Method and device for beam management in wireless communication system

Abstract

This method may include the steps of: receiving, by a wireless user equipment, a reference signal from a base station in a wireless communication system; performing measurement for at least one of training and inference on the basis of the reference signal; and transmitting, to the base station, prediction beam information derived through an AI / ML model on the basis of the measurement, wherein the AI / ML model may be located in the wireless user equipment.

Description

Beam management method and device in a wireless communication system

[0001] The present disclosure relates to a method and device for managing beams in a wireless communication system. Specifically, the present disclosure relates to a method and device for managing beams based on artificial intelligence / machine learning (AI / ML).

[0002]

[0003] The International Telecommunication Union (ITU) is developing the International Mobile Telecommunication (IMT) framework and standards, and is currently discussing fifth-generation (5G) communications through a program called "IMT for 2020 and beyond."

[0004] To meet the requirements presented in "IMT for 2020 and beyond," the 3rd Generation Partnership Project (3GPP) NR (New Radio) system is being discussed to support various numerologies based on time-frequency resource units, taking into account various scenarios, service requirements, and potential system compatibility.

[0005] Additionally, 5G communications can support the transmission of physical signals or physical channels through multiple beams to overcome adverse channel conditions such as high path loss, phase noise, and frequency offset that occur at high carrier frequencies. Through this, 5G communications can support applications such as enhanced Mobile Broadband (eMBB), massive Machine Type Communications (mMTC), and Ultra Reliable and Low Latency Communication (URLLC).

[0006]

[0007] The technical problem of the present disclosure is a method and device for managing a beam in a wireless communication system.

[0008] The technical problem of the present disclosure is a method and device for managing a beam based on AI / ML.

[0009] The technical problem of the present disclosure is a method and device for deriving an optimal beam through an inference operation of an AI / ML model when AI / ML is located on the terminal side.

[0010] The technical problem of the present disclosure is a method and device for predicting a beam based on at least one of a spatial domain and a time domain based on AI / ML.

[0011] The technical problem of the present disclosure is a procedure and signaling for managing a beam based on AI / ML.

[0012] The technical problems to be achieved in the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by a person having ordinary skill in the technical field to which the present disclosure belongs from the description below.

[0013]

[0014] According to one aspect of the present disclosure, a wireless user device comprises the steps of receiving a reference signal from a base station, performing a measurement for at least one of training and inference based on the reference signal, and transmitting predicted beam information derived through an AI / ML model based on the measurement to the base station, wherein the AI / ML model can be located in the wireless user device.

[0015] Also, according to one aspect of the present disclosure, a wireless user device includes at least one processor and a memory storing instructions for causing the wireless user device to perform a specific operation by the at least one processor, wherein the specific operation comprises: receiving a reference signal from a base station, performing a measurement for at least one of training and inference based on the reference signal, and transmitting predicted beam information derived through an AI / ML model based on the measurement to the base station, wherein the AI / ML model can be located in the wireless user device.

[0016] Additionally, the following may be commonly applied:

[0017] According to one aspect of the present disclosure, a wireless user device can receive a reference signal after transmitting a reference signal transmission request to a base station, or can receive a reference signal based on reference signal configuration information transmitted by the base station without a reference signal transmission request.

[0018] In addition, according to one aspect of the present disclosure, the wireless user device generates data information as an AI / ML model input based on the measurement, wherein the data information may include at least one of: a reference signal received power (RSRP) value and beam-related information of all beams of set B or the highest beam K as a set of beams for channel measurement; a RSRP value and beam-related information of all beams of set A or the highest beam K as a set of beams corresponding to AI / ML model output values; beam ID information of the highest beam K for set A; time stamp information; and AI / ML model training-related information.

[0019] Additionally, according to one aspect of the present disclosure, the predicted beam information derived through the AI / ML model may include at least one of beam information for the highest K beams predicted from a set of beams, RSRP values ​​for the highest K beams, probability information for the highest K beams, and reliability information for the RSRP values ​​for the highest K beams.

[0020] Additionally, according to one aspect of the present disclosure, the wireless user device may perform measurements within a measurement window to obtain input values ​​of an AI / ML model, and derive predicted beam information corresponding to each of N time instances within the prediction window based on the AI / ML model, and report the derived predicted beam information to a base station.

[0021] Additionally, according to one aspect of the present disclosure, a first time instance within a prediction window may be determined based on a reference time, and time instances after the first time instance may be determined within the prediction window based on an offset value based on the first instance.

[0022] Additionally, according to one aspect of the present disclosure, the reference time may be determined based on at least one of a time instance for an inference report, a time instance for a channel state information (CSI) reference resource, and a time instance for a reference signal transmission opportunity within set B.

[0023]

[0024] According to the present disclosure, a beam management method in a wireless communication system can be provided.

[0025] According to the present disclosure, a method for managing a beam based on AI / ML can be provided.

[0026] According to the present disclosure, a method for deriving an optimal beam through an inference operation of an AI / ML model can be provided in a case where AI / ML is located on the terminal side.

[0027] According to the present disclosure, a method for predicting a beam based on at least one of a spatial domain and a temporal domain can be provided based on AI / ML.

[0028] According to the present disclosure, a procedure and signaling for managing a beam based on AI / ML can be provided.

[0029] According to the present disclosure, a procedure and signaling for managing a beam based on AI / ML in a wireless communication system can be provided.

[0030] 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.

[0031]

[0032] FIG. 1 is a drawing for explaining the frame structure of a wireless communication system to which the present disclosure can be applied.

[0033] FIG. 2 is a diagram showing the resource structure of a wireless communication system to which the present disclosure can be applied.

[0034] FIG. 3 is a diagram illustrating CSI-RS resources to which the present disclosure can be applied.

[0035] FIG. 4 is a diagram illustrating a type 1 CSI applicable to the present disclosure.

[0036] FIG. 5 is a diagram illustrating a method of using multiple SRSs that can be applied to the present disclosure.

[0037] FIG. 6 is a diagram illustrating a method for performing non-codebook based precoding that can be applied to the present disclosure.

[0038] FIG. 7 is a diagram illustrating CSI omission applicable to the present disclosure.

[0039] Figure 8 is a diagram illustrating AI / ML model life cycle management applicable to the present disclosure.

[0040] FIG. 9 is a diagram illustrating a method for performing AI / ML model training based on Type 1 applicable to the present disclosure.

[0041] FIG. 10 is a diagram illustrating a method for performing AI / ML model training based on Type 2 applicable to the present disclosure.

[0042] FIG. 11 is a diagram illustrating a method for performing AI / ML model training based on Type 3 applicable to the present disclosure.

[0043] FIG. 12 is a diagram illustrating a type of beam management procedure that can be applied to the present disclosure.

[0044] FIG. 13 is a diagram illustrating the LCM procedure when the AI / ML model applied to the present disclosure is located on a terminal.

[0045] FIG. 14 is a diagram illustrating a reference time determination method and a prediction window indication method applied to the present disclosure.

[0046] FIG. 15 is a flowchart of a method for performing beam management applicable to the present disclosure.

[0047] Figure 16 is a drawing showing a base station device and a terminal device to which the present disclosure can be applied.

[0048]

[0049] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein.

[0050] In describing embodiments of the present disclosure, detailed descriptions of known configurations or functions will be omitted if they are deemed to obscure the gist of the present disclosure. Furthermore, portions of the drawings that are irrelevant to the description of the present disclosure have been omitted, and similar portions are designated with similar reference numerals.

[0051] In the present disclosure, when a component is said to be "connected," "coupled," or "connected" to another component, this may include not only a direct connection, but also an indirect connection in which another component exists in between. Furthermore, when a component is said to "include" or "have" another component, unless otherwise specifically stated, this does not exclude the other component, but rather implies that the other component may be included.

[0052] In this disclosure, terms such as first, second, etc. are used solely to distinguish one component from another, and do not limit the order or importance of components unless specifically stated otherwise. Accordingly, within the scope of this disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment may be referred to as a first component in another embodiment.

[0053] In this disclosure, distinct components are used to clearly illustrate their respective characteristics, and do not necessarily imply that the components are separated. That is, multiple components may be integrated into a single hardware or software unit, or a single component may be distributed into multiple hardware or software units. Therefore, even if not specifically mentioned, such integrated or distributed embodiments are also included within the scope of this disclosure.

[0054] In the present disclosure, the components described in various embodiments are not necessarily essential components, and some may be optional components. Therefore, embodiments comprising a subset of the components described in one embodiment are also within the scope of the present disclosure. Furthermore, embodiments including other components in addition to the components described in various embodiments are also within the scope of the present disclosure.

[0055] The present disclosure describes a wireless communication network, and operations performed in the wireless communication network may be performed in a process of controlling the network and transmitting or receiving a signal in a system (e.g., a base station) that manages the wireless communication network, or in a process of transmitting or receiving a signal in a terminal connected to the wireless network.

[0056] It is self-evident that various operations performed for communication with terminals in a network consisting of multiple network nodes including a base station can be performed by the base station or other network nodes other than the base station. 'Base station (BS)' can be replaced by terms such as fixed station, Node B, eNodeB (eNB), ng-eNB, gNodeB (gNB), and access point (AP). In addition, 'terminal' can be replaced by terms such as UE (User Equipment), MS (Mobile Station), MSS (Mobile Subscriber Station), SS (Subscriber Station), and non-AP station (non-AP STA).

[0057] In the present disclosure, transmitting or receiving a channel means transmitting or receiving information or a signal through the channel. For example, transmitting a control channel means transmitting control information or a signal through the control channel. Similarly, transmitting a data channel means transmitting data information or a signal through the data channel.

[0058] In the following description, the term NR (New Radio) system is used for the purpose of distinguishing the system to which various examples of the present disclosure are applied from existing systems; however, the scope of the present disclosure is not limited by this term.

[0059] NR systems support a variety of subcarrier spacings (SCS) to accommodate diverse scenarios, service requirements, and potential system compatibility. Furthermore, NR systems can support the transmission of physical signals / channels across multiple beams to overcome challenging channel conditions, such as high path loss, phase noise, and frequency offsets that occur at high carrier frequencies. This enables NR systems to support applications such as enhanced Mobile Broadband (eMBB), massive Machine Type Communications (mMTC) / ultra Machine Type Communications (uMTC), and Ultra Reliable and Low Latency Communications (URLLC).

[0060] Hereinafter, 5G mobile communication technology can be defined to include not only the NR system, but also the existing LTE-A (Long Term Evolution-Advanced) system and LTE (Long Term Evolution) system. 5G mobile communication may include technology that operates in consideration of backward compatibility with previous systems as well as the newly defined NR system. Therefore, the 5G mobile communication below may include technology that operates based on the NR system and technology that operates based on previous systems (e.g., LTE-A, LTE), and is not limited to a specific system.

[0061] First, we would like to briefly explain the physical resource structure of the wireless communication system to which the present invention is applied.

[0062] FIG. 1 is a drawing for explaining an NR frame structure to which the present disclosure can be applied.

