Method and device for monitoring performance of channel state information prediction

Abstract

A method according to an embodiment of the present specification comprises the steps of: receiving configuration information related to channel state information (CSI), wherein the configuration information includes i) a first report configuration related to prediction and ii) a second report configuration related to prediction accuracy; reporting first CSI on the basis of the first report configuration; and reporting second CSI related to the prediction accuracy on the basis of the second report configuration. The first CSI is based on the prediction, the second CSI is based on channel measurement related to the second reporting configuration, and the second CSI is reported on the basis of i) a prediction instance of the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

Description

Performance monitoring method and device for predicting channel state information

[0001] The present specification relates to a performance monitoring method and device for predicting channel state information.

[0002] Mobile communication systems were developed to provide voice services while ensuring user activity. However, they have expanded beyond voice to include data services. Currently, explosive growth in traffic is leading to resource shortages and users are demanding faster services, necessitating a more advanced mobile communication system.

[0003] Next-generation mobile communication systems must support explosive data traffic growth, dramatically increasing data rates per user, a vastly increased number of connected devices, ultra-low end-to-end latency, and high energy efficiency. To achieve these goals, various technologies are being studied, including dual connectivity, massive multiple input multiple output (MIMO), in-band full duplex, non-orthogonal multiple access (NOMA), super wideband support, and device networking.

[0004] Meanwhile, the reporting behavior of Channel State Information (CSI) is defined. For example, CSI can be reported based on a Channel State Information-Reference Signal (CSI-RS).

[0005] According to the Channel State Information (CSI) prediction operation, CSI prediction based on an AI / ML (Artificial Intelligence / Machine Learning) model can be performed. At this time, a method may be considered in which a terminal performs performance monitoring on predicted CSI based on the prediction and reports the performance monitoring to a base station. Specifically, a method may be considered in which i) the terminal calculates a performance metric for the predicted CSI and reports the output of the performance monitoring based thereon to the base station (type 1), or ii) the terminal calculates a performance metric for the predicted CSI and reports it to the base station, and the base station calculates the output of the performance monitoring based on the performance metric (type 3).

[0006] At this time, if there is a mismatch between the prediction instance of the predicted CSI and the computation instance of the CSI (or ground-truth CSI) for calculating the performance indicator of the predicted CSI, there is a concern that the calculation of the performance indicator may be performed inaccurately.

[0007] The purpose of this specification is to propose a method to solve the above-mentioned problems.

[0008] The technical problems to be achieved in this specification are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0009] In order to solve the above-described technical problem, a method according to one embodiment of the present specification includes a step of receiving configuration information related to channel state information (CSI), a step of reporting a first CSI based on the first reporting configuration, and a step of reporting a second CSI related to the prediction accuracy based on the second reporting configuration.

[0010] The above configuration information includes i) a first reporting configuration related to prediction and ii) a second reporting configuration related to prediction accuracy.

[0011] The above first CSI is based on the above prediction.

[0012] The above second CSI is based on channel measurements related to the second reporting settings.

[0013] The second CSI is reported based on i) a first time point associated with the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

[0014] The first CSI may include i) a predicted channel state information-reference signal resource indicator (P-CRI), ii) a predicted SSB resource indicator (P-SSBRI), and / or iii) a predicted Layer 1-Reference Signal Received Power (P-L1-RSRP).

[0015] The above prediction is performed based on a measurement, and the measurement can be performed based on a resource setting related to the first report setting.

[0016] The second CSI may include a Reference Signal-Prediction Accuracy Indicator (RS-PAI) that includes information related to the prediction accuracy for the prediction.

[0017] The above second CSI may be reported based on the first point in time closest to the transmission point in time of the resource set.

[0018] The second CSI is reported based on the prediction time point of the first CSI being earlier than the time point related to the channel measurement, and the first CSI can be predicted immediately before the transmission time point of the resource set.

[0019] The second CSI is reported based on a point in time related to the channel measurement being earlier than the predicted point in time of the first CSI, and the first CSI can be predicted immediately after the transmission point in time of the resource set.

[0020] The second CSI may include i) an average value of performance metrics for multiple predictions and / or ii) a weighted average value of the performance metrics.

[0021] The above channel measurement is performed based on the CSI-RS for the channel measurement, and the CSI-RS for the channel measurement can be received based on the prediction time point and the transmission time point.

[0022] A method according to one embodiment of the present specification may further include a step of transmitting information related to the prediction time and the transmission time to a base station.

[0023] The information related to the prediction time and the transmission time may include i) information indicating a mismatch between the prediction time and the transmission time and / or ii) information regarding a difference between the prediction time and the transmission time.

[0024] The above prediction accuracy may be based on a preset or defined rank and / or layer.

[0025] The first CSI may include a rank indicator (RI), and the second CSI may include a weighted average value of performance indicators for each layer calculated based on the RI.

[0026] The above second report setting may be linked to the above first report setting.

[0027] A terminal according to another embodiment of the present disclosure may include one or more transceivers, one or more processors, and one or more memories connected to the one or more processors and storing instructions.

[0028] The above instructions are characterized in that they cause the terminal to perform all steps of any one of the above methods based on being executed by the one or more processors.

[0029] According to another embodiment of the present disclosure, a device comprises one or more memories and one or more processors connected to the one or more memories. The one or more memories are characterized in that they store instructions that cause the device to perform all steps of any one of the above methods based on instructions executed by the one or more processors.

[0030] A non-transitory computer-readable medium according to another embodiment of the present disclosure stores instructions, the instructions being executable by one or more processors, characterized in that they cause a terminal to perform all steps of any one of the above methods.

[0031] A method according to another embodiment of the present disclosure includes the steps of transmitting configuration information related to channel state information (CSI), receiving first CSI based on the first reporting configuration, and receiving second CSI related to the prediction accuracy based on the second reporting configuration.

[0032] The above configuration information includes i) a first reporting configuration related to prediction and ii) a second reporting configuration related to prediction accuracy.

[0033] The above first CSI is based on the above prediction.

[0034] The above second CSI is based on channel measurements related to the second reporting settings.

[0035] The second CSI is reported based on i) a prediction time of the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

[0036] A base station according to another embodiment of the present disclosure includes one or more transceivers, one or more processors, and one or more memories coupled to the one or more processors and storing instructions.

[0037] The above instructions are characterized in that they cause the base station to perform all steps of the method according to claim 18, based on being executed by the one or more processors.

[0038] According to the operation according to the prior art, there is a problem that the performance monitoring result may not be accurate if the prediction time of the predicted CSI and the calculation time of the calculated CSI (or ground-truth CSI) do not match.

[0039] According to an embodiment of the present specification, when the prediction time of predicted CSI and the calculation time of calculated CSI do not match, the accuracy of performance indicator calculation can be improved by defining predicted CSI to be used for performance monitoring.

[0040] According to an embodiment of the present specification, when the prediction time of predicted CSI and the calculation time of calculated CSI do not match, the accuracy of performance index calculation can be improved by the terminal receiving a reference signal (RS) for performance index calculation from the base station through separate signaling.

[0041] As described above, according to the embodiment of the present specification, even if a mismatch occurs between the prediction time and the calculation time, more accurate performance indicator calculation or performance monitoring result calculation is possible, and the base station receives more accurate performance indicator or performance monitoring result and performs a fallback operation, thereby improving the reliability of the downlink transmission and reception procedure.

[0042] The effects that can be obtained from this specification are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0043] Figure 1 is a flowchart showing an example of a CSI-related procedure.

[0044] Figure 2 is a diagram to explain overall functions from an AI / ML model perspective.

[0045] Figure 3 is a flowchart showing the general form of AI / ML related procedures performed between a network and a terminal.

[0046] Figure 4 is a flowchart showing an example of AI / ML-based CSI measurement / reporting operations.

[0047] Figure 5 is a diagram showing an example of a CSI report based on an AI / ML model.

[0048] Figure 6 is a diagram showing an example of CSI prediction based on an AI / ML model.

[0049] Figure 7 is a diagram illustrating a mismatch between the calculation time of the calculated CSI and the prediction time of the predicted CSI.

[0050] FIG. 8 is a flowchart illustrating an example of signaling based on a method according to at least one embodiment of the present specification.

[0051] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0052] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0053] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0054] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description set forth below, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the present disclosure and is not intended to represent the only embodiments in which the invention according to the present disclosure may be practiced. The following detailed description includes specific details to provide a thorough understanding of the present disclosure.

[0055] In some cases, to avoid obscuring the concept of the invention according to the embodiments of the present specification, well-known structures and devices may be omitted or illustrated in block diagram form focusing on the core functions of each structure and device.

[0056] Hereinafter, downlink (DL) refers to communication from a base station to a terminal, and uplink (UL) refers to communication from a terminal to a base station. In downlink, a transmitter may be part of a base station, and a receiver may be part of a terminal. In uplink, a transmitter may be part of a terminal, and a receiver may be part of a base station. A base station may be expressed as a first communication device, and a terminal may be expressed as a second communication device. A base station (BS) may be replaced by terms such as a fixed station, Node B, eNB (evolved-NodeB), gNB (Next Generation NodeB), BTS (base transceiver system), access point (AP: Access Point), network (5G network), AI system, RSU (road side unit), vehicle, robot, drone (Unmanned Aerial Vehicle, UAV), 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, robot, AI module, drone (Unmanned Aerial Vehicle, UAV), AR (Augmented Reality) device, VR (Virtual Reality) device, etc.

[0057] < CSI-related actions >

[0058] In NR (New Radio) systems, CSI-RS (channel state information-reference signal) is used for time / frequency tracking, CSI computation, L1 (layer 1)-RSRP (reference signal received power) computation, and mobility. Here, CSI computation is related to CSI acquisition, and L1-RSRP computation is related to beam management (BM).

[0059] CSI (channel state information) is a general term for information that can indicate the quality of the wireless channel (or link) formed between the terminal and the antenna port.

[0060] The base station can transmit CSI-RS to the terminal to determine the characteristics of the downlink channel, and receive feedback from the terminal on the channel measurement results based on the CSI-RS.

[0061] A CSI-RS can be configured for one or more terminals. Different CSI-RS configurations may be provided for each terminal, or the same CSI-RS configuration may be provided to multiple terminals. A CSI-RS can support up to 32 antenna ports. CSI-RSs corresponding to N (N is 1 or more) antenna ports can be mapped to N RE positions within a time-frequency unit corresponding to one slot and one RB. When N is 2 or more, the N-port CSI-RSs can be multiplexed by CDM, FDM, and / or TDM. One CDM group can include two antenna ports (CDM2) distinguished based on code resources on the same two adjacent subcarriers, four antenna ports (CDM4) distinguished based on code resources on the same two adjacent subcarriers and the same two adjacent OFDM slots, or eight antenna ports (CDM8) distinguished based on code resources on the same two adjacent subcarriers and the same four adjacent OFDM slots. When multiple CDM groups exist, the CDM groups may not be mapped to adjacent subcarriers and / or adjacent OFDM symbols. CSI-RS antenna ports may be indexed in the order of CDM group, frequency domain, and time domain. CSI-RS may be mapped to REs other than REs to which CORESET, DMRS, and SSB are mapped.

[0062] In the frequency domain, CSI-RS can be configured for the entire bandwidth, a portion of the bandwidth (BWP), or a portion of the bandwidth. CSI-RS can be transmitted on each RB within the configured bandwidth (i.e., density = 1), or on every second RB (e.g., even or odd RB) (i.e., density = 1 / 2). When CSI-RS is used as a Tracking Reference Signal (TRS), a single-port CSI-RS can also be mapped on three subcarriers in each resource block (i.e., density = 3).

[0063] One or more CSI-RS resource sets may be configured for a terminal in the time domain. Each CSI-RS resource set may include one or more CSI-RS configurations.

[0064] Each CSI-RS resource set can be configured as periodic, semi-persistent, or aperiodic. For a periodic CSI-RS resource set, the period can be configured as a number of slots greater than or equal to 4 and less than or equal to 640. In addition, a start offset value of the periodic CSI-RS resource set can be configured. For a semi-persistent CSI-RS resource set, an offset and a period for a CSI-RS resource set candidate can be configured. Here, actual CSI-RS transmission can be activated / deactivated based on a MAC Control Element (CE). When a CSI-RS resource set is activated, CSI-RS transmission can be performed according to the configured offset and period until deactivated. When a CSI-RS resource set is deactivated, CSI-RS transmission may not be performed until it is explicitly reactivated. For aperiodic CSI-RS transmission, information about each CSI-RS resource set can be explicitly provided by DCI.

[0065] A CSI-IM resource may be configured for interference measurement (IM) of a terminal. A CSI-IM resource may include four resource elements (REs) within one slot and one resource block. The four REs may correspond to two consecutive OFDM symbols and two consecutive subcarriers, or one OFDM symbol and four consecutive subcarriers. In the frequency domain, the CSI-IM RE positions may be determined by the CSI-IM configuration. In the time domain, a CSI-IM resource set may be configured periodically, semi-persistently, or aperiodically, similar to a CSI resource set. Typically, in a CSI-IM resource, transmission may not be performed in the corresponding cell, but may be performed in a neighboring cell. In this way, the CSI-IM resource may be configured as a zero power (ZP)-CSI-RS for the terminal.

