Apparatus and method for performing ai / ml based beam management in wireless communication system

Abstract

Various embodiments of the present disclosure provide a terminal operation method in a wireless communication system, the method comprising the steps of: receiving a channel state information (CSI) resource configuration from a base station; receiving a plurality of CSI-RSs from the base station on the basis of a plurality of first synchronization signal block resource indicators (SSBRI) or a plurality of first CSI reference signal resource indicators (CRI) related to the CSI resource configuration; measuring a signal interference power (SINR) or a received signal received power (RSRP) related to the first CRI or the first SSBRI; calculating a derivative value per time unit of the measured RSRP or SINR; selecting a predetermined number of second CRIs or second SSBRIs from the first CRIs or first SSBRIs based on a derivative value and an absolute value of the RSRP or SINR; and transmitting a report message related to the second CRI or the second SSBRI to the base station, the report message including an absolute value of the RSRP or SINR related to the second CRI or the second SSBRI and a derivative value of the RSRP or SINR related to the second CRI or the second SSBRI.

Description

Technical Field

[0001] The present disclosure relates to an apparatus and method for performing artificial intelligence / machine learning (AI / ML)-based beam management in a wireless communication system. More specifically, the present disclosure relates to a method for a user equipment (UE) to report information that can be mainly used as an input parameter of a base station AI / ML in AI / ML-based beam management in a wireless communication system, and an apparatus and method for performing beam reporting through UE AI / ML. Background Art

[0002] In 3GPP Rel-18 standardization, studies will be conducted to improve the communication performance between base stations (BS) and user equipment (UE) using artificial intelligence (AI) / machine learning (ML). Three main use cases for evaluating performance improvements using AI / ML have been proposed as CSI reporting, beam management and positioning (see Rel-18 AI / ML SI objectives below). Specifically, in beam management, sub-use cases for beam prediction in the time and / or space domain for overhead and delay reduction and improvement of beam selection accuracy are proposed.

[0003] To list the types of AI / ML-based operations between a base station and a UE, they can be simply divided into BS AI / ML operations, UE AI / ML operations, and BS-UE joint AI / ML operations. The present disclosure describes a method in which a UE reports information that can be mainly used as an input parameter of BS AI / ML in AI / ML-based beam management, and a beam reporting method by UE AI / ML. The present disclosure proposes a beam reporting operation of a UE for AI / ML-based beam management. Summary of the invention

[0004] Technical issues

[0005] To solve the above and other problems, the present disclosure provides an apparatus and method for performing artificial intelligence / machine learning (AI / ML) based beam management in a wireless communication system.

[0006] The present disclosure provides a method for a user equipment (UE) to report information that can be mainly used as an input parameter of a base station (BS) AI / ML in AI / ML-based beam management in a wireless communication system, as well as a device and method for performing beam reporting through UE AI / ML.

[0007] Technical objects to be achieved by the present disclosure are not limited to those described above by way of example only, and other technical objects not mentioned can be clearly understood from the following description by those skilled in the art to which the present disclosure belongs.

[0008] Technical Solution

[0009] According to various embodiments of the present disclosure, a method for operating a user equipment (UE) in a wireless communication system is provided, including: receiving a channel state information (CSI) resource configuration from a base station; receiving multiple CSI reference signals (RS) from the base station based on multiple first CSI reference signal resource indicators (CRIs) or multiple first synchronization signal block resource indicators (SSBRIs) related to the CSI resource configuration; measuring a received signal received power (RSRP) or a signal to interference power (SINR) related to the first CRI or the first SSBRI; calculating a derivative value per time unit of the measured RSRP or SINR; selecting a predetermined number of second CRIs or second SSBRIs from the first CRI or the first SSBRI based on the absolute value and the derivative value of the RSRP or SINR; and sending a report message related to the second CRI or the second SSBRI to the base station, wherein the report message includes the absolute value of the RSRP or SINR related to the second CRI or the second SSBRI and the derivative value of the RSRP or SINR related to the second CRI or the second SSBRI.

[0010] According to various embodiments of the present disclosure, a method for operating a base station in a wireless communication system is provided, including: sending a channel state information (CSI) resource configuration to a user equipment (UE); sending multiple CSI reference signals (RS) to the UE based on multiple first CSI reference signal resource indicators (CRIs) or multiple first synchronization signal block resource indicators (SSBRIs) related to the CSI resource configuration; and receiving a report message related to a second CRI or a second SSBRI as part of the first CRI or the first SSBRI from the UE, wherein the second CRI or the second SSBRI is a predetermined number of CRIs or SSBRIs selected from the first CRI or the first SSBRI based on the absolute value of received signal received power (RSRP) or signal to interference power (SINR) related to the first CRI or the first SSBRI and the derivative value per time unit of the RSRP or SINR related to the first CRI or the first SSBRI, and the report message includes the absolute value of the RSRP or SINR related to the second CRI or the second SSBRI and the derivative value of the RSRP or SINR related to the second CRI or the second SSBRI.

[0011] According to various embodiments of the present disclosure, a user equipment (UE) in a wireless communication system is provided, the UE including a transceiver, at least one processor and at least one memory, the at least one memory being operably connected to the at least one processor and configured to store instructions for performing operations based on execution by the at least one processor, wherein the operations include all steps of the method for operating the UE according to various embodiments of the present disclosure.

[0012] According to various embodiments of the present disclosure, a base station in a wireless communication system is provided, the base station including a transceiver, at least one processor and at least one memory, the at least one memory being operably connected to the at least one processor and configured to store instructions for performing operations based on execution by the at least one processor, wherein the operations include all steps of the method for operating a base station according to various embodiments of the present disclosure.

[0013] According to various embodiments of the present disclosure, a control device for controlling a user equipment (UE) in a wireless communication system is provided, the control device comprising at least one processor and at least one memory operably connected to the at least one processor, wherein the at least one memory is configured to store instructions for performing operations based on execution by the at least one processor, and the operations include all steps of the method for operating the UE according to the various embodiments of the present disclosure.

[0014] According to various embodiments of the present disclosure, a control device for controlling a base station in a wireless communication system is provided, the control device comprising at least one processor and at least one memory operably connected to the at least one processor, wherein the at least one memory is configured to store instructions for performing operations based on execution by the at least one processor, and the operations include all steps of the method for operating a base station according to the various embodiments of the present disclosure.

[0015] According to various embodiments of the present disclosure, one or more non-transitory computer-readable media storing one or more instructions are provided, wherein the one or more instructions are configured to perform operations based on execution by one or more processors, and the operations include all steps of a method of operating a user equipment (UE) according to various embodiments of the present disclosure.

[0016] According to various embodiments of the present disclosure, one or more non-transitory computer-readable media storing one or more instructions are provided, wherein the one or more instructions are configured to perform operations based on execution by one or more processors, and the operations include all steps of the method of operating a base station according to various embodiments of the present disclosure.

[0017] Beneficial Effects

[0018] To solve the above and other problems, the present disclosure may provide an apparatus and method for performing artificial intelligence / machine learning (AI / ML)-based beam management in a wireless communication system.

[0019] The present disclosure may provide a method for a user equipment (UE) to report information that can mainly serve as an input parameter of a base station (BS) AI / ML in AI / ML-based beam management in a wireless communication system, as well as a device and method for performing beam reporting through UE AI / ML. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are included to further understand the present disclosure and constitute a part of the detailed description, illustrate embodiments of the present disclosure and are used together with the description to explain the technical features of the present disclosure. The technical features of the present disclosure are not limited to specific drawings, and the features disclosed in the drawings can be combined with each other to form new embodiments. The figure numbers in the drawings may represent structural elements.

[0021] Figure 1 Illustrated are examples of concepts related to deep learning-based artificial intelligence (AI) that may be applied in the systems of the present disclosure.

[0022] Figure 2 An example of the structure of a feed-forward neural network (FFNN) as an example of a deep learning model that can be applied to the system of the present disclosure is illustrated.

[0023] Figure 3 An example of the structure of a recurrent neural network (RNN) as an example of a deep learning model that can be applied to the system of the present disclosure is illustrated.

[0024] Figure 4 An example of the structure of a convolutional neural network (CNN) as an example of a deep learning model that can be applied in the system of the present disclosure is illustrated.

[0025] Figure 5 An example of the structure of an autoencoder as an example of a deep learning model that can be applied to the system of the present disclosure is illustrated.

[0026] Figure 6 An example of the structure of a functional framework of Radio Access Network (RAN) intelligence applicable to the system of the present disclosure is illustrated.

[0027] Figure 7 An example of an operation process of a UE in the system applicable to the present disclosure is illustrated.

[0028] Figure 8 The diagram illustrates an example of an operation process of a base station in a system applicable to the present disclosure.

[0029] Fig. 9 An example of the structure of the first device and the second device applicable to the system of the present disclosure is illustrated. DETAILED DESCRIPTION

[0030] In various embodiments of the present disclosure, "A or B" may mean "only A", "only B", or "both A and B". In other words, in various embodiments of the present disclosure, "A or B" may be interpreted as "A and / or B". For example, in various embodiments of the present disclosure, "A, B, or C" may mean "only A", "only B", "only C", or "any combination of A, B, and C".

