Method and apparatus for beam reporting in wireless communication system

Abstract

A method performed by a terminal in a wireless communication system according to an embodiment of the present disclosure comprises the steps of: receiving configuration information related to channel state information (CSI); receiving at least one downlink reference signal (DL RS); calculating CSI on the basis of the measurement for the at least one DL RS; and reporting the CSI. The configuration information includes information related to the beams of the first set. The at least one DL RS is based on a first DL RS associated with the beams of the first set. The CSI includes information related to at least one beam in a second set related to the first set.

Description

Technical Field

[0001] The present disclosure relates to methods and apparatus for beam reporting in a wireless communication system. Background Art

[0002] In order to provide voice services while ensuring user activities, a mobile communication system has been developed. However, the area of ​​the mobile communication system has been expanded to data services in addition to voice. Due to the current explosive increase in traffic, resource shortages have occurred, so users need higher-speed services. Therefore, a more advanced mobile communication system is needed.

[0003] The requirements for next generation mobile communication systems need to be able to support the accommodation of explosive data traffic, a significant increase in data rates per user, an accommodation of a significant increase in the number of connected devices, very low end-to-end latency, and high energy efficiency. To this end, various technologies have been studied, such as dual connectivity, massive multiple-input multiple-output (MIMO), in-band full-duplex, non-orthogonal multiple access (NOMA), ultra-wideband support, and device networking.

[0004] Regarding beam management, set A and set B are defined. Specifically, according to BM-Case 1, the UE estimates / determines the beam of set A (e.g., the preferred beam among the beams of set A) based on the measurement of the beam of set B (e.g., the measurement of the RS related to the beam of set B). Summary of the invention

[0005] Technical issues

[0006] According to the existing beam measurement and reporting method, the UE measures and reports the received power or quality without knowing the information of the corresponding beam (e.g., absolute / relative beam angle, beam shape, etc.). In the existing method, because the information given to the UE is limited, it may be difficult to perform beam prediction based on the above BM-Case 1, or the accuracy of the beam prediction may be low.

[0007] The purpose of the present disclosure is to provide a method for supporting beam estimation / prediction operations based on the above-mentioned BM-Case 1.

[0008] The technical objectives of the present disclosure are not limited to the above-mentioned technical objectives, and other technical objectives not mentioned above will be obviously understood by ordinary technicians in the art from the following description.

[0009] Technical Solution

[0010] According to an embodiment of the present disclosure, a method performed by a user equipment in a wireless communication system includes: receiving configuration information related to channel state information (CSI); receiving at least one downlink reference signal (DL RS); calculating CSI based on measurement of at least one DL RS; and reporting CSI.

[0011] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0012] The second DL RS associated with the second set of beams may include the first DL RS.

[0013] The second DL RS associated with the second set of beams may be different from the first DL RS.

[0014] The beamwidth associated with the second set of beams may be narrower than the beamwidth associated with the first set of beams.

[0015] A quasi co-location (QCL) relationship may be configured between the second DL RS and the first DL RS.

[0016] The configuration information may include angle information associated with the first set of beams.

[0017] The CSI may include information for at least one of the following items: i) one or more first DL RSs among the first DL RSs, ii) one or more linear combination coefficients related to the one or more first DL RSs, and / or iii) one or more beam quality values ​​related to the one or more first DL RSs.

[0018] The configuration information may include coordinate information associated with the first set of beams. The coordinate information may include coordinates of the first DLRS within the beam grid.

[0019] The second DL RS associated with the second set of beams may be associated with beams that can be represented based on a beam grid.

[0020] The CSI may include information on at least one of the following items: i) one or more coordinates associated with one or more of the second DL RSs, and / or ii) one or more beam quality values ​​associated with the one or more second DL RSs.

[0021] In the CSI, the payload size for each of the one or more second DL RSs may be different. The payload size for each of the one or more second DL RSs may be related to a coordinate range determined based on a ranking of the one or more beam quality values.

[0022] The coordinate range determined for a specific second DL RS among one or more second DL RSs can be i) the entire coordinate range of the beam grid, or ii) a range determined based on coordinates related to a second DL RS preceding the specific second DL RS in the sorting of one or more beam quality values.

[0023] According to another embodiment of the present disclosure, a user equipment operating in a wireless communication system includes one or more transceivers, one or more processors, and one or more memories, wherein the one or more memories are operably connected to the one or more processors and store instructions, and the instructions configure the one or more processors to perform operations based on being executed by the one or more processors.

[0024] The operations include: receiving configuration information related to channel state information (CSI); receiving at least one downlink reference signal (DL RS); calculating the CSI based on measurements for the at least one DL RS; and reporting the CSI.

[0025] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0026] According to another embodiment of the present disclosure, an apparatus includes one or more memories and one or more processors operatively connected to the one or more memories. The one or more memories include instructions that configure the one or more processors to perform operations based on being executed by the one or more processors.

[0027] The operations include: receiving configuration information related to channel state information (CSI); receiving at least one downlink reference signal (DL RS); calculating the CSI based on measurements for the at least one DL RS; and reporting the CSI.

[0028] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0029] One or more non-transitory computer-readable media according to another embodiment of the present disclosure stores one or more instructions. The one or more instructions executable by one or more processors configure the one or more processors to perform operations.

[0030] The operations include: receiving configuration information related to channel state information (CSI); receiving at least one downlink reference signal (DL RS); calculating the CSI based on measurements for the at least one DL RS; and reporting the CSI.

[0031] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0032] A method performed by a base station in a wireless communication system according to another embodiment of the present disclosure includes: transmitting configuration information related to channel state information (CSI); transmitting at least one downlink reference signal (DL RS); and receiving the CSI.

[0033] The CSI is calculated based on measurements of at least one DL RS.

[0034] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0035] According to another embodiment of the present disclosure, a base station operating in a wireless communication system includes one or more transceivers, one or more processors, and one or more memories, which are operably connected to the one or more processors and store instructions, and the instructions configure the one or more processors to perform operations based on being executed by the one or more processors.

[0036] The operations include: sending configuration information related to channel state information (CSI); sending at least one downlink reference signal (DL RS); and receiving the CSI.

[0037] The CSI is calculated based on measurements of at least one DL RS.

[0038] The configuration information includes information related to the first set of beams. The at least one DL RS is based on the first DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set.

[0039] Beneficial Effects

[0040] According to an embodiment of the present disclosure, information related to a first set of beams is configured, and the UE reports CSI calculated based on measurement of a DL RS related to the first set of beams. The CSI includes information related to at least one beam in a second set related to the first set. Based on the information related to the first set of beams, a relationship between the first set of beams being measured (set B) and the second set of beams being reported (set A) can be determined.

[0041] Therefore, the beam estimation / prediction operation based on the above-mentioned BM-Case 1 can be supported. Since the beam is estimated / determined in units more accurate than the beam sent by the base station (the beam measured by the UE), the accuracy of beam management can be improved without increasing RS overhead compared to the existing method.

[0042] Effects that can be obtained by the present disclosure are not limited to the above-described effects, and other technical effects not described above can be clearly understood by ordinary technicians in the field to which the present disclosure belongs according to the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 An example of beamforming using SSB and CSI-RS is illustrated.

[0044] Figure 2 is a flow chart illustrating an example of a DL BM procedure using SSB.

[0045] Figure 3 Illustrate the functional framework of AI / ML models.

[0046] Figure 4 A signaling process according to an embodiment of the present disclosure is illustrated.

[0047] Figure 5 is a flowchart illustrating a method performed by a user equipment according to an embodiment of the present disclosure.

[0048] Figure 6 is a flowchart illustrating a method performed by a base station according to another embodiment of the present disclosure.

[0049] Figure 7 The configurations of the first device and the second device according to the embodiment of the present disclosure are illustrated. DETAILED DESCRIPTION

[0050] The following will be attached Figure 1The detailed description disclosed above will describe exemplary embodiments of the present disclosure, rather than describing unique embodiments for performing the present disclosure. The following detailed description includes details that provide a complete understanding of the present disclosure. However, those skilled in the art will appreciate that the present disclosure may be performed without these details.

[0051] In some cases, in order to prevent the concepts of the present disclosure from being obscure, known structures and devices may be omitted, or may be illustrated in a block diagram format based on the core functions of each structure and device.