[0066] ZP-CSI-RS can be configured to be distinct from Non-Zero Power (NZP)-CSI-RS. When a PDSCH is scheduled on a resource including a CSI-RS RE, the first terminal can assume that rate matching considering the CSI-RS RE is applied to the corresponding PDSCH, and that the PDSCH is not mapped to the CSI-RS RE. Here, the CSI-RS may be configured for the first terminal or may be configured for the second terminal. In this case, the CSI-RS for the first terminal can be configured as an NZP-CSI-RS for the first terminal, and an NZP-CSI-RS resource set can be configured for the first terminal. Meanwhile, the CSI-RS for the second terminal can be configured as a ZP-CSI-RS for the first terminal, and a ZP-CSI-RS resource set can be configured for the first terminal. The NZP-CSI-RS resource set can be used for the CSI reporting configuration of the corresponding terminal. The NZP-CSI-RS resource set can also be associated with CSI-RS or SSB. Additionally, multiple periodic NZP-CSI-RS resource sets can be configured as TRS resource sets.

[0067] Figure 1 is a flowchart showing an example of a CSI-related procedure.

[0068] A terminal (e.g., user equipment, UE) receives configuration information related to CSI from a base station (e.g., general Node B, gNB) through RRC (radio resource control) signaling (S110).

[0069] The configuration information related to the above CSI may include at least one of CSI-IM (interference management) resource related information, CSI measurement configuration related information, CSI resource configuration related information (e.g., M≥1 CSI-ResourceConfig resource setting), CSI-RS resource related information, or CSI report configuration related information (e.g., N≥1 CSI-ReportConfig reporting setting).

[0070] For example, the configuration information may include a first CSI resource configuration for measurement and a second CSI resource configuration for prediction. As a specific example, a measurement related to prediction of CSI, which will be described later, may be performed based on the first CSI resource configuration. The terminal may perform L1-RSRP measurements on CSI-RS resources or SS / PBCH block resources associated with the first CSI resource configuration. As a specific example, the prediction of CSI, which will be described later, may be performed based on the second CSI resource configuration. The terminal may perform prediction on CSI-RS resources or SS / PBCH block resources associated with the second CSI resource configuration based on the L1-RSRP measurements. In other words, best CRI / best SSBRI (e.g., P-CRI(s), P-SSBRI(s)) may be predicted using L1-RSRPs as measurement metrics.

[0071] For example, the configuration information may include a first CSI reporting setting related to prediction and a second CSI reporting setting related to prediction accuracy.

[0072] i) CSI-IM resource-related information may include CSI-IM resource information, CSI-IM resource set information, etc. A CSI-IM resource set is identified by a CSI-IM resource set ID (identifier), and one resource set includes at least one CSI-IM resource. Each CSI-IM resource is identified by a CSI-IM resource ID.

[0073] ii) CSI resource configuration related information can be expressed as CSI-ResourceConfig IE. The CSI resource configuration related information defines a group including at least one of a non-zero power (NZP) CSI-RS resource set, a CSI-IM resource set, or a CSI-SSB resource set. That is, the CSI resource configuration related information includes a CSI-RS resource set list, and the CSI-RS resource set list can include at least one of an NZP CSI-RS resource set list, a CSI-IM resource set list, or a CSI-SSB resource set list. A CSI-RS resource set is identified by a CSI-RS resource set ID, and one resource set includes at least one CSI-RS resource. Each CSI-RS resource is identified by a CSI-RS resource ID.

[0074] Table 1 shows an example of an NZP CSI-RS resource set IE. As shown in Table 1, parameters indicating the purpose of CSI-RS (e.g., BM-related 'repetition' parameter, tracking-related 'trs-Info' parameter) can be set for each NZP CSI-RS resource set.

[0075]

[0076] And, the repetition parameter corresponding to the higher layer parameter corresponds to the 'CSI-RS-ResourceRep' of the L1 parameter.

[0077] iii) Information related to the CSI report configuration includes a report configuration type parameter (reportConfigType) indicating time domain behavior and a report quantity parameter (reportQuantity) indicating the CSI-related quantity to be reported. The time domain behavior may be periodic, aperiodic, or semi-persistent.

[0078] The above reportQuantity parameter is a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), a Layer 1-Reference Signal Received Power (L1-RSRP), a Layer 1-Signal-to-Interference-plus-Noise Ratio (L1-SINR), a predicted CQI (predicted CQI, P-CQI), a predicted PMI (predicted PMI, P-PMI), a predicted CRI (predicted CRI, P-CRI), a predicted SSBRI (predicted SSBRI, P-SSBRI), a predicted LI (predicted LI, P-LI), a predicted RI (predicted RI, P-RI), a predicted L1-RSRP (predicted L1-RSRP, P-L1-RSRP) and / or a predicted It can be set to a value representing at least one of L1-SINR (predicted L1-SINR, P-L1-SINR) and / or Prediction Accuracy Indicator (PAI) (or RS-PAI).

[0079] For example, the reportQuantity parameter can be set to cri, ssb-Index, cri-RSRP, or ssb-Index-RSRP. cri represents the CSI-RS resource indicator (CRI). RSRP represents the Layer 1-Reference Signal Received Power (L1-RSRP). ssb-Index represents the SS / PBCH block resource indicator (SSBRI).

[0080] For example, the reportQuantity parameter can be set to p-cri, p-ssb-index, p-cri-RSRP, or p-ssb-index-RSRP. p-cri represents predicted CRI (P-CRI). p-ssb-index represents predicted SSBRI (P-SSBRI). p-cri-RSRP represents predicted CRI (P-CRI) and predicted L1-RSRP (P-L1-RSRP). p-ssb-index-RSRP represents predicted SSBRI (P-SSBRI) and predicted L1-RSRP (P-L1-RSRP).

[0081] For example, the reportQuantity parameter can be set to pai (or rs-pai), which represents PA (or RS-PAI).

[0082] Information related to CSI report configuration can be expressed in CSI-ReportConfig IE, and Table 2 below shows an example of CSI-ReportConfig IE.

[0083]

[0084] - The terminal measures CSI based on configuration information related to the above CSI (S120).

[0085] The above CSI measurement may include (1) a process of receiving a CSI-RS of a terminal (S121) and (2) a process of calculating (computing) CSI using the received CSI-RS (S122), which will be described in detail later.

[0086] CSI-RS sets the RE (resource element) mapping of CSI-RS resources in the time and frequency domains by the higher layer parameter CSI-RS-ResourceMapping.

[0087] Table 3 shows an example of the CSI-RS-ResourceMapping IE.

[0088]

[0089] In Table 3, density (D) represents the density of CSI-RS resources measured in RE / port / PRB (physical resource block), and nrofPorts represents the number of antenna ports.

[0090] - The terminal reports the measured CSI to the base station (S130).

[0091] Here, if the quantity of CSI-ReportConfig in Table E is set to 'none (or No report)', the terminal may omit the report.

[0092] However, even if the above quantity is set to 'none (or No report)', the terminal may report to the base station.

[0093] When the above quantity is set to 'none', it triggers an aperiodic TRS or repetition is set.

[0094] Here, the report of the terminal can be omitted only when repetition is set to 'ON'.

[0095] CSI measurement

[0096] The NR system supports more flexible and dynamic CSI measurement and reporting. Here, the CSI measurement may include a procedure for receiving a CSI-RS and computing the received CSI-RS to acquire CSI.

[0097] As a time-domain behavior for CSI measurement and reporting, aperiodic / semi-persistent / periodic channel measurement (CM) and interference measurement (IM) are supported. A 4-port NZP CSI-RS RE pattern is used to configure CSI-IM.

[0098] NR's CSI-IM-based IMR has a similar design to LTE's CSI-IM and is configured independently of the ZP CSI-RS resources for PDSCH rate matching. Furthermore, in the NZP CSI-RS-based IMR, each port emulates an interference layer with (preferred channel and) precoded NZP CSI-RS. This is for intra-cell interference measurement in multi-user cases, primarily targeting MU interference.

[0099] The base station transmits precoded NZP CSI-RS to the terminal on each port of the configured NZP CSI-RS-based IMR.

[0100] The terminal assumes a channel / interference layer for each port in the resource set and measures interference.

[0101] For a channel, if there is no PMI and RI feedback, multiple resources are configured in a set, and the base station or network indicates a subset of NZP CSI-RS resources via DCI for channel / interference measurement.

[0102] Let's take a closer look at resource settings and resource setting configuration.

[0103] Resource setting

[0104] Each CSI resource setting 'CSI-ResourceConfig' contains a configuration for S≥1 CSI resource sets (given by the higher layer parameter csi-RS-ResourceSetList). A CSI resource setting corresponds to a CSI-RS-resourcesetlist, where S represents the number of configured CSI-RS resource sets. Wherein, the list of S≥1 CSI resource sets contains either or both of NZP CSI-RS resource set(s) and SS / PBCH block (SSB) set(s) used for L1-RSRP computation, or contains CSI-IM resource set(s).

[0105] Each CSI resource setting is located in a DL BWP (bandwidth part) identified by the higher layer parameter BWP-id. All CSI resource settings linked to a CSI reporting setting have the same DL BWP.

[0106] The time domain behavior of CSI-RS resources within a CSI resource setting included in the CSI-ResourceConfig IE is indicated by the higher layer parameter resourceType, and can be set to aperiodic, periodic, or semi-persistent. For periodic and semi-persistent CSI resource settings, the number of configured CSI-RS resource sets (S) is limited to '1'. For periodic and semi-persistent CSI resource settings, the configured periodicity and slot offset are given in the numerology of the associated DL BWP, as given by the BWP-id.

[0107] When a UE is configured with multiple CSI-ResourceConfigs containing the same NZP CSI-RS resource ID, the same time domain behavior is configured for the multiple CSI-ResourceConfigs.

[0108] When a UE is configured with multiple CSI-ResourceConfigs containing the same CSI-IM resource ID, the same time domain behavior is configured for multiple CSI-ResourceConfigs.

[0109] One or more CSI resource settings for channel measurement (CM) and interference measurement (IM) are configured via higher layer signaling.

[0110] - CSI-IM resource for interference measurement.

[0111] - NZP CSI-RS resources for interference measurement.

[0112] - NZP CSI-RS resources for channel measurement.

[0113] That is, the CMR (channel measurement resource) can be NZP CSI-RS for CSI acquisition, and the IMR (Interference measurement resource) can be NZP CSI-RS for CSI-IM and IM.

[0114] Here, CSI-IM (or ZP CSI-RS for IM) is mainly used for inter-cell interference measurement.

[0115] And, NZP CSI-RS for IM is mainly used for intra-cell interference measurement from multi-user.

[0116] A UE may assume that the CSI-RS resource(s) configured for channel measurement for one CSI reporting and the CSI-IM / NZP CSI-RS resource(s) for interference measurement (when NZP CSI-RS resource(s) are used for interference measurement) are in a QCL relationship with respect to 'QCL-TypeD' per resource.

[0117] Resource setting configuration

[0118] As we have seen, resource setting can mean a resource set list.

[0119] For aperiodic CSI, each trigger state set using the higher layer parameter CSI-AperiodicTriggerState is associated with one or more CSI-ReportConfigs, and each CSI-ReportConfig is linked to a periodic or semi-persistent or aperiodic resource setting.

[0120] One reporting setting can be linked to up to three resource settings.

[0121] - When a resource setting is set, that resource setting (given by the higher layer parameter resourcesForChannelMeasurement) is for channel measurement for L1-RSRP computation or channel and interference measurement for L1-SINR computation.

[0122] - When two resource settings are set, the first resource setting (given by the higher layer parameter resourcesForChannelMeasurement) is for channel measurement, and the second resource setting (given by csi-IM-ResourcesForInterference or nzp-CSI-RS-ResourcesForInterference) is for interference measurement performed on CSI-IM or NZP CSI-RS.

[0123] - When three resource settings are set, the first resource setting (given by resourcesForChannelMeasurement) is for channel measurement, the second resource setting (given by csi-IM-ResourcesForInterference) is for CSI-IM based interference measurement, and the third resource setting (given by nzp-CSI-RS-ResourcesForInterference) is for NZP CSI-RS based interference measurement.

[0124] For semi-persistent or periodic CSI, each CSI-ReportConfig is linked to a periodic or semi-persistent resource setting(s).

[0125] - When one resource setting (given by resourcesForChannelMeasurement) is set, the resource setting is for channel measurement for L1-RSRP computation or channel and interference measurement for L1-SINR computation.

[0126] - When two resource settings are set, the first resource setting (given by resourcesForChannelMeasurement) is for channel measurement, and the second resource setting (given by higher layer parameter csi-IM-ResourcesForInterference or nzp-CSI-RS-ResourcesForInterference) is used for interference measurement performed on CSI-IM or NZP CSI-RS.

[0127] CSI computation

[0128] When interference measurements are performed on CSI-IM, each CSI-RS resource for channel measurements is associated with a CSI-IM resource in the order of the CSI-RS resources and CSI-IM resources within the corresponding resource set. The number of CSI-RS resources for channel measurements is equal to the number of CSI-IM resources.

