Method and device for measurement prediction activation and deactivation on terminal side by using artificial intelligence and machine learning in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting higher data transmission rates. This method performed by a terminal of a wireless communication system may comprise the steps of: receiving, from a base station, a first message including configuration information for artificial intelligence and machine learning (AI / ML)-based measurement prediction; on the basis of the configuration information, transmitting, to the base station, a second message for reporting applicability of the AI / ML-based measurement prediction; identifying that the AI / ML-based measurement prediction has been activated; and transmitting, to the base station, a report on a result of the activated AI / ML-based measurement prediction.

Description

Method and device for activating and deactivating terminal-side measurement prediction using artificial intelligence and machine learning in a wireless communication system

[0001] The present disclosure relates to a wireless communication system. More specifically, the present disclosure relates to a method and device for activating and deactivating terminal-side measurement prediction using artificial intelligence and machine learning.

[0002] 5G mobile communication technology defines a wide frequency band to enable fast transmission speeds and new services, and can be implemented not only in the sub-6GHz frequency band such as 3.5 gigahertz (3.5GHz), but also in the ultra-high frequency band called millimeter wave (mmWave) such as 28GHz and 39GHz ('Above 6GHz'). In addition, for 6G mobile communication technology, which is called the system after 5G communication (Beyond 5G), implementation in the terahertz band (for example, the 3 terahertz (3THz) band at 95GHz) is being considered to achieve a transmission speed that is 50 times faster than 5G mobile communication technology and an ultra-low latency time that is reduced to one-tenth.

[0003] In the early stages of 5G mobile communication technology, the goal is to support services and satisfy performance requirements for enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communications (URLLC), and massive Machine-Type Communications (mMTC). These include beamforming and massive MIMO to mitigate path loss of radio waves in ultra-high frequency bands and increase the transmission distance of radio waves, support for various numerologies (such as operation of multiple subcarrier intervals) and dynamic operation of slot formats for efficient use of ultra-high frequency resources, initial access technology to support multi-beam transmission and wideband, definition and operation of BWP (Bidth Part), new channel coding methods such as LDPC (Low Density Parity Check) codes for large-capacity data transmission and Polar Code for reliable transmission of control information, and L2 pre-processing (L2). Standardization has been made for network slicing, which provides dedicated networks specialized for specific services, and pre-processing.

[0004] Currently, discussions are underway to improve and enhance the initial 5G mobile communication technology in consideration of the services that 5G mobile communication technology was intended to support, and physical layer standardization is in progress for technologies such as V2X (Vehicle-to-Everything) to help autonomous vehicles make driving decisions and increase user convenience based on their own location and status information transmitted by vehicles, NR-U (New Radio Unlicensed) for the purpose of system operation that complies with various regulatory requirements in unlicensed bands, NR terminal low power consumption technology (UE Power Saving), Non-Terrestrial Network (NTN), which is direct terminal-satellite communication to secure coverage in areas where communication with terrestrial networks is impossible, and Positioning.

[0005] In addition, standardization of wireless interface architecture / protocols is in progress for technologies such as intelligent factories (Industrial Internet of Things, IIoT) to support new services through linkage and convergence with other industries, Integrated Access and Backhaul (IAB) that provides nodes for expanding network service areas by integrating wireless backhaul links and access links, Mobility Enhancement technology including Conditional Handover and Dual Active Protocol Stack (DAPS) handover, and 2-step random access (2-step RACH for NR) that simplifies random access procedures. Standardization is also in progress for system architecture / services such as 5G baseline architecture (e.g., Service-based Architecture, Service-based Interface) for grafting Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC) that provides services based on the location of the terminal.

[0006] Once these 5G mobile communication systems are commercialized, an explosive increase in connected devices will be connected to the communication network, necessitating enhanced functionality and performance of 5G mobile communication systems and integrated operation of these connected devices. To this end, new research will be conducted on improving 5G performance and reducing complexity, supporting AI services, supporting metaverse services, and drone communications by utilizing eXtended Reality (XR), Artificial Intelligence (AI), and Machine Learning (ML) to efficiently support Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR).

[0007] In addition, the development of these 5G mobile communication systems includes new waveforms to ensure coverage in the terahertz band of 6G mobile communication technology, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), Array Antenna, and Large Scale Antenna, metamaterial-based lenses and antennas to improve the coverage of terahertz band signals, high-dimensional spatial multiplexing technology using Orbital Angular Momentum (OAM), Reconfigurable Intelligent Surface (RIS) technology, as well as full duplex technology to improve the frequency efficiency and system network of 6G mobile communication technology, satellite, AI (Artificial Intelligence) from the design stage and AI-based communication technology that realizes system optimization by internalizing end-to-end AI support functions, and ultra-high-performance communication and computing resources to provide services with complexity that exceeds the limits of terminal computing capabilities. It can serve as a basis for the development of next-generation distributed computing technologies that can be realized by utilizing them.

[0008] The present disclosure aims to introduce an AI / ML algorithm-based handover mechanism to solve problems of existing reactive handovers that may occur in high-density micro-cell environments and environments with high mobility, and to improve the overall performance and stability of the network.

[0009] According to one embodiment of the present disclosure, a method performed by a terminal of a wireless communication system is provided. The method comprises the steps of: receiving, from a base station, a first message including configuration information for artificial intelligence and machine learning (AI / ML)-based measurement prediction; transmitting, to the base station, a second message for reporting applicability of the AI / ML-based measurement prediction based on the configuration information; identifying that the AI / ML-based measurement prediction has been activated; and transmitting, to the base station, a report on the result of the activated AI / ML-based measurement prediction.

[0010] According to one embodiment of the present disclosure, a method performed by a base station of a wireless communication system is provided. The method comprises the steps of: transmitting a first message including configuration information for AI / ML-based measurement prediction to a terminal; receiving a second message from the terminal for reporting applicability of the AI / ML-based measurement prediction associated with the configuration information; identifying that the AI / ML-based measurement prediction has been activated within the terminal; and receiving a report on the result of the activated AI / ML-based measurement prediction from the terminal.

[0011] According to one embodiment of the present disclosure, a terminal of a wireless communication system is provided. The terminal includes a transceiver and a control unit. The control unit is configured to receive a first message including configuration information for AI / ML-based measurement prediction from a base station through the transceiver, and to transmit a second message for reporting applicability of the AI / ML-based measurement prediction to the base station through the transceiver based on the configuration information, identify that the AI / ML-based measurement prediction has been activated, and transmit a report on the result of the activated AI / ML-based measurement prediction to the base station through the transceiver.

[0012] According to one embodiment of the present disclosure, a base station of a wireless communication system is provided. The base station includes a transceiver and a control unit. The control unit is configured to transmit a first message including configuration information for AI / ML-based measurement prediction to a terminal through the transceiver, receive a second message from the terminal through the transceiver for reporting applicability of the AI / ML-based measurement prediction associated with the configuration information, identify that the AI / ML-based measurement prediction has been activated within the terminal, and receive a report on the result of the activated AI / ML-based measurement prediction from the terminal through the transceiver.

[0013] According to various embodiments of the present disclosure, the efficiency of the handover process can be increased, proactive response can be enabled before problems occur, network operation and configuration decisions can be improved, and wireless resource management performance can be improved.

[0014] FIG. 1 is a diagram illustrating the structure of a mobile communication system according to one embodiment of the present disclosure.

[0015] FIG. 2 is a diagram for explaining a wireless connection state transition in a mobile communication system according to one embodiment of the present disclosure.

[0016] FIG. 3 is a flowchart illustrating a process in which a terminal performs cell measurement and reporting operations according to one embodiment of the present disclosure.

[0017] FIG. 4 is a diagram illustrating an operation of reporting cell measurement results when a specific condition is satisfied according to one embodiment of the present disclosure.

[0018] FIG. 5 is a flowchart illustrating a procedure for performing AI / ML prediction related to mobility of a terminal according to one embodiment of the present disclosure.

[0019] FIG. 6 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0020] FIG. 7 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0021] FIG. 8 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0022] FIG. 9 is a diagram illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0023] FIG. 10 is a diagram illustrating the structure of a base station according to one embodiment of the present disclosure.

[0024] In describing the embodiments in this specification, descriptions of technical details that are well known in the technical field to which the present disclosure pertains and are not directly related to the present disclosure will be omitted. This is to avoid obscuring the gist of the present disclosure by omitting unnecessary explanations and to convey the gist more clearly.

[0025] For the same reason, some components in the attached drawings are exaggerated, omitted, or schematically depicted. Furthermore, the dimensions of each component do not entirely reflect its actual size. Identical or corresponding components in each drawing are assigned the same reference numbers.

[0026] The advantages and features of the present disclosure, and methods for achieving them, will become clearer with reference to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided only to ensure that the disclosure of the present disclosure is complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

[0027] At this time, it will be understood that each block of the processing flow diagrams and combinations of the flow diagrams can be performed by computer program instructions. These computer program instructions can be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flow diagram block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to implement the functions in a specific manner, so that the instructions stored in the computer-available or computer-readable memory can also produce a manufactured item that includes an instruction means for performing the functions described in the flow diagram block(s). Since the computer program instructions may be installed on a computer or other programmable data processing device, a series of operational steps may be performed on the computer or other programmable data processing device to create a computer-executable process, and the instructions that cause the computer or other programmable data processing device to perform the steps for performing the functions described in the flowchart block(s) may also provide steps for performing the functions described in the flowchart block(s).

[0028] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions.

[0029] Here, the term '~ unit' used in the present embodiment means a software or hardware component such as an FPGA or ASIC, and the '~ unit' performs certain roles. However, the '~ unit' is not limited to software or hardware. The '~ unit' may be configured to be on an addressable storage medium and may be configured to play one or more processors. Accordingly, as an example, the '~ unit' includes components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. Additionally, components and '~parts' may be implemented to regenerate one or more CPUs within a device or secure multimedia card.

[0030] FIG. 1 is a diagram illustrating the structure of a mobile communication system according to one embodiment of the present disclosure.

