Method and apparatus for transmitting and receiving channel state information in wireless communication system

Abstract

Disclosed are a method and apparatus for transmitting and receiving channel state information (CSI) in a wireless communication system. The method according to an embodiment of the present disclosure may comprise the steps of: receiving, by a UE, configuration information related to a CSI report from a base station; receiving, by the UE, a downlink RS from the base station; and on the basis of a prediction-based CSI report being configured on the basis of the configuration information, transmitting, by the UE, the prediction-based CSI report for the downlink RS to the base station.

Description

Method and device for transmitting and receiving channel state information in a wireless communication system

[0001] The present disclosure relates to a wireless communication system, and more specifically, to a method and apparatus for transmitting and receiving channel state information in a wireless communication system.

[0002] Mobile communication systems were developed to provide voice services while ensuring user mobility. However, mobile communication systems have expanded their scope to include data services as well as voice. Currently, due to the explosive increase in traffic leading to resource shortages and users demanding higher-speed services, more advanced mobile communication systems are required.

[0003] The requirements for next-generation mobile communication systems largely include the ability to accommodate explosive data traffic, a dramatic increase in transmission rates per user, a significantly increased number of connected devices, very low end-to-end latency, and high energy efficiency. To achieve this, various technologies are being researched, such as dual connectivity, massive multiple input multiple output (MMIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] The technical problem of the present disclosure is to provide a method and apparatus for transmitting and receiving channel state information (CSI) (including beam reports).

[0005] In addition, an additional technical objective of the present disclosure is to provide a method and apparatus for performing AI / ML (artificial intelligence / machine learning) CSI reporting (e.g., prediction-based CSI reporting) by a UE.

[0006] In addition, an additional technical objective of the present disclosure is to provide a method and apparatus for managing a processing unit for processing AI / ML CSI reports (e.g., prediction-based CSI reports) by a UE.

[0007] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure belongs from the description below.

[0008] A method according to an aspect of the present disclosure may include: receiving configuration information related to a channel state information (CSI) report from a base station by a user device (UE); receiving a downlink reference signal (RS) from the base station by the UE; and transmitting the prediction-based CSI report for the downlink RS to the base station by the UE, based on the prediction-based CSI report being configured by the configuration information. For the prediction-based CSI report, both a first CSI processing unit (CPU) not specific to the prediction-based CSI report and a second CPU specific to the prediction-based CSI report may be occupied.

[0009] A method according to a further aspect of the present disclosure may include: transmitting configuration information related to a channel state information (CSI) report to user equipment (UE) by a base station; transmitting a downlink reference signal (RS) to the UE by the base station; and receiving a prediction-based CSI report for the downlink RS from the UE by the base station based on the prediction-based CSI report being set by the configuration information. For the prediction-based CSI report, both a first CSI processing unit (CPU) not specific to the prediction-based CSI report and a second CPU specific to the prediction-based CSI report may be occupied.

[0010] According to an embodiment of the present disclosure, conventional CSI processing and AI / ML processing can be performed together for AI / ML CSI reporting (including beam reporting) (e.g., prediction-based CSI reporting).

[0011] In addition, according to an embodiment of the present disclosure, processing units can be flexibly managed as conventional CSI processing and AI / ML processing are performed together for AI / ML CSI reporting (including beam reporting) (e.g., prediction-based CSI reporting).

[0012] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below.

[0013] The accompanying drawings, which are included as part of the detailed description to aid in understanding the present disclosure, provide embodiments of the present disclosure and explain the technical features of the present disclosure together with the detailed description.

[0014] FIG. 1 illustrates the structure of a wireless communication system to which the present disclosure can be applied.

[0015] FIG. 2 illustrates a frame structure in a wireless communication system to which the present disclosure may be applied.

[0016] FIG. 3 illustrates a resource grid in a wireless communication system to which the present disclosure may be applied.

[0017] FIG. 4 illustrates a physical resource block in a wireless communication system to which the present disclosure may be applied.

[0018] FIG. 5 illustrates a slot structure in a wireless communication system to which the present disclosure may be applied.

[0019] FIG. 6 illustrates physical channels used in a wireless communication system to which the present disclosure may be applied, and a general method of transmitting and receiving signals using these channels.

[0020] FIG. 7 is a diagram illustrating downlink beam management operations in a wireless communication system to which the present disclosure may be applied.

[0021] FIG. 8 is a diagram illustrating a downlink beam management procedure using an SSB in a wireless communication system to which the present disclosure may be applied.

[0022] FIG. 9 is a diagram illustrating downlink beam management operation using CSI-RS in a wireless communication system to which the present disclosure may be applied.

[0023] FIG. 10 is a diagram illustrating the process of determining the receiving beam of a terminal in a wireless communication system to which the present disclosure may be applied.

[0024] FIG. 11 is a diagram illustrating the transmission beam determination process of a base station in a wireless communication system to which the present disclosure may be applied.

[0025] FIG. 12 is a diagram illustrating resource allocation in the time and frequency domains related to the operation of downlink beam management in a wireless communication system to which the present disclosure may be applied.

[0026] FIG. 13 illustrates an exemplary functional framework for AI / ML operations to which some examples of the present disclosure may be applied.

[0027] FIG. 14 illustrates an exemplary communication procedure based on an AI / ML model between a first node and a second node to which some examples of the present disclosure may be applied.

[0028] FIG. 15 is a diagram illustrating a signaling procedure between a base station and a UE for a prediction-based CSI reporting method according to one embodiment of the present disclosure.

[0029] FIG. 16 is a diagram illustrating the operation of a UE for reporting predicted channel status information according to one embodiment of the present disclosure.

[0030] FIG. 17 is a diagram illustrating the operation of a base station for reporting channel status information according to one embodiment of the present disclosure.

[0031] FIG. 18 illustrates a block diagram of a wireless communication device according to one embodiment of the present disclosure.

[0032] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the present disclosure may be practiced. The following detailed description includes specific details to provide a complete understanding of the present disclosure. However, those skilled in the art will know that the present disclosure may be practiced without such specific details.

[0033] In some cases, to avoid obscuring the concept of the present disclosure, known structures and devices may be omitted or illustrated in the form of a block diagram focusing on the core functions of each structure and device.

[0034] In the present disclosure, when a component is described as being “connected,” “combined,” or “joined” with another component, this may include not only a direct connection but also an indirect connection in which another component exists between them. Furthermore, in the present disclosure, the terms “comprising” or “having” specify the presence of the mentioned features, steps, actions, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, actions, elements, components, and / or groups thereof.

[0035] In the present disclosure, terms such as "first," "second," etc. are used solely for the purpose of distinguishing one component from another and are not used to limit the components, nor do they limit the order or importance of the components unless specifically stated otherwise. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and likewise, a second component in one embodiment may be referred to as a first component in another embodiment.

[0036] The terms used in this disclosure are for the description of specific embodiments and are not intended to limit the claims. As used in the description of embodiments and in the appended claims, the singular form is intended to include the plural form unless the context clearly indicates otherwise. The term "and / or" as used in this disclosure may refer to one of the related enumerated items, or refers to and includes any and all possible combinations of two or more of them. Additionally, the " / " between words in this disclosure has the same meaning as "and / or" unless otherwise noted.

[0037] The present disclosure describes a wireless communication network or a wireless communication system, and operations performed in the wireless communication network may be performed in the process of controlling the network and transmitting or receiving signals by a device (e.g., a base station) governing the wireless communication network, or in the process of transmitting or receiving signals with or between the network and terminals by a terminal connected to the wireless network.

[0038] In the present disclosure, transmitting or receiving a channel includes the meaning of transmitting or receiving information or a signal through said 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.

[0039] In the following, the downlink (DL) refers to communication from a base station to a terminal, and the uplink (UL) refers to communication from a terminal to a base station. In the downlink, the transmitter may be part of the base station, and the receiver may be part of the terminal. In the uplink, the transmitter may be part of the terminal, and the receiver may be part of the base station. The base station may be referred to as the first communication device, and the terminal as the second communication device. The term base station (BS) may be replaced by terms such as fixed station, Node B, eNB (evolved-NodeB), gNB (Next Generation NodeB), BTS (base transceiver system), Access Point (AP), network (5G network), AI (Artificial Intelligence) system / module, RSU (roadside unit), robot, drone (UAV: Unmanned Aerial Vehicle), AR (Augmented Reality) device, VR (Virtual Reality) device, etc.In addition, the terminal may be fixed or mobile and may be replaced with terms such as UE (User Equipment), MS (Mobile Station), UT (user terminal), MSS (Mobile Subscriber Station), SS (Subscriber Station), AMS (Advanced Mobile Station), WT (Wireless terminal), MTC (Machine-Type Communication) device, M2M (Machine-to-Machine) device, D2D (Device-to-Device) device, vehicle, RSU (road side unit), robot, AI (Artificial Intelligence) module, drone (UAV: Unmanned Aerial Vehicle), AR (Augmented Reality) device, VR (Virtual Reality) device.

[0040] The following technologies can be used in various wireless access systems such as CDMA, FDMA, TDMA, OFDMA, and SC-FDMA. CDMA can be implemented using wireless technologies such as UTRA (Universal Terrestrial Radio Access) or CDMA2000. TDMA can be implemented using wireless technologies such as GSM (Global System for Mobile Communications), GPRS (General Packet Radio Service), and EDGE (Enhanced Data Rates for GSM Evolution). OFDMA can be implemented using wireless technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (Evolved UTRA). UTRA is part of the UMTS (Universal Mobile Telecommunications System). 3GPP (3rd Generation Partnership Project) LTE (Long Term Evolution) is part of E-UMTS (Evolved UMTS) using E-UTRA, and LTE-A (Advanced) / 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.

[0041] For clarity of explanation, the description is based on 3GPP communication systems (e.g., LTE-A, NR), but the technical scope of this disclosure is not limited thereto. LTE refers to technology from 3GPP Technical Specification (TS) 36.xxx Release 8 onwards. Specifically, LTE technology from 3GPP TS 36.xxx Release 10 onwards is referred to as LTE-A, and LTE technology from 3GPP TS 36.xxx Release 13 onwards is referred to as LTE-A pro. 3GPP NR refers to technology from TS 38.xxx Release 15 onwards. LTE / NR may be referred to as a 3GPP system. "xxx" indicates a specific standard document number. LTE / NR may be collectively referred to as a 3GPP system. Regarding background technology, terms, abbreviations, etc. used in the description of this disclosure, reference may be made to matters described in standard documents published prior to this disclosure. For example, the following documents may be referenced.

[0042] For 3GPP LTE, refer to TS 36.211 (Physical channels and modulation), TS 36.212 (Multiplexing and channel coding), TS 36.213 (Physical layer procedures), TS 36.300 (General description), and TS 36.331 (Radio resource control).

[0043] For 3GPP NR, you may refer to TS 38.211 (Physical Channels and Modulation), TS 38.212 (Multiplexing and Channel Coding), TS 38.213 (Physical Layer Procedures for Control), TS 38.214 (Physical Layer Procedures for Data), TS 38.300 (General Description of NR and NG-RAN (New Generation-Radio Access Network)), and TS 38.331 (Radio Resource Control Protocol Specification).

[0044] Abbreviations of terms that may be used in this disclosure are defined as follows.

[0045] - BM: Beam management

[0046] - CQI: Channel quality indicator

[0047] - CRI: Channel State Information - Reference Signal Resource Indicator

[0048] - CSI: Channel state information

[0049] - CSI-IM: Channel state information - interference measurement

[0050] - CSI-RS: Channel state information - reference signal

[0051] - DMRS: demodulation reference signal

[0052] - FDM: Frequency Division Multiplexing

[0053] - FFT: Fast Fourier Transform

[0054] - IFDMA: Interleaved frequency division multiple access

[0055] - IFFT: Inverse Fast Fourier Transform

[0056] - L1-RSRP: Layer 1 reference signal received power

[0057] - L1-RSRQ: Layer 1 reference signal received quality

[0058] - MAC: Medium Access Control

[0059] - NZP: Non-zero power

[0060] - OFDM: Orthogonal Frequency Division Multiplexing

[0061] - PDCCH: Physical downlink control channel

[0062] - PDSCH: Physical downlink shared channel

[0063] - PMI: Precoding Matrix Indicator

[0064] - RE: resource element

[0065] - RI: Rank indicator

[0066] - RRC: Radio Resource Control

[0067] - RSSI: Received signal strength indicator

[0068] - Rx: Reception

[0069] - QCL: quasi co-location

[0070] - SINR: Signal to interference and noise ratio

[0071] - SSB (or SS / PBCH block): Synchronization signal block (including primary synchronization signal (PSS), secondary synchronization signal (SSS), and physical broadcast channel (PBCH))

[0072] - TDM: Time Division Multiplexing

[0073] - TRP: transmission and reception point

[0074] - TRS: Tracking Reference Signal

[0075] - Tx: transmission

[0076] - UE: User equipment

[0077] - ZP: Zero Power

[0078] General System

[0079] As more communication devices require larger communication capacities, the need for enhanced mobile broadband communication compared to existing radio access technology (RAT) is emerging. Furthermore, Massive Machine Type Communications (MTC), which connects multiple devices and objects to provide various services anytime and anywhere, is also one of the major issues to be considered in next-generation communication. In addition, communication system designs that take into account services and terminals sensitive to reliability and latency are being discussed. As such, the introduction of next-generation RATs considering eMBB (enhanced mobile broadband communication), Mmtc (massive MTC), and URLLC (Ultra-Reliable and Low Latency Communication) is being discussed, and for convenience, this technology is referred to as NR in this disclosure. NR is an expression representing an example of 5G RAT.

[0080] A new RAT system including NR uses an OFDM transmission method or a similar transmission method. The new RAT system may follow OFDM parameters different from those of LTE. Alternatively, the new RAT system may follow the existing LTE / LTE-A numerology but support a larger system bandwidth (e.g., 100 MHz). Or, a single cell may support multiple numerologies. That is, terminals operating with different numerologies can coexist within a single cell.

