Method and apparatus for performing handover in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate than a 4G communication system such as LTE. An operation method of a user equipment (UE) according to one embodiment of the present disclosure may comprise the steps of: receiving a prediction request for handover and / or configuration information related to the prediction request from a base station; deriving information for a prediction report by using an AI / ML model on the basis of the configuration information related to the prediction request; and transmitting the prediction report including the derived information to the base station.

Description

Method and device for performing handover in a wireless communication system

[0001] The present disclosure relates to operations of terminals and base stations in a wireless communication system, and more particularly, to a method and device for predicting handover failure and performing handover operations using AI / ML in a next-generation mobile communication system.

[0002] Looking back at the evolution of wireless communication over successive generations, technologies have primarily been developed for human-facing services such as voice, multimedia, and data. With the commercialization of 5G (5th-generation) communication systems, an explosive increase in connected devices is expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction equipment, and factory equipment. Mobile devices are expected to evolve into diverse form factors, including augmented reality glasses, virtual reality headsets, and holographic devices. In the 6th-generation (6G) era, efforts are being made to develop improved 6G communication systems to connect hundreds of billions of devices and objects and provide diverse services. For this reason, 6G communication systems are often referred to as "beyond 5G."

[0003] The 6G communication system, expected to be realized around 2030, will have a maximum transmission speed of terabytes per second (i.e., 1,000 gigabits per second) and a wireless latency of 100 microseconds (μsec). In other words, compared to 5G, the transmission speed in a 6G communication system will be 50 times faster, while the wireless latency will be reduced to one-tenth.

[0004] To achieve these high data rates and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz band (e.g., from 95 gigahertz (GHz) to 3 terahertz (THz)). Compared to the millimeter wave (mmWave) band introduced in 5G, the terahertz band is expected to experience more severe path loss and atmospheric absorption, making it more crucial to ensure signal reach, or coverage, in this band. Key technologies to ensure coverage include radio frequency (RF) components, antennas, new waveforms that offer better coverage than OFDM (orthogonal frequency division multiplexing), beamforming, and multiple antenna transmission technologies such as massive multiple-input and multiple-output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing using orbital angular momentum (OAM), and reconfigurable intelligent surfaces (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, in order to improve frequency efficiency and system network, 6G communication systems are developing full duplex technology that utilizes the same frequency resources for uplink and downlink at the same time; network technology that integrates satellites and high-altitude platform stations (HAPS); network structure innovation technology that supports mobile base stations and enables optimization and automation of network operation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes artificial intelligence (AI) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services with complexity that exceeds the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources (mobile edge computing (MEC), cloud, etc.). In addition, efforts are being made to further strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase the openness of wireless communications through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe use of data, and the development of technologies for maintaining privacy.

[0006] Research and development of these 6G communication systems are expected to enable a new level of hyper-connected experience through the hyper-connectivity of 6G communication systems, which encompass not only connections between things but also connections between people and things. Specifically, 6G communication systems are expected to enable services such as truly immersive extended reality (Truly Immersive XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through enhanced security and reliability, will find application in diverse fields such as industry, healthcare, automotive, and home appliances.

[0007] According to one embodiment, a method of a user equipment (UE) in a wireless communication system is provided. The method of the UE may include: transmitting a UE capability information message including capability information regarding AI / ML-based prediction to a base station; receiving handover-related prediction configuration information from the base station; performing handover performance prediction using AI / ML based on the handover-related prediction configuration information; and transmitting a prediction report including predicted handover performance-related information to the base station. A target cell for handover may be determined based on the prediction report.

[0008] According to one embodiment, the handover-related prediction configuration information may include information regarding one or more first target candidate cells. The UE method may include a step of performing a handover performance prediction for each of the one or more first target candidate cells using AI / ML based on the handover-related prediction configuration information. The prediction report may include predicted handover performance-related information for each of the one or more first target candidate cells.

[0009] According to one embodiment, the handover-related prediction configuration information may include information regarding one or more second target candidate cells, wherein the second target candidate cells may be cells that have indicated permission for an AI / ML-based handover request. The UE's method may include a step of performing a handover performance prediction for each of the one or more second target candidate cells using AI / ML based on the handover-related prediction configuration information. The prediction report may include predicted handover performance-related information for each of the one or more second target candidate cells.

[0010] According to one embodiment, the capability information regarding AI / ML-based prediction included in the UE capability information message may include at least one of: whether the UE supports AI / ML-based handover failure (HOF)-related information prediction and reporting; whether the UE supports AI / ML-based radio link failure (RLF)-related information prediction and reporting; whether the UE supports AI / ML-based cell time of stay (TOS)-related information prediction and reporting; whether the UE supports AI / ML-based handover interruption time-related information prediction and reporting; whether the UE supports AI / ML-based handover indication response prediction and reporting; or whether the UE supports AI / ML-based preferred network configuration prediction and reporting.

[0011] According to one embodiment, the handover-related prediction configuration information may include at least one of: a threshold value for a probability that the UE will fail the handover; a threshold value for a probability that the UE will fail the wireless connection; a threshold value for the cell residence time of the UE; a reference time at which prediction is performed; information indicating whether each piece of information that the UE can include in the prediction report is included; or a length value for a timer related to prediction and reporting of the UE.

[0012] According to one embodiment, the prediction report may include at least one of: a list of one or more cells in which HOF is predicted; a list of one or more cells in which HOF is not predicted; a list of one or more cells in which RLF is predicted; a list of one or more cells in which RLF is not predicted; a list of one or more cells in which RLF is not predicted; a list of one or more cells in which a predicted TOS value is lower than a threshold value; a list of one or more cells in which a predicted TOS value is higher than a threshold value; information indicating whether a HOF probability higher than a threshold value, an RLF probability higher than a threshold value, or a TOS lower than a threshold value is predicted for each cell; a predicted HOF probability or RLF probability or a TOS value for each cell; a predicted handover interruption time for each cell; a predicted cell measurement value for each cell; information indicating a preference of the UE for handover for each cell; or a preferred network setting of the UE when assuming a handover for each cell.

[0013] In one embodiment, the step of transmitting a prediction report to a base station may include the step of determining whether at least one condition for triggering a prediction report is satisfied; and the step of transmitting the prediction report to the base station if the at least one condition for triggering a prediction report is satisfied.

[0014] According to one embodiment, in a wireless communication system, a user equipment (UE) is provided. The UE may include a memory storing one or more commands; and at least one processor. The at least one processor may execute one or more commands stored in the memory to: transmit a UE capability information message including capability information regarding AI / ML-based prediction to a base station; receive handover-related prediction configuration information from the base station; perform handover performance prediction using AI / ML based on the handover-related prediction configuration information; and transmit a prediction report including predicted handover performance-related information to the base station. A target cell for handover may be determined based on the prediction report.