[0031] Referring to FIG. 1, a wireless access network of a mobile communication system (New Radio, NR) according to an embodiment of the present disclosure may be composed of a base station (next generation Node B, hereinafter referred to as gNB) (1-10) and an AMF (1-05, access and mobility management function or New Radio Core Network). A user terminal (New Radio User Equipment, hereinafter referred to as (NR) UE or terminal) (1-15) may access an external network through the gNB (1-10) and the AMF (1-05). The mobile communication system according to an embodiment of the present disclosure may be a next generation mobile communication system, and the base station may be a next generation base station.

[0032] In Fig. 1, the gNB (1-10) may correspond to the eNB (1-30) (Evolved Node B) of the existing LTE system. The gNB is connected to the NR UE (1-15) via a wireless channel (1-20) and may provide a service superior to that of the existing Node B. In the next-generation mobile communication system according to an embodiment of the present disclosure, since all user traffic is serviced through a shared channel, a device that collects status information such as buffer status, available transmission power status, and channel status of UEs and performs scheduling is required, and the gNB (1-10) may be responsible for this. One gNB can typically control multiple cells. In order to implement ultra-high-speed data transmission compared to the existing LTE, it may have a bandwidth higher than the existing maximum, and an orthogonal frequency division multiplexing (OFDM) scheme may be used as a wireless access technology, and additional beamforming technology may be incorporated. Additionally, an adaptive modulation and coding (AMC) method that determines the modulation scheme and channel coding rate according to the channel status of the terminal can be applied.

[0033] AMF (1-05) can perform functions such as mobility support, bearer setup, and QoS (quality of service) setup. AMF (1-05) is a device that handles various control functions as well as mobility management functions for terminals and can be connected to multiple base stations.

[0034] In addition, the mobile communication system according to one embodiment of the present disclosure can be interoperable with the existing LTE system, and the AMF (1-05) can be connected to the MME (1-25, mobility management entity) through a network interface. The MME (1-25) can be connected to the existing base station, eNB (1-30). An NR UE (1-15) supporting LTE-NR Dual Connectivity can transmit and receive data while maintaining a connection (1-35) with not only the gNB (1-10) but also the eNB (1-30).

[0035] FIG. 2 is a diagram for explaining a wireless connection state transition in a mobile communication system according to one embodiment of the present disclosure.

[0036] A mobile communication system according to an embodiment of the present disclosure may have three radio connection states (RRC (radio resource control) states) or RRC modes. The connected mode (RRC_CONNECTED, 2-05) is a radio connection state in which a terminal can transmit and receive data. The idle mode (RRC_IDLE, 2-30) is a radio connection state in which a terminal monitors whether paging is transmitted to itself. The above two modes are radio connection states that are also applied to the existing LTE system, and the detailed technology is the same as that of the existing LTE system. The mobile communication system according to an embodiment of the present disclosure may be a next-generation mobile communication system.

[0037] In a mobile communication system according to one embodiment of the present disclosure, a new inactive (RRC_INACTIVE) radio connection state (2-15) is defined. In this inactive radio connection state, the UE context is maintained between the base station and the terminal, and RAN (radio access network)-based paging can be supported. The characteristics of this inactive radio connection state are listed below.

[0038] - Cell re-selection mobility;

[0039] - CN - NR RAN connection (both C / U-planes (control plane / user plane)) has been established for UE;

[0040] - The UE AS (Access Stratum) context is stored in at least one gNB and the UE;

[0041] - Paging is initiated by NR RAN;

[0042] - RAN-based notification area is managed by NR RAN;

[0043] - NR RAN knows the RAN-based notification area which the UE belongs to;

[0044] According to one embodiment of the present disclosure, a terminal in an inactive wireless connection state can transition to a connected mode or a standby mode using a specific procedure. The transition (2-10) between the connected mode and the inactive mode can be performed through Resume or Release with suspend. For example, the terminal can transition from INACTIVE mode to connected mode through the Resume procedure, and can transition from connected mode to INACTIVE mode by receiving a Release message including suspend configuration information (2-10). The above procedure is performed by transmitting and receiving one or more RRC messages between the terminal and the base station, and can consist of one or more steps. In addition, the terminal can transition from INACTIVE mode to standby mode through the Release procedure after Resume (2-20). The transition (2-25) between the connected mode and the standby mode can follow the existing LTE technology. For example, the transition between the modes can be performed through the establishment or release procedure.

[0045] FIG. 3 is a flowchart illustrating a process in which a terminal performs cell measurement and reporting operations according to one embodiment of the present disclosure.

[0046] According to one embodiment of the present disclosure, in step 3-15, the terminal (3-05) may report its capability information to the base station (3-10). In step 3-20, the base station (3-10) may transmit an RRCReconfiguration message including configuration information (measConfig IE) related to the cell measurement operation to the terminal (3-05).

[0047] The above configuration information (measConfig IE) may include information necessary for reporting the results measured by the terminal (3-05) to the base station (3-10) depending on the type of measurement report (e.g., periodical, event-triggered, event-triggered periodical). For example, in the case of “event-triggered” or “event-triggered periodical,” the terminal (3-05) may report a given measurement result when a specific event set based on the above configuration information is satisfied. For example, the following events may be set in the NR system.

[0048] - Event(s) related to typical intra- / inter-RAT measurements are as shown in Table 1 below.

[0049] Event A1: Serving becomes better than absolute threshold;Event A2: Serving becomes worse than absolute threshold;Event A3: Neighbour becomes amount of offset better than PCell / PSCell;Event A4: Neighbour becomes better than absolute threshold;Event A5: PCell / PSCell becomes worse than absolute threshold1 AND Neighbour / SCell becomes better than another absolute threshold2;Event A6: Neighbour becomes amount of offset better than SCell;Event D1: Distance between UE and a reference location referenceLocation1 becomes larger than configured threshold distanceThreshFromReference1 and distance between UE and a reference location referenceLocation2 becomes shorter than configured threshold distanceThreshFromReference2;Event B1: Neighbour becomes better than absolute threshold;Event B2: PCell becomes worse than absolute threshold1 AND Neighbour becomes better than another absolute threshold2;

[0050] - Similar to condition-based measurement reporting, in condition-based handover, when a specific event is satisfied, the terminal (3-05) can perform a handover according to condition-based handover configuration information. Event(s) related to condition-based handover are as shown in Table 2 below.

[0051] CondEvent A3: Conditional reconfiguration candidate becomes amount of offset better than PCell / PSCell;CondEvent A4: Conditional reconfiguration candidate becomes better than absolute threshold;CondEvent A5: PCell / PSCell becomes worse than absolute threshold1 AND Conditional reconfiguration candidate becomes better than another absolute threshold2;CondEvent D1: Distance between UE and a reference location referenceLocation1 becomes larger than configured threshold distanceThreshFromReference1 and distance between UE and a reference location referenceLocation2 of conditional reconfiguration candidate becomes shorter than configured threshold distanceThreshFromReference2;CondEvent T1: Time measured at UE becomes more than configured threshold t1-Threshold but is less than t1-Threshold + duration;

[0052] - (Sidelink) When a specific event is satisfied in the Relay, the terminal (3-05) can perform a specific action. Event(s) related to the Relay are as shown in Table 3 below.

[0053] Event X1: Serving L2 U2N Relay UE becomes worse than absolute threshold1 AND NR Cell becomes better than another absolute threshold2;Event

[0054] - In the case of NR-U (Unlicensed), when a specific event is satisfied, the terminal (3-05) can perform a specific action. Event(s) related to NR-U are as shown in Table 4 below.

[0055] Event I1: Interference becomes higher than absolute threshold.

[0056] In step 3-25, the terminal (3-05) can evaluate whether the configured Events are satisfied. If the previously described Events continue to satisfy a predetermined condition for a predetermined time period (time-to-trigger), the terminal (3-05) can consider the Event to be satisfied. In step 3-30, when the configured condition is satisfied, the terminal (3-05) can report a MeasurementReport message including the measurement result to the base station (3-10). Alternatively, the terminal (3-05) can perform a predetermined action corresponding to the condition, for example, a condition-based handover.

[0057] The base station (3-10) that receives the above measurement results can use the measurement results for a predetermined purpose. For example, in step 3-35, the base station (3-10) can determine whether to trigger a handover of the terminal (3-05). In step 3-40, if the base station (3-10) triggers a handover, it can request the handover to the target cell(s). In step 3-45, the base station (3-10) can transmit handover configuration information configured based on predetermined configuration information received from the target cell(s) to the terminal (3-05). In step 3-50, the terminal (3-05) that received the configuration information can perform a handover.

[0058] FIG. 4 is a diagram illustrating an operation of reporting cell measurement results when a specific condition is satisfied according to one embodiment of the present disclosure.

[0059] Referring to FIG. 4, the terminal (4-10) can evaluate the signal strength or quality of the base station (4-05) signal based on the SSB (synchronization signal block or SS / PBCH block) or CSI-RS (channel state information reference singal) transmitted from the base station (4-05). In the following, for convenience of explanation, the cell measurement result reporting operation of the terminal (4-10) is described mainly with respect to SSB, but the same can be applied to CSI-RS.

[0060] In the case of SSB, the transmission cycle of SSB can be determined according to the settings of the base station (4-05). Typically, the transmission cycle of SSB can be set to 20 ms, and the base station (4-05) can transmit SSB with a cycle of up to 160 ms.

[0061] When the base station (4-05) sets Event A2 to the terminal (4-10), the terminal (4-10) can continuously evaluate whether the RSRP value measured based on SSB is lower than the threshold for a predetermined time period (time-to-trigger, TTT) from the time point (4-15) when the RSRP (reference signal received power) value measured based on SSB becomes lower than the set absolute threshold value.

[0062] If the RSRP value measured based on SSB is continuously lower than the threshold from the initial time point (4-15) when the RSRP value becomes lower than the set absolute threshold value to the time point (4-20) when the time interval has elapsed, the terminal (4-10) may consider that the Event A2 has been satisfied and may report a measurement report triggered by Event A2 to the base station (4-05). As described above, by considering the TTT in determining whether the conditions for performing the measurement report are satisfied, the variability of the measurement signal may be compensated for. The TTT value may be set by the base station (4-05) for each Event.

[0063] If the above-mentioned Events continuously satisfy a predetermined condition for a predetermined time interval (TTT), the terminal (4-10) can perform an action corresponding to the purpose of the set Event. If the type of measurement report according to the measurement-related setting information received by the terminal (4-10) is set to “periodical” or “event-triggered periodical,” the terminal (4-10) can perform a measurement report periodically.

