Method and apparatus for reducing codebook monitoring overhead

Abstract

Provided is a method performed by a terminal in a wireless communication system according to an embodiment of the present disclosure. The method comprises the steps of: receiving configuration information including information related to codebook monitoring of the terminal; receiving a channel state information-reference signal (CSI-RS); performing codebook monitoring on the basis of the configuration information and the CSI-RS; and transmitting a report including the result of codebook monitoring. The information related to codebook monitoring includes first information regarding the codebook monitoring type and second information associated with the report.

Description

Method and device for reducing codebook monitoring overhead

[0001] The present disclosure relates to a method and device related to channel state information (CSI) in a wireless communication system. More specifically, the present disclosure relates to a method for monitoring a codebook for CSI and a device capable of performing the same.

[0002] Looking back at the development process over the generations of wireless communication, technologies have been developed primarily for human-targeted services such as voice, multimedia, and data.

[0003] 5G (5th-generation) New Radio (NR) communication systems must be able to freely reflect the diverse needs of service providers and users, and thus support services that simultaneously satisfy these diverse requirements. Services being considered for 5G communication systems include enhanced Mobile Broadband (eMBB), massive Machine Type Communication (mMTC), and Ultra Reliability Low Latency Communication (URLLC).

[0004] eMBB aims to provide data transmission rates that are significantly higher than those supported by existing LTE (long term evolution), LTE-A (LTE-advanced), or LTE-Pro. For example, in a 5G communication system, eMBB must be able to support a peak data rate of 20 Gbps in the downlink and a peak data rate of 10 Gbps in the uplink from a single base station. Furthermore, 5G communication systems must provide not only the peak data rate but also the increased user-perceived data rate for terminals. To meet these requirements, improvements in various transmission and reception technologies, including improved multi-antenna transmission technologies, are required. Furthermore, while current LTE transmits signals using a maximum transmission bandwidth of 20 MHz in the 2 GHz band, 5G communication systems can meet the data transmission rates required by 5G communication systems by using a wider frequency bandwidth than 20 MHz in the 3-6 GHz or higher 6 GHz band.

[0005] 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, such as basements, beyond cell coverage due to the nature of the service, requiring wider coverage than other services provided by 5G communication systems. Terminals supporting mMTC must be comprised of low-cost terminals, and since frequent battery replacement is difficult, a very long battery life, such as 10 to 15 years, is required.

[0006] 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 systems must provide a smaller Transmit Time Interval (TTI) than other services, while simultaneously allocating extensive resources in the frequency band to ensure communication link reliability.

[0007] With the commercialization of 5G 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 infrastructure, construction equipment, and factory equipment. Mobile devices are also expected to evolve into diverse form factors, including augmented reality glasses, virtual reality headsets, and holographic devices. Efforts are underway to develop improved 6G communication systems to connect hundreds of billions of devices and objects in the 6G (6th-generation) era and provide diverse services. For this reason, 6G communication systems are often referred to as "Beyond 5G" systems.

[0008] 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.

[0009] 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 orthogonal frequency division multiplexing (OFDM), 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.

[0010] 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 at the same time for uplink and downlink; 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.

[0011] 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 (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 be applied in diverse fields such as industry, medicine, automobiles, and home appliances.

[0012] Satisfying these diverse services often requires beam management and support for multiple frequency bands. In these situations, diverse channel environments can arise for each frequency band / beam, and resource consumption is significant for channel estimation at the terminal and reporting the results to the base station. Furthermore, channel conditions recovered through the existing 5G NR codebook-based CSI reporting suffer from information loss during the transmission of the estimated channel H due to codebook quantization issues. While codebooks can be configured more diversely, this also increases the amount of data to be transmitted.

[0013] For this reason, CSI compression is being discussed, in which the terminal compresses and transmits CSI based on an auto-encoder (AE), rather than the codebook-based CSI feedback of the current 5G NR, and decodes the information received from the base station.

[0014] The present disclosure provides a method for a terminal to perform codebook monitoring along with reporting CSI through AI / machine learning (ML) based CSI compression.

[0015] In a method performed by a terminal in a wireless communication system according to one embodiment of the present disclosure, the method includes the steps of: receiving configuration information including information related to codebook monitoring of the terminal; receiving a channel state information-reference signal (CSI-RS); performing codebook monitoring based on the configuration information and the CSI-RS; and transmitting a report including a result of the codebook monitoring, wherein the information related to the codebook monitoring includes first information about a codebook monitoring type and second information associated with the report. The codebook referred to in the present disclosure may include a type 1 codebook, a type 2 codebook, a rel-16 type 2 (Enhanced type II codebook), etc. listed in the 3GPP standard. In addition, the codebook referred to in the present disclosure may include a codebook mentioned in the 3GPP standard other than the above-mentioned codebook, and may include various types of codebooks that map and quantize CSI.

[0016] In a method performed by a base station in a wireless communication system according to one embodiment of the present disclosure, the method includes the steps of transmitting configuration information including information related to codebook monitoring of a terminal to the terminal, transmitting a CSI-RS to the terminal, and receiving a report including a result of codebook monitoring based on the configuration information and the CSI-RS from the terminal, wherein the information related to codebook monitoring includes first information on a codebook monitoring type and second information associated with the report.

[0017] A terminal of a wireless communication system according to one embodiment of the present disclosure includes at least one transceiver and at least one processor, wherein the at least one processor is configured to receive configuration information including information related to codebook monitoring of the terminal, receive a CSI-RS, perform codebook monitoring based on the configuration information and the CSI-RS, and transmit a report including a result of the codebook monitoring, wherein the information related to the codebook monitoring includes first information on a codebook monitoring type and second information associated with the report.

[0018] A base station of a wireless communication system according to one embodiment of the present disclosure includes at least one transceiver and at least one processor, wherein the at least one processor is configured to transmit configuration information including information related to codebook monitoring of a terminal to the terminal, transmit a CSI-RS to the terminal, and receive a report including a result of codebook monitoring based on the configuration information and the CSI-RS from the terminal, and wherein the information related to codebook monitoring includes first information on a codebook monitoring type and second information associated with the report.

[0019] The technical problems to be achieved in various embodiments of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0020] According to one embodiment of the present disclosure, when operating AI / ML-based CSI compression, a terminal can perform codebook monitoring.

[0021] In addition, according to one embodiment of the present disclosure, transmission overhead can be significantly reduced since there is no need to transmit codebook PMI (precoding matrix indicator) and quantized V compared to a method of performing codebook monitoring at a base station (network).

[0022] Additionally, according to one embodiment of the present disclosure, codebook monitoring accuracy can be improved by having the terminal perform codebook monitoring using ground truth V.

[0023] In addition, according to one embodiment of the present disclosure, when a terminal performs codebook monitoring based on an AI model provided by a network (base station), codebook monitoring can be implemented so that it is performed privately by vendor / operator of the network (base station).

[0024] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from the description below.

[0025] FIG. 1 is a schematic diagram of an AI / ML-based CSI compression technology according to an embodiment of the present disclosure.