[0081] Numerology corresponds to a single subcarrier spacing in the frequency domain. Different numerologies can be defined by scaling the reference subcarrier spacing to an integer N.

[0082] FIG. 1 illustrates the structure of a wireless communication system to which the present disclosure can be applied.

[0083] Referring to FIG. 1, the NG-RAN consists of gNBs that provide NG-RA (NG-Radio Access) user plane (i.e., new access stratum (AS) sublayer / Packet Data Convergence Protocol (PDCP) / Radio Link Control (RLC) / MAC / PHY)) and control plane (RRC) protocol endpoints for the UE. The gNBs are interconnected via Xn interfaces. The gNBs are also connected to the NGC (New Generation Core) via NG interfaces. More specifically, the gNBs are connected to the AMF (Access and Mobility Management Function) via N2 interfaces and to the UPF (User Plane Function) via N3 interfaces.

[0084] FIG. 2 illustrates a frame structure in a wireless communication system to which the present disclosure may be applied.

[0085] An NR system can support multiple numerologies. Here, the numerology can be defined by subcarrier spacing and cyclic prefix (CP) overhead. In this case, multiple subcarrier spacings can be derived by scaling the base (reference) subcarrier spacing by an integer N (or μ). Furthermore, the numerology used can be selected independently of the frequency band, even if it is assumed that very low subcarrier spacings are not used at very high carrier frequencies. Additionally, various frame structures based on multiple numerologies can be supported in an NR system.

[0086] Below, we examine the OFDM numerologies and frame structures that can be considered in NR systems. Many OFDM numerologies supported in NR systems can be defined as shown in Table 1 below.

[0087] μΔf=2 μ ·15 [kHz]CP015 Normal 130 Normal 260 Normal, Extended 3120 Normal 4240 Normal

[0088] NR supports multiple numerologies (or subcarrier spacing (SCS)) to support various 5G services. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.

[0089] The NR frequency band is defined by two types of frequency ranges (FR1, FR2). FR1 and FR2 can be configured as shown in Table 2 below. Additionally, FR2 may refer to millimeter wave (mmW).

[0090] Frequency Range Designation Corresponding Frequency Range Subcarrier Spacing FR1 4 10MHz - 7125MHz 15, 30, 60kHz FR2 24 250MHz - 52600MHz 60, 120, 240kHz

[0091] Regarding the frame structure in an NR system, the magnitude of various fields in the time domain is T c =1 / (Δf max ·N f It is expressed as a multiple of the time unit of ). Here, Δf max =480·10 3 Hz and N f = 4096. Downlink and uplink transmission is T f =1 / (Δf max N f / 100)·T c It is organized into radio frames having an interval of = 10ms. Here, each radio frame is T sf =(Δf max N f / 1000)·T c =1ms It consists of 10 subframes having the interval. In this case, there may be one set of frames for the uplink and one set of frames for the downlink. Additionally, the transmission at uplink frame number i from the terminal is T before the start of the corresponding downlink frame at the terminal.TA =(N TA +N TA,offset )T c Must start previously. For a subcarrier spacing configuration μ, the slots are n within the subframe. s μ ∈{0,..., N slot Numbered in increasing order of {subframe,μ-1}, and n within the radio frame s,f μ ∈{0,..., N slot frame,μ Numbers are assigned in increasing order of {-1}. One slot is N symb slot It consists of consecutive OFDM symbols of, and N symb slot is determined by CP. Slot n in the subframe s μ The start is OFDM symbol n in the same subframe. s μ N symb slot It is aligned with the start and time of. Not all terminals can transmit and receive simultaneously, which means that not all OFDM symbols in the downlink slot or uplink slot can be used.

[0092] Table 3 shows the number of OFDM symbols per slot in a standard CP (N symb slot ), number of slots per wireless frame (N slot frame,μ ), number of slots per subframe (N slot Table 4 shows the number of OFDM symbols per slot, the number of slots per wireless frame, and the number of slots per subframe in the extended CP.

[0093] μN symb slot N slot frame,μ N slotsubframe,μ01410111420221440431480841416016

[0094] μN symb slot N slot frame,μ N slot subframe,μ212404

[0095] FIG. 2 is an example of the case where μ=2 (SCS is 60 kHz), and referring to Table 3, 1 subframe can contain 4 slots. The 1 subframe={1,2,4} slot shown in FIG. 2 is an example, and the number of slot(s) that can be included in 1 subframe is defined as in Table 3 or Table 4. Additionally, a mini-slot can contain 2, 4, or 7 symbols, or more or fewer symbols.

[0096] Regarding physical resources in an NR system, antenna ports, resource grids, resource elements, resource blocks, and carrier parts may be considered. Below, we will examine in detail the aforementioned physical resources that can be considered in an NR system.

[0097] First, regarding antenna ports, an antenna port is defined such that the channel carrying a symbol on the antenna port can be inferred from the channel carrying another symbol on the same antenna port. If the large-scale property of the channel carrying a symbol on one antenna port can be inferred from the channel carrying a symbol on another antenna port, the two antenna ports can be said to be in a QC / QCL (quasi-co-located or quasi-co-location) relationship. Here, the large-scale property includes one or more of delay spread, Doppler spread, frequency shift, average received power, and received timing.

[0098] FIG. 3 illustrates a resource grid in a wireless communication system to which the present disclosure may be applied.

[0099] Referring to Fig. 3, the resource grid N in the frequency domain RB μ N sc RB It consists of subcarriers, and one subframe is 14.2 μ It is described by way of example as being composed of OFDM symbols, but is not limited thereto. In an NR system, the transmitted signal is N RB μ N sc RB One or more resource grids composed of subcarriers and 2 μ N symb (μ) It is described by the OFDM symbols of. Here, N RB μ≤ N RB max,μ It is. The above N RB max,μrepresents the maximum transmission bandwidth, which can vary not only between numerologies but also between uplink and downlink. In this case, a single resource grid can be established for each μ and antenna port p. Each element of the resource grid for μ and antenna port p is referred to as a resource element and is uniquely identified by an index pair (k,l'). Here, k=0,...,N RB μ N sc RB -1 is an index in the frequency domain, and l'=0,...,2 μ N symb (μ) -1 refers to the location of a symbol within a subframe. When referring to resource elements in a slot, an index pair (k,l) is used. Here, l=0,...,N symb μ It is -1. The resource factor (k,l') for μ and antenna port p is the complex value a k,l' (p,μ) It corresponds to. If there is no risk of confusion or if a specific antenna port or numerology is not specified, the indices p and μ may be dropped, and the resulting complex value is a k,l' (p) or a k,l' This can be. In addition, the resource block (RB) is N in the frequency domain. sc RB =12 is defined by consecutive subcarriers.

[0100] Point A serves as a common reference point for the resource block grid and is acquired as follows.

[0101] - OffsetToPointA for the Primary Cell (PCell) downlink represents the frequency offset between point A and the lowest subcarrier of the lowest resource block that overlaps with the SS / PBCH block used by the terminal for initial cell selection. It is expressed in resource block units assuming a 15 kHz subcarrier interval for FR1 and a 60 kHz subcarrier interval for FR2.

[0102] - absoluteFrequencyPointA represents the frequency-location of point A as expressed in ARFCN (absolute radio-frequency channel number).

[0103] Common resource blocks are numbered from 0 upward in the frequency domain for a subcarrier spacing setting μ. The center of subcarrier 0 of common resource block 0 for a subcarrier spacing setting μ coincides with 'point A'. Common resource block number n in the frequency domain CRB μ The relationship between the resource element (k,l) and the subcarrier spacing setting μ is given as Equation 1 below.

[0104]

[0105] In Equation 1, k is defined relative to point A such that k=0 corresponds to a subcarrier centered at point A. Physical resource blocks range from 0 to N within the bandwidth part (BWP). BWP,i size,μ Numbers are assigned up to -1, and i is the BWP number. Physical resource block n in BWP i PRB and common resource block n CRB The relationship between them is given by the following mathematical formula 2.

[0106]

[0107] N BWP,i start,μ is a common resource block where BWP starts relative to common resource block 0.

[0108] FIG. 4 illustrates a physical resource block in a wireless communication system to which the present disclosure may be applied. FIG. 5 illustrates a slot structure in a wireless communication system to which the present disclosure may be applied.

[0109] Referring to FIGS. 4 and 5, a slot contains multiple symbols in the time domain. For example, in the case of a standard CP, one slot contains 7 symbols, but in the case of an extended CP, one slot contains 6 symbols.

[0110] A carrier includes multiple subcarriers in the frequency domain. A Resource Block (RB) is defined as multiple (e.g., 12) consecutive subcarriers in the frequency domain. A Bandwidth Part (BWP) is defined as multiple consecutive (physical) resource blocks in the frequency domain and can correspond to a single numerology (e.g., SCS, CP length, etc.). A carrier may include up to N (e.g., 5) BWPs. Data communication is performed through the active BWPs, and only one BWP can be active for a single terminal. In the resource grid, each element is referred to as a Resource Element (RE) and can be mapped to a single complex symbol.

[0111] NR systems can support up to 400 MHz per Component Carrier (CC). If a terminal operating in such a wideband CC always keeps its radio frequency (RF) chip turned on for the entire CC, the terminal's battery consumption may increase. Alternatively, considering various use cases operating within a single wideband CC (e.g., eMBB, URLLC, Mmtc, V2X, etc.), different numerologies (e.g., subcarrier spacing) may be supported for each frequency band within that CC. Or, the capability regarding maximum bandwidth may vary by terminal. Taking this into account, the base station may instruct the terminal to operate only on a portion of the bandwidth rather than the entire bandwidth of the wideband CC, and for convenience, this portion of bandwidth is defined as the bandwidth part (BWP). A BWP can consist of consecutive RBs on the frequency axis and can correspond to a single numerology (e.g., subcarrier spacing, CP length, slot / mini-slot interval).

[0112] Meanwhile, the base station may configure multiple BWPs within a single CC configured for a terminal. For example, a BWP occupying a relatively small frequency range may be configured in the PDCCH monitoring slot, and the PDSCH indicated by the PDCCH may be scheduled on a larger BWP. Alternatively, if UEs are concentrated on a specific BWP, some terminals may be configured to a different BWP for load balancing. Or, considering frequency domain inter-cell interference cancellation between neighboring cells, a portion of the spectrum in the middle of the total bandwidth may be excluded, and both BWPs may be configured within the same slot. That is, the base station may configure at least one DL / UL BWP for a terminal associated with a broadband CC. The base station may activate at least one DL / UL BWP among the DL / UL BWP(s) configured at a specific time (by L1 signaling, MAC CE (Control Element), or RRC signaling, etc.). Additionally, the base station may instruct a switch to another configured DL / UL BWP (by L1 signaling, MAC CE, RRC signaling, etc.). Alternatively, a switch to a defined DL / UL BWP may occur based on a timer when the timer value expires. In this case, the activated DL / UL BWP is defined as the active DL / UL BWP. However, since the terminal may not receive the configuration for the DL / UL BWP in situations such as when the terminal is performing the initial access process or before the RRC connection is set up, the DL / UL BWP assumed by the terminal in such situations is defined as the initial active DL / UL BWP.

[0113] FIG. 6 illustrates physical channels used in a wireless communication system to which the present disclosure may be applied, and a general method of transmitting and receiving signals using these channels.

[0114] In a wireless communication system, a terminal receives information from a base station via the downlink and transmits information to the base station via the uplink. The information transmitted and received by the base station and the terminal includes data and various control information, and various physical channels exist depending on the type and purpose of the information being transmitted and received.

[0115] When the terminal is powered on or enters a new cell, it performs an initial cell search operation, such as synchronizing with the base station (S601). To this end, the terminal receives a Primary Synchronization Signal (PSS) and a Secondary Synchronization Signal (SSS) from the base station to synchronize with the base station and obtain information such as a cell identifier (ID). Subsequently, the terminal receives a Physical Broadcast Channel (PBCH) from the base station to obtain broadcast information within the cell. Meanwhile, during the initial cell search phase, the terminal receives a Downlink Reference Signal (DL RS) to check the downlink channel status.

[0116] A terminal that has completed initial cell search can obtain more specific system information by receiving a Physical Downlink Control Channel (PDCCH) and a Physical Downlink Shared Channel (PDSCH) according to the information carried on the PDCCH (S602).

[0117] Meanwhile, when a terminal first connects to a base station or when there are no wireless resources available for signal transmission, the terminal may perform a Random Access Procedure (RACH) with respect to the base station (steps S603 to S606). To do this, the terminal transmits a specific sequence as a preamble through a Physical Random Access Channel (PRACH) (S603 and S605), and may receive a response message for the preamble through a PDCCH and a corresponding PDSCH (S604 and S606). In the case of a contention-based RACH, a Contention Resolution Procedure may additionally be performed.

[0118] A terminal that has performed the procedure described above may subsequently perform PDCCH / PDSCH reception (S607) and Physical Uplink Shared Channel (PUSCH) / Physical Uplink Control Channel (PUCCH) transmission (S608) as a general uplink / downlink signal transmission procedure. In particular, the terminal receives Downlink Control Information (DCI) through the PDCCH. Here, the DCI includes control information such as resource allocation information for the terminal, and its format varies depending on its purpose of use.

[0119] Meanwhile, control information transmitted by the terminal to the base station via the uplink or received by the terminal from the base station includes downlink / uplink ACK / NACK (Acknowledgement / Non-Acknowledgement) signals, CQI (Channel Quality Indicator), PMI (Precoding Matrix Indicator), RI (Rank Indicator), etc. In the case of a 3GPP LTE system, the terminal may transmit the aforementioned control information, such as CQI / PMI / RI, via PUSCH and / or PUCCH.

[0120] Table 5 shows an example of the DCI format in an NR system.