[0031] A slash ( / ) or a comma used in various embodiments of the present disclosure may represent "and / or". For example, "A / B" may represent "A and / or B". Thus, "A / B" may represent "only A", "only B", or "both A and B". For example, "A, B, C" may represent "A, B, or C".

[0032] In various embodiments of the present disclosure, “at least one of A and B” may mean “only A”, “only B”, or “both A and B”. In addition, in various embodiments of the present disclosure, the expression “at least one of A or B” or “at least one of A and / or B” may be interpreted as having the same meaning as “at least one of A and B”.

[0033] Furthermore, in various embodiments of the present disclosure, “at least one of A, B, and C” may mean “only A”, “only B”, “only C”, or “any combination of A, B, and C”. Furthermore, “at least one of A, B, or C” or “at least one of A, B, and / or C” may mean “at least one of A, B, and C”.

[0034] In addition, the brackets used in the various embodiments of the present disclosure may represent "for example". Specifically, when describing "control information (PDCCH)", "PDCCH" may be proposed as an example of "control information". In other words, the "control information" in the various embodiments of the present disclosure is not limited to "PDCCH", and "PDDCH" may be proposed as an example of "control information". In addition, even when describing "control information (ie, PDCCH)", "PDCCH" may be proposed as an example of "control information".

[0035] In various embodiments of the present disclosure, technical features described separately in one drawing may be implemented separately or simultaneously.

[0036] 3GPP LTE and NR specifications

[0037] In the following, downlink (DL) means communication from a base station (BS) to a terminal, and uplink (UL) means communication from a terminal to a base station. In the downlink, the transmitter may be part of a base station, and the receiver may be part of a terminal. In the uplink, the transmitter may be part of a terminal, and the receiver may be part of a base station. The base station may be expressed as a first communication device, and the terminal may be expressed as a second communication device. The base station may be replaced by terms including the following parts: fixed station, node B, evolved node B (eNB), next generation node B (gNB), base transceiver system (BTS), access point (AP), network (5G network), artificial intelligence (AI) system / module, roadside unit (RSU), robot, unmanned aerial vehicle (UAV), augmented reality (AR) device, virtual reality (VR) device, etc. In addition, the terminal may be fixed or mobile, and may be replaced by terms including the following parts: user equipment (UE), mobile station (MS), user terminal (UT), mobile subscriber station (MSS), subscriber station (SS), advanced mobile station (AMS), wireless terminal (WT), machine type communication (MTC) device, machine-to-machine (M2M) device, device-to-device (D2D) device, vehicle, roadside unit (RSU), robot, AI module, unmanned aerial vehicle (UAV), augmented reality (AR) device, virtual reality (VR) device, etc.

[0038] The following techniques may be used in various radio access systems including CDMA, FDMA, TDMA, OFDMA, SC-FDMA, etc. CDMA may be implemented as a radio technology such as Universal Terrestrial Radio Access (UTRA) or CDMA2000. TDMA may be implemented as a radio technology such as Global System for Mobile Communications (GSM) / General Packet Radio Service (GPRS) / Enhanced Data Rate for GSM Evolution (EDGE). OFDMA may be implemented as a radio technology such as Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Evolved UTRA (E-UTRA), etc. UTRA is part of Universal Mobile Telecommunications System (UMTS). The 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) is part of Evolved UMTS (E-UMTS) using E-UTRA, and Advanced LTE (A) / LTE-A pro is an evolved version of 3GPP LTE. 3GPP NR (New Radio or New Radio Access Technology) is an evolved version of 3GPP LTE / LTE-A / LTE-A pro.

[0039] For clarity in description, the following description will mainly focus on 3GPP communication systems (such as LTE-A or 5GNR). However, the technical features of the embodiments according to the present disclosure will not be limited thereto. LTE refers to the technology after 3GPP TS 36.xxxRelease 8. Specifically, the LTE technology after 3GPP TS 36.xxx Release 10 is called LTE-A, and the LTE technology after 3GPP TS 36.xxx Release 13 is called LTE-A pro. 3GPP NR refers to the technology after TS 38.xxxRelease 15. LTE / NR can be referred to as a 3GPP system. "xxx" represents a detailed standard document number. LTE / NR can be collectively referred to as a 3GPP system. For terms and technologies not specifically described in the terms and technologies used in this disclosure, reference can be made to the wireless communication standard documents published before the submission of this disclosure. For example, reference can be made to the following documents.

[0040] 3GPP LTE

[0041] -36.211: Physical channels and modulation

[0042] -36.212: Multiplexing and channel coding

[0043] -36.213: Physical layer procedures

[0044] -36.300: General description

[0045] -36.331: Radio Resource Control (RRC)

[0046] 3GPP NR

[0047] -38.211: Physical channels and modulation

[0048] -38.212: Multiplexing and channel coding

[0049] -38.213: Physical layer procedures for control -38.214: Physical layer procedures for data -38.300: NR and NG-RAN general description -38.331: Radio Resource Control (RRC) protocol specification

[0050] Definitions and Abbreviations

[0051] BM: Beam Management

[0052] CQI: Channel Quality Indicator

[0053] CRI: CSI-RS (Channel State Information-Reference Signal) Resource Indicator CSI: Channel State Information

[0054] CSI-IM: Channel State Information-Interference Measurement

[0055] CSI-RS: Channel State Information-Reference Signal

[0056] DMRS: Demodulation Reference Signal

[0057] FDM: Frequency Division Multiplexing

[0058] FFT: Fast Fourier Transform

[0059] IFDMA: Interleaved Frequency Division Multiple Access

[0060] IFFT: Inverse Fast Fourier Transform

[0061] L1-RSRP: Layer 1 reference signal received power

[0062] L1-RSRQ: Layer 1 reference signal reception quality

[0063] MAC: Media Access Control

[0064] NZP: Non Zero Power

[0065] OFDM: Orthogonal Frequency Division Multiplexing

[0066] PDCCH: Physical Downlink Control Channel

[0067] PDSCH: Physical Downlink Shared Channel

[0068] PMI: Precoding Matrix Indicator

[0069] RE: Resource Element

[0070] RI: Rank Indicator

[0071] RRC: Radio Resource Control

[0072] RSSI: Received Signal Strength Indicator

[0073] Rx: Receive

[0074] QCL: Quasi-Co-located

[0075] SINR: Signal to Interference and Noise Ratio

[0076] SSB (or SS / PBCH block): synchronization signal block (including primary synchronization signal, secondary synchronization signal and physical broadcast channel)

[0077] TDM: Time Division Multiplexing

[0078] TRP: Transmit and Receive Point

[0079] TRS: Tracking Reference Signal

[0080] Tx: Send

[0081] UE: User Equipment

[0082] ZP: Zero Power

[0083] Technical Problem / Motivation of the Present Disclosure

[0084] In the 3GPP Rel-18 standardization, research will be conducted to improve the performance in communications between base stations (BSs) and user equipments (UEs) using artificial intelligence (AI) / machine learning (ML). Three main use cases for evaluating performance improvements using AI / ML have been proposed as CSI reporting, beam management, and positioning. In order to list the types of AI / ML-based operations between BS and UE, they can be simply divided into BS AI / ML operations, UE AI / ML operations, and BS-UE joint AI / ML operations. The present disclosure describes a method in which a UE reports information that can mainly be used as input parameters for BS AI / ML in AI / ML-based beam management, and a beam reporting method through UE AI / ML.

[0085] The present disclosure proposes a beam reporting operation of a UE for AI / ML-based beam management.

[0086] The configuration, operation, and other features of the present disclosure will be understood by describing the embodiments of the present disclosure with reference to the accompanying drawings.

[0087] In the following, downlink (DL) means communication from a base station (BS) to a terminal, and uplink (UL) means communication from a terminal to a base station. In the downlink, the transmitter may be part of a base station, and the receiver may be part of a terminal. In the uplink, the transmitter may be part of a terminal, and the receiver may be part of a base station. The base station may be expressed as a first communication device, and the terminal may be expressed as a second communication device. The base station may be replaced by terms including the following parts: fixed station, NodeB, evolved NodeB (eNB), next generation NodeB (gNB), base transceiver system (BTS), access point (AP), network (5G network), artificial intelligence (AI) system / module, roadside unit (RSU), robot, unmanned aerial vehicle (UAV), augmented reality (AR) device, virtual reality (VR) device, etc. In addition, the terminal may be fixed or mobile, and may be replaced by terms including the following parts: user equipment (UE), mobile station (MS), user terminal (UT), mobile subscriber station (MSS), subscriber station (SS), advanced mobile station (AMS), wireless terminal (WT), machine type communication (MTC) device, machine-to-machine (M2M) device, device-to-device (D2D) device, vehicle, roadside unit (RSU), robot, AI module, unmanned aerial vehicle (UAV), augmented reality (AR) device, virtual reality (VR) device, etc.

[0088] Standardize related operations

[0089] Beam Management (BM)

[0090] The BM process, which is a Layer 1 (L1) / Layer 2 (L2) process for acquiring and maintaining a set of base station (e.g., gNB, TRP, etc.) and / or terminal (e.g., UE) beams that can be used for downlink (DL) and uplink (UL) transmission / reception, may include the following processes and terms.