[0026] FIG. 2 illustrates an AI / ML-based CSI compression procedure according to one embodiment of the present disclosure.

[0027] FIG. 3 illustrates a method for monitoring an AI / ML model at the network side (e.g., base station) based on quantized CSI according to an embodiment of the present disclosure.

[0028] FIG. 4 illustrates a method for monitoring an AI / ML model on the terminal side based on a proxy model according to an embodiment of the present disclosure.

[0029] Figure 5 shows a performance comparison of enhanced type II CSI and AI-based CSI.

[0030] FIG. 6 is a schematic diagram of a codebook monitoring method on the network side according to an embodiment of the present disclosure.

[0031] FIG. 7 illustrates a codebook monitoring operation at a terminal using a metric function according to an embodiment of the present disclosure.

[0032] FIG. 8 illustrates a codebook monitoring operation at a terminal using an AI model according to an embodiment of the present disclosure.

[0033] FIG. 9 illustrates a procedure for performing codebook monitoring at a terminal according to an embodiment of the present disclosure.

[0034] FIG. 10 illustrates a procedure for periodically performing codebook monitoring on the terminal side according to one embodiment of the present disclosure.

[0035] FIG. 11 illustrates a procedure for performing semi-continuous codebook monitoring on the terminal side according to one embodiment of the present disclosure.

[0036] FIG. 12 illustrates a procedure for reporting codebook monitoring results aperiodically according to one embodiment of the present disclosure.

[0037] FIG. 13 illustrates a procedure in which periodic codebook monitoring reports and aperiodic codebook monitoring reports are combined and performed at the terminal side according to one embodiment of the present disclosure.

[0038] FIG. 14a illustrates a procedure for reporting codebook monitoring results based on an event trigger according to one embodiment of the present disclosure.

[0039] FIG. 14b illustrates a case where the offset value is set to 2 according to one embodiment of the present disclosure.

[0040] FIG. 15 illustrates a procedure for performing codebook monitoring further using codebook PMI and quantized V at the request of a base station according to one embodiment of the present disclosure.

[0041] FIG. 16 illustrates a codebook monitoring procedure of a base station using SRS according to one embodiment of the present disclosure.

[0042] FIG. 17 illustrates the structure of a terminal in a wireless communication system according to an embodiment of the present disclosure.

[0043] FIG. 18 illustrates the structure of a base station in a wireless communication system according to an embodiment of the present disclosure.

[0044] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0045] 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. These embodiments are provided solely to ensure that the disclosure is complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined solely by the scope of the claims.

[0046] In addition, when describing embodiments of the present disclosure, descriptions of technical contents that are well known in the technical field to which the present disclosure pertains and are not directly related to the present disclosure will be omitted. This is to convey the gist of the present disclosure more clearly without obscuring it by omitting unnecessary explanations. For the same reason, some components in the attached drawings are exaggerated, omitted, or schematically illustrated. Furthermore, the size of each component does not entirely reflect the actual size. Identical or corresponding components in each drawing are given the same reference numerals. Identical reference numerals refer to identical components throughout the specification.

[0047] 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 contents of this specification as a whole.

[0048] Hereinafter, the base station is an entity that performs resource allocation of a terminal, and may be at least one of a gNode B, an eNode B, a Node B, a BS (Base Station), a wireless access unit, a base station controller, or a node on a network. The terminal may include a UE (User Equipment), an MS (Mobile Station), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing a communication function. In the present disclosure, downlink (DL) refers to a wireless transmission path of a signal transmitted from a base station to a terminal, and uplink (UL) refers to a wireless transmission path of a signal transmitted from a terminal to a base station.

[0049] At this time, it will be understood that each block of the processing flowchart drawings and combinations of the flowchart drawings 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 flowchart 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 flowchart 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).

[0050] 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.

[0051] Here, the term '~ part' used in this embodiment means software or hardware components such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and the '~ part' performs certain roles. However, the '~ part' is not limited to software or hardware. The '~ part' may be configured to be on an addressable storage medium or may be configured to play one or more processors. Therefore, as an example, the '~ part' includes components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and '~ parts' may be combined into a smaller number of components and '~ parts' or further separated into additional components and '~ parts'. Additionally, the components and '~parts' may be implemented to activate one or more CPUs within a device or secure multimedia card. In addition, in an embodiment, the '~parts' may include one or more processors.

[0052] In order to know the status of the downlink channel estimated by the terminal at the base station, a separate feedback process is required to transmit channel state information (CSI) from the terminal to the base station. Specifically, the base station transmits a CSI reference signal (CSI-RS) to the terminal. The terminal performs channel estimation with the received CSI-RS and calculates the estimated channel ( ) can be obtained. The terminal transmits PMI (precoding matrix indicator), which is channel information related to the precoding matrix to be used by the base station. After performing EVD (eigenvalue decomposition) or SVD (singular value decomposition), V can be known from . When the terminal transmits V, one of the existing 5G NR CSI feedback methods is to transmit the index of the codebook most similar to V in the form of PMI based on a predefined codebook.

[0053] However, such codebook-based CSI reporting can lead to discrepancies with the actual V due to the limited granularity of the codebook, which can degrade the performance of MIMO systems. Furthermore, as the performance of MU-MIMO systems is further enhanced by the CSI feedback from each terminal, more accurate CSI feedback is required in future communication systems. To this end, existing CSI feedback systems can increase the number of bits used for CSI reporting to obtain more accurate CSI. However, this overhead increases as the number of base station antennas, bandwidth, and granularity increase.

[0054] To address this, methods for reporting CSI using artificial intelligence (AI) / machine learning (ML) are being considered. Among these, AI / ML-based CSI compression is being discussed, where the terminal compresses V itself and transmits it to the base station as a low-dimensional vector z, and the base station then restores the original V from the compressed vector z.

[0055] FIG. 1 is a schematic diagram of an AI / ML-based CSI compression technology according to an embodiment of the present disclosure.

[0056] Referring to Figure 1, the concept / configuration including an encoder located on the terminal side and a decoder located on the base station side represents an AI / ML-based auto-encoder (AE). The auto-encoder can be viewed as a structure that learns to minimize the difference between input and output. In the auto-encoder, V is compressed through the encoder of the terminal, and the compressed result, the latent vector (feature vector) z, is transmitted from the terminal to the base station, and then it is processed through the decoder of the base station. The process of restoring / releasing can be performed.

[0057] The terminal estimates the channel through preprocessing processes such as EVD and SVD (singular value decomposition). can be generated as the input V of the auto-encoder. The encoder of the terminal can compress the precoding matrix V into a latent vector (feature vector) z. In the encoder of the terminal, lossy compression can be performed centered on the information required for restoration. The terminal can transmit the compressed latent vector (feature vector) z to the base station. The decoder of the base station can decode the latent vector (feature vector) z based on the latent vector (feature vector) z. can be restored.

[0058] FIG. 2 illustrates an AI / ML-based CSI compression procedure according to one embodiment of the present disclosure.