[0015] According to one embodiment, the handover-related prediction configuration information may include information regarding one or more first target candidate cells. At least one processor may further execute one or more commands stored in memory to: perform handover performance prediction for one or more first target candidate cells using AI / ML based on the handover-related prediction configuration information. The prediction report may include predicted handover performance-related information for one or more first target candidate cells.

[0016] According to one embodiment, the handover-related prediction configuration information may include information regarding one or more second target candidate cells, wherein the second target candidate cells may be cells that have indicated permission for an AI / ML-based handover request. At least one processor may perform a handover performance prediction for each of the one or more second target candidate cells using the AI / ML, based on the handover-related prediction configuration information, by executing one or more instructions stored in a memory. The prediction report may include predicted handover performance-related information for each of the one or more second target candidate cells.

[0017] According to one embodiment, a method of a base station in a wireless communication system is provided. The method of the base station may include: receiving, from a user equipment (UE), a UE capability information message including capability information regarding AI / ML-based prediction; transmitting, to the UE, handover-related prediction configuration information; receiving, from the UE, a prediction report including handover performance-related information predicted using AI / ML; and determining a target cell for handover based on the prediction report.

[0018] According to one embodiment, the method of the base station may further include the step of determining one or more first target candidate cells. The handover-related prediction configuration information may include information regarding the one or more first target candidate cells, and the prediction report may include predicted handover performance-related information for each of the one or more first target candidate cells.

[0019] According to one embodiment, a method of a base station may further include: determining one or more first target candidate cells; transmitting a handover request message to the one or more first target candidate cells; receiving a grant message for the handover request from at least one of the one or more first target candidate cells; and determining at least one cell as a second target candidate cell. The handover-related prediction configuration information may include information regarding the one or more second target candidate cells, and the prediction report may include predicted handover performance-related information for each of the one or more second target candidate cells.

[0020] According to one embodiment, a base station in a wireless communication system is provided. The base station may include a memory storing one or more commands; and at least one processor. The at least one processor may execute the one or more commands stored in the memory to: receive, from a user equipment (UE), a UE capability information message including capability information regarding AI / ML-based prediction; transmit, to the UE, handover-related prediction configuration information; receive, from the UE, a prediction report including handover performance-related information predicted using AI / ML; and determine a target cell for handover based on the prediction report.

[0021] According to one embodiment, at least one processor may further include: determining one or more first target candidate cells by executing one or more instructions stored in a memory; The handover-related prediction configuration information may include information regarding one or more first target candidate cells, and the prediction report may include predicted handover performance-related information for each of the one or more first target candidate cells.

[0022] FIG. 1A is a diagram illustrating the structure of a wireless communication system according to one embodiment of the present disclosure.

[0023] FIG. 1b is a diagram for explaining a wireless connection state transition of a terminal in a wireless communication system according to one embodiment of the present disclosure.

[0024] FIG. 1c is a flowchart illustrating a process in which a terminal performs cell measurement and reporting operations according to one embodiment of the present disclosure.

[0025] FIG. 1D is a diagram for explaining an operation of a terminal reporting cell measurement results when a specific condition is satisfied according to one embodiment of the present disclosure.

[0026] FIG. 1e is a diagram illustrating an example of input information (Input) and derived information (Output) of an AI / ML model used by a terminal according to one embodiment of the present disclosure.

[0027] FIG. 1f is a diagram illustrating a signaling procedure for performing handover between a terminal and a base station according to one embodiment of the present disclosure.

[0028] FIG. 1g is a diagram illustrating a signaling procedure for performing a handover based on prediction and related reporting using an AI / ML model between a terminal and a base station according to one embodiment of the present disclosure.

[0029] FIG. 1h is a diagram illustrating a signaling procedure for performing a handover based on prediction and related reporting using an AI / ML model between a terminal and a base station according to one embodiment of the present disclosure.

[0030] FIG. 1ia and FIG. 1ib are diagrams illustrating a signaling procedure for performing handover based on prediction and related report using AI / ML model between a terminal and a base station according to one embodiment of the present disclosure.

[0031] FIG. 1J is a diagram illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0032] FIG. 1k is a diagram illustrating the structure of a base station according to one embodiment of the present disclosure.

[0033] In describing the embodiments of this disclosure, descriptions of technical details that are well-known in the technical field to which this disclosure pertains and are not directly related to this disclosure will be omitted. This is to avoid obscuring the gist of this disclosure by omitting unnecessary explanations and to convey it more clearly. Furthermore, the terms described below are defined based on their functions in this disclosure and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the contents throughout this specification.

[0034] 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.

[0035] 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 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 solely to ensure that the 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 designate like elements throughout the disclosure.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] The terms used in the following description to identify connection nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, and terms referring to various identification information are provided for convenience of explanation. Therefore, the present invention is not limited to the terms described below, and other terms referring to objects with equivalent technical meanings may be used.

[0040] Hereinafter, the base station is an entity that performs resource allocation of the terminal, and may be at least one of a gNode B, an eNode B, a Node B, a BS (Base Station), a wireless access unit, a base station controller, or a node on a network. The terminal may include a UE (User Equipment), an MS (Mobile Station), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing a communication function. In the present disclosure, downlink (DL) refers to a wireless transmission path of a signal transmitted from a base station to a terminal, and uplink (UL) refers to a wireless transmission path of a signal transmitted from a terminal to a base station. In addition, although the LTE or LTE-A system may be described below as an example, the embodiments of the present disclosure may also be applied to other communication systems having similar technical backgrounds or channel types. For example, the 5th generation mobile communication technology (5G, new radio, NR) or the 5G advanced system developed after LTE-A may be included in a system to which the embodiments of the present disclosure may be applied, and 5G below may also be a concept that includes existing LTE, LTE-A, and other similar services.

[0041] For convenience of explanation, this disclosure uses terms and names defined in the 5GS and NR standards defined by the 3rd Generation Partnership Project (3GPP). However, the present invention is not limited to these terms and names and can be equally applied to wireless communication networks conforming to other standards. For example, the present invention can be applied to the 3GPP 5GS / NR (5th generation mobile communication standard) or the 3GPP 5G advanced standard.

[0042] FIG. 1A is a diagram illustrating the structure of a wireless communication system according to one embodiment of the present disclosure.

[0043] Referring to FIG. 1a, 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) (1a-10) and an AMF (1a-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) (1a-15) may access an external network through the gNB (1a-10) and the AMF (1a-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.