[0091] - Beamforming: An operation where a base station or UE measures the characteristics of a received beamforming signal

[0092] -Beam determination: The operation by which a base station or UE selects its transmit beam (Tx beam) / receive beam (Rx beam).

[0093] - Beam scanning: The operation of covering a spatial area using Tx and / or Rx beams in a predetermined manner and at predetermined time intervals.

[0094] -Beam reporting: An operation in which the UE reports information about beamforming signals based on beam measurements.

[0095] The BM process can be divided into (1) a DL BM process using a synchronization signal (SS) / physical broadcast channel (PBCH) block or a CSI-RS, and (2) a UL BM process using a sounding reference signal (SRS).

[0096] In addition, each BM process may include Tx beam scanning for determining a Tx beam and RX beam scanning for determining an Rx beam.

[0097] Evolution of beam management methods

[0098] Rel-15 and Rel-16 beam management

[0099] <Background - BS UE Rx beam configuration / indication and UE Tx beam configuration / indication>

[0100] The TCI state can be used when the base station configures / indicates the Rx beam (i.e., spatial Rx parameters) to be used when receiving PDCCH and PDSCH (more specifically, when receiving DMRS of PDCCH and PDSCH) to the UE using the quasi-co-location (QCL) concept introduced in (Rel-15) NR. The Rx beam used when receiving the DL RS configured as a reference can be indicated when receiving PDCCH or PDSCH by configuring / updating the DL reference signal (e.g., SSB-RI, CRI (P / SP / AP)) as the reference RS or source RS of the QCL Type-D component via the TCI state.

[0101] In Rel-15 NR, in order to configure / indicate to the UE the Tx beam to be used when transmitting a UL channel, the base station can use spatialRelationInfo. The base station configures / indicates which UL Tx beam (i.e., spatial Tx parameters) to use when transmitting PUCCH and SRS by configuring / updating the DL reference signal (i.e., SSB-RI, CRI (P / SP / AP)) or SRS (i.e., SRS resources) as the reference RS of the target UL channel and / or target RS via RRC configuration and / or MAC CE activation. In addition, when the base station schedules PUSCH to the UE, the Tx beam configured / updated / indicated by the base station and used for SRS transmission (for CB or NCB purposes) is indicated as the Tx beam for PUSCH via the SRI field of the UL grant DCI and is used as the PUSCH Tx beam of the UE.

[0102] <Background - Update of UE's Rx / Tx beam>

[0103] In Rel-15 NR, TCI state configuration can be used to configure / indicate the Rx beam for the target DL RS / channel. If the target DL RS / channel is CSI-RS, the UE Rx beam can be configured by configuring QCL type-D RS at the RRC / MAC CE level (configured by TCI state ID in the TCI state pool). If the target DL RS / channel is PDCCH, after configuring up to 64 TCI state IDs for a specific CORESET, the specific TCI state ID is indicated via MAC CE, so that the UE Rx beam can be configured, and the Rx beam of the corresponding CORESET can be updated via the same MAC CE message. In addition, for PDSCH Rx beams, the PDSCH Rx beam can be indicated by TCI indication during DL scheduling by connecting up to 8 TCI state IDs to the TCI state field of DL DCI (within a maximum of 128 TCI state pools) via MAC CE, and the PDSCH Rx beam can be updated by updating the TCI state ID connected to the TCI state field via the same MAC CE message.

[0104] In Rel-16 NR, in order to reduce the overhead of DL Rx beam configuration / indication, the operation between the base station and the UE is enhanced through the MAC CE message, which enables the TCI state ID to be activated simultaneously in multiple CCs (BWP) for PDCCH and PDSCH.

[0105] In Rel-15 NR, the Tx beam can be configured by connecting PUCCH-SpatialRelationInfoId to each PUCCH resource via a MAC CE message to configure / indicate the PUCCH Tx beam, and the MAC level of PUCCH-SpatialRelationInfo can be updated through the same MAC CE message. In addition, for SRS, the SRS-SpatialRelationInfo of the SRS resource in the corresponding semi-persistent SRS resource set can be updated through the MAC CE message of the transmission of the SRS that activates SP-SRS.

[0106] In Rel-16 NR, in order to reduce the delay of UL Tx beam configuration / indication, the operation between the BS and the UE has been enhanced so that the SRS-SpatialRelationInfo of the SRS resources in the corresponding non-periodic SRS resource set can be updated through the MAC CE message of the AP-SRS. In addition, in the same way as the DL Rx beam, the operation between the BS and the UE has also been enhanced so that the spatial relationship reference RS in multiple CCs (BWP) of SP-SRS and AP-SRS can be updated simultaneously through the MAC CE message. In addition, by introducing the concept of PUCCH resource groups (per BWP), the operation between the BS and the UE has also been enhanced so that the spatial relationship of PUSCH resources in the PUCCH resource group can be updated simultaneously.

[0107] Rel-17 Beam Management

[0108] In NR Rel-15 / Rel-16, higher layer signaling such as RRC and MAC CE is mainly used for beam indication / update operations for reception / transmission between BS and UE, and DCI-based beam indication operations have been supported for certain channels / RS (PDSCH, PUSCH), etc. In Rel-17, dynamic beam update operations using joint DL / UL TCI states and separate DL / UL TCI states are introduced, and the base station has standardized a UE common beam update operation, which performs common indication / update of multiple UE-specific channel / RS combinations for one beam by using DCI. The target channel / RS for the common beam update may include UE-specific CORESET and UE-specific reception on PDSCH in the case of DL, and may include all or a subset of DG / CG-PUSCH and dedicated PUCCH in the case of UL. In addition, APCSI-RS and SRS for tracking / BM can be configured for the target channel / RS.

[0109] In addition, as a method for supporting panel-specific UL transmission of UE, a standard discussion of UE capability reporting operation and beam reporting operation for panel-related information has been conducted as follows. According to the following two protocols, one function corresponds to what is agreed upon as a working assumption and is defined as a UE capability value set index (hereinafter referred to as C-ID), and how many C-IDs the UE has is reported to the UE as a UE capability report. The attribute to be included in the C-ID agreed upon so far is the maximum number of SRS ports supported by the UE for each C-ID. That is, C-IDs are defined only for panels with different numbers of SRS ports. Another function is an operation of (immediate / periodic) reporting by including the C-ID as a UE capability report in the beam report captured in the protocol. For convenience, this evolved reporting method will be referred to as "panel-specific beam reporting" hereinafter. If panel-specific beam reporting is configured / indicated, when the UE is configured / indicated using existing beam reporting, the RS index (i.e., CRI or SSBRI) associated with the best N BS Tx beams (where N is a value between 1 and 4 and is set by the base station) (regardless of the UE Rx panel) will be reported to the base station together with the L1-RSRP or L1-SINR value (which is the reception quality value of the corresponding RS). The panel-specific beam reporting method will report the optimal C-ID (for each CRI / SSBRI) and the L1-RSRP / L1-SINR associated with the CRI / SSBRI. Modes for reporting the C-ID of each CRI / SSBRI separately and / or modes for reporting a single C-ID for all CRI / SSBRIs will be supported here.

[0110]

[0111] In addition, in NR Rel-15 / Rel-16, the power control configuration / indication of the UE of the base station is performed by the configuration of each UL channel / RS (ie, PUSCH, PUCCH, SRS). As above, in Rel-17, with the enhancement of being able to indicate the DL / UL Rx / Tx beam through a unified TCI (e.g., joint and / or separate DL / UL TCI) state, a method for configuring / indicating UL power control parameters and TCI state configuration / indication is discussed (see the protocol below).

[0112]

[0113]

[0114]

[0115] In the above, the path loss reference RS (hereinafter referred to as PL-RS) has been standardized so that it is associated with or included in the joint TCI state and / or the UL TCI state (the association / inclusion is determined in RAN2). In addition, power control parameters (P0, alpha, closed loop index) other than PL-RS have been standardized so that they are associated with the joint TCI state and / or the UL TCI state. That is, due to the Rel-17 MIMO standardization, the base station can configure / indicate the UL Tx beam for a specific target DL / UL channel / RS of the UE through the joint and / or separate UL TCI state, and also configure / indicate the power control parameters required to determine the transmission power.

[0116] AI / ML for Wireless Communications

[0117] Figure 1 Illustrated are examples of concepts related to deep learning-based artificial intelligence (AI) in a system applicable to the present disclosure.

[0118] With the technological advancement of artificial intelligence / machine learning (AI / ML), the nodes and UEs that constitute the wireless communication network have become more intelligent / advanced. In particular, due to the intelligence of the network / base station, it is expected that various network / base station decision parameter values ​​(e.g., the transmit / receive power of each BS, the transmit power of each UE, the precoder / beam of the BS / UE, the time / frequency resource allocation of each UE, the duplex method of each BS, etc.) can be quickly optimized and derived / applied based on various environmental parameters (e.g., the distribution / location of base stations, the distribution / location / material of buildings / furniture, etc., the location / moving direction / speed of UE, climate information, etc.). In line with this trend, many standardization organizations (e.g., 3GPP, O-RAN) are considering the introduction, and research on this is also actively underway.