[0059] Referring to Fig. 2, in step 210, the terminal can receive the CSI-RS from the base station (network). In step 220, the terminal (i.e., the encoder of the terminal) can derive the latent vector (feature vector) z from the precoding matrix V (this can be called encoder inference). In step 230, the terminal can transmit the output latent vector (feature vector) z through the encoder inference to the base station. In step 240, the base station (i.e., the decoder of the base station) can derive the latent vector (feature vector) z from the latent vector (feature vector) z. can be restored (this can be called decoder inference).

[0060] However, due to the nature of AI / ML, such as changes in data distribution, fluctuations in model performance, and unexpected events, the performance of currently used AI / ML models can deteriorate over time. Therefore, periodic monitoring of AI / ML models is necessary to ensure the operation of AI / ML CSI compression technology.

[0061] Two methods are being considered for AI / ML model monitoring. First, AI / ML model monitoring can be performed on the network side (e.g., base station) using quantized CSI. Second, AI / ML model monitoring can be performed on the terminal side using a proxy model.

[0062] FIG. 3 illustrates a method for monitoring an AI / ML model at the network side (e.g., base station) based on quantized CSI according to an embodiment of the present disclosure.

[0063] Referring to Figure 3, the output of the base station's decoder is And the quantized form of the ground truth V, which is the correct answer, is quantized V (i.e., V q) can be used to monitor AI / ML models. This method periodically monitors the terminal V q There is a disadvantage in that overhead occurs because it is necessary to transmit to the base station.

[0064] FIG. 4 illustrates a method for monitoring an AI / ML model on the terminal side based on a proxy model according to an embodiment of the present disclosure.

[0065] Referring to Figure 4, AI / ML model monitoring can be performed on a terminal that knows both the ground truth V and the latent vector (feature vector) z. The terminal can utilize a proxy model trained to mimic the base station decoder and output a squared generalized cosine similarity (SGCS) value corresponding to the input latent vector (feature vector) z. This method can be advantageous compared to AI / ML model monitoring methods in the network because it does not require quantized CSI transmission.

[0066] As mentioned above, the need for AI / ML model monitoring is being raised, but there is no discussion on monitoring codebook performance.

[0067] Figure 5 illustrates a performance comparison of enhanced Type II (i.e., eTypeII) CSI and AI-based CSI.

[0068] Referring to Figure 5, there may be a section where the performance of the AI / ML-based CSI compression method deteriorates compared to the improved Type II CSI performance of NR.

[0069] In these cases, a fallback from AI / ML-based CSI to existing codebook-based CSI feedback methods may be necessary. Therefore, periodic monitoring of codebook performance is necessary even while AI / ML-based CSI compression is in progress.

[0070] FIG. 6 is a schematic diagram of a codebook monitoring method on the network side according to an embodiment of the present disclosure.

[0071] Referring to Fig. 6, when codebook monitoring is performed on the network (e.g., base station) side, the terminal periodically transmits the PMI mapped to the codebook to the V q A process is required to transmit the codebook to the network. The network (e.g., base station) receives the PMI and V mapped to the codebook. q Codebook monitoring can be performed using .

[0072] In this case, the eTypeII codebook PMI is less than 600 bits, V q In this case, an overhead of about 1000 to 1600 bits may be involved. Also, V q Due to the use of , the monitoring accuracy may be reduced compared to when using V in float32 format.

[0073] To address these issues, the present disclosure provides a method for reducing overhead when performing codebook monitoring during the operation of AI / ML-based CSI compression technology. Specifically, the present disclosure provides a method for performing codebook monitoring on a terminal. According to embodiments of the present disclosure, the overhead and latency required for codebook monitoring can be significantly reduced, and the accuracy of codebook monitoring can be significantly increased.

[0074] The terminal measures the channel through channel estimation. Since we have a V and can derive the codebook PMI from the codebook, we can directly monitor the codebook performance. Two methods can be considered when performing codebook monitoring on the terminal side.

[0075] As a first method, the terminal can perform codebook monitoring using a metric function.

[0076] FIG. 7 illustrates a codebook monitoring operation at a terminal using a metric function according to an embodiment of the present disclosure.

[0077] Referring to Fig. 7, the terminal can derive the codebook monitoring result using the metric function and share the result with the base station. The base station can utilize the codebook monitoring result obtained from the terminal. When using this method, a separate codebook PMI and quantizedV (i.e., V) for codebook monitoring are required. q ) can be transmitted without any overhead, which can be greatly reduced.

[0078] Alternatively, as a second method, the terminal can perform codebook monitoring using an AI model. The AI ​​model used for codebook monitoring can also be referred to as a black-box monitoring model.

[0079] FIG. 8 illustrates a codebook monitoring operation at a terminal using an AI model according to an embodiment of the present disclosure.

[0080] Referring to Fig. 8, the terminal can derive the codebook monitoring results through the AI ​​model. The terminal can perform codebook monitoring by using V and codebook PMI obtained through channel estimation as inputs to the AI ​​model. The AI ​​model can be provided from the network side. The proxy model used for AI model-based codebook monitoring is a model with approximately 1000 times fewer parameters than an actual auto-encoder and can be transmitted from the network side to the terminal. This method can provide private results by using an AI model that does not disclose to the terminal and other vendors / operators what values ​​the network derives (if the terminal does not want to disclose what results are compared), so that the implementation performance of the network vendor can be given weight for performing codebook monitoring. In other words, codebook monitoring can be implemented by each vendor / operator. Even when using this method, separate codebook PMI and V for codebook monitoring are required. q The overhead can be significantly reduced as transmission is not involved.

[0081] In order to perform codebook monitoring in the above-described terminal, signaling between the terminal and the base station (network) needs to be defined.

[0082] FIG. 9 illustrates a procedure for performing codebook monitoring at a terminal according to an embodiment of the present disclosure.

[0083] Referring to FIG. 9, at step 910, the base station can transmit configuration information to the terminal. That is, the terminal can receive configuration information from the base station. The configuration information can be transmitted via radio resource control (RRC) signaling. For example, the configuration information can be included in an RRC reset message. Alternatively, the configuration information can be added to a CSI report configuration (e.g., CSI-reportconfig).

[0084] The above configuration information allows the base station to provide the terminal with information related to the terminal's codebook monitoring. For example, the configuration information may include at least one of information regarding the codebook monitoring type, settings for codebook monitoring reporting, or settings for codebook monitoring measurement.

[0085] Information about the codebook monitoring type may indicate how the codebook monitoring is performed. For example, information about the codebook monitoring type may indicate metric function-based codebook monitoring (e.g., FIG. 7), AI model-based codebook monitoring (e.g., FIG. 8), or codebook PMI and quantized V (V q ) can be directed to one of the codebook monitoring (e.g., Fig. 6). The codebook PMI and the quantized V (V q ) may mean codebook monitoring by the base station (e.g., FIG. 6).

[0086] Table 1 shows information about codebook monitoring types according to one embodiment of the present disclosure.