[0044] In FIG. 1a, the gNB (1a-10) may correspond to the eNB (1a-30) (Evolved Node B) of the existing LTE system. The gNB is connected to the NR UE (1a-15) via a wireless channel (1a-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 (1a-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 bandwidth, 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.

[0045] AMF (1a-05) can perform functions such as mobility support, bearer setup, and QoS (quality of service) setup. AMF (1a-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.

[0046] In addition, the mobile communication system according to one embodiment of the present disclosure can be interoperable with an existing LTE system, and an AMF (1a-05) can be connected to an MME (1a-25, mobility management entity) through a network interface. The MME (1a-25) can be connected to an existing base station, an eNB (1a-30). An NR UE (1a-15) supporting LTE-NR Dual Connectivity can transmit and receive data while maintaining a connection (1a-35) with not only a gNB (1a-10) but also an eNB (1a-30).

[0047] FIG. 1b is a diagram for explaining a wireless connection state transition of a terminal in a wireless communication system according to an embodiment of the present disclosure.

[0048] In a wireless communication system according to an embodiment of the present disclosure, a terminal may have three radio connection states (RRC (radio resource control) states) or RRC modes. The connected mode (RRC_CONNECTED, 1b-05) is a radio connection state in which the terminal can transmit and receive data. The idle mode (RRC_IDLE, 1b-30) is a radio connection state in which the terminal monitors whether paging is transmitted to itself. The two modes (connected mode and idle mode) are radio connection states that can also be applied to an LTE system, and the detailed technology is the same as that of the LTE system. The wireless communication system according to an embodiment of the present disclosure may be a next-generation mobile communication system.

[0049] In a wireless communication system according to an embodiment of the present disclosure, an inactive (RRC_INACTIVE) radio connection state (1b-15) may be defined. In the inactive radio connection state, the UE context is maintained between the base station and the terminal, and RAN (radio access network)-based paging may be supported. The characteristics of the inactive radio connection state are listed below.

[0050] - Cell re-selection mobility;

[0051] - CN - NR RAN connection (both C / U-planes (control plane / user plane)) has been established for UE;

[0052] - The UE AS (Access Stratum) context is stored in at least one gNB and the UE;

[0053] - Paging is initiated by NR RAN;

[0054] - RAN-based notification area is managed by NR RAN;

[0055] - NR RAN knows the RAN-based notification area which the UE belongs to;

[0056] 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 (1b-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 (1b-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 operations. In addition, the terminal can transition from INACTIVE mode to standby mode through the Release procedure after Resume (1b-20). The transition (1b-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.

[0057] FIG. 1c is a flowchart illustrating a process in which a terminal performs cell measurement and reporting operations according to an embodiment of the present disclosure.

[0058] According to one embodiment of the present disclosure, in operation 1c-15, the terminal (1c-05) may report its capability information to the base station (1c-10). In operation 1c-20, the base station (1c-10) may transmit an RRCReconfiguration message including configuration information (measConfig IE) related to the cell measurement operation to the terminal (1c-05).

[0059] The configuration information (measConfig IE) may include information necessary for reporting the results measured by the terminal (1c-05) to the base station (1c-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 (1c-05) may report a given measurement result when a specific event configured based on the configuration information (measConfig IE) is satisfied. For example, the following events may be configured in the NR system.

[0060] - Event(s) related to intra- / inter-RAT measurements are as shown in Table 1 below.

[0061] [Table 1]

[0062]

[0063] - Similar to condition-based measurement reporting, in condition-based handover, when a specific event is satisfied, the terminal (1c-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.

[0064] [Table 2]

[0065]

[0066] - (Sidelink) When a specific event is satisfied in the Relay, the terminal (1c-05) can perform a specific action. Event(s) related to the Relay are as shown in Table 3 below.

[0067] [Table 3]

[0068]

[0069] - In the case of NR-U (Unlicensed), when a specific event is satisfied, the terminal (1c-05) can perform a specific action. Event(s) related to NR-U are as shown in Table 4 below.

[0070] [Table 4]

[0071]

[0072] In operation 1c-25, terminal (1c-05) can evaluate whether the configured Events are satisfied. If the Events described above continue to satisfy a predetermined condition for a predetermined time interval (time-to-trigger), terminal (1c-05) can consider the Event to be satisfied.

[0073] In operation 1c-30, the terminal (1c-05) may report a MeasurementReport message containing measurement results to the base station (1c-10) when a set condition is satisfied. Alternatively, the terminal (1c-05) may perform a predetermined operation corresponding to the above condition, for example, a condition-based handover.

[0074] The base station (1c-10) that receives the measurement result from the terminal (1c-05) can use the measurement result for a predetermined purpose. For example, in operation 1c-35, the base station (1c-10) can determine whether to trigger a handover of the terminal (1c-05). In operation 1c-40, if the base station (1c-10) triggers a handover, it can request a handover to the target cell(s). In operation 1c-45, the base station (1c-10) can transmit handover configuration information configured based on predetermined configuration information received from the target cell(s) to the terminal (1c-05). In operation 1c-50, the terminal (1c-05) that receives the handover configuration information can perform a handover.

[0075] FIG. 1D is a diagram for explaining an operation of a terminal reporting a cell measurement result when a specific condition is satisfied according to an embodiment of the present disclosure.

[0076] Referring to FIG. 1d, the terminal (1d-10) can evaluate the signal strength or quality of the base station (1d-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 (1d-05). Hereinafter, for convenience of explanation, the cell measurement result reporting operation of the terminal (1d-10) is described mainly with respect to SSB, but the same can be applied to CSI-RS.

[0077] In the case of SSB, the transmission cycle of SSB can be determined according to the settings of the base station (1d-05). Typically, the transmission cycle of SSB can be set to 20 ms, and the base station (1d-05) can transmit SSB with a cycle of up to 160 ms.

[0078] When the base station (1d-05) sets Event A2 to the terminal (1d-10), the terminal (1d-10) can continuously evaluate whether the RSRP value measured based on SSB is lower than the threshold during a predetermined time period (time-to-trigger, TTT) from the time point (1d-15) when the RSRP (reference signal received power) value measured based on SSB by the terminal (1d-10) becomes lower than the set absolute threshold value.

[0079] If the measured RSRP value based on SSB is continuously lower than the threshold from the initial time point (1d-15) when the RSRP value becomes lower than the set absolute threshold value to the time point (1d-20) when a predetermined time-to-trigger (TTT) has elapsed, the terminal (1d-10) may consider that the Event A2 is satisfied and may report a measurement report triggered by Event A2 to the base station (1d-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 can be compensated for. The TTT value may be set by the base station (1d-05) for each Event.