[0119] AI / ML might easily be referred to in a narrow sense as artificial intelligence based on deep learning, but conceptually it is as shown in the table below.

[0120] (1) Artificial Intelligence (AI): It is any automation that allows machines to perform work that humans would otherwise do.

[0121] (2) Machine Learning (ML): It refers to technologies in which machines learn patterns for making decisions from data without explicitly programmed rules.

[0122] (3) Deep learning: It is a model based on artificial neural networks that allows machines to perform feature extraction and decision making from unstructured data in one go. The algorithm relies on a multi-layer network composed of interconnected nodes for feature extraction and transformation, and is inspired by biological neural systems, namely neural networks. Common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0123] Types of AI / ML based on various standards

[0124] (1) Offline vs. Online

[0125] (1-1) Offline learning

[0126] (1-1-1) Offline learning faithfully follows the sequential process of database collection, learning, and prediction. That is, collection and learning can be done offline, and the completed program can be installed on site and used for prediction work. In most cases, this offline learning method is used.

[0127] (1-2) Online learning

[0128] (1-2-1) Online learning refers to a method of gradually improving performance by gradually learning with the generated additional data, taking advantage of the fact that data that can be used for recent learning is continuously generated via the Internet.

[0129] (2) Classification based on AI / ML framework concepts

[0130] (2-1) Centralized learning

[0131] (2-1-1) In centralized learning, when training data collected from multiple different nodes are reported to one centralized node, all data resources / storage / learning (e.g., supervised learning, unsupervised learning, reinforcement learning, etc.) are performed in one centralized node.

[0132] (2-2) Federated Learning

[0133] (2-2-1) Federated learning is built on data where a collective model exists across individually distributed data owners. Instead of collecting data into the model, the AI / ML model is imported into the data source, allowing local nodes / single devices to collect data and train their own copies of the model, so there is no need to report the source data to the centralized node. In federated learning, the parameters / weights of the AI / ML model are sent again to the centralized node to support general model training. Federated learning has advantages in improving computing speed and information security. That is, there is no need to upload personal data to a central server, and the leakage and abuse of personal information can be prevented.

[0134] (2-3) Distributed Learning

[0135] (2-3-1) Distributed learning refers to the concept of scaling and distributing the machine learning process across a cluster of nodes. The training model is shared across multiple nodes that are split and run simultaneously to speed up model training.

[0136] (3) Classification by learning method

[0137] (3-1) Supervised Learning

[0138] (3-1-1)Supervised learning is a machine learning task that aims to learn a mapping function from input to output given a labeled dataset. The input data is called training data and has known labels or results. Examples of supervised learning are as follows.

[0139] (3-1-1-1) Regression: Linear regression, logistic regression

[0140] (3-1-1-2) Example-based algorithm: k-nearest neighbor (KNN)

[0141] (3-1-1-3) Decision Tree Algorithm: CART

[0142] (3-1-1-4) Support Vector Machine: SVM

[0143] (3-1-1-5) Bayesian algorithm: Naive Bayes

[0144] (3-1-1-6) Ensemble algorithms: extreme gradient boosting, bagging: random forest

[0145] (3-1-2)Supervised learning can be further divided into regression and classification problems, where classification predicts labels and regression predicts quantities.

[0146] (3-2) Unsupervised Learning

[0147] (3-2-1) Unsupervised learning is a machine learning task that aims to learn a function that describes the hidden structure in unlabeled data. The input data is unlabeled and there is no known outcome. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and long short-term memory (LSTM).

[0148] (3-3) Reinforcement Learning

[0149] (3-3-1) In reinforcement learning (RL), an agent aims to optimize a long-term goal by interacting with the environment based on a trial-and-error process, and is goal-oriented learning based on interaction with the environment. Examples of RL algorithms are as follows.

[0150] (3-3-1-1) Q-learning

[0151] (3-3-1-2) Multi-armed bandit learning

[0152] (3-3-1-3) Deep Q Network

[0153] (3-3-1-4) State-Action-Reward-State-Action (SARSA)

[0154] (3-3-1-5) Temporal Difference Learning

[0155] (3-3-1-6) Actor-Critic Reinforcement Learning

[0156] (3-3-1-7) Deep Deterministic Policy Gradient

[0157] (3-3-1-8) Monte Carlo Tree Search

[0158] (3-3-2) Reinforcement learning can be further divided into model-based reinforcement learning and model-free reinforcement learning.

[0159] (3-3-3) Model-based reinforcement learning: This refers to RL algorithms that use a predictive model and utilize the various dynamic states of the environment and the model in which these states lead to rewards to obtain the transition probability between states.

[0160] (3-3-4) Model-free reinforcement learning: It refers to value-based or policy-based RL algorithms that achieve maximum future rewards. The multi-agent environment / state is computationally less complex and does not require an accurate representation of the environment.

[0161] (3-3-5)RL algorithms can also be divided into value-based RL versus policy-based RL, policy-based RL versus non-policy RL, etc.

[0162] Representative models of deep learning include feed-forward neural network (FFNN), recurrent neural network (RNN), convolutional neural network (CNN), and autoencoder.

[0163] Figure 2 An example of the structure of a feed-forward neural network (FFNN) as an example of a deep learning model applicable to the system of the present disclosure is illustrated.

[0164] 1. Feedforward Neural Network (FFNN)

[0165] It consists of an input layer, a hidden layer, and an output layer.

[0166] Figure 3 An example of the structure of a recurrent neural network (RNN) as an example of a deep learning model applicable to the system of the present disclosure is illustrated.

[0167] 2. Recurrent Neural Network (RNN)

[0168] RNN is an artificial neural network in which hidden nodes are connected to directed edges to form a directed cycle. It is a model suitable for processing sequential data such as speech and text.

[0169] One type of RNN is Long Short-Term Memory (LSTM), which is a structure that adds a cell-state to the hidden state of the RNN.

[0170] -Add input gate, forget gate and output gate to RNN unit

[0171] - Added unit status

[0172] Figure 4 An example of the structure of a convolutional neural network (CNN) as an example of a deep learning model applicable to the system of the present disclosure is illustrated.

[0173] CNN is used for two purposes: reducing the model complexity and extracting good features by applying convolution operations commonly used in the field of video processing or image processing.

[0174] - Kernel or Filter: Refers to a unit / structure that applies weights to the input of a specific range / unit.

[0175] -Stride: refers to the range of movement of the kernel within the input.

[0176] -Feature map: refers to the result of applying the kernel to the input.

[0177] -Padding: refers to the value added to resize the feature map.

[0178] -Pooling: refers to the operation of reducing the size of feature maps by downsampling them (e.g., max pooling, average pooling).

[0179] Figure 5 An example of the structure of an autoencoder as an example of a deep learning model applicable in the system of the present disclosure is illustrated.

[0180] -An autoencoder is a neural network that receives a feature vector x as input and outputs the same or a similar vector x'.

[0181] -The input nodes and output nodes of the autoencoder have the same features.

[0182] -Autoencoders are a type of unsupervised learning

[0183] -Loss function: Where h = f(x) = Wx, x′ = g(h) = Vh

[0184] Figure 6 An example of the structure of a functional framework of Radio Access Network (RAN) intelligence applicable to the system of the present disclosure is illustrated.

[0185] To explain AI / ML, the following definition can be provided and is from 3GPP TS37.817.

[0186] the term:

[0187] (1) Data collection: Data collected from network nodes, management entities, or UEs serves as the basis for ML model training, data analysis, and inference.

[0188] (2) ML model: A data-driven algorithm that applies machine learning techniques to generate a set of outputs consisting of predictive information based on a set of inputs.

[0189] (3) ML training: An online or offline process of training an ML model by learning the features and patterns that best represent the data and obtaining the trained ML model for inference.

[0190] (4) ML reasoning: The process of using a trained ML model to make predictions or guide decisions based on the collected data and the ML model.

[0191] (the term:

[0192] (1) Data collection: Data collected from network nodes, management entities, or UEs serves as the basis for ML model training, data analysis, and inference.

[0193] (2) ML model: A data-driven algorithm that applies machine learning techniques to generate a set of outputs consisting of predictive information based on a set of inputs.

[0194] (3) ML training: an online or offline process of training an ML model by learning the features and patterns that best represent the data and obtaining the trained ML model for inference.

[0195] (4) ML reasoning: The process of using a trained ML model to make predictions or guide decisions based on collected data and the ML model.

[0196] (1) Data collection is a function that provides input data to model training and model inference functions. AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) is not performed in the data collection function.

[0197] Examples of input data may include measurements from UEs or different network entities, feedback from Actors, and outputs from AI / ML models.

[0198] (1-1) Training data: Data required as input for AI / ML model training functions.

[0199] (1-2) Inference data: data required as input for the inference function of the AI / ML model.

[0200] ((1) Data collection is a function that provides input data to the model training and model inference functions. AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) is not performed in the data collection function.

[0201] Examples of input data may include measurements from UEs or different network entities, feedback from Actors, outputs from AI / ML models.

[0202] (1-1) Training data: Data required as input for AI / ML model training functions.