[0087] Index Codebook Monitoring Type 0 Metric function-based codebook monitoring 1 AI model-based codebook monitoring (codebook monitoring using proxy model) 2 Codebook PMI and quantized V (V q ) Codebook monitoring

[0088] For example, information about the codebook monitoring type may be composed of 2 bits. Referring to Table 1, '00' may indicate codebook monitoring based on a metric function of index 0, '01' may indicate codebook monitoring based on an AI model of index 1, and '10' may indicate codebook monitoring according to codebook PMI and quantized V. '11' may be a reserved bit. In the above example, information about the codebook monitoring type indicates an index corresponding to each codebook monitoring type. However, the scope of the present disclosure is not limited thereto. Information about the codebook monitoring type may be in the form of a bitmap (e.g., 3 bits), wherein each bit may correspond to one of the codebook monitoring types. The terminal may apply the codebook monitoring type corresponding to the bit set to '1' in the bitmap. For example, when AI model-based codebook monitoring is configured based on information about the codebook monitoring type, the configuration information may further include information about the AI ​​model used for codebook monitoring.

[0089] The settings for codebook monitoring reports provide information for reporting when a terminal reports codebook monitoring results to a base station. The settings for the codebook monitoring report may include at least one of periodicity, reporting offset, reporting value, or monitoring metric.

[0090] Table 2 is an example of settings for a codebook monitoring report according to one embodiment of the present disclosure.

[0091]

[0092] In Table 2, the index of the codebook monitoring type may correspond to the index of Table 1. Periodicity may indicate the time domain behavior of the codebook monitoring report. For example, the periodicity may be set to one of periodic, aperiodic, and semi-continuous. When the periodicity is set to periodic or semi-continuous, the configuration for the codebook monitoring report may further include information about the period. In addition, the periodicity may be set for each of the codebook monitoring types in Table 1.

[0093] The reporting offset indicates the monitoring interval to be included when reporting codebook monitoring results. Based on the reporting offset value, the terminal can determine how much of the previous time interval to report monitoring results from the reporting point. Furthermore, the reporting offset can be configured for each codebook monitoring type in Table 1.

[0094] For example, when applying a reporting offset, an offset value (e.g., offset A) may be predefined. In this case, the reporting offset field may be used to inform the terminal whether to apply the predefined offset value. In the example of Table 2, if the reporting offset field is set to '0', the terminal may transmit the codebook monitoring output (or codebook PMI and quantized V) at the reporting time to the base station. If the reporting offset field is set to '1', the terminal may report the codebook monitoring output (or codebook PMI and quantized V) from a time point prior to the reporting time by offset A to the reporting time.

[0095] As another example, the reporting offset field may indicate an offset value (e.g., offset A) that the terminal should apply. If the value of the reporting offset field is '0', the terminal may only report the codebook monitoring output (or codebook PMI and quantized V) at the reporting time. If the reporting offset is not 0, the terminal may apply the value as the value of offset A, and report the codebook monitoring output (or codebook PMI and quantized V) from a time point prior to the reporting time by offset A to the reporting time.

[0096] For example, the above reported offset value (e.g., offset A) may be in units of slot, sub-slot, or symbol.

[0097] The report value indicates the quantity that the terminal should report as a codebook monitoring result. The report value can be set only for metric function-based codebook monitoring (type 0) and AI model-based codebook monitoring (type 1). For example, it can be set to report the codebook monitoring output value (e.g., SGCS_CB, 0<=SGCS_CB<=1). Or, it can be set to report the difference value (e.g., SGCS_CB-SGCS_AI) between the codebook monitoring output and the monitoring output (SGCS_AI) of the AI / ML compression model. Or, it can be set to report the difference value (e.g., SGCS_AI-SGCS_CB) between the monitoring output of the AI / ML compression model and the codebook monitoring output.

[0098] The monitoring metric indicates which metric function to use when performing codebook monitoring based on a metric function. The monitoring metric can be set only when the information about the codebook monitoring type indicates codebook monitoring based on a metric function. For example, the monitoring metric information can indicate a metric function based on one of SGCS, GCS (Generalized cosine similarity), SINR (signal to interference and noise ratio), or MSE (mean square error). In addition to the methods mentioned above, the metric function indicated by the monitoring metric information may further include intermediate KPIs (key performance indicators) described (agreed upon) in the standard and various metric methods in the field of communications.

[0099] Table 2 shows the index corresponding to each parameter, but each piece of information can be set in bitmap form instead of an index.

[0100] At step 920, the base station can transmit a CSI-RS to the terminal. That is, the terminal can receive the CSI-RS from the base station. While the embodiments of the present disclosure focus on examples using CSI-RS, other downlink signals may also be used.

[0101] In step 930, the terminal may perform codebook monitoring based on the configuration information and CSI-RS. The terminal may perform codebook monitoring in a manner configured by information about the codebook monitoring type. For example, if information about the codebook monitoring type indicates codebook monitoring based on a metric function, the terminal may perform codebook monitoring using the metric function configured by the monitoring metric information. For example, if information about the codebook monitoring type indicates codebook monitoring based on an AI model, the terminal may perform codebook monitoring using an AI model. For example, if information about the codebook monitoring type indicates codebook monitoring based on codebook PMI and quantized V, the terminal may prepare to transmit the codebook PMI and quantized V to the base station for codebook monitoring of the base station, instead of performing codebook monitoring directly.

[0102] In step 940, the base station may receive a report including the results of codebook monitoring from the terminal. That is, the terminal may report the results of performing codebook monitoring to the base station. For example, the results of the codebook monitoring may be transmitted via uplink control information (UCI). The reported quantity may be in the form of a report value indicated in the codebook monitoring report configuration. For example, if the report value indicated in the codebook monitoring report configuration indicates index 0, the terminal may report the codebook monitoring output value itself. For example, if the report value indicated in the codebook monitoring report configuration indicates index 1 or 2, the terminal may report the difference between the codebook monitoring output value and the AI / ML-based CSI monitoring output. For example, if information about the codebook monitoring type indicates codebook monitoring according to the codebook PMI and quantized V, the terminal may transmit the codebook PMI and quantized V to the base station.

[0103] At step 950, the base station can determine the CSI reporting type based on the codebook monitoring report. The CSI reporting type can indicate whether to use AI / ML-based CSI reporting or codebook-based reporting.

[0104] For example, if the codebook monitoring results are higher than the AI / ML-based CSI monitoring results, the base station can switch from AI / ML-based CSI to codebook-based CSI. Another example is when the base station or terminal lacks AI / ML resources, the base station may decide to switch from AI / ML-based CSI to codebook-based CSI.

[0105] If the CSI reporting type is changed in step 950, the base station may transmit new configuration information (reconfiguration information) to the terminal in step 960 to inform the terminal of the changed CSI reporting type. That is, the terminal may receive new configuration information from the base station. The new configuration information may be transmitted via RRC signaling and may include information about the changed CSI reporting type.

[0106] FIG. 10 illustrates a procedure for periodically performing codebook monitoring on the terminal side according to one embodiment of the present disclosure.