[0080] If the above-described Events continuously satisfy a predetermined condition for a predetermined time interval (TTT), the terminal (1d-10) can perform an action corresponding to the purpose of the Event according to the purpose of the configured Event. If the type of measurement report according to the measurement-related setting information received by the terminal (1d-10) is set to “periodical” or “event-triggered periodical,” the terminal (1d-10) can perform a measurement report periodically.

[0081] In the existing L3 (Layer 3) handover mechanism, handover can be 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. That is, it can be understood as a kind of reactive manner.

[0082] Reactive handover schemes can be effective for existing services, such as when terminals move between macro cells or when they have low mobility. However, reactive handover schemes can be problematic when terminals have high mobility, move between dense micro cells, or for future services such as XR. For example, unintended consequences such as handover failures, radio link failures, ping-pong behavior, throughput loss, or premature / late handovers can occur.

[0083] Accordingly, conditional handover was introduced in Rel-16 to improve handover robustness, and lower-layer triggered mobility (LTM) handover was introduced in Rel-18 to reduce service interruption due to frequent handovers between small cells. However, these two handover mechanisms (conditional handover and LTM) may not be sufficient because they are still based on a reactive approach.

[0084] On the other hand, handover 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 predicted cell measurement information to the base station (or network). This allows the base station to prepare for handovers in advance, preventing delays. Furthermore, by proactively instructing the UE to perform a handover, the UE can be handed over to another base station or cell before a problem (e.g., Radio Link Failure (RLF)) occurs. Furthermore, by receiving predicted cell measurement information for the UE, the base station can achieve improved handover and / or Radio Resource Management (RRM) performance compared to reactive approaches. For example, the base station can make better network operation / configuration decisions or take proactive measures to avoid unintended events. Alternatively, the base station or network may generate predictive information by running an AI / ML model using report information received from the terminal, and the base station or network may instruct the terminal to perform a preemptive handover using the generated predictive information.

[0085] FIG. 1e is a diagram illustrating an example of input information (Input) and derived information (Output) of an AI / ML model used by a terminal according to one embodiment of the present disclosure.

[0086] In step 1e-05, the terminal may use L3 (Layer 3) and / or L1 (Layer 1) measurement information (e.g., measured cell information, measured time information, measured RSRP value, measured RSRQ value, measured SINR value) for the serving cell and / or neighboring cells (from the past to the present or present) as one input information of the AI / ML model.

[0087] At step 1e-10, the terminal can use a reference time or a predicted time (T) as one input information for the AI / ML model. The reference time can indicate a specific time in the future.

[0088] - In one embodiment of the present disclosure, when predicting / deriving a cell measurement value as an output, the terminal can derive the predicted cell measurement value at a time point (T) indicated by the input reference time point.

[0089] - In one embodiment of the present disclosure, when predicting / deriving the HOF (Handover failure) probability as an output, the terminal can derive the predicted HOF probability at a time point (T) indicated by the input reference time point. For example, the HOF probability here may mean one of the following.

[0090] - Assuming that the terminal receives a handover command (e.g., an RRCReconfiguration message including reconfigurationWithSync) at a reference time T, the probability that the terminal will not complete the handover to the target cell (e.g., not complete the transmission of the RRCReconfigurationComplete message) (e.g., within a fixed or set time interval) can be indicated.

[0091] - The terminal may indicate the probability of detecting or declaring 1) an RLF and / or 2) a probability of expiring timer T304 and / or 3) a probability of expiring timer T311 and / or 4) a probability of expiring timer T310 and / or 5) a probability of expiring timer T312 and / or 6) a probability of receiving (X consecutive) out-of-sync indicators from L1 (Layer 1) (e.g., from L3) before and / or after receiving a handover command at a reference time T.

[0092] - After the UE receives a handover command at a reference time T and performs a successful handover to the target cell (e.g., after successfully completing transmission of an RRCReconfigurationComplete message), it may indicate (e.g., within a fixed or configured time interval) 1) the probability of detecting or declaring an RLF and / or 2) the probability of expiring a timer T304 and / or 3) the probability of expiring a timer T311 and / or 4) the probability of expiring a timer T310 and / or 5) the probability of expiring a timer T312 and / or 6) the probability of receiving (X consecutive) out-of-sync indicators from L1 (Layer 1) (e.g., from L3).

[0093] - In one embodiment of the present disclosure, when predicting / deriving an RLF (Radio link failure) probability as an output, the terminal can derive the predicted RLF probability at a time point (T) indicated by the input reference time point.

[0094] For example, the RLF probability here may indicate the probability that the terminal 1) detects or declares an RLF at a reference time T or within a fixed or set time interval relative to T and / or 2) the probability that timer T304 expires and / or 3) the probability that timer T311 expires and / or 4) the probability that timer T310 expires and / or 5) the probability that timer T312 expires and / or 6) the probability that (X consecutive) out-of-sync indicators are received from L1 (Layer 1) (e.g., from L3).

[0095] - In one embodiment of the present disclosure, when predicting / deriving a TOS (Time of Stay, time staying in a connected cell) value as an output, the terminal can derive the predicted TOS value at a time point (T) indicated by the input reference time point.

[0096] For example, the TOS value here may mean (e.g., within a fixed or configured time interval) 1) a time until the UE detects or declares an RLF after receiving a handover command at a reference time T, or after completing a handover at a reference time T, or after transitioning to a connected mode (with a new cell) at a reference time T, and / or 2) a time until the timer T304 expires, and / or 3) a time until the timer T311 expires, and / or 4) a time until the timer T310 expires, and / or 5) a time until the timer T312 expires, and / or 6) a time until receiving (X consecutive) out-of-sync indicators from L1 (Layer 1) (e.g., from L3) and / or 7) a time until receiving a handover command to another cell, and / or 8) a time until completing a handover to another cell, and / or 9) a time until transitioning to an inactive or standby mode.

[0097] - In one embodiment of the present disclosure, when predicting / deriving network configuration parameters (e.g., RRC parameters) to be used in the future as output, the terminal can derive optimal (or appropriate or recommended) network configuration parameters (e.g., RRC parameters) predicted at a time point (T) indicated by the input reference time point.

[0098] In step 1e-15, the terminal provides, as one input information of the AI / ML model, information and history of timer settings (from the past to the present or present) related to RLF or handover (e.g., timer length and expiration history for timers T304, T310, T311, T312); information and history of counter values ​​(e.g., N310, N311) related to RLF or handover (from the past to the present or present); information and history of RLF reports (e.g., RLF-Report) (from the past to the present or present); information and history of successful HO (Handover) reports (e.g., SuccessHO-Report) (from the past to the present or present); information and history of RA (Random access) reports (e.g., RA-Report) (from the past to the present or present); or information and history of CEF (Connection establishment failure) reports (e.g., ConnEstFailReport) (from the past to the present or present). At least one of them can be used.