[0203] (1-2) Inference data: Data required as input for the inference function of AI / ML models. )

[0204] (2) Model training is the function that performs ML model training, validation, and testing, and it can generate model performance metrics as part of the model testing process. If necessary, the model training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function.

[0205] (2-1) Model deployment / update: used to initially deploy trained, validated, and tested AI / ML models to the model inference function, or to deliver updated models to the model inference function.

[0206] (2-1-1) Note: The details of the model deployment / update process and the use case specific AI / ML models delivered through this process are outside the scope of the RAN3 Rel-17 study. The feasibility of a single vendor or multi-vendor environment has not been studied in the RAN3 Rel-17 study.

[0207] ((2) Model training is the function that performs ML model training, validation, and testing, and it can generate model performance metrics as part of the model testing process. If necessary, the model training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function.

[0208] (2-1) Model deployment / update: used to initially deploy trained, validated, and tested AI / ML models to the model inference function, or to deliver updated models to the model inference function.

[0209] (2-1-1) Note: The details of the model deployment / update process and the use case specific AI / ML models delivered through this process are outside the scope of the RAN3 Rel-17 study. The feasibility of a single vendor or multi-vendor environment has not been studied by the RAN3 Rel-17 study. )

[0210] (3) Model inference is a function that provides AI / ML model inference output (e.g., prediction or decision). The model inference function can provide model performance feedback to the model training function when applicable. If necessary, the model inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered by the data collection function.

[0211] (3-1) Output: The inference output of the AI / ML model generated by the model inference function.

[0212] (3-1-1) Note: The details of the inference output are use case specific.

[0213] (3-2) Model performance feedback: It can be used to monitor the performance of AI / ML models.

[0214] (3-2-1) Note: Details of the model performance feedback process are beyond the scope of RAN3.

[0215] ((3) Model inference is a function that provides AI / ML model inference output (e.g., predictions or decisions). The model inference function can provide model performance feedback to the model training function when applicable. If necessary, the model inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered by the data collection function.

[0216] (3-1) Output: The inference output of the AI / ML model generated by the model inference function.

[0217] (3-1-1) Note: The details of the inference output are use case specific.

[0218] (3-2) Model performance feedback: It can be used to monitor the performance of AI / ML models.

[0219] (3-2-1) Note: Details of the model performance feedback process are beyond the scope of RAN3. )

[0220] (4) An Actor is a function that receives the output from the model reasoning function and triggers or executes the corresponding action. An Actor can trigger actions on other entities or itself.

[0221] (4-1) Feedback: Information that may be needed to derive training or inference data or performance feedback.

[0222] ((4)Actor is a function that receives the output from the model reasoning function and triggers or executes the corresponding action. Actors can trigger actions on other entities or themselves.

[0223] (4-1) Feedback: Information that may be needed to derive training or inference data or performance feedback.

[0224] Dataset

[0225] The definition of train / validation / test in datasets used in AI / ML can be divided as follows.

[0226] (1) Training Data

[0227] (1-1) Dataset used to train the model

[0228] (2) Verify data

[0229] (2-1) Dataset used to validate the model that has completed its training

[0230] (2-1-1) Datasets that are usually used to prevent overfitting of training datasets

[0231] (2-2) is used to select the best dataset from the various models trained during the training process

[0232] (2-2-1) Therefore, it can be regarded as a type of training

[0233] (3) Test data

[0234] (3-1) Dataset used for final evaluation

[0235] (3-1-1) Not related to training

[0236] In the dataset, if the training set is usually divided, the training data and validation data in the entire training set are divided and used in a ratio of approximately 8:2 or 7:3, and if the test data is included, they are divided and used in a ratio of 6:2:2 (training: validation: test).

[0237] Collaboration Level

[0238] The cooperation level may be defined as follows depending on whether the AI / ML function between the base station and the UE is available, and variations due to combination or separation of the following levels are also possible.

[0239] Cat 0a) No collaboration framework: AI / ML algorithms are purely implementation-based and do not require air interface changes.

[0240] Baseline

[0241] Cat 0b) has no collaborative framework and modifies the air interface to accommodate efficient implementation-based AI / ML algorithms.

[0242] Cat 1) Inter-node assistance to improve AI / ML algorithms at individual nodes. This would apply to UEs getting assistance from the gNB (for training, adaptation, etc.) and vice versa. This level does not require model exchange between network nodes.

[0243] Cat 2) Joint ML operations between UE and gNB. This level requires AI / ML model instruction or exchange between network nodes.

[0244] (Cat 0a) No collaboration framework: AI / ML algorithms are purely implementation-based and do not require air interface changes.

[0245] Baseline

[0246] Cat 0b) has no collaborative framework and modifies the air interface to accommodate efficient implementation-based AI / ML algorithms.

[0247] Cat 1) Inter-node assistance to improve AI / ML algorithms at individual nodes. This would apply to UEs getting assistance from the gNB (for training, adaptation, etc.) and vice versa. This level does not require model exchange between network nodes.

[0248] Cat 2) Joint ML operations between UE and gNB. This level requires AI / ML model instruction or exchange between network nodes.

[0249] Configuration of various embodiments of the present disclosure

[0250] In 3GPP Rel-18 standardization, studies will be conducted to improve the performance on the communication between base station (BS) and user equipment (UE) using artificial intelligence (AI) / machine learning (ML). Three main use cases for evaluating performance improvement using AI / ML have been proposed as CSI reporting, beam management and positioning (see Rel-18 AI / ML SI objectives below). Specifically, in beam management, sub-use cases are proposed for beam prediction in the time domain and / or spatial domain to reduce overhead and latency, and to improve beam selection accuracy.

[0251]

[0252]

[0253]

[0254]

[0255] In order to list the types of AI / ML-based operations between the base station and the UE, they can be simply divided into BS AI / ML operations, UE AI / ML operations, and BS-UE joint AI / ML operations. The present disclosure describes: a method for UE reporting information in AI / ML-based beam management, wherein the information can mainly be used as an input parameter of BS AI / ML; and a beam reporting method through UE AI / ML.

[0256] The present disclosure proposes a beam reporting operation of a UE for AI / ML-based beam management.

[0257] In the present disclosure, “ / ” may be interpreted as “and”, “or” or “and / or” according to the context.

[0258] Recommendation 1: In addition to / independent of conventional L1-RSRP / SINR-based beam reporting, the UE may perform optimal CRI / SSBRI reporting from the best beam perspective with a large slope / derivative value and / or from a beam perspective with a slope / derivative value greater than or equal to a threshold based on the slope of the L1-RSRP / SINR value in the CRI / SSBRI in the CSI resource configuration for a specific beam report (e.g., based on the derivative value of the L1-RSRP / SINR value per time unit). The beam report of the slope / derivative value may be reported to the base station as an additional payload of the conventional beam report instance (e.g., CRI / SSBRI+RSRP / SINR value of CRI / SSBRI+slope / derivative value of CRI / SSBRI), or independently reported to the base station via a separate beam report configuration. In addition, if the best beam is selected / reported based on the slope / derivative value, a beam with a smaller absolute value of RSRP / SINR but a better slope may be selected and reported. Therefore, the UE proposes a method of defining / configuring and using a metric that considers both the absolute value and the slope of L1-RSRP / SINR for a specific CRI / SSBRI (e.g., selecting the beam with the maximum value of w1*RSRP / SINR+w2*slope_RSRP / SINR). Alternatively / and, the UE may select N1 beams based on the absolute value of RSRP / SINR and select N2 beams based on the slope to report a total of N1+N2 beam IDs and related quality information (RSRP / SINR values ​​for N1 beams and slope / derivative values ​​for N2 beams).

[0259] reportQuantity for beam reporting may be newly introduced.

[0260] When the instantaneous L1-RSRP / SINR is expressed as a function y(x) with time as a variable, the slope / derivative value may be expressed as (y(t2)-y(t1)) / (t2-t1).

[0261] The time units for calculating the slope / derivative values ​​(t1 and t2 in the above example) or / and w1 / w2 in the metrics for considering absolute value and slope may be specified / defined in the specification or configured / indicated by the base station configuration.

[0262] The best beam report using the slope / derivative value can be used by the base station without any separate processing by the base station to determine the DL service beam of the UE, or can be used as one of the input parameters of the AI / ML function for future DL service beam prediction on the base station side. That is, if a base station without (or with) AI / ML function configures and receives a UE beam report, the base station can immediately configure / indicate at least one of the reported best beams as a DL beam for DL ​​transmission / reception because the beam report contains information that the RSRP / SINR value of a specific beam is increased. Or / and, when a base station with AI / ML function drives the AI / ML function for future DL service beam prediction, the base station can apply the beam report information as one of the input parameters and use it for UE service beam prediction. Thereafter, the base station can configure / indicate the DL beam for DL ​​transmission / reception to the UE based on the predicted service beam information.