[0063] In NR, the basic unit of time domain is It can be, , and N can be 4096. Meanwhile, in LTE, the basic unit of the time domain is It can be, And, =2048. The constant for the multiplication relationship between the NR time base unit and the LTE time base unit is k= can be defined as

[0064] Referring to Figure 1, the time structure of a frame for downlink / uplink (DL / UL) transmission is can have. Here, one frame is It consists of 10 subframes corresponding to time. The number of consecutive OFDM symbols in each subframe is = It can be. In addition, each frame is divided into two half frames of the same size, half frame 1 can be composed of sub frames 0-4, and half frame 2 can be composed of sub frames 5-9.

[0065] represents the timing advance (TA) between the downlink (DL) and uplink (UL). Here, the transmission timing of the uplink transmission frame i is determined based on the downlink reception timing at the terminal, based on the following mathematical expression 1.

[0066] [Mathematical Formula 1]

[0067]

[0068]

[0069] Here, It may be a TA offset value that occurs due to differences in duplex mode, etc. In FDD (Frequency Division Duplex), has a value of 0, but in TDD (Time Division Duplex), it takes into account the margin for DL-UL switching time. It can be defined as a fixed value. For example, in TDD (Time Division Duplex) of FR1 (Frequency Range 1), which is a frequency below 6 GHz, is 39936 or 25600 It could be 39936 is 20.327μs, and 25600 is 13.030μs. Also, at FR2 (Frequency Range 2), which is a millimeter wave (mmWave) frequency, is 13792 It could be. At this time, 13792 is 7.020 μs.

[0070] FIG. 2 is a diagram showing an NR resource structure to which the present disclosure can be applied.

[0071] Resource elements (REs) within a resource grid can be indexed according to each subcarrier spacing. Here, one resource grid can be created for each antenna port and each subcarrier spacing. Uplink and downlink transmission and reception can be performed based on the corresponding resource grid.

[0072] In the frequency domain, one Resource Block (RB) consists of 12 REs, and each of the 12 REs can be configured with an index (nPRB) for one RB. The index for an RB can be utilized within a specific frequency band or system bandwidth. The index for an RB can be defined as in the following mathematical expression 2. Here, represents the number of subcarriers per RB, and k represents the subcarrier index.

[0073] [Equation 2]

[0074]

[0075]

[0076] Different numerologies can be configured to meet the diverse services and requirements of NR systems. For example, while LTE / LTE-A systems can support a single subcarrier spacing (SCS), NR systems can support multiple SCSs.

[0077] A new numerology for NR systems supporting multiple SCSs can operate in frequency ranges or carriers such as below 3GHz, 3GHz-6GHz, 6GHZ-52.6GHz or above 52.6GHz to address the issue of not being able to use wide bandwidth in frequency ranges or carriers such as 700MHz or 2GHz.

[0078] Table 1 below shows examples of numerologies supported by the NR system.

[0079] [Table 1]

[0080]

[0081]

[0082] Referring to Table 1 above, the numeral can be defined based on the subcarrier spacing (SCS), cyclic prefix (CP) length, and number of OFDM symbols per slot used in the Orthogonal Frequency Division Multiplexing (OFDM) system. The above values ​​can be provided to the terminal through the upper layer parameters DL-BWP-mu and DL-BWP-cp for the downlink, and through the upper layer parameters UL-BWP-mu and UL-BWP-cp for the uplink.

[0083] In Table 1 above, when the subcarrier spacing setting index (u) is 2, the subcarrier spacing (Δf) is 60 kHz, and normal CP and extended CP can be applied. For other numerology indices, only normal CP can be applied.

[0084] A normal slot can be defined as the basic time unit used to transmit a single piece of data and control information in an NR system. The length of a normal slot can be set to the number of OFDM symbols, which is 14 by default. Furthermore, unlike slots, a subframe has an absolute time length equivalent to 1 ms in an NR system and can be used as a reference time for the length of other time intervals. Here, for coexistence or backward compatibility between LTE and NR systems, a time interval similar to an LTE subframe may be required in the NR standard.

[0085] For example, in LTE, data can be transmitted based on a unit of time called a Transmission Time Interval (TTI), which can be set to one or more subframes. Here, one subframe can be set to 1ms and can contain 14 OFDM symbols (or 12 OFDM symbols).

[0086] In addition, a non-slot can be defined in NR. A non-slot can mean a slot having a number that is at least one symbol smaller than a normal slot. For example, in the case of providing low latency such as URLLC service, latency can be reduced through a non-slot having a number of symbols smaller than a normal slot. Here, the number of OFDM symbols included in a non-slot can be determined by considering the frequency range. For example, a non-slot with a length of 1 OFDM symbol can be considered in a frequency range of 6 GHz or higher. As an additional example, the number of OFDM symbols defining a non-slot can include at least 2 OFDM symbols. Here, the range of the number of OFDM symbols included in a non-slot can be set as the length of a mini-slot up to a predetermined length (e.g., the normal slot length - 1). However, as a specification of a non-slot, the number of OFDM symbols may be limited to 2, 4, or 7 symbols, but is not limited thereto.

[0087] Additionally, for example, in unlicensed bands below 6 GHz, subcarrier spacing where u equals 1 and 2 may be used, and in unlicensed bands above 6 GHz, subcarrier spacing where u equals 3 and 4 may be used. For example, when u equals 4, it may be used for SSB (Synchronization Signal Block).

[0088] [Table 2]

[0089]

[0090]

[0091] Table 2 shows the number of OFDM symbols per slot for normal CP, by subcarrier spacing setting (u). ), number of slots per frame ( ), number of slots per subframe ( ) is shown. Table 2 shows the above-described values ​​based on a normal slot having 14 OFDM symbols.

[0092] [Table 3]

[0093]

[0094]

[0095] Table 3 shows the number of slots per frame and the number of slots per subframe based on normal slots with 12 OFDM symbols per slot when extended CP is applied (i.e., when u is 2 and the subcarrier spacing is 60 kHz).

[0096] As mentioned above, one subframe may correspond to 1ms on the time axis. Furthermore, one slot may correspond to 14 symbols on the time axis. For example, one slot may correspond to 7 symbols on the time axis. Accordingly, the number of slots and symbols that can be considered within 10ms corresponding to one radio frame may be set differently. Table 4 may show the number of slots and symbols according to each SCS. In Table 4, the 480kHz SCS may not be considered, but the present invention is not limited to these examples.

[0097] [Table 4]

[0098]

[0099]

[0100] A terminal can calculate downlink CSI parameters (e.g., CQI, PMI, RI, L1-RSRP, etc.) through a DL (downlink) CSI (channel state information) reporting procedure and report the calculated CSI information to a base station. The base station can utilize the received CSI information for downlink data transmission. The CSI parameters are measurement values ​​associated with a channel state, and the base station can perform downlink data transmission based on the measurement values. The base station can instruct the terminal about data scheduling information based on the CSI parameters. The terminal generally reports the CSI calculation and derived CSI parameters to the base station as feedback information by receiving a CSI-RS transmitted by the base station. Alternatively, the terminal can measure the channel state through another downlink signal (e.g., SSB (synchronization signal block)) in addition to the CSI-RS and report the measured value to the base station.

[0101]

[0102] Select RI (rank indicator):

[0103] RI can be a CSI parameter that indicates the number of layers available for downlink transmission in a specific channel environment. RI can also indicate the maximum number of uncorrelated paths available for downlink transmission. Here, other CSI parameters (e.g., PMI, CQI) can be calculated based on the rank provided by RI.

[0104]

[0105] Select precoding matrix index (PMI):

[0106] A PMI may include a set of indices corresponding to a precoding matrix. The base station may apply the PMI reported by the terminal to downlink transmission. However, the base station may have the freedom to apply a precoding matrix other than the PMI. For example, the standard may support multiple types of codebooks to report the precoding matrix for the PMI. Each codebook type is described below.

[0107] Codebook type

[0108] - Type 1 single-panel codebooks

[0109] - Type 1 multi-panel codebooks

[0110] - Type 2 codebooks

[0111] - Enhanced Type 2 codebooks

[0112]

[0113] For example, PMI selection may be performed based on the codebook type, the number of transmission layers represented by RI values, and other CSI reporting configuration parameters (e.g., antenna panel dimensions). Each codebook may include a set of precoding matrices. For example, in NR, a dual-stage precoding matrix codebook design may be applied, but is not limited thereto.

[0114] The dual-stage precoding matrix may be as shown in Equation 3 below. In Equation 3, W1 may be a matrix representing a DFT (discrete Fourier transform) beam or a beam group for both polarizations according to the codebook type, and W2 may be selected from one of the following according to the codebook type.

[0115] W2 codebook type

[0116] - Beam selection from W1

[0117] - Weighting coefficients for the beams in W1

[0118] - Cophasing values ​​between two polarizations

[0119]

[0120] [Equation 3]

[0121]

[0122]

[0123] The terminal calculates a PMI value that represents the highest SINR (signal interference noise ratio) value at the receiver using the codebook selected for "Type I single-panel codebook" and "Type I multi-panel codebook" as the codebook type and all possible precoding matrices in the given channel environment. For example, a Type 1 codebook may be considered for PMI selection in a single user multi-input multi-output (SU-MIMO) scenario, but is not limited thereto.

[0124] A Type II codebook can consider a set of orthogonal DFT beams. In Equation 3, the W1 matrix contains information associated with the DFT beams, and the PMI selection function calculates beam amplitude scaling and cophasing values ​​(W2) for all DFT beams within each orthogonal beam group for a given channel environment and number of DFT beams. The terminal can report the i1 and i2 values ​​to the base station based on the PMI selection function, and each index corresponds to a precoding matrix (W) that provides the maximum SINR value. A Type II codebook-based PMI can provide more accurate channel information than a Type I codebook-based PMI. A Type II codebook can provide more accurate channel information because multiple beams are applied to estimate the channel eigenvector. For example, a Type II codebook-based PMI can be used in a MU (multi)-MIMO scenario because it considers multiple beams, but is not limited thereto. For example, a Type 2 codebook can only support up to Rank 2, while an enhanced Type 2 codebook can support up to Rank 4 with overhead reduction methods, which will be described later.

[0125] Furthermore, based on the above, CSI reporting performed by a terminal may consider explicit CSI feedback and implicit CSI feedback. Explicit CSI feedback is a method in which the terminal directly feeds back channel information (e.g., channel eigenvector / eigenvalue, SVD) indicating the channel state measured by the terminal, and may not consider how the base station processes the reported CSI. On the other hand, implicit CSI feedback may be a method in which a selected precoder matrix (desired precoder matrix) W within a set of candidate precoder matrices from a possible precoder codebook is indicated.

[0126] For example, CSI parameters (or CSI contents) related to CSI feedback may be as shown in Table 5 below, but may not be limited thereto.

[0127] [Table 5]

[0128]

[0129]

[0130] The CSI content within a CSI report can be set by different combinations of the CSI parameters in Table 5. Here, the CSI content within a CSI report can be set by reportQuantity.