[0099] At step 1e-20, the terminal can use the terminal's status information (from the past to the present or current) as one input information of the AI / ML model.

[0100] For example, the status information of the terminal may include at least one of the following: information on the remaining power (battery capacity) of the terminal, whether the terminal is charged, location information of the terminal, moving speed of the terminal, moving path information of the terminal, pose and direction information of the terminal, manufacturer and / or model information of the terminal, or hardware (e.g., RAM, CPU, GPU, graphics card, memory)-related information (e.g., performance) information of the terminal.

[0101] At step 1e-25, the terminal can use the configuration parameter information (from the past to the present or current) as one input information of the AI / ML model.

[0102] For example, the configuration parameter information may include at least one of configuration information and parameter values ​​for each layer (e.g., RRC, SDAP, PDCP, RLC, MAC, PHY) set by a base station or a network, or configuration information and parameter values ​​set by AMF through NAS signaling.

[0103] In step 1e-30, the terminal can predict / derive L3 (Layer 3) and / or L1 (Layer 1) measurement information (e.g., measured cell information, measured time information, measured RSRP value, measured RSRQ value, measured SINR value) for a serving cell and / or neighboring cells predicted at a future point in time as one output information of the AI / ML model.

[0104] At step 1e-35, the terminal can predict / derive the aforementioned HOF probability (e.g., cell-specific HOF probability) as one output information of the AI / ML model.

[0105] At step 1e-40, the terminal can predict / derive the aforementioned RLF probability (e.g., cell-specific RLF probability) as one output information of the AI / ML model.

[0106] At step 1e-45, the terminal can predict / derive the aforementioned TOS value (e.g., cell-specific TOS value) as one output information of the AI / ML model.

[0107] At step 1e-50, the terminal can derive setting parameter information that can be used at a future point in time or at a value derivation point in time as one output information of the AI / ML model.

[0108] For example, the terminal may use the derived values ​​instead of the layer-specific (e.g., RRC, SDAP, PDCP, RLC, MAC, PHY) configuration information and parameter values ​​set by the base station or the network and / or the configuration information and parameter values ​​set by the AMF through NAS signaling.

[0109] FIG. 1f is a diagram illustrating a signaling procedure for performing handover between a terminal and a base station according to one embodiment of the present disclosure.

[0110] In step 1f-05, the base station may transmit a UE capability enquiry message requesting the transmission of support capability (e.g., Capability) information to a terminal in connected mode. Upon receiving this, the terminal may transmit a UE capability information message containing the terminal's support capability information to the base station. In this case, the UE capability information message may include support capability information of the terminal related to the terminal performing a handover (e.g., presence or absence of support capability).

[0111] In step 1f-07, a terminal in connected mode can receive configuration information regarding cell measurement reports (e.g., Measurement report or MR) from a base station via an RRC Reconfiguration message.

[0112] In step 1f-10, the terminal may perform cell measurement according to configuration information regarding cell measurement report (e.g., Measurement report or MR) and report the resulting generated measurement report information to the base station via a Measurement Report message.

[0113] In step 1f-15, the base station or source base station may transmit a HANDOVER REQUEST message requesting a handover of the terminal to the target base station. The source base station may decide to transmit the HANDOVER REQUEST message after receiving a cell measurement report from the terminal (e.g., after receiving a measurement report triggered by event A3).

[0114] In step 1f-20, the target base station that has received the HANDOVER REQUEST message may transmit a HANDOVER REQUEST ACKNOWLEDGE message to the source base station to allow the handover of the terminal. The HANDOVER REQUEST ACKNOWLEDGE message may include configuration information about the target cell to which the terminal performs the handover.

[0115] At step 1f-22, the source base station may start running Timer 1 (e.g., TXnRELOCoveral) after receiving the HANDOVER REQUEST ACKNOWLEDGE message.

[0116] In step 1f-25, the source base station can transmit the target cell configuration information to the terminal via an RRC Reconfiguration message.

[0117] In step 1f-30, after receiving the RRC Reconfiguration message including target cell configuration information, the terminal may attempt a handover to the target cell using the configuration information. To this end, the terminal may perform random access to the target cell and transmit an RRC Reconfiguration Complete message to the target cell.

[0118] In step 1f-35, the target base station may transmit a UE CONTEXT RELEASE (COMMAND) message to the source base station to notify the source base station of a successful handover. Before transmitting the UE CONTEXT RELEASE (COMMAND) message, the target base station may change the downlink data path and establish an NG interface by exchanging a PATH SWITCH REQUEST message (e.g., a message transmitted from the target base station to the AMF) and a PATH SWITCH REQUEST ACKNOWLEDGE message (e.g., a message transmitted from the AMF to the target base station) with the AMF.

[0119] In step 1f-37, the source base station may release configuration information or context regarding the terminal after receiving the UE CONTEXT RELEASE (COMMAND) message (e.g., after a successful handover). The source base station may stop Timer 1 after receiving the UE CONTEXT RELEASE (COMMAND) message.

[0120] In one embodiment of the present disclosure, if the terminal reconnects to the source base station or source cell (e.g., after a handover failure) before the timer expires (e.g., before receiving a UE CONTEXT RELEASE message), the source base station may stop the timer 1.

[0121] In one embodiment of the present disclosure, if timer 1 expires (e.g., if the source base station did not provide configuration information or context regarding the terminal before timer 1 expired), the source base station may release the configuration information or context regarding the terminal.

[0122] In one embodiment of the present disclosure, if timer 1 expires (e.g., if the source base station did not establish configuration information or context regarding the UE before timer 1 expires), the source base station may request the AMF to release UE-associated configuration and connection (UE-associated logical NG-connection) information. That is, timer 1 may be a timer for the source base station and / or the AMF to release the configuration and / or connection and / or context information regarding the UE without continuing to store it (e.g., when the UE connects to another base station through an RRC Reestablishment procedure after a handover failure).

[0123] FIG. 1g is a diagram illustrating a signaling procedure for performing a handover based on prediction and related reporting using an AI / ML model between a terminal and a base station according to one embodiment of the present disclosure.

[0124] In step 1g-05, the base station may transmit a UE capability enquiry message requesting the transmission of support capability (e.g., Capability) information to a terminal in connected mode. Upon receiving this message, the terminal may transmit a UE capability information message containing the terminal's support capability information to the base station. In this case, the UE capability information message may include at least one of the following terminal support capability information.