[0052] In the following, downlink (DL) means communication from a base station to a terminal, and uplink (UL) means communication from a terminal to a base station. In the downlink, the transmitter may be part of a base station, and the receiver may be part of a terminal. In the uplink, the transmitter may be part of a terminal, and the receiver may be part of a base station. The base station may be represented as a first communication device, and the terminal may be represented as a second communication device. The base station (BS) may be replaced with terms including a fixed station, a node B, an evolved node B (eNB), a next generation node B (gNB), a base transceiver system (BTS), an access point (AP), a network (5G network), an AI system, a roadside unit (RSU), a vehicle, a robot, an unmanned aerial vehicle (UAV), an AR (augmented reality) device, a VR (virtual reality) device, and the like. In addition, the terminal may be fixed or mobile, and may be replaced by terms including user equipment (UE), mobile station (MS), user terminal (UT), mobile subscriber station (MSS), subscriber station (SS), advanced mobile station (AMS), wireless terminal (WT), machine type communication (MTC) device, machine-to-machine (M2M) device and device-to-device (D2D) device, vehicle, robot, AI module, unmanned aerial vehicle (UAV), AR (augmented reality) device, VR (virtual reality) device, etc.

[0053] Beam Management (BM)

[0054] The BM process, which is a Layer 1 (L1) / Layer 2 (L2) process for acquiring and maintaining a set of base station (e.g., gNB, TRP, etc.) and / or terminal (e.g., UE) beams that can be used for downlink (DL) and uplink (UL) transmission / reception, may include the following processes and terms.

[0055] - Beam measurement: The operation of measuring the characteristics of a beamforming signal received by an eNB or UE.

[0056] -Beam determination: The operation of selecting the transmit (Tx) beam / receive (Rx) beam of the eNB or UE by the eNB or UE.

[0057] - Beam scanning: The operation of covering a spatial area using transmit and / or receive beams for time intervals by a predetermined scheme.

[0058] -Beam reporting: An operation in which the UE reports information of beamformed signals based on beam measurements.

[0059] The BM process may be divided into (1) a DL BM process using a synchronization signal (SS) / physical broadcast channel (PBCH) block or a CSI-RS and (2) a UL BM process using a sounding reference signal (SRS).

[0060] In addition, each BM process may include Tx beam scanning for determining a Tx beam and Rx beam scanning for determining an Rx beam.

[0061] DL BM

[0062] The DL BM process may include (1) transmission of a beamforming DL reference signal (RS) (eg, CSI-RS or SS block (SSB)) by the eNB and (2) beam reporting by the UE.

[0063] Here, the beam report includes a preferred DL RS identifier (ID) and an L1 reference signal received power (RSRP) corresponding to the preferred DL RS identifier (ID).

[0064] The DL RS ID may be a SSB resource indicator (SSBRI) or a CSI-RS resource indicator (CRI).

[0065] Figure 1 An example of beamforming using SSB and CSI-RS is illustrated.

[0066] like Figure 1 As shown, SSB beams and CSI-RS beams can be used for beam management. The measurement metric is L1-RSRP for each resource / block. SSB can be used for coarse beam management, and CSI-RS can be used for fine beam management. SSB can be used for both Tx beam scanning and Rx beam scanning.

[0067] Rx beam scanning using SSB may be performed when the UE changes the Rx beam for the same SSBRI across multiple SSB bursts. Here, one SS burst includes one or more SSBs, and one SS burst set includes one or more SSB bursts.

[0068] Figure 2 is a flow chart illustrating an example of a DL BM procedure using SSB.

[0069] Configuration of beam reporting using SSB is performed during CSI / beam configuration in the RRC connected state (or RRC connected mode).

[0070] - The UE receives a CSI-ResourceConfig IE including a CSI-SSB-ResourceSetList including SSB resources for a BM from the eNB (S210).

[0071] Table 1 shows an example of the CSI-ResourceConfig IE. As shown in Table 1, a BM configuration using SSB is not separately defined, and SSB is configured similarly to a CSI-RS resource.

[0072] [Table 1]

[0073]

[0074] In Table 1, the csi-SSB-ResourceSetList parameter represents a list of SSB resources in a resource set for beam management and reporting. Here, the SSB resource set can be configured as {SSBx1, SSBx2, SSBx3, SSBx4, ...}. For example, the SSB index can be defined as 0 to 63.

[0075] -The UE receives SSB resources from the eNB based on the CSI-SSB-ResourceSetList (S220).

[0076] - When CSI-reportConfig associated with reporting of SSBRI and L1-RSRP is configured, the UE (beam) reports the best SSBRI and L1-RSRP corresponding thereto to the eNB (S230).

[0077] In other words, when reportQuantity of CSI-reportConfig IE is configured as "ssb-Index-RSRP", the UE reports the best SSBRI and L1-RSRP corresponding thereto to the eNB.

[0078] In addition, when CSI-RS resources are configured in the same OFDM symbol as SSB (SS / PBCH block) and "QCL-Type D" is applicable, the UE can assume that the CSI-RS and SSB are quasi-co-located from the perspective of "QCL-Type D".

[0079] Here, QCL TypeD may mean that the antenna port is QCL from the perspective of spatial Rx parameters. When the UE receives multiple DL antenna ports with a QCL TypeD relationship, the same Rx beam may be applied. In addition, the UE does not expect the CSI-RS to be configured in REs that overlap with REs of SSB.

[0080] BM enhancement in NR Rel-16

[0081] The DL / UL beam indication standardized in 3GPP NR Rel-15 has been designed to indicate the beam used for each DL / UL channel / RS resource separately to ensure beam indication flexibility, and the indication method has been designed separately for each channel / RS.

[0082] This design direction ultimately has the following problems: the base station must indicate the beam change for each channel / RS resource to multiple UEs communicating with the base station using a single beam in order to change the serving beam for multiple UEs, which results in large signaling overhead and large beam change delay. With the UL beam change, UL power control related parameters, especially path loss RS (PL RS), must be changed for each UL channel / RS, which also results in signaling overhead / delay problems. In order to compensate for these shortcomings, five features are introduced in Rel-16. The following Table 2 shows these five features.

[0083] [Table 2]

[0084]

[0085]

[0086] In Rel-16, in addition to the above-mentioned enhancements related to beam / PL RS indication, enhancements related to beam reporting are also made. In Rel-15, a mode in which the UE measures / reports L1-RSRP for each beam RS is supported. However, in an environment with high inter-beam interference, it is difficult to ensure that a specific beam RS has good quality as a serving beam simply because the L1-RSRP (i.e., the received strength of a specific beam RS) is high. In other words, the UE may select a beam with high received strength but high beam interference, and report the beam to the base station. To overcome this shortcoming, Rel-16 supports a new beam reporting mode in which the base station configures resources for interference measurement and RS for channel measurement, and the UE measures L1-SINR for channel resources and interference resources based on this, and reports several RSs with high L1-SINR values.

[0087] BM enhancement in NR Rel-17

[0088] As mentioned above, various BM enhancements were made in Rel-16. Specifically, features were created that can significantly reduce the signaling overhead / latency associated with the beam indication method. However, there is still no configuration / indication channel / RS unified beam for UEs operating with a single serving beam.

[0089] Based on this motivation, Rel-17 will standardize the channel / RS unified beam configuration / indication method. In NR, the DL beam is indicated by sending a configuration indicator (TCI), so it is called a unified TCI state. The existing TCI state is configured / indicated separately for each DLRS / channel, but the unified TCI state is characterized by a unified configuration / indication. Basically, the DL unified TCI state indicates that the QCL type-D RS is uniformly applied to (some) PDCCH, PDSCH and (some) CSI-RS resources, and the UL unified TCI state indicates that the spatial relationship RS (and PL RS) of (some) PUCCH, PUSCH and (some) SRS is uniformly applied. For UEs that have established beam correspondence, since the UL spatial relationship and PL RS can also be matched with the DL beam RS in the same way as the Rel-16 default spatial relationship / PLRS feature, the channel / RS to which the unified TCI state is applied can cover both DL channels / RS and UL channels / RS. This is called a joint DL / UL TCI state. That is, the following two modes will be supported.

[0090] -Joint DL / UL TCI configuration / indication mode: The DL RS configured / indicated in the joint TCI state can be applied not only as a QCL type-D RS for the DL channel / RS, but also as a spatial relationship RS (and PLRS) for the UL channel / RS. That is, if an update to the joint TCI state is indicated, the beam RS (or / and PL RS) for the DL channel / RS and the UL channel / RS can be changed together.

[0091] -Separate DL and UL TCI configuration / indication mode: QCL type-D source RS for DL ​​channels / RS is unified and configured / indicated by DL TCI state, and spatial relationship RS (and PL RS) for UL channels / RS is unified and configured / indicated by UL TCI state. DL TCI state and UL TCI state are configured / indicated separately.