[0263] In the beam reporting operation of Recommendation 1, the L3 filtered RSRP value can be used instead of the L1-RSRP / SINR value. That is, the UE can perform the best beam report for the beam with a good trend (e.g., slope / derivative value) of the RSRP value filtered in L3. The third layer filtering of the higher layer is performed according to the process shown in the table below. In the following formula, the value of 'a' is configured by the base station RRC configuration. As an additional embodiment, the present invention proposes a method for L3 filtering of beam measurement quantities through base station AI / ML or / and UE AI / ML. The base station can configure the optimal 'a' value for the UE through AI / ML, or / and the UE can calculate and configure / apply the filter output of a specific beam measurement quantity (using the beam measurement as an input parameter) through the AI / ML function, instead of using the following formula for L3 filtering.

[0264]

[0265]

[0266] Recommendation 2: In addition to / independent of the traditional L1-RSRP / SINR based beam reporting, the UE may also perform best beam reporting for a specific time instance in the past or / and future time instances. That is, when reporting CRI / SSBRI and L1-RSRP / SINR values ​​in the beam reporting payload, the UE device may report the best CRI / SSBRI and L1-RSRP / SINR values ​​for each timestamp. For example, ...t-2: CRI1, -76dBm, t-1: CRI1, -68dBm, t: CRI3, -70dBm, t+1: CRI3, -72dBm, t+2: CRI3, -66dBm, ... In the above report, when beam reporting is performed for multiple CRI / SSBRIs per timestamp, the RSRP( / SINR) value of the best CRI / SSBRI for each timestamp can be represented by a 7-bit value in the range of [-140,-44]( / [-23,40])dBm and a step size of 1( / 0.5)dB, and with reference to the maximum measured L1-RSRP( / SINR) value as part of the same L1-RSRP( / SINR) reporting instance, the RSRP( / SINR) values ​​of the remaining CRI / SSBRIs can be represented by calculation using a 2dB( / 1dB) step size. For another example, in addition to the method of reporting the measured / predicted value using a timestamp, the UE can also report the change in the measured / predicted value in the form of a function. For example, the UE can use a customized series to express and calculate the value of the variation at a specific "t" as y(t) = f(t0) + f(t0)'*(t-t0) + 0.5*f(t0)"*(t-t0)^2…, and can report the beam with the best variation. Here, f(a) can be a function of the variation. In addition to the report, the UE can also report coefficients of order 0, order 1, order 2… (if necessary) for measuring the variation at a specific reference time (t0).

[0267] For another example, in addition to the method of reporting the measured / predicted value using a timestamp, the UE may also report the change in the measured / predicted value in the form of a function. For example, the UE may use a customized series to express and calculate the value of the change at a specific 't' as y(t) = f(t0) + f(t0)'*(t-t0) + 0.5*f(t0)"*(t-t0)^2..., and may report the beam with the best change. Here, f(a) may be a function of the change. In addition to the report, the UE may also report one or more 0th order, 1st order, 2nd order... (if necessary) coefficients for measuring the change at a specific reference time (t0). That is, the UE may report one or more coefficients within a polynomial to express the change / rate of change.

[0268] In beam reporting of Recommendation 2, the time unit between timestamps and the number of timestamps to be reported may be specified / defined in the specification or configured / indicated by the base station configuration.

[0269] In the beam reporting of Recommendation 2, in the best beam reporting at a future point in time, the best beam can be determined based on the RSRP / SINR trends measured at the UE as described in Recommendation 1, or based on UE AI / ML calculations if there is AI / ML functionality on the UE side.

[0270] The best beam report for each timestamp in Recommendation 2 can be used by the base station without any separate processing by the base station to determine the DL serving beam for the UE, or can be used as one of the input parameters of the AI / ML function on the base station side for future DL serving beam prediction.

[0271] The operations between the base station and the UE may adopt at least one combination of the embodiments of Proposals 1 and 2.

[0272] Signaling process of various embodiments of the present disclosure

[0273] An example of UE (or base station) operation based on at least one of the above embodiments (eg, at least one of Suggestions 1 and 2) is as follows.

[0274] 1) Receiving (sending) configuration information related to beam measurement and reporting

[0275] The configuration information can be based on suggestions 1 and 2.

[0276] 2) Reception (transmission) and quality measurement of candidate beams based on beam configuration

[0277] 3) The UE sends (receives) a beam report of the best beam based on the reception / measurement of the candidate beams.

[0278] The best beam measurement / determination can be based on suggestions 1 and 2.

[0279] The UE / BS operation is only an example, and each operation (and step) is not necessarily essential. For example, the operations related to the UE's beam measurement and reporting according to the above embodiment may be omitted or added based on the UE / BS implementation method.

[0280] From an implementation perspective, the operations of the UE / BS according to the above embodiments (eg, operations related to UE beam measurement and reporting based on at least one of Recommendations 1 and 2) may be performed as described below. Fig. 9 equipment (e.g. Fig. 9 Processors 1610 and 1660) are used for processing.

[0281] In addition, the operations of the UE / BS according to the above-mentioned embodiments (e.g., operations related to beam measurement and reporting of the UE based on at least one of Recommendations 1 and 2) can be stored in a memory (e.g., Fig. 9 1640 and 1690) for running at least one processor (e.g., Fig. 9 processors 1610 and 1660).

[0282] [Description of claims related to UE]

[0283] Below, refer to Figure 7 The above embodiments are described in detail from the perspective of UE operation. The methods to be described below are distinguished only for the convenience of explanation. Therefore, as long as the methods are not mutually exclusive, it is obvious that a partial configuration of any method can be replaced by a partial configuration of another method or combined with a partial configuration of another method.

[0284] Figure 7 An example of an operation process of a UE in the system applicable to the present disclosure is illustrated.

[0285] In step S3210, the UE receives channel state information (CSI) resource configuration from the base station.

[0286] In step S3220, the UE receives multiple CSI reference signals (RS) from the base station based on multiple first CSI reference signal resource indicators (CRIs) or multiple first synchronization signal block resource indicators (SSBRIs) related to the CSI resource configuration.

[0287] In step S3230, the UE measures a received signal received power (RSRP) or a signal to interference power (SINR) related to the first CRI or the first SSBRI.

[0288] In step S3240, the UE calculates a derivative value per time unit of the measured RSRP or SINR.

[0289] In step S3250, the UE selects a predetermined number of second CRIs or second SSBRIs from the first CRI or first SSBRI based on the absolute value and the derivative value of RSRP or SINR.

[0290] In step S3260, the UE sends a report message related to the second CRI or the second SSBRI to the base station.

[0291] According to various embodiments of the present disclosure, the report message may include an absolute value of RSRP or SINR associated with the second CRI or the second SSBRI and a derivative value of RSRP or SINR associated with the second CRI or the second SSBRI.

[0292] According to various embodiments of the present invention, the report message may include a first reporting configuration based on the absolute value of RSRP or SINR associated with the second CRI or the second SSBRI, and a second reporting configuration based on the derivative value of RSRP or SINR associated with the second CRI or the second SSBRI.

[0293] According to various embodiments of the present disclosure, the second report configuration may be sent together with the first report configuration as an additional payload of the first report configuration. Alternatively, the second report configuration may be configured separately from the first report configuration and sent separately from the first report configuration.

[0294] According to various embodiments of the present disclosure, the second CRI or the second SSBRI may include (N1+N2) CRIs or (N1+N2) SSBRIs.

[0295] According to various embodiments of the present disclosure, N1 CRIs or N1 SSBRIs among the second CRIs or second SSBRIs may be CRIs or SSBRIs determined based on the absolute value of RSRP or SINR among multiple first CRIs or first SSBRIs.

[0296] According to various embodiments of the present disclosure, N2 CRIs or N2 SSBRIs among the second CRI or second SSBRI may be CRIs or SSBRIs determined based on a derivative value of RSRP or SINR among a plurality of first CRIs or first SSBRIs.

[0297] According to various embodiments of the present disclosure, the report message may be based on a metric based on both the absolute value and the derivative value of RSRP or SINR.

[0298] According to various embodiments of the present disclosure, the second CRI or the second SSBRI may be a predetermined number of CRIs or SSBRIs having the highest value based on the metric among the first CRI or the first SSBRI.

[0299] According to various embodiments of the present disclosure, the report message may include the best second CRI or second SSBRI for each timestamp, and RSRP or SINR related to the best second CRI or second SSBRI at each time.

[0300] According to various embodiments of the present disclosure, the report message may include a report on an optimal CRI or SSBRI or a prediction of an optimal CRI or SSBRI at a specific time in the past or future based on the second CRI or the second SSBRI.

[0301] According to various embodiments of the present disclosure, the report message may be expressed in the form of an absolute value of RSRP or SINR associated with the second CRI or the second SSBRI or a rate of change value of one or more of the derivatives of RSRP or SINR associated with the second CRI or the second SSBRI at a specific time.

[0302] According to various embodiments of the present disclosure, the report message may include information about a CRI or SSBRI having an optimal change rate based on a change rate value.

[0303] According to various embodiments of the present disclosure, a change rate value at a specific time may be calculated by a polynomial based on a variable at the specific time.

[0304] According to various embodiments of the present disclosure, the report message may include information about one or more coefficients included in the polynomial.

[0305] According to various embodiments of the present disclosure, a user equipment (UE) in a wireless communication system is provided. The UE may include a transceiver and at least one processor, and the at least one processor may be configured to perform a Figure 7 An operating method of a UE.