[0125] - Information 1. Whether the terminal supports prediction and / or reporting of HOF-related information (e.g., HOF probability) (using AI / ML)

[0126] - Information 2. Whether the terminal supports prediction and / or reporting of RLF-related information (e.g., RLF probability) (using AI / ML)

[0127] - Information 3. Whether the terminal supports prediction and / or reporting of TOS-related information (e.g., RLF probability) (using AI / ML)

[0128] - Information 4. Whether the terminal supports prediction and / or reporting of handover-related information (e.g., handover interruption time) (using AI / ML). The handover interruption time may refer to the time during which uplink and / or downlink data transmission is temporarily interrupted during handover from the source base station to the target base station.)

[0129] - Information 5. Whether the terminal supports predicting and / or reporting responses (e.g., handover acceptance or rejection, or preference for handover acceptance or preference for handover rejection) to handover instructions (e.g., RRC Reconfiguration message including reconfigurationWithSync) (using AI / ML)

[0130] - Information 6. Whether the terminal supports requests for desired or preferred network settings (using AI / ML)

[0131] A terminal may indicate to a base station that it supports a given capability by including or setting (e.g., setting to “true”) a specific indicator for the capability in a UE capability information message. A terminal may indicate to a base station that it does not support a given capability by omitting or setting (e.g., setting to “false”) a specific indicator for the capability in a UE capability information message.

[0132] In step 1g-10, the base station may transmit cell measurement reporting related settings to the terminal (e.g., via MeasConfig in the RRC Reconfiguration message). For example, the base station may provide the terminal with cell measurement reporting settings associated with event A3.

[0133] In one embodiment, if the terminal supports AI / ML-based prediction capabilities (as described above in 1g-05), the base station may configure a prediction request and / or prediction request-related settings for the terminal, together with or including the cell measurement report settings. The prediction request-related settings may include at least one of the following information.

[0134] - Information 1. HOF probability threshold

[0135] - Information 2. RLF probability threshold

[0136] - Information 3. TOS threshold

[0137] - Information 4. Reference time mentioned above

[0138] □ For example, this value may be a relative time value based on when the terminal received the cell measurement report related settings and / or prediction request related settings (e.g., 1g-10). For example, if the terminal received the cell measurement report related settings and / or prediction request related settings at absolute time 10:05:03 and the reference time was set to 10 seconds, the reference time, which is the time point predicted by the terminal, may be 10:05:13.

[0139] - Information 5. Inclusion of each piece of information that the terminal can include in the prediction report

[0140] □ For example, a base station may instruct a terminal to include prediction report information in a prediction report by including or setting (e.g., setting to “true”) a specific indicator for each piece of information that may be included in the prediction report. For example, a base station may instruct a terminal not to include prediction report information in a prediction report by omitting or setting (e.g., setting to “false”) a specific indicator for each piece of information that may be included in the prediction report.

[0141] - Information 6. Length value for timer (e.g., timer 2) related to terminal prediction and / or related reporting.

[0142] □ When the terminal receives a length value for timer 2, the terminal may start timer 2 upon receiving a prediction request related configuration. If the terminal performs or finishes reporting (e.g., 1g-15) for the prediction request, the terminal may terminate timer 2. If the terminal does not perform reporting for the prediction request until timer 2 expires (i.e., upon timer expiration), the terminal may no longer perform prediction and / or related reporting or may not include it in cell measurement reporting (e.g., 1g-15). If the terminal does not perform reporting for the prediction request until timer 2 expires (i.e., upon timer expiration), the terminal may release the prediction request related configuration.

[0143] The above prediction request-related settings may be transmitted to the terminal by being included in an RRC Reconfiguration message, a UE information Request message, or a new RRC message. In one embodiment of the present disclosure, the prediction request-related settings may be transmitted to the terminal from an AMF or OAM other than the base station (e.g., via NAS signaling).

[0144] In step 1g-12, the terminal can run an AL / ML model based on prediction request related configuration information (1g-10) to predict / derive information to be used in prediction reporting (1g-15).

[0145] In step 1g-15, the terminal may report predicted / derived information to the base station (e.g., prediction report or prediction report) if at least one of the following conditions is satisfied.

[0146] - Condition 1. If the prediction request-related settings are linked to a cell measurement report, and the cell measurement report is triggered (e.g., if an event set for the cell measurement report is triggered or a periodic cell measurement report is set / triggered).

[0147] - Condition 2. When an event set to predictive reporting is triggered or when periodic predictive reporting is set / triggered.

[0148] - Condition 3. If the predicted / derived HOF probability is greater than a certain threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0149] □ When a prediction report is triggered by this condition, the base station can know that HOF will occur with a relatively high probability when the terminal performs a handover to a specific cell, so this can be useful information for the base station to decide / instruct the terminal to handover to the corresponding cell. For example, the base station may decide / instruct not to handover to the corresponding cell.

[0150] - Condition 4. If the predicted / derived HOF probability is less than a certain threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0151] □ When a prediction report is triggered by this condition, the base station can know that there is a relatively low probability that HOF will occur when the terminal performs a handover to a specific cell, so this can be useful information for the base station to decide / instruct the terminal to handover to the corresponding cell. For example, the base station can decide / instruct the handover to the corresponding cell.

[0152] - Condition 5. If the predicted / derived RLF probability is greater than a certain threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0153] □ When the prediction report is triggered by this condition, the base station can know that there is a relatively high probability that an RLF will occur when the terminal performs a handover to a specific cell (or stays in the current cell), so this can be useful information for the base station to decide / instruct the terminal to handover to the corresponding cell (or stay in the current cell). For example, the base station may decide / instruct not to handover to the corresponding cell.

[0154] - Condition 6. If the predicted / derived RLF probability is less than a certain threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0155] □ When the prediction report is triggered by this condition, the base station can know that RLF will occur with a relatively low probability when the terminal performs a handover to a specific cell (or stays in the current cell), so this can be useful information for the base station to decide / instruct the terminal to handover to the corresponding cell (or stay in the current cell). For example, the base station can decide / instruct a handover to the corresponding cell.

[0156] - Condition 7. If the predicted / derived TOS value is less than a specific threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0157] □ When the prediction report is triggered by this condition, the base station can know that the TOS will be relatively low (e.g., another handover is needed) when the terminal performs a handover to a specific cell (or stays in the current cell), so this can be useful information for the base station to decide / instruct the terminal to handover to that cell (or stay in the current cell). For example, the base station may decide / instruct not to handover to that cell.