[0131] For example, if set to "none", the base station may trigger aperiodic CSI-RS transmission. Aperiodic CSI-RS transmission may be triggered by the terminal for channel measurement and receiver parameter adjustment, and related CSI reporting may not be performed by the terminal. Aperiodic CSI-RS transmission may be, but is not limited to, aperiodic transmission of CSI-RS or TRS (tracking reference signal) for tracking purposes for synchronization purposes, or spatial aperiodic receive beam sweeping for the terminal to adjust the receive filter. The following operations do not require the base station to report aperiodic CSI to the terminal, but may operate within the same framework as aperiodic CSI requests.

[0132] - Aperiodic transmission of the Tracking Reference Signal (TRS or CSI-RS for tracking)

[0133] - Aperiodic Rx beam sweeping (so called P3 beam sweep) - adjusts the Rx spatial received filter to the UE

[0134]

[0135] Additionally, CSI contents within a single CSI report may be set as shown in Table 6 below, but may not be limited thereto. For example, the combinations of CSI contents in Table 6 below are representative combinations of CSI contents that a base station will primarily need.

[0136] [Table 6]

[0137]

[0138]

[0139] For example, “cri-RI-i1” in Table 6 can operate based on “Hybrid beamformed / non-precoded CSI acquisition operation” as shown in FIG. 3.

[0140] The base station can mainly use UE-specific beamformed CSI-RS (320) with several ports per CSI-RS resource for the purpose of CSI acquisition. However, in order for the base station to recognize how to beamform the CSI-RS for each UE, non-precoded CSI-RS resources (310) can be transmitted in the middle together with multiple antenna ports (e.g., 32 ports). Here, the UE can report PMI corresponding to all antenna ports (e.g., 32 ports) based on the received CSI-RS, thereby indicating a preferred beam direction. For example, beamforming of the CSI-RS can be based on the wideband / long-term part of the reported precoder. That is, the reported W1 metrics can be used to perform UE-specific CSI-RS beamforming. Additionally, the short-term subband CS (short-term / subband CSI) (W2) can be determined from the beamforming CSI-RS.

[0141] For example, non-precoded CSI-RS (310) can be used to identify how CSI-RS beamforming is performed, and based on this, the terminal may only need to report CSI corresponding to W1 and not report for W2. This can reduce overhead.

[0142] Additionally, the terminal can select a PMI based on a specific number of transmit antennas. Specifically, the terminal can select a PMI based on a specific number of transmit antennas given by the number of antenna ports of a configured CSI-RS associated with the reporting configuration.

[0143] Additionally, in the case of MU-MIMO scheduling, the base station may select a PMI other than the PMI reported by the target terminal, taking into account interference or channel conditions from other terminals simultaneously scheduled. Considering the above, two types of CSI can be defined in a wireless communication system, as shown in Table 7 below.

[0144] [Table 7]

[0145]

[0146]

[0147] Specifically, type 1 CSI may have different sub-codebook formats based on different antenna configurations at the transmitter. As an example, FIG. 4 is a diagram illustrating type 1 CSI applicable to the present disclosure. Specifically, FIG. 4(a) may be a case where 16 antenna ports are configured with (N1, N2) = (4, 2). The precoding matrix W for type 1 single panel CSI may be expressed as the product of two matrices (W1, W2), each of which may be independently reported as a different part of the overall PMI. For example, W1 may reflect long-term frequency independent channel characteristics, and thus may report channel information corresponding to the entire bandwidth (Wideband reporting). For example, W1 may be as shown in Equation 4 below. W1 may indicate a set of beams pointing in different directions, and matrix B may define one beam. In Equation 4, based on the 2 X 2 block structure, there can be two polarizations, and the selection of W1 can be a limited set that has the same beam direction.

[0148] [Equation 4]

[0149]

[0150]

[0151] As a concrete example, for rank 1 or 2, a single beam or four neighboring beams can be indicated by the W1 matrix. The correct beam among the four neighboring beams can be selected by W2 reported for each subband, thereby selecting an optimized beam for each subband. Furthermore, W2 can provide cophasing between two polarizations. If W1 defines a single beam, then W2 in B, which is a single-column matrix, can only provide cophasing between two polarizations. On the other hand, if multiple neighboring beams are defined by W1, W2 can select one correct beam and provide cophasing between two polarizations within that beam.

[0152] On the other hand, if the rank is greater than 2, W1 can define N neighboring orthogonal beams, which can be as shown in Equation 5. In Equation 5, N beams used for transmission of R transmission layers can be indicated, and W2 can only provide cophasing between two polarizations. Here, transmission to the same terminal can be possible for up to 8 transmission layers.

[0153] [Equation 5]

[0154]

[0155]

[0156] On the other hand, W2 is short-term and can potentially indicate different channel characteristics depending on the frequency. W2 may not be reported in certain cases. Here, the base station can randomly select W2 for each physical resource block group (PRG), and the terminal can select the channel quality indicator (CQI) based on this assumption.

[0157] Also, Fig. 4(b) may be a Type 1 multi-panel CSI. Multi-panel CSI may be applied considering a case where multiple antenna panels are used at a base station. Here, coherence between different panels may be difficult to guarantee. For example, Fig. 4(b) may be a case where (N1, N2) = (4, 1) and there are 32 antenna ports by 4 panels, but the present invention is not limited thereto. Here, the difference between the single panel of Fig. 4(a) and the multi-panel of Fig. 4(b) is that coherence may be difficult to guarantee between the antenna ports of different antenna panels. In the multi-panel, W1 may be the same set of beams for different polarizations and panels, just like in the single panel. On the other hand, in the case of the multi-panel, W2 may provide cophasing not only between polarizations but also between multi-panels for each subband.

[0158] Type 2 CSI can provide channel information with higher spatial granularity than Type 1 CSI and can be primarily applied to MU-MIMO scenarios. For example, Type 2 CSI may be limited to a maximum of two ranks, while Enhanced Type 2 CSI may be extended to four ranks, but may not be limited to a specific form. For convenience of explanation, the terms Type 2 CSI and Enhanced Type 2 CSI are referred to below, but may not be limited thereto.

[0159] Here, in the above-described mathematical expressions 3 and 4, W1 may be a wideband report. Type 2 CSI may report up to four beams, corresponding to four columns within B. W2 may provide amplitude values ​​(partially wideband and partially subband reporting) and phase values ​​(subband reporting) for each of the four reported beams and two polarizations within B.

[0160] Type 2 CSI can provide more detailed channel model information than Type 1, providing main ray, amplitude, and phase information. Based on the CSI reported from multiple terminals, the base station can determine which combinations of terminals are appropriate for simultaneous transmission on the same time / frequency resource.

[0161] Additionally, enhanced Type 2 CSI (e.g., Rel-16 enhanced Type 2 CSI) may be considered. Enhanced Type 2 CSI can report a set of beams on the wideband, similar to Type 2 CSI, along with a set of combining coefficients on an additional narrowband. Here, the reported beams can be linearly combined using the combining coefficients to provide a set of precoder vectors for each transmission layer. For example, in the existing Type 2 CSI, the combining coefficient value can be reported independently for each subband. Therefore, even considering the fact that the channels between adjacent subbands are highly correlated, the existing Type 2 CSI must report a relatively large combining coefficient value on a per-subband basis, which can increase the overhead. Enhanced Type 2 CSI can utilize frequency correlation to reduce this overhead. Furthermore, enhanced Type 2 CSI can improve the frequency-domain granularity of the PMI report. For example, compression operations can be applied to subbands or half-subbands based on frequency domain units. While conventional Type 2 CSI uses one precoder per subband, enhanced Type 2 CSI can use a recommended precoder for each frequency domain unit. However, actual reporting can be performed together for all frequency units. Specifically, given layer k, the reported precoders for all frequency domain units can be expressed as in Equation 6 below, where N can be the number of frequency domain units.

[0162] [Equation 6]

[0163]

[0164]

[0165] Here, Equation 6 may not be a mapping of layers and antennas, but may mean a set of precoder vectors for the entire set of frequency domain units for layer k. For the entire k layers, there may be a set of k precoder vectors, each set may consist of N precoder vectors, and the layer and antenna port mapping for a specific frequency domain unit n may be as shown in Equation 6 below.

[0166] Additionally, in the expression for vectors in Equation 7, W1 can be the same as Equation 4 described above, which is the same as the existing Type 2 CSI.

[0167] [Equation 7]

[0168]

[0169] Here, the B columns can correspond to the L selected beams, and W1 can be the same for all frequency domain units. (wideband reporting) Also, W1 can be the same for all layers.

[0170] Additionally, as an example, the enhanced Type 2 CSI has a compression matrix (size M x N) can be considered. can be constructed as a set of row vectors from the DFT basis, and can provide a transformation from N dimensions in the frequency domain (N frequency domain units) to M dimensions in the smaller delay domain. can be frequency independent, but can be reported independently for each layer. That is, can be a single common metric for all frequency domain units, but can be reported independently for each layer. The number of rows can be equal to M in Equation 8. In Equation 8, R can be the number of frequency domain units per subframe (R=1 or 2), and p can be a configurable parameter that controls the amount of compression.

[0171] [Equation 8]

[0172]

[0173] Finally (2L x M) can perform mapping from the delay domain to the beam domain. For example, W2 of the existing Type 2 CSI can generate a similar matrix for all subbands, and the matrix can be mapped from the frequency (subband) domain to the beam domain. On the other hand, can perform allocation from a smaller delay domain to a beam domain. can be adjusted by the reported rank and compression factor parameters p, which allows reporting based on fewer parameters. In addition, You can adjust the amount of CSI to be reported through the value, which allows you to get a smaller Fewer parameters can be reported based on size.

[0174] Additionally, as an example, the enhanced Type 2 CSI may be expanded to a maximum of 4 reported ranks and a maximum number of selectable beams to 6, with reduced overhead and improved frequency domain granularity. Table 8 below may illustrate possible configurations of the enhanced Type 2 CSI, but is not limited thereto.

[0175] [Table 8]

[0176]

[0177]

[0178] Additionally, multi-antenna precoding can be considered in uplink transmission. PUSCH (physical uplink shared channel) MIMO precoding can support up to four layers. For uplink transmission, DFT-based precoding can only support single-user (SU) MIMO. For example, a terminal can perform codebook-based transmission and non-codebook-based transmission with two different PUSCH precoding modes. In case of codebook-based precoding, the uplink grant transmitted by the base station can include precoder-related information (e.g., PMI). It is assumed that the terminal uses the precoder provided by the base station in the uplink differently from the downlink transmission. Furthermore, coherence can be assumed between the terminal antennas in uplink MIMO transmission, and the phases of the signals transmitted on the two antennas can be adjusted. Here, if there is no coherence between the antenna ports, each antenna port may result in a random relative phase, which may mean that the use of antenna port specific weight factors is limited.