[0064] In the existing L3 (Layer 3) handover mechanism, handover is triggered and executed by the network or base station based on historical cell measurement results and / or cell measurement event(s) reported in the past. In other words, it can be understood as a kind of reactive manner.

[0065] This reactive handover approach can be effective for existing services when UEs move between macro cells or when UEs have low mobility. However, it can be problematic when UEs have high mobility or move between dense micro cells, or for future services such as XR. For example, it can cause unintended consequences such as handover failures, radio link failures, ping-pong behavior, throughput loss, or premature / late handovers. Accordingly, conditional handovers were introduced in Rel-16 to improve handover robustness, and lower-layer triggered mobility (LTM) handovers were introduced in Rel-18 to reduce service interruption due to frequent handovers between small cells. However, these two handover mechanisms are still reactive and may not be sufficient.

[0066] On the other hand, mechanisms based on AI / ML (Artificial Intelligence and Machine Learning) algorithms can enable proactive approaches. For example, a UE can generate predicted cell measurement information for the future using an AI / ML model and report this to the base station (or network). This allows the base station to prepare for handovers in advance, preventing delays. Furthermore, by preemptively instructing the UE to perform a handover, the base station can initiate a handover to another base station or cell before a problem (e.g., radio link failure) occurs. Furthermore, by receiving cell measurement information from the UE, the base station can achieve improved handover and / or radio resource management (RRM) performance compared to reactive approaches. For example, it can make better network operation / configuration decisions or take proactive measures to avoid unintended events.

[0067] FIG. 5 is a flowchart illustrating a procedure for performing AI / ML prediction related to mobility of a terminal according to one embodiment of the present disclosure.

[0068] In step 5-15, the terminal (5-05) may report mobility-related AI / ML prediction capabilities and / or cell measurement-related capabilities to the base station (5-10) or the network. This may be conveyed via a UE capability message (e.g., a UECapabilityInformation message). To request this, the base station may previously transmit a message (e.g., a UECapabilityRequest message) requesting transmission of the relevant terminal capabilities to the terminal. The mobility-related AI / ML prediction capabilities may mean at least one of the following or a combination thereof.

[0069] - Whether the terminal supports performing operations using AI / ML related to mobility

[0070] - Whether the terminal supports prediction using AI / ML related to mobility

[0071] - Whether the terminal supports prediction of cell-level measurements (e.g., RSRP / RSRQ / SINR) using mobility-related AI / ML

[0072] - Whether the terminal supports beam-level measurement (e.g., RSRP / RSRQ / SINR) prediction using mobility-related AI / ML

[0073] - Whether the terminal supports handover failure prediction using mobility-related AI / ML

[0074] - Whether the terminal supports RLF (Radio link failure) prediction using mobility-related AI / ML

[0075] - Whether the terminal supports prediction of specific events (e.g., event A3) using mobility-related AI / ML

[0076] When more than one AI / ML model is defined / indicated, the aforementioned mobility-related AI / ML prediction capabilities may be defined / indicated per AI / ML model (e.g., per model ID).

[0077] Examples of specific events using the above mobility-related AI / ML may be as shown in Table 5 below.

[0078] Event A1: Serving becomes better than absolute threshold;Event A2: Serving becomes worse than absolute threshold;Event A3: Neighbour becomes amount of offset better than PCell / PSCell;Event A4: Neighbour becomes better than absolute threshold;Event A5: PCell / PSCell becomes worse than absolute threshold1 AND Neighbour / SCell becomes better than another absolute threshold2;Event A6: Neighbour becomes amount of offset better than SCell;Event D1: Distance between UE and a reference locationreferenceLocation1becomes larger than configured thresholddistanceThreshFromReference1and distance between UE and a reference locationreferenceLocation2becomes shorter than configured thresholddistanceThreshFromReference2;CondEvent A3: Conditional reconfiguration candidate becomes amount of offset better than PCell / PSCell;CondEvent A4: Conditional reconfiguration candidate becomes better than absolute threshold wherecondEventA4can also be used for current PSCell (i.e., in case it is configured as candidate PSCell for CondEvent A4 evaluation) for CHO with candidate SCG(s) case;CondEvent A5: PCell / PSCell becomes worse than absolute threshold1 AND Conditional reconfiguration candidate becomes better than another absolute threshold2;CondEvent D1: Distance between UE and a reference locationreferenceLocation1becomes larger than configured thresholddistanceThreshFromReference1and distance between UE and a reference locationreferenceLocation2of conditional reconfiguration candidate becomes shorter than configured thresholddistanceThreshFromReference2;CondEvent D2: Distance between UE and a moving reference location determined based onreferenceLocation1becomes larger than configured thresholddistanceThreshFromReference1and distance between UE and a moving reference location determined based onreferenceLocation2of conditional reconfiguration candidate becomes shorter than configured thresholddistanceThreshFromReference2;CondEvent T1: Time measured at UE becomes more than configured thresholdt1-Thresholdbut is less thant1-Threshold + duration;Event X1: Serving L2 U2N Relay UE becomes worse than absolute threshold1 AND NR Cell becomes better than another absolute threshold2;Event X2: Serving L2 U2N Relay UE becomes worse than absolute threshold;For event I1, measurement reporting event is based on CLI measurement results, which can either be derived based on SRS-RSRP or CLI-RSSI.Event I1: Interference becomes higher than absolute threshold.The reporting events concerning Aerial UE altitude are labelled HNwithNequal to 1 and 2. Additionally, the reporting events concerning Aerial UE altitude and the neighboring cell measurements simultaneously are labelled AMHNwithMequal to 3, 4, 5 andNequal to 1, 2.Event H1: Aerial UE altitude becomes higher than a threshold;Event H2: Aerial UE altitude becomes lower than a threshold.Event A3H1: Neighbour becomes offset better than SpCell and the Aerial UE altitude becomes higher than a threshold.Event A3H2: Neighbour becomes offset better than SpCell and the Aerial UE altitude becomes lower than a threshold.Event A4H1: Neighbour becomes better than threshold1 and the Aerial UE altitude becomes higher than a threshold2.Event A4H2: Neighbour becomes better than threshold1 and the Aerial UE altitude becomes lower than a threshold2.Event A5H1: SpCell becomes worse than threshold1 and neighbour becomes better than threshold2 and the Aerial UE altitude becomes higher than a threshold3.Event A5H2: SpCell becomes worse than threshold1 and neighbour becomes better than threshold2 and the Aerial UE altitude becomes lower than a threshold3.;

[0079] If the terminal supports the aforementioned mobility-related AI / ML prediction capabilities and / or cell measurement-related capabilities, it may indicate to the base station support for the aforementioned capabilities by including the relevant indicator in the UE capability message or setting it to a specific value (e.g., true). Additionally or alternatively, if the terminal does not support the aforementioned capabilities, it may indicate to the base station that it does not support the aforementioned capabilities by not including the relevant indicator in the UE capability message or setting it to a specific value (e.g., false).

[0080] In step 5-20, the base station (5-10) may provide cell measurement and AI / ML prediction-related settings to the terminal (5-05). These settings may be generated and provided based on the terminal's capabilities received in step 5-15. These settings may include information about the AI / ML model (UE-sided model) being executed by the terminal. Alternatively, information about the AI / ML model being executed by the terminal may be provided to the terminal from an external server (e.g., OTT).

[0081] Additionally or optionally, the terminal may receive cell measurement configuration (e.g., MeasConfig) from the base station together with or separately from the AI / ML prediction related configuration. The cell measurement configuration may be transmitted via an RRC Reconfiguration message or an RRC Resume message, and may include information on “measurement objects” that indicate radio resource information on which the terminal is to perform measurements. For example, each measurement object may indicate frequency / time location and / or subcarrier spacing information of a reference signal (e.g., SSB or CSI-RS) on which the terminal is to perform measurements. Each measurement object configuration (e.g., MeasObjectNR) may be indicated / identified by a specific ID (e.g., MeasObjectId).

[0082] Additionally or optionally, the configuration may include “Reporting configurations” that indicate configurations related to measurement reporting of the terminal. For example, each reporting configuration may indicate whether the terminal should report periodically or trigger upon the satisfaction of a specific event, and may indicate a reference signal used by the terminal for measurement / reporting. Each reporting configuration (e.g., ReportConfigNR) may be indicated / identified by a specific ID (e.g., ReportConfigId). A cell measurement configuration (e.g., MeasConfig) may include one or more measurement object configurations (e.g., MeasObjectNR) and / or one or more reporting configurations (e.g., ReportConfigNR), and a specific measurement object may be associated with a specific reporting configuration. For this purpose, the cell measurement configuration may include an association ID (e.g., MeasId) to indicate / identify an association between the ID of the associated measurement object and the ID of the reporting configuration. In this case, in steps 5-25 and 5-30 described below, the terminal can perform measurement and reporting according to the corresponding measurement object and associated reporting settings.

[0083] In step 5-25, the terminal (5-05) can perform cell measurement and AI / ML prediction according to the received cell measurement and AI / ML prediction related settings.

[0084] In step 5-30, the terminal (5-05) can transmit information / report generated as a result of cell measurement and AI / ML prediction (result of AI / ML model operation) to the base station (e.g., via a MeasurementReport message). For example, the terminal can transmit cell measurement values ​​predicted in the future (e.g., reference signal received power (RSRP), reference signal received quality (RSRQ), signal to interference and noise ratio (SINR)) to the base station. The predicted cell measurement value may be a cell-level measurement value or a beam-level measurement value. The predicted cell measurement value may be a value generated by combining measurement result values ​​received from a physical layer and a prediction value using AI / ML prediction values ​​(e.g., using Layer 3 filtering). Alternatively, the predicted cell measurement value may be a value generated only with AI / ML prediction values ​​(e.g., using Layer 3 filtering). By including an associated ID (e.g., MeasId) in each measurement report (e.g., MeasResults), the UE can indirectly indicate to the base station which measurement object (e.g., indicated by MeasObjectId) and which report configuration (e.g., indicated by ReportConfigId) the measurement report was generated from. As a result of running the AI / ML model, the UE can report predicted events (e.g., Event A3, RLF, handover failure) to the base station in addition to predicted cell measurement values ​​(e.g., RSRP, RSRQ, SINR). Furthermore, the UE can indicate to the network how accurate the prediction is or how likely it is to occur by also indicating the prediction accuracy or occurrence probability of the predicted cell measurement value or event to the network.