[0092] The DL / UL / joint TCI state will be indicated / updated via MAC-CE and / or DCI. More specifically, one or more TCI states (referred to as a TCI state pool) among the multiple TCI states configured by RRC are activated by MAC-CE. If multiple TCI states are activated by MAC-CE, one of the multiple TCI states is indicated by DCI.

[0093] DCI indication will be supported via downlink DCI formats (DCI1-1 / 1-2) that support the TCI field, and will be supported in both cases with and without PDSCH scheduling. In the latter case, since PDSCH scheduling is omitted (similar to the DCI-based semi-persistent scheduling (SPS) release method), UE ACK transmission for the corresponding DCI will be supported.

[0094] Enhancements related to beam reporting will be made in Rel-17. The Rel-17 beam reporting mode will support a mode in which the UE measures / reports the best beam RS for each TRP, targeting a multi-TRP environment. To this end, if the beam measurement RS set / group is divided into two subsets / subgroups and the base station configures them, the UE will select RS for each subset / subgroup and report them together with the quality value of the corresponding RS (L1-RSRP, [L1-SINR]).

[0095] AIML related description

[0096] With the technological advancement of artificial intelligence / machine learning (AI / ML), the nodes and UEs that constitute wireless communication networks are becoming more and more intelligent / advanced.

[0097] In particular, due to the intelligence of the network / base station, it is expected that various network / base station decision parameters can be quickly optimized and derived / applied based on various environmental parameters.

[0098] The environmental parameters may include at least one of the distribution / location of base stations, the distribution / location / material of buildings / furniture, the location / moving direction / speed of UE, or climate information. However, the above parameters are only examples, and in addition to the listed parameters, the environmental parameters may also include other environmental parameters related to the network / base station decision parameters.

[0099] The network / base station decision parameters may include at least one of the transmit / receive power of each base station (BS), the transmit power of each UE, the precoder / beam of the BS / UE, the time / frequency resource allocation for each UE, or the duplex method of each BS. However, the above parameters are only examples, and in addition to the listed parameters, the network / base station decision parameters may also include other parameters determined by the network / base station.

[0100] In line with this trend, many standardization organizations (e.g., 3GPP, O-RAN) are considering the introduction of AI / ML, and related research is also actively underway.

[0101] In a narrow sense, AI / ML can be simply referred to as artificial intelligence based on deep learning, but conceptually, it can be classified as follows.

[0102] -Artificial Intelligence: It is any automation that allows machines to do work that would otherwise be done by humans.

[0103] -Machine Learning: It refers to a technology in which machines learn patterns for decision making from data by themselves without explicit programming rules.

[0104] - Deep learning: It is a model based on artificial neural networks and allows machines to perform feature extraction and decision making based on unstructured data simultaneously. The algorithm depends on a multi-layer network composed of interconnected nodes for feature extraction and transformation, which is inspired by biological nervous systems (i.e., neural networks). Common deep learning network architectures include deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0105] As described above, artificial intelligence (AI) is the broadest concept of AI / ML, and deep learning is the narrowest concept of AI / ML. Machine learning (ML) can be explained as a concept narrower than artificial intelligence and broader than deep learning.

[0106] Types of AI / ML based on various criteria

[0107] - Offline and online

[0108] Offline learning

[0109] -Offline learning faithfully follows the sequential process of database collection, learning, and prediction. That is, collection and learning can be performed offline, and the completed program can be installed on site and used for prediction work. In most cases, this offline learning method is used.

[0110] Online Learning

[0111] - Online learning refers to a method that gradually improves performance by performing incremental learning using additional data generated, taking advantage of the fact that data that can be used for recent learning is continuously generated via the Internet.

[0112] Classification based on AI / ML framework concepts

[0113] -Focused learning

[0114] In centralized learning, all data resources / storage / learning (e.g., supervised learning, unsupervised learning, reinforcement learning, etc.) are performed in one centralized node while training data collected from multiple different nodes is reported to the centralized node.

[0115] - Federated Learning

[0116] Federated learning is built on data where there is a collective model across distributed data owners. Instead of collecting data into the model, the AI / ML model is imported into the data source, allowing local nodes / individual devices to collect data and train their own copy of the model, thus eliminating the need to report source data to a centralized node.

[0117] In federated learning, the parameters / weights of the AI / ML model are sent again to the centralized node to support general model training. Federated learning has advantages in terms of computing speed and improvement of information security. That is, the process of uploading personal data to the central server is unnecessary, and the leakage and misuse of personal information can be prevented.

[0118] -Distributed learning

[0119] Distributed learning refers to the concept of scaling and distributing the machine learning process across a cluster of nodes. The trained model is shared across multiple nodes, which are split and operated simultaneously to accelerate model training.

[0120] Classification by learning method

[0121] -Supervised Learning

[0122] Supervised learning is a machine learning task that aims to learn a mapping function from input to output given a labeled dataset. The input data is called training data and has known labels or outcomes. An example of supervised learning is as follows.

[0123] 1) Regression: linear regression, logistic regression

[0124] 2) Instance-based algorithm: k-nearest neighbor (KNN)

[0125] 3) Decision Tree Algorithm: CART

[0126] 4) Support Vector Machine: SVM

[0127] 5) Bayesian algorithm: Naive Bayes

[0128] 6) Ensemble algorithms: Extreme Gradient Boosting, Bagging: Random Forest

[0129] Supervised learning can be further grouped into regression and classification problems, where classification is predicting a label and regression is predicting a quantity.

[0130] - Unsupervised learning

[0131] Unsupervised learning is a machine learning task that aims to learn a function that describes the hidden structure in unlabeled data. The input data is not labeled and there is no known outcome. Some examples of unsupervised learning include K-means clustering, principal component analysis (PCA), nonlinear independent component analysis (ICA), and long short-term memory (LSTM).

[0132] - Reinforcement Learning

[0133] In reinforcement learning (RL), an agent aims to optimize a long-term goal by interacting with the environment based on a trial-and-error process, and is goal-oriented learning based on interaction with the environment. Examples of RL algorithms are as follows.

[0134] 1) Q-Learning

[0135] 2) Bandit learning

[0136] 3) Deep Q Network

[0137] 4) State-Action-Reward-State-Action (SARSA)

[0138] 5) Time difference learning

[0139] 6) Executor-Critic Reinforcement Learning

[0140] 7) Deep Deterministic Policy Gradient

[0141] 8) Monte Carlo Tree Search

[0142] Reinforcement learning can be additionally grouped into model-based reinforcement learning and model-free reinforcement learning.

[0143] Model-based reinforcement learning: It refers to RL algorithms that use a predictive model and use the various dynamic states of the environment and the model in which these states bring rewards to derive the transition probabilities between states.

[0144] Model-free reinforcement learning: It refers to RL algorithms based on values ​​or policies that achieve maximum future rewards. The multi-agent environment / state is less computationally complex and does not require an accurate representation of the environment.

[0145] RL algorithms can also be classified into value-based RL and policy-based RL, policy-based RL and non-policy RL, etc.

[0146] Representative models of deep learning

[0147] 1. Feedforward Neural Network (FFNN)

[0148] FFNN consists of an input layer, a hidden layer, and an output layer.

[0149] 2. Recurrent Neural Network (RNN)

[0150] RNN is a type of artificial neural network in which hidden nodes are connected to directed edges to form a directed loop. It is a model suitable for processing sequentially occurring data such as speech and text.

[0151] 3. Convolutional Neural Network (CNN)

[0152] CNN is used for two purposes: reducing model complexity and extracting good features by applying convolution operations generally used in the fields of video processing or image processing.

[0153] - Kernel or Filter: It refers to a unit / structure that applies weights to the input of a specific range / unit.

[0154] - Stride size: It refers to the range of movement of the kernel within the input.

[0155] -Feature map: It refers to the result of applying the kernel to the input.

[0156] -Padding: It refers to the value that is added to resize the feature map.

[0157] - Pooling: It refers to the operation of reducing the size of feature maps by downsampling them (e.g., max pooling, average pooling).

[0158] 4. Autoencoder

[0159] An autoencoder is a neural network that receives a feature vector x as input and outputs the same or a similar vector x'. The input nodes and output nodes of the autoencoder have the same features.

[0160] Figure 3 Illustrate the functional framework of AI / ML models.

[0161] exist Figure 3 In the functional framework shown, the definition of each term and the operation of each function can be based on the following Table 3.