[0121] DCI Format Utilization 0_0 Scheduling of PUSCH within a single cell 0_1 Scheduling of one or multiple PUSCH within a single cell, or instructing the UE with cell group (CG) downlink feedback information 0_2 Scheduling of PUSCH within a single cell 1_0 Scheduling of PDSCH within a single DL cell 1_1 Scheduling of PDSCH within a single cell 1_2 Scheduling of PDSCH within a single cell

[0122] Referring to Table 5, DCI formats 0_0, 0_1, and 0_2 may include resource information related to PUSCH scheduling (e.g., UL / SUL (Supplementary UL), frequency resource allocation, time resource allocation, frequency hopping, etc.), information related to Transport Blocks (TB: Transport Block) (e.g., MCS (Modulation Coding and Scheme), NDI (New Data Indicator), RV (Redundancy Version), etc.), information related to Hybrid - Automatic Repeat and request (e.g., process number, DAI (Downlink Assignment Index), PDSCH-HARQ feedback timing, etc.), information related to multiple antennas (e.g., DMRS sequence initialization information, antenna port, CSI request, etc.), and power control information (e.g., PUSCH power control, etc.), and the control information included in each DCI format may be predefined.

[0123] DCI format 0_0 is used for PUSCH scheduling in a cell. The information contained in DCI format 0_0 is transmitted after being scrambled by CRC (cyclic redundancy check) by C-RNTI (Cell RNTI: Cell Radio Network Temporary Identifier), CS-RNTI (Configured Scheduling RNTI), or MCS-C-RNTI (Modulation Coding Scheme Cell RNTI).

[0124] DCI format 0_1 ​​is used to instruct a terminal on the scheduling of one or more PUSCHs in a cell, or on configured grant (CG) downlink feedback information. The information contained in DCI format 0_1 ​​is transmitted after being CRC scrambled by C-RNTI, CS-RNTI, SP-CSI-RNTI (Semi-Persistent CSI RNTI), or MCS-C-RNTI.

[0125] DCI format 0_2 is used for scheduling PUSCH in a single cell. The information contained in DCI format 0_2 is transmitted after being CRC scrambled by C-RNTI, CS-RNTI, SP-CSI-RNTI, or MCS-C-RNTI.

[0126] Next, DCI formats 1_0, 1_1, and 1_2 may include resource information related to PDSCH scheduling (e.g., frequency resource allocation, time resource allocation, VRB (virtual resource block)-PRB (physical resource block) mapping, etc.), transmission block (TB) related information (e.g., MCS, NDI, RV, etc.), HARQ related information (e.g., process number, DAI, PDSCH-HARQ feedback timing, etc.), multiple antenna related information (e.g., antenna port, TCI (transmission configuration indicator), SRS (sounding reference signal) request, etc.), PUCCH related information (e.g., PUCCH power control, PUCCH resource indicator, etc.), and the control information included in each DCI format may be predefined.

[0127] DCI format 1_0 is used for scheduling PDSCH in a single DL cell. The information contained in DCI format 1_0 is transmitted after being CRC scrambled by C-RNTI, CS-RNTI, or MCS-C-RNTI.

[0128] DCI format 1_1 is used for scheduling PDSCH in a single cell. The information contained in DCI format 1_1 is transmitted after being CRC scrambled by C-RNTI, CS-RNTI, or MCS-C-RNTI.

[0129] DCI format 1_2 is used for PDSCH scheduling in a single cell. The information contained in DCI format 1_2 is transmitted after being CRC scrambled by C-RNTI, CS-RNTI, or MCS-C-RNTI.

[0130] Quasi-Co Location (QCL)

[0131] An antenna port is defined such that the channel carrying a symbol on the antenna port can be inferred from the channel carrying another symbol on the same antenna port. If the property of the channel carrying a symbol on one antenna port can be inferred from the channel carrying a symbol on another antenna port, the two antenna ports can be said to be in a QC / QCL (quasi co-located or quasi co-location) relationship.

[0132] Here, the channel characteristics include one or more of delay spread, Doppler spread, frequency / Doppler shift, average received power, received timing / average delay, and spatial Rx parameters. Here, spatial Rx parameters refer to spatial (received) channel characteristic parameters such as the angle of arrival.

[0133] The terminal may be configured with a list of up to M TCI-State settings within the upper-level parameter PDSCH-Config to decode the PDSCH according to the detected PDCCH having the DCI intended for the terminal and the given serving cell. The said M depends on the UE capability.

[0134] Each TCI-State includes parameters for establishing a quasi-co-location relationship between one or two DL reference signals and the DM-RS port of the PDSCH.

[0135] The quasi co-location relationship is established by the upper-level parameter qcl-Type1 for the first DL RS and qcl-Type2 for the second DL RS (if set). For two DL RSs, the QCL type is not the same regardless of whether the references are the same DL RS or different DL RSs.

[0136] The quasi co-location type corresponding to each DL RS is given by the higher layer parameter qcl-Type of QCL-Info and can take one of the following values:

[0137] - 'QCL-TypeA': {Doppler shift, Doppler spread, average delay, delay spread}

[0138] - 'QCL-TypeB': {Doppler shift, Doppler spread}

[0139] - 'QCL-TypeC': {Doppler shift, average delay}

[0140] - 'QCL-TypeD': {Spatial Rx parameter}

[0141] For example, if a target antenna port is a specific NZP CSI-RS, the NZP CSI-RS antenna port(s) may be indicated / configured to be QCLed with a specific TRS in terms of QCL-Type A and with a specific SSB in terms of QCL-Type D. A terminal that receives such indication / configuration can receive the NZP CSI-RS using the Doppler and delay values ​​measured at the QCL-Type A TRS, and apply the receiving beam used for receiving the QCL-Type D SSB to receiving the NZP CSI-RS.

[0142] The UE can receive an activation command via MAC CE signaling used to map up to eight TCI states to codepoints in the DCI field 'Transmission Configuration Indication'.

[0143] Beam management (BM)

[0144] BM procedures are L1 (layer 1) / L2 (layer 2) procedures 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, and may include the following procedures and terms.

[0145] - Beam measurement: An operation in which a base station or UE measures the characteristics of a received beamforming signal.

[0146] - Beam determination: The operation in which a base station or UE selects its transmit beam (Tx beam) / receive beam (Rx beam).

[0147] - Beam sweeping: An operation that covers a spatial area using transmitting and / or receiving beams for a set time interval in a predetermined manner.

[0148] - Beam report: An operation in which the UE reports information about the beam-formed signal based on beam measurements.

[0149] The BM procedure can be divided into (1) a DL BM procedure using an SS (synchronization signal) / PBCH (physical broadcast channel) Block or CSI-RS, and (2) a UL BM procedure using an SRS (sounding reference signal).

[0150] In addition, each BM procedure may include transmission beam sweeping to determine the transmission beam (Tx beam) and reception beam sweeping to determine the reception beam (Rx beam).

[0151] The DL BM procedure is described below.

[0152] The DL BM procedure may include (1) transmission to beamformed DL RS (reference signals) of the base station (e.g., CSI-RS or SS Block (SSB)) and (2) beam reporting of the terminal.

[0153] Here, beam reporting may include preferred DL RS ID(identifier)(s) and the corresponding L1-RSRP(Reference Signal Received Power).

[0154] The above DL RS ID may be SSBRI (SSB Resource Indicator) or CRI (CSI-RS Resource Indicator).

[0155] The following describes the DL BM procedure using SSB.

[0156] FIG. 7 is a diagram illustrating downlink beam management operations in a wireless communication system to which the present disclosure may be applied.

[0157] Referring to Fig. 7, the SSB beam and the CSI-RS beam can be used for beam measurement. The measurement metric is L1-RSRP per resource / block. The SSB is used for coarse beam measurement, while the CSI-RS can be used for fine beam measurement. The SSB can be used for both Tx beam sweeping and Rx beam sweeping.

[0158] Rx beam sweeping using SSBs can be performed with the UE changing the Rx beam across multiple SSB bursts for the same SSBRI. Here, one SS burst includes one or more SSBs, and one SS burst set includes one or more SSB bursts.

[0159] FIG. 8 is a diagram illustrating a downlink beam management procedure using an SSB in a wireless communication system to which the present disclosure may be applied.

[0160] Configuration for beam reporting using SSB is performed during CSI / beam configuration in the RRC connected state (or RRC connected mode).

[0161] Referring to FIG. 8, the terminal receives a CSI-ResourceConfig IE from the base station that includes a CSI-SSB-ResourceSetList containing SSB resources used for BM (S410).

[0162] Table 6 shows an example of CSI-ResourceConfig IE. As shown in Table 6, BM configuration using SSB is not defined separately, and SSB is configured like a CSI-RS resource.

[0163] -- ASN1START-- TAG-CSI-RESOURCECONFIG-STARTCSI-ResourceConfig ::= SEQUENCE {csi-ResourceConfigId CSI-ResourceConfigId,csi-RS-ResourceSetList CHOICE {nzp-CSI-RS-SSB SEQUENCE {nzp-CSI-RS-ResourceSetList SEQUENCE (SIZE (1..maxNrofNZP-CSI-RS-ResourceSetsPerConfig)) OF NZP-CSI-RS-ResourceSetId OPTIONAL,csi-SSB-ResourceSetListSEQUENCE (SIZE (1..maxNrofCSI-SSB-ResourceSetsPerConfig)) OF CSI-SSB-ResourceSetIdOPTIONAL},csi-IM-ResourceSetList SEQUENCE (SIZE (1..maxNrofCSI-IM-ResourceSetsPerConfig)) OF CSI-IM-ResourceSetId},bwp-Id BWP-Id,resourceType ENUMERATED { aperiodic, semiPersistent, periodic},...}-- TAG-CSI-RESOURCECONFIGTOADDMOD-STOP-- ASN1STOP

[0164] In Table 6, the csi-SSB-ResourceSetList parameter represents a list of SSB resources used for beam management and reporting in a single resource set. Here, the SSB resource set can be set to {SSBx1, SSBx2, SSBx3, SSBx4, ...}. The SSB index can be defined from 0 to 63.

[0165] The terminal receives SSB resources from the base station based on the above CSI-SSB-ResourceSetList (S420).

[0166] When a CSI-RS reportConfig related to reporting on SSBRI and L1-RSRP is configured, the terminal reports the best SSBRI and the corresponding L1-RSRP to the base station (beam) (S430).

[0167] The DL BM procedure using CSI-RS is described below.

[0168] Regarding the uses of CSI-RS, i) if the repetition parameter is set for a specific CSI-RS resource set and TRS_info is not set, CSI-RS is used for beam management. ii) if the repetition parameter is not set and TRS_info is set, CSI-RS is used for the tracking reference signal (TRS). iii) if the repetition parameter is not set and TRS_info is not set, CSI-RS is used for CSI acquisition.

[0169] These repetition parameters can only be set for CSI-RS resource sets associated with a CSI-ReportConfig that has an L1 RSRP or a 'No Report (or None)' report.

[0170] If a terminal receives a CSI-ReportConfig in which reportQuantity is set to 'cri-RSRP' or 'none', and includes an NZP-CSI-RS-ResourceSet in which the upper layer parameter 'repetition' is set and the CSI-ResourceConfig (upper layer parameter resourcesForChannelMeasurement) for channel measurement does not include the upper layer parameter 'trs-Info', then the terminal may be configured with only ports of the same number (1-port or 2-port) having the upper layer parameter 'nrofPorts' for all CSI-RS resources within the NZP-CSI-RS-ResourceSet.

[0171] (Upper layer parameter) When repetition is set to 'ON', it relates to the terminal's Rx beam sweeping procedure. In this case, when the terminal is configured with NZP-CSI-RS-ResourceSet, the terminal can assume that at least one CSI-RS resource within NZP-CSI-RS-ResourceSet is transmitted through the same downlink spatial domain transmission filter. That is, at least one CSI-RS resource within NZP-CSI-RS-ResourceSet is transmitted through the same Tx beam. Here, at least one CSI-RS resource within NZP-CSI-RS-ResourceSet may be transmitted with different OFDM symbols. Additionally, the terminal does not expect to receive different periodicities in periodicityAndOffset from all CSI-RS resources within NZP-CSI-RS-ResourceSet.

[0172] On the other hand, when Repetition is set to 'OFF', it relates to the base station's Tx beam sweeping procedure. In this case, when repetition is set to 'OFF', the terminal does not assume that at least one CSI-RS resource within NZP-CSI-RS-ResourceSet is transmitted through the same downlink spatial domain transmission filter. That is, at least one CSI-RS resource within NZP-CSI-RS-ResourceSet is transmitted through different Tx beams.

[0173] That is, if the reportQuantity of the above CSI-RS reportConfig IE is set to 'ssb-Index-RSRP', the terminal reports the best SSBRI and the corresponding L1-RSRP to the base station.

[0174] And, if the terminal has a CSI-RS resource configured at the same OFDM symbol(s) as the SSB (SS / PBCH Block) and 'QCL-TypeD' is applicable, the terminal can assume that the CSI-RS and the SSB are quasi-co-located in terms of 'QCL-TypeD'.

[0175] Here, the above QCL Type D may mean that antenna ports are QCL-connected in terms of spatial reception parameters. When a terminal receives multiple DL antenna ports that are in a QCL Type D relationship, it is acceptable to apply the same reception beam. Additionally, the terminal does not expect CSI-RS to be established in an RE that overlaps with the RE of the SSB.

[0176] FIG. 9 is a diagram illustrating downlink beam management operation using CSI-RS in a wireless communication system to which the present disclosure may be applied.

[0177] FIG. 9(a) illustrates the Rx beam determination (or refinement) procedure of a terminal, and FIG. 9(b) illustrates the Tx beam sweeping procedure of a base station. Additionally, FIG. 9(a) is the case where the repetition parameter is set to 'ON', and FIG. 9(b) is the case where the repetition parameter is set to 'OFF'.

[0178] FIG. 10 is a diagram illustrating the process of determining the receiving beam of a terminal in a wireless communication system to which the present disclosure may be applied.

[0179] Referring to Figures 9(a) and 10, we will examine the Rx beam determination process of the terminal.

[0180] The terminal receives an NZP CSI-RS resource set IE containing an upper layer parameter repetition from the base station via RRC signaling (S610). Here, the repetition parameter is set to 'ON'.