[0129] And, if interference measurement is performed on NZP CSI-RS, the UE does not expect to be configured with more than one NZP CSI-RS resource in the associated resource set within the resource setting for channel measurement.

[0130] A terminal with the higher layer parameter nzp-CSI-RS-ResourcesForInterference set does not expect more than 18 NZP CSI-RS ports to be set within a single NZP CSI-RS resource set.

[0131] For CSI measurement(s) other than L1-SINR, the terminal assumes the following:

[0132] - Each NZP CSI-RS port configured for interference measurement corresponds to an interference transport layer.

[0133] - All interference transmission layers of the NZP CSI-RS port for interference measurement consider the associated EPRE (energy per resource element) ratio.

[0134] - Other interference signals on RE(s) of NZP CSI-RS resource for channel measurement, NZP CSI-RS resource for interference measurement or CSI-IM resource for interference measurement.

[0135] CSI report

[0136] A terminal can measure channel characteristics based on CSI-RS and feed back a CSI report to the base station as a result. To this end, a CSI report configuration can be provided for the terminal. Each CSI report configuration can include settings for feedback type, measurement resources, and report type.

[0137] Feedback types may include a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), a CSI-RS Resource Indicator (CRI), an SSB Resource block Indicator (SSBRI), a Layer Indicator (LI), a Rank Indicator (RI), and a Layer 1-Reference Signal Received Strength (RSRP).

[0138] Measurement resources may include configurations for downlink signals and / or downlink resources on which a terminal will perform measurements to determine feedback information. Measurement resources may be configured as ZP and / or NZP CSI-RS resource sets associated with CSI reporting configurations. The NZP CSI-RS resource set may include a CSI-RS set or an SSB set. For example, L1-RSRP may be measured for a CSI-RS set or an SSB set.

[0139] The report type may include settings for the time at which the terminal performs the report and the uplink channel. The report time may be set to be periodic, semi-persistent, or aperiodic. Periodic CSI reports may be transmitted on the PUCCH. Semi-persistent CSI reports may be transmitted on the PUCCH or PUSCH based on a MAC CE indicating activation / deactivation. Aperiodic CSI reports may be indicated by DCI signaling. For example, the CSI request field of the uplink grant may indicate one of various report trigger sizes. Aperiodic CSI reports may be transmitted on the PUSCH.

[0140] CSI can be defined in two types. Type 1 CSI may be related to a case where a single user is scheduled, and Type 2 CSI may be related to a case where multiple users are scheduled simultaneously on the same resource. Type 1 CSI may include single-panel CSI and multi-panel CSI, each of which may correspond to a different codebook. The precoding matrix in the codebook may be specified by a combination of w1 and w2. Long-term and wideband characteristics may correspond to w1, and short-term and subband characteristics may correspond to w2. While Type 1 CSI reports a single precoding matrix selected by the UE, Type 2 CSI may report information on the sizes and phases of up to four beams.

[0141] For CSI reporting, the time and frequency resources available to the UE are controlled by the base station.

[0142] CSI (channel state information) may include at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), L1-RSRP, and / or L1-SINR.

[0143] In the case of the CSI prediction described below, the CSI related to the prediction may include at least one of predicted CQI (predicted CQI, P-CQI), predicted PMI (predicted PMI, P-PMI), predicted CRI (predicted CRI, P-CRI), predicted SSBRI (predicted SSBRI, P-SSBRI), predicted LI (predicted LI, P-LI), predicted RI (predicted RI, P-RI), predicted L1-RSRP (predicted L1-RSRP, P-L1-RSRP), and / or predicted L1-SINR (predicted L1-SINR, P-L1-SINR).

[0144] When monitoring the performance / accuracy of the CSI prediction described below, the CSI related to the prediction accuracy may include a Prediction Accuracy Indicator (PAI). The PAI may indicate the accuracy of predicted downlink reference signal(s) (e.g., predicted CRI(s) and / or predicted SSBRI(s)), and the PAI may be interpreted / replaced with a Reference Signal-Prediction Accuracy Indicator (RS-PAI).

[0145] For CQI, PMI, CRI, SSBRI, LI, RI, and L1-RSRP, the UE is configured by a higher layer with N≥1 CSI-ReportConfig reporting settings, M≥1 CSI-ResourceConfig resource settings, and a list of one or two trigger states (provided by CSI-AperiodicTriggerStateList and CSI-SemiPersistentOnPUSCH-TriggerStateList). Each trigger state in the CSI-AperiodicTriggerStateList includes an associated list of CSI-ReportConfigs indicating resource set IDs for channel and optionally interference. Each trigger state in the CSI-SemiPersistentOnPUSCH-TriggerStateList includes one associated CSI-ReportConfig.

[0146] Additionally, the time domain behavior of CSI reporting supports periodic, semi-persistent, and aperiodic.

[0147] i) Periodic CSI reporting is performed on short PUCCH and long PUCCH. The periodicity and slot offset of periodic CSI reporting can be configured via RRC, and refer to the CSI-ReportConfig IE.

[0148] ii) SP (semi-periodic) CSI reporting is performed on short PUCCH, long PUCCH, or PUSCH.

[0149] In case of SP CSI on short / long PUCCH, the period and slot offset are set by RRC, and CSI reporting is activated / deactivated with a separate MAC CE / DCI.

[0150] In the case of SP CSI on PUSCH, the periodicity of SP CSI reporting is set to RRC, but the slot offset is not set to RRC, and SP CSI reporting is activated / deactivated by DCI (format 0_1). For SP CSI reporting on PUSCH, a separate RNTI (SP-CSI C-RNTI) is used.

[0151] The initial CSI reporting timing follows the PUSCH time domain allocation value indicated in the DCI, and subsequent CSI reporting timing follows the cycle set by RRC.

[0152] DCI format 0_1 ​​contains a CSI request field and can activate / deactivate a specific configured SP-CSI trigger state. SP CSI reporting has the same or similar activation / deactivation mechanism as data transmission on the SPS PUSCH.

[0153] iii) Aperiodic CSI reporting is performed on PUSCH and is triggered by DCI. In this case, information related to the triggering of aperiodic CSI reporting can be transmitted / indicated / configured via MAC-CE.

[0154] For AP CSI with AP CSI-RS, AP CSI-RS timing is set by RRC, and timing for AP CSI reporting is dynamically controlled by DCI.

[0155] NR does not apply the method of dividing CSI into multiple reporting instances (e.g., transmitting in the order of RI, WB PMI / CQI, and SB PMI / CQI) used for PUCCH-based CSI reporting in LTE. Instead, NR restricts specific CSI reporting on short / long PUCCHs and defines CSI omission rules. Furthermore, with respect to AP CSI reporting timing, PUSCH symbol / slot locations are dynamically indicated by DCI. Candidate slot offsets are configured by RRC. For CSI reporting, the slot offset (Y) is configured for each reporting setting. For UL-SCH, the slot offset K2 is configured separately.

[0156] Two CSI latency classes (low latency class, high latency class) are defined from the perspective of CSI computation complexity. Low latency CSI is WB CSI including up to 4 ports Type-I codebook or up to 4-port non-PMI feedback CSI. High latency CSI refers to any CSI other than low latency CSI. For a normal terminal, (Z, Z') is defined in units of OFDM symbols. Here, Z represents the minimum CSI processing time from receiving an aperiodic CSI triggering DCI to performing a CSI report. In addition, Z' represents the minimum CSI processing time from receiving a CSI-RS for channel / interference to performing a CSI report.

[0157] Additionally, the terminal reports the number of CSIs it can calculate simultaneously.

[0158] < AI / ML for Wireless Communication >

[0159] With the advancement of computing technology, artificial intelligence (AI) and machine learning (ML) are being adopted in various industries and technical fields. In the field of wireless communications, various discussions are underway to apply AI models trained based on ML, and this is referred to as AI / ML in the 3GPP standardization process. Although this specification describes “AI / ML” according to the terminology used in the 3GPP standardization process, “AI / ML” may be referred to by various other terms depending on the progress and implementation of the standard in the future. For example, it may be referred to as “transmission / reception mode” or “signal / channel / operation / transmission / reception configuration” configured for AI / ML, but is not limited thereto. The meaning of the terms currently used in the 3GPP standardization process is briefly summarized as follows.

[0160] - AI / ML model: A data-driven algorithm that applies AI / ML technology to generate a set of outputs containing prediction information and / or decision parameters based on a set of inputs.

[0161] - Data collection: The process of collecting data required for AI / ML model training, data analysis, and inference from network nodes, management entities, or terminals.

[0162] - AI / ML Training: An online or offline process of training an AI model by learning features and patterns that best represent the data and obtain a trained AI / ML model for inference.

[0163] - Offline training: The process of training a model based on a previously collected data set, and the trained model is used or provided for future inference.

[0164] - Online training: This is a method in which the model is trained in real time when new training sample data is acquired and used for inference.

[0165] - AI / ML Inference: This is the process of making predictions or inducing decisions based on collected data and the AI ​​model using a trained AI model. Meanwhile, depending on whether the AI / ML model is set up on both the transmitting and receiving devices or only on one of them, it can be divided into (i) a two-sided model and (ii) a one-sided model. (i) In the case of the two-sided model, collaborative inference is performed through paired AI / ML models. Collaborative inference refers to cooperation between the network and the UE, in which one party performs part of the inference and the other party performs the rest of the inference. (ii) The one-sided model is divided into a UE-side model and a network-side model. Inference in the one-sided model is performed entirely by the UE / network-side model.

[0166] 1. Life Cycle Management (LCM) for AI / ML models

[0167] LCM for AI / ML models is a concept that encompasses all the overall procedures for AI / ML models, including data collection, model training, model deployment, model inference, model monitoring, and model updates.

[0168] LCM for AI / ML models can be broadly categorized into functionality-based LCM and model ID-based LCM. In functionality-based LCM, the network can instruct the activation / deactivation / fallback / switching of specific functions, even if the target AI / ML model may not be identified by the network. In model ID-based LCM, the network can instruct the activation / deactivation / selection / switching of AI / ML models identified by their AI / ML model ID.

[0169] Figure 2 is a diagram to explain overall functions from an AI / ML model perspective.

[0170] Referring to FIG. 2, a general AI / ML functional framework can 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).

[0171] 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) can perform data preparation and provide input data processed through data preparation.

[0172] 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).

[0173] The Model Training function (20) is a function that performs AI / ML model training, validation, and testing, and 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) transmitted from the Data Collection function (10).

[0174] Trained / Updated Model (21): If there is a Model Storage function (50), it is used to pass a trained, validated and tested AI / ML model to the Model Storage function (50) or to pass an updated version of the model to the Model Storage function (50).

[0175] The Management function (30) is a function that monitors the operation of the AI / ML model or AI / ML function. In addition, the Management function (30) may perform a decision to ensure appropriate inference operation 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)).

[0176] Management Instruction (32) is information required as input to manage the Inference function (40). The relevant information may include selection / (de)activation / switching of an AI / ML model or AI / ML-based function, and may also include fallback to non-AI / ML operations (i.e., not relying on the inference process).

[0177] A Model Transfer / Delivery Request (33) can be used to request model(s) from Model Storage (50).

[0178] A Performance Feedback / Retraining Request (31) refers to information required as input to the Model Training function (20) (e.g., for the purpose of (re)training or updating the model).

[0179] 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 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 Data Collection (10). If necessary, the Inference function (40) may also perform data preparation (e.g., data preprocessing and cleaning, forming, and transformation) based on the Inference Data (13) provided by Data Collection function (10).

[0180] 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 the AI / ML model generated by the Inference function (30), and the details of the inference output may vary depending on the use case.

[0181] The Model Storage function (50) stores a learned / updated model that can be used to perform the Inference function (40). The Model Storage function (50) illustrated in FIG. 2 can be used as a reference point (if any) when applicable to protocol termination, model transmission / delivery, and related processes. Furthermore, the Model Storage function (50) is merely an example and is not intended to limit the storage location of actual AI / ML models, and may be omitted.

[0182] Model Transfer / Delivery (51) is used to transfer AI / ML models to inference functions.

[0183] 2. General AI / ML-related procedures between networks and terminals

[0184] Figure 3 illustrates the general form of AI / ML-related procedures performed between a network and a terminal. While Figure 2 examined LCM from an AI / ML model perspective, Figure 3 describes the general form of procedures performed from a signaling / protocol perspective between a terminal and the network.

[0185] (1) Setting procedures related to AI / ML

[0186] Referring to FIG. 3, an AI / ML-related configuration procedure may be performed between a network and a terminal (S310). The AI / ML-related configuration procedure may include information exchange between the terminal and the network via at least one upper-layer signaling, and / or preparatory / follow-up operations at the terminal / network, respectively, before / after the upper-layer signaling.

[0187] Specifically, the AI / ML-related configuration procedure may include, but is not limited to, at least one of (i) AI / ML-related terminal capability reporting, (ii) data collection, (iii) model training, (iv) model transfer / transfer, (v) AI / ML function / model selection, and (vi) configuration for various operations performed based on AI / ML models (e.g., AI / ML-based CSI / Positioning / Beam Management).

[0188] (i) A terminal can report to the network its capabilities, such as models / functionalities supported by the terminal in relation to AI / ML, through UE Capability Reporting. The network can provide AI / ML-related settings to the terminal based on the AI / ML-related capabilities reported by the terminal.

