, the BS and / or UE may retrain only the 5th layer of the AI / ML model, and transmit / forward only the parameter(s) of the 5th layer to the UE and / or BS. Here, the beam change may be determined / indicated based on a synchronization signal block (SSB) and / or a CSI report.

[0124] For another example, if the precoding is changed, the BS and / or UE may retrain the 4th layer and / or the 5th layer, and transmit / convey only the parameter(s) of the 4th layer and / or the 5th layer to the BS and / or the UE. Here, the precoding change may be determined / indicated via DCI.

[0125] According to some implementations of this specification, a BS and / or a UE that has received information about a (re)trained AI / ML model, parameter(s) of the (re)trained AI / ML model, and / or parameter(s) of the (re)trained AI / ML model can also perform online training. In this way, by performing online training together with offline training and transmitting and receiving feedback related to the online training, the performance of the AI / ML model can be improved. For example, a UE that has received a plurality of parameters and / or some parameter(s) of an AI / ML model from a BS can perform online training and transmit feedback related thereto to the BS, thereby improving the performance of the BS.

[0126] Additionally, the feedback transmitted by the BS and / or UE that performed the online training may include parameter(s) associated with the online training of the AI / ML model of the UE and / or BS (or corresponding to the model ID of the AI / ML model), and the parameter(s) may be transmitted through the feedback channel.

[0127] Additionally, the feedback transmitted by the BS and / or UE that performed online training may include a codebook index of a pre-shared codebook, and the codebook index may be transmitted through a feedback channel. Here, the codebook may be preset for parameter(s) of the corresponding AI / ML model and shared between the BS and UE, and the transmitted and received codebook index(es) may refer to index(es) for parameter(s) associated with (re)training.

[0128] As described in Proposal 1, some implementations of the present specification provide methods and / or procedures for updating certain parameter(s) of an AI / ML model based on characteristics and / or implicit information of the AI / ML model for channel estimation. The BS and / or UE can improve the performance of channel estimation based on the AI / ML model by (re)training / updating the AI / ML model based on changes in the channel environment.

[0129] Training / updating / retraining AI / ML models, or transmitting / receiving AI / ML models, according to some implementations of this specification is not limited to AI / ML models for channel estimation, except for aspects specific to channel estimation. For example, it may also be applicable to AI / ML models for beam management, positioning accuracy improvement, etc.

[0130] - Proposal 2

[0131] As described above, fixed AI / ML models may experience performance degradation depending on beam changes, received SNR, handover, indoor / outdoor coverage / environment-based scenarios, (user) mobility, etc., and thus, it may be necessary to update / (re)train the AI / ML models.

[0132] In performing channel estimation based on AI / ML, due to the reciprocity of the channel, the UE-side AI / ML model and the BS-side AI / ML model can be the same, so that one of the BS and / or the UE that updates / retrains the AI / ML model according to a change in the channel environment can perform the update / retraining by receiving parameter(s) related to the update / retraining from the other.

[0133] The BS and / or UE may retrain the AI / ML model based on beam change, received SNR, handover, indoor / outdoor coverage / environment-based scenarios, mobility, etc., and transmit the retrained AI / ML model to the UE and / or BS according to the following proposed method(s). In other words, according to some implementations of the present specification, the transmission / forwarding of the retrained AI / ML model may be triggered according to the method(s) described in Proposal 2.

[0134] The BS and / or the UE may transmit / forward the (re)trained AI / ML model based on a request from the UE and / or the BS. For example, the BS may receive a request for an AI / ML model from the UE via uplink control information (UCI) or a feedback channel, and transmit / forward the (re)trained AI / ML model to the UE based on receipt of the request.

[0135] Alternatively, the BS and / or UE may transmit / forward the (re)trained AI / ML model based on a preset period. Alternatively, the BS and / or UE may transmit / forward the (re)trained AI / ML model aperiodically.

[0136] If the BS and / or the UE periodically transmit the AI / ML model and / or the parameter(s) of the AI / ML model using a non-codebook method, the overhead may increase. According to some implementations of the present specification, the overhead can be reduced by transmitting and receiving the AI / ML model and / or the parameter(s) of the AI / ML model using a codebook method and / or based on a preset table. For example, the BS and / or the UE can transmit / forward the (re)trained AI / ML model by transmitting an indicator associated with the (re)trained AI / ML model via DCI in a preset codebook and / or a preset table.

[0137] Additionally, the BS and / or UE may transmit / forward a (re)trained AI / ML model based on a beam change. Here, the beam may be changed at the BS. For example, the BS may decide whether to change the beam. If the BS desires a beam change, the AI / ML model for channel estimation must be changed. Therefore, the (re)trained AI / ML model may be transmitted / forwarded to the UE when the BS changes the beam.

[0138] As described in Proposals 1 and 2, some implementations of the present specification provide method(s) and / or procedure(s) for determining when to trigger an update of an AI / ML model based on characteristics and / or implicit information of the AI / ML model for channel estimation, and method(s) and / or procedure(s) for determining when to trigger transmission / forwarding of an updated AI / ML model.