[0179] For example, the coherence between antenna ports can correspond to any one of full coherence, partial coherence, and no coherence, and the corresponding information can be provided as terminal capability information. In addition, the use of multiple sounding reference signals (SRS) for codebook-based PUSCH can be considered. FIG. 5 is a diagram illustrating a method of using multiple SRSs applicable to the present disclosure. Referring to FIG. 5, a terminal can transmit relatively large beams on a multi-port SRS. For example, the beams can correspond to different terminal antenna panels (in different directions), and each panel can include a set of antenna elements. That is, each panel can correspond to antenna ports of a multi-port SRS. The base station can transmit an SRI (SRS Resource Indicator) to the terminal to determine whether to perform transmission through which beam. The terminal can determine which transmission to perform within the selected beam based on the number of layers and precoder using SRI and precoder information.

[0180] FIG. 6 is a diagram illustrating a method for performing non-codebook-based precoding applicable to the present disclosure. Referring to FIG. 6, when performing non-codebook-based precoding, a terminal can perform transmission based on a precoder indication and channel measurement received from a base station. In codebook-based precoding, the terminal performs transmission based on an uplink precoder selected based on channel measurement by the base station, but in non-codebook, uplink transmission can be performed through a precoder selected based on measurement based on channel reciprocity. Here, each column of the precoder matrix W can be a digital beam for a corresponding layer. When the terminal selects a precoder for N layers, it can be regarded as selecting N different beam directions, and each beam can correspond to one possible layer.

[0181] For example, referring to FIG. 6, a terminal may be capable of PUSCH transmission based on the selected precoding. However, the precoder selected by the terminal based on downlink channel measurements may not be the optimal precoder from the base station's perspective. Considering the above, the base station may modify the precoder selected by the terminal. For example, the base station may remove some beams or some columns selected by the terminal from the precoder and transmit information about this to the terminal. Specifically, the base station may indicate the result of beam selection based on measured SRS information back to the terminal through SRI. Based on the indicated information, the terminal may perform only some beam transmissions, which may implicitly indicate reduced layer transmission.

[0182]

[0183] A terminal can transmit uplink control information (UCI) to a base station. For example, the terminal can simultaneously transmit UCI on a physical uplink control channel (PUCCH) and a PUSCH. Specifically, the terminal can be instructed with a "simultaneous PUCCH and PUSCH transmission" parameter through upper layer signaling or dynamic signaling, and can configure simultaneous PUCCH and PUSCH transmission for UCI. That is, the terminal can be configured to perform simultaneous transmission for PUCCH and PUSCH. Here, if PUCCH and PUSCH are transmitted on the same carrier, "non-single carrier waveform transmission" may occur. Accordingly, PUCCH and PUSCH can be transmitted based on a large transmission backoff (e.g., 10 dB) based on frequency location resource allocation size, transmission power, and other factors. On the other hand, when PUCCH and PUSCH are transmitted on different carriers, a large power backoff may or may not be required based on a single power amplitude (PA) or multiple PAs.

[0184] As another example, if simultaneous transmission on PUCCH and PUSCH is required, the UE may drop the PUCCH and transmit UCI on the PUSCH. For example, the UCI type piggybacked on the PUSCH may be at least one of HARQ (hybrid automatic repeat and request), CSI type 1, and CSI type 2. On the other hand, the SR (scheduling request) may not be piggybacked on the PUSCH and may be replaced with a BSR (buffer state report), but is not limited thereto.

[0185] Upper layer parameter beta The value is used to determine the amount of radio resources transmitted on the PUSCH, and this value can be indicated to the UE from the base station. The beta value can have a wide range based on the amount of radio resources. When the UE transmits UCI on the PUSCH, the UE can determine the amount of radio resources required for UCI transmission by considering the UCI payload size on the PUSCH and the PUSCH spectral efficiency along with the above-mentioned beta value. This can prevent unnecessary resource usage for UCI, and the corresponding operation can be controlled by upper-layer parameters.

[0186] Additionally, as an example, the size of the UCI information bits may vary depending on the UCI type, and thus different UCI handling methods may be considered. Consider the cases in Table 9 below.

[0187] [Table 9]

[0188]

[0189]

[0190]

[0191] [Table 10]

[0192]

[0193]

[0194] For example, in case of PUCCH-based subband CSI reporting and PUSCH-based reports with Type 1 CSI feedback, CSI Part 1 may include RI (if reported) and CSI-RS Resource Indicator (CRI) (if reported). In addition, CSI Part 1 may include CQI for the first codeword (first CW). CSI Part 2 may include CQI and PMI for the second CW when RI is greater than 4.

[0195] CSI Part 1 may additionally include an indication of the number of "non-zero wideband amplitude coefficients per layer" for Type 2 CSI feedback over PUSCH. Here, the "wideband amplitude coefficient" is part of Type 2 CB, and the PMI payload size may vary depending on whether the coefficient value is zero or not.

[0196] Additionally, CSI Part 1 and CSI Part 2 can each be set based on Table 11 and Table 12.

[0197] [Table 11]

[0198]

[0199]

[0200] [Table 12]

[0201]

[0202]

[0203] Additionally, diverse uplink data scheduling may be required. The beta value can be dynamically indicated to the UE, taking into account the potentially different QoS requirements for each UCI and UCI of the PUSCH. For example, the base station can indicate one of four different beta values ​​pre-configured through higher layers via downlink control information (DCI).

[0204] For example, when allocating UCI on PUSCH, HARQ may have the highest priority, followed by CSI Type 1 and CSI Type 2. The priority may be determined based on whether the UCI is mapped closely to the DMRS on the PUSCH on which it is transmitted.

[0205] Here, in case of UCI 1 or 2-bit HARQ, some REs can be reserved for puncturing by pretending to be 2-bit HARQ bits, and the corresponding information can be transmitted through puncturing. In addition, in case of UCI greater than 2-bit HARQ and CSI Part 1 and CSI Part 2, rate matching can be performed starting from the available REs from the right non-DMRS symbol after the first DMRS symbol, and HARQ can be performed first, followed by CSI Part 1 and CSI Part 2.

[0206] Additionally, for example, CSI Part 1 may not be allocated to REs reserved for HARQ to avoid being punctured by HARQ. On the other hand, CSI Part 2 and uplink data may be allocated to REs reserved for HARQ (i.e., potentially entailing puncturing).

[0207] UCI on PUSCH can be allocated in frequency order and then in time order. That is, UCI on PUSCH can be allocated starting from the lowest available RE of the lowest available symbol. As described above, the base station can decode UCI quickly. In order to maximize the frequency diversity gain for UCI on PUSCH within one uplink symbol, REs for UCI can be allocated in a 'frequency-distributed' manner, but is not limited thereto. Specifically, the distance (d) between two adjacent REs within one orthogonal frequency division multiplexing (OFDM) symbol to which UCI is allocated can be set to 1 (d=1) when the number of modulation symbols to be allocated for UCI is greater than or equal to the number of REs available within the uplink symbol.

[0208] Otherwise, d can be determined by floor(number of available REs in an uplink symbol / number of modulation symbols to be allocated for UCI). Here, d>1 for a UL symbol, and the allocation of UCI modulation symbols in that symbol can be frequency distributed. In addition, all UCI types can be allocated to all layers of PUSCH transmission and use the same PUSCH modulation. For example, CSI can be allocated only to the layer with the highest modulation coding scheme (MCS), but is not limited thereto.

[0209] For example, in UL MIMO transmission, 2 TBs are used in LTE, but in 5G NR, 4-layer UL MIMO transmissions are used for one TB, so CSI can be allocated only to the layer with the highest MCS.

[0210] Additionally, when frequency hopping is enabled on the PUSCH, UCI modulation symbols can be divided into two parts of approximately equal size. These two parts can be assigned to each of the two hops, and can be divided into approximately equal parts. Accordingly, the negative impact on uplink data due to UCI piggybacking on the PUSCH can be equally distributed across the two hops.

[0211]

[0212] Additionally, partial CSI omission can be considered in PUSCH-based CSI reporting. In PUSCH-based CSI reporting and Type 2 CSI reporting, the CSI payload size can dynamically change depending on the Rank Indicator (RI) selection. For example, when Type 2 CSI reporting is performed, the PMI payload when RI is 2 can be approximately twice as large as the PMI payload when RI is 1. Since the base station cannot recognize the RI selection in advance, it can perform scheduling by predicting the RI value that the UE is likely to select when performing PUSCH scheduling. Therefore, a misalignment due to RI selection may occur between the base station and the UE. If the RI selected by the UE is larger than the RI value expected by the base station, the CSI payload size may increase, which may prevent it from being included on the PUSCH. In other words, the code rate may be too high or uncoded systematic bits may not be included. In the above-described case, instead of dropping the CSI report, the terminal can report some high-priority CSI information to the base station via PUSCH through partial CSI omission.

[0213] As an example, FIG. 7 is a diagram illustrating CSI omission applicable to the present disclosure. Referring to FIG. 7, some (710) of the CSI information may be included in the report, and the remaining part (720) may be omitted from the report. As an example, the terminal may perform ordering of CSI contents within CSI Part 2. When multiple CSI reports are transmitted on the PUSCH, wideband CSI components (i.e., wideband PMI and CQI) in all CSI reports are allocated to the most significant bit (MSB) of the UCI, and subband CSI (each CSI report) may be allocated in the manner of "even SB CSI - odd SB CSI - even SB CSI", which may be as shown in FIG. 7.

[0214] For example, if the UCI code rate exceeds a threshold, some of the UCI least significant bit (LSB) bits may be omitted. Here, the omission (720) may be performed until the code rate falls below the threshold, which may be as shown in FIG. 7. As an example, in FIG. 7, "SB CSI for odd numbered" may be omitted first, but the present invention may not be limited thereto.

[0215] For example, a base station can interpolate PMI / CQI by estimating missing PMI / CQI values ​​in the frequency domain. That is, omission can be performed based on the above-described order so that the base station can estimate the maximum interpolation for some of the omitted SB CSIs. This can maintain higher performance than omitting all consecutive SB CSIs.

[0216]

[0217] For example, AI / ML (artificial intelligence / machine learning)-based operations may be performed below. The terms in Table 13 below may be used within the AI / ML-based framework, but may not be limited thereto.

[0218] [Table 13]

[0219]

[0220]

[0221]

[0222]

[0223] For example, deep learning, a subcategory of machine learning (ML), can be a method that focuses on parameterizing multi-layer neural networks. Deep learning can be a method for learning representativeness of data and has demonstrated high performance in image classification, speech recognition, and natural language processing. However, deep learning can require a large amount of data during the training process, and the computational complexity required to train deep learning-based models on large data sets can be high, necessitating high hardware performance.

[0224] Regarding AI / ML, AI / ML-based mobile communications can be implemented. For example, AI has been able to reduce CAPEX and OPEX costs by managing data from devices operating on existing wireless communication systems. Furthermore, the introduction of next-generation networks may require low operating costs and high return-to-cost compensation, and AI can help address the complexity and optimization challenges of network operations. Furthermore, network intelligence and automation may be critical issues in next-generation mobile communication systems, and these challenges can be addressed using AI / ML. For example, budget management, network management, equipment lifecycle management, service level agreement (SLA) management, network performance management, and network planning can be implemented using AI / ML. AI / ML can enhance the Quality of Experience (QoE) of network operation and usage, but is not limited to this. Furthermore, AI / ML can improve network quality and enhance the provision of more personalized services, but is not limited to a specific form.