[0189] (ii) AI / ML-related configuration procedures may include data collection and / or provision of configuration information related to AI / ML model training / inference, etc. Configuration information related to data collection may relate to how to configure the method / action of data collection, etc.

[0190] (iii) AI / ML-related configuration procedures may include online or offline AI / ML model training and / or providing configuration information for AI / ML model training. Configuration information for AI / ML model training may relate to how to configure the method / operation of training the AI / ML model, etc.

[0191] (iv) The AI / ML-related configuration procedure may include transmitting / delivering configuration information for the model. The configuration information for the model may include parameters configuring the AI / ML model and / or an identifier (ID) for the AI / ML model.

[0192] The AI / ML model provided can be either a network-trained model or a model that requires self-training on the terminal. Even if a network-trained model is provided, the terminal can perform fine-tuning / retraining processes as needed. Meanwhile, if a network-trained model is provided, the terminal can provide training data to the network.

[0193] Meanwhile, AI / ML models can be categorized into Type A models, which can be identified without over-the-air (OTA) signaling, and Type B models, which are identified through OTA signaling. A model ID can be assigned during the model identification process, which can be further subdivided into terminal-initiated and network-initiated methods.

[0194] (v) The AI / ML-related configuration procedure may include a configuration of how to select an AI / ML Functionality / model and / or a selection process for the AI / ML Functionality / model. Selection of the UE part in a UE-side AI / ML model or a two-sided AI / ML model may be performed through instructions / signaling from the network or may be performed by the UE itself. Selection of the AI / ML Functionality / model may be performed when multiple AI / ML Functionality / models are configured / provided.

[0195] (vi) The AI / ML-related setup procedure may include setup information for various inference operations performed based on AI / ML models, for example, AI / ML-based CSI measurement / reporting, AI / ML-based Positioning, and / or AI / ML-based Beam Management.

[0196] (2) Actions based on inference from AI / ML models

[0197] Referring back to FIG. 3, the network and / or the terminal may perform inference of the AI / ML model through the trained AI / ML model, and perform various operations based on the inference of the AI / ML model (S320). If the AI / ML model is a one-sided model, the inference of the AI / ML model may be performed on either the network or the terminal where the AI / ML model is configured. If the AI / ML model is a two-sided model, each part of the inference of the AI / ML model may be performed on the network and the terminal, and such inference may be performed cooperatively between the network and the terminal depending on the implementation.

[0198] (i) Actions performed based on the inference of the AI / ML model may include AI / ML-based CSI measurement / reporting. The AI / ML-based CSI measurement / reporting may be for improving CSI feedback, and may be related to overhead reduction / CSI compression, accuracy improvement, and / or CSI prediction.

[0199] (ii) The actions performed based on the inference of the AI / ML model may include AI / ML-based beam management. The AI / ML-based beam management may be related to beam prediction in the time domain, reducing overhead / delay in the spatial domain, and / or improving beam selection accuracy.

[0200] (iii) Actions performed based on the inference of the AI / ML model may include AI / ML-based positioning. AI / ML-based positioning may be relevant to improving positioning accuracy in various scenarios, such as non-line-of-sight environments.

[0201] (3) Procedures for AI / ML management

[0202] The network and / or terminal can perform procedures for managing AI / ML Functionality / model or settings thereof (S330).

[0203] The network and / or terminal may perform monitoring of AI / ML Functionality / model during the process of AI / ML model inference or operation based thereon (S320) for management procedures (S330).

[0204] Management procedures may include, for example, at least one of activation / deactivation, switching, model update, and / or fallback operations for AI / ML Functionality / models. Signaling for management procedures may use various 3GPP signaling methods, such as RRC, MAC-CE, and DCI.

[0205] As an example of model switching, multiple model groups are formed, and switching between them, groups can be performed based on models having a common model structure or partially common sub-structures, and models within the same group can be related to different input / output formats or processing.

[0206] Model updating is the process of changing the parameters used by the model to adapt them to changing channel conditions over time, and fine-tuning is an example of model updating.

[0207] fallback: In a wireless communication system using an AI / ML model, when the reliability of the AI / ML model is reduced due to internal / external environmental factors, it can mean not using the AI / ML model or operating in a default operation mode that is set / defined in advance.

[0208] For example, the decision to perform a management procedure may be made by the network. For example, the network may decide to perform a management procedure upon network initiation, or upon terminal initiation and request.

[0209] As another example, the decision to perform a management procedure can be made by the terminal. For example, the terminal's decision to perform a management procedure can be triggered by the satisfaction of an event condition set by the network, by reporting the terminal's decision to the network, or by the terminal performing the decision autonomously.

[0210] 3. Specific examples of actions based on AI / ML model inference

[0211] CSI prediction and / or compression (CSI prediction / compression)

[0212] Figure 4 illustrates an example of AI / ML-based CSI measurement / reporting operations.

[0213] Referring to FIG. 4, the network / terminal may perform a configuration procedure related to AI / ML-based CSI (S410). The network / terminal may exchange configuration information for upper-layer signaling for AI / ML-based CSI measurement / reporting, and perform a configuration procedure for an AI / ML model to be used for AI / ML-based CSI. For example, at least one of information related to model inference, configuration of RS / resources to be used for CSI measurement, monitoring performance, data collection, and conditions / resources for CSI reporting may be signaled.

[0214] The terminal can perform CSI measurements based on AI / ML model inference (S420). The AI / ML model used by the terminal for CSI measurements may be a UE-side AI / ML model corresponding to a one-side AI / ML model, or an AI / ML model corresponding to the terminal portion of a two-side AI / ML model.

[0215] The terminal may report CSI to the network based on the CSI measurement results (S430). CSI reporting may be performed periodically or aperiodically depending on the configuration, and in the case of aperiodic CSI reporting, a network instruction (not shown) such as DCI that triggers it may be additionally signaled. The CSI report may include AI / ML-based CSI content, and additionally (depending on the configuration / scheduling) may further include legacy CSI content (e.g., non-AI / ML-based RI, PMI, CQI, etc.). The AI / ML-based CSI content may be related to at least one of 1) CSI compression to reduce the overhead of CSI reporting, and 2) CSI prediction for future time points in the time domain.

[0216] The network can obtain CSI based on the CSI report of the terminal.

[0217] If a two-sided AI / ML model is configured, the network can reconstruct CSI using the terminal's CSI report as input data to the network-configured AI / ML model (S440). The inference (output) of the network-configured AI / ML model can be the reconstructed CSI. In this two-sided AI / ML model, the terminal-side AI / ML model portion can be understood as a CSI encoder, while the network-side AI / ML model portion can be understood as a concept similar to a CSI decoder.

[0218] CSI compression is a spatial-frequency domain CSI compression, which can be primarily based on two-sided AI / ML models. CSI prediction can primarily be based on one-sided, specifically, UE-side AI / ML models.

[0219] In CSI compression based on two-side AI / ML models, AI / ML model training may include at least one of (i) Type 1, in which either the terminal or the network jointly trains two-side AI / ML models, (ii) Type 2, in which the terminal and the network each jointly train their respective two-side AI / ML model parts, and (iii) Type 3, in which the terminal and the network each separately train their respective two-side AI / ML model parts, with the terminal training being primarily related to CSI generation and the network training being primarily related to CSI reconstruction. Joint training means that the CSI generation / reconstruction model is trained in the same loop for forward / backward delays, and separate training may mean a sequential method in which either the terminal or the network starts training first and then the other performs training.

[0220] In this specification, ' / ' means 'and', 'or', or 'and / or' depending on the context.

[0221] Figure 5 is a diagram showing an example of a CSI report based on an AI / ML model.

[0222] Referring to FIG. 5, this specification considers AI / ML (Artificial Intelligence / Machine Learning)-based CSI reporting. A terminal may be equipped with an AI encoder, and a base station may be equipped with an AI decoder. As described above, a model that performs AI / ML model inference at two nodes can be expressed as a two-sided model. The terminal-side model (UE-sided model) and the network (or base station)-side model (NW-sided model) of FIG. 5 aim to reduce overhead through CSI compression.

[0223] For example, a two-sided AI / ML model is deployed / configured on the terminal and the network (or base station), respectively, so that each model can perform inference.

[0224] In the terminal side model (CSI encoder side in Fig. 5), i) channel information (e.g., channel matrix / channel covariance matrix / channel eigenvector) can be used as input, or ii) information that has gone through a pre-processing process for the channel information can be used as input to calculate the AI / ML model inference output.

[0225] The terminal can feed back the output information to the base station. At this time, the output information may be information that has undergone a specific post-processing process or information that has not undergone a specific post-processing process.

[0226] The base station side model (CSI decoder side in Fig. 5) may or may not preprocess the feedback information at this time.

[0227] The base station can calculate an inference output using the above feedback information, either preprocessed or unpreprocessed, as input.

[0228] The base station may or may not perform a post-processing process on the above inference output and may decode the final CSI based on the output.

[0229] As another use case, the Rel-18 AI / ML study studied CSI prediction based on a terminal-side model, and the use case for CSI prediction is illustrated in Figure 6.

[0230] Figure 6 is a diagram showing an example of CSI prediction based on an AI / ML model.

[0231] Referring to FIG. 6, an AI / ML model is provided only on the terminal side, and the UE-sided model can perform model inference in an AI / ML-based channel estimation use case that predicts / estimates one or more future CSIs. In this case, the CSI type of the input of the UE-sided model can be a raw channel matrix or a precoder type (e.g., eigenvector).

[0232] In non-AI / ML based CSI reporting (e.g., Rel-15 Type I / II CSI reporting), for the purpose of inter-cell interference management, RRC can be used to instruct / configure the UE to limit the use of PMIs to be used in CSI calculation. Thereafter, the UE can exclude the corresponding PMIs from CSI calculation and calculate and report preferred CSI (e.g., CQI / RI / PMI) to the base station.

[0233] In AI / ML-based CSI reporting, i) operations such as CodeBook Subset Restriction (SBSR) can be performed for the purpose of inter-cell interference control, and ii) rank restrictions / CBSR / codebook types can be predicted based on AI / ML. This effectively reduces feedback overhead during the UE's CSI reporting process. This specification aims to present an effective method for this purpose.

[0234] First, let's take a quick look at the legacy CBSR:

[0235] 1) Type 1 CSI

[0236] A. PMI restriction - bitmap-based indication

[0237] i. In the above bitmap , represents the number of antennas in the first and second domains of the base station antenna port (x-pol antenna port), respectively. At this time, is the length of the DFT-vector (1D / 2D) corresponding to the ports corresponding to one slant of the cross polarization (x-pol) antenna, and the length of the final DL precoder is , two The DFT vectors are connected in co-phase. In the case of Rank 1 codebook, can be expressed in the form of, is length is a DFT vector, has the values ​​{1, j, -1, -j} as co-phase values.

[0238] ii. and are the oversampling factors applied to the 1st domain and the 2nd domain, respectively.

[0239] iii. represents the total number of DFT vectors, and a specific bit corresponds to a specific DFT vector.

[0240] B. RI restriction - 8-bit bitmap is used

[0241] i. The size of the RI restriction can be determined based on the maximum rank value set by the base station. For example, if the max rank set by the base station is 8, the rank value that the terminal should use can be indicated as 8 bits. For example, even if the max rank is 8, if "11110000" is indicated as the RI restriction, the terminal can only calculate and report CSI corresponding to ranks 1, 2, 3, and 4.

[0242] 2) Type 2 CSI

[0243] A. PMI restriction

[0244] i. Restrictions are not applied to the entire DFT vector, but rather to specific beam groups. For beams within a beam group, the amplitude available for Type 2 CSI configuration is also limited to 2 bits for each combining beam, based on Table 4 below.

[0245] - Above The dog's beam Partitioning into groups of dogs, and each group -by- It consists of adjacent beams of a dog.

[0246] - Select the P-beam group as an indicator.

[0247] - And, is the length is a bitmap, -by- The beam is It is limited to beams, and each beam is limited to 2-bit soft power.

[0248]

[0249] B. RI restriction - 4-bit bitmap is used

[0250] Release 18 introduced a codebook capable of predicting N_4 future time instances by compressing N_4={1,2,4,8} basis vectors into the Doppler domain in CSI. Similarly, CSI prediction for N_4 time instances can be performed using AI / ML.

[0251] The information included in the CSI related to the prediction described below and the information included in the CSI related to monitoring are explained based on the background of the CSI-related operations described above as follows.

[0252] For example, CSI reported based on existing reporting configuration may include at least one of CSI-RS Resource Indicator (CRI), SSB Resource block Indicator (SSBRI), Layer Indicator (LI), and Layer 1-Reference Signal Received Strength (RSRP). In other words, the reportQuantity parameter in CSI-Reportconfig may be set to a value indicating at least one of CRI, LI, SSBRI, and / or L1-RSRP.

[0253] For example, CSI reported based on prediction-related reporting settings may include predicted information / predicted parameter(s) / indicator(s). As a specific example, the prediction-related CSI may include at least one of predicted CRI, predicted SSBRI, and / or predicted L1-RSRP. In other words, the reportQuantity parameter in CSI-Reportconfig may be set to a value indicating at least one of predicted CRI, predicted SSBRI, and / or predicted L1-RSRP. For convenience of explanation, a predicted parameter may be expressed as a P-parameter in the present specification. For example, predicted CRI, predicted SSBRI, and predicted L1-RSRP may be expressed as P-CRI, P-SSBRI, and P-L1-RSRP.