[0162] [Table 3]

[0163]

[0164]

[0165] Dataset

[0166] The datasets used in AI / ML are classified into training data, validation data, and test data, and their definitions are as follows.

[0167] - Training data

[0168] Dataset used to train the model

[0169] - Verify data

[0170] Dataset used to validate the trained model

[0171] Validation data is a dataset that is often used to prevent overfitting of the training dataset.

[0172] Validation data is a data set used to select the best model among the various models trained during the training process. Therefore, validation data can be considered as a data set related to training.

[0173] -Test data

[0174] The test data is the dataset used for final evaluation. The test data is independent of the training data.

[0175] The data set may use a training set including the above data in a predetermined proportion.

[0176] For example, a training set including training data and validation data in a ratio of 8:2 or 7:3 may be used.

[0177] For example, a training set including training data, validation data, and test data in a ratio of 6:2:2 may be used.

[0178] Collaboration Level

[0179] Depending on whether the AI / ML function between the base station and the UE is capable, the collaboration level can be defined as follows.

[0180] [Table 4]

[0181]

[0182] The collaboration levels shown in Table 4 are examples and may be modified and utilized differently from the illustrated examples based on implementation methods. For example, a collaboration level combining two or more of the illustrated collaboration levels may be defined / utilized. For example, a collaboration level that does not include one or more of the illustrated collaboration levels may be utilized.

[0183] Figure 4 A signaling process according to an embodiment of the present disclosure is illustrated.

[0184] More specifically, Figure 4 An example of signaling between a user equipment (UE) and a network (NW) based on the above-mentioned methods (eg, method 1, method 2) is illustrated.

[0185] UE / NW are merely examples and may be replaced with various devices as described above. Figure 4 It is only for the convenience of explanation and does not limit the scope of the present disclosure. In addition, depending on the situation and / or setting, it can be omitted. Figure 4 Some of the steps are illustrated in Figure 4 In the present invention, NW may correspond to any entity belonging to a network, such as a base station (BS), a Node B, or a TRP.

[0186] In S405, the UE may report UE capability information to the NW. The UE capability information may include information related to the UE AI / ML model (training / inference), and report information on whether beam prediction is possible.

[0187] In S410, the UE may receive a configuration related to set B (and set A) from the NW. The configuration may include ID information for the beam, transmission period and time / frequency position information, sequence information, information about the relationship between RSs (e.g., whether there is a QCL), beam angle information, beam width information, and beam grid related information.

[0188] After the beam-related configuration in S410, in S415, the base station may send a beam RS belonging to set B to the UE, and the UE may perform measurement on the beam RS.

[0189] The UE performing beam-related configuration (S410) and measurement of the set B beams may select a preferred beam based on the configuration and the measurement values. In S420, the AI / ML of the UE may be utilized / applied in the process.

[0190] Subsequently, in S425, the UE may send information to the NW on the selected beam by applying the information to the proposed method (eg, method 1, method 2).

[0191] The above NW / UE signaling and operations can be performed by Figure 7 For example, the NW may correspond to the first device 100, and the UE may correspond to the second device 200. In some cases, the opposite case may also be considered.

[0192] For example, the above NW / UE signaling and operations can be performed by Figure 7 The NW / UE signaling and operations described above may be stored in a memory (e.g., Figure 7 in memory 140 / 240).

[0193] In the present disclosure, " / " may be interpreted as "and", "or" or "and / or" depending on the context. In the present disclosure, "beam" may refer to a source RS for a "spatial filter" or a "spatial relationship" and may be interpreted as a QCL (type-D) RS or a TCI state or spatial relationship RS (in the uplink).

[0194] 3GPP Rel-18 started to study how to use AI / ML in the air interface. This study item (SI) covers beam management, CSI and positioning as the main use cases of AI / ML. This disclosure covers the beam management method among them.

[0195] There may be two use cases for performing improved beam management using AI / ML: "improving beam management performance through spatial beam prediction" and "improving beam management performance through temporal beam prediction". This disclosure mainly considers "improving beam management performance through spatial beam prediction", but it should be noted that the techniques in this disclosure can be modified and applied to "improving beam management performance through temporal beam prediction".

[0196] "Improved beam management performance through spatial beam prediction" is a use case that achieves more improved beam management accuracy with lower RS ​​overhead based on UE location / mobility information, etc. as measurement results of current / past beam RSs. In this case, AI / ML of the UE and / or network (NW) can be used for spatial beam prediction operations. For example, AI / ML can be used to achieve performance comparable to beam selection from a large number of beam RSs based on the results measured from a small number of beam RSs.

[0197] AI / ML based beam prediction may be defined based on inputs and outputs associated with the AI / ML model (of the UE and / or NW).

[0198] For example, the input may be information related to measurements of a beam (eg, an RS associated with the beam), and the output may be information about a specific beam (eg, an ID of an RS associated with the specific beam).

[0199] For example, the input may be the reference signal received power (RSRP) of the beams in the first set, and the output may be the RSRP of the beams in the second set (e.g., the RSRP of the RS associated with all beams or the RSRP of the RS associated with the set A of beams). The RSRP of the beams in the first set may include the RSRP of the RS associated with some of the beams in all beams and / or the RSRP associated with the set B of beams. The RSRP of the beams in the second set may include the RSRP of the RS associated with all beams and / or the RSRP of the RS associated with the set A of beams.

[0200] Table 5 below summarizes the discussion and results related to beamforming performance improvements.

[0201] [Table 5]

[0202]

[0203]

[0204] In the results, BM-Case 1 refers to “a case where estimation / prediction of beams of set A is performed based on measurement results of beams included in set B.” Set A and set B are different.

[0205] A set A and a set B related to the embodiments of the present disclosure described below may be defined based on Table 5 above. Set B may be a set including beams related to an RS transmitted by a base station (RS received by a UE). Set A may be a beam set for estimating / determining a beam based on a measurement result of an RS related to set B. Set A may be a beam set for indicating a specific beam.

[0206] The purpose of BM-Case 1 is to select / estimate / predict beams more accurately than selecting beams based on existing methods. Specifically, according to BM-Case 1, beams are selected / estimated / predicted based on set A, and set A is more accurate than set B (for example, in the selection, set A includes a larger number of beams than set B, and has a beam shape with a narrower width than the width of the beams of set B).

[0207] The present disclosure proposes a method for performing beam reporting for set A based on beam measurement results based on set B. "Beam reporting for set A" refers to beam reporting for a higher beam granularity than set B (e.g., a larger number of beams, a larger maximum / minimum angle difference between beams, a smaller angle difference between beams, etc.), and the beam reporting is still applicable even if set A is not explicitly defined / set.

[0208] According to the existing beam reporting method, the UE reports the beam RS ID (e.g., CRI, SSBRI) and the beam quality value (e.g., L1-RSRP, L1-SINR) of the corresponding beam. If the above report is performed based on the measurement results for set B, only as many granularities as the number of beams belonging to set B can be included.

[0209] According to the AI / ML-based beam reporting method, the UE can perform beam reporting for high granularity based on UE location / mobility information, UE / base station beam information, etc., as a (cumulative) measurement result for the set B beam RS. To this end, the base station can provide the UE with information about the beam angle (e.g., visual axis direction / angle), beam width (e.g., 3dB beam width), beamforming coefficients, etc. of each set B beam (and set A beam). This information can be an absolute value, but it can also be a relative value between beams (e.g., the difference in beam angle / beam width between the first beam and the nth beam).

[0210] In such an environment as described above, a method of reporting a beam with a higher beam granularity may consider a method of replacing an existing beam RS ID and transmitting (linear) combination information for a plurality of set B beams.

[0211] Method 1

[0212] The base station configures the information of the set B beams (eg, absolute / relative beam angle information) to the UE. The UE reports (linear) combination coefficient information for (some of) the set B beams to the base station, and the combination coefficient information is included as beam information.

[0213] An example of configuring report parameters by applying the above method is as follows.

[0214] Information for N1 beams (sets) may be reported. In this example, information for each of the N1 beams (sets) may include at least one of the following i) to iii).

[0215] i) N2 beam RS IDs

[0216] ii) Information about the linear combination (LC) coefficients of the N2 beam RSs

[0217] iii) Beam quality information (e.g., L1-RSRP / SINR)

[0218] In ii), the LC coefficients may be based on quantized LC coefficients or codebook indices. The codebook may refer to a DFT codebook including a vector / matrix of LC coefficients.