[0225]

[0226] For example, AI / ML-based operations may consider two types of operations: model generation and inference operations. Model generation may be performed based on model training, model validation, model testing, and application stages. For example, model training may be performed based on at least one of input / output, pre-processing / post-processing, and online / offline application, but may not be limited thereto.

[0227] In addition, inference operations can be performed based on input / output, pre / post-processing, and application stages. A general AI / ML framework and an AI / ML model life cycle management (LCM) procedure can be performed based on the following steps. As an example, FIG. 8 is a diagram illustrating an AI / ML model life cycle management applicable to the present disclosure. Referring to FIG. 8, data collection for an AI / ML model can be performed. Here, the collected data can include data for model training, monitoring data for model management and performance monitoring, and inference data for model inference. Model training can perform model learning based on training data, and the learned and updated model can be stored. Here, the model can be stored based on a function or model identifier or an identifier related to the model and additional information, but is not limited to a specific form. In addition, model training can be performed based on model training control information based on model management and performance monitoring.

[0228] Model management and performance monitoring can control model inference based on monitoring data. Model management and performance monitoring can control the activation / deactivation / selection / switching / fallback of model inference, as well as other operations. Model management and performance monitoring can obtain information about the results of model inference. Model inference can obtain inference data, perform inference operations, and obtain result information. Model inference can receive models stored in storage and perform inference operations based on them.

[0229] In relation to the LCM (life cycle management) process, one AI / ML model may have one model ID and related information and / or model functions for AI / ML operations, as described above.

[0230] Actions within the LCM procedure

[0231] - Data Collection

[0232] - Model Training

[0233] - Functionality / model identification

[0234] - Model transfer

[0235] - Model Inference

[0236] - Functionality / model selection, activation, deactivation, switching and fallback operation

[0237] - Functionality / model monitoring

[0238] - Model update

[0239] - Model Storage

[0240] - UE capability

[0241]

[0242] For example, AI / ML-based operations in wireless communication systems can consider the following cases. However, this is only one example, and AIML-based operations can also be applied to other cases.

[0243] AI / ML-based operation of wireless communication systems

[0244] CSI (Channel State Information): compression (**), temporal prediction (*)

[0245] BM(Beam Management): spatial prediction (*), temporal prediction (*)

[0246] Positioning: direct (*), assisted (*)

[0247] (**) is a two-side model (*) is a single-side model

[0248]

[0249] As a concrete example, we can consider AI / ML model training collaborations for CSI compression using a two-sided model.

[0250] For example, with respect to CSI compression, AI / ML model inference can be performed on both the terminal and the base station. That is, AI / ML model inference can be performed on the two-side. To this end, a CSI generation part can be configured on the terminal, and a CSI reconstruction part corresponding to the CSI generation part can be configured on the base station. The CSI generation part is a part for CSI compression, and the CSI reconstruction part can be used to obtain (recover) more accurate CSI for better MU (multi-user) scheduling operation in a massive MIMO scenario, but is not limited thereto, and cooperation on the two-side AI / ML model can be performed in various forms.

[0251] As another example, considering the limitations of the terminal's capability or computing power, it may be considered that a third entity (e.g., a server for the terminal) performs AI / ML model training or inference operations. That is, the terminal-side operations (e.g., model training / inference / monitoring / switching / activation / deactivation / validation / testing) in the above-described AI / ML operations may include the operations of other entities and are not limited to a specific form.

[0252] For example, training collaboration can consider Types 1 through 3 below. In the following, all AI / ML model-related operations performed at the base station or network are assumed to be performed at the network level. However, this may not be limited. Since the "network" is an inclusive term that includes the base station, the two terms may be used interchangeably. What is performed at the network can encompass both the base station side and the broader network side. For convenience of explanation, the following description will be described as being performed at the network.

[0253]

[0254] For example, joint training can be performed based on Type 1. Type 1 can be a method in which training for an AI / ML model is performed on one side / entity. Other sides / entities can then obtain specific model parts through downloading / uploading, and CSI feedback operations can be performed based on these.

[0255] As a specific example, FIG. 9 is a diagram illustrating a method for performing AI / ML model training based on Type 1. Referring to FIG. 9, model training for the CSI generation part of the terminal and the CSI reconstruction part of the base station can be performed on the network (920) side in a joint training manner. Thereafter, the network side can provide the trained model information to the terminal (910) through downloading and can also apply it to the network (920). As another example, model training for the CSI generation part of the terminal and the CSI reconstruction part of the base station can be performed on the terminal (910) side in a joint training manner. Thereafter, the terminal side can apply the trained model information to the terminal (910) and provide it to the network (920) through an uplink. In other words, an AI / ML model can be trained on one side / entity, and the trained AI / ML model can be transferred to another side / entity.

[0256] As a specific example, network-side model 1 training can train the CSI generation part using a data set related to CSI generation for training purposes in the network, and train the CSI reconstruction part by transferring the result value into the training loop of the CSI reconstruction part. Here, the CSI reconstruction part located in the base station can be utilized for subsequent AI / ML model-based CSI feedback. On the other hand, the CSI generation part (i.e., CSI encoder) that performed model training by the base station can transfer the trained model information to the terminal via the wireless interface (UE download AI / ML model). The terminal can perform the AI / ML model-based CSI feedback operation using the downloaded CSI generation part model. That is, CSI compression can be performed through the CSI generation part to perform CSI feedback.

[0257] On the other hand, when the AI / ML model is trained on the terminal side, terminal-side Type 1 training can train the CSI generation part using a data set of CSI generation for training purposes at the terminal. Then, the output value can be provided to the training loop of the CSI reconstruction part, and the CSI reconstruction part can be trained based on the output value. For example, the CSI generation part located at the terminal can be used to generate CSI feedback information based on the AI / ML model. The CSI reconstruction part (i.e., the CSI decoder) that performed the model training by the base station can transmit the trained model information to the base station via the wireless interface (UE upload AI / ML model). Thereafter, the base station can perform the AI / ML model-based CSI feedback operation using the CSI reconstruction part model received through the terminal upload. That is, CSI feedback can be performed by recovering CSI feedback information through the CSI reconstruction part.

[0258] Additionally, AI / ML model joint training type 1 may require AI / ML model exchange. For example, AI / ML model inference may require a common reference for model inference and a common AI / ML model inference algorithm, which may require AL / ML model exchange. For example, terminal-specific joint training type 1 may perform AI / ML model transfer based on the open format of the AI / ML model structure recognized by the terminal. On the other hand, non-terminal-specific joint training type 1 may mean model transfer within an open format without the terminal being aware of the AI / ML model structure. For example, when training a terminal-side model on the network side, the terminal-specific model may be trained on the network side based on the terminal capabilities and the terminal model structure, but may not be limited to a specific form.

[0259]

[0260] As another example, FIG. 10 is a diagram illustrating a method for performing AI / ML model training based on Type 2 applicable to the present disclosure. Referring to FIG. 10 , Type 2 model training may be identical to Type 1 in that both the CSI generation part and the CSI reconstruction part are performed within a single, identical loop. However, Type 2 model training differs from Type 1 in that training is not performed on a specific side / entity, but on both sides / entities. That is, both the network and the terminal may be involved in the training.

[0261] For example, referring to FIG. 10, the terminal side can perform a forward propagation (FP) operation based on a data sample. That is, the terminal (1010) can generate a CSI feedback result and transmit the FP result as information thereon to the network side. Thereafter, the network (1020) can perform a CSI reconstruction operation based on the FP result, thereby training the CSI reconstruction part. The network side can generate BP (backward propagation) information (e.g., gradients) based on the above-described method and transmit the generated BP information back to the terminal side. The terminal side can perform training for the CSI generation part based on the BP information received from the network side. Here, the data set can be aligned on both the terminal side and the network side, and training can be performed through the above-described method.

[0262] Also, as an example, FIG. 11 is a diagram illustrating a method for performing AI / ML model training based on Type 3 applicable to the present disclosure. Referring to FIG. 11, Type 3 model training is a sequential training method, and unlike the joint training of Types 1 and 2, model training can be performed sequentially / independently for each node. That is, Type 3 model training can be performed based on the exchange of aligned data set information between a branch station and a terminal within a separate loop, without training the CSI generation part and the CSI reconstruction part within the same loop. For example, Type 3 model training can be distinguished into network-first training or terminal-first training, similar to Type 1 model training.

[0263] Referring to Figure 11, in the case of network-first training, the network may use the CSI generation part for training the CSI reconstruction model set on the network side. However, the CSI generation part is for training purposes and may not be used in subsequent model inference.

[0264] The network (1020) side inputs the CSI generation part's input values ​​( ) based on the corresponding CSI generation part and its output value ( ) and the final output value ( through model training of the CSI reconstruction part based on this ) can be generated. The CSI reconstruction part for which training is completed can be used for the AI / ML-based CSI feedback operation of the network. Thereafter, the network (1120) side can share the data set information (e.g., dataset including labels and intermediate results) utilized in the model training of the network side with the terminal after the model training is completed. The terminal (1110) side can apply the data set information to the CSI generation part training. Thereafter, a joint inference operation can be performed through the CSI generation part performed on the terminal (1110) side and the CSI reconstruction part performed on the network (1120). In addition, information on the CSI generation part trained on the terminal (1110) side (e.g., model / functionality identification process - information on available CSI generation parts) can be reported or transmitted to the network (1120). The network (1120) can select or optimize a CSI reconstruction part corresponding to the CSI generation part model of the terminal based on information about the CSI generation part obtained from the terminal (1110).

[0265] As an example, options for training a terminal-side CSI generation model for network-first type 3 joint training can be considered as shown in Table 14 below.

[0266] [Table 14]

[0267]

[0268]

[0269] The terminal-side CSI output format or the base station-side CSI input format may be as shown in Table 15 below. That is, the CSI generated by the terminal by considering AI / ML and transmitted to the base station may be in the form of Table 15 below. Option 1 in Table 15 may be a case where the terminal-side CSI output format or the base station-side CSI input format is in the form of a precoding matrix similar to the existing CSI feedback. The terminal may report CSI feedback to the base station in the form of a precoding matrix together with the confirmed layer number information. For example, the terminal may report CSI feedback in the angular-delay domain as the domain of option 1-b in Table 15, but may not be limited to the embodiment. (e.g., via spatial-frequency DFT domain transformation to angular / delay domain)

[0270] On the other hand, option 2 in Table 15 may be a case where the terminal-side CSI output format or the base station-side CSI input format is a channel matrix with explicit CSI feedback. That is, the explicit CSI feedback of option 2 may not include precoding vectors assigned to each layer as a channel matrix. The explicit channel matrix may be based on channels in the space-frequency domain (option 2-a) or based on channels in the angle-delay domain (option 2-b), but is not limited to a specific form. For example, in the angle-delay domain of option 2-b, loss may be caused by sub-selection of angle-delay domain-based indices, but is not limited thereto.