[0254] For example, CSI reported based on monitoring-related reporting settings may include parameter(s) / indicators(s) related to monitoring / prediction accuracy. As a specific example, the CSI related to monitoring / prediction accuracy may include a prediction accuracy indicator (e.g., a metric based on the embodiments described below). In other words, the reportQuantity parameter within CSI-Reportconfig may be set to a value indicating the prediction accuracy indicator. For convenience of explanation, the prediction accuracy indicator may be referred to as PAI in this specification.

[0255] This specification proposes a method for calculating and reporting performance metrics to effectively monitor performance in AI / ML-based CSI prediction.

[0256] Proposal 1. How to handle cases where the ground-truth CSI calculation time and the predicted CSI time are different for a report.

[0257] Figure 7 is a diagram illustrating a mismatch between the calculation time of the calculated CSI and the time related to the predicted CSI.

[0258] Referring to Fig. 7, a plurality of time instances (e.g., N4=4) to be predicted within a prediction window can be set. Performance monitoring can be performed based on a comparison between predicted CSI (e.g., RS indicator(s), P-CRI(s), P-SSBRI(s) determined based on prediction) and ground-truth CSI (e.g., RS indicator(s), CRI(s), SSBRI(s) determined based on measurement). The ground-truth CSI can be CSI for performance monitoring with respect to the predicted CSI.

[0259] Ground-truth CSI is required to calculate metrics / outputs (e.g., PAI) for performance monitoring. To this end, the base station can configure a new monitoring RS (e.g., periodic CSI-RS, semi-persistent CSI-RS, aperiodic CSI-RS) for the UE and transmit the RS to the UE.

[0260] At this time, as in the example of Fig. 7, a case may be considered where the time point related to the predicted CSI and the time point of calculating the ground-truth CSI are not the same time point.

[0261] For example, the time point related to the predicted CSI may mean i) a prediction time point of the predicted CSI, ii) a transmission time point of the predicted CSI, or iii) a reception time point of a reference resource (e.g., a reference signal) related to the predicted CSI.

[0262] For example, the above prediction time point may mean a time instance at which the predicted CSI is predicted.

[0263] For example, ground-truth CSI may be based on channel measurements for performance monitoring related to the prediction accuracy of the predicted CSI.

[0264] As a concrete example, ground-truth CSI may be based on channel measurements for reporting related to the performance monitoring / prediction accuracy for predicted CSI.

[0265] More specifically, ground-truth CSI can be calculated / measured based on resource sets for the above channel measurements.

[0266] For convenience of explanation in this specification, the calculation / measurement of ground-truth may represent channel measurement.

[0267] In this way, when a mismatch occurs between the calculation time of ground-truth CSI and the prediction instance, the terminal can calculate the performance metric as follows and report it to the base station.

[0268] Proposal 1-1. i) A terminal can calculate and report a (performance) metric / output (e.g., PAI) to a base station based on a time point related to the predicted CSI closest to the time point of RS reception for measuring / calculating ground-truth CSI (channel) or ii) a time point related to the predicted CSI closest to the time point of measuring / calculating the ground-truth CSI.

[0269] For example, the time point related to the predicted CSI may mean i) a prediction time point of the predicted CSI, ii) a transmission time point of the predicted CSI, or iii) a reception time point of a reference resource (e.g., a reference signal) related to the predicted CSI.

[0270] As a specific example, the terminal may calculate and report to the base station a (performance) metric / output (e.g., PAI) based on i) the predicted CSI predicted at the closest point in time from the RS reception time for measuring / calculating the ground-truth CSI (channel) or ii) the predicted CSI predicted at the closest point in time from the measurement / calculation time of the ground-truth CSI.

[0271] As a specific example, the terminal may calculate and report a (performance) metric / output (e.g., PAI) to the base station based on i) the predicted CSI transmitted at the closest time point from the RS reception time point for measuring / calculating the ground-truth CSI (channel) or ii) the predicted CSI transmitted at the closest time point from the measurement / calculation time point of the ground-truth CSI.

[0272] As a specific example, the terminal may calculate and report a (performance) metric / output (e.g., PAI) to the base station based on i) a reference resource related to predicted CSI received at the closest time point from the RS reception time point for measuring / calculating ground-truth CSI (channel) or ii) a reference resource related to predicted CSI received at the closest time point from the measurement / calculation time point of the ground-truth CSI.

[0273] For example, the metric / output may be calculated / measured and / or reported based on a transmission occasion of a Resource Set for measurement of ground-turth CSI and a time point associated with the predicted CSI that is closest to the transmission occasion.

[0274] As a specific example, the time point associated with the predicted CSI may have a minimum offset (e.g., minimum slot offset) from the transmission time point of the resource set for measuring ground-truth CSI.

[0275] As a specific example, the metric / output may be calculated / measured and / or reported based on a time point related to the predicted CSI that is closest to the time point of reception of the Reference Signal for measuring the ground-truth CSI.

[0276] For example, the metric / output may be calculated / measured and / or reported based on a time point associated with the predicted CSI that is closest to the time point of measurement / calculation of the ground-truth CSI.

[0277] Proposal 1-2. i) A terminal can calculate and report a metric / output based on a point in time related to the closest predicted CSI before / after the RS reception point for measuring / calculating ground-truth CSI, or ii) a point in time related to the closest predicted CSI before / after the point in time for measuring / calculating the ground-truth CSI.

[0278] In the above proposal 1-2, the terminal can calculate / report the metric / output in different ways depending on the ground-truth CSI calculation time (channel measurement time).

[0279] For example, as in the example of FIG. 7, if the measurement / calculation time of the first ground-truth CSI within the prediction window is later than the first prediction instance, the terminal can calculate and report the metric / output based on the closest predicted CSI before the ground-truth CSI calculation time.

[0280] For example, if the measurement / calculation time of the first ground-truth CSI is later than the first prediction instance, the terminal may calculate / measure and / or report the metric / output based on the predicted CSI immediately before the transmission time of the resource set for measuring the ground-truth CSI. As a specific example, the terminal may calculate / measure and / or report the metric / output based on the predicted CSI predicted immediately before the transmission time of the resource set for measuring the ground-truth CSI.

[0281] For example, if the measurement / calculation time of the first ground-truth CSI is later than the first prediction instance, the terminal may calculate / measure and / or report the metric / output based on the predicted CSI immediately before the reception time of the reference signal for measuring the ground-truth CSI.

[0282] As another example, if the first ground-truth CSI is earlier than the first prediction instance, the terminal can compute and report the metric / output based on the closest predicted CSI after the ground-truth CSI computation time.

[0283] For example, if the first ground-truth CSI is earlier than the first prediction instance, the terminal may calculate / measure and / or report a metric / output based on the predicted CSI immediately after the transmission time of the resource set for measuring the ground-truth CSI. As a specific example, the terminal may calculate / measure and / or report a metric / output based on the predicted CSI immediately after the transmission time of the resource set for measuring the ground-truth CSI.

[0284] For example, if the measurement / calculation time of the first ground-truth CSI is earlier than the first prediction instance, the terminal may calculate / measure and / or report the metric / output based on the predicted CSI immediately after the reception time of the reference signal for measuring the ground-truth CSI.

[0285] Proposal 1-3. The terminal can calculate the filtered value (e.g., average value / weighted average value) of the predicted CSI as a monitoring metric (or performance metric) and report it to the base station.

[0286] If any of the prediction instances mismatches with the ground-truth CSI, the terminal can report the filtered value of the predicted CSI as a metric to the base station.

[0287] For example, the terminal may calculate metrics in the same manner as in Proposal 1-1 and / or Proposal 1-2, apply weights to each metric to calculate a weighted average value, and report the calculated weighted average value to the base station.

[0288] As a concrete example, silver Indicates the metric value for the th instance, silver The th weight value can be represented. At this time, the weighted average Is It can be calculated as follows, It can be set as follows, and each weight value can be i) determined and reported by the terminal or ii) set / instructed by the base station to the terminal.

[0289] Proposal 2. When a mismatch occurs between the ground-truth CSI and the predicted CSI within the prediction window, the terminal can request the base station to accurately receive the monitoring RS from the base station through separate signaling.

[0290] The terminal calculating metrics in the same manner as in Proposal 1 above does not resolve the mismatch between ground-truth CSI and predicted CSI, and thus cannot be considered to be calculating accurate metrics. Therefore, a method to request accurate monitoring RS through separate signaling to prevent mismatches may be considered.

[0291] For example, the time point related to the predicted CSI may mean i) a prediction time point of the predicted CSI, ii) a transmission time point of the predicted CSI, or iii) a reception time point of a reference resource (e.g., a reference signal) related to the predicted CSI.

[0292] As a specific example, the terminal may calculate and report to the base station a (performance) metric / output (e.g., PAI) based on i) the predicted CSI predicted at the closest point in time from the RS reception time for measuring / calculating the ground-truth CSI (channel) or ii) the predicted CSI predicted at the closest point in time from the measurement / calculation time of the ground-truth CSI.

[0293] As a specific example, the terminal may calculate a metric / output and report it to the base station based on i) the predicted CSI transmitted at the closest time point from the RS reception time point for measuring / calculating the ground-truth CSI (channel) or ii) the predicted CSI transmitted at the closest time point from the measurement / calculation time point of the ground-truth CSI.

[0294] As a specific example, the terminal may calculate a metric / output and report it to the base station based on i) a reference resource related to predicted CSI received at the closest time point from the RS reception time point for measuring / calculating ground-truth CSI (channel) or ii) a reference resource related to predicted CSI received at the closest time point from the measurement / calculation time point of the ground-truth CSI.

[0295] For example, the terminal may transmit a 1-bit indicator to the base station that a mismatch has occurred between the ground-truth CSI and the instances within the prediction window.

[0296] For example, a terminal can request the base station to change the timing of ground-truth CSI transmission by separately transmitting information such as misaligned timing information (timing advance / delaying) and / or # of monitoring occasions to the base station via signaling. This allows the terminal to set / receive ground-truth CSI from the base station at the correct time, thereby calculating accurate metrics.

[0297] As a specific example, the terminal may request the base station to change the information regarding the following contents of 3GPP TS 38.214: i) in case of periodic / semi-persistent CSI, the terminal may request the base station to change the information regarding periodicityAndOffset, and ii) in case of aperiodic CSI, the terminal may request the base station to change the number of AP-CSI-RS resources K and / or the separation information m between two consecutive CSI-RS resources.

[0298] 3GPP TS 38.214

[0299] "5.2.1.4.1 Configuring Resource Settings

[0300] For aperiodic CSI, each trigger state configured using the upper layer parameter CSI-AperiodicTriggerState is associated with one or more CSI-ReportConfigs that are not configured with groupBasedBeamReporting-r17 or groupBasedBeamReporting-v18 and are linked to periodic, semi-persistent, or aperiodic resource settings.

[0301] - If one resource configuration is configured, the resource configuration (provided by the upper layer parameter resourcesForChannelMeasurement) is for channel measurements for L1-RSRP or channel and interference measurements for L1-SINR calculation.

[0302] - When two resource settings are configured, the first resource setting (provided by the upper layer parameter resourcesForChannelMeasurement) is for channel measurements, and the second resource setting (provided by the upper layer parameter csi-IM-ResourcesForInterference or the upper layer parameter nzp-CSI-RS-ResourcesForInterference) is for interference measurements performed on CSI-IM or NZP CSI-RS.

[0303] - When three resource settings are configured, the first resource setting (given by the upper layer parameter resourcesForChannelMeasurement) is for channel measurement, the second resource setting (given by the upper layer parameter csi-IM-ResourcesForInterference) is for CSI-IM based interference measurement, and the third setting (given by the upper layer parameter nzp-CSI-RS-ResourcesForInterference) is for NZP CSI-RS based interference measurement.

[0304] For aperiodic CSI and periodic and semi-persistent CSI resource configurations, each trigger state configured using the upper layer parameter CSI-AperiodicTriggerState is associated with one or more CSI-ReportConfigs configured with groupBasedBeamReporting-r17 or groupBasedBeamReporting-v18, which are linked to the periodic or semi-persistent configuration.

[0305] - When a resource configuration is configured, the resource configuration is provided by resourcesForChannelMeasurement for L1-RSRP measurements. In this case, the number of CSI resource sets configured in the resource configuration is S=2.

[0306] For aperiodic CSI and aperiodic CSI resource settings, each trigger state configured using the upper layer parameter CSI-AperiodicTriggerState is associated with one or more CSI-ReportConfigs, where the CSI-ReportConfigs configured with groupBasedBeamReporting-r17 or groupBasedBeamReporting-v18 are associated with resourcesForChannel and resourcesForChannel2 corresponding to the first and second resource sets, respectively, for L1-RSRP measurements. For semi-persistent or periodic CSI, each CSI-ReportConfig is associated with a periodic or semi-persistent Resource Setting.