[0181] The terminal repeatedly receives resource(s) within a CSI-RS resource set set to repetition 'ON' in different OFDM symbols through the same Tx beam (or DL ​​spatial domain transmission filter) of the base station (S620).

[0182] The terminal determines its own Rx beam (S630).

[0183] The terminal omits the CSI report (S640). In this case, the reportQuantity of the CSI report settings can be set to 'No report (or None)'.

[0184] That is, if the above terminal is set to repetition 'ON', CSI reporting can be omitted.

[0185] FIG. 11 is a diagram illustrating the transmission beam determination process of a base station in a wireless communication system to which the present disclosure may be applied.

[0186] Referring to Fig. 9(b) and Fig. 11, we will examine the Tx beam determination process of the base station.

[0187] The terminal receives an NZP CSI-RS resource set IE containing an upper layer parameter repetition from the base station via RRC signaling (S710). Here, the repetition parameter is set to 'OFF' and is related to the base station's Tx beam sweeping procedure.

[0188] The terminal receives resources within the CSI-RS resource set set to repetition 'OFF' through different Tx beams (DL spatial domain transmission filters) of the base station (S720).

[0189] The terminal selects (or determines) the best beam (S740)

[0190] The terminal reports the ID and associated quality information (e.g., L1-RSRP) for the selected beam to the base station (S740). In this case, the reportQuantity of the CSI reporting settings can be set to 'CRI + L1-RSRP'.

[0191] That is, the terminal reports the CRI and the L1-RSRP for it to the base station when the CSI-RS is transmitted for BM.

[0192] FIG. 12 is a diagram illustrating resource allocation in the time and frequency domains related to the operation of downlink beam management in a wireless communication system to which the present disclosure may be applied.

[0193] Referring to Fig. 12, when repetition 'ON' is set in the CSI-RS resource set, multiple CSI-RS resources are used repeatedly by applying the same transmission beam, and when repetition 'OFF' is set in the CSI-RS resource set, different CSI-RS resources are transmitted to different transmission beams.

[0194] Below, a beam indication method related to downlink BM is described.

[0195] The terminal may receive a list of up to M candidate Transmission Configuration Indication (TCI) states for the purpose of at least Quasi Co-location (QCL) instructions in RRC configuration. Here, M can be 64.

[0196] Each TCI state can be configured as one RS set. Each ID of a DL RS for spatial QCL purposes (QCL Type D) within at least one RS set may refer to one of the DL RS types, such as SSB, P(periodic)-CSI RS, SP(semi-persistent)-CSI RS, A(aperiodic)-CSI RS.

[0197] At least the initialization / update of the IDs of the DL RS(s) within the RS set used for spatial QCL purposes can be performed through at least explicit signaling.

[0198] Table 7 shows an example of a TCI-State information element (IE: information element).

[0199] TCI-State IE associates one or two DL reference signals (RS) with corresponding quasi-co-location (QCL) types.

[0200] -- ASN1START-- TAG-TCI-STATE-STARTTCI-State ::= SEQUENCE {tci-StateId TCI-StateId,qcl-Type1 QCL-Info,qcl-Type2 QCL-Info OPTIONAL, -- Need R...}QCL-Info ::= SEQUENCE {cell ServCellIndex OPTIONAL, -- Need Rbwp-Id BWP-Id OPTIONAL, -- Cond CSI-RS-IndicatedreferenceSignal CHOICE {csi-rs NZP-CSI-RS-ResourceId,ssb SSB-Index},qcl-Type ENUMERATED {typeA, typeB, typeC, typeD},...}-- TAG-TCI-STATE-STOP-- ASN1STOP

[0201] In Table 7, the bwp-Id parameter represents the DL BWP (bandwidth part) where the RS is located, the cell parameter represents the carrier where the RS is located, and the referencesignal parameter represents the reference antenna port(s) or a reference signal containing them that serves as the source of quasi-co-location for the corresponding target antenna port(s). The target antenna port(s) may be a CSI-RS, PDCCH DMRS, or PDSCH DMRS. For example, to indicate QCL reference RS information for a non-zero power (NZP) CSI-RS, the corresponding TCI state ID (identifier) ​​may be indicated in the NZP CSI-RS resource configuration information. As another example, to indicate QCL reference information for a PDCCH DMRS antenna port(s), the TCI state ID may be indicated in each CORESET configuration. As another example, the TCI state ID can be indicated via DCI to indicate QCL reference information for PDSCH DMRS antenna port(s).

[0202] artificial intelligence

[0203] The introduction of AI into communications can streamline and enhance real-time data transmission. AI can determine how complex target tasks are performed using numerous analyses. In other words, AI can increase efficiency and reduce processing latency. Time-consuming tasks such as handover, network selection, and resource scheduling can be performed instantly using AI. AI can also play a significant role in M2M, machine-to-human, and human-to-machine communication. Furthermore, AI can enable rapid communication in Brain-Computer Interfaces (BCI). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.

[0204] The following describes a functional framework for AI / ML (artificial intelligence / machine learning) operations.

[0205] Below, to provide a more specific explanation of AI (or AI / ML), terms may be defined as follows.

[0206] - Data collection: Data collected from network nodes, management entities, or terminals, serving as a basis for AI model training, data analysis, and inference.

[0207] - AI Model: A data-driven algorithm that applies AI technology to generate a set of outputs containing predictive information and / or decision parameters based on a set of inputs.

[0208] - AI / ML Training: An online or offline process of training an AI model by learning features and patterns that best represent data and acquire an AI / ML model trained for inference.

[0209] - AI / ML Inference: A process of making predictions or deriving decisions based on collected data and AI models using trained AI models.

[0210] Life Cycle Management (LCM) procedures for AI / ML models (i.e., model training, model deployment, model inference, model monitoring, model updating, etc.) can be classified into functionality-based LCM and model-based LCM. In functionality-based LCM, AI / ML models may not be identifiable within the network, and the network can direct the activation, deactivation, fallback, or switching of AI / ML functionality. In model-ID (identifier)-based LCM, AI / ML models can be identified within the network, and the network or terminal can activate, deactivate, select, or switch AI / ML models via the model ID.

[0211] FIG. 13 illustrates an exemplary functional framework for AI / ML operations to which some examples of the present disclosure may be applied.

[0212] Figure 13 illustrates a general functional architecture related to both Functionality-based LCM and Model-based LCM. Some functions or some data / information / command flows (i.e., arrows) illustrated in Figure 13 may be omitted.

[0213] Referring to FIG. 13, a general functional framework may be configured to include a data collection function (10), a model training function (20), a management function (30), an inference function (40), and a model storage function (50).

[0214] The Data Collection function (10) is a function that provides input data to the Model Training function (20), Management function (30), and Inference function (40). The Data Collection function (10) performs data preparation based on raw data and can provide input data processed through data preparation. Examples of raw data may include received data / measurement data from terminals or other network entities, inference / output of AI / ML models, etc. The Data Collection function (10) may be performed by a single entity (e.g., terminal, network node, etc.) but may also be performed by multiple entities.

[0215] Here, training data (11) refers to data required as input for the AI / ML model training function (20). monitoring data (12) refers to data required as input for the management (30) of the AI / ML model or AI / ML function. inference data (13) refers to data required as input for the AI / ML inference function (30).

[0216] The Model Training function (20) is a function that performs AI / ML model training, validation, and testing, which can generate model performance metrics that can be used as part of the AI / ML model testing procedure. If necessary, the Model Training function (20) can perform data preparation (e.g., data pre-processing and cleaning, forming and transformation) based on the Training Data (11) delivered from the Data Collection function (10).

[0217] Trained / Updated Model (21): If there is a Model Storage function (50), it is used to transfer trained, validated, and tested AI / ML models to the Model Storage function (50) or to transfer updated versions of the models to the Model Storage function (50).

[0218] The Management function (30) is a function that supervises the operation of an AI / ML model or an AI / ML function. Additionally, the Management function (30) may make decisions to ensure appropriate inference operations based on data received from the Data Collection function (10) (i.e., Monitoring Data (12)) and / or data received from the Inference function (40) (i.e., Inference Output (41)).

[0219] Management Instruction (32) is information required as input to manage the Inference function (40). The relevant information may include the selection / (de)activation / switching of an AI / ML model or an AI / ML-based function, and may also include a fallback to a non-AI / ML operation (i.e., not relying on the inference process).

[0220] A Model Transfer / Delivery Request (33) can be used to request model(s) from Model Storage (50).

[0221] Performance Feedback / Retraining Request (31) refers to information required as input to Model Training function (20) (e.g., for the purpose of retraining or updating the model).

[0222] The inference function (40) is a function that provides output from the process of applying an AI / ML model or AI / ML function using data (i.e., inference data (13)) provided by the data collection (10) as input. Data preparation (e.g., data preprocessing and cleaning, formatting and transformation) may also be performed based on the inference data (13) delivered by the data collection (10). If necessary, the inference function (40) may also perform data preparation (e.g., data pre-processing and cleaning, forming and transformation) based on the inference data (13) provided by the data collection function (10).

[0223] Inference Output (41) is data used in the Management function (30) to monitor the performance of an AI / ML model or AI / ML function. Inference Output (41) may include the inference output of an AI / ML model generated by the Inference function (30), and the details of the inference output may vary depending on the use case.

[0224] The Model Storage function (50) is a function that stores a trained / updated model that can be used to perform the Inference function (40). The Model Storage function (50) can be used as a reference point (if any) applicable to protocol termination, model transmission / delivery, and related processes. Additionally, the Model Storage function (50) is an example and is not intended to restrict the storage location of the actual AI / ML model, and may be omitted.

[0225] Model Transfer / Delivery (51) is used to transfer an AI / ML model to an inference function.

[0226] Cooperation levels can be defined as follows based on the capability of AI / ML functions among multiple nodes, and variations resulting from the combination of multiple levels or the separation of any one level are also possible.

[0227] Cat 0a) No collaboration framework: AI / ML algorithms are based on pure implementation and do not require changes to the wireless interface.

[0228] Cat 0b) This level corresponds to a framework that involves a wireless interface modified to fit efficient implementation-based AI / ML algorithms but without cooperation.

[0229] Cat 1) Inter-node support is involved to improve the AI / ML algorithms of each node. For example, this applies when a specific node receives support from other nodes (for training, adaptation, etc.) and vice versa. At this level, model exchange between network nodes is not required.

[0230] Cat 2) Collaborative AI / ML tasks can be performed among multiple nodes. This level requires the exchange of AI / ML model commands or network nodes.

[0231] FIG. 13 is a diagram illustrating an overall functional framework for an AI / ML model, and all functions and / or all data / information / command signals illustrated in FIG. 13 may not be performed within a specific node, and only some may be performed.

[0232] AI / ML models can be classified into one-side models and two-side models depending on whether training and / or inference are performed on a single node or jointly / sequentially on multiple nodes.

[0233] A one-side model can refer to an AI / ML model where inference is performed entirely by a single node (e.g., a terminal or a network). Here, the training of the AI / ML model can also be performed entirely by a single node. The training and inference of the AI / ML model may be performed by the same node, or they may be performed by different nodes.

[0234] A two-side model can refer to an AI / ML model in which joint inference is performed across multiple nodes (e.g., terminals and networks). Joint inference means that inference is performed collaboratively across multiple nodes; for example, the first part of the inference may be performed by the first node, and the remainder by the second node. Two-side models can be classified into various types as follows, depending on the training method of the AI / ML model.

[0235] - First type: An AI / ML model can be trained on a single node. In this case, joint training can be performed. The trained model can then be distributed to other nodes / entities.

[0236] - Second type: Joint training of AI / ML models can be performed on multiple nodes / entities (e.g., networks and terminals). Joint training can mean that model generation (e.g., CSI generation) and model reconstruction (CSI compression by sub-use cases) are trained in the same loop for forward activation and backward gradient. In this type, joint training can include both simultaneous training (i.e., model generation training and model reconstruction training are performed simultaneously) and sequential training (i.e., model reconstruction training is performed after model generation training).

[0237] - Third Type: Separate training of AI / ML models can be performed at multiple nodes (e.g., networks and terminals). Separate training may mean that training starts sequentially at one node and continues at another node. In this case, if the first node performs the AI / ML model first and shares the training data with the second node, the second node can perform the AI / ML model using the shared training data. For example, training for the CSI generation part may be performed by the terminal, while CSI reconstruction may be performed by the network.

[0238] FIG. 14 illustrates an exemplary communication procedure based on an AI / ML model between a first node and a second node to which some examples of the present disclosure may be applied.

[0239] Step 1: In the description of the present disclosure below, signaling (e.g., information / data / channel / signal, etc.) or a set of signaling between a specific node (e.g., terminal, network, etc.) and another node may be interpreted as the signaling or a set of signaling of Step 1 used to perform an operation based on an AI / ML model, unless otherwise noted. For example, it may correspond to training data for training (i.e., creation and / or reconstruction) of an AI / ML model, or to inference data used for inference of an AI / ML model, or to feedback to an AI / ML model, etc. If signaling between nodes is not required prior to an operation based on an AI / ML model in the present disclosure, Step 1 may be omitted. If a one-side model is used in the present disclosure, unidirectional / bidirectional signaling (set) in the present disclosure may correspond to the signaling of Step 1. In addition, when a two-side model is used in the present disclosure, unidirectional / bidirectional signaling in the present disclosure may correspond to one stage of signaling, and repetitive signaling operations may also correspond to one stage of signaling.

[0240] For example, in AI / ML model-based beam management, when a base station predicts (i.e., infers) high-quality beam(s) based on an AI / ML model, the base station can receive quality / intensity information for multiple beams from the terminal. Additionally, when a terminal predicts (i.e., infers) high-quality beam(s) based on an AI / ML model, the terminal can receive multiple beams from the base station.

[0241] Step 2: In the description of the present disclosure below, operations (e.g., computation, selection, prediction, etc.) at a specific node (e.g., terminal, network, etc.) or common operations (e.g., computation, selection, prediction, etc.) at multiple nodes (e.g., terminal, network, etc.) may correspond to operations of Step 2 based on one or more functions in the functional framework of an AI / ML model, unless otherwise noted. For example, they may correspond to training of an AI / ML model (i.e., creation and / or reconstruction) or inference of an AI / ML model. Where a one-side model is used, operations performed by a single node in the present disclosure may correspond to operations of Step 2, and where a two-side model is used, common operations performed by multiple nodes in the present disclosure may correspond to operations of Step 2.