[0107] Referring to FIG. 10, at step 1010, the terminal may receive configuration information from the base station. The configuration information may be transmitted via RRC signaling. Step 1010 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced. The periodicity included in the codebook monitoring report setting within the configuration information may be set to "periodic."

[0108] In step 1020, the terminal and the base station can perform an AI / ML-based CSI reporting procedure. Step 1020 may correspond to the process of FIG. 2. The terminal receives a CSI-RS from the base station and compresses the CSI derived based on the CSI-RS through an encoder in the terminal. The terminal can transmit a CSI report including the compressed latent vector (feature vector) through the encoder to the base station. The decoder in the base station can restore / decompress the CSI based on the received latent vector (feature vector).

[0109] In step 1030, the terminal and the base station may perform a codebook monitoring procedure. Step 1030 may correspond to steps 920 to 940 of FIG. 9. Therefore, the descriptions of steps 920 to 940 may be referred to. The terminal may perform codebook monitoring based on the received CSI-RS and report the codebook monitoring results to the base station. Based on the above-described configuration information, the terminal may periodically report the codebook monitoring results according to a set cycle. The reported quantity may be determined based on a report value included in the codebook monitoring reporting configuration.

[0110] In step 1040, the base station can determine the CSI reporting type based on the codebook monitoring results. Step 1040 may correspond to step 950 of FIG. 9, and thus, the description of step 950 may be referenced.

[0111] If the CSI reporting type is changed in step 1040, the base station may transmit reset information to the terminal in step 1050. Step 1050 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0112] Although the AI / ML-based CSI reporting procedure of step 1020 and the codebook monitoring reporting procedure of step 1030 are illustrated separately in FIG. 10, they are illustrated separately only to facilitate understanding of the present disclosure, and it is to be understood that the two steps may be performed simultaneously. For example, the terminal may receive a CSI-RS and perform CSI compression and codebook monitoring based on the received CSI-RS. Furthermore, the CSI reporting and codebook monitoring reporting may be performed separately, or together in a single step.

[0113] FIG. 11 illustrates a procedure for performing semi-continuous codebook monitoring on the terminal side according to one embodiment of the present disclosure.

[0114] Referring to FIG. 11, at step 1110, the terminal may receive configuration information from the base station. The configuration information may be transmitted via RRC signaling. Step 1110 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced. The periodicity included in the codebook monitoring report setting within the configuration information may be set to 'semi-continuous'.

[0115] At step 1120, the terminal and base station can perform an AI / ML-based CSI reporting procedure. Step 1120 may correspond to step 1020 of FIG. 10 , and thus, the description of step 1020 may be referenced.

[0116] At step 1125, the base station may transmit a message requesting a codebook monitoring report to the terminal. That is, the terminal may receive a message requesting a codebook monitoring report from the base station. For example, the request message may be transmitted via MAC-CE signaling or DCI.

[0117] After receiving the above request message, the terminal and the base station can perform a codebook monitoring procedure at step 1130. Step 1130 may correspond to steps 920 to 940 of FIG. 9. Therefore, the descriptions of steps 920 to 940 may be referred to. The terminal may perform codebook monitoring based on the received CSI-RS and report the codebook monitoring results to the base station. Based on the above configuration information, the terminal may semi-continuously report the codebook monitoring results according to a set cycle. The reported quantity may be determined based on a report value included in the codebook monitoring report configuration.

[0118] In step 1140, the base station can determine the CSI reporting type based on the codebook monitoring results. Step 1140 may correspond to step 950 of FIG. 9, and thus, the description of step 950 may be referenced.

[0119] If the CSI reporting type is changed in step 1140, the base station may transmit reset information to the terminal in step 1150. Step 1150 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0120] Although the AI / ML-based CSI reporting procedure of step 1120 and the codebook monitoring reporting procedure of step 1130 are illustrated separately in FIG. 11, they are merely illustrated separately to facilitate understanding of the present disclosure, and it is to be understood that the two steps may be performed simultaneously. For example, a terminal may receive a CSI-RS and perform CSI compression and codebook monitoring based on the received CSI-RS. Furthermore, CSI reporting and codebook monitoring reporting may be performed separately, or together in a single step.

[0121] FIG. 12 illustrates a procedure for reporting codebook monitoring results aperiodically according to one embodiment of the present disclosure.

[0122] Referring to FIG. 12, at step 1210, the terminal may receive configuration information from the base station. The configuration information may be transmitted via RRC signaling. Step 1210 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced. The periodicity included in the codebook monitoring report setting within the configuration information may be set to "aperiodic."

[0123] At step 1220, the terminal and base station can perform an AI / ML-based CSI reporting procedure. Step 1220 may correspond to step 1020 of FIG. 10 , and thus, the description of step 1020 may be referenced.

[0124] At step 1225, the terminal may receive a message requesting a codebook monitoring report. The request message may be received via one of RRC, MAC-CE, or DCI.

[0125] At step 1230, the terminal may report codebook monitoring results to the base station based on the above request. The reported quantity may be determined based on the reporting values ​​included in the codebook monitoring reporting settings.

[0126] In step 1240, the base station can determine the CSI reporting type based on the codebook monitoring results. Step 1240 may correspond to step 950 of FIG. 9, and thus, the description of step 950 may be referenced.

[0127] If the CSI reporting type is changed in step 1240, the base station may transmit reset information to the terminal in step 1250. Step 1250 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0128] FIG. 13 illustrates a procedure in which periodic codebook monitoring reports and aperiodic codebook monitoring reports are combined and performed at the terminal side according to one embodiment of the present disclosure.

[0129] Referring to FIG. 13, at step 1310, the terminal may receive configuration information from the base station. The configuration information may be transmitted via RRC signaling. Step 1310 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced. For example, the periodicity included in the codebook monitoring report settings within the configuration information may be set to "periodic."

[0130] At step 1320, the terminal and base station can perform an AI / ML-based CSI reporting procedure. Step 1320 may correspond to step 1020 of FIG. 10 , and thus, the description of step 1020 may be referenced.

[0131] At step 1330, the terminal and base station may perform a codebook monitoring reporting procedure. Step 1330 may correspond to step 1030 of FIG. 10 , and thus, the description of step 1030 may be referenced. The codebook monitoring reporting procedure may be performed repeatedly and periodically.

[0132] At step 1340, the terminal may receive a message requesting a codebook monitoring report. The request message may be received via one of RRC, MAC-CE, or DCI.

[0133] At step 1350, the terminal may report codebook monitoring results to the base station in response to the request. The reported quantity may be determined based on the reporting values ​​included in the codebook monitoring reporting settings.

[0134] In step 1360, the base station can determine the CSI reporting type based on the codebook monitoring results. The base station can use both the periodically reported codebook monitoring results in step 1330 and the aperiodically reported codebook monitoring results in step 1350 to determine whether to switch from AI / ML-based CSI to codebook-based CSI. Step 1360 may correspond to step 950 of FIG. 9, and thus, the description of step 950 may be referenced.