[0139] Meanwhile, based on the method(s) and / or procedure(s) for triggering transmission / delivery of the AI / ML model described in Proposal 2, update / retraining of the AI / ML model may also be triggered.

[0140] The methods according to Proposals 1 and 2 are examples for updating or transmitting / receiving an AI / ML model according to some implementations of this specification, and are not limited thereto, and an AI / ML model may be transmitted / received by a method combining each of the methods included in Proposals 1 and 2.

[0141] In this specification, a computer-readable storage medium can store at least one instruction or computer program, which when executed by at least one processor can cause the at least one processor to perform operations according to some embodiments or implementations of this specification.

[0142] In this specification, a computer program or computer program product may be recorded on at least one computer-readable (non-volatile) storage medium and may contain instructions that, when executed, cause (at least one processor) to perform operations according to some embodiments or implementations of this specification.

[0143] In this specification, a processing device or apparatus may include at least one processor and at least one computer memory connectable to the at least one processor. The at least one computer memory may store instructions or programs, which, when executed, cause at least one processor operably connected to the at least one memory to perform operations according to some embodiments or implementations of the present specification.

[0144] As described above, the examples disclosed in this specification are provided to enable those skilled in the relevant technical fields to implement and practice this specification. While the examples of this specification have been described above with reference to the examples, those skilled in the relevant technical fields can modify and adapt the examples of this specification in various ways. For example, those skilled in the art can utilize the individual components described in the examples of this specification in combination with each other.

Claims

1. When a base station transmits and receives signals in a wireless communication system, Train artificial intelligence or machine learning-based models for user equipment (UE) and channel estimation, Transmitting multiple parameters of the above model to the UE, Retrain the model based on satisfying certain conditions related to the LCM (Life Cycle Management) of the above model, and Including transmitting parameter information related to the retraining among the plurality of parameters to the UE, Method of transmitting and receiving signals.

2. In paragraph 1, The above predetermined condition related to the LCM includes at least one of a beam change or a precoding change. Method of transmitting and receiving signals.

3. In paragraph 1, Retraining the above model is: Retraining a layer related to a certain condition that is satisfied among the multiple layers of the above model. Method of transmitting and receiving signals.

4. In paragraph 1, Transmitting the above parameter information is: Based on receiving a request for the model from the UE, Method of transmitting and receiving signals.

5. In paragraph 1, Transmitting the above parameter information is: Performed based on a preset cycle, Method of transmitting and receiving signals.

6. In paragraph 1, The above parameter information includes index information for the parameters related to the retraining based on a predetermined codebook for the plurality of parameters. Method of transmitting and receiving signals.

7. In paragraph 1, Further comprising saving the retrained model, Method of transmitting and receiving signals.

8. In paragraph 1, Retraining the above model is: Receiving information that retrains the model from the UE or a UE other than the UE, Method of transmitting and receiving signals.

9. In a base station that transmits and receives signals in a wireless communication system, At least one transmitter / receiver; at least one processor; and At least one computer memory operably connected to said at least one processor and storing instructions that, when executed, cause said at least one processor to perform operations, said operations comprising: Train artificial intelligence or machine learning-based models for user equipment (UE) and channel estimation, Transmitting multiple parameters of the above model to the UE, Retrain the model based on satisfying certain conditions related to the LCM (Life Cycle Management) of the above model, and Including transmitting parameter information related to the retraining among the plurality of parameters to the UE, Base station.

10. In paragraph 9, The above predetermined condition related to the LCM includes at least one of a beam change or a precoding change. Base station.

11. In paragraph 9, Retraining the above model is: Retraining a layer related to a certain condition that is satisfied among the multiple layers of the above model. Base station.

12. In paragraph 9, Transmitting the above parameter information is: Based on receiving a request for the model from the UE, Base station.

13. In paragraph 9, Transmitting the above parameter information is: Performed based on a preset cycle, Base station.

14. In paragraph 9, The above parameter information includes index information for the parameters related to the retraining based on a predetermined codebook for the plurality of parameters. Base station.

15. In paragraph 9, The above actions are: Further comprising saving the retrained model, Base station.

16. In paragraph 9, Retraining the above model is: Receiving information that retrains the model from the UE or a UE other than the UE, Base station.

17. In a method for a user device to transmit and receive signals in a wireless communication system, Determine an artificial intelligence or machine learning-based model for base station and channel estimation, Receive multiple parameters of the above model from the base station, and Based on satisfying a predetermined condition related to the LCM (Life Cycle Management) of the above model, including receiving parameter information related to retraining of the model among the plurality of parameters from the base station, Method of transmitting and receiving signals.

18. In a user device that transmits and receives signals in a wireless communication system, At least one transmitter / receiver; at least one processor; and At least one computer memory operably connectable to said at least one processor and storing instructions that, when executed, cause said at least one processor to perform operations, said operations comprising: Determine an artificial intelligence or machine learning-based model for base station and channel estimation, Receive multiple parameters of the above model from the base station, and Based on satisfying a predetermined condition related to the LCM (Life Cycle Management) of the above model, including receiving parameter information related to retraining of the model among the plurality of parameters from the base station, User device.

Images