[0306] According to various embodiments of the present disclosure, a device for controlling a user equipment (UE) in a wireless communication system is provided. The device may include at least one processor and at least one memory operably connected to the at least one processor. The at least one memory may be configured to store instructions, which are executed by the at least one processor to execute a command based on Figure 7 An operating method of a UE.

[0307] According to various embodiments of the present disclosure, one or more non-transitory computer readable media (CRMs) storing one or more instructions are provided. The one or more instructions may be configured to perform operations based on execution by one or more processors, and these operations may include performing operations based on Figure 7 An operating method of a UE.

[0308] [Description of claims related to BS]

[0309] Below, reference Figure 8 The above embodiments are described in detail from the perspective of the operation of the base station. The methods to be described below are distinguished only for the convenience of explanation. Therefore, as long as the methods are not mutually exclusive, it is obvious that a partial configuration of any method can be replaced by a partial configuration of another method or combined with a partial configuration of another method.

[0310] Figure 8 An example of an operation process of a base station applicable to the system of the present disclosure is illustrated.

[0311] In step S3310, the base station sends a channel state information (CSI) resource configuration to the UE.

[0312] In step S3320, the base station sends multiple CSI reference signals (RS) to the UE based on multiple first CSI reference signal resource indicators (CRIs) or multiple first synchronization signal block resource indicators (SSBRIs) related to the CSI resource configuration.

[0313] In step S3330, the base station receives a report message related to the second CRI or the second SSBRI which is a part of the first CRI or the first SSBRI from the UE.

[0314] According to various embodiments of the present disclosure, the second CRI or the second SSBRI can be a predetermined number of CRIs or SSBRIs selected from the first CRI or the first SSBRI based on the absolute value of the received signal received power (RSRP) or the signal to interference power (SINR) related to the first CRI or the first SSBRI and the derivative value per time unit of the RSRP or SINR related to the first CRI or the first SSBRI.

[0315] According to various embodiments of the present disclosure, the report message may include an absolute value of RSRP or SINR associated with the second CRI or the second SSBRI and a derivative value of RSRP or SINR associated with the second CRI or the second SSBRI.

[0316] According to various embodiments of the present disclosure, the report message may include a first reporting configuration based on the absolute value of RSRP or SINR associated with the second CRI or the second SSBRI and a second reporting configuration based on the derivative value of RSRP or SINR associated with the second CRI or the second SSBRI.

[0317] According to various embodiments of the present disclosure, the second report configuration may be received together with the first report configuration as an additional payload of the first report configuration. Alternatively, the second report configuration may be configured separately from the first report configuration and received separately from the first report configuration.

[0318] According to various embodiments of the present disclosure, the second CRI or the second SSBRI may include (N1+N2) CRIs or (N1+N2) SSBRIs.

[0319] According to various embodiments of the present disclosure, N1 CRIs or N1 SSBRIs among the second CRIs or second SSBRIs may be CRIs or SSBRIs determined based on the absolute value of RSRP or SINR among multiple first CRIs or first SSBRIs.

[0320] According to various embodiments of the present disclosure, N2 CRIs or N2 SSBRIs among the second CRI or second SSBRI may be CRIs or SSBRIs determined based on a derivative value of RSRP or SINR among a plurality of first CRIs or first SSBRIs.

[0321] According to various embodiments of the present disclosure, the report message may be based on a metric based on both the absolute value and the derivative value of RSRP or SINR.

[0322] According to various embodiments of the present disclosure, the second CRI or the second SSBRI is a predetermined number of CRIs or SSBRIs having the highest value based on the metric among the first CRIs or the first SSBRIs.

[0323] According to various embodiments of the present disclosure, the report message may include the best second CRI or second SSBRI for each timestamp, and RSRP or SINR related to the best second CRI or second SSBRI for each time.

[0324] According to various embodiments of the present disclosure, the report message may include a report on an optimal CRI or SSBRI or a prediction of the optimal CRI or SSBRI at a specific time in the past or future based on the second CRI or second SSBRI.

[0325] According to various embodiments of the present disclosure, the report message may be expressed in the form of an absolute value of RSRP or SINR related to the second CRI or the second SSBRI or a rate of change value of one or more of the derivatives of RSRP or SINR related to the second CRI or the second SSBRI at a specific time.

[0326] According to various embodiments of the present disclosure, the report message may include information about a CRI or SSBRI having an optimal change rate based on a change rate value.

[0327] According to various embodiments of the present disclosure, a change rate value at a specific time may be calculated by a polynomial based on a variable at the specific time.

[0328] According to various embodiments of the present disclosure, the report message may include information about one or more coefficients included in the polynomial.

[0329] According to various embodiments of the present disclosure, a base station in a wireless communication system is provided. The base station may include a transceiver and at least one processor, and the at least one processor may be configured to execute based on Figure 8 The operation method of BS.

[0330] According to various embodiments of the present disclosure, a device for controlling a base station in a wireless communication system is provided. The device may include at least one processor and at least one memory operably connected to the at least one processor. The at least one memory may be configured to store instructions, which are executed by the at least one processor to execute a command based on Figure 8 Instructions on the operating methods of the BS.

[0331] According to various embodiments of the present disclosure, one or more non-transitory computer readable media (CRM) storing one or more instructions are provided. The one or more instructions may be configured to perform operations based on execution by one or more processors, and the operations may include performing operations based on Figure 8 The operation method of BS.

[0332] Wireless devices applicable to the present disclosure

[0333] An example of a wireless device to which various embodiments of the present disclosure are applied is described below.

[0334] Fig. 9 An example of the structure of the first device and the second device applicable to the system of the present disclosure is illustrated.

[0335] The first device 1600 may include a processor 1610 , an antenna unit 1620 , a transceiver 1630 , and a memory 1640 .

[0336] The processor 1610 may perform baseband-related signal processing and include a higher layer processing unit 1611 and a physical layer processing unit 1615. The higher layer processing unit 1611 may process the operation of the MAC layer, the RRC layer, or a higher layer. The physical layer processing unit 1615 may process the operation of the PHY layer. For example, if the first device 1600 is a base station (BS) device in base station-UE communication, the physical layer processing unit 1615 may perform uplink received signal processing, downlink transmitted signal processing, etc. For example, if the first device 1600 is a first UE device in inter-UE communication, the physical layer processing unit 1615 may perform downlink received signal processing, uplink transmitted signal processing, side link transmitted signal processing, etc. In addition to performing baseband-related signal processing, the processor 1610 may also control the overall operation of the first device 1600.

[0337] The antenna unit 1620 may include one or more physical antennas, and if the antenna unit 1620 includes multiple antennas, MIMO transmission / reception is supported. The transceiver 1630 may include a radio frequency (RF) transmitter and an RF receiver. The memory 1640 may store information processed by the processor 1610 and software, an operating system, and applications related to the operation of the first device 1600. The memory 1640 may also include components such as a buffer.

[0338] The processor 1610 of the first device 1600 may be configured to implement operations of a BS in BS-UE communication (or operations of a first UE device in inter-UE communication) in the embodiments described in the present disclosure.

[0339] The second device 1650 may include a processor 1660 , an antenna unit 1670 , a transceiver 1680 , and a memory 1690 .

[0340] The processor 1660 may perform baseband-related signal processing and include a higher layer processing unit 1661 and a physical layer processing unit 1665. The higher layer processing unit 1661 may process the operation of the MAC layer, the RRC layer, or a higher layer. The physical layer processing unit 1665 may process the operation of the PHY layer. For example, if the second device 1650 is a UE device in BS-UE communication, the physical layer processing unit 1665 may perform downlink received signal processing, uplink transmitted signal processing, etc. For example, if the second device 1650 is a second UE device in inter-UE communication, the physical layer processing unit 1665 may perform downlink received signal processing, uplink transmitted signal processing, side link received signal processing, etc. In addition to performing baseband-related signal processing, the processor 1660 may also control the overall operation of the second device 1660.

[0341] The antenna unit 1670 may include one or more physical antennas, and if the antenna unit 1670 includes multiple antennas, MIMO transmission / reception is supported. The transceiver 1680 may include an RF transmitter and an RF receiver. The memory 1690 may store information processed by the processor 1660 and software, an operating system, and applications related to the operation of the second device 1650. The memory 1690 may also include components such as a buffer.

[0342] The processor 1660 of the second device 1650 may be configured to implement the operation of the UE in the BS-UE communication (or the operation of the second UE device in the inter-UE communication) in the embodiments described in the present disclosure.

[0343] The description of the BS and the UE in BS-UE communication (or the first UE device and the second UE device in inter-UE communication) in the examples of the present disclosure is also applicable to the operations of the first device 1600 and the second device 1650, and detailed description is omitted here.

[0344] According to the wireless communication technology implemented in the devices 1600 and 1650 of the present disclosure, in addition to LTE, NR, and 6G, it may also include a narrowband Internet of Things (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of a low-power wide area network (LPWAN) technology and may be implemented in standards such as LTE Cat NB1 and / or LTE Cat NB2. NB-IoT technology is not limited to the above names.