[0242] For example, in an AI / ML model-based BM, a base station can predict (i.e., infer) high-quality beam(s) based on an AI / ML model by using quality / intensity information for multiple beams received from a terminal as inference data. Additionally, a terminal can measure multiple beams received from a base station and predict (i.e., infer) high-quality beam(s) based on an AI / ML model by using the measurement results as inference data.

[0243] Step 3: In the description of the present disclosure below, signaling (e.g., information / data / channel / signal, etc.) or a set of signaling between a specific node (e.g., terminal, network, etc.) and another node may be interpreted as the signaling or set of signaling of Step 3 generated as a result of an operation based on an AI / ML model, unless otherwise noted. For example, it may correspond to an output resulting from the inference of an AI / ML model. If signaling between nodes is not required as a result of an operation based on an AI / ML model in the present disclosure, Step 3 may be omitted. If a one-side model is used in the present disclosure, unidirectional / bidirectional signaling (set) in the present disclosure may correspond to the signaling of Step 3. Furthermore, if a two-side model is used in the present disclosure, unidirectional / bidirectional signaling in the present disclosure may correspond to the signaling of Step 3, and repetitive signaling operations may also correspond to the signaling of Step 3.

[0244] For example, in an AI / ML model-based BM, the base station may transmit beam(s) predicted based on the AI / ML model as candidates to the terminal so that the terminal can determine the optimal beam. Additionally, the terminal may report the beam(s) predicted based on the AI / ML model to the base station to request the base station to transmit candidate beams as candidates for determining the optimal beam.

[0245] Processing unit management method for AI / ML-based CSI / beam measurement / reporting

[0246] Due to advancements in computational processing technology and AI / ML technologies, the nodes and UEs constituting wireless communication networks are becoming more intelligent and sophisticated. In particular, this network intelligence is expected to enable the rapid optimization, derivation, and application of various network decision parameter values ​​(e.g., transmit / receive power of each base station, transmit power of each UE, precoders / beams of base stations and UEs, time / frequency resource allocation for each UE, duplex mode of each base station, etc.) based on diverse network environment parameters (e.g., distribution / location of base stations, distribution / location / material of buildings / furniture, location / movement direction / speed of terminals, weather information, etc.).

[0247] The present disclosure proposes a method for managing / determining a processing unit (PU) for AI / ML-based CSI / BEAM reporting when it is performed in an evolved network / base station / terminal.

[0248] In this disclosure, ' / ' means 'and', 'or', or 'and / or' depending on the context. In this disclosure, 'beam' may mean a source reference signal (source RS) for a 'spatial filter' or a 'spatial relation', and may also be interpreted as a QCL (type-D) RS, a (DL / UL / joint) TCI state, or a spatial relation RS (in the case of an uplink).

[0249] The beam management (BM) method of an NR system is composed of beam measurement / reporting methods and base station beam indication methods. Beam measurement / reporting is performed periodically, non-periodically, or semi-persistently (SP) based on the base station's configuration / instruction. Under these base station configurations / instructions, the UE performs beam measurement / reporting, and based on the beam report information provided by the UE, the base station can perform beam activation and / or beam indication to the UE. In environments where UE movement is significant (e.g., UE rotation, fast-moving UE, etc.) or where the presence or location of scatterers, reflectors, and blockers on the beam / radio channel changes rapidly due to severe movement of objects surrounding the UE (e.g., indoor hotspots), beam measurement / reporting must be performed frequently to find the optimal beam. Consequently, problems such as RS overhead, implementation burdens associated with UE measurement / reporting, and increased power consumption arise.

[0250] Recently, AI / ML (artificial intelligence / machine learning)-based beam management methods are being discussed at 3GPP to address these issues. Two main use cases for enhanced beam management utilizing AI / ML are considered: 'improving beam management performance through spatial beam prediction' and 'improving beam management performance through temporal beam prediction.' 'Improving beam management performance through spatial beam prediction' aims to achieve improved beam management precision with lower beam RS overhead by having UE AI / ML and / or Network (NW) AI / ML utilize current / past beam RS measurement results, UE location / movement information, etc. For example, AI / ML can be utilized to achieve performance comparable to beam selection from a large number of beam RS based on results measured from a small number of beam RS. 'Improving beam management performance through temporal beam prediction' enables UE AI / ML and / or NW AI / ML to predict the quality of beam(s) at future time points based on current / past beam RS measurement results, UE location / movement information, and the time-varying characteristics of the channel. In the 3GPP Rel-18 / 19 AI / ML item, BM-Case 1 corresponds to the case where only spatial beam prediction is performed, while BM-Case 2 is currently being standardized to include both cases where spatial beam prediction is performed along with temporal beam prediction, as well as cases where only temporal beam prediction is performed. To facilitate this discussion, several sets of beam RSs have been defined; Set A refers to the beam RS set where the UE or NW performs prediction, and Set B refers to the beam RS set used as input to the AI / ML model to perform prediction in Set A. Additionally, Set C refers to the beam RS set measured by the terminal, and Set B may be identical to or a subset of Set C. For example, the following relationship may hold.

[0251] (example)

[0252] - Set A includes 128 beams: beam RS#0, RS#1, 쪋 , RS#127

[0253] The base station may transmit Set A beams to the UE at relatively long intervals or on-demand, utilizing them for purposes such as monitoring the performance of NW AI / ML or UE AI / ML.

[0254] - Set C contains 32 beams: beams RS#0, RS#4, RS#8, … , RS#124 (includes one of each of the 4 beams from Set A)

[0255] The base station transmits Set C to the UE periodically or non-periodically to enable the UE to perform measurements and related beam reporting. Here, the UE can select and report from the beams of Set A through spatial beam prediction via beam reporting.

[0256] - Set B can include a subset of Set C.

[0257] Set B is the beam set used for actual AI / ML input. Depending on the model implementation, all beams in Set C may be used as input, or only a subset may be used (for example, only the best N beams may be used, only beams with a beam quality above a certain threshold may be used, or other cases are possible).

[0258] At 3GPP, standardization discussions are underway regarding not only the aforementioned AI / ML-based beam measurement / reporting methods but also two-sided model-based CSI compression methods, one-sided model-based CSI prediction methods, and one-sided model-based positioning methods. CSI compression refers to a method in which CSI calculated by the UE is encoded and transmitted by a UE-part AI / ML model, and then decoded by a NW-part AI / ML model. For CSI prediction methods, use cases are primarily being considered where a UE-sided AI / ML model predicts CSI at future time points and reports it to the NW. AI / ML-based positioning methods assume that AI / ML can be implemented in various locations, such as the UE, UE-side servers, base stations / NWs, and location management functions (LMFs). In addition, the input to the AI / ML model mainly uses phase difference / time difference / quality values ​​of signals received from multiple TRPs, and phase difference / time difference / quality values ​​of signals received from multiple TRPs, etc., and considers both i) a direct AI / ML positioning method that directly determines the position of the UE as an output, and ii) an AI / ML assisted positioning method in which the output of the AI / ML model is not a direct result of positioning but consists of values / information that help improve the accuracy of positioning (e.g., angle of departure / arrival indication, line of sight (LoS) / non-line of sight (NloS) indication, etc.).

[0259] In the following description of the present disclosure, 'channel state information (CSI)' may include calculations / reports of quality values ​​for a beam (e.g., L1-RSRP / SINR, etc.).

[0260] In addition to the AI / ML use cases currently being considered by 3GPP mentioned above, it is expected that a wider variety of AI / ML-based use cases will be introduced in future 5G enhancements or 6G (e.g., reduction of RS overhead, hardware impairment compensation, etc.). In such environments, particularly when a UE needs to perform various AI / ML-related operations (e.g., inference, training, monitoring, etc.), it may be difficult to perform multiple AI / ML-related operations simultaneously due to limitations in the UE's AI / ML processing capacity. This may be implemented based on separate / distinct hardware (e.g., GPU (Graphical Processing Unit)) because AI / ML operations require fast computation on large amounts of data, and such hardware may be common hardware for multiple AI / ML models / operations. With this motivation, a proposal is being discussed at 3GPP to manage the computational burden on UEs by defining AI / ML processing units (APUs) for AI / ML.

[0261] In this regard, 3GPP NR has standardized the CSI processing unit (CPU) as follows.

[0262] The UE supports concurrent CSI calculations N CPUThe number is indicated using the simultaneousCSI-ReportsPerCC parameter on the component carrier and the simultaneousCSI-ReportsAllCC parameter across all component carriers. The UE is N CPU If simultaneous CSI calculations are supported, N for CSI report processing CPU It means having CSI processing units (CPUs). If L CPUs are occupied for the calculation of CSI reports in a given OFDM symbol, the UE has N CPU - Has L unoccupied CPUs. N CSI reports are N CPU - If L CPUs start occupying their respective CPUs on the same unoccupied OFDM symbol (where each CSI report n=0,...,N-1 is O (n) CPU (corresponds to), the UE is not required to update the NM requested CSI reports with the lowest priority. Here, M is 0 ≤ M ≤ N, where ∑ n=0 M-1 O (n) CPU ≤ N CPU It is the maximum value that satisfies -L.

[0263] UE is N CPU It is not expected that non-periodic CSI trigger states exceeding the report setting will be set. Processing CSI reports occupies CPU resources for the symbols as follows:

[0264] - For a CSI report having a CSI-ReportConfig with a higher-level parameter reportQuantity set to 'none' and a CSI-RS-ResourceSet with a higher-level parameter trs-Info set, O CPU =0,

[0265] - For a CSI report having a CSI-ReportConfig with a parent parameter reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-SINR', 'ssb-Index-SINR', 'cri-RSRP-Capability[Set]Index', 'ssb-Index-RSRP-Capability[Set]Index', 'cri-SINR-Capability[Set]Index', 'ssb-Index-SINR-Capability[Set]Index', or 'none' (and a CSI-RS-ResourceSet with the parent parameter trs-Info not set), O CPU =1,

[0266] - For a CSI report having a CSI-ReportConfig with a higher-level parameter reportQuantity set to 'cri-RI-PMI-CQI', 'cri-RI-i1', 'cri-RI-i1-CQI', 'cri-RI-CQI', or 'cri-RI-LI-PMI-CQI',

[0267] If max{μPDCCH, μCSI-RS, μUL} ≤ 3 and L=0 CPU is occupied, and a CSI report is triggered acyclically without a PUSCH transmission containing a transmission block or HARQ-ACK or both, where CSI corresponds to a single CSI with broadband frequency-granularity and up to 4 CSI-RS ports within a single resource without CSI reporting, codebookType is set to 'typeI-SinglePanel' or reportQuantity is set to 'cri-RI-CQI', and O CPU =N CPU ,

[0268] If CSI-ReportConfig is set to a codebookType of 'typeI-SinglePanel' and the corresponding CSI-RS resource set for channel measurements is configured with two resource groups and N resource pairs, then O CPU =2N+M,

[0269] Otherwise, O CPU =K s , here, K s is the number of CSI-RS resources in the CSI-RS resource set for channel measurement.

[0270] For a CSI report with a CSI-ReportConfig having a higher-level parameter reportQuantity that is not set to 'none', the CPU(s) for the OFDM symbols are occupied as follows:

[0271] - Periodic or semi-persistent CSI reports (excluding initial semi-persistent CSI reports occurring in PUSCH after PDCCH triggers a report) occupy CPU(s) from the first symbol of the earliest symbol of each CSI-RS / CSI-IM / SSB resource for channel or interference measurement, until each most recent CSI-RS / CSI-IM / SSB occasion is no later than the corresponding CSI reference resource, up to the last symbol of PUSCH / PUCCH carrying the report.

[0272] - Aperiodic CSI reports occupy CPU(s) from the first symbol following the PDCCH that triggered the CSI report until the last symbol of the scheduled PUSCH carrying the report. When a PDCCH reception contains two PDCCH candidates from two sets of search spaces, the PDCCH candidate that ends later in time is used to determine the CPU occupancy duration.

[0273] - The initial semi-persistent CSI report on PUSCH following the PDCCH trigger occupies CPU(s) from the first symbol after the PDCCH until the last symbol of the scheduled PUSCH carrying the report. When the PDCCH reception contains two PDCCH candidates from two sets of search spaces, the PDCCH candidate that ends later in time is used to determine the CPU occupancy duration.

[0274] For a CSI report with a CSI-ReportConfig having a higher-level parameter reportQuantity set to 'none' and a CSI-RS-ResourceSet with a higher-level parameter trs-Info not set, CPU(s) for OFDM symbols are occupied as follows:

[0275] - Semi-continuous CSI reporting (excluding the first semi-continuous CSI reporting on PUSCH after the PDCCH that triggers the reporting) occupies CPU(s) from the first symbol of the earliest of each transmission occasion of the periodic or semi-continuous CSI-RS / SSB resource for channel measurement for L1-RSRP calculation, up to Z3' symbols after the last symbol of the most recent CSI-RS / SSB resource for channel measurement for L1-RSRP calculation in each transmission occasion.

[0276] - Aperiodic CSI reporting occupies CPU(s) from the first symbol after the PDCCH that triggers the CSI report to the last symbol between the Z3 symbol and the last symbol of the most recent of each CSI-RS / SSB resource for channel measurement for L1-RSRP calculation.

[0277] Here, Z3 and Z3' are defined in the standard.