[0307] - If one resource configuration (provided by the upper layer parameter resourcesForChannelMeasurement) is configured, the resource configuration is for channel measurements for L1-RSRP or channel and interference measurements for L1-SINR calculation.

[0308] - When two resource configurations are configured, the first resource configuration (provided by the upper layer parameter resourcesForChannelMeasurement) is for channel measurement, and the second resource configuration (provided by the upper layer parameter csi-IM-ResourcesForInterference) is used for interference measurements performed on CSI-IM. For L1-SINR calculation, the second resource configuration (provided by the upper layer parameter csi-IMResourcesForInterference or the upper layer parameter nzp-CSI-RS-ResourceForInterference) is used for interference measurements performed on CSI-IM or NZP CSI-RS.

[0309] For aperiodic CSI, a UE configured with a CSI-ReportConfig with the upper layer parameter reportQuantity set to 'tdcp' is expected to be configured with one CSI resource setting (provided by the upper layer parameter resourcesForChannelMeasurement). The CSI Resource Setting may be periodic, and the CSI-RS Resource Sets are configured with the upper layer parameter trs-Info. Support of 2 or 3 may depend on UE capability indications. For a periodic CSI-ResourceConfig, the UE may assume that all CSI-RS resources within the KTRS CSI-RS resource set K_TRS∈{1,2,3,}K_TRS= share the same QCL-TypeA / C and, if applicable, TypeD. The UE expects that all CSI-RS resources within the CSI-RS resource set(s) are configured with the same bandwidth and subcarrier locations. A UE configured with CSI-ReportConfig with upper layer parameter reportQuantity set to 'tdcp' is not expected to be configured for interference measurements in CSI-IM and / or NZP-CSI-RS.

[0310] For UEs configured with [LTM-CSI-ReportConfig], aperiodic, semi-persistent or periodic CSI is associated with one Resource Setting given by [ltm-ResourcesForChannelMeasurement] for L1-RSRP measurements.

[0311] A UE is not expected to be configured with more than one CSI-RS resource in the resource set for channel measurements for a CSI-ReportConfig with the upper layer parameter codebookType set to 'typeII', 'typeII-PortSelection', 'typeII-r16', 'typeII-PortSelection-r16' or 'typeII-PortSelection-r17'. The UE is expected not to be configured with more than 64 NZP CSI-RS resources and / or SS / PBCH block resources in the resource configuration for channel measurements for CSI-ReportConfig, where the upper layer parameter reportQuantity is set to 'none', 'cri-RI-CQI', 'cri-RSRP', 'ssb-Index-RSRP', 'cri-SINR', or 'ssb-Index-SINR', 'cri-RSRP-Index', 'cri-RSRP-Index', 'cri-RSRP-Index', 'ssb-Index-RSRP-Index', 'cri-SINR-Index', 'cri-Index-SINR-Index'. When interference measurements are performed on CSI-IM, each CSI-RS resource for channel measurements is associated with a CSI-IM resource on a resource basis by the order of CSI-RS resources and CSI-IM resources in the corresponding resource sets. The number of CSI-RS resources for channel measurement is equal to the number of CSI-IM resources.

[0312] A UE configured with CSI-ReportConfig with upper layer parameter reportQuantity set to 'cri-RI-PMI-CQI' and codebookType set to 'typeII-CJT-r18' or 'typeII-CJT-PortSelection-r18' is expected to be configured with 1 ≤ K ≤ 4 CSI-RS resources in the resource set for channel measurements. When interference measurements are performed on CSI-IM, only one resource is configured in the corresponding csi-IM-ResourceSet. When interference measurements are performed on NZP CSI-RS, only one resource is configured in the corresponding NZP-CSI-RS-ResourceSet for interference measurements.

[0313] A UE configured with CSI-ReportConfig with upper layer parameters N4 and reportQuantity set to 'cri-RI-PMI-CQI' is expected to have a resource set for channel measurement consisting of K ∈ {4,8,12} aperiodic CSI-RS resources, or a single periodic or semi-persistent CSI-RS resource. For the aperiodic CSI-RS resource set for channel measurement, the K CSI-RS resources are triggered by the same triggering instance, and the separation between two consecutive CSI-RS resources is m ∈ {1,2} slots, which is configured by the upper layer parameters of NZP-CSI-RS-ResourceSet. The K aperiodic CSI-RS resources are transmitted in the order of the CSI-RS resource IDs configured in the CSI-RS resource set. The UE assumes that antenna ports with the same port index of the K aperiodic CSI-RS resources are identical. When interference measurement is performed in CSI-IM, only one resource is configured in the corresponding csi-IM-ResourceSet. When performing interference measurements on NZP CSI-RS, only one resource is configured in the corresponding NZP-CSI-RS-ResourceSet for interference measurements."

[0314] "5.2.2.3 Reference Signal (CSI-RS)

[0315] 5.2.2.3.1 NZP CSI-RS

[0316] A UE may be configured with one or more NZP CSI-RS resource set configuration(s) indicated by higher layer parameters CSI-ResourceConfig and NZP-CSI-RS-ResourceSet. Each NZP CSI-RS resource set consists of K≥1 NZP CSI-RS resources. The following parameters, which allow the UE to assume non-zero transmit power for CSI-RS resources, are configured for each CSI-RS resource configuration via higher layer parameters NZP-CSI-RS-Resource, CSI-ResourceConfig and NZP-CSI-RS-ResourceSet.

[0317] - nzp-CSI-RS-ResourceId determines the CSI-RS resource configuration identity.

[0318] - periodicityAndOffset defines the CSI-RS periodicity and slot offset for periodic / semi-persistent CSI-RS. All CSI-RS resources within a set are configured with the same periodicity, while the slot offset can be the same or different for different CSI-RS resources.

[0319] The above separate signaling may also include information related to mismatch in the frequency domain as well as the time domain.

[0320] For example, the terminal may also transmit offset information for the frequency domain between the ground-truth CSI and the predicted CSI to the base station to request that the frequency domain of the ground-truth CSI and the frequency domain of the predicted CSI be brought closer together or overlap.

[0321] Proposal 3. When performing CSI prediction (for multiple time instances), the rank / layer to be assumed when calculating the performance metric (e.g., Squared Generalized Cosine Similarity (SGCS)) by the terminal can be i) agreed / defined in advance, ii) set / instructed by the base station to the terminal, and / or iii) determined by the terminal and reported to the base station.

[0322] In the case of the above proposal 3, as shown in Fig. 7, i) CSI for K time instances within the observation window is used / applied as input to AI / ML, and ii) within the prediction window This relates to an AI / ML-based channel estimation use case where the CSI for a given time instance is used / applied as the output of AI / ML to estimate / predict future CSI. In this case, the terminal calculates a performance metric (e.g., SGCS) to monitor the model's performance. Since the terminal can calculate metrics using multiple ranks / layers, it must determine which rank / layer to use for metric calculation. The following methods for determining the rank / layer to use for metric calculation can be considered.

[0323] Proposal 3-1. A method to restrict the terminal to use a specific rank / layer (e.g., rank / layer 1) separately / differently from the reported rank value when calculating monitoring metrics.

[0324] In the above proposal 3-1, the terminal can calculate the performance metric by determining a specific rank / layer without separate settings / instructions.

[0325] As another example, the base station can set / instruct the terminal to set a value for the above-mentioned specific rank / layer information.

[0326] As another example, if a terminal calculates a performance metric / output based on a specific rank / layer and reports it to a base station, information related to the specific rank / layer may be reported to the base station along with the report on the monitoring metric / output.

[0327] Proposal 3-2. A method of using the weighted average value for the metric calculated for each layer for the number of layers corresponding to the reported rank value.

[0328] The terminal can use the weighted average value calculated by multiplying the metric calculated for each layer by the weight.

[0329] For example, silver Indicates the metric value for the th layer, silver The th weight value can be represented. At this time, the weighted average Is It can be expressed as, It can be set as follows, and each weight value can be i) determined by the terminal and reported to the base station, or ii) set / instructed by the base station to the terminal.

[0330] Reporting for the above monitoring metrics can be based on UCI, and both 1 part encoding and 2 part encoding can be considered.

[0331] For the above 1-part encoding, the UCI size may be determined based on i) the (configured) maximum number of monitoring occasions and / or ii) the number of monitoring metrics configured to be reported. For example, if the actual reported number is less than i) the (configured) maximum number of monitoring occasions and / or ii) the number of monitoring metrics configured to be reported, the remaining bits used for reporting may be zero-padded to eliminate ambiguity in the payload.

[0332] For the above 2-part encoding, Part 1 CSI (fixed payload) may i) include at least # of metrics, or ii) include additional values ​​for the first metric. The terminal may report values ​​for the remaining metrics in Part 2 CSI (variable payload).

[0333] For example, if the first metric is not reported in part 1 CSI, all metrics may be reported in part 2 CSI.

[0334] For example, if only a single metric is reported, reporting of part 2 CSI may be omitted.

[0335] For example, a metric could be reported along with inference (e.g., predicted CSI), and an indicator of whether monitoring-related reporting is performed could be included in the part 1 CSI.

[0336] The following are the operation procedures of the terminal (UE) and the network (NW) / base station (BS) for Proposal 1, Proposal 2 and / or Proposal 3.

[0337] <UE-sided model>

[0338] Terminal operation:

[0339] Step 1: Reporting / transmitting the terminal's capabilities to the base station, including i) the maximum number of CSI-RS resources that the terminal can support, ii) the number of CSI-RS ports and the total number of CSI-RS ports that can be supported simultaneously, and iii) the number of Rx antenna groups.

[0340] Step 2: Step of receiving configuration information related to CSI-RS transmission and configuration information related to CSI reporting from the base station.

[0341] Step 3: Receive CSI-RS from the base station and measure / predict / calculate CSI using AI / ML model based on CSI-RS.

[0342] Step 3-1: Step of performing CSI omission based on configuration information and CSI priority received from the base station.

[0343] Step 4: Reporting the measured / predicted / calculated CSI to the base station.

[0344] Step 5: The step of receiving scheduling for downlink channels (e.g., PDCCH, PDSCH) from the base station.

[0345] Step 6: Receiving downlink channels / signals from the base station

[0346] Base station operation:

[0347] Step 1: A step of reporting / receiving the capability of the terminal, including i) the maximum number of CSI-RS resources that the terminal can support, ii) the number of CSI-RS ports and the total number of CSI-RS ports that can be supported simultaneously, and iii) the number of Rx antenna groups.

[0348] Step 2: Step of transmitting configuration information related to CSI-RS transmission and configuration information related to CSI reporting to the terminal.

[0349] Step 3: Transmitting CSI-RS to the terminal

[0350] Step 4: The step of receiving CSI measured / predicted / calculated by the terminal from the terminal.

[0351] Step 5: A step of scheduling downlink channels (e.g., PDCCH, PDSCH) based on the CSI reported from the terminal and transmitting them to the terminal.

[0352] <Base station side model (NW-sided model)>

[0353] Terminal operation:

[0354] Step 1: Reporting / transmitting the terminal's capabilities to the base station, including i) the maximum number of CSI-RS resources that the terminal can support, ii) the number of CSI-RS ports and the total number of CSI-RS ports that can be supported simultaneously, and iii) the number of Rx antenna groups.

[0355] Step 2: Step of receiving configuration information related to CSI-RS transmission and configuration information related to CSI reporting from the base station.

[0356] Step 3: Receive CSI-RS from the base station and measure / predict / calculate CSI based on the CSI-RS.

[0357] Step 3-1: Step of performing CSI omission based on configuration information and CSI priority received from the base station.

[0358] Step 4: Reporting the measured / predicted / calculated CSI to the base station.

[0359] Step 5: The step of receiving scheduling for downlink channels (e.g., PDCCH, PDSCH) from the base station.

[0360] Step 6: Step of receiving the downlink channel / signal transmitted by the base station.

[0361] Base station operation:

[0362] Step 1: A step of receiving a capability report from the terminal, including i) the maximum number of CSI-RS resources that the terminal can support, ii) the number of CSI-RS ports and the total number of CSI-RS ports that can be supported simultaneously, and iii) the number of Rx antenna groups.

[0363] Step 2: Step of transmitting configuration information related to CSI-RS transmission and configuration information related to CSI reporting to the terminal.

[0364] Step 3: Transmitting CSI-RS to the terminal

[0365] Step 4: The stage where the terminal receives the measured / predicted / calculated CSI from the terminal.

[0366] Step 5: A step of predicting CSI using an AI / ML model based on the CSI reported from the terminal, scheduling downlink channels (e.g., PDCCH, PDSCH), and transmitting the same to the terminal.

[0367] In the above terminal / base station operation, (some) specific steps may be omitted.

[0368] The above suggestions 1 / 2 / 3 can be used alone or in combination.

[0369] FIG. 8 is a flowchart illustrating an example of signaling based on a method according to at least one of the embodiments of the present specification (e.g., Proposal 1, Proposal 2 and / or Proposal 3).

[0370] Referring to FIG. 8, in step S810, 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 in this specification may be interpreted as a 'first signaling' or a 'set of first signaling' used to perform an operation based on an AI / ML model, even if not otherwise mentioned.

[0371] For example, the first signaling may correspond to i) training data for training (e.g., generation and / or reconstruction) of an AI / ML model, ii) inference data used for inference of an AI / ML model, or iii) feedback for an AI / ML model.