[0135] If there is a need to change the CSI reporting type, the base station may transmit reset information to the terminal at step 1370. Step 1370 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0136] FIG. 14a illustrates a procedure for reporting codebook monitoring results based on an event trigger according to one embodiment of the present disclosure.

[0137] Referring to FIG. 14a, at step 1410, the terminal may receive configuration information from the base station. This configuration information may be transmitted via RRC signaling. For example, this configuration information may be added to a CSI reporting configuration (e.g., CSI-reportconfig). Step 1410 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced.

[0138] For codebook monitoring based on event triggers, the above configuration information may further include configurations for codebook monitoring measurements. The configurations for codebook monitoring measurements may include (1) a codebook monitoring report event, (2) an offset value, and (3) a trigger condition.

[0139] The Codebook Monitoring Report event defines the conditions under which a terminal transmits codebook monitoring results to the base station. Regardless of the frequency of the codebook monitoring report settings, a terminal can transmit codebook monitoring results to the base station if the conditions defined for the Codebook Monitoring Report event are met.

[0140] Table 3 shows examples of codebook monitoring report events according to one embodiment of the present disclosure.

[0141]

[0142] Referring to Table 3, conditions can be set for determining whether a terminal transmits codebook monitoring results to a base station based on an index indicated by information about a codebook monitoring report event. The terminal can report codebook monitoring results to the base station if the conditions of the set event are satisfied. In Table 3, OutputCB,layer v, (v=1, 2, 3,...) represents the codebook-based CSI output at layer v, and Output th v(v=1, 2, 3,...) represents the threshold for each layer. OutputCB,AVGlayer represents the average codebook-based CSI output for all layers, and Output AVGth represents the average threshold to be applied to all layers. OutputAI,layer v, (v=1, 2, 3,...) represents the AI / ML-based CSI output at layer v, and OutputAI,AVGlayer represents the average AI / ML-based CSI output for all layers. For example, when index 0 is set, the codebook-based CSI output for layer 1 is set to the threshold (Output th1 ) is greater than the threshold, the terminal can report the codebook monitoring result to the base station. If the codebook-based CSI output for layer 1 is greater than the threshold (Output th1 ) is less than, the terminal may not report the codebook monitoring result to the base station.

[0143] For example, if index 5 is set, the terminal can report the codebook monitoring result to the base station if the average codebook-based CSI output for the entire layer is greater than the average AI / ML-based CSI output for the entire layer.

[0144] The events defined in Table 3 are merely examples and do not limit the technical scope of the present invention. It should be understood that other events may be additionally defined. For example, events using ">=" instead of ">" in Table 3 may be defined.

[0145] Table 4 illustrates examples of offset values ​​associated with event-triggered codebook monitoring according to one embodiment of the present disclosure. The offset values ​​in Table 4 are merely examples for illustrative purposes and do not limit the scope of the present disclosure. Therefore, other offset values ​​may be set, and may be set in units such as sub-slots or symbols, rather than slot units.

[0146] Index Offset Value 00 Offset 12 Offset (uses 2 past values) 24 Offset (uses 4 past values) 36 Offset (uses 6 past values)

[0147] The offset value indicates the offset to be applied when calculating the codebook output value. Referring to Table 4, for example, if the offset value is set to 0, the terminal can compare the codebook output value at the current time with a threshold value to determine whether the triggering condition is satisfied. If the offset value is set to 4, the terminal can compare the output values ​​from the previous 4 slots of the current slot to the current slot with a threshold value to determine whether the triggering condition is satisfied. Fig. 14b illustrates a case where the offset value is set to 2 according to an embodiment of the present disclosure. Referring to Fig. 14b, if the current slot is slot t and the offset value is set to 2, the terminal can compare the output values ​​in slot t-2, slot t-1, and slot t with a threshold value to determine whether the event triggering condition is satisfied.

[0148] If the offset is set to a non-zero value, a trigger condition can also be set. The terminal can determine whether the trigger condition is satisfied by comparing the average value across all slots to which the offset is applied with a threshold value, based on the trigger condition. Alternatively, the terminal can determine whether all output values ​​in each slot satisfy the trigger condition, based on the trigger condition.

[0149] Table 5 shows examples of trigger conditions associated with event trigger codebook monitoring according to one embodiment of the present disclosure.

[0150] Conditions for index triggering (condition to trigger) 0 The average value satisfies the codebook monitoring report event 1 All values ​​satisfy the codebook monitoring report event

[0151] For example, it can be assumed that the codebook monitoring report event is set to index 0 and the offset index is 1, i.e., 2 offsets are set. If the trigger condition is set to index 0, the terminal can compare the average output value in slot t-2, slot t-1, and slot t with a threshold value. If the trigger condition is set to index 1, the terminal can compare the output value in slot t-2 with the threshold value, the output value in slot t-1 with the threshold value, and the output value in slot t with the threshold value, and report the codebook monitoring result if the event trigger condition is satisfied in all slots. Although the index is indicated corresponding to each setting in Tables 3 to 5, the settings may also be indicated in the form of a bitmap. In step 1420, the terminal and the base station can perform an AI / ML-based CSI reporting procedure. Step 1402 may correspond to step 1020 of FIG. 10. The terminal can receive a CSI-RS from the base station and compress the CSI derived based on the CSI-RS through the terminal's encoder. The terminal can transmit a CSI report including the compressed latent vector (feature vector) through the encoder to the base station. The base station's decoder can restore / decompress the CSI based on the received latent vector (feature vector).

[0152] At step 1430, the terminal can receive a CSI-RS from the base station. The CSI-RS may be the CSI-RS received at step 1420.

[0153] At step 1440, the terminal can perform codebook monitoring based on the received CSI-RS.

[0154] At step 1450, the terminal can determine whether a codebook monitoring report is triggered. The terminal can determine whether the event trigger conditions set by the codebook monitoring report event information included in the configuration information are met.

[0155] If the above event trigger condition is satisfied, the terminal may transmit a scheduling request for uplink transmission to the base station in step 1455, and the terminal may receive an UL grant from the base station in step 1460. Alternatively, if resources for codebook monitoring reporting have already been allocated, steps 1455 and 1460 may be omitted.

[0156] If the above event trigger condition is satisfied, the terminal can transmit the codebook monitoring result to the base station based on the UL grant at step 1470.

[0157] In step 1480, the base station can determine the CSI reporting type based on the codebook monitoring results. Step 1480 may correspond to step 950 of FIG. 9, and thus, the description of step 950 may be referenced.

[0158] If the CSI reporting type changes, the base station may transmit reset information to the terminal in step 1490. Step 1490 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0159] In the procedures illustrated in FIGS. 9 through 14a, the base station determines whether to change the CSI reporting type based on the report on the codebook monitoring results received from the terminal. Additionally, upon receiving the codebook monitoring results, the base station may further request the terminal to provide the codebook PMI and quantized V to determine whether to change the CSI reporting type.