[0278] In any slot, a UE is not expected to have more active CSI-RS ports or active CSI-RS resources in an active BWP than its reported capability. NZP CSI-RS resources are active for a duration defined as follows: For non-periodic CSI-RS, it starts at the end of the PDCCH containing the request and ends at the end of the scheduled PUSCH containing the report associated with that non-periodic CSI-RS. If a PDCCH candidate is associated with a set of search spaces configured with searchSpaceLinking, the PDCCH candidate that ends later in time among the two linked PDCCH candidates is used to determine the NZP CSI-RS resource active duration. For semi-persistent CSI-RS, it is from the time the enable command is applied until the time the disable command is applied. For periodic CSI-RS, it is from the time the periodic CSI-RS is established via upper-level signaling until the time the periodic CSI-RS configuration is released. If a CSI-RS resource is referenced N times by one or more CSI reporting settings, the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted N times. For a set of CSI-RS resources for channel measurements configured with two resource groups and N resource pairs, if a CSI-RS resource is referenced X times by one of M CSI-RS resources and / or by one or two resource pairs, the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted X times.

[0279] As mentioned above, according to the standards regarding CPU management, the number of CSIs (N) that can be simultaneously computed / processed per UE CPU) may differ (e.g., based on parallel processing capability). Accordingly, it is possible to ensure that the triggered CSI does not exceed that limit (e.g., UE is N CPU It is not expected that non-periodic CSI trigger states exceeding the report setting will be set.) Alternatively, when a number of CSI operations / reports exceeding the limit is required, the UE may perform processing relaxation to report previously reported CSIs without performing operations on lower-priority CSIs (e.g., N CSI reports N CPU - If L CPUs start occupying their respective CPUs on the same unoccupied OFDM symbol (where each CSI report n=0,...,N-1 is O (n) CPU (corresponds to), the UE is not required to update the NM requested CSI reports with the lowest priority. Here, M is 0 ≤ M ≤ N, where ∑ n=0 M-1 O (n) CPU ≤ N CPU It is the maximum value that satisfies -L.).

[0280] In the following description of the present disclosure, an APU (AI / ML processing unit) may refer to a processing unit for AI / ML-related operations. For convenience of explanation, the term APU is primarily used in the description of the present disclosure, but this is merely an example and the present disclosure is not limited thereto. For example, AI / ML-related operations may include prediction-based CSI / BEAM reporting, and the APU may be referred to as a CPU for prediction-based CSI / BEAM reporting (i.e., a CPU specific to prediction-based CSI / BEAM reporting). In this case, the CPU for conventional CSI / BEAM reporting (i.e., CSI / BEAM reporting without prediction) may be referred to as a first CPU (i.e., a CPU not specific to prediction-based CSI / BEAM reporting), and the CPU for prediction-based CSI / BEAM reporting may be referred to as a second CPU (i.e., a CPU specific to prediction-based CSI / BEAM reporting).

[0281] That is, in the description of the present disclosure, AI / ML-based CSI / beam reporting may mean CSI / beam reporting involving (or involving) prediction in the time and / or space and / or frequency domain, and non-AI / ML-based CSI / beam reporting may mean CSI / beam reporting without (or not involving) prediction.

[0282] In APU management as well, a method similar to the aforementioned CPU management approach can be considered. Here, the APU may have the following differences from existing CPUs.

[0283] Method 1. The APU value occupied may vary depending on the AI / ML model, functionality, or (sub-)use case.

[0284] The amount of computation required can vary significantly depending on the implementation of the AI / ML model (e.g., input / output data size, algorithm type / structure, number of (hidden) layers and parameters, etc.).

[0285] Method 1-A: The UE may report to the base station the maximum APU occupancy it can handle, as well as the (minimum) APU occupancy required for each AI / ML model / function / (sub-)use example. For example, the UE may report to the base station the maximum APU occupancy with its capability and the (minimum) APU occupancy required for each AI / ML model / function / (sub-)use example.

[0286] The above APU occupancy values ​​may consist of natural numbers (i.e., integers greater than 0) like the CPU described above, or may allow values ​​up to the decimal point.

[0287] The (minimum) APU occupancy value required for each of the above AI / ML models / functions / (sub-)use examples can be defined as a single value, and it may be a value that the base station assumes the UE is using that amount of APU when the said model / function / (sub-)use example is operating.

[0288] Alternatively, for each of the above AI / ML models / functions / (sub-)use examples, the (minimum) APU occupancy value may consist of multiple candidate values ​​or a range of values. In such cases, the number / value of APUs assumed to be used by the UE when the said AI / ML model / function / (sub-)use example is in operation may be determined by specific rules (e.g., defined in a standard or set by a base station) and / or additional reports from the UE (e.g., reports on the actual APU occupancy value among the multiple candidate values / ranges).

[0289] Examples of the above rules are as follows. The rules exemplified below may be used alone, two exemplified rules may be used together (combined), and at least one of two exemplified rules may be used together (combined) with another rule that is not exemplified.

[0290] Example 1) It can be determined based on the APU occupancy situation.

[0291] For a specific AI / ML model / feature / (sub-)use example, among multiple (minimum) APU occupancy candidate values ​​or ranges of values, the largest value, which is smaller than the APU currently unoccupied for the UE, may be applied.

[0292] Example 2) It can be determined by the attributes of the related AI / ML operation (e.g., priority, urgency).

[0293] For example, when an AI / ML operation requiring high priority and / or fast processing is triggered, the APU occupancy for other occupied (low priority) AI / ML operations may be adjusted to the lower of a plurality of (minimum) APU occupancy candidate values ​​or a range of values. And / or, for the high priority AI / ML operation, the largest value among the plurality of (minimum) APU occupancy candidate values ​​or a range of values ​​(though smaller than the unoccupied APU) may be applied, or the entire APU may be occupied for the high priority AI / ML operation.

[0294] Method 1-B: The base station can set the APU occupancy value to be applied to each AI / ML model / function / (sub-)use example for the UE.

[0295] The configuration according to Method B may be performed based on Method A described above. In this case, the base station is not expected to set a value smaller than the (minimum) APU occupancy value required for each corresponding AI / ML model / function / (sub-)use example reported by the UE. For example, the UE may not expect the base station to set 2 APUs, even though the UE has reported that 2.4 APUs are required for a specific AI / ML function.

[0296] And / or, the base station may set / instruct which value to apply for each AI / ML model / function / (sub)use case, either within the range of APU occupancy values ​​supported by the UE or from among candidate values. Here, the total sum of APUs set / instructed for all activated / triggered AI / ML models / functions / (sub)use cases may not exceed the UE's maximum APU occupancy value. For example, the UE may not expect the sum of the APU values ​​instructed / set by the base station to exceed the limit of the maximum APU occupancy value.

[0297] Method 1-C: The APU occupancy value to be applied for each AI / ML model / function / (sub-)use example can be predefined (e.g., specified in the standard).

[0298] In this case, the UE may need to implement AI / ML algorithms in accordance with the corresponding APU occupancy value (at or below that value).

[0299] Method 2. The APU can be applied to other UE-side / part AI / ML related operations other than CSI / beam reporting.

[0300] Regardless of the application, since AI / ML-related operations can be performed based on common hardware (e.g., GPU), the APU needs to be managed in this case as well.

[0301] Assuming that APU management is introduced as described above, since the hardware managed / responsible for the APU and CPU may be different, CPU occupancy management rules can be executed together / simultaneously / independently along with APU occupancy management rules.

[0302] Accordingly, the following method is proposed when the APU exceeds the limit for the corresponding UE.

[0303] Method 1: The UE may not expect the base station to set / trigger AI / ML operations that exceed the APU limit (e.g., reported as capability by the UE). For example, based on the (minimum) APU occupancy value required for each AI / ML operation (e.g., AI / ML model / function / (sub-)use example) according to the method described above, the sum of the APU occupancy values ​​for all AI / ML operations set for the UE may not exceed the UE's APU limit.

[0304] Method 2: When an AI / ML operation exceeding the APU limit (e.g., reported by the UE as a capability) is triggered / set, the execution of certain AI / ML operation(s) (corresponding to lower priority according to a defined priority) may not be required.

[0305] For AI / ML operation(s) for which the execution of the above AI / ML is not required, if the relevant AI / ML operation is an operation related to reporting (through AI / ML computation) of the UE (e.g., CSI / BEAM reporting, performance monitoring result reporting (e.g., for active / inactive model(s)), positioning-related result reporting (e.g., intermediate KPI (Key Performance Indicator), predicted position), etc.), the UE may operate as follows.

[0306] Method 2-1: The UE is not required to update the report content or the results of the AI / ML model.

[0307] Method 2-2: The UE can report non-AI / ML based result(s) (e.g., results based on a predefined fallback action, non-AI / ML based prediction results).

[0308] Method 2-3: The UE can report predefined / set value(s) / content(s) (e.g., all 0, other information / content set by the network).

[0309] The method 1 and method 2 described above may be determined based on the type of AI / ML operation, base station configuration, etc. Additionally, the method 1 and method 2 described above may be applied together for specific AL / ML operation(s).

[0310] Additionally, the above-described method 1 and / or method 2 may be applied only to some / defined / configured AI / ML operations (e.g., some (sub-)use examples, functions).

[0311] In addition, which of the above-described methods 2-1 / 2-2 / 2-3 is applied may also vary depending on the type of AI / ML operation, base station settings, etc.

[0312] Here, with respect to Method 2-2 (and / or Method 2-3), if the AI / ML operation is an operation related to CSI measurement / reporting, the method may be applied only when the number of CPUs required for the non-AI / ML-based method is equal to or less than the number of unoccupied CPUs (i.e., when there are as many unoccupied CPUs as there are CPUs required for the non-AI / ML-based method). Otherwise (e.g., when all CPUs are occupied, or when there are not as many unoccupied CPUs as there are CPUs required for the non-AI / ML-based method), Method 2-1 (or Method 2-3) may be applied. This is because it is necessary to occupy CPUs to calculate non-AI / ML-based CSI.

[0313] (example)

[0314] APU overload situation + low-priority APU-related actions are predicted CSI / beam reports

[0315] Option 1) The UE can report a non-AI / ML based predicted CSI / beam instead of an AI / ML based predicted CSI / beam.

[0316] Here, non-AI / ML-based prediction may be based on statistical / mathematical prediction algorithms / models.

[0317] For example, in the case of CSI, it may be a time / Doppler domain predicted CSI report introduced in Rel-18 MIMO.

[0318] Option 2) The UE can report non-predicted CSI / beams instead of AI / ML-based predicted CSI / beams.

[0319] Here, non-predicted CSI / beam may be a CSI / beam report calculated without performing time / space / frequency domain predictions.

[0320] For example, in the case of a report where BM-Case1 (i.e., performing only spatial beam prediction) / Case2 (performing both temporal and spatial beam prediction), the non-predicted CSI / beam may be an action of selecting and reporting the best beam RS from Set B (i.e., the beam RS set used as input to the AI / ML model to perform prediction in Set A) instead of Set A (i.e., the beam RS set where the UE or network performs prediction).

[0321] In addition, for example, in the case of a report where BM-Case2 is set, the non-predicted CSI / beam may be an action of selecting the beam RS for the current time point rather than a future time point to report.

[0322] Additionally, for example, in the case of a report with CSI prediction enabled, a non-predicted CSI / beam may be an action that calculates / reports the CSI for the current point in time rather than a future point in time.

[0323] The above-described Option 1 and / or Option 2 may be performed only if there is enough unoccupied CPU remaining to perform the CSI / beam reporting.

[0324] In addition, regarding the above-mentioned Option 1 and / or Option 2, which information to calculate / report in the above cases may be set by the base station or predefined (e.g., specified in the standard).

[0325] In the method described above, a scenario was considered where non-AI / ML CSIs are calculated and reported using spare (unoccupied) CPUs when APUs are insufficient. Conversely, a scenario where AI / ML CSIs are calculated and reported using spare (unoccupied) APUs when CPUs are insufficient can also be considered. For example, in a situation where a non-predicted beam report is configured / triggered, and the report is a low-priority report that cannot occupy a CPU due to CPU occupancy rules, it may be configured / defined to transmit AI / ML-based predicted / non-predicted beam reports instead of the CPU. Here, the information for the AI / ML-based predicted / non-predicted beam reports may be configured to follow settings as similar / identical as possible to those of the non-AI / ML reports (for example, in the case of AI / ML-based time-domain prediction, the predicted result may be reported for a time point as close as possible to the CSI reference resource time point, or the predicted result may be reported for the CSI reference resource time point).

[0326] In applying the methods of exchanging / replacing the APU and CPU described above, the number / value of APUs and CPUs occupied for the same function / (sub)use example may be the same or different. For example, the number / value of APUs occupied may be determined according to the (minimum) APU occupancy value required for each function / (sub)use example reported by the UE, as proposed in Method 1-A. Furthermore, if both the APU and CPU are insufficient for CSI calculation / reporting, un-updated CSIs are transmitted (e.g., the UE is not required to update CSIs), whereas if either one is not insufficient, the CSIs may be calculated / reported using the processing unit that is not insufficient.

[0327] Additionally, AI / ML-based CSI / BEAM reporting can be configured / defined to occupy both the CPU and the APU. In other words, both the CPU and the APU can be occupied for AI / ML-based CSI / BEAM reporting (e.g., CSI / BEAM reporting related to or involving prediction).

[0328] This is because operations such as CSI / Beam RS measurement, CSI / Beam reporting, and / or AI / ML-related pre / post-processing—which are necessary process(s) in addition to AI / ML processing (e.g., the process of deriving output data from input data)—may still require hardware operations related to the CPU. In this case, since CSI processing is not fully required, the unoccupied CPU may be assigned a value equal to or smaller than that for non-AI / ML CSI (e.g., scaled by delta (<1), where delta can be a predefined or set value; as another example, a value minus gamma can be applied to the non-AIML CPU, where gamma can be a predefined or set value). And / or, the CPU occupancy duration may be defined / set to occupy less time compared to non-AIML CSI. For example, it may be defined as RS reception time + alpha value and / or CSI reporting time - beta value, and the alpha / beta values ​​may be defined / configured to apply smaller values ​​than in the case of non-AIML CSI. Alternatively, when both the CPU and APU are occupied for AI / ML-based CSI / beam reporting (e.g., CSI / beam reporting related to or involving prediction), the duration of CPU occupancy (e.g., number of OFDM symbols) and the duration of APU occupancy (e.g., number of OFDM symbols) may be the same. Alternatively, the duration of CPU occupancy and the duration of APU occupancy may be different; in this case, for example, the alpha / beta values ​​as in the previous example may be defined / configured, and the APU may be occupied during the time interval when the CPU is not occupied (e.g., from RS reception time + alpha value to CSI reporting time - beta value).