[0085] If a terminal transmits the predicted cell measurement values ​​to the base station by running the UE-sided model, the base station can use this to prepare for the terminal's handover in advance or to handover the terminal to another cell or base station in advance before the occurrence of an RLF. The base station can also prevent the handover ping-pong phenomenon. However, from the terminal's perspective, running the UE-sided AI / ML model can be a task that requires a large amount of computing resources and energy consumption. Furthermore, if the predicted information generated by running the AI / ML model is excessive, this can lead to a large signaling overhead between the terminal and the network, which can result in a waste of radio resources. Therefore, the network needs to instruct / configure the terminal with the AI / ML prediction-related settings appropriate to the situation (e.g., under the network's judgment).

[0086] In one embodiment of the present disclosure, in step 5-20, the base station may optionally provide AI / ML prediction settings to the terminal. In this case, the cell measurement settings and the AI / ML prediction settings may be linked. In step 5-20, the terminal may receive one or more measurement objects (e.g., each indicated by MeasObjectId), one or more report settings (e.g., each indicated by ReportConfigId) through the cell measurement settings, and one or more linkage IDs (e.g., MeasId) linking them.

[0087] In one embodiment of the present disclosure, in step 5-20, the base station may indicate that the reporting configuration is to be used for AI / ML prediction by including an AI / ML prediction indicator or related configuration information in the reporting configuration (e.g., ReportConfig). Upon receiving this, the terminal may perform AI / ML prediction during cell measurement / reporting associated with the reporting configuration indicated above in steps 5-25 and 5-30, and report the AI / ML prediction results (e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0088] In one embodiment of the present disclosure, in step 5-20, the base station may indicate a report configuration ID (e.g., ReportConfigId) to use for AI / ML prediction. Upon receiving this, the terminal may perform AI / ML prediction during cell measurement / reporting associated with the report configuration indicated above (e.g., the report configuration indicated by ReportConfigId) in steps 5-25 and 5-30, and report the AI / ML prediction results (e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0089] In one embodiment of the present disclosure, in step 5-20, the base station may indicate a linkage ID (e.g., MeasId) to use for AI / ML prediction. Upon receiving this, the terminal may perform AI / ML prediction during cell measurement / reporting indicated by the linkage ID (e.g., MeasId) indicated above in steps 5-25 and 5-30, and report the AI / ML prediction results (e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0090] In one embodiment of the present disclosure, in step 5-20, the base station may indicate that the measurement object (e.g., MeasObjectNR) is to be used for AI / ML prediction by including an AI / ML prediction indicator or related configuration information in the measurement object. The terminal receiving this may perform AI / ML prediction when measuring / reporting a cell associated with the measurement object indicated above in steps 5-25 and 5-30, and report the AI / ML prediction result value (e.g., predicted RSRP, RSRQ, SINR value) to the base station.

[0091] In one embodiment of the present disclosure, in step 5-20, the base station may indicate a measurement object ID (e.g., MeasObjectId) to use for AI / ML prediction. Upon receiving this, the terminal may perform AI / ML prediction when measuring / reporting cells associated with the measurement object indicated above (e.g., indicated by MeasObjectId) in steps 5-25 and 5-30, and report the AI / ML prediction results (e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0092] In one embodiment of the present disclosure, in step 5-20, a measurement object (e.g., MeasObjectAIML) that will utilize AI / ML prediction can be defined separately from a cell measurement object (e.g., MeasObject), and the base station can use the separate measurement object to indicate the measurement object that will utilize AI / ML prediction. The terminal that receives this can perform AI / ML prediction when measuring / reporting cells linked to the measurement object indicated above in steps 5-25 and 5-30, and report the AI / ML prediction result values ​​(e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0093] In one embodiment of the present disclosure, in step 5-20, a reporting configuration (e.g., ReportConfigAIML) that utilizes AI / ML prediction may be defined separately from a cell reporting configuration (e.g., ReportConfig), and the base station may use the separate reporting configuration to indicate a reporting configuration that utilizes AI / ML prediction. Upon receiving this, the terminal may perform AI / ML prediction during cell measurement / reporting linked to the reporting configuration indicated above in steps 5-25 and 5-30, and report the AI / ML prediction result values ​​(e.g., predicted RSRP, RSRQ, SINR values) to the base station.

[0094] In one embodiment of the present disclosure, the AI / ML prediction result values ​​(e.g., predicted RSRP, RSRQ, SINR values) transmitted by the terminal in step 5-30 may be transmitted together with actual cell measurement values ​​(e.g., actual measured RSRP, RSRQ, SINR values). In order to distinguish between the AI / ML prediction result values ​​included in the measurement report by the terminal and the actual cell measurement values, an IE or parameter dedicated to the AI / ML prediction result values ​​may be defined and included in the measurement report. For example, a new IE such as MeasResultsAIML may be defined, and the actual cell measurement values ​​in the measurement report message (e.g., MeasurementReport) transmitted by the terminal to the base station may be included in MeasResults and the AI / ML prediction result values ​​may be included in MeasResultsAIML and transmitted. As another example, a separate parameter (e.g., measResultServingMOListAIML, measResultNeighCellsAIML) including the AI / ML prediction result values ​​in MeasResults may be newly defined and reported to the base station.

[0095] In one embodiment of the present disclosure, in step 5-30, the terminal may report only measurement values ​​(RSRP and / or RSRQ and / or SINR) for one measurement point per cell (e.g., indicated by PhyscellId) or per beam for conventional cell measurement values ​​(e.g., MeasResultNR), but may report measurement values ​​for one or more future points in time for AI / ML prediction values, respectively. For example, in step 5-30, the terminal may transmit to the base station for a specific cell RSRP and RSRQ and SINR prediction values ​​for 2 seconds in the future, RSRP and RSRQ and SINR prediction values ​​for 4 seconds in the future, and RSRP and RSRQ and SINR prediction values ​​for 6 seconds in the future. The network or the base station may set a time interval (e.g., 2 seconds in the above example) between prediction values ​​to the terminal in step 5-20. For example, when the channel condition of a terminal changes rapidly (e.g., when the terminal is moving), the network or base station can receive a result that predicts the rapidly changing channel condition quickly and accurately by setting a short prediction interval in the near future. Conversely, for a terminal with a relatively static channel, the network or base station may want to obtain intermittent prediction results by setting a long prediction interval. In addition, the network or base station may set the maximum number of prediction values ​​that the terminal will report at one time (e.g., in MeasResultNR) in step 5-20. For example, if the network or base station determines that the signaling overhead is large, the network or base station may instruct the terminal to report only a relatively small number of prediction values. Conversely, if the network or base station wants to obtain a large number of prediction values ​​from the terminal, the network or base station may instruct the terminal to report a relatively large number of prediction values.

[0096] In one embodiment of the present disclosure, in step 5-30, the terminal may transmit to the base station the difference (e.g., -10 dB) between the current measured value or the previous predicted value (e.g., -60 dBm) and the predicted value, rather than the absolute value (e.g., -70 dBm) for the predicted value. For example, the terminal may transmit to the base station the difference (e.g., -3 dB) between the current measured value and the predicted RSRP value 2 seconds later (e.g., -40 dBm) and the difference (e.g., -5 dB) between the current measured value and the predicted RSRP value 4 seconds later (e.g., -38 dBm) and the difference (e.g., -2 dB) between the current measured value and the predicted RSRP value 6 seconds later (e.g., -45 dBm) and the difference (e.g., -43 dBm) for the current cell. For another example, the UE may transmit to the BS the difference (e.g., 3dB) between the current measured RSRP (e.g., -43dBm) and the predicted RSRP 2 seconds from now (e.g., -40dBm) compared to the previous predicted value, the difference (e.g., 2dB) between the predicted RSRP 4 seconds from now (e.g., -38dBm) and the previous measured value (e.g., 2dB) between the predicted RSRP 2 seconds from now (e.g., -40dBm), and the difference (e.g., -7dB) between the predicted RSRP 6 seconds from now (e.g., -45dBm) and the previous measured value (e.g., -38dBm). While RSRP is an example in the above description, other measurement metrics such as RSRQ and SINR can be applied in the same way. This allows the UE to transmit the predicted values ​​to the BS using fewer bits than if it were to indicate the absolute RSRP / RSRQ / SINR values.

[0097] In one embodiment of the present disclosure, in steps 5-20, the network or base station may set restrictions on the cells or neighboring cells in which the terminal performs and / or reports AI / ML prediction measurements. Such restrictions may be necessary to reduce the terminal's computer resource and energy consumption due to excessive AI / ML model execution, and at the same time, to reduce excessive wireless resource usage due to excessive AI / ML prediction-related reporting.

[0098] In one embodiment of the present disclosure, the network or base station may indicate one or more cells or neighboring cells within the measurement object in step 5-20. The terminal may perform AI / ML prediction and / or reporting for the indicated cells in steps 5-25 and 5-30, and may not perform AI / ML prediction and / or reporting for cells that are not indicated.

[0099] In one embodiment of the present disclosure, the network may limit the maximum number of cells or neighboring cells for which the terminal performs and / or reports AI / ML prediction in step 5-20. The terminal may perform AI / ML prediction and / or reporting for cell(s) within the indicated number in steps 5-25 and 5-30. For example, if more cells or neighboring cells are detected than the indicated number, the terminal may select cells within the indicated number in descending order of actual cell measurement value (RSRP or RSRQ or SINR). Thereafter, the terminal may perform AI / ML prediction and / or reporting for the selected terminals. For another example, if more cells or neighboring cells are detected than the indicated number, the terminal may first perform AI / ML prediction on all detected / measured cells, and then select cells within the indicated number in descending order of predicted cell measurement value (RSRP or RSRQ or SINR) or prediction accuracy / probability. Afterwards, the terminal can perform AI / ML reporting on the selected cells.