[0372] For example, if signaling between nodes is not required prior to actions based on the AI / ML model, the first signaling may be omitted.

[0373] For example, if a one-side model is used in this specification, the unidirectional / bidirectional signaling (set) in this specification may correspond to the first signaling.

[0374] For example, if a two-side model is used in this specification, the unidirectional / bidirectional signaling in this specification may correspond to the first signaling.

[0375] For example, a repetitive signaling operation may correspond to the first signaling.

[0376] For example, in AI / ML model-based beam management (BM), when beam(s) with good quality are predicted / inferred by the base station based on the AI / ML model, the base station can receive quality / intensity information for multiple beams from the terminal.

[0377] For example, if beam(s) of good quality are predicted / inferred by the terminal based on an AI / ML model, the terminal may receive multiple beams from the base station.

[0378] In step S820, in this specification, an operation (e.g., calculation, selection, prediction, etc.) at a specific node (e.g., terminal, network, etc.) or an operation (e.g., calculation, selection, prediction, etc.) at multiple nodes (e.g., terminal, network, etc.) may correspond to an 'operation based on an AI / ML model' based on one or more functions in the functional framework of the AI / ML model, even if not mentioned separately.

[0379] For example, i) training (e.g., generating and / or reconstructing) an AI / ML model, or ii) inference of an AI / ML model, etc. may correspond to the 'AI / ML model-based operation' of FIG. 6.

[0380] For example, if a one-side model is used in this specification, an operation performed by a single node in this specification may correspond to an operation based on the AI / ML model.

[0381] For example, if a two-side model is used in this specification, a joint operation performed by multiple nodes in this specification may correspond to an operation based on the AI / ML model.

[0382] For example, in an AI / ML model-based BM, a base station can use quality / intensity information for multiple beams received from a terminal as inference data to predict / infer beam(s) with good quality based on an AI / ML model.

[0383] For example, a terminal can measure multiple beams received from a base station and use the measurement results as inference data to predict / infer beam(s) with good quality based on an AI / ML model.

[0384] In step S830, 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 in this specification may be interpreted as a 'second signaling' or a 'set of second signaling' generated (as a result of) an operation based on the AI / ML model, even if not otherwise stated.

[0385] For example, the second signaling may correspond to an output resulting from inference of an AI / ML model.

[0386] For example, if signaling between nodes is not required as a result of an action based on an AI / ML model, the second signaling may be omitted.

[0387] For example, if a one-side model is used in this specification, the unidirectional / bidirectional signaling (set) in this specification may correspond to the second signaling.

[0388] For example, if a two-side model is used in this specification, the unidirectional / bidirectional signaling in this specification may correspond to the second signaling.

[0389] For example, a repetitive signaling operation may correspond to the second signaling.

[0390] For example, in an AI / ML model-based BM, the base station can transmit to the terminal the beam(s) predicted based on the AI / ML model as candidates so that the terminal can determine the optimal beam.

[0391] For example, the terminal may report to the base station the beam(s) predicted based on the AI / ML model to request the base station to transmit candidate beams as candidates for determining the optimal beam.

[0392] In terms of implementation, the operations of the base station / terminal according to the embodiments described above (e.g., operations based on at least one of Proposals 1 to 3) can be processed by the device of FIG. 11 described below (e.g., processor (110, 210) of FIG. 11).

[0393] In addition, the operations of the base station / terminal according to the above-described embodiment (e.g., operations based on at least one of proposals 1 to 3) may be stored in a memory (e.g., memory (140, 240) of FIG. 11) in the form of a command / program (e.g., instruction, executable code) for driving at least one processor (e.g., processor (110, 210) of FIG. 11).

[0394] The embodiments described below are specifically described with reference to FIGS. 9 and 10 in terms of the operation of the terminal and base station. The methods described below are distinguished for convenience of explanation, and it is understood that some components of one method may be substituted for or combined with some components of another method.

[0395] FIG. 9 is a flowchart illustrating a method according to one embodiment of the present specification.

[0396] Referring to FIG. 9, a method according to one embodiment of the present specification includes a step of receiving setting information related to CSI (S910), a first CSI reporting step (S920), and a second CSI reporting step (S930).

[0397] In S910, the terminal receives configuration information related to channel state information (CSI).

[0398] The above configuration information may include at least one of one or more resource configurations (e.g., M≥1 CSI-ResourceConfig resource settings) and / or one or more reporting configurations (e.g., N≥1 CSI-ReportConfig reporting settings). Each of the one or more reporting configurations may be associated with up to three resource configurations. In other words, each reporting configuration may include IDs (e.g., CSI-ResourceConfigId) of up to three resource configurations.

[0399] The above configuration information includes i) a first reporting configuration related to prediction and ii) a second reporting configuration related to prediction accuracy.

[0400] For example, the number of one or more time instances (e.g., prediction instances) may be set based on the first report setting. For example, the first report setting may include information indicating the number of one or more time instances (e.g., information indicating the above-described N4 or the upper layer parameter nroftimeinstance).

[0401] At step S920, the terminal reports the first CSI based on the first report setting.

[0402] The above first CSI is based on the above prediction.

[0403] For example, the first CSI may include i) a predicted channel state information-reference signal resource indicator (P-CRI), ii) a predicted SSB resource indicator (P-SSBRI), and / or iii) a predicted Layer 1-Reference Signal Received Power (P-L1-RSRP).

[0404] For example, the first CSI may include predicted CSI parameter(s) (e.g., P-CRI(s), P-SSBRI(s) and / or P-L1-RSRP(s)) based on a report quantity of the first report setting.

[0405] For example, the report quantity of the first report configuration can be set to p-cri, p-cri-RSRP, p-ssb-index or p-ssb-index-RSRP. p-cri represents a predicted channel state information-reference signal resource indicator (P-CRI). p-ssb-index represents a predicted SSB resource indicator (P-SSBRI). In p-cri-RSRP or p-ssb-index-RSRP, RSRP represents a predicted Layer 1-Reference Signal Received Power (P-L1-RSRP).

[0406] For example, the prediction may be performed based on a measurement. The measurement may be performed based on a resource configuration (e.g., CSI-ResourceConfig) associated with the first report configuration.

[0407] For example, the measurement may include Layer 1-Reference Signal Received Power (L1-RSRP) measurements. Based on the L1-RSRP measurements, i) at least one predicted channel state information-reference signal resource indicator (CSI-RS Resource Indicator, P-CRI), ii) at least one predicted SSB Resource Indicator (P-SSBRI), and / or iii) at least one predicted Layer 1-Reference Signal Received Power (P-L1-RSRP) may be determined.

[0408] More specifically, predictions can be made for CSI-RS resources or SSB resources associated with the second resource configuration based on the L1-RSRP measurements. Specifically, predicted L1-RSRPs of the CSI-RS resources or SSB resources associated with the second resource configuration can be determined. For example, best CRI(s) or best SSBRI(s) can be determined based on an order or ranking of the predicted L1-RSRPs. For example, predicted P-CRI(s) or predicted SSBRI(s) reported through the first CSI can be based on the best CRI(s) or the best SSBRI(s).

[0409] For convenience of explanation in this specification, the first CSI may represent predicted CSI.

[0410] At step S930, the terminal reports second CSI related to the prediction accuracy based on the second report setting.

[0411] For example, the second CSI may include information (e.g., RS-PAI) related to a time instance for monitoring among the one time instances. The monitoring may be related to the prediction accuracy.

[0412] For example, the second CSI may include i) a performance metric and / or ii) a performance monitoring output based on the performance metric.

[0413] As a specific example, the performance indicator may be based on an intermediate Key Performance Indicator (KPI) for evaluating the accuracy of the AI / ML output CSI. The intermediate KPI may be derived based on calculations of the Mean Squared Error (MSE), the Normalized Mean Squared Error (NMSE), the Mean Absolute Error (MAE), and / or the Squared Generalized Cosine Similarity (SGCS).

[0414] For example, the second CSI may include a CSI parameter (e.g., RS-PAI) based on the report quantity of the second report configuration. For example, the report quantity of the second report configuration may be set to rs-pai.

[0415] In one embodiment, the second CSI may include a Reference Signal-Prediction Accuracy Indicator (RS-PAI) that includes information related to the prediction accuracy for the prediction.

[0416] For example, a metric (RS-PAI) for monitoring may be determined based on a comparison of predicted CSI and ground-truth CSI. As a specific example, the RS-PAI may be determined based on whether CSI parameters (e.g., CRIs, SSBRIs) determined for the time instance for monitoring are mapped to at least one predicted CSI parameter (e.g., P-CRI(s) and / or P-SSBRI(s)) within the first CSI. As a specific example, the RS-PAI may be related to the number of CSI parameters among the determined CSI parameters that are mapped to the at least one predicted CSI parameter.

[0417] The above second CSI is based on channel measurements related to the second reporting settings.

[0418] As an example, the channel measurements may include calculation / measurement of ground-truth CSI.

[0419] For example, the ground-truth CSI may be based on channel measurements for monitoring related to the prediction accuracy of the predicted CSI.

[0420] As a concrete example, ground-truth CSI may be based on channel measurements for reporting related to the performance monitoring / prediction accuracy for predicted CSI.

[0421] More specifically, ground-truth CSI can be calculated / measured based on resource sets for the above channel measurements.

[0422] For example, the channel measurement may be performed based on a resource configuration (e.g., CSI-ResourceConfig) associated with the second reporting configuration.

[0423] For example, the channel measurements may include Layer 1-Reference Signal Received Power (L1-RSRP) measurements. The second CSI may be reported based on the L1-RSRP measurements.

[0424] More specifically, the prediction accuracy for the prediction can be determined based on the L1-RSRP measurements.

[0425] In one embodiment, an inference report (first CSI report) and a monitoring report (second CSI report) may be configured to be performed together. Specifically, the second report configuration may be linked to the first report configuration. The second report configuration may include information (e.g., a defined ID or inferenceReportConfigId) that links the report of the first CSI with the report of the second CSI. As a specific example, the configuration information may include first report configurations related to prediction and second report configurations related to prediction accuracy. Each second report configuration may be linked to one of the first report configurations based on the information (ID).

[0426] For example, the 1st / 2nd CSI can be interpreted / replaced with the 1st / 2nd CSI report.

[0427] The second CSI is reported based on i) a first time point associated with the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

[0428] In one embodiment, the first point in time may mean i) a prediction point in time of the first CSI, ii) a transmission point in time of the first CSI, and / or iii) a reception point in time of a reference resource related to the first CSI.

[0429] For example, the second CSI may be reported based on i) the prediction time of the first CSI and ii) the transmission time of the resource set.

[0430] For example, the second CSI may be reported based on i) the transmission time of the first CSI and ii) the transmission time of the resource set.

[0431] For example, the second CSI may be reported based on i) a reception time of the reference resource associated with the first CSI and ii) a transmission time of the resource set.

[0432] In one embodiment, the second CSI may be reported based on the first point in time that is closest to the transmission point in time of the resource set for the channel measurement.

[0433] For example, the second CSI may be reported based on the first point in time closest to the transmission point in time of the resource set for measurement of ground-truth CSI.

[0434] As a specific example, the second CSI may be reported based on the first time point having a minimum offset (e.g., minimum slot offset) from the transmission time point of the resource set for measurement of ground-truth CSI.

[0435] For example, the second CSI may be reported based on the first point in time closest to the point in time of reception of a reference signal for measuring ground-truth CSI.

[0436] For example, the second CSI may be reported based on the first CSI predicted at the closest point in time to the ground-truth CSI. This embodiment may be based on Proposal 1-1.

[0437] In one embodiment, the second CSI may be reported based on the prediction time of the first CSI being earlier than the time associated with the channel measurement. As a specific example, the second CSI may be reported based on the measurement / calculation time of the first ground-truth CSI being later than the first prediction instance. In this case, the first CSI may be predicted CSI predicted immediately before the transmission time of the resource set. For example, the first CSI may be predicted immediately before the reception time of a reference signal for measuring the ground-truth CSI. This embodiment may be based on Proposal 1-2.

[0438] In one embodiment, the second CSI may be reported based on a point in time related to the channel measurement being earlier than the predicted point in time of the first CSI. As a specific example, the second CSI may be reported based on a point in time of measurement / calculation of the first ground-truth CSI being earlier than the first prediction instance. In this case, the first CSI may be predicted immediately after the transmission point in time of the resource set. For example, the first CSI may be predicted immediately after the reception point of a reference signal for measuring the ground-truth CSI. This embodiment may be based on Proposal 1-2.

[0439] In one embodiment, the second CSI may include i) an average value of performance metrics for a plurality of predictions and / or ii) a weighted average value of the performance metrics.

[0440] For example, the above performance indicators may be calculated based on Proposal 1-1 and / or Proposal 1-2. The present embodiment may be based on Proposal 1-3.

[0441] In one embodiment, the channel measurement may be performed based on a CSI-RS for the channel measurement. In this case, the CSI-RS for the channel measurement may be received based on the prediction time and the transmission time.

[0442] As an example, the method may further include a step of transmitting information related to the prediction time and the transmission time to a base station.