[0329] FIG. 15 is a diagram illustrating a signaling procedure between a base station and a UE for a prediction-based CSI reporting method according to one embodiment of the present disclosure.

[0330] FIG. 15 illustrates a signaling procedure between a UE and a base station based on the proposed methods described above. The example in FIG. 15 is for convenience of explanation and does not limit the scope of the present disclosure. Some step(s) illustrated in FIG. 15 may be omitted depending on the situation and / or configuration. Also, the base station and the UE in FIG. 15 are merely examples and may be implemented as the device illustrated in FIG. 18 below. For example, the processor (102 / 202) in FIG. 18 may control the transmission and reception of channels / signals / data / information, etc. using a transceiver (106 / 206), and may also control the storage of channels / signals / data / information, etc. to be transmitted or received in a memory (104 / 204).

[0331] Referring to FIG. 15, the base station can receive UE capability information from the UE (S1501).

[0332] UE capability information may include information related to UE AI / ML models (training / inference) and / or functionality, beam predictability, etc.

[0333] Additionally, the above UE capability information may include information on the maximum number of first CPUs not specific to the prediction-based CSI reporting supported by the UE, and information on the maximum number of second CPUs specific to the prediction-based CSI reporting supported by the UE.

[0334] In addition, the UE capability information may further include information regarding the (minimum) number of occupancy of the second CPU required for each AI / ML model, function, or use-case with respect to the second CPU.

[0335] Here, the UE capability information may indicate multiple values ​​or a range of values ​​regarding the number of occupancy units of the second CPU required for each AI / ML model, function, or use-case for the second CPU. In this case, the number of occupancy units of the second CPU for the AI / ML model, function, or use-case used by the UE may be determined within the multiple values ​​or the range of values ​​based on a specific rule, a report by the UE, or a setting by the base station.

[0336] The base station transmits configuration information to the UE (S1502).

[0337] Here, the configuration information may be configuration information related to CSI / BEAM reporting. Additionally, the configuration information may include reporting configuration information related to AI / ML (e.g., predicted) CSI / BEAM reporting, positioning, etc. Additionally, it may include information related to AI / ML performance monitoring, information related to additional network-side conditions (e.g., association ID), etc.

[0338] For example, configuration information may refer to configuration information for one or more parameter(s) related to the base station's Tx beam (or beam RS or RS) and / or the UE's Rx beam (or beam RS or RS). For example, it may be configuration information related to beam (or CSI) reporting (e.g., configuration information related to CSI reporting (including L1-RSRP and / or L1-SINR) (e.g., CSI-ReportConfig)), configuration information related to resources for beam (or CSI) reporting (e.g., CSI-ResourceConfig)), or configuration information related to beam configuration for a specific channel / signal, BWP, serving cell, etc. (e.g., configuration information including (DL / UL or unified) TCI state(s).

[0339] Here, the beam (or beam RS or RS) may refer to a beamformed RS (e.g., SSB, CSI-RS, etc.). Additionally, the beam (or beam RS or RS) may have different directionality depending on the transmitted resource, and the different resource(s) to which the beamformed RS is transmitted may refer to different beams (or beam RS or RS).

[0340] Although not shown in Fig. 15, the base station can transmit control information to the UE.

[0341] Here, control information may refer to information for activating and / or directing a beam (or beam RS or RS) (i.e., QCL type-D RS (or TCI state)). Alternatively, it may refer to control information for activating / triggering a beam report (e.g., L1-RSRP / SINR) to assist in the selection of the base station's Tx beam (or beam RS or RS) and / or the UE's Rx beam (or beam RS or RS). Such control information may be transmitted via MAC CE, may be transmitted via DCI, or may be transmitted via both MAC CE and DCI.

[0342] The base station transmits a downlink reference signal (i.e., a beam) (e.g., SSB, CSI-RS, etc.) to the UE (S1503).

[0343] As described above, the beam (or beam RS or RS) may refer to a beamformed reference signal (e.g., SSB, CSI-RS, etc.). Additionally, the beam (or beam RS or RS) may have different directions depending on the transmitted resource, and the different resource(s) to which the beamformed RS is transmitted may refer to different beams (or beam RS or RS).

[0344] That is, the base station can transmit downlink RS to the UE through different beams on one or more downlink RS resources.

[0345] Here, some of the measurements for downlink RS can be used / applied as some of the input parameters of a terminal AI / ML model.

[0346] The UE transmits a CSI report (e.g., beam report) to the base station (S1504).

[0347] For example, in the case of a beam report, the UE may transmit a CSI report (e.g., a beam report) based on a measurement of the downlink reference signal to the base station. Here, (in the case of a beam report) the report value may be i) a pair of the identifier of the reference signal resource (e.g., CRI, SSBRI) and L1-RSRP or ii) a pair of the identifier of the reference signal resource and L1-SNIR.

[0348] In addition, the terminal that has performed the above configuration information and measurements for the downlink RS can perform AI / ML processing based on the said configuration and measurements. That is, based on the fact that a prediction-based CSI report (e.g., predicted CRI, predicted SSBRI, predicted L1-RSRP, etc.) is set by the above configuration information, the UE can transmit the prediction-based CSI report for the downlink RS to the base station. For example, (in the case of a beam report) the report value may be i) a pair of the identifier of the reference signal resource (e.g., CRI, SSBRI) and the predicted L1-RSRP, or ii) a pair of the identifier of the reference signal resource and the predicted L1-SNIR.

[0349] In this process, management of the first CPU and the second CPU (i.e., APU) can be performed based on the proposed methods of the present disclosure.

[0350] Here, regarding the prediction-based CSI report, both a first CPU not specific to the prediction-based CSI report (e.g., an existing CPU or a CPU for non-predicted CSI) and a second CPU specific to the prediction-based CSI report (e.g., an APU) may be occupied. In this case, the first CPU and the second CPU may be occupied for the same time interval. Additionally, the number of times the second CPU is occupied may be equal to or smaller than the number of times the first CPU is occupied.

[0351] In addition, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, it may not be required to update the content of the prediction-based CSI report.

[0352] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPU, a non-predicted-based CSI report may be transmitted instead of the prediction-based CSI report.

[0353] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, specific information that is predefined or pre-set may be transmitted instead of the prediction-based CSI report.

[0354] FIG. 16 is a diagram illustrating the operation of a UE for reporting predicted channel status information according to one embodiment of the present disclosure.

[0355] FIG. 16 illustrates the operation of a UE based on the proposed methods described above. The example in FIG. 16 is for convenience of explanation and does not limit the scope of the present disclosure. Some step(s) illustrated in FIG. 16 may be omitted depending on the situation and / or configuration. Also, the UE in FIG. 16 is merely an example and may be implemented as the device illustrated in FIG. 18 below. For example, the processor (102 / 202) of FIG. 18 may control the transmission and reception of channels / signals / data / information, etc. using a transceiver (106 / 206), and may also control the transmission or reception of channels / signals / data / information, etc. to be stored in a memory (104 / 204).

[0356] Additionally, the operation of FIG. 16 may be processed by one or more processors (102, 202) of FIG. 18. Additionally, the operation of FIG. 16 may be stored in memory (e.g., one or more memories (104, 204) of FIG. 18) in the form of an instruction / program (e.g., instruction, executable code) for driving at least one processor (e.g., 102, 202) of FIG. 18.

[0357] Although not illustrated in Fig. 16, the UE can transmit UE capability information to the base station.

[0358] UE capability information may include information related to UE AI / ML models (training / inference) and / or functionality, beam predictability, etc.

[0359] Additionally, the above UE capability information may include information on the maximum number of first CPUs not specific to the prediction-based CSI reporting supported by the UE, and information on the maximum number of second CPUs specific to the prediction-based CSI reporting supported by the UE.

[0360] In addition, the UE capability information may further include information regarding the (minimum) number of occupancy of the second CPU required for each AI / ML model, function, or use-case with respect to the second CPU.

[0361] Here, the UE capability information may indicate multiple values ​​or a range of values ​​regarding the number of occupancy units of the second CPU required for each AI / ML model, function, or use-case for the second CPU. In this case, the number of occupancy units of the second CPU for the AI / ML model, function, or use-case used by the UE may be determined within the multiple values ​​or the range of values ​​based on a specific rule, a report by the UE, or a setting by the base station.

[0362] Referring to FIG. 16, the UE receives configuration information related to CSI reporting from the base station (S1601).

[0363] Here, CSI reporting may include beam reporting (e.g., L1-RSRP and / or L1-SINR), and configuration information related to CSI reporting (e.g., CSI-ReportConfig) may include reporting configuration information related to AI / ML (e.g., predicted) CSI / beam reporting, positioning, etc.

[0364] The UE receives a downlink reference signal (i.e., a beam) (e.g., SSB, CSI-RS, etc.) from the base station (S1602).

[0365] As described above, the beam (or beam RS or RS) may refer to a beamformed reference signal (e.g., SSB, CSI-RS, etc.). Additionally, the beam (or beam RS or RS) may have different directions depending on the transmitted resource, and the different resource(s) to which the beamformed RS is transmitted may refer to different beams (or beam RS or RS).

[0366] That is, the base station can transmit downlink RS to the UE through different beams on one or more downlink RS resources.

[0367] Here, some of the measurements for downlink RS can be used / applied as some of the input parameters of a terminal AI / ML model.

[0368] Based on the prediction-based CSI report being set by the configuration information, the UE transmits the prediction-based CSI report for the downlink RS to the base station (S1603).

[0369] That is, based on the fact that a prediction-based CSI report (e.g., predicted CRI, predicted SSBRI, predicted L1-RSRP, etc.) is set by the above-mentioned setting information, the UE may transmit the prediction-based CSI report for the downlink RS to the base station. For example, (in the case of a beam report) the report value may be i) a pair of the identifier of the reference signal resource (e.g., CRI, SSBRI) and the predicted L1-RSRP or ii) a pair of the identifier of the reference signal resource and the predicted L1-SNIR.

[0370] In this process, management of the first CPU and the second CPU (i.e., APU) can be performed based on the proposed methods of the present disclosure.

[0371] Here, regarding the prediction-based CSI report, both a first CPU not specific to the prediction-based CSI report (e.g., an existing CPU or a CPU for non-predicted CSI) and a second CPU specific to the prediction-based CSI report (e.g., an APU) may be occupied. In this case, the first CPU and the second CPU may be occupied for the same time interval. Additionally, the number of times the second CPU is occupied may be equal to or smaller than the number of times the first CPU is occupied.

[0372] In addition, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, it may not be required to update the content of the prediction-based CSI report.

[0373] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPU, a non-predicted-based CSI report may be transmitted instead of the prediction-based CSI report.

[0374] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, specific information that is predefined or pre-set may be transmitted instead of the prediction-based CSI report.

[0375] FIG. 17 is a diagram illustrating the operation of a base station for reporting channel status information according to one embodiment of the present disclosure.

[0376] FIG. 17 illustrates the operation of a base station based on the proposed methods described above. The example in FIG. 17 is for convenience of explanation and does not limit the scope of the present disclosure. Some step(s) illustrated in FIG. 17 may be omitted depending on the situation and / or configuration. Also, the base station in FIG. 17 is merely an example and may be implemented as the device illustrated in FIG. 18 below. For example, the processor (102 / 202) in FIG. 18 may control the transmission and reception of channels / signals / data / information, etc. using a transceiver (106 / 206), and may also control the storage of channels / signals / data / information, etc. to be transmitted or received in a memory (104 / 204).

[0377] Additionally, the operation of FIG. 17 may be processed by one or more processors (102, 202) of FIG. 18. Additionally, the operation of FIG. 17 may be stored in memory (e.g., one or more memories (104, 204) of FIG. 18) in the form of an instruction / program (e.g., instruction, executable code) for driving at least one processor (e.g., 102, 202) of FIG. 18.

[0378] Although not shown in Fig. 17, the base station can receive UE capability information from the UE.

[0379] UE capability information may include information related to UE AI / ML models (training / inference) and / or functionality, beam predictability, etc.

[0380] Additionally, the above UE capability information may include information on the maximum number of first CPUs not specific to the prediction-based CSI reporting supported by the UE, and information on the maximum number of second CPUs specific to the prediction-based CSI reporting supported by the UE.

[0381] In addition, the UE capability information may further include information regarding the (minimum) number of occupancy of the second CPU required for each AI / ML model, function, or use-case with respect to the second CPU.

[0382] Here, the UE capability information may indicate multiple values ​​or a range of values ​​regarding the number of occupancy units of the second CPU required for each AI / ML model, function, or use-case for the second CPU. In this case, the number of occupancy units of the second CPU for the AI / ML model, function, or use-case used by the UE may be determined within the multiple values ​​or the range of values ​​based on a specific rule, a report by the UE, or a setting by the base station.

[0383] Referring to FIG. 17, the base station transmits configuration information related to CSI reporting to the UE (S1701).

[0384] Here, CSI reporting may include beam reporting (e.g., L1-RSRP and / or L1-SINR), and configuration information related to CSI reporting (e.g., CSI-ReportConfig) may include reporting configuration information related to AI / ML (e.g., predicted) CSI / beam reporting, positioning, etc.

[0385] The base station transmits a downlink reference signal (i.e., a beam) (e.g., SSB, CSI-RS, etc.) to the UE (S1702).

[0386] As described above, the beam (or beam RS or RS) may refer to a beamformed reference signal (e.g., SSB, CSI-RS, etc.). Additionally, the beam (or beam RS or RS) may have different directions depending on the transmitted resource, and the different resource(s) to which the beamformed RS is transmitted may refer to different beams (or beam RS or RS).

[0387] That is, the base station can transmit downlink RS to the UE through different beams on one or more downlink RS resources.