[0100] In one embodiment of the present disclosure, the terminal may predict and report to the base station not only the cell measurement values ​​predicted in steps 5-30 but also specific events (e.g., handover failure, RLF, Event A2) as a result (output) of the AI / ML model operation. Additionally or optionally, the terminal may include in the report and transmit, as an output of the AI / ML model operation, the time and / or section (e.g., including a case where the event is satisfied at least once within the section or the event is satisfied throughout the section) at which the event is predicted to occur.

[0101] In one embodiment of the present disclosure, the terminal may transmit actual cell measurement values ​​and / or predicted cell measurement values ​​as outputs of the AI / ML model operation in the report. Additionally or optionally, the terminal may transmit the probability of the event occurring and / or the prediction accuracy as outputs of the AI / ML model operation in the report.

[0102] Meanwhile, since the AI / ML model operated by the terminal can generate different outputs depending on the input information (e.g., terminal mobility, cell measurement values, location information), the content previously reported by the terminal may change. For example, the terminal predicts the detection of a specific event (e.g., predicts the event of time t1 at time T1, T1 < t1) and reports this to the base station (Report 1), but the terminal may predict that the event will no longer occur (e.g., predicts that the event at time t1 will not occur at time T2, T1 < T2 < t1). At this time, the terminal can indicate to the base station that the previous report (Report 1) is no longer valid through a new report (Report 2). As another example, the terminal may indicate to the base station that the previous prediction is invalid if at least one of the following conditions is satisfied, or may indicate / report that the condition is satisfied.

[0103] - Condition 1. If the terminal predicts that the event predicted in the previous report will no longer occur (e.g., if the leaving condition of the event is satisfied).

[0104] - Condition 2. If the predicted probability (at the present or a specific point in time t) for an event predicted by the terminal in the previous report is less than a specific threshold.

[0105] - Condition 3. If the predicted probability (at the present or a specific point in time t) for an event predicted by the terminal in the previous report is less than the predicted probability in the previous report.

[0106] - Condition 4. If the predicted probability (at the present or at a specific point in time) for an event predicted by the terminal in the previous report is less than the predicted probability in the previous report minus a specific hysteresis value.

[0107] - Condition 5. If the time point (e.g., T2) at which the prediction is made that the event (currently or at a specific point in time) will not occur is earlier than the expected event occurrence time (e.g., t1) or interval in the last report.

[0108] - Condition 6. If the prediction time window of the time point predicted by the terminal includes a time point or section within the past prediction time window in which the event was instructed / reported to occur in the last report (for example, the base station may instruct / configure the terminal to perform event prediction for the section between time a (e.g., 3 seconds) after the prediction time point and time b (e.g., 10 seconds) after the prediction time point in step 5-20, and the terminal may predict an event occurring within the prediction time window of length ba (e.g., 7 seconds). The window may move together on the time axis as time passes. In this situation, the terminal may predict the event occurring within the prediction time window [t 1,1 , t 1,2 ] can predict at time T1 that a specific event will occur at a specific time t1 within the time period, and report the result to the base station. At this time, t 1,1 is T1+a seconds, t 1,2 can be T1+b seconds. After that, the terminal uses the prediction time window [t 2,1 , t 2,2 ] I can predict at time T2 (>T1) that my above-mentioned time point t1 is included and that the above-mentioned event will no longer occur at t1. At this time, t2,1 is T2+a seconds, t 2,2 may be T2+b seconds.)

[0109] Information about the aforementioned threshold value, hysteresis value, prediction target time point, and / or prediction time window (e.g., a, b) may be determined through predefined fixed values, or may be determined based on values ​​set / indicated by the network in steps 5-20.

[0110] In steps 5-30, the terminal may indicate that the previous measurement report for the associated ID is invalid or satisfies one of the above conditions by including a linkage ID (e.g., MeasId) and / or a specific new indicator. Alternatively, the terminal may indicate that the previous measurement report is invalid or satisfies one of the above conditions by reporting the associated ID (e.g., MeasId) but not including information about the time or time interval when the event occurred. In this case, if the terminal reports the associated ID (e.g., MeasId) and includes information about the time or time interval when the event is expected to occur, this may mean that the terminal changes / updates the time or time interval when the event occurs.

[0111] In one embodiment of the present disclosure, a new event for cell measurement reporting or cell measurement prediction value reporting may be defined. For example, in step 5-20, the base station may include information about the event in a report configuration (e.g., ReportConfigNR) and transmit it to the terminal. The event may be composed of at least one of the following examples, or a combination thereof.

[0112] - Event 1. The entering condition of an event may be satisfied when the variation (or variation minus a positive hysteresis value) of a measurement value (e.g., Layer 3 filtered RSRP and / or RSRQ and / or SINR) for a serving cell or a neighboring cell is greater than a certain threshold value for a certain time to trigger (TTT) period (e.g., when the UE is moving).

[0113] * For example, the variation range of the above cell measurement value may be the variance value or standard deviation value of the cell measurement value.

[0114] * For example, the variation of the cell measurement value may be defined as the difference between the reference value of the cell measurement value and the current cell measurement value, and the reference value may be a value that is reset to the cell measurement value at that point in time whenever a specific condition is satisfied (e.g., when the measurement value at that point in time is greater than the reference value, when the entering condition of the event is not satisfied during the TTT, after completing a handover to a new base station, after successfully completing random access to a new base station, etc.).

[0115] Conversely, the leaving condition of an event may be satisfied when the variation (or variation plus a positive hysteresis value) of a measurement value (e.g., Layer 3 filtered RSRP and / or RSRQ and / or SINR) for the serving cell or neighboring cells is less than a certain threshold for a certain time to trigger (TTT) period (e.g., when the UE is stationary). The base station may also set a parameter (e.g., reportOnLeave) indicating whether to allow or disallow the UE to report the measurement value and / or prediction value when the leaving condition is satisfied.

[0116]

[0117] - Event 2. The entering condition of an event may be satisfied when the variation (or variation minus a positive hysteresis value) of a predicted measurement value (e.g., predicted Layer 3 filtered RSRP and / or RSRQ and / or SINR) for a serving cell or a neighboring cell is greater than a certain threshold value for a certain time to trigger (TTT) period (e.g., when the UE is moving).

[0118] * For example, the variation range of the cell prediction measurement value may be the variance value or standard deviation value of the cell prediction measurement value.

[0119] * For example, the variation of the cell prediction measurement value may be defined as the difference between the reference value of the cell prediction measurement value and the cell prediction measurement value, and the reference value may be a value that is reset to the cell prediction measurement value whenever a specific condition is satisfied (e.g., when the prediction value is greater than the reference value, when the entering condition of the event is not satisfied during the TTT, when a handover to a new base station is completed or is predicted to be completed, when a random access to a new base station is successfully completed or is predicted to be completed, etc.).

[0120] Conversely, the leaving condition of an event may be satisfied when the variation (or variation plus a positive hysteresis value) of predicted measurements (e.g., predicted Layer 3 filtered RSRP and / or RSRQ and / or SINR) for the serving cell or neighboring cells is less than a certain threshold for a certain time to trigger (TTT) period (e.g., when the UE is stationary). The base station may also set a parameter (e.g., reportOnLeave) indicating whether to allow or disallow the UE to perform measurement and / or predicted value reporting when the leaving condition is satisfied.

[0121] - Event 3. The entering condition in the aforementioned Event 1 can be defined as the leaving condition of Event 3, and the leaving condition in the aforementioned Event 1 can be defined as the entering condition of Event 3.

[0122] - Event 4. The entering condition in the aforementioned Event 2 can be defined as the leaving condition of Event 4, and the leaving condition in the aforementioned Event 2 can be defined as the entering condition of Event 4.

[0123] - Event 5. The entering condition of an event may be satisfied when a predicted measurement value (e.g., predicted Layer 3 filtered RSRP and / or RSRQ and / or SINR) for the serving cell or neighboring cell (or the predicted value minus a positive hysteresis value) is greater than a certain threshold value for a certain time to trigger (TTT) period (e.g., when the UE is close to the cell).

[0124] Conversely, the leaving condition of an event may be satisfied when a predicted measurement value (e.g., predicted Layer 3 filtered RSRP and / or RSRQ and / or SINR) for the serving cell or a neighboring cell (or a predicted value plus a positive hysteresis value) is less than a certain threshold for a certain time to trigger (TTT) period (e.g., when the UE is far away from the cell). The base station may also set a parameter (e.g., reportOnLeave) indicating whether to allow or disallow the UE to perform measurement and / or predicted value reporting when the leaving condition is satisfied.

[0125] - Event 6. The entering condition in the aforementioned event 5 can be defined as the leaving condition of event 6, and the leaving condition in the aforementioned event 5 can be defined as the entering condition of event 6.

[0126] - Event 7. The event entering condition may be satisfied when an RLF for the serving cell or a neighboring cell is predicted / detected. Additionally or optionally, the event leaving condition may be satisfied when an RLF for the serving cell or a neighboring cell is (no longer) predicted / detected.

[0127] - Event 8. The entering condition in the aforementioned event 7 can be defined as the leaving condition of event 8, and the leaving condition in the aforementioned event 7 can be defined as the entering condition of event 8.

[0128] - Event 9. The event entering condition may be satisfied when a Handover Failure (HOF) (for a target / neighboring cell) is predicted / detected. Additionally or optionally, the event leaving condition may be satisfied when a Handover Failure (HOF) (for a target / neighboring cell) is no longer predicted / detected.

[0129] - Event 10. The entering condition in the aforementioned event 9 can be defined as the leaving condition of event 10, and the leaving condition in the aforementioned event 8 can be defined as the entering condition of event 9.

[0130] - Event 11. The event entering condition may be satisfied when the time of stay (TOS) in the target cell where the handover is completed is predicted / detected to be short. For example, the event entering condition may be satisfied when the TOS of the handover is predicted / detected to be below a certain threshold. Additionally or optionally, the event leaving condition may be satisfied when the TOS of the handover is predicted / detected to be long. For example, the event leaving condition may be satisfied when the TOS of the handover is predicted / detected to be above a certain threshold.

[0131] - Event 12. The entering condition in the aforementioned event 11 can be defined as the leaving condition of event 12, and the leaving condition in the aforementioned event 11 can be defined as the entering condition of event 12.