[0219] In the above example, information about one beam may be configured by a linear combination for N2 beams, and the configured information may include a beam quality value for the combined beam. N1 combinations of combined beams and beam quality values ​​may be reported.

[0220] In other words, information about N1 (preferred) beams may be reported to include at least one of the above i) to iii).

[0221] Various beams (having beam angles) other than the beams constituting the set B may be expressed based on beam combining coefficients (the above-mentioned LC coefficients) for the plurality of beams. The operation of expressing various beams based on the combining coefficients may be an operation of interpolating / extrapolating beams.

[0222] For example, in order for the UE to find a preferred beam based on the above method, information about the beams constituting set B (e.g., absolute / relative beam angle (difference)) may be required. The union of all candidate beams that can be combined by LC coefficients applicable to beams of set B may constitute set A.

[0223] For example, candidate values ​​for the LC coefficients may be set or specified by the base station.

[0224] For example, the UE may freely select candidate values ​​for the LC coefficients. In this instance, the quantization level (how many bits each value will be represented with) may be specified / set. The UE may select and report the quantization level.

[0225] In the application of method 1, the combined beam preferred by the UE configuring multiple beams / panels may vary according to the applied beams / panels. In this case, the UE may operate as follows.

[0226] The UE may report information for (multiple N2 beams and) multiple LC values ​​for the same base station beam (for multiple UE beams / panels).

[0227] In this embodiment, although it is assumed that the N2 value is the same for the corresponding combined beams, it is obvious that different N2 values ​​can be applied to each combined beam. For example, the first combined beam can be based on a linear combination of two RSs, and the second combined beam can be based on a linear combination of three RSs. That is, in the information for each of the above N1 sets, N2 can be different for each set.

[0228] In the application of method 1, the UE can perform beam reporting based on set B before the AI / ML model training is completed or when the trained model is outdated.

[0229] For example, whether a trained model is outdated can be determined based on the error rate of the model via model validation or model monitoring (eg, if the error rate is greater than or equal to a threshold, the trained model is determined to be outdated).

[0230] For example, with respect to beam reporting based on set B, the UE may select and report LC coefficients where only one LC coefficient has a value of 1 while the rest are 0.

[0231] For example, according to the beam reporting operation based on set B, the report information may include only information related to the beams of set B. The base station / NW may implicitly determine the training status of the UE model or whether the UE model training is completed based on whether the report information includes only information related to the beams of set B.

[0232] For example, the UE may explicitly report the training status of the model or whether the model training is completed to the base station / NW.

[0233] In an embodiment, based on implicit / explicit information (for example, a report that only includes information related to the beams of set B or report information including the training status of the model / whether the model training is completed), the base station can decide / determine whether to apply the beam report based on method 1 or the existing beam report based on set B.

[0234] In an embodiment, based on implicit / explicit information (e.g., a report that only includes information related to the beams of set B or report information that includes the training status of the model / whether the model training is completed), the feedback information configuration and the number of bits for the same report configuration may vary (depending on the relevant base station configuration / indication).

[0235] As a specific example, whether to apply fallback beam reporting based on set B or beam reporting based on method 1 can be determined / controlled by feedback information configuration and configuration / indication related to the number of bits. Based on the feedback information configuration and the configuration / indication related to the number of bits, the UE can perform fallback beam reporting based on set B (based on measurement of set B, report on relevant information of set B), or perform beam reporting based on method 1 (based on measurement of set B, report on relevant information of set A).

[0236] A beam reporting method is proposed below, which can be used as an alternative or in addition to method 1.

[0237] Method 2

[0238] The base station configures / indicates coordinate information for the set B of beams to the UE. The coordinate information of the beams of the set B may be information based on a configured / specified beam grid.

[0239] The UE reports the coordinate information for the beam grid to the base station as the beam information. The coordinate information for the beam grid may be estimated / determined based on i) the coordinate information of the beams of set B and ii) the measurement results for set B of beams.

[0240] The beam grid can be configured as a one-dimensional, two-dimensional, or three-dimensional grid.

[0241] The beam grid may be interpreted / defined / configured / specified as i) a grid for beam boresight angles, ii) a grid for the locations at which each beam is pointed, or iii) a grid for the area covered by each beam, etc.

[0242] For example, the beam set that can be represented by a beam grid in method 2 can constitute set A. The beam set that can be represented by a beam grid can correspond to a virtual beam set including a specific beam angle (assuming beam properties such as a specific beam gain). The UE can perform estimation based on the result of correcting the received measurement results of the set B beams to match the virtual beam set (e.g., pre-filtering of input data for UE AI / ML).

[0243] The (estimated) quality value (eg, L1-RSRP / SINR) for the beam represented by the coordinates may be reported together with the coordinate information.

[0244] The beams of set B may be configured / defined to be located only at the intersections of the grids. As in Example 1 below, the set B configuration information of the base station may include only information about the intersections of the grids (eg, coordinate information represented as integers).

[0245] Example 1) 2D grid from (0,0) to (4,4), set B = {SSB1 = (1,2), SSB2 = (1,3), SSB3 = (2,2), SSB4 = (2,3)}

[0246] The beams of set B may be configured / defined to be located at locations other than the intersections of the grids. As in Example 2 below, the set B configuration information of the base station may include coordinate information (eg, coordinate information represented as integers / real numbers) about other locations as well as the intersections of the grids.

[0247] Example 2) 2D grid from (0, 0) to (4, 4), set B = {SSB1 = (1.5, 2.2), SSB2 = (1.2, 3.9), SSB3 = (2.1, 2.8), SSB4 = (2.0, 3.9)}

[0248] In an example, the UE may select a (preferred) beam grid from among the intersection points (eg, best beam = (2, 4)), or select other positions represented as decimal points within the grid (eg, best beam = (0.5, 0.3)).

[0249] In addition, the (estimated) beam quality value (eg, L1-RSRP / SINR) for the beam at the corresponding coordinates may also be reported.

[0250] In the above report, coordinate information for multiple beams (and quality values ​​for corresponding beams) may be reported to the base station. In this case, the same number of payload bits or different numbers of payload bits may be applied to the feedback information for each beam.

[0251] For example, the number of payload bits may be determined as follows.

[0252] The range of coordinate values ​​that may be selected / reported for the second best beam may be determined based on the coordinate values ​​selected for the best beam (e.g., selecting the second beam only in the vicinity of the first beam, or conversely, selecting the second beam excluding the vicinity of the first beam). The number of payload bits for the second best beam may be determined by reducing / determining the coordinate range based on the coordinate values ​​selected for the best beam.

[0253] As described above, by limiting the candidate values ​​(coordinate candidate values), information about the second best beam can be sent using a smaller number of bits. In the same manner as the second best beam, the third best beam, the fourth best beam, and so on can depend on the coordinates of a beam with a higher ranking (e.g., the first beam).

[0254] In other words, the number of payload bits reported by the UE for representing the coordinate information of each beam of the set A may be related to the coordinate range determined based on the ranking of the beam quality values.

[0255] For example, coordinate information of a first beam having a maximum beam quality value may be reported according to a first payload based on a first coordinate range. The first coordinate range may be based on the entire range of a grid.

[0256] Coordinate information of a second beam having a second maximum beam quality value may be reported according to a second payload based on a second coordinate range. The second coordinate range may be based on a range determined according to the coordinates of the first beam. The size of the second payload may be smaller than the size of the first payload.

[0257] As described above, the coordinate range associated with the payload (number of bits) used to report the coordinate information of each beam can be i) the entire range of the grid or ii) a range determined by the coordinates of the beam preceding the beam quality value of each beam based on the ordering of the beam quality values.

[0258] In the application of method 2, a UE configured with multiple beams / panels may change the preferred coordinate information based on the applied beams / panels. In this case, multiple coordinate value information for the same base station beam (for multiple UE beams / panels) may be reported.

[0259] When configuring the AI / ML of the UE based on method 2, an example of configuring the input parameters and output parameters is as follows.

[0260] AI / ML input parameters: (beam grid, RSRP / SINR) for each set of B beams

[0261] AI / ML output: N1 best beams predicted on the beam grid

[0262] The (beam grid, RSRP / SINR) of each set B beam as the input parameters of AI / ML on the UE side may be corrected data.

[0263] The UE's AI / ML can estimate / determine N1 best beams based on the input parameters.

[0264] In the example of AI / ML model configuration, how to perform AI / ML model training may be a problem. The following methods A to C can be considered as solutions.