[0158] - Condition 8. If the predicted / derived TOS value is greater than a certain threshold (e.g., a threshold set by the base station in 1g-10 or a fixed value defined in the standard).

[0159] □ When the prediction report is triggered by this condition, the base station can know that the TOS will be relatively large (e.g., no further handover is required) when the terminal performs a handover to a specific cell (or stays in the current cell), so this can be useful information for the base station to decide / instruct the terminal to handover to that cell (or stay in the current cell). For example, the base station can decide / instruct the handover to that cell.

[0160] - Condition 9. If HOF is predicted when performing a handover

[0161] - Condition 10. When RLF is predicted when performing a handover to a specific cell (or staying in the current cell)

[0162] - Condition 11. When a short TOS is expected when performing a handover to a specific cell (or staying in the current cell), or when a handover ping-pong (e.g. between two cells or between multiple cells) is expected.

[0163] - Condition 12. If the terminal receives a setting regarding a prediction (report) request (e.g., in the reportConfig setting).

[0164] - Condition 13. If the set of events (e.g. Event A1, A2, A3, A4, A5, A6, B1, B2) is satisfied based on the predicted cell measurement values ​​(instead of the actual cell measurement values).

[0165] If the above conditions are not satisfied, the terminal may not report the predicted / derived information to the base station (e.g., a prediction report). In this case, the terminal may only transmit cell measurement values ​​(e.g., not including the prediction report) to the base station.

[0166] The prediction report transmitted by the terminal may include at least one of the following information.

[0167] - Information 1. (For the event that triggered the measurement report, or among the cells that triggered the measurement report) a list of one or more cells with a predicted HOF probability higher than a threshold (e.g., set by the base station or fixed in the standard) and related information (e.g., cell ID). For example, a base station that receives this information may not decide / instruct a handover to the corresponding cell.

[0168] - Information 2. A list of one or more cells with a predicted RLF probability higher than a threshold (e.g., set by the base station or fixed in the standard) (or predicted to have RLF) (for the event that triggered the measurement report, or among the cells that triggered the measurement report) and related information (e.g., cell ID). For example, a base station that receives this information may not decide / instruct a handover to the corresponding cell.

[0169] - Information 3. A list of one or more cells (e.g., cell IDs) with a predicted TOS value lower than a threshold (e.g., set by the base station or fixed in the standard) (or for which a handover ping-pong is expected) for the event that triggered the measurement report, or among the cells that triggered the measurement report. For example, a base station that receives this information may not decide / instruct a handover to the corresponding cell.

[0170] - Information 4. (For the event that triggered the measurement report, or among the cells that triggered the measurement report) A list of one or more cells with a predicted HOF probability lower than a threshold (e.g., set by the base station or fixed in the standard) (or for which HOF is not predicted) and related information (e.g., cell ID). For example, a base station that receives this information can decide / instruct a handover to the corresponding cell.

[0171] - Information 5. (For the event that triggered the measurement report, or among the cells that triggered the measurement report) A list of one or more cells with a predicted RLF probability lower than a threshold (e.g., set by the base station or fixed in the standard) (or where RLF is not predicted) and related information. For example, a base station that receives this information can decide / instruct a handover to the corresponding cell.

[0172] - Information 6. (For the event that triggered the measurement report, or among the cells that triggered the measurement report) A list of one or more cells with a predicted TOS value higher than a threshold (e.g., set by the base station or fixed in the standard) (or for which a handover ping-pong is not expected) and related information (e.g., cell ID). For example, a base station that receives this information can decide / instruct a handover to the corresponding cell.

[0173] - Information 7. (For each cell) Whether a high HOF probability, a high RLF probability, or a low TOS is predicted. If the indicator related to this information is included in the prediction report or set to a specific value (e.g., “true”), this may mean / indicate that a high HOF probability, a high RLF probability, or a low TOS is predicted (for each cell). If the indicator related to this information is omitted from the prediction report or set to a specific value (e.g., “false”), this may mean / indicate that a low HOF probability, a low RLF probability, or a high TOS is predicted (for each cell).

[0174] - Information 8. (On a cell-by-cell basis) Whether HOF or RLF or handover ping-pong is expected. If the corresponding information-related indicator is included in the prediction report or set to a specific value (e.g., “true”), this may mean / indicate that HOF or RLF or handover ping-pong is expected (on a cell-by-cell basis). If the corresponding information-related indicator is omitted in the prediction report or set to a specific value (e.g., “false”), this may mean / indicate that HOF or RLF or handover ping-pong is not expected (on a cell-by-cell basis).

[0175] - Information 9. (For each cell) Predicted HOF probability or RLF probability or TOS value

[0176] - Information 10. (Cell-by-cell) Expected interruption time

[0177] - Information 11. (Cell-by-cell) Predicted cell measurements (e.g., RSRP, RSRQ, SINR)

[0178] - Information 12. (by cell) Terminal preference for handover (e.g., accept or reject)

[0179] - Information 13. (For each cell) Setting information (desired or preferred) by the terminal when assuming handover

[0180] The above prediction report may be transmitted to the base station via a Measurement Report message, a UE Information Response message, a UE Assistance Information message, or a new RRC message.

[0181] In one embodiment of the present disclosure, a new event may be defined to trigger cell measurement and / or prediction reporting. This may be configured in the terminal via a cell measurement configuration and / or prediction request (e.g., reportConfig). For example, a new event called Event X' may be defined, and Event X' may be an event that is triggered when at least one of the following events is satisfied or triggered.

[0182] - Event 1. When Event X (e.g. Event A1, A2, A3, A4, A5, A6, B1, B2) based on cell measurement is triggered.

[0183] - Event 2. When a prediction-based condition (e.g., the predicted HOF probability is higher or lower than the threshold, the conditions listed in 1g-15 above) is satisfied.

[0184] In one embodiment of the present disclosure, the terminal may transmit cell measurement and / or prediction reports either one-time (e.g., upon configured event trigger) or periodically (e.g., according to network settings).

[0185] In step 1g-20, the source base station may determine the target cell to which the terminal will be handed over. For example, this may be determined based on cell measurement and / or prediction reports transmitted by the terminal in step 1g-15.

[0186] The operations from steps 1g-25 to 1g-40 thereafter refer to the above-described steps 1f-15 to 1f-37 of FIG. 1f and the related descriptions, and any redundant descriptions are omitted here.

[0187] FIG. 1h is a diagram illustrating a signaling procedure for performing a handover based on prediction and related reporting using an AI / ML model between a terminal and a base station according to one embodiment of the present disclosure.

[0188] For the operation for step 1h-05, refer to the description of the operation (part or all) for step 1g-05 of Fig. 1g, and any duplicate description is omitted here.