[0160] FIG. 15 illustrates a procedure for performing codebook monitoring further using codebook PMI and quantized V at the request of a base station according to one embodiment of the present disclosure.

[0161] Referring to FIG. 15, at step 1510, the terminal may receive configuration information from the base station. This configuration information may be transmitted via RRC signaling. Step 1510 may correspond to step 910 of FIG. 9, and thus, the description of step 910 may be referenced.

[0162] At step 1520, the terminal and base station can perform an AI / ML-based CSI reporting procedure. Step 1520 may correspond to step 1020 of FIG. 10 , and thus, the description of step 1020 may be referenced.

[0163] At step 1530, the terminal and base station can perform a codebook monitoring reporting procedure. Step 1530 may correspond to step 1030 of FIG. 10, and thus, the description of step 1030 may be referenced.

[0164] In step 1540, the terminal may receive a message requesting a codebook PMI and quantized V from the base station. The request message may be received via one of RRC, MAC-CE, or DCI. For example, the request message may be transmitted to determine whether to change the CSI reporting type when the codebook monitoring result received in step 1530 is below a threshold. The threshold may be predefined between the terminal and the base station. Alternatively, the threshold may be determined by a configuration of the base station.

[0165] At step 1550, the terminal may report the codebook monitoring results to the base station in response to the request. At this time, the terminal may report the codebook PMI and quantized V.

[0166] In step 1560, the base station can determine the CSI reporting type based on the codebook monitoring results. The base station can use both the codebook monitoring results reported in step 1530 and the codebook monitoring results reported in step 1550 (i.e., codebook PMI and quantized V) to determine whether to switch from AI / ML-based CSI to codebook-based CSI. Step 1560 may correspond to step 950 of FIG. 9 , and thus, the description of step 950 may be referenced.

[0167] If there is a need to change the CSI reporting type, the base station may transmit reset information to the terminal at step 1570. Step 1570 may correspond to step 960 of FIG. 9, and thus the description of step 960 may be referenced.

[0168] Although the above-described embodiments describe operations based on CSI-RS, the scope of the present disclosure is not limited thereto and can also be used for uplink channel estimation methods. Accordingly, it can also be used for methods using SRS (sounding reference signal).

[0169] When applying the aforementioned AL / ML-based compression technique to uplink channel estimation, the encoder in the autoencoder can be located on the network (e.g., base station) side, and the decoder can be located on the terminal side. Since the base station possesses both the estimated channel H and the codebook TPMI (transmit precoding matrix indicator) based on the SRS received from the terminal, the base station can directly perform codebook monitoring.

[0170] FIG. 16 illustrates a codebook monitoring procedure of a base station using SRS according to one embodiment of the present disclosure.

[0171] Referring to Figure 16, an AI / ML-based TPMI transmission procedure may be performed at step 1610. The base station may receive an SRS from the terminal. The base station (the base station's encoder) may transmit an AI / ML-based compressed TPMI to the terminal. The terminal's decoder may decompress the compressed result.

[0172] At step 1620, the base station can receive SRS from the terminal.

[0173] At step 1630, the base station can perform codebook monitoring. The codebook monitoring method may be a metric function-based codebook monitoring method described above or an AI model-based codebook monitoring method.

[0174] At step 1640, the base station can determine a TPMI type based on the codebook monitoring results. The TPMI type may represent either an AI / ML-based TPMI or a codebook-based TPMI.

[0175] For example, if the codebook monitoring results are higher than the AI / ML-based TPMI monitoring results, the base station can switch from the AI / ML-based TPMI to the codebook-based TPMI. Another example is when the AI / ML resources of the base station or terminal are insufficient, the base station can decide to switch from the AI / ML-based TPMI to the codebook-based TPMI.

[0176] At step 1650, the base station may notify the terminal of any changes in the TPMI feedback method by transmitting reset information. This reset information may be transmitted via RRC signaling. This reset information may include information indicating whether the TPMI is codebook-based or AI / ML-based.

[0177] FIG. 17 illustrates the structure of a terminal in a wireless communication system according to an embodiment of the present disclosure.

[0178] Referring to FIG. 17, the terminal may include a transceiver, which refers to a terminal receiving unit (1700) and a terminal transmitting unit (1710), a memory (not shown), and a terminal processing unit (1705, or a terminal control unit or processor). Depending on the communication method of the terminal described above, the transceiver units (1700, 1710), the memory, and the terminal processing unit (1705) of the terminal may operate. However, the components of the terminal are not limited to the examples described above. For example, the terminal may include more or fewer components than the components described above. In addition, the transceiver unit, the memory, and the processor may be implemented in the form of a single chip.

[0179] A transceiver unit can transmit and receive signals to and from a base station. Here, the signals may include control information and data. To this end, the transceiver unit may be configured with an RF transmitter that up-converts and amplifies the frequency of a transmitted signal, and an RF receiver that low-noise amplifies and down-converts the frequency of a received signal. However, this is only one embodiment of the transceiver unit, and the components of the transceiver unit are not limited to the RF transmitter and RF receiver. In addition, the transceiver unit may receive a signal through a wireless channel and output it to a processor, and transmit a signal output from the processor through the wireless channel.

[0180] Memory can store programs and data necessary for the operation of the terminal. Furthermore, memory can store control information or data included in signals transmitted and received by the terminal. Memory can be comprised of a storage medium, such as ROM, RAM, a hard disk, CD-ROM, or DVD, or a combination of such storage media. Furthermore, there can be multiple memories.

[0181] Additionally, the processor may control a series of processes so that the terminal can operate according to the aforementioned embodiments. For example, the processor may be configured to receive configuration information including information related to codebook monitoring of the terminal, receive a CSI-RS, perform codebook monitoring based on the configuration information and the CSI-RS, and transmit a report including the results of the codebook monitoring. There may be multiple processors, and the processors may perform component control operations of the terminal by executing a program stored in memory.

[0182] FIG. 18 illustrates the structure of a base station in a wireless communication system according to an embodiment of the present disclosure.

[0183] Referring to FIG. 18, the base station may include a transceiver, which refers to a base station receiver (1800) and a base station transmitter (1810), a memory (not shown), and a base station processor (1805, or a base station control unit or processor). Depending on the communication method of the base station described above, the transceiver (1800, 1810), the memory, and the base station processor (1805) of the base station may operate. However, the components of the base station are not limited to the examples described above. For example, the base station may include more or fewer components than the components described above. In addition, the transceiver, the memory, and the processor may be implemented in the form of a single chip.

[0184] A transceiver can transmit and receive signals with a terminal. Here, the signals can include control information and data. To this end, the transceiver can be configured with an RF transmitter that up-converts and amplifies the frequency of a transmitted signal, and an RF receiver that low-noise amplifies and frequency-converts a received signal. However, this is only one embodiment of the transceiver, and the components of the transceiver are not limited to the RF transmitter and RF receiver. In addition, the transceiver can receive a signal through a wireless channel, output it to a processor, and transmit the signal output from the processor through the wireless channel.