[0265] Method A) Model migration from NW

[0266] Method B) Training data provided by NW

[0267] For example, the NW may (pre)receive reports from the UE on the best beam output results for various (beam grid, RSRP) combinations (+UE Rx beam / panel configurations) and provide this data to each UE. The method may be based on supervised learning.

[0268] Method C) RS assisted by NW

[0269] According to this method, in order to help the UE learn the model, the NW can send beam RSs for various possible grids to the UE (multiple times).

[0270] For example, NW can show the set B beams by migrating the coordinates.

[0271] For example, the NW may additionally provide coordinate information of other DL RSs in addition to the set B beam. As a specific example, the NW may periodically / aperiodically send a beam to the UE that is sent in a grid wider than the set B. As another example, the set B includes CSI-RS, but the NW may additionally provide grid information of the SSB. The UE may measure the SSB in a long period of time.

[0272] In the application of method 2, before the AI / ML model training is completed or when the trained model is outdated, the UE may perform beam reporting based on the grid for set B. As described above, whether the trained model is outdated may be determined based on the error rate of the model via model validation or model monitoring (e.g., if the error rate is greater than or equal to a threshold, the trained model is determined to be outdated).

[0273] For example, according to the beam reporting operation based on the grid for set B, the report information may include only information related to the beams of set B. The base station / NW may implicitly determine the training status of the UE model or whether the UE model training is completed based on whether the report information includes only information related to the beams of set B.

[0274] For example, the UE may explicitly report the training status of the model or whether the model training is completed to the base station / NW.

[0275] In an embodiment, based on implicit / explicit information (for example, a report that only includes information related to the beams of set B or report information including the training status of the model / whether the model training is completed), the base station can determine whether to apply the beam report based on method 2 or the existing beam report based on set B.

[0276] In an embodiment, based on implicit / explicit information (e.g., a report that only includes information related to the beams of set B or report information that includes the training status of the model / whether the model training is completed), the feedback information configuration and the number of bits used for the same reporting configuration may vary (depending on the relevant base station configuration / indication).

[0277] As a specific example, whether to apply fallback beam reporting based on set B or beam reporting based on method 2 can be determined / controlled by feedback information configuration and configuration / indication related to the number of bits. Based on the feedback information configuration and the configuration / indication related to the number of bits, the UE can perform fallback beam reporting based on set B (based on measurement of set B, report on information related to set B), or perform beam reporting based on method 2 (based on measurement of set B, report on grid information related to set A).

[0278] In the proposed techniques of the present disclosure, the reference time for beam reporting and predicted RSRP / SINR may be based on i) a set B measurement time (eg, a time based on an existing CSI reference resource) or ii) a future time.

[0279] For example, the method of the present disclosure may also be applied together with beam prediction for a future time. In this case, the information reported based on the proposed technology of the present disclosure (e.g., information related to the beams of set A) may correspond to (preferred) beam information for a future time. The future time may be based on a time later than the CSI-RS reference resource time or the reporting time.

[0280] Although the proposed technology of the present disclosure has been described based on AI / ML on the UE side, this does not mean that the technology of the present disclosure can be applied only in the AI / ML implementation environment of the UE. The proposed technology of the present disclosure can be applied to the AI / ML implementation environment or non-AI / ML environment on the base station / NW side. In addition, the proposed technology of the present disclosure can be applied to side link communication. Specifically, in the proposed technology of the present disclosure, the base station / NW can be changed to another UE and applied.

[0281] From an implementation perspective, the operation of the base station / UE according to the above embodiment (eg, the operation based on at least one of method 1 and method 2) can be performed as described below. Figure 7 Devices (e.g. Figure 7 110 and processor 210) for processing.

[0282] The operation of the base station / UE according to the above embodiment (for example, the operation based on at least one of method 1 and method 2) can be used to execute at least one processor (for example, Figure 7 The processor 110 and the processor 210) are stored in the form of commands / programs (e.g., instructions, executable codes) in the memory (e.g., Figure 7 in memory 140 and memory 240).

[0283] Refer to the following Figure 4 The signaling process based on the above implementation is described in detail.

[0284] Figure 4 A signaling process according to an embodiment of the present disclosure is illustrated.

[0285] More specifically, Figure 4 An example of signaling between a user equipment (UE) and a network (NW) based on the above-mentioned methods (eg, method 1, method 2) is illustrated.

[0286] UE / NW are merely examples and may be replaced with various devices as described above. Figure 4 It is only for the convenience of explanation and does not limit the scope of the present disclosure. In addition, depending on the situation and / or setting, it can be omitted. Figure 4 Some of the steps shown in Figure 4 In the present invention, NW may correspond to any entity belonging to a network, such as a base station (BS), a Node B, or a TRP.

[0287] In S405, the UE may report UE capability information to the NW. The UE capability information may include information related to the UE AI / ML model (training / inference), and report information on whether beam prediction is possible.

[0288] In S410, the UE may receive a configuration related to set B (and set A) from the NW. The configuration may include ID information for the beam, transmission period and time / frequency position information, sequence information, information about the relationship between RSs (e.g., whether there is a QCL), beam angle information, beam width information, and beam grid related information.

[0289] After the beam-related configuration in S410, in S415, the base station may send a beam RS belonging to set B to the UE, and the UE may perform measurement therefor.

[0290] The UE performing beam-related configuration (S410) and measurement of the set B beams may select a preferred beam based on the configuration and the measurement values. In S420, the AI / ML of the UE may be utilized / applied in the process.

[0291] Subsequently, in S425, the UE may send information to the NW on the selected beam by applying the information to the proposed method (eg, method 1, method 2).

[0292] As mentioned above, the above NW / UE signaling and operations can be performed by Figure 7 For example, the NW may correspond to the first device 100, and the UE may correspond to the second device 200. In some cases, the opposite case may also be considered.

[0293] For example, the above NW / UE signaling and operations can be performed by Figure 7 The NW / UE signaling and operations described above may be stored in a memory (e.g., Figure 7 in memory 140 and memory 240).

[0294] Below, refer to Figure 5 and Figure 6 The above embodiments are described in detail from the perspective of the operation of the UE and the base station. The methods described below are distinguished only for the convenience of explanation. Therefore, as long as these methods are not mutually exclusive, it is obvious that part of the configuration of any method can be replaced by or combined with part of the configuration of another method.

[0295] Figure 5 is a flowchart illustrating a method performed by a user equipment in a wireless communication system according to an embodiment of the present disclosure.

[0296] Reference Figure 5According to an embodiment of the present disclosure, the method performed by a user equipment in a wireless communication system includes: a step S510 of receiving configuration information related to channel state information (CSI), a step S520 of receiving a downlink reference signal (DLRS), a step S530 of calculating CSI, and a step S540 of reporting CSI.

[0297] In step S510, the UE receives configuration information related to channel state information (CSI) from the base station. The configuration information may include information based on the above method 1 and / or method 2.

[0298] According to an embodiment, the configuration information may include information related to the first set of beams.

[0299] Specifically, the configuration information may include at least one of the following 1) to 6).

[0300] 1) ID information for a beam (for example, information including at least one of an ID of a first DL RS associated with a first set of beams and / or an ID of a second DL RS associated with a second set of beams)

[0301] 2) Transmission period and time / frequency position information of DL RS (eg, first DL RS and / or second DL RS)

[0302] 3) Sequence information related to a DL RS (eg, a first DL RS and / or a second DL RS)

[0303] 3) Information about the relationship between RSs (e.g., QCL information (QCL Type-D) configured between the first DL RS and the second DL RS or QCL information (QCL Type-D) configured between the antenna port of the first DL RS and the antenna port of the second DL RS)

[0304] 4) Beam angle information (e.g., absolute / relative information of beams associated with the first set and / or the second set, boresight direction, boresight angle (azimuth / zenith angle))

[0305] 5) Beamwidth information (e.g., 3dB beamwidth)

[0306] 6) Beam grid information (e.g., information related to the beam grid of method 2)

[0307] For example, the configuration information may include angle information associated with the first set of beams. The angle information associated with the first set of beams may be based on 4) beam angle information. The angle information associated with the first set of beams may include angle information based on the auxiliary information of Table 5 above.

[0308] For example, the configuration information may include coordinate information associated with the first set of beams. The coordinate information may be based on 6) beam grid information. The coordinate information may include the coordinates of the first DL RS within the beam grid. The second DL RS (associated with the second set of beams) may be associated with a beam that may be represented based on a beam grid. That is, the second set of beams may be based on a beam that may be represented based on a beam grid.

[0309] According to an embodiment, the configuration information may be based on configuration information related to existing CSI.