[0271] [Table 15]

[0272]

[0273]

[0274] Additionally, as an example, applicable new content and transmission methods between AI CSI reports for AI / ML-based CSI compression may be as shown in Tables 16 and 17 below. The priority applied by reflecting AI CSI reports may be determined based on Table 16 below.

[0275] [Table 16]

[0276]

[0277]

[0278] [Table 17]

[0279]

[0280]

[0281]

[0282] For example, the input values ​​for AI / ML-based encoders can be the eigenvectors of the raw channel matrix (H) or the ray channel matrix (V). Here, if the raw channel matrix is ​​the input, the eigenvector calculation may be performed at the base station, which may increase the complexity of the base station. For example, the raw channel matrix may contain unnecessary information for precoder selection, which may increase unnecessary feedback overhead.

[0283] Therefore, considering the above-described characteristics, the AI ​​reporting procedure can be performed by considering which CSI content information will be used as input values ​​for the AI ​​encoder. Furthermore, by determining which CSI content information may impact the AI ​​decoder and how its performance may change accordingly, the AI ​​CSI reporting procedure can be performed by combining appropriate input values ​​from the input values ​​in Tables 16 and 17 described above, but is not limited to a specific format.

[0284] For example, when comparing AI / ML-based quantized CSI compression information for an AI / ML-based CSI feedback mechanism with existing CSI report / contents, the AI / ML-based CSI report fields may have differences as shown in Table 18 below.

[0285] [Table 18]

[0286]

[0287]

[0288] FIG. 12 is a diagram showing a type of beam management procedure applicable to the present disclosure.

[0289] In wireless communication systems, digital precoding-based beamforming can be considered alongside analog beamforming as a beam management method. For example, while analog beamforming can be easily implemented, it can only perform transmit / receive beamforming in one direction at a time. Therefore, analog beamforming can suffer from time delays when multiple beam sweeps are required. Furthermore, a case can be considered where a large number of antennas are used for beamforming. Using a large number of antennas can narrow the beam width and increase the probability of beam tracking failure. If a UE fails beam tracking, it can trigger a beam recovery procedure to recover the beam. Furthermore, each cell can perform beam-based transmission and reception at multiple transmission points. However, since the UE is unaware of the beam-based transmissions of each cell, the beam management procedure can be UE-transparent. Beam correspondence can mean that a transmitting and receiving node have a single appropriate beam pair. For example, beam correspondence may not imply tracking a rapidly changing and frequency-selective channel. Furthermore, beam correspondence may not always require downlink and uplink transmissions to be performed on the same frequency carrier. Therefore, beam correspondence can also be applied to frequency division multiplex (FDD) systems.

[0290] FIG. 12 may be a beam management procedure type and beam management process applicable to the present disclosure. For example, referring to FIG. 12(a), in order to support selection of a base station (1210) transmission beam and a terminal (1220) reception beam, the terminal may perform measurements for selecting a transmission beam on multiple transmission beams. That is, the base station (1210) may perform multiple transmission beam transmissions based on various beam types, and the terminal (1220) may perform measurements on multiple transmission beams transmitted by the base station (1210). Thereafter, the terminal (1220) may select a transmission beam with the best reception quality based on the measurements. The terminal (1220) may report information on the selected transmission beam to the base station (1210) through explicit or implicit signaling. The base station (1210) may then consider the reported transmission beam information as information for narrower beam transmission. As an example, FIG. 12(a) may be, but is not limited to, a P-1 beam management process.

[0291] Referring to Fig. 12(b), the terminal (1240) can perform measurements for different narrow beams. That is, Fig. 12(b) may be a beam refinement procedure for selecting a narrower beam. For example, Fig. 12(b) may be, but is not limited to, a P-2 beam management process. The base station (1230) and the terminal (1240) may perform a procedure for selecting a rough transmission beam according to Fig. 12(a) and then determining a more detailed transmission beam within the transmission beam direction. Here, the base station (1230) may perform different CSI-RS (channel state information-reference signal) transmissions based on different beams. Here, the terminal (1240) may measure only the transmission beams without Rx sweeping. The terminal (1240) can report to the base station (1230) the L1-RSRP (reference signal received power) and CRI (CSI-RS Resource Indicator) for beams with the highest quality based on the measurement.

[0292] Referring to Fig. 12(c), the terminal (1260) can perform reception beam readjustment. Fig. 12(c) may be a P-3 beam management process, but is not limited thereto. Here, the base station (1250) can transmit a CSI-RS having the same transmission beam to the terminal (1260). The terminal (1260) can measure the quality of the reception beam through which the corresponding CSI-RS is received, and select the reception beam based on the quality. However, the terminal (1260) may not report any information about the reception beam selection to the base station (1250). Beam management can be performed based on the above, and the following describes a method of applying an AI / ML algorithm when performing beam management.

[0293]

[0294] Below, we describe a beam management method based on an AI / ML (artificial intelligence / machine learning) model. For example, existing beam management methods, as described above, may have required beam sweeping and sparse beam sweeping for narrow beams between a base station and a terminal. However, since the base station generally transmits using narrow beams in frequency range 2 (FR2), beam sweeping overhead needs to be considered. The beam management operations and procedures between the base station and the terminal may have limitations in that they rely on sparse beam sweeping due to excessive beam sweeping overhead. Therefore, there may be limitations in finding the optimal beam between the base station and the terminal, which may result in degradation of wireless signal transmission and reception.

[0295] Considering the above, a beam management scheme based on AI / ML models is described below. The AI / ML model can perform beam management operations by pretraining at least one of the spatial and temporal aspects of the channel. This allows for improved performance and lower beam management overhead compared to non-AI / ML-based beam management techniques. Furthermore, as described above, reduced delay can be achieved.

[0296] For example, optimal transmission / reception (Tx / Rx) beam information between a base station and a terminal may continuously change based on time / space and frequency due to the mobility of the terminal and the variability of the wireless channel environment in a mobile communication network. Here, the base station may have limitations in performing frequent beam sweeping procedures due to beam sweeping overhead. Considering the above, the base station has no choice but to continuously use the beam information acquired from the previous beam sweeping until the next beam sweeping cycle.

[0297] For example, if beam information obtained from a previous sweep is no longer valid, the transmission and reception performance of data and control channels based on that beam information may be significantly degraded. Therefore, a new beam management method that performs beam management based on an AI / ML model may be required, and a procedure for AI / ML model-based beam management and signaling based on the procedure may be required. Below, a method for performing AI / ML-based beam management procedures is described.

[0298] For example, if an AI / ML model is located on the terminal side, the terminal needs to report the inference result value as the output of the AI / ML model to the base station. Here, the location of the AI / ML model on the terminal side may mean that the AI / ML model is located on the terminal device itself or on an over-the-top (OTT) server. In other words, it may mean that the AI / ML model is located not only within the terminal device, but also on any network, server, or similar device managed by the terminal vendor to perform the LCM procedure on the terminal side.

[0299]

[0300] A beam management method applied in a wireless communication system may include a process of deriving an optimal combination of transmission / reception (Tx / Rx) beams between a base station side (NW side) and a terminal side (UE side). When performing beam management operation based on an AI / ML model, reduction of radio resource overhead, reduction of delay time for selecting an optimal beam pair, and improvement of wireless data transmission / reception performance through selection of an optimal Tx beam may be considered. When an AI / ML model is located on the terminal side, the terminal may be required to report (or transmit) the inference (or inference) result value of the AI / ML model to the base station.

[0301] Figure 13 is a diagram illustrating the LCM procedure when the AI / ML model applied to the present disclosure is located on a terminal. Referring to Figure 13, the terminal (user equipment, UE, 1310) may need to acquire channel measurement values ​​to perform model training or inference operations. The terminal (1310) may request the base station (NW, 1320) to transmit a related reference signal (RS) (e.g., synchronization signal block (SSB) / channel state information-reference signal (CSI-RS)) for channel measurement. Alternatively, the base station (1320) may provide the terminal (1310) with various configuration information required for the LCM procedure, including related RS configuration, based on UE capabilities information to perform a beam management method applying an AI / ML model without the above-described request. The base station (1320) may provide various configuration information to the terminal (1310) and transmit a related RS (e.g., SSB / CSI-RS) to the terminal (1310) based on the above-described configuration information. The terminal (1310) may receive the related RS to obtain channel measurement values ​​and use the channel measurement values ​​for at least one of model training and inference.

[0302] The terminal (1310) side may use channel measurement values ​​as data information required for at least one of training and inference. The data information may include L1-RSRP (L1-reference signal received power) values ​​and beam-related information of all beams or top-K beams of a set of beams for channel measurement (e.g., set B). In addition, the data information may include L1-RSRP values ​​and beam-related information of all beams or top-K beams of a set of beams (e.g., set A) corresponding to AI / ML model output values, and top-K beam IDs for the set of beams (e.g., set A) corresponding to AI / ML model output values. In addition, in the case of BM-case 2, the data information (or data set information) may include at least one of associated timestamp information, additional information required for other model training, and other information. The data information may include all or some combination of the above-described information, and is not limited to a specific form.

[0303] Here, BM-case 1 may be a method for selecting the optimal beam based on the AI / ML model. That is, BM-case 1 may be a method for performing prediction in the spatial domain by deriving a beam set (Set A) as an AI / ML model output based on the results of a beam set (Set B) measured at a specific point in time based on the AI / ML model. BM-case 2 may be a method for performing prediction by considering the time domain by deriving a current (or future) beam set (Set A) based on the historical data of beams (Set B) measured at past time instances. In addition, as an example, Set B may be a measured beam (or beam set), and Set A may be a predicted beam (or beam set).

[0304] When data information (or data set information) is used for training an AI / ML model, the required contents may differ depending on the AI / ML model type. Here, when measured data information is used as an input value for AI / ML model inference, predicted beam / L1-RSRP values ​​as AI / ML model output values ​​may be generated on the terminal side. The terminal (1310) may report beam prediction information, which is an AI / ML model output value, to the base station (1320). Based on the above-described information, the base station (1320) may obtain information on an optimal narrow beam preferred by the terminal side. Based on the above-described beam information, the base station (1320) may determine a transmission beam for subsequent data / RS transmission. Thereafter, beam indication information regarding which beam has been selected on the base station side may be transmitted from the base station side to the terminal side.

[0305] In addition, monitoring of AI / ML models located on the terminal side can be performed on the base station side (Type 1) or the terminal side (Type 2) depending on the type or method of AI / ML model performance monitoring. For example, when performing Type 1 performance monitoring, the terminal side needs to calculate and report to the base station the measured beam measurement value or performance metric information required for model monitoring. The base station side can verify the validity of the performance of the AI / ML model currently being operated on the terminal side based on the acquired performance metric information. Here, if the performance monitoring metric value is lower than any standard or threshold value, the base station side can instruct or request deactivation / switching / fallback or other actions to disable the AI / ML model located on the terminal side. On the other hand, when performing Type 2 (i.e. terminal-side) performance monitoring, the terminal side can calculate performance metric values ​​and independently determine whether to change the AI / ML model based on the calculated values ​​and perform the corresponding LCM operation.