[0132] In one embodiment of the present disclosure, when comparing the hierarchical relationship of cell measurement values ​​or predicted values ​​to confirm whether the entering condition and leaving condition described above are satisfied, the terminal may calculate by applying a different offset for each cell or an offset for each measurement object.

[0133] In one embodiment of the present disclosure, at least one of the aforementioned threshold and TTT and hysteresis and indicator reportOnLeave and cell-specific offset and measurement object-specific offset may be a predefined fixed value, and may be a value set / indicated by the network in steps 5-20.

[0134] In one embodiment of the present disclosure, the terminal may perform cell measurement value and / or prediction value reporting in steps 5-30 if the entering condition or leaving condition of the event (e.g., when the reportOnLeave indicator is set to true) is satisfied. The terminal may stop the ongoing reporting in steps 5-30 if the leaving condition of the event is satisfied.

[0135] In one embodiment of the present disclosure, if the entering condition or leaving condition of the event (e.g., when the reportOnLeave indicator is set to true) is satisfied, the terminal may perform prediction and / or prediction reporting in steps 5-25 and / or 5-30. If the leaving condition of the event is satisfied, the terminal may stop the prediction performance and / or prediction reporting that was in progress in steps 5-25 and / or 5-30.

[0136] In one embodiment of the present disclosure, the values ​​predicted and / or measured by the terminal may be Layer 3 RSRP and / or RSRQ and / or SINR. These values ​​may be values ​​obtained by filtering Layer 1 RSRP and / or RSRQ and / or SINR values.

[0137] In one embodiment of the present disclosure, the values ​​predicted and / or measured by the terminal may be Layer 1 RSRP and / or RSRQ and / or SINR.

[0138] In one embodiment of the present disclosure, a base station or a network may disable or enable AI / ML prediction and / or reporting of a terminal. From the terminal's perspective, performing AI / ML prediction may consume a large amount of computing resources and energy, and reporting the resulting results may require a large amount of radio resources and may consume energy due to transmission. To prevent excessive energy consumption, the base station may instruct the terminal to disable the settings for AI / ML prediction (reporting) provided to the terminal (e.g., the setting information provided in step 5-20) depending on the situation / need (e.g., when it is determined that there is no problem with the terminal performance even without the AI / ML prediction report of the terminal), and may reset it later (e.g., when it is determined that the terminal's AI / ML prediction report is necessary due to a problem with the terminal performance).

[0139] However, the repetitive release and reset of the setting information for AI / ML prediction (reporting) requires a large amount of radio resources (e.g., AI / ML model transmission) and may cause delays in the process, preventing immediate AI / ML release and reset. Therefore, rather than instructing the terminal to release the setting for AI / ML prediction (reporting), it may be more efficient to temporarily suspend (disable) the operation according to the setting for the relevant AI / ML prediction (reporting). For example, if the terminal is instructed to deactivate the performance of AI / ML prediction, the terminal may maintain the setting for AI / ML prediction (reporting) but suspend the related operation (prediction / reporting). In addition, if the base station later instructs to resume (enable) the performance of AI / ML prediction, the terminal may reuse the setting for AI / ML prediction (reporting) and perform the prediction / reporting operation again. The procedure for activating and deactivating the setting for AI / ML prediction (reporting) will be described later in the description of FIG. 6.

[0140] FIG. 6 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0141] The descriptions of Steps 6-15 through 6-30 can refer to the descriptions of Steps 5-15 through 5-30.

[0142] In step 6-15, the terminal (6-05) may transmit information to the base station (6-10) or the network regarding whether it supports the function for enabling and disabling the AI / ML prediction (reporting) setting. For example, by including or setting a specific indicator to true in the UE capability information message, it may indicate whether the capability is supported, and by omitting or setting a specific indicator to false, it may indicate disabling the capability. Information regarding whether it supports the function for enabling and disabling the AI / ML prediction (reporting) setting may be transmitted together with or separately from the mobility-related AI / ML prediction capabilities listed in the description of FIG. 5. In step 6-35, the base station (6-10) may instruct the terminal (6-05) to deactivate the configuration information for the AI / ML prediction (reporting) provided in step 6-20. For example, the base station may instruct the deactivation of the configuration information for the AI / ML prediction (reporting) because it determines that there is no longer an issue with the terminal and network performance without the terminal's AI / ML prediction reporting. The above deactivation may be indicated by a medium access control (MAC) control element (CE) or an RRC message (e.g., using a reporting configuration), and the base station may indicate the association ID to be deactivated and / or the reporting configuration ID (or by including a specific indicator within the corresponding reporting configuration) and / or the measurement object ID (or by including a specific indicator within the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or the deactivation period.

[0143] At step 6-40, the terminal (6-05) may stop prediction using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0144] In step 6-45, the terminal (6-05) may stop reporting measurements using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0145] In step 6-50, the base station (6-10) may instruct the terminal (6-05) to resume or activate the configuration information for the deactivated AI / ML prediction (reporting). For example, the base station may detect a problem with the terminal and network performance and instruct the terminal to resume / activate the AI / ML prediction reporting. The activation may be indicated by a MAC CE or RRC message (e.g., using a reporting configuration), and the base station may indicate the association ID to be activated and / or the reporting configuration ID (or by including a specific indicator in the corresponding reporting configuration) and / or the measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or the activation period. Here, resuming or activating the configuration information for the AI / ML prediction (reporting) does not necessarily require that deactivation be previously indicated. For example, if the terminal receives cell measurement and AI / ML prediction related settings in step 6-20, it may store the settings without immediately performing AI / ML prediction / measurement, and may activate AI / ML prediction / measurement only when it receives a MAC CE or RRC message activating AI / ML prediction. In step 6-55, the terminal (6-05) may resume prediction using the AI / ML model and / or configuration information for which activation has been instructed (e.g., during an activation period set by the base station). The terminal may perform the operation of step 5-25 for prediction using the configuration information for the resumed AI / ML prediction (report).

[0146] In step 6-60, the terminal (6-05) may resume measurement reporting using the activated AI / ML model and / or configuration information (e.g., during an activation period set by the base station). The terminal may perform the operations of step 5-30 for measurement reporting using the configuration information for the resumed AI / ML prediction (report).

[0147] In one embodiment of the present disclosure, a terminal may transmit its preference for activating / deactivating AI / ML prediction and / or reporting to a base station or network. As described above, AI / ML prediction and / or reporting is an operation that requires a significant load or energy on the terminal, so the terminal may transmit its request, and the base station or network may consider this and instruct the terminal to activate / deactivate it. The procedure for activating and deactivating AI / ML prediction (reporting) based on the terminal's preference will be described later in the description of FIG. 7.

[0148] FIG. 7 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0149] The descriptions of Steps 7-15 through 7-30 can refer to the descriptions of Steps 5-15 through 5-30.

[0150] In step 7-15, the terminal (7-05) may transmit to the base station (7-10) or the network information regarding whether it supports the function for activating and deactivating settings for AI / ML prediction (reporting). For example, by including a specific indicator in the UE capability information message or setting it to true, it may indicate whether the capability is supported, and by omitting a specific indicator or setting it to false, it may indicate non-support for the capability. In addition, in step 7-15, the terminal may transmit to the base station or the network information regarding whether it supports the function for transmitting the terminal's preference for activating and deactivating settings for AI / ML prediction (reporting). For example, by including a specific indicator in the UE capability information message or setting it to true, it may indicate whether the capability is supported, and by omitting a specific indicator or setting it to false, it may indicate non-support for the capability. Information on whether the function for enabling and disabling settings for AI / ML prediction (reporting) is supported and / or information on whether the function for transmitting the terminal's preference for enabling and disabling settings for AI / ML prediction (reporting) is supported may be transmitted together with or separately from the mobility-related AI / ML prediction capabilities listed in the description of FIG. 5.

[0151] In step 7-20, the base station (7-10) may provide the terminal (7-05) with settings related to cell measurement and AI / ML prediction, together with or separately from the settings related to AI / ML prediction, settings regarding the terminal's preferred transmission for activating and deactivating settings for AI / ML prediction (reporting) (e.g., to allow / instruct preferred transmission). For example, the preferred transmission settings of the terminal may be included as part of settings regarding UE Assistance Information in an RRC Reconfiguration message that the base station transmits to the terminal. At this time, a prohibit timer for the preferred transmission of the terminal may be set to control frequent preferred transmission of the terminal. Alternatively, the preferred transmission settings of the terminal may be included as settings in a UE information request message that the base station transmits to the terminal. The base station may indicate a link ID and / or a reporting configuration ID (or by including a specific indicator in the corresponding reporting configuration) and / or a measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., a model ID) that instruct / allow the terminal's preferred transmission.

[0152] In step 7-32, the terminal (7-05) may indicate to the base station (7-10) that it prefers to deactivate some or all of the AI / ML prediction / reporting configurations (e.g., when the terminal is overloaded or for energy saving purposes). The terminal may transmit a specific indicator defined for the indication in a UE assistance information message or a UE information response message or a Measurement report message. The terminal may indicate an association ID and / or a reporting configuration ID (or by including a specific indicator in the corresponding reporting configuration) and / or a measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., a model ID) for which it prefers to deactivate.

[0153] In step 7-35, the base station (7-10) may instruct the terminal (7-05) to deactivate the configuration information for the AI / ML prediction (report) provided in step 7-20. For example, the base station may decide to deactivate considering the terminal's preference for deactivation. For example, the base station may instruct the deactivation because it determines that there is no problem with the terminal and network performance even without the terminal's AI / ML prediction report any longer. The deactivation may be indicated by a MAC CE or RRC message (e.g., using a report configuration), and the base station may indicate the association ID to be deactivated and / or the report configuration ID (or by including a specific indicator in the corresponding report configuration) and / or the measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or the deactivation period.

[0154] In step 7-40, the terminal (7-05) may stop prediction using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0155] In step 7-45, the terminal (7-05) may stop reporting measurements using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0156] In step 7-47, the terminal (7-05) may indicate to the base station (7-10) that it prefers to activate / restart some or all of the AI / ML prediction / reporting configurations (e.g., when the terminal's overload is resolved or when energy usage becomes available). The terminal may transmit a specific indicator defined for the indication, including a UE assistance information message, a UE information response message, or a Measurement report message. The terminal may indicate an association ID and / or a reporting configuration ID (or by including a specific indicator in the corresponding reporting configuration) and / or a measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., a model ID) for which it prefers to activate.