[0185] The memory can store programs and data necessary for the operation of the base station. Furthermore, the memory can store control information or data included in signals transmitted and received by the base station. The memory can be comprised of a storage medium, such as ROM, RAM, a hard disk, CD-ROM, or DVD, or a combination of such storage media. Furthermore, there can be multiple memories.

[0186] The processor may control a series of processes so that the base station can operate according to the embodiments of the present disclosure described above. For example, the processor may be configured to transmit configuration information including information related to codebook monitoring of the terminal to the terminal, transmit a CSI-RS to the terminal, and receive a report from the terminal including the results of codebook monitoring based on the configuration information and the CSI-RS. There may be multiple processors, and the processors may perform component control operations of the base station by executing a program stored in memory.

[0187] 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.

[0188] When implemented in software, 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 within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to the embodiments described in the claims or specification of the present disclosure.

[0189] 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 device, compact disc ROM (CD-ROM), digital versatile discs (DVDs) or other forms of optical storage device, magnetic cassette. Or, they may be stored in a memory configured as a combination of some or all of these. In addition, each configuration memory may be included in multiple numbers.

[0190] Additionally, the 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 local area network (WLAN), a storage area network (SAN), or a combination thereof. Such a 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.

[0191] In the specific embodiments of the present disclosure described above, components included in the invention 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.

[0192] Meanwhile, the embodiments of the present disclosure disclosed in this specification and drawings are merely specific examples to easily explain the technical contents of the present disclosure and help understand the present disclosure, and are not intended to limit the scope of the present disclosure. In other words, it will be apparent to those skilled in the art to which the present disclosure pertains that other modified examples based on the technical idea of ​​the present disclosure are possible. In addition, the above-mentioned embodiments can be combined and operated with each other as needed. For example, parts of one embodiment of the present disclosure and another embodiment can be combined with each other to operate a base station and a terminal.

[0193] Meanwhile, the order of description in the drawings explaining the method of the present invention does not necessarily correspond to the order of execution, and the order of precedence may be changed or executed in parallel.

[0194] Alternatively, the drawings illustrating the method of the present invention may omit some components and include only some components within a scope that does not harm the essence of the present invention.

[0195] In addition, the method of the present invention may be implemented by combining some or all of the contents included in each embodiment within a scope that does not harm the essence of the invention.

[0196] Various embodiments of the present disclosure have been described above. The foregoing description of the present disclosure is for illustrative purposes only, and the embodiments of the present disclosure are not limited to the disclosed embodiments. Those skilled in the art will appreciate that the present disclosure can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present disclosure. The scope of the present disclosure is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included within the scope of the present disclosure.

Claims

1. A method performed by a terminal in a wireless communication system, A step of receiving configuration information including information related to codebook monitoring of the terminal; A step of receiving a CSI-RS (channel state information-reference signal); A step of performing codebook monitoring based on the above setting information and the CSI-RS; and A step of transmitting a report including the results of the above codebook monitoring, A method wherein the information related to the above codebook monitoring includes first information about the codebook monitoring type and second information associated with the report.

2. In paragraph 1, A method characterized in that the first information indicates one of codebook monitoring based on a metric function, codebook monitoring based on an artificial intelligence (AI) model, or codebook monitoring by a base station.

3. In paragraph 2, If the first information indicates codebook monitoring based on the metric function, the second information includes information about the metric function, and A method characterized in that the information about the above metric function represents a metric function based on one of squared generalized cosine similarity (SGCS), generalized cosine similarity (GCS), signal to interference and noise ratio (SINR), or mean square error (MSE).

4. In paragraph 1, A method characterized in that the second information includes information about periodicity, report offset, and report value.

5. In paragraph 1, The information related to the above codebook monitoring further includes third information about the codebook monitoring measurement, and A method characterized in that the third information includes information about an event associated with a report of the codebook monitoring, an offset, and a condition for triggering by the event.

6. In paragraph 5, Further comprising a step of checking whether a set event has been satisfied based on information about an event associated with a report of the above codebook monitoring, A method characterized in that when the above-described set event is satisfied, a report including the results of the codebook monitoring is transmitted.

7. A method performed by a base station in a wireless communication system, A step of transmitting configuration information including information related to codebook monitoring of the terminal to the terminal; A step of transmitting a CSI-RS (channel state information-reference signal) to the terminal; and A step of receiving a report including the setting information and the result of codebook monitoring based on the CSI-RS from the terminal, A method wherein the information related to the above codebook monitoring includes first information about the codebook monitoring type and second information associated with the report.

8. In paragraph 7, A method characterized in that the first information indicates one of codebook monitoring based on a metric function, codebook monitoring based on an artificial intelligence (AI) model, or codebook monitoring by a base station.

9. In paragraph 8, If the first information indicates codebook monitoring based on the metric function, the second information includes information about the metric function, and A method characterized in that the information about the above metric function represents a metric function based on one of squared generalized cosine similarity (SGCS), generalized cosine similarity (GCS), signal to interference and noise ratio (SINR), or mean square error (MSE).

10. In paragraph 7, The information related to the above codebook monitoring further includes third information about the codebook monitoring measurement, The third information includes information about an event associated with the report of the codebook monitoring, an offset, and a condition for triggering by the event, and A method characterized in that a report including the results of the codebook monitoring is received when an event set based on information about an event associated with a report of the codebook monitoring is satisfied.

11. In paragraph 7, A step of determining whether to change the CSI report of the terminal from artificial intelligence or machine learning-based CSI to codebook-based CSI based on a report including the results of the above codebook monitoring; and A method characterized by further comprising a step of transmitting information about the codebook-based CSI to the terminal when it is decided to change to the codebook-based CSI.

12. In the terminal of a wireless communication system, At least one transceiver; and comprising at least one processor, said at least one processor comprising: Receive configuration information including information related to codebook monitoring of the above terminal, Receives CSI-RS (channel state information-reference signal), Perform codebook monitoring based on the above setting information and the CSI-RS, is set to transmit a report including the results of the above codebook monitoring, and A terminal, wherein the information related to the above codebook monitoring comprises first information about the codebook monitoring type and second information associated with the above report.

13. In paragraph 12, The above first information indicates one of codebook monitoring based on a metric function, codebook monitoring based on an artificial intelligence (AI) model, or codebook monitoring by a base station, and A terminal characterized in that the second information includes information about periodicity, report offset, and report value.

14. In a base station of a wireless communication system, At least one transceiver; and comprising at least one processor, said at least one processor comprising: Transmitting configuration information including information related to codebook monitoring of the terminal to the terminal, Transmits CSI-RS (channel state information-reference signal) to the above terminal, and is configured to receive a report including the result of codebook monitoring based on the setting information and the CSI-RS from the terminal, and A base station, wherein the information related to the above codebook monitoring includes first information about the codebook monitoring type and second information associated with the report.

15. In paragraph 14, The above first information indicates one of codebook monitoring based on a metric function, codebook monitoring based on an artificial intelligence (AI) model, or codebook monitoring by a base station, and A base station, characterized in that the second information includes information about periodicity, report offset, and report value.

Images