[0443] For example, the information related to the prediction time and the transmission time may include i) information indicating a mismatch between the prediction time and the transmission time and / or ii) information regarding a difference between the prediction time and the transmission time.

[0444] As a specific example, information about the difference between the prediction time and the calculation time may include i) information about misaligned timing (timing advance / delaying) and / or information about the # of monitoring occasions. This embodiment may be based on Proposal 2.

[0445] In one embodiment, the prediction accuracy may be based on a preset or defined rank and / or layer.

[0446] For example, the terminal may perform performance monitoring using a specific rank and / or layer (e.g., rank / layer 1) determined separately / differently from the reported rank value. This embodiment may be based on Proposal 3-1.

[0447] In one embodiment, the first CSI may include a rank indicator (RI).

[0448] For example, the second CSI may include a weighted average value of performance indicators for each layer calculated based on the RI. This embodiment may be based on Proposal 3-2.

[0449] In one embodiment, the prediction may be based on the output of the model.

[0450] For example, the model may include a user equipment-sided model (UE-sided model).

[0451] The operations based on S910 to S930 described above can be implemented by the device of FIG. 11. For example, referring to FIG. 11, the terminal (200) can control one or more transceivers (230) and / or one or more memories (240) to perform the operations based on S910 to S930.

[0452] The embodiments described below are specifically described in terms of base station operation.

[0453] S1010 to S1030 described below correspond to S910 to S930 described in FIG. 9. Considering the above correspondence, redundant descriptions are omitted. The specific descriptions of base station operations described below may be replaced by the corresponding descriptions / exemplifications of FIG. 9.

[0454] FIG. 10 is a flowchart illustrating a method according to another embodiment of the present specification.

[0455] Referring to FIG. 10, a method according to another embodiment of the present specification includes a CSI-related setting information transmission step (S1010), a first CSI reception step (S1020), and a second CSI reception step (S1030).

[0456] In step S1010, the base station transmits configuration information related to channel state information (CSI).

[0457] The above configuration information includes i) a first reporting configuration related to prediction and ii) a second reporting configuration related to prediction accuracy.

[0458] At step S1020, the base station receives the first CSI based on the first report setting.

[0459] The above first CSI is based on the above prediction.

[0460] For example, the first CSI may include i) a predicted channel state information-reference signal resource indicator (P-CRI), ii) a predicted SSB resource indicator (P-SSBRI), and / or iii) a predicted Layer 1-Reference Signal Received Power (P-L1-RSRP).

[0461] For example, the above prediction can be performed based on measurements.

[0462] For example, the measurement may be performed based on resource settings associated with the first report settings.

[0463] At step S1030, the base station receives second CSI related to the prediction accuracy based on the second reporting settings.

[0464] The above second CSI is based on channel measurements related to the second reporting settings.

[0465] The second CSI is reported based on i) a first time point associated with the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

[0466] For example, the second CSI may include a Reference Signal-Prediction Accuracy Indicator (RS-PAI) that includes information related to the prediction accuracy for the prediction.

[0467] In one embodiment, the second CSI may be reported based on the first point in time that is closest to the transmission point in time of the resource set.

[0468] In one embodiment, the second CSI may be reported based on the prediction time of the first CSI being earlier than the transmission time of the resource set.

[0469] For example, the first CSI may be predicted immediately before the transmission time.

[0470] In one embodiment, the second CSI may be reported based on the transmission time of the resource set being earlier than the predicted time of the first CSI.

[0471] For example, the first CSI may be predicted immediately after the transmission time.

[0472] In one embodiment, the second CSI may include i) an average value of performance metrics for a plurality of predictions and / or ii) a weighted average value of the performance metrics.

[0473] In one embodiment, the channel measurement may be performed based on a CSI-RS for the channel measurement.

[0474] For example, the CSI-RS for the channel measurement can be received based on the prediction time and the transmission time.

[0475] As an example, the method may further include a step of transmitting information related to the prediction time and the transmission time to a base station.

[0476] For example, the information related to the prediction time and the transmission time may include i) information indicating a mismatch between the prediction time and the transmission time and / or ii) information regarding a difference between the prediction time and the transmission time.

[0477] In one embodiment, the prediction accuracy may be performed based on a preset or defined rank and / or layer.

[0478] In one embodiment, the first CSI may include a rank indicator (RI).

[0479] For example, the second CSI may include a weighted average value of performance indicators for each layer calculated based on the RI.

[0480] In one embodiment, the prediction may be based on the output of the model.

[0481] For example, the model may include a user equipment-sided model (UE-sided model).

[0482] The operations based on S1010 to S1030 described above can be implemented by the device of FIG. 11. For example, referring to FIG. 11, the base station (100) can control one or more transceivers (130) and / or one or more memories (140) to perform the operations based on S1010 to S1030.

[0483] The operations / terms based on the embodiments described above have been described assuming a 5G system. However, this is for convenience of explanation and is not intended to limit the scope of application of the technical problems and problem-solving means to be solved by this specification to a specific system. The technical problems / technical issues / problems mentioned in this specification may equally exist in other systems (e.g., 6G systems). It is self-evident that the embodiments of this specification can be expanded and applied to solve problems equally existing in the other systems. Therefore, for the expanded application of the embodiments of this specification to other systems, the terms defined / described based on the 5G system may be replaced / changed with terms defined in the other systems (or generalized terms not specific to one system). For example, PRACH, PUSCH, PUCCH, or SRS may be replaced / changed with uplink signals (or uplink channels). For example, SSB, CSI-RS, PDSCH, and PDCCH may be replaced / changed with downlink signals (or downlink channels).

[0484] Hereinafter, a device to which an embodiment of the present specification can be applied (a device that implements a method / operation according to an embodiment of the present specification) is described with reference to FIG. 9.

[0485] FIG. 11 is a drawing showing the configuration of a first device and a second device according to an embodiment of the present specification.

[0486] The first device (100) may include a processor (110), an antenna unit (120), a transceiver (130), and a memory (140).

[0487] The processor (110) performs baseband-related signal processing and may include a higher layer processing unit (111) and a physical layer processing unit (115). The higher layer processing unit (111) may process operations of a MAC layer, an RRC layer, or higher layers. The physical layer processing unit (115) may process operations of a PHY layer. For example, when the first device (100) is a base station device in base station-terminal communication, the physical layer processing unit (115) may perform uplink reception signal processing, downlink transmission signal processing, etc. For example, when the first device (100) is a first terminal device in terminal-to-terminal communication, the physical layer processing unit (115) may perform downlink reception signal processing, uplink transmission signal processing, sidelink transmission signal processing, etc. In addition to performing baseband-related signal processing, the processor (110) may also control the overall operation of the first device (100).

[0488] The antenna unit (120) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO transmission and reception. The transceiver (130) may include an RF (Radio Frequency) transmitter and an RF receiver. The memory (140) may store information processed by the processor (110), and software, an operating system, applications, etc. related to the operation of the first device (100), and may also include components such as a buffer.

[0489] The processor (110) of the first device (100) may be configured to implement the operation of the base station in the base station-to-terminal communication (or the operation of the first terminal device in the terminal-to-terminal communication) in the embodiments described in the present disclosure.

[0490] The second device (200) may include a processor (210), an antenna unit (220), a transceiver (230), and a memory (240).

[0491] The processor (210) performs baseband-related signal processing and may include a higher layer processing unit (211) and a physical layer processing unit (215). The higher layer processing unit (211) may process operations of a MAC layer, an RRC layer, or higher layers. The physical layer processing unit (215) may process operations of a PHY layer. For example, when the second device (200) is a terminal device in base station-terminal communication, the physical layer processing unit (215) may perform downlink reception signal processing, uplink transmission signal processing, etc. For example, when the second device (200) is a second terminal device in terminal-to-terminal communication, the physical layer processing unit (215) may perform downlink reception signal processing, uplink transmission signal processing, sidelink reception signal processing, etc. In addition to performing baseband-related signal processing, the processor (210) may also control the overall operation of the second device (210).

[0492] The antenna unit (220) may include one or more physical antennas, and when it includes multiple antennas, it may support MIMO transmission and reception. The transceiver (230) may include an RF transmitter and an RF receiver. The memory (240) may store information processed by the processor (210), software, an operating system, applications, etc. related to the operation of the second device (200), and may also include components such as a buffer.

[0493] The processor (210) of the second device (200) may be configured to implement operations of the terminal in base station-to-terminal communication (or operations of the second terminal device in terminal-to-terminal communication) in the embodiments described in the present disclosure.

[0494] In the operation of the first device (100) and the second device (200), the same explanations given for the base station and the terminal (or the first terminal and the second terminal in the terminal-to-terminal communication) in the examples of the present disclosure may be applied, and redundant explanations are omitted.

[0495] Here, the wireless communication technology implemented in the device of the present disclosure may include LTE, NR, and 6G, as well as Narrowband Internet of Things (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology and may be implemented in standards such as LTE Cat NB1 and / or LTE Cat NB2, and is not limited to the above-described names.

[0496] Additionally or alternatively, the wireless communication technology implemented in the device of the present disclosure may perform communication based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology and may be called by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology may be implemented by at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the above-described names.

[0497] Additionally or alternatively, the wireless communication technology implemented in the device of the present disclosure may include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN), which take low-power communication into account, and is not limited to the above-described names. For 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 called by various names.

Claims

1. In the method, A step of receiving configuration information related to channel state information (CSI), the configuration information including i) a first report configuration related to prediction and ii) a second report configuration related to prediction accuracy; A step of reporting a first CSI based on the first report setting; and A step of reporting a second CSI related to the prediction accuracy based on the second report setting; The above first CSI is based on the above prediction, The above second CSI is based on channel measurements related to the second reporting settings, A method, characterized in that the second CSI is reported based on i) a first time point related to the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

2. In paragraph 1, A method, characterized in that the first CSI comprises i) a predicted channel state information-reference signal resource indicator (P-CRI), ii) a predicted SSB resource indicator (P-SSBRI), and / or iii) a predicted Layer 1-Reference Signal Received Power (L1-RSRP).

3. In paragraph 1, The above predictions are made based on measurements, A method, characterized in that the above measurement is performed based on resource settings related to the first report settings.

4. In paragraph 1, A method, characterized in that the second CSI includes a Reference Signal-Prediction Accuracy Indicator (RS-PAI) that includes information related to the prediction accuracy for the prediction.

5. In paragraph 1, A method characterized in that the second CSI is reported based on the first point in time that is closest to the transmission point in time of the resource set.

6. In paragraph 5, The second CSI is reported based on the prediction time of the first CSI being earlier than the time associated with the channel measurement, A method, characterized in that the first CSI is predicted immediately before the transmission time of the resource set.

7. In paragraph 5, The second CSI is reported based on the point in time associated with the channel measurement being earlier than the predicted point in time of the first CSI, A method, characterized in that the first CSI is predicted immediately after the transmission time of the resource set.

8. In paragraph 5, A method, characterized in that the second CSI comprises i) an average value of performance metrics for a plurality of predictions and / or ii) a weighted average value of the performance metrics.

9. In paragraph 1, The above channel measurement is performed based on the CSI-RS for the above channel measurement, A method, characterized in that the CSI-RS for the channel measurement is received based on the prediction time and the transmission time.

10. In paragraph 9, A method, characterized in that it further comprises a step of transmitting information related to the prediction time and the transmission time to a base station.

11. In paragraph 10, A method, characterized in that the information related to the prediction time and the transmission time includes i) information indicating a mismatch between the prediction time and the transmission time and / or ii) information regarding a difference between the prediction time and the transmission time.

12. In paragraph 1, A method, wherein the above prediction accuracy is based on a preset or defined rank and / or layer.

13. In paragraph 1, The above first CSI includes a rank indicator (RI), A method characterized in that the second CSI includes a weighted average value of performance indicators for each layer calculated based on the RI.

14. In paragraph 1, A method, characterized in that the second report setting is linked to the first report setting.

15. At the terminal, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A terminal, characterized in that the instructions, based on being executed by the one or more processors, cause the terminal to perform all steps of the method according to any one of claims 1 to 14.

16. In a device comprising one or more memories and one or more processors connected to the one or more memories, A device characterized in that said one or more memories store instructions that cause said device to perform all steps of a method according to any one of claims 1 to 14, based on being executed by said one or more processors.

17. In a non-transitory computer-readable medium storing instructions, A non-transitory computer-readable medium, characterized in that the instructions executable by one or more processors cause a terminal to perform all steps of a method according to any one of claims 1 to 14.

18. In the method, A step of transmitting configuration information related to channel state information (CSI), wherein the configuration information includes i) a first report configuration related to prediction and ii) a second report configuration related to prediction accuracy; A step of receiving a first CSI based on the first report setting; and A step of receiving a second CSI related to the prediction accuracy based on the second report setting; including; The above first CSI is based on the above prediction, The above second CSI is based on channel measurements related to the second reporting settings, A method characterized in that the second CSI is reported based on i) a prediction time of the first CSI and ii) a transmission occasion of a resource set for the channel measurement.

19. At the base station, One or more transmitters and receivers; one or more processors; and One or more memories connected to said one or more processors and storing instructions, A base station, characterized in that the instructions, based on being executed by the one or more processors, cause the base station to perform all steps of the method according to claim 18.

Images