[0157] In step 7-50, the base station (7-10) may instruct the terminal (7-05) to resume or activate the configuration information for the deactivated AI / ML prediction (reporting). For example, the base station may decide to resume / activate considering the terminal's preference for activation. For example, the base station may detect a problem with the terminal and network performance and instruct to resume / activate the terminal's AI / ML prediction reporting. The activation indication may be indicated by a MAC CE or RRC message (e.g., using a report configuration), and the base station may indicate the association ID and / or report configuration ID to be activated (or by including a specific indicator in the corresponding report configuration) and / or measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or an activation period. Here, resuming or activating the configuration information for the AI / ML prediction (reporting) does not necessarily require that deactivation be instructed beforehand. For example, when the terminal receives settings related to cell measurement and AI / ML prediction in step 7-20, it may store the settings without performing AI / ML prediction / measurement right away, and then indicate to the base station its preference for activation as described in step 7-47. It may also activate AI / ML prediction / measurement only after receiving a MAC CE or RRC message activating AI / ML prediction.

[0158] In step 7-55, the terminal (7-05) may resume prediction using the AI / ML model and / or configuration information for which activation has been instructed (e.g., during the activation period set by the base station). The terminal may perform the operation of step 5-25 for prediction using the configuration information for the resumed AI / ML prediction (report).

[0159] In step 7-60, the terminal (7-05) may resume measurement reporting using the activated AI / ML model and / or configuration information (e.g., during the activation period set by the base station). The terminal may perform the operations of step 5-30 for measurement reporting using the configuration information for the resumed AI / ML prediction (report).

[0160] In one embodiment of the present disclosure, even if a terminal has an AI / ML prediction model and / or settings, it may not always be able to execute them. For example, the AI / ML prediction model and / or settings may be valid or available or applicable when certain conditions are met (e.g., when the channel changes abruptly, when the terminal moves, when the terminal is located within a certain area, when the terminal's remaining power exceeds a certain value, when the terminal's hardware exceeds a certain specification, when the terminal's memory exceeds a certain value, when the terminal has been set to a certain setting, etc.). If the above-described condition(s) are not met, if the terminal reports information generated by executing the AI / ML prediction model to the base station, this may be invalid information, resulting in a waste of radio resources and the base station may perform network operations in an incorrect direction. Therefore, the terminal may report the validity, applicability, or availability of the AI / ML prediction model and / or settings to the base station. In this disclosure, validity, applicability, and availability can all be collectively referred to as "applicability." The procedures for enabling and disabling settings for AI / ML predictions (reporting) based on applicability reports are described later in the description of FIG. 8.

[0161] FIG. 8 is a flowchart illustrating a procedure for activating and deactivating settings for AI / ML prediction (reporting) according to one embodiment of the present disclosure.

[0162] The descriptions of Steps 8-15 through 8-20 can refer to the descriptions of Steps 5-15 through 5-20.

[0163] In step 8-15, the terminal (8-05) may transmit information to the base station (8-10) or the network regarding whether it supports the function for activating and deactivating settings for AI / ML prediction (reporting). For example, by including a specific indicator in the UE capability information message or setting it to true, it may indicate whether the capability is supported, and by omitting a specific indicator or setting it to false, it may indicate non-support for the capability. In addition, in step 8-15, the terminal may transmit information to the base station or the network regarding whether it supports the function for reporting the applicability of the AI / ML prediction model and / or settings. For example, by including a specific indicator in the UE capability information message or setting it to true, it may indicate whether the capability is supported, and by omitting a specific indicator or setting it to false, it may indicate non-support for the capability. Information about whether the ability to enable and disable settings for AI / ML prediction (reporting) is supported and / or information about whether the ability to report applicability to AI / ML prediction models and / or settings is supported may be transmitted together with or separately from the mobility-related AI / ML prediction capabilities listed in the description for FIG. 5.

[0164] In step 8-20, the base station (8-10) may provide the terminal (8-05) with settings related to reporting the applicability of the AI / ML prediction model and / or settings (e.g., to allow / instruct applicability transmission), together with or separately from the cell measurement and AI / ML prediction related settings. For example, the settings may be included as part of the settings regarding UE Assistance Information in an RRC Reconfiguration message transmitted by the base station to the terminal. At this time, a prohibit timer for preferred transmission of the terminal may be set to control frequent applicability transmission of the terminal. Alternatively, the applicability transmission settings of the terminal may be included as settings in a UE information request message transmitted by the base station to the terminal. The base station may indicate / allow the terminal to transmit applicability information by indicating a link ID and / or a reporting configuration ID (or by including a specific indicator within the corresponding reporting configuration) and / or a measurement object ID (or by including a specific indicator within the corresponding measurement object) and / or a specific AI / ML model (e.g., a model ID).

[0165] In step 8-25, the terminal (8-05) may indicate to the base station (8-10) the applicability of some or all of the AI / ML prediction / reporting configurations (e.g., when specific conditions for applicability / availability of the AI / ML prediction model and / or configurations are satisfied). The terminal may transmit a specific indicator defined for the indication by including it in a UE assistance information message, a UE information response message, or a Measurement report message. The terminal may indicate a link ID and / or a Reporting Configuration ID (or by including a specific indicator in the corresponding Reporting Configuration) and / or a Measurement Object ID (or by including a specific indicator in the corresponding Measurement Object) and / or a specific AI / ML model (e.g., a Model ID) for the applicable / available AI / ML prediction model and / or configuration.

[0166] In step 8-30, the base station (8-10) may instruct the terminal (8-05) to activate or use the configuration information for AI / ML prediction (reporting) provided in step 8-20. For example, the base station may determine the activation or use of the configuration information for the AI / ML prediction (reporting) by considering the report on the applicability of the terminal. For example, the base station may receive the applicability of the AI / ML prediction model and / or configuration of the terminal and detect a problem with the terminal and network performance to instruct the resumption / activation of the AI / ML prediction reporting of the terminal. The activation may be indicated by a MAC CE or RRC message (e.g., using a report configuration), and the base station may indicate the association ID and / or report configuration ID to be activated (or by including a specific indicator in the corresponding report configuration) and / or the measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or an activation period. In one embodiment of the present disclosure, step 8-30 may be omitted. That is, the terminal can perform steps 8-35 and 8-40 without instructions from the base station or network after reporting applicability.

[0167] At step 8-35, the terminal (8-05) can start / resume prediction using the AI / ML model and / or configuration information for which activation has been instructed (e.g., during the activation period set by the base station).

[0168] At step 8-40, the terminal (8-05) can start / resume measurement reporting using the AI / ML model and / or configuration information for which activation has been instructed (e.g., during the active period set by the base station).

[0169] In step 8-45, the terminal (8-05) may indicate to the base station (8-10) the inapplicability of some or all of the AI / ML prediction / reporting configurations (e.g., when specific conditions for applicability / availability of the AI / ML prediction model and / or configurations are not satisfied). The terminal may transmit a specific indicator defined for the indication in a UE assistance information message or a UE information response message or a Measurement report message. The terminal may indicate the association ID and / or the reporting configuration ID (or by including a specific indicator in the corresponding reporting configuration) and / or the measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., a model ID) for the AI / ML prediction model and / or configurations that are not applicable / available.

[0170] In step 8-50, the base station (8-10) may instruct the terminal (8-05) to deactivate some or all of the AI / ML model or configuration being applied. For example, the base station may decide to deactivate the AI / ML model or configuration in consideration of a report of inapplicability of the terminal. For example, the base station may receive inapplicability of the AI / ML model or configuration of the terminal and determine that there is no problem with the terminal and network performance without further AI / ML prediction report from the terminal, and may instruct deactivation. The deactivation may be indicated by a MAC CE or RRC message (e.g., using a report configuration), and the base station may indicate the association ID and / or report configuration ID to be deactivated (or by including a specific indicator in the corresponding report configuration) and / or the measurement object ID (or by including a specific indicator in the corresponding measurement object) and / or a specific AI / ML model (e.g., model ID) and / or the deactivation period. In one embodiment of the present disclosure, step 8-50 may be omitted. That is, the terminal can perform steps 8-55 and 8-60 without instructions from the network after reporting inapplicability.

[0171] At step 8-55, the terminal (8-05) may stop prediction using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0172] At step 8-60, the terminal (8-05) may stop reporting measurements using the AI / ML model and / or configuration information that has been instructed to be deactivated (e.g., during the deactivation period set by the base station).

[0173] In one embodiment of the present disclosure, since there may be one or more AI / ML models or features, the operation of the network and / or terminal and / or related parameters / indicators for each of the aforementioned embodiments may be defined / performed for each AI / ML model or feature.

[0174] FIG. 9 is a diagram illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0175] Referring to FIG. 9, the terminal includes an RF (Radio Frequency) processing unit (9-10), a baseband processing unit (9-20), a storage unit (9-30), and a control unit (9-40).

[0176] The RF processing unit (9-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (9-10) up-converts the baseband signal provided from the baseband processing unit (9-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (9-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital to analog convertor (DAC), an analog to digital convertor (ADC), etc. In the drawing, only one antenna is shown, but the terminal may be equipped with multiple antennas. In addition, the RF processing unit (9-10) may include multiple RF chains. Furthermore, the RF processing unit (9-10) may perform beamforming. For the above beamforming, the RF processing unit (9-10) can adjust the phase and size of each signal transmitted and received through multiple antennas or antenna elements. In addition, the RF processing unit can perform MIMO, and can receive multiple layers when performing the MIMO operation.

[0177] The baseband processing unit (9-20) above performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the baseband processing unit (9-20) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (9-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (9-10). For example, in the case of following the OFDM (orthogonal frequency division multiplexing) method, when transmitting data, the baseband processing unit (9-20) generates complex symbols by encoding and modulating a transmission bit stream, maps the complex symbols to subcarriers, and then configures OFDM symbols through an inverse fast Fourier transform (IFFT) operation and a cyclic prefix (CP) insertion. In addition, when receiving data, the baseband processing unit (9-20) divides the baseband signal provided from the RF processing unit (9-10) into OFDM symbol units, restores signals mapped to subcarriers through FFT (fast Fourier transform) operation, and then restores the received bit string through demodulation and decoding.