[0388] Here, some of the measurements for downlink RS can be used / applied as some of the input parameters of a terminal AI / ML model.

[0389] Based on the prediction-based CSI report being set by the configuration information, the base station receives a prediction-based CSI report for the downlink RS from the UE (S1703).

[0390] That is, based on the fact that a prediction-based CSI report (e.g., predicted CRI, predicted SSBRI, predicted L1-RSRP, etc.) is set by the above-mentioned setting information, the base station may receive the prediction-based CSI report for the downlink RS from the UE. For example, (in the case of a beam report) the report value may be i) a pair of the identifier of the reference signal resource (e.g., CRI, SSBRI) and the predicted L1-RSRP or ii) a pair of the identifier of the reference signal resource and the predicted L1-SNIR.

[0391] In this process, management of the first CPU and the second CPU (i.e., APU) can be performed based on the proposed methods of the present disclosure.

[0392] Here, regarding the prediction-based CSI report, both a first CPU not specific to the prediction-based CSI report (e.g., an existing CPU or a CPU for non-predicted CSI) and a second CPU specific to the prediction-based CSI report (e.g., an APU) may be occupied. In this case, the first CPU and the second CPU may be occupied for the same time interval. Additionally, the number of times the second CPU is occupied may be equal to or smaller than the number of times the first CPU is occupied.

[0393] In addition, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, it may not be required to update the content of the prediction-based CSI report.

[0394] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPU, a non-predicted-based CSI report may be transmitted instead of the prediction-based CSI report.

[0395] Additionally, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs, specific information that is predefined or pre-set may be transmitted instead of the prediction-based CSI report.

[0396] General devices to which the present disclosure may be applied

[0397] FIG. 18 illustrates a block diagram of a wireless communication device according to one embodiment of the present disclosure.

[0398] Referring to FIG. 18, the first wireless device (100) and the second wireless device (200) can transmit and receive wireless signals through various wireless access technologies (e.g., LTE, NR).

[0399] The first wireless device (100) includes one or more processors (102) and one or more memories (104), and may additionally include one or more transceivers (106) and / or one or more antennas (108). The processor (102) controls the memory (104) and / or transceivers (106) and may be configured to implement the descriptions, functions, procedures, proposals, methods and / or sequences of operation disclosed in this disclosure. For example, the processor (102) may process information within the memory (104) to generate a first information / signal and then transmit a wireless signal containing the first information / signal through the transceiver (106). Additionally, the processor (102) may receive a wireless signal containing a second information / signal through the transceiver (106) and then store information obtained from the signal processing of the second information / signal in the memory (104). The memory (104) may be connected to the processor (102) and may store various information related to the operation of the processor (102). For example, the memory (104) may store software code containing instructions for performing some or all of the processes controlled by the processor (102) or for performing the descriptions, functions, procedures, proposals, methods, and / or sequences of operation disclosed in this disclosure. Here, the processor (102) and the memory (104) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (106) may be connected to the processor (102) and may transmit and / or receive wireless signals through one or more antennas (108). The transceiver (106) may include a transmitter and / or receiver. The transceiver (106) may be combined with an RF (Radio Frequency) unit. In the present disclosure, a wireless device may refer to a communication modem / circuit / chip.

[0400] The second wireless device (200) includes one or more processors (202) and one or more memories (204), and may additionally include one or more transceivers (206) and / or one or more antennas (208). The processor (202) controls the memory (204) and / or transceivers (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods and / or sequences of operation disclosed in this disclosure. For example, the processor (202) may process information within the memory (204) to generate a third information / signal and then transmit a wireless signal containing the third information / signal through the transceiver (206). Additionally, the processor (202) may receive a wireless signal containing a fourth information / signal through the transceiver (206) and then store information obtained from the signal processing of the fourth information / signal in the memory (204). Memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, memory (204) may store software code including instructions for performing some or all of the processes controlled by the processor (202) or for performing the descriptions, functions, procedures, proposals, methods, and / or sequences of operation disclosed in this disclosure. Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). A transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals through one or more antennas (208). The transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeable with an RF unit. In this disclosure, a wireless device may refer to a communication modem / circuit / chip.

[0401] Hereinafter, hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as PHY, MAC, RLC, PDCP, RRC, SDAP). One or more processors (102, 202) may generate one or more Protocol Data Units (PDUs) and / or Service Data Units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and / or flowcharts of operation disclosed in this disclosure. One or more processors (102, 202) may generate messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or flowcharts of operation disclosed in this disclosure. One or more processors (102, 202) may generate a signal (e.g., a baseband signal) including a PDU, SDU, message, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this disclosure and provide it to one or more transceivers (106, 206). One or more processors (102, 202) may receive a signal (e.g., a baseband signal) from one or more transceivers (106, 206) and may obtain a PDU, SDU, message, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or flowcharts disclosed in this disclosure.

[0402] One or more processors (102, 202) may be referred to as a controller, microcontroller, microprocessor, or microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), or one or more Field Programmable Gate Arrays (FPGAs) may be included in one or more processors (102, 202). The descriptions, functions, procedures, proposals, methods, and / or flowcharts disclosed in this disclosure may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. Firmware or software configured to perform the descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this disclosure may be included in one or more processors (102, 202) or stored in one or more memories (104, 204) and driven by one or more processors (102, 202). The descriptions, functions, procedures, proposals, methods, and / or operation sequences disclosed in this disclosure may be implemented using firmware or software in the form of code, instructions, and / or sets of instructions.

[0403] One or more memories (104, 204) may be connected to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. One or more memories (104, 204) may be composed of ROM, RAM, EPROM, flash memory, hard drive, registers, cache memory, computer read storage media, and / or combinations thereof. One or more memories (104, 204) may be located inside and / or outside of one or more processors (102, 202). Additionally, one or more memories (104, 204) may be connected to one or more processors (102, 202) through various technologies such as wired or wireless connections.

[0404] One or more transceivers (106, 206) may transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or operation flowcharts, etc., of the present disclosure to one or more other devices. One or more transceivers (106, 206) may receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or operation flowcharts, etc., disclosed in the present disclosure from one or more other devices. For example, one or more transceivers (106, 206) may be connected to one or more processors (102, 202) and may transmit and receive wireless signals. For example, one or more processors (102, 202) may control one or more transceivers (106, 206) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (106, 206) may be connected to one or more antennas (108, 208), and one or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or flowcharts of operation disclosed in this disclosure through one or more antennas (108, 208). In this disclosure, one or more antennas may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports). One or more transceivers (106, 206) can convert the received wireless signal / channel, etc. from an RF band signal to a baseband signal in order to process the received user data, control information, wireless signal / channel, etc. using one or more processors (102, 202).One or more transceivers (106, 206) can convert user data, control information, wireless signals / channels, etc. processed using one or more processors (102, 202) from baseband signals to RF band signals. To this end, one or more transceivers (106, 206) may include (analog) oscillators and / or filters.

[0405] The embodiments described above are combinations of the components and features of the present disclosure in a specific form. Each component or feature should be considered optional unless otherwise explicitly stated. Each component or feature may be implemented in a form not combined with other components or features. Additionally, it is possible to construct embodiments of the present disclosure by combining some components and / or features. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment. It is obvious that embodiments may be constructed by combining claims that are not explicitly related in the claims, or that they may be included as new claims by amendment after filing.

[0406] It is obvious to those skilled in the art that the present disclosure may be embodied in other specific forms without departing from the essential features of the present disclosure. Accordingly, the detailed description set forth above should not be interpreted restrictively in all respects and should be considered exemplary. The scope of the present disclosure shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present disclosure are included within the scope of the present disclosure.

[0407] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that enable operations according to the methods of various embodiments to be executed on a device or computer, and a non-transitory computer-readable medium on which such software or instructions, etc. are stored and executable on a device or computer. Instructions that may be used to program a processing system to perform the features described in the present disclosure may be stored on or within a storage medium or a computer-readable storage medium, and the features described in the present disclosure may be implemented using a computer program product comprising such a storage medium. The storage medium may include, but is not limited to, high-speed random access memory such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices, and may include non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. The memory may optionally include one or more storage devices located remotely from the processor(s). Memory or alternatively, non-volatile memory device(s) within memory comprises a non-transient computer-readable storage medium. The features described in this disclosure may be stored in any one of the machine-readable media and integrated into software and / or firmware that can control the hardware of a processing system and allow the processing system to interact with other mechanisms utilizing results according to the embodiments of this disclosure. Such software or firmware may include, but is not limited to, application code, device drivers, operating systems, and execution environments / containers.

[0408] Here, the wireless communication technology implemented in the wireless device (100, 200) of the present disclosure may include LTE, NR, and 6G, as well as Narrowband Internet of Things for low-power communication. In this case, for example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology and may be implemented according to standards such as LTE Cat NB1 and / or LTE Cat NB2, but is not limited to the names mentioned above. Additionally, or generally, the wireless communication technology implemented in the wireless device (XXX, YYY) of the present disclosure may perform communication based on LTE-M technology. In this case, for example, LTE-M technology may be an example of LPWAN technology and may be referred to by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology may be implemented in 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, and is not limited to the names mentioned above. Additionally or generally, wireless communication technology implemented in the wireless device (XXX, YYY) of the present disclosure may include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN) for low-power communication, and is not limited to the names mentioned above. As an example, ZigBee technology can create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and may be referred to by various names.

[0409] Although the method proposed in this disclosure has been described with an example applied to 3GPP LTE / LTE-A and 5G systems, it can be applied to various wireless communication systems in addition to 3GPP LTE / LTE-A and 5G systems.

Claims

1. A step of receiving configuration information related to channel state information (CSI) reporting from a base station by a user device (UE: user equipment); The step of receiving a downlink reference signal (RS) from the base station by the above UE; and Based on the prediction-based CSI report being set by the above setting information, the UE transmits the prediction-based CSI report for the downlink RS to the base station, and A method in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specific to the above prediction-based CSI report and a second CPU specific to the above prediction-based CSI report are occupied.

2. In Paragraph 1, A method in which the first CPU and the second CPU are occupied during the same time interval.

3. In Paragraph 1, A method in which the number of the second CPUs occupied is equal to or smaller than the number of the first CPUs occupied.

4. In Paragraph 1, A method further comprising the step of reporting to the base station by the above UE information regarding the maximum number of the first CPU supported by the UE and information regarding the maximum number of the second CPU supported by the UE.

5. In Paragraph 4, A method in which updating the content of the prediction-based CSI report is not required, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs.

6. In Paragraph 1, A method in which a non-predicted based CSI report is transmitted instead of the predicted based CSI report, based on the setting of the predicted based CSI report exceeding the maximum number of the second CPUs.

7. In Paragraph 1, A method in which specific information that is predefined or pre-set is transmitted instead of the prediction-based CSI report, based on the setting of the prediction-based CSI report exceeding the maximum number of the second CPUs.

8. In Paragraph 1, A method further comprising the step of reporting to the base station by the above UE information regarding the number of occupancy of the second CPU required for the second CPU according to an AI / ML (artificial intelligence / machine learning) model, function, or use-case.

9. In Paragraph 8, A method in which information regarding the number of occupancy values ​​of the second CPU required above indicates a plurality of values ​​or a range of values.

10. In Paragraph 9, A method in which the number of occupants of the second CPU for an AI / ML model, function, or use-case used by the above UE is determined within the plurality of values ​​or the range of values ​​based on a specific rule, a report by the above UE, or a setting by the above base station.

11. User equipment (UE) is: One or more transceivers for transmitting and receiving wireless signals; and It includes one or more processors that control the above one or more transmitting and receiving units, and The above one or more processors are: Receive configuration information related to channel state information (CSI) reporting from a base station; Receive a downlink reference signal (RS) from the above base station; and Based on the prediction-based CSI report being set by the above setting information, the UE is set to transmit the prediction-based CSI report for the downlink RS to the base station, and A UE in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specific to the above prediction-based CSI report and a second CPU specific to the above prediction-based CSI report are occupied.

12. One or more non-transitory computer-readable media storing one or more instructions, The above one or more commands are executed by one or more processors, and user equipment (UE): Receive configuration information related to channel state information (CSI) reporting from a base station; Receive a downlink reference signal (RS) from the above base station; and Based on the prediction-based CSI report being set by the above setting information, the UE controls the transmission of the prediction-based CSI report for the downlink RS to the base station, and A computer-readable medium in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specified in the above prediction-based CSI report and a second CPU specified in the above prediction-based CSI report are occupied.

13. A processing device configured to control user equipment (UE), wherein the processing device: One or more processors; and It includes one or more computer memories that are operably connected to one or more processors and store instructions for performing operations based on execution by one or more processors, and The above operations are: A step of receiving configuration information related to channel state information (CSI) reporting from a base station; A step of receiving a downlink reference signal (RS) from the base station; and Based on the prediction-based CSI report being set by the above setting information, the UE transmits the prediction-based CSI report for the downlink RS to the base station, and A processing device in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specific to the above prediction-based CSI report and a second CPU specific to the above prediction-based CSI report are occupied.

14. A step of transmitting configuration information related to channel state information (CSI) reporting to user equipment (UE) by the base station; The step of transmitting a downlink reference signal (RS) to the UE by the base station; and The method includes the step of receiving the prediction-based CSI report for the downlink RS from the UE based on the prediction-based CSI report being set by the base station according to the setting information, and A method in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specific to the above prediction-based CSI report and a second CPU specific to the above prediction-based CSI report are occupied.

15. The base station is: One or more transceivers for transmitting and receiving wireless signals; and It includes one or more processors that control the above one or more transmitting and receiving units, and The above one or more processors are: Transmit configuration information related to channel state information (CSI) reporting to user equipment (UE); Transmitting a downlink reference signal (RS) to the above UE; and Based on the prediction-based CSI report being set by the above setting information, it is set to receive the prediction-based CSI report for the downlink RS from the UE, and A base station in which, for the above prediction-based CSI report, both a first CSI processing unit (CPU: CSI processing unit) not specified in the above prediction-based CSI report and a second CPU specified in the above prediction-based CSI report are occupied.

Images