[0306]

[0307] Below, we describe a method for reporting the inference result value, which is the output value of an AI / ML model located on the terminal side, to the base station. For example, based on the BM Case-1 described above, at least one of the possible inference result values, as shown in Table 19 below, can be reported to the base station. Referring to Table 19, each alternative can be a combination of content for the possible inference result values. Inference result values ​​generated on the terminal side can be reported to the base station through a combination of at least one or more of the Alts in Table 19.

[0308] [Table 19]

[0309]

[0310]

[0311] The K value in Alt of Table 19 described above can be at least one value. In addition, the K value in Alt can be a maximum of 64 or 256, but is not limited thereto and other values ​​can also be used. The base station (NW) can provide the beam-related settings of set A to the terminal for prediction (i.e. inference output) performed on the terminal side where the AI / ML model is located. In addition, the base station can provide beam-related settings information of set B to the terminal for inference performance, and the terminal can use it as an input value of the corresponding AI / ML model after performing measurement. For example, the set B settings can be basically configured by including 'CSI-resourceConfigID' information in 'CSI reportConfig' based on the existing CSI framework. In addition, the set A settings can also be configured based on the existing CSI framework similarly to the set B settings.

[0312] As another example, set A beams can be indicated by mapping to RS resources. However, the above-described mapping may have a disadvantage of increasing the RS resource configuration set for set A, thereby increasing resource overhead. Since one of the main purposes of applying the actual AI / ML model is to avoid this overhead in the beam management procedure, it may be preferable not to consider an operation that runs counter to this motivation, if possible, in the beam management procedure based on the AI / ML model. Accordingly, if the wireless channel environment causes a lot of overhead in consideration of the overhead for RS resources for indicating set A beams at the base station, the RS resource configuration for indicating set A beams can be avoided, and only the RS resource configuration for beams within set B can be provided.

[0313] As another example, beams of set A may be configured to be directed based on an associated ID with set B. That is, beams within set A may be directed based on association information related to the association IDs between beams of set A and set B. As a specific example, an association between set A and set B may be determined based on whether they have the same associated ID.

[0314] If set A and set B have the same association ID, the terminal can assume that the DL Tx beam or beam set / list within the two sets have similar Tx beam characteristics. That is, the DL Tx physical beam / beam set / list of set A and set B can have the same measurement resource mapping / order based on their consistent characteristics. Here, an additional beam ID (A-Beam ID) can be used for more precise indication information for the beams of set A. The A-Beam ID is used to indicate set A beam information based on beam setting information within set B from 'set B -> set A' among sets having the same associated ID. The A-Beam ID can be used to distinguish the most suitable beam or the closest beam information among the beams within the set.

[0315] That is, the associated ID may be an ID that the terminal uses as an identifier to distinguish the network conditions (NW conditions) (e.g., DL Tx RF filter, cell / site related information, NW specific environmental information, etc.) for training and inference of the base station in the case of a terminal-side AI / ML model, so as to operate a specific AI / ML model. If the above-mentioned IDs are the same, the terminal can assume that there are consistent physical beam characteristics between the beam measurement values ​​(set B), which are input values ​​of the AI / ML model, and the inference result values ​​(set A), which are output values ​​of the model. Accordingly, the terminal can determine which AI / ML model's beam measurement values ​​of one set B should be used as the input values ​​and which set A's beams corresponding to the output values ​​for the model's inference should be reported to the base station. Here, the A-Beam ID value can be additionally utilized to distinguish a specific transmission beam among multiple beams within set A.

[0316] Here, the beam information described above can be reported based on the RS resource ID (e.g., CSI-RS Resource Indicator (CRI), SSBRI (SSB Resource Indicator)), beam ID, or associated ID information included in set A. Alternatively, the terminal can report the beam information to the base station based on a combination of the ID values ​​described above. Here, the probability information on the reliability of the predicted Top K beams can provide the probability value of the reliability for each inference result as an inference result value according to the AI / ML model type. Accordingly, the predicted Top K beams having values ​​(i.e., higher reliability) higher than a threshold value (i.e., a threshold) for which the information on the probability is set (or determined in advance) can be selected as the reported beam. Alternatively, confidence information about the accuracy of the predicted RSRP values ​​for the predicted Top K beams may also be provided for each beam as information about whether the predicted RSRP values ​​have a confidence probability (or an accuracy probability). For example, when the above-described information is provided, the terminal may select beams of predicted RSRP values ​​that have confidence information higher than the above-described information and a set (or predetermined) threshold value as Top-K beams and report them to the base station.

[0317] That is, all possible information for reporting the inference result as described above may correspond to information associated with the transmission (Tx) beams set within set A, and the terminal may select the output value of the model inference based on the set A setting and report some or all of the possible information to the base station through a combination.

[0318] As another example, the result of the inference according to the AI / ML model can be output in the form of RSRP of the predicted Top K beams. In the case described above, the RSRP value actually associated with the beam can be derived based on the associated ID value that indicates whether there is consistency between set A and set B. The RSRP value, which is a measured value for the beams in set B used as an input value of the AI / ML model, can be compared with the predicted RSRP value for the beams in set A, which is an output value of the model. As a specific example, if the beams in set B and the beam-related settings in set A have the same associated ID and some beams can have an intersection form with each other, the predicted RSRP value of the beams in set A included in the intersection described above and the measured RSRP value of the beams in set B can be compared with each other. Here, the compared values ​​can be used as the output values ​​of the model.

[0319] For example, we can consider a case where the predicted RSRP value of set A is not utilized, but the measured RSRP value of set B is used instead. Since the predicted Tx beam, which is the model output value corresponding to set A, is already related to the beam on which the terminal performed the measurement, the actual measured value may have higher reliability than the predicted value. Therefore, only in the above case, the measured RSRP value can be selectively used as a substitute for the predicted RSRP value, and through this, the terminal can report a more accurate RSRP value to the base station. In addition, the 'CSI-report' setting that can be used to report the inference result can consider the two methods in Table 20 below.

[0320] [Table 20]

[0321]

[0322]

[0323] For example, one method among the above-described options may be determined by the base station and provided to the terminal via upper-layer signaling. Alternatively, the configuration for both options may be provided to the terminal, and one method may be indicated to the terminal via dynamic L1 signaling. However, this embodiment is not limited thereto.

[0324]

[0325] Additionally, in the case where the AI / ML model is located on the terminal side, BM-case2 may be a case where the terminal transmits to the base station the inference result values ​​on one or more future time instances (N) for the beam measurement procedure based on the AI / ML model in a single CSI reporting. Here, N future time instances need to be determined.

[0326] FIG. 14 is a diagram illustrating a reference time determination method and a prediction window indication method applicable to the present disclosure. Referring to FIG. 14, a case where N=4 can be considered within one prediction window (1410). However, this is for convenience of explanation and may not be limited thereto. The inference result values ​​of the terminal model can derive the result by inferring the optimal beam (or beam set) for each of the four time instances, and the terminal can report the result to the base station. Here, the input values ​​for supporting the inference operation for the time instance and the settings for reporting the result value can be applied in the same way as discussed in BM-case 1 described above. That is, BM-case 2 can include inference result values ​​for one or more time instances in the time domain in one report and report it to the base station by the terminal. Referring to FIG. 14, in order to indicate the time position of a time instance, a reference point in time must first be determined. For example, the criterion may be a reference time, but is not limited to that term. Here, the earliest time instance within the prediction window (1410) may be indicated based on the aforementioned reference time. For example, various options may be considered to define the point in time that becomes the reference time, as shown in Table 21 below.

[0327] [Table 21]

[0328]

[0329]

[0330] Specifically, referring to Table 21, Option 1 determines a time instance determined to report the inference result value as a time instance for inference reporting as a reference time, and applies an offset value based on that time point to indicate the time position of the first time instance for beam measurement.

[0331] As another example, option 2 in Table 21 can use a slot (time instance) indicated by the CSI reference resource as a time instance for a CSI reference resource. Here, the CSI reference resource can refer to a case where a downlink slot is designated as a timing reference, and channel / interference measurement values ​​after the slot should not be used as input for the corresponding CSI report. The downlink slot corresponding to the above-described CSI reference resource can be used as a reference time point for designating the time position of the first time instance in option 2. Based on the reference time point, an offset value can be applied to designate the time position of the first time instance for beam prediction.

[0332] As another example, Option 3 in Table 21 may be a method for specifying the time position of the first time instance for beam measurement by applying an offset value based on the RS configuration information for measurement configuration for beams in Set B (i.e., the time instance corresponding to the Tx occasion in which the corresponding RS is transmitted), in which the Time instance for SSB / CSI-RS Transmission occasion in Set B is a time instance for SSB / CSI-RS transmission occasion in Set B. The first time instance among the future N time instances may be indicated based on at least one of the above-described options. Alternatively, it may be considered that all the remaining time instances are indicated separately, and the present invention is not limited to a specific form.

[0333] For example, if the first time instance is indicated based on at least one of the options described above, each of the remaining time instances (e.g., 2nd, 3rd, 4th time instance, etc.) can be indicated using an additional prediction offset value, as in Fig. 14. As a specific example, the second time instance (2 ndThe 1st time instance can be indicated using the prediction offset (e.g., in Slot / OFDM symbol units) described above based on the indicated 1st time instance. In addition, the location of the 3rd time instance can also be indicated using the prediction offset value described above based on the previous 1st or 2nd time instance. Similarly, the 4th time instance can also be indicated, but is not limited to a specific form. The above-mentioned prediction offset value can be applied equally to all time instances as a single value. As another example, the prediction offset value can be defined independently for each of the N time instances and use different values. From the perspective of signaling overhead, it may be desirable to define a single value and apply it equally to all, but is not limited thereto.

[0334] Also, referring to FIG. 14, a measurement window (measurement window 1420) can be used as a time window to determine the input values ​​required for the corresponding inference operation for BM-case2. That is, time information related to when the measurement values ​​to support the inference operation of the AI / ML model should be measured and utilized can be set. The time position of the above-described measurement window (1420) can be determined based on the time point at which the inference result value is reported, as shown in FIG. 14. The channel information values ​​measured within the measurement window (1420) can be utilized as representative average values. For example, the average value of the RSRP values ​​measured within the corresponding measurement window can be utilized as an input value for model inference. In addition, one or more of the above-described measurement windows can be set, and the terminal can derive one or more average values. The above-described plurality of average RSRP values ​​can be utilized as input values ​​of the model.

[0335]

[0336]

[0337] FIG. 15 is a flowchart of a method for performing beam management applicable to the present disclosure.