[0310] The configuration information may include at least one of the following items: i) CSI-interference management (IM) resource related information, ii) CSI measurement configuration related information, iii) CSI resource configuration related information, iv) CSI-RS resource related information, or v) CSI report configuration related information. For example, at least one of i) to v) may include information for at least one of 1) to 6). For example, CSI resource configuration related information (e.g., CSI-ResourceConfig IE of Table 1) may include ID information for a beam and / or beam grid information.

[0311] The first set may be based on set B of Table 5 above, and the second set may be based on set A of Table 5 above.

[0312] For example, the second DL RS associated with the second set of beams may include the first DL RS. That is, the first DL RS may be based on a subset of the second DL RS (Alternative 1 of Table 5 above).

[0313] For example, the second DL RS associated with the second set of beams may be different from the first DL RS. The first set of beams may be different from the second set of beams. The first DL RS and the second DL RS may be based on different beams (Alternative 2 of Table 5 above).

[0314] According to an embodiment, the beamwidth associated with the second set of beams may be narrower than the beamwidth associated with the first set of beams.The first set may include beams with a wide beamwidth and the second set may include beams with a narrow beamwidth.

[0315] According to an embodiment, a quasi co-location (QCL) relationship may be configured between the first DL RS and the second DL RS. The QCL relationship may be configured by a qcl type (qcl-Type).

[0316] For example, the antenna port of the first DL RS may be quasi co-located (QCLed) with the second DL RS in terms of the qcl type. For example, the antenna port of the second DL RS may be quasi co-located with the first DL RS in terms of the qcl type.

[0317] The qcl type can be configured as TypeD (spatial Rx parameters).

[0318] The information related to the QCL relationship may be included in the configuration information related to the CSI (e.g., information about the relationship between RSs). For example, the information related to the QCL relationship may include QCL information related to the corresponding first DL RS. The QCL information related to the corresponding first DL RS may include the ID of at least one second DL RS. The QCL information related to the corresponding first DL RS may also include information about the QCL type (if the QCL type is configured for each first DL RS).

[0319] In step S520, the UE receives at least one downlink reference signal (DL RS) from the base station.

[0320] The at least one DL RS may be based on a synchronization signal / physical broadcast channel block (SS / PBCH block) (SSB) and / or a channel state information reference signal (CSI-RS).

[0321] According to an embodiment, the at least one DL RS may be based on a first DL RS associated with a first set of beams. The first set may be based on set B of Table 5 above.

[0322] In step S530 , the UE calculates CSI based on measurement of at least one DL RS.

[0323] The parameters included in the CSI may be determined / calculated based on the measurement of at least one DL RS. The parameters included in the CSI may be parameters based on "reportquantity".

[0324] For example, 'reportquantity' may be set to cri-RI-PMI-CQI, cri-RI-i1, cri-RI-i1-CQI, cri-RI-CQI, cri-RSRP, ssb-Index-RSRP, or cri-RI-LI-PMI-CQI.

[0325] Based on "reportquantity", CSI may include at least one of channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), SSB resource block indicator (SSBRI), layer indicator (LI), rank indicator (RI), layer 1 reference signal received power (L1-RSRP) or layer 1 signal to interference and noise ratio (L1-SINR).

[0326] In step S540, the UE reports CSI to the base station. The CSI may be reported based on a CSI report configuration (CSI-reportConfig IE). The CSI may be reported periodically, semi-continuously, or aperiodically.

[0327] The CSI may be sent on the Physical Uplink Control Channel (PUCCH) or the Physical Uplink Shared Channel (PUSCH).

[0328] Periodic CSI reporting is performed on short PUCCH or long PUCCH. Semi-persistent (SP) CSI reporting is performed on short PUCCH, long PUCCH or PUSCH. 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 sent / indicated / configured via MAC-CE.

[0329] The CSI may include information based on method 1 and / or method 2. The CSI may include information related to a second set of beams estimated / determined based on an AI / ML model of the UE. For example, the input of the AI / ML model may be information based on measurements of at least one DLRS (e.g., L1-RSRP related to the first set of beams and / or L1-SINR related to the first set of beams). The output of the AI / ML model may be information related to the second set of beams (e.g., RS IDs related to the second set of beams, linear combination coefficients related to the second set of beams, coordinate information related to the second set of beams, RSRP related to the second set of beams, and / or SINR related to the second set of beams).

[0330] According to an embodiment, the CSI may include information related to at least one beam in the second set related to the first set.

[0331] For example, the CSI may include information (reporting parameters) based on method 1. The CSI may include information about N1 beams (e.g., at least one beam in the second set of beams). Specifically, the CSI may include information for at least one of the following items: i) one or more first DL RSs in the first DL RSs, ii) one or more linear combination coefficients associated with the one or more first DL RSs, and / or iii) one or more beam quality values ​​associated with the one or more first DL RSs (e.g., L1-RSRP and / or L1-SINR).

[0332] For example, the CSI may include information based on method 2. The CSI may include coordinate information associated with at least one beam in the second set. Specifically, the CSI may include information for at least one of the following items: i) one or more coordinates associated with one or more second DL RSs in the second DL RSs, and / or ii) one or more beam quality values ​​(e.g., L1-RSRP and / or L1-SINR) associated with one or more second DL RSs. In the CSI, the payload size (e.g., the number of bits) for the corresponding one or more second DL RSs may be different. This will be described in detail below.

[0333] If the coordinate information related to each of the one or more second DL RSs included in the CSI is a value represented based on the entire range of the beam grid, the CSI may not include the coordinate information related to the one or more second DL RSs. In other words, the coordinate information related to the one or more second DL RSs may be larger than the payload of the limited CSI. The following embodiments may be considered to solve this problem.

[0334] The payload size (eg, the number of bits for coordinate information or the number of bits for coordinate information + the number of bits for beam quality value) for each of the one or more second DL RSs may be related to a coordinate range determined based on the ranking of the one or more beam quality values.

[0335] The coordinate range determined for a specific second DL RS among the one or more second DL RSs may be i) the entire coordinate range of the beam grid or ii) a range determined based on coordinates associated with a second DL RS whose beam quality value is ranked before the specific second DL RS. This will be described in detail in the following example.

[0336] If the beam quality of a specific second DL RS is the best (the ranking of the beam quality value is first), the determined coordinate range may be the entire coordinate range of the beam grid.

[0337] If the beam quality of a specific second DL RS is the second best (the ranking of the beam quality value is second), the determined coordinate range may be a range determined based on the coordinates of the second DL RS whose ranking of the beam quality value is first. The range determined based on the coordinates of the second DL RS whose ranking of the beam quality value is first may be a part of the entire coordinate range of the beam grid. A part of the entire coordinate range of the beam grid may be a range including the coordinates of the second DL RS whose ranking of the beam quality value is first. A part of the entire coordinate range of the beam grid may be a range excluding the coordinates of the second DL RS whose ranking of the beam quality value is first.

[0338] The operations based on the above steps S510 to S540 and the SSB receiving step can be performed by Figure 7 For example, the UE 200 may control one or more transceivers 230 and / or one or more memories 240 to perform operations based on steps S510 to S540.

[0339] The above implementation is described in detail below from the perspective of base station operation.

[0340] Steps S610 to S630 described below correspond to the steps of Figure 5 In consideration of the above correspondence, redundant descriptions are omitted. That is, the detailed description of the base station operation described below can be used in conjunction with the corresponding base station operation. Figure 5 For example, Figure 5 The description / implementation of steps S510 and S520 in the embodiment may be additionally applied to the base station operations of steps S610 and S620 described below. For example, Figure 5 The description / implementation of steps S530 and S540 in the embodiment may be additionally applied to the base station operation of step S630 described below.

[0341] Figure 6 is a flowchart illustrating a method performed by a base station according to another embodiment of the present disclosure.

[0342] Reference Figure 6 According to another embodiment of the present disclosure, a method performed by a base station in a wireless communication system includes a step S610 of sending configuration information related to channel state information (CSI), a step S620 of sending a downlink reference signal (DL RS), and a step S630 of receiving CSI.

[0343] In step S610, the base station sends configuration information related to channel state information (CSI) to the UE.

[0344] In step S620, the base station sends at least one downlink reference signal (DL RS) to the UE.

[0345] In step S630 , the base station receives CSI from the UE.

[0346] The operations based on the above steps S610 to S630 can be performed by Figure 7 For example, the base station 100 may control one or more transceivers 230 and / or one or more memories 240 to perform operations based on steps S610 to S630.