[0178] The baseband processing unit (9-20) and the RF processing unit (9-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (9-20) and the RF processing unit (9-10) may be referred to as a transmitter, a receiver, a transceiver, or a communication unit. Furthermore, at least one of the baseband processing unit (9-20) and the RF processing unit (9-10) may include a plurality of communication modules to support a plurality of different wireless access technologies. In addition, at least one of the baseband processing unit (9-20) and the RF processing unit (9-10) may include different communication modules to process signals of different frequency bands. For example, the different wireless access technologies may include a wireless LAN (e.g., IEEE 802.11), a cellular network (e.g., LTE), etc. Additionally, the different frequency bands may include a super high frequency (SHF) (e.g., 2.NRHz, NRhz) band and a millimeter wave (mm wave) (e.g., 60GHz) band.

[0179] The above storage unit (9-30) stores data such as basic programs, application programs, and setting information for the operation of the terminal. The above storage unit (9-30) provides the stored data at the request of the control unit (9-40).

[0180] The above control unit (9-40) controls the overall operations of the terminal. For example, the control unit (9-40) transmits and receives signals through the baseband processing unit (9-20) and the RF processing unit (9-10). In addition, the control unit (9-40) records and reads data in the storage unit (9-30). For this purpose, the control unit (9-40) may include at least one processor. For example, the control unit (9-40) may include a communication processor (CP) that performs control for communication and an application processor (AP) that controls upper layers such as application programs, and may include a multi-connection processing unit (9-42) as illustrated in the drawing.

[0181] FIG. 10 is a diagram illustrating the structure of a base station according to one embodiment of the present disclosure.

[0182] Referring to FIG. 10, a base station according to an example of the present disclosure is configured to include an RF processing unit (10-10), a baseband processing unit (10-20), a backhaul communication unit (10-30), a storage unit (10-40), and a control unit (10-50).

[0183] The RF processing unit (10-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (10-10) up-converts the baseband signal provided from the baseband processing unit (10-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (10-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc. In the drawing, only one antenna is shown, but the base station may be equipped with multiple antennas. In addition, the RF processing unit (10-10) may include multiple RF chains. Furthermore, the RF processing unit (10-10) may perform beamforming. For the above beamforming, the RF processing unit (10-10) can adjust the phase and size of each signal transmitted and received through multiple antennas or antenna elements. The RF processing unit can perform a downlink MIMO operation by transmitting one or more layers.

[0184] The baseband processing unit (10-20) above performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the wireless access technology. For example, when transmitting data, the baseband processing unit (10-20) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (10-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (10-10). For example, in the case of OFDM, when transmitting data, the baseband processing unit (10-20) generates complex symbols by encoding and modulating a transmission bit stream, maps the complex symbols to subcarriers, and then configures OFDM symbols through IFFT operation and CP insertion. In addition, when receiving data, the baseband processing unit (10-20) divides the baseband signal provided from the RF processing unit (10-10) into OFDM symbol units, restores the signals mapped to subcarriers through FFT operation, and then restores the received bit string through demodulation and decoding. The baseband processing unit (10-20) and the RF processing unit (10-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (10-20) and the RF processing unit (10-10) may be referred to as a transmitter, a receiver, a transceiver, a communication unit, or a wireless communication unit.

[0185] The above backhaul communication unit (10-30) provides an interface for performing communication with other nodes within the network. That is, the backhaul communication unit (10-30) converts a bit string transmitted from the main base station to another node, such as an auxiliary base station or core network, into a physical signal, and converts a physical signal received from the other node into a bit string.

[0186] The storage unit (10-40) stores data such as basic programs, application programs, and setting information for the operation of the main base station. In particular, the storage unit (10-40) can store information on bearers assigned to connected terminals, measurement results reported from connected terminals, and the like. In addition, the storage unit (10-40) can store information that serves as a judgment criterion for whether to provide or terminate multiple connections to a terminal. In addition, the storage unit (10-40) provides the stored data at the request of the control unit (10-50).

[0187] The control unit (10-50) controls the overall operations of the base station. For example, the control unit (10-50) transmits and receives signals through the baseband processing unit (10-20) and the RF processing unit (10-10) or through the backhaul communication unit (10-30). In addition, the control unit (10-50) records and reads data in the storage unit (10-40). For this purpose, the control unit (10-50) may include at least one processor and, as illustrated in the drawing, may include a multi-connection processing unit (10-52).

[0188] Meanwhile, the embodiments of the present disclosure disclosed in this specification and drawings are merely specific examples presented to easily explain the technical content of the present disclosure and aid in understanding of the present disclosure, and are not intended to limit the scope of the present disclosure. In other words, it will be apparent to those skilled in the art to which the present disclosure pertains that other modified examples based on the technical concepts of the present disclosure are possible.

[0189] Furthermore, the above embodiments may be combined and operated as needed. For example, parts of one embodiment of the present disclosure and parts of another embodiment may be combined to operate a base station and a terminal. Furthermore, the embodiments of the present disclosure are applicable to other communication systems, and other modifications based on the technical concepts of the embodiments may also be implemented. For example, the embodiments may be applied to LTE systems, 5G, NR systems, or 6G systems. Therefore, the scope of the present disclosure should not be limited to the described embodiments, but should be determined not only by the scope of the following claims but also by equivalents thereof.

Claims

1. In a method performed by a terminal of a wireless communication system, A step of receiving a first message including setup information for artificial intelligence and machine learning (AI / ML)-based measurement prediction from a base station; A step of transmitting a second message to the base station based on the above setting information to report the applicability of the AI / ML-based measurement prediction; A step of identifying that the above AI / ML-based measurement prediction is activated; and A method comprising the step of transmitting a report on the results of the activated AI / ML-based measurement prediction to the base station.

2. In paragraph 1, A method characterized in that the first message further includes information indicating whether the terminal is permitted to report applicability to the AI / ML-based measurement prediction.

3. In paragraph 1, After transmitting the second message, based on receiving information from the base station indicating activation of the AI / ML-based measurement prediction, the AI / ML-based measurement prediction is activated, or A method characterized in that, based on transmitting the second message, the AI / ML-based measurement prediction is deemed to be activated.

4. In paragraph 1, A step of identifying that the above AI / ML based measurement prediction is not applicable; A step of transmitting a third message to the base station to report that the AI / ML-based measurement prediction is not applicable; and A method further comprising the step of receiving information from the base station indicating deactivation of the AI / ML-based measurement prediction.

5. In a method performed by a base station of a wireless communication system, A step of transmitting a first message including setting information for artificial intelligence and machine learning (AI / ML)-based measurement prediction to a terminal; A step of receiving a second message from the terminal for reporting the applicability of the AI / ML-based measurement prediction associated with the above setting information; A step of identifying that the AI / ML-based measurement prediction is activated within the terminal; and A method comprising the step of receiving a report on the results of the activated AI / ML-based measurement prediction from the terminal.

6. In paragraph 5, A method characterized in that the first message further includes information indicating whether the terminal is permitted to report applicability to the AI / ML-based measurement prediction.

7. In paragraph 5, Based on transmitting information indicating activation of the AI / ML-based measurement prediction to the terminal after receiving the second message, the AI / ML-based measurement prediction is activated within the terminal, or A method characterized in that, based on receiving the second message, the AI / ML-based measurement prediction is deemed to be activated within the terminal.

8. In paragraph 5, A step of receiving a third message from the terminal to report that the AI / ML-based measurement prediction is not applicable; and A method further comprising the step of transmitting information instructing deactivation of the AI / ML-based measurement prediction to the terminal.

9. In the terminal of a wireless communication system, Transmitter and receiver; and comprising a control unit, wherein the control unit is: Receive a first message including setup information for artificial intelligence and machine learning (AI / ML)-based measurement prediction from a base station through the transceiver, Based on the above setting information, a second message for reporting the applicability of the AI / ML-based measurement prediction is transmitted to the base station through the transceiver, Identifies that the above AI / ML based measurement prediction is activated, A terminal configured to transmit a report on the results of the activated AI / ML-based measurement prediction to the base station through the transceiver.

10. In paragraph 9, A terminal characterized in that the first message further includes information indicating whether the terminal is permitted to report applicability to the AI / ML-based measurement prediction.

11. In paragraph 9, After transmitting the second message, based on receiving information from the base station indicating activation of the AI / ML-based measurement prediction, the AI / ML-based measurement prediction is activated, or A terminal characterized in that the AI / ML-based measurement prediction is considered to be activated based on transmitting the second message.

12. In paragraph 9, The above control unit, Identify that the above AI / ML based measurement prediction is not applicable, A third message is transmitted to the base station through the transceiver to report that the above AI / ML-based measurement prediction is not applicable, A terminal configured to receive information instructing deactivation of the AI / ML-based measurement prediction from the base station through the transceiver.

13. In a base station of a wireless communication system, Transmitter and receiver; and comprising a control unit, wherein the control unit is: Transmitting a first message including setup information for artificial intelligence and machine learning (AI / ML)-based measurement prediction to a terminal through the transceiver, Receive a second message from the terminal through the transceiver to report the applicability of the AI / ML-based measurement prediction associated with the above setting information, Identifying that the above AI / ML based measurement prediction has been activated within the terminal, A base station configured to receive a report on the results of the activated AI / ML-based measurement prediction from the terminal through the transceiver.

14. In paragraph 13, The first message further includes information indicating whether the terminal is permitted to report applicability to the AI / ML-based measurement prediction, A base station characterized in that, based on transmitting information indicating activation of the AI / ML-based measurement prediction to the terminal after receiving the second message, the AI / ML-based measurement prediction is activated within the terminal, or based on receiving the second message, the AI / ML-based measurement prediction is considered to be activated within the terminal.

15. In paragraph 13, The above control unit, A third message is received from the terminal through the transceiver to report that the above AI / ML-based measurement prediction is not applicable, A base station configured to transmit information indicating deactivation of the AI / ML-based measurement prediction to the terminal through the transceiver.

Images