[0345] Additionally or alternatively, the wireless communication technology implemented in the devices 1600 and 1650 according to the present disclosure may communicate based on the LTE-M technology. For example, the LTE-M technology may be an example of an LPWAN technology and may be referred to by various names, such as enhanced machine type communication (eMTC). For example, the LTE-M technology may be implemented by at least one of various standards, such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-bandwidth limited), 5) LTE-MTC, 6) LTE machine type communication, and / or 7) LTE M. The LTE-M technology is not limited to the above names.

[0346] Additionally or alternatively, the wireless communication technology implemented in the devices 1600 and 1650 according to the present disclosure may include at least one of ZigBee, Bluetooth, and a low power wide area network (LPWAN) considering low power communication, and is not limited to the above names. For example, ZigBee technology can create a personal area network (PAN) related to small / low power digital communication based on various standards such as IEEE 802.15.4, and can be called by various names.

[0347] The claims described in the various embodiments of the present disclosure may be combined in various ways. For example, the technical features of the method claims of the various embodiments of the present disclosure may be combined and implemented as a device, and the technical features of the device claims of the various embodiments of the present disclosure may be combined and implemented as a method. In addition, the technical features of the method claims in the various embodiments of the present disclosure may be combined with the technical features of the device claims and implemented as a device, and the technical features of the method claims in the various embodiments of the present disclosure may be combined with the technical features of the device claims and implemented as a method.

Claims

1. A method of operating a user equipment (UE) in a wireless communication system, the method comprising: receiving a channel state information (CSI) resource configuration from a base station; receiving a plurality of CSI reference signals (RS) from the base station based on a plurality of first CSI reference signal resource indicators (CRIs) or a plurality of first synchronization signal block resource indicators (SSBRIs) associated with the CSI resource configuration; measuring a received signal received power (RSRP) or a signal to interference ratio (SINR) related to the first CRI or the first SSBRI; Calculating a derivative value per time unit of the measured RSRP or SINR; Selecting a predetermined number of second CRIs or second SSBRIs from the first CRI or the first SSBRI based on the absolute value of the RSRP or the SINR and the derivative value; as well as sending a report message related to the second CRI or the second SSBRI to the base station, The report message includes the absolute value of the RSRP or the SINR related to the second CRI or the second SSBRI, and the derivative value of the RSRP or the SINR related to the second CRI or the second SSBRI.

2. The method according to claim 1, wherein: the report message includes a first report configuration based on the absolute value of the RSRP or the SINR associated with the second CRI or the second SSBRI, and a second report configuration based on the derivative value of the RSRP or the SINR associated with the second CRI or the second SSBRI, wherein the second reporting configuration is sent together with the first reporting configuration as an additional payload of the first reporting configuration, or The second reporting configuration is configured separately from the first reporting configuration and is sent separately from the first reporting configuration.

3. The method according to claim 1, wherein: The second CRI or the second SSBRI includes (N1+N2) CRIs or (N1+N2) SSBRIs, wherein N1 CRIs or N1 SSBRIs among the second CRIs or the second SSBRIs are CRIs or SSBRIs determined based on the absolute value of the RSRP or the SINR among the plurality of first CRIs or first SSBRIs, and Among them, N2 CRIs or N2 SSBRIs among the second CRI or the second SSBRI are CRIs or SSBRIs among the multiple first CRIs or first SSBRIs determined based on the derivative value of the RSRP or the SINR.

4. The method according to claim 1, wherein: The report message is based on a metric based on both the absolute value and the derivative value of the RSRP or the SINR, and The second CRI or the second SSBRI is a predetermined number of CRIs or SSBRIs having the highest value based on the metric among the first CRIs or the first SSBRIs.

5. The method according to claim 1, wherein: The report message includes the best second CRI or second SSBRI for each time stamp, and the RSRP or the SINR associated with the best second CRI or second SSBRI at each time, and The report message also includes a report on an optimal CRI or SSBRI or a prediction of the optimal CRI or SSBRI at a specific time in the past or future based on the second CRI or the second SSBRI.

6. The method according to claim 1, wherein: The report message is expressed in the form of a change rate value of one or more of the absolute value of the RSRP or the SINR associated with the second CRI or the second SSBRI or the derivative of the RSRP or the SINR associated with the second CRI or the second SSBRI at a specific time, and The report message includes information about a CRI or SSBRI having an optimal change rate based on the change rate value.

7. The method according to claim 6, wherein: calculating the rate of change value at the specific time by a polynomial based on the variables at the specific time, and The report message includes information about one or more coefficients included in the polynomial.

8. A method of operating a base station in a wireless communication system, the method comprising: Sending channel state information (CSI) resource configuration to user equipment (UE); Sending a plurality of CSI reference signals (RS) to the UE based on a plurality of first CSI reference signal resource indicators (CRIs) or a plurality of first synchronization signal block resource indicators (SSBRIs) associated with the CSI resource configuration; and receiving, from the UE, a report message related to a second CRI or a second SSBRI, wherein the second CRI or the second SSBRI is a part of the first CRI or the first SSBRI, wherein the second CRI or the second SSBRI is a predetermined number of CRIs or SSBRIs selected from the first CRI or the first SSBRI based on an absolute value of a received signal received power (RSRP) or a signal to interference power (SINR) associated with the first CRI or the first SSBRI and a derivative value per time unit of the RSRP or the SINR associated with the first CRI or the first SSBRI, and The report message includes the absolute value of the RSRP or the SINR related to the second CRI or the second SSBRI, and the derivative value of the RSRP or the SINR related to the second CRI or the second SSBRI.

9. The method according to claim 8, wherein: the report message includes a first report configuration based on the absolute value of the RSRP or the SINR associated with the second CRI or the second SSBRI, and a second report configuration based on the derivative value of the RSRP or the SINR associated with the second CRI or the second SSBRI, wherein the second reporting configuration is received together with the first reporting configuration as an additional payload of the first reporting configuration, or The second reporting configuration is configured separately from the first reporting configuration and is received separately from the first reporting configuration.

10. The method according to claim 8, wherein: The second CRI or the second SSBRI includes (N1+N2) CRIs or (N1+N2) SSBRIs, wherein N1 CRIs or N1 SSBRIs among the second CRIs or the second SSBRIs are CRIs or SSBRIs determined based on the absolute value of the RSRP or the SINR among the plurality of first CRIs or first SSBRIs, and Among them, N2 CRIs or N2 SSBRIs among the second CRI or the second SSBRI are CRIs or SSBRIs among the multiple first CRIs or first SSBRIs determined based on the derivative value of the RSRP or the SINR.

11. The method according to claim 8, wherein: The report message is based on a metric based on both the absolute value and the derivative value of the RSRP or the SINR, and The second CRI or the second SSBRI is a predetermined number of CRIs or SSBRIs having the highest value based on the metric among the first CRIs or the first SSBRIs.

12. The method according to claim 8, wherein: The report message includes the best second CRI or second SSBRI for each time stamp, and the RSRP or the SINR associated with the best second CRI or second SSBRI at each time, and The report message also includes a report on an optimal CRI or SSBRI or a prediction of the optimal CRI or SSBRI at a specific time in the past or future based on the second CRI or the second SSBRI.

13. The method according to claim 8, wherein: The report message is expressed in the form of a change rate value of one or more of the absolute value of the RSRP or the SINR associated with the second CRI or the second SSBRI or the derivative of the RSRP or the SINR associated with the second CRI or the second SSBRI at a specific time, and The report message includes information about a CRI or SSBRI having an optimal change rate based on the change rate value.

14. The method according to claim 13, wherein: calculating the rate of change value at the specific time by a polynomial based on the variables at the specific time, and The report message includes information about one or more coefficients included in the polynomial.

15. A user equipment (UE) in a wireless communication system, the UE comprising: Transceiver; at least one processor; as well as at least one memory operably connected to the at least one processor and configured to store instructions for performing operations based on execution by the at least one processor, Wherein, the operation includes all steps of the method according to any one of claims 1 to 7.

16. A base station in a wireless communication system, the base station comprising: Transceiver; at least one processor; as well as at least one memory operably connected to the at least one processor and configured to store instructions for performing operations based on execution by the at least one processor, Wherein, the operation includes all steps of the method according to any one of claims 8 to 14.

17. A control device for controlling a user equipment in a wireless communication system, the control device comprising: at least one processor; as well as at least one memory operably connected to the at least one processor, wherein the at least one memory is configured to store instructions for performing operations based on execution by the at least one processor, and Wherein, the operation includes all steps of the method according to any one of claims 1 to 7.

18. A control device for controlling a base station in a wireless communication system, the control device comprising: at least one processor; as well as at least one memory operatively connected to the at least one processor, wherein the at least one memory is configured to store instructions for performing operations based on execution by the at least one processor, and Wherein, the operation includes all steps of the method according to any one of claims 8 to 14.

19. One or more non-transitory computer-readable media storing one or more instructions, in, The one or more instructions are configured to perform operations upon execution by one or more processors, and Wherein, the operation includes all steps of the method according to any one of claims 1 to 7.

20. One or more non-transitory computer-readable media storing one or more instructions, in, The one or more instructions are configured to perform operations upon execution by one or more processors, and Wherein, the operation comprises all steps of the method according to any one of claims 8 to 14.

Images