[0347] Refer to the following Figure 7 The following describes a device to which the embodiments of the present disclosure are applicable (a device that implements the method / operation according to the embodiments of the present disclosure).

[0348] Figure 7 The configurations of the first device and the second device according to the embodiment of the present disclosure are illustrated.

[0349] The first device 100 may include a processor 110 , an antenna unit 120 , a transceiver 130 , and a memory 140 .

[0350] The processor 110 may perform signal processing related to the baseband, and includes a high-level processing unit 111 and a physical layer processing unit 115. The high-level processing unit 111 may process operations of a MAC layer, an RRC layer, or a higher layer. The physical layer processing unit 115 may process operations of a PHY layer. For example, if the first device 100 is a base station (BS) device in BS-UE communication, the physical layer processing unit 115 may perform uplink received signal processing, downlink transmitted signal processing, etc. For example, if the first device 100 is a first UE device in inter-UE communication, the physical layer processing unit 115 may perform downlink received signal processing, uplink transmitted signal processing, sidelink transmitted signal processing, etc. In addition to performing signal processing related to the baseband, the processor 110 may also control the overall operation of the first device 100.

[0351] The antenna unit 120 may include one or more physical antennas, and if the antenna unit 120 includes multiple antennas, MIMO transmission / reception is supported. The transceiver 130 may include a radio frequency (RF) transmitter and an RF receiver. The memory 140 may store information processed by the processor 110 and software, an operating system, and applications related to the operation of the first device 100. The memory 140 may also include components such as a buffer.

[0352] In the embodiments described in the present disclosure, the processor 110 of the first device 100 may be configured to implement operations of a BS in BS-UE communication (or operations of a first UE device in inter-UE communication).

[0353] The second device 200 may include a processor 210 , an antenna unit 220 , a transceiver 230 , and a memory 240 .

[0354] The processor 210 may perform signal processing related to the baseband, and includes a high-level processing unit 211 and a physical layer processing unit 215. The high-level processing unit 211 may process operations of a MAC layer, an RRC layer, or a higher layer. The physical layer processing unit 215 may process operations of a PHY layer. For example, if the second device 200 is a UE device in BS-UE communication, the physical layer processing unit 215 may perform downlink received signal processing, uplink transmitted signal processing, etc. For example, if the second device 200 is a second UE device in inter-UE communication, the physical layer processing unit 215 may perform downlink received signal processing, uplink transmitted signal processing, side link received signal processing, etc. In addition to performing signal processing related to the baseband, the processor 210 may also control the overall operation of the second device 210.

[0355] The antenna unit 220 may include one or more physical antennas, and if the antenna unit 220 includes multiple antennas, MIMO transmission / reception is supported. The transceiver 230 may include an RF transmitter and an RF receiver. The memory 240 may store information processed by the processor 210 and software, operating systems, and applications related to the operation of the second device 200. The memory 240 may also include components such as a buffer.

[0356] In the embodiments described in the present disclosure, the processor 210 of the second device 200 may be configured to implement the operation of the UE in BS-UE communication (or the operation of the second UE device in inter-UE communication).

[0357] The description of the BS and the UE in BS-UE communication (or the first UE device and the second UE device in inter-UE communication) in the examples of the present disclosure are equally applicable to the operations of the first device 100 and the second device 200, and redundant descriptions are omitted.

[0358] In addition to LTE, NR, and 6G, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may also include a narrowband Internet of Things (NB-IoT) for low-power communication. For example, the NB-IoT technology may be an example of a low-power wide area network (LPWAN) technology and may be implemented in standards such as LTE Cat NB1 and / or LTE Cat NB2. The NB-IoT technology is not limited to the above names.

[0359] Additionally or alternatively, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may perform communication based on the LTE-M technology. For example, the LTE-M technology may be an example of the LPWAN technology and may be referred to as various names, such as enhanced machine type communication (eMTC). For example, the LTE-M technology may be implemented with at least one of various standards, such as 1) LTE CAT0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-bandwidth limited), 5) LTE-MTC, 6) LTE machine type communication and / or 7) LTE M. The LTE-M technology is not limited to the above names.

[0360] Additionally or alternatively, in consideration of low power communication, the wireless communication technology implemented in the apparatus 100 and the apparatus 200 according to the present disclosure may include at least one of ZigBee, Bluetooth, and a low power wide area network (LPWAN), and is not limited to the above names. For example, ZigBee technology may create a personal area network (PAN) related to small / low power digital communication based on various standards such as IEEE 802.15.4, and may be referred to by various names.

Claims

1. A method performed by a user equipment in a wireless communication system, the method comprising the following steps: Receiving configuration information related to channel state information CSI; Receiving at least one downlink reference signal DL RS; calculating the CSI based on measurements of the at least one DL RS; and The CSI reported, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

2. The method according to claim 1, wherein: A second DL RS associated with the second set of beams includes the first DL RS.

3. The method according to claim 1, wherein: A second DL RS associated with the second set of beams is different from the first DL RS.

4. The method according to claim 3, wherein: A beamwidth associated with the second set of beams is narrower than a beamwidth associated with the first set of beams.

5. The method according to claim 3, wherein: A quasi co-site QCL relationship is configured between the second DL RS and the first DL RS.

6. The method according to claim 1, wherein: The configuration information includes angle information associated with the first set of beams.

7. The method according to claim 1, wherein: The CSI includes information for at least one of the following items: i) one or more first DL RSs among the first DL RSs, ii) one or more linear combination coefficients related to the one or more first DL RSs, and / or iii) one or more beam quality values ​​related to the one or more first DL RSs.

8. The method according to claim 1, wherein: The configuration information includes coordinate information associated with the first set of beams, and The coordinate information includes the coordinates of the first DL RS in the beam grid.

9. The method according to claim 8, wherein: The second DL RSs associated with the second set of beams are associated with beams that can be represented based on the beam grid.

10. The method according to claim 9, wherein: The CSI includes information on at least one of the following items: i) one or more coordinates associated with one or more second DL RSs among the second DL RSs, and / or ii) one or more beam quality values ​​associated with the one or more second DL RSs.

11. The method according to claim 10, wherein: In the CSI, a payload size for each of the one or more second DLRSs is different, and The payload size for each of the one or more second DL RSs is related to a coordinate range determined based on the ranking of the one or more beam quality values.

12. The method according to claim 11, wherein: The coordinate range determined for a specific second DL RS among the one or more second DL RSs is i) the entire coordinate range of the beam grid, or ii) a range determined based on coordinates associated with a second DL RS preceding the specific second DL RS in the sorting of the one or more beam quality values.

13. A user equipment operating in a wireless communication system, the user equipment comprising: one or more transceivers; one or more processors; as well as one or more memories operatively connectable to the one or more processors and storing instructions that upon execution by the one or more processors configure the one or more processors to perform operations, The operations include: Receiving configuration information related to channel state information CSI; Receiving at least one downlink reference signal DL RS; calculating the CSI based on measurements of the at least one DL RS; and The CSI reported, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

14. A device, comprising: one or more memories; as well as one or more processors operatively connected to the one or more memories, wherein the one or more memories include instructions that, upon being executed by the one or more processors, configure the one or more processors to perform operations, The operations include: Receiving configuration information related to channel state information CSI; Receiving at least one downlink reference signal DL RS; calculating the CSI based on measurements of the at least one DL RS; and The CSI reported, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

15. One or more non-transitory computer-readable media storing one or more instructions, in, The one or more instructions executable by one or more processors configure the one or more processors to perform operations, The operations include: Receiving configuration information related to channel state information CSI; Receiving at least one downlink reference signal DL RS; calculating the CSI based on measurements of the at least one DL RS; and The CSI reported, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

16. A method performed by a base station in a wireless communication system, the method comprising the following steps: Sending configuration information related to channel state information CSI; Sending at least one downlink reference signal DL RS; as well as receiving the CSI, The CSI is calculated based on a measurement of the at least one DL RS, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

17. A base station operating in a wireless communication system, the base station comprising: one or more transceivers; one or more processors; as well as one or more memories operatively connectable to the one or more processors and storing instructions that upon execution by the one or more processors configure the one or more processors to perform operations, The operations include: Sending configuration information related to channel state information CSI; transmitting at least one downlink reference signal DL RS; and receiving the CSI, The CSI is calculated based on a measurement of the at least one DL RS, The configuration information includes information related to a first set of beams, wherein the at least one DL RS is based on a first DL RS associated with the first set of beams, and The CSI includes information related to at least one beam in a second set related to the first set.

Images