[0338] Referring to FIG. 15, a wireless user device may receive a reference signal from a base station. (S1510) Thereafter, the wireless user device may perform measurements for at least one of training and inference based on the reference signal. (S1520) The wireless user device may derive prediction beam information through an AI / ML model (S1530) and transmit the derived prediction beam information to the base station. (S1540) Here, the AI / ML model may be located in the wireless user device. Here, the wireless user device may receive the reference signal after transmitting a reference signal transmission request to the base station. Alternatively, the wireless user device may receive the reference signal based on reference signal configuration information transmitted by the base station without a reference signal transmission request. In addition, as an example, the wireless user device may generate data information as an AI / ML model input based on the measurement. For example, the data information may include at least one of the RSRP values ​​and beam-related information of all beams of set B or the highest beam K as a set of beams for channel measurement, the RSRP values ​​and beam-related information of all beams of set A or the highest beam K as a set of beams corresponding to AI / ML model output values, beam ID information of the highest beam K for set A, time stamp information, and AI / ML model training-related information. In addition, the predicted beam information derived through the AI / ML model may include at least one of the beam information for the highest beams K predicted among the set of beams, the RSRP values ​​for the highest beams K, probability information for the highest beams K, and reliability information of the RSRP values ​​for the highest beams K. In addition, the wireless user device may obtain an input value of the AI / ML model by performing a measurement within a measurement window. Thereafter, the wireless user device may derive predicted beam information corresponding to each of N time instances within the prediction window based on the AI / ML model and report the derived predicted beam information to the base station.

[0339] Here, the first time instance within the prediction window can be determined based on the reference time. For example, time instances after the first time instance can be determined within the prediction window based on an offset value relative to the first instance. In addition, the reference time can be determined based on at least one of a time instance for inference reporting, a time instance for a channel state information (CSI) reference resource, and a time instance for a reference signal transmission opportunity within set B, as described above.

[0340] Figure 16 is a drawing showing a base station device and a terminal device to which the present disclosure can be applied.

[0341] The base station device (1600) may include a processor (1620), an antenna unit (1612), a transceiver (1626), and a memory (1616).

[0342] The processor (1620) performs baseband-related signal processing and may include a higher layer processing unit (1630) and a physical layer processing unit (1640). The higher layer processing unit (1630) may process operations of a MAC (Medium Access Control) layer, an RRC (Radio Resource Control) layer, or higher layers. The physical layer processing unit (1640) may process operations of a physical (PHY) layer (e.g., uplink reception signal processing, downlink transmission signal processing). In addition to performing baseband-related signal processing, the processor (1620) may also control the overall operation of the base station device (1600).

[0343] The antenna unit (1612) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO (Multiple Input Multiple Output) transmission and reception. In addition, it may support beamforming.

[0344] The memory (1616) can store information processed by the processor (1620), software related to the operation of the base station device (1600), an operating system, applications, etc., and may also include components such as a buffer.

[0345] The processor (1620) of the base station (1600) may be configured to implement the operations of the base station in the embodiments described in the present invention.

[0346] The terminal device (1650) may include a processor (1670), an antenna unit (1662), a transceiver (1664), and a memory (1666). For example, the terminal device (1650) in the present invention may communicate with a base station device (1600). As another example, the terminal device (1650) in the present invention may perform sidelink communication with another terminal device. That is, the terminal device (1650) in the present invention refers to a device that can communicate with at least one of the base station device (1600) and another terminal device, and is not limited to communication with a specific device.

[0347] The processor (1670) performs baseband-related signal processing and may include a higher layer processing unit (1680) and a physical layer processing unit (1690). The higher layer processing unit (1680) may process operations of the MAC layer, the RRC layer, or higher layers. The physical layer processing unit (1690) may process operations of the PHY layer (e.g., downlink reception signal processing, uplink transmission signal processing). In addition to performing baseband-related signal processing, the processor (1670) may also control the overall operation of the terminal device (1650).

[0348] The antenna unit (1662) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO transmission and reception. In addition, it may support beamforming.

[0349] The memory (1666) can store information processed by the processor (1670), software related to the operation of the terminal device (1650), an operating system, applications, etc., and may also include components such as a buffer.

[0350] A terminal device (1650) according to an example of the present invention may be associated with a vehicle. For example, the terminal device (1650) may be integrated into, positioned in, or positioned on the vehicle. Furthermore, the terminal device (1650) according to the present invention may be the vehicle itself. Furthermore, the terminal device (1650) according to the present invention may be at least one of a wearable terminal, an AV / VR, an IoT terminal, a robot terminal, and a public safety terminal. The terminal device (1650) to which the present invention is applicable may include any type of communication device that supports interactive services utilizing sidelink for services such as Internet access, service execution, navigation, real-time information, autonomous driving, and safety and risk diagnosis. Furthermore, any type of communication device capable of sidelink operation or an AR / VR device or a sensor that performs relay operation may be included.

[0351] Here, the vehicles to which the present invention is applied may include autonomous vehicles, semi-autonomous vehicles, non-autonomous vehicles, etc. Meanwhile, while the terminal device (1650) according to one example of the present invention is described as being associated with a vehicle, one or more of the UEs may not be associated with a vehicle. This is merely an example, and should not be construed as limiting the application of the present invention to the described example.

[0352] For example, the terminal device (1650) can perform measurements for at least one of training and inference based on a reference signal. The terminal device (1650) can derive predicted beam information through an AI / ML model and transmit the derived predicted beam information to the base station (1600). Here, the AI / ML model can be located in the terminal device (1650). The terminal device (1650) can receive the reference signal after transmitting a reference signal transmission request to the base station (1600). Alternatively, the terminal device (1650) can receive the reference signal based on reference signal configuration information transmitted by the base station (1600) without a reference signal transmission request. In addition, for example, the terminal device (1650) can generate data information as an AI / ML model input based on the measurement. For example, the data information may include at least one of the RSRP values ​​and beam-related information of all beams of set B or the highest beam K as a set of beams for channel measurement, the RSRP values ​​and beam-related information of all beams of set A or the highest beam K as a set of beams corresponding to AI / ML model output values, beam ID information of the highest beam K for set A, time stamp information, and AI / ML model training-related information. In addition, the predicted beam information derived through the AI / ML model may include at least one of the beam information for the highest beams K predicted among the set of beams, the RSRP values ​​for the highest beams K, probability information for the highest beams K, and reliability information of the RSRP values ​​for the highest beams K. In addition, the terminal device (1650) may perform a measurement within a measurement window to obtain an input value of the AI / ML model. Thereafter, the terminal device (1650) may derive predicted beam information corresponding to each of N time instances within the prediction window based on the AI / ML model and report the derived predicted beam information to the base station (1600).

[0353] Here, the first time instance within the prediction window can be determined based on the reference time. For example, time instances after the first time instance can be determined within the prediction window based on an offset value relative to the first instance. In addition, the reference time can be determined based on at least one of a time instance for inference reporting, a time instance for a CSI reference resource, and a time instance for a reference signal transmission opportunity within set B, as described above.

[0354] Additionally, various embodiments of the present disclosure may be implemented by hardware, firmware, software, or a combination thereof. In the case of hardware implementation, the embodiments may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general processors, controllers, microcontrollers, microprocessors, etc.

[0355] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that cause operations according to the methods of various embodiments to be executed on a device or a computer, and a non-transitory computer-readable medium having such software or instructions stored thereon and executable on the device or computer.

[0356] The various embodiments of the present disclosure are not intended to list all possible combinations but rather to illustrate representative aspects of the present disclosure, and the matters described in the various embodiments may be applied independently or in combination of two or more.

[0357]

[0358] The above may also apply to other systems.

Claims

1. In the method, A step in which a wireless user device receives a reference signal from a base station; A step of performing a measurement for at least one of training and inference based on the above reference signal; and A method comprising a step of transmitting predicted beam information derived through an AI / ML (artificial intelligence / machine learning) model based on the above measurement to a base station, wherein the AI / ML model is located in the wireless user device.

2. In paragraph 1, A method in which the wireless user device receives the reference signal after transmitting a reference signal transmission request to the base station or receives the reference signal based on reference signal setting information transmitted by the base station without the reference signal transmission request.

3. In paragraph 1, The wireless user device generates data information as input to the AI / ML model based on the measurement, A method in which the above data information includes at least one of the RSRP (reference signal received power) value and beam-related information of all beams of set B or the highest beam K as a set of beams for channel measurement, the RSRP value and beam-related information of all beams of set A or the highest beam K as a set of beams corresponding to AI / ML model output values, beam ID information of the highest beam K for the set A, time stamp information, and AI / ML model training-related information.

4. In paragraph 1, A method in which the predicted beam information derived through the AI / ML model includes at least one of beam information for the highest K beams predicted among a set of beams, RSRP values ​​for the highest K beams, probability information for the highest K beams, and reliability information for the RSRP values ​​for the highest K beams.

5. In paragraph 1, A method wherein the wireless user device performs the measurement within the measurement window to obtain an input value of the AI / ML model, and derives predicted beam information corresponding to each of N time instances within the prediction window based on the AI / ML model and reports the derived predicted beam information to the base station.

6. In paragraph 5, A method wherein the first time instance within the prediction window is determined based on a reference time, and time instances after the first time instance are determined within the prediction window based on an offset value with respect to the first instance.

7. In paragraph 6, A method wherein the above reference time is determined based on at least one of a time instance for an inference report, a time instance for a channel state information (CSI) reference resource, and a time instance for a reference signal transmission opportunity within set B.

8. For wireless user devices, at least one processor; and A memory storing instructions that cause the wireless user device to perform a specific operation by the at least one processor, The above specific actions are: Receive a reference signal from a base station, Performing measurements for at least one of training and inference based on the above reference signal, and A wireless user device that transmits predicted beam information derived through an AI / ML model based on the above measurement to a base station, wherein the AI / ML model is located in the wireless user device.

9. In paragraph 8, The above specific actions are: A wireless user device that receives a reference signal after transmitting a reference signal transmission request to the base station or receives the reference signal based on reference signal setting information transmitted by the base station without the reference signal transmission request.

10. In paragraph 1, A wireless user device generating data information as an input to the AI / ML model based on the measurement, wherein the data information includes at least one of: a reference signal received power (RSRP) value and beam-related information of all beams of set B or the highest beam K as a set of beams for channel measurement; a RSRP value and beam-related information of all beams of set A or the highest beam K as a set of beams corresponding to AI / ML model output values; beam ID information of the highest beam K for the set A; time stamp information; and AI / ML model training-related information.

11. In paragraph 8, A wireless user device, wherein the predicted beam information derived through the AI / ML model includes at least one of beam information for the highest K beams predicted among a set of beams, RSRP values ​​for the highest K beams, probability information for the highest K beams, and reliability information for the RSRP values ​​for the highest K beams.

12. In paragraph 8, The above specific actions are: A wireless user device that performs the measurement within the measurement window to obtain an input value of the AI / ML model, derives predicted beam information corresponding to each of N time instances within the prediction window based on the AI / ML model, and reports the derived predicted beam information to the base station.

13. In paragraph 12, A wireless user device, wherein the first time instance within the prediction window is determined based on a reference time, and the time instances after the first time instance are determined within the prediction window based on an offset value based on the first instance.

14. In paragraph 13, A wireless user equipment, wherein the above reference time is determined based on at least one of a time instance for an inference report, a time instance for a CSI reference resource, and a time instance for a reference signal transmission opportunity within set B.

Images