[0189] For the operation for step 1h-10, refer to the description related to the operation (part or all) for step 1f-07 of Fig. 1f, and the redundant description is omitted here.

[0190] For the operation for step 1h-15, refer to the description related to the operation (part or all) for step 1f-10 of Fig. 1f, and the redundant description is omitted here.

[0191] In step 1h-20, the base station may determine one or more target candidate cells or target candidate base stations to which to transmit a prediction request before handing over the terminal based on the cell measurement report received from the terminal. For example, instead of instructing the terminal to perform the prediction request for all surrounding cells, the base station may instruct the terminal to perform the prediction request only for some best neighboring cells (e.g., cells with the highest RSRP) based on the cell measurement report. This is because the process of the terminal executing an AI / ML model to perform the prediction and reporting the result to the base station may result in the use and overload of a significant amount of computing resources and power (energy) resources, as well as radio resources for transmission and reception, compared to conventional wireless communication technologies, and therefore it may be desirable for the base station to transmit such prediction requests only for some cells.

[0192] The operation for step 1h-25 refers to the description related to the operation (partial or entire) related to the prediction request for step 1g-10 of FIG. 1g, and the redundant description is omitted here. In one embodiment of the present disclosure, the base station can request the prediction request separately from the cell measurement configuration. In one embodiment of the present disclosure, the message used for the cell measurement configuration (e.g., the RRC Reconfiguration message) and the message used for the prediction request may be different. In step 1h-25, the base station can transmit the prediction request for one or more target candidate cells, and can transmit related information (e.g., cell ID) about the target candidate cells together.

[0193] The operation for step 1h-30 refers to the description of the operation (partial or entire) for step 1g-12 of FIG. 1g, and any duplicate description is omitted here. In one embodiment of the present disclosure, the terminal can derive information to be used for prediction reporting for each target candidate cell set in step 1h-25.

[0194] The operation for step 1h-35 refers to the description of the operation (partial or entire) related to the prediction report for step 1g-15 of FIG. 1g, and the redundant description is omitted here. In one embodiment of the present disclosure, the terminal can transmit a prediction report including the above-described prediction report information (for each target candidate cell set in step 1h-25) if the above-described prediction report transmission condition is satisfied (for each target candidate cell set in step 1h-25).

[0195] In step 1h-40, the source base station may determine the target cell to which the terminal will be handed over. For example, this may be determined based on cell measurement and / or prediction reports transmitted by the terminal in steps 1h-15 and / or 1h-25.

[0196] For the operations from steps 1h-45 to 1h-60, refer to the description of the operations (part or all) of the aforementioned steps from steps 1f-15 to 1f-37 of FIG. 1f, and any redundant description is omitted here.

[0197] FIG. 1ia and FIG. 1ib are diagrams illustrating a signaling procedure for performing a handover based on prediction and related report using AI / ML between a terminal and a base station according to one embodiment of the present disclosure.

[0198] For the operation for step 1i-05, refer to the description related to the operation (part or all) for step 1g-05 of Fig. 1g, and the redundant description is omitted here.

[0199] For the operations for step 1i-10, refer to the description related to the operations (partial or complete) for step 1f-07 of Fig. 1f, and redundant description is omitted here.

[0200] The operation for steps 1i-15 refers to the description related to the operation (partial or complete) for step 1f-10 of FIG. 1f, and redundant description is omitted here.

[0201] In step 1i-17, the base station may determine one or more target candidate cells or target candidate base stations to which to transmit a prediction request before handing over the terminal based on the cell measurement report received from the terminal. For example, instead of instructing the terminal to perform a prediction request for all surrounding cells, the base station may instruct the terminal to perform the prediction request only for some best neighboring cells (e.g., cells with the highest RSRP) based on the cell measurement report. This is because the process of the terminal executing an AI / ML model to perform a prediction and reporting the result to the base station may result in the use and overload of a significant amount of computing resources and power (energy) resources, as well as radio resources for transmission and reception, compared to conventional wireless communication technologies, and therefore it may be desirable for the base station to transmit such prediction requests only for some cells.

[0202] In Fig. 1h, the base station transmits a prediction request for a target candidate cell to the terminal (step 1h-25), the terminal performs prediction (step 1h-30) and transmits the prediction result to the base station via a prediction report (step 1h-35). Then, the base station determines the target cell (step 1h-40) and transmits a handover request (step 1h-45) to the target base station. However, at this time, the target base station may not permit the handover request (e.g., by replying a HANDOVER PREPARATION FAILURE message). In this case, a series of (prediction-related) operations (steps 1h-25, 1h-30 and 1h-35) of the terminal and the base station for the target cell may be meaningless operations, which may result in a waste of computing, wireless and energy resources of the terminal and the base station. To address this issue, in FIG. 1i, before transmitting a prediction request (step 1i-45) for the determined target candidate cells (step 1i-17), the source base station may transmit a handover request (e.g., by transmitting a HANDOVER REQUEST message) for each target candidate cell and receive an authorization for the handover request (e.g., by receiving a HANDOVER REQUEST ACKNOWLEDGE message) for each target candidate cell (steps 1i-20, 1i-25, 1i-30, and 1i-35). In steps 1i-20 and 1i-25, the source base station may transmit a handover request (e.g., by transmitting a HANDOVER REQUEST message) for each target candidate cell. At this time, the source base station may indicate that the handover request is a prediction-based handover request. For example, a prediction-based handover request can be indicated by including a specific indicator (or related setting) in the HANDOVER REQUEST message or setting it to a specific value (e.g., “true”), and a non-prediction-based handover request can be indicated by omitting the indicator (or related setting) or setting it to a specific value (e.g., “false”).This may be to prevent a target candidate cell that does not support or permit a prediction-based handover from permitting the prediction-based handover request (e.g., by replying a HANDOVER PREPARATION FAILURE message). For example, a prediction-based handover, unlike a conventional handover, may incur additional time delay due to prediction-related operations (steps 1i-45, 1i-50, and 1i-55) and may be later canceled (step 1i-70) even if the target candidate base station permits the request, so the target candidate base station may not support or permit it.

[0203] In steps 1i-30 and 1i-35, the source base station may receive permission for the handover request (e.g., by receiving a HANDOVER REQUEST ACKNOWLEDGE message) as a response to the handover request (e.g., by transmitting a HANDOVER REQUEST message) for each target candidate cell. The HANDOVER REQUEST ACKNOWLEDGE message may include configuration information for the target cell to which the terminal performs the handover. The terminal may store the target cell configuration information for each target candidate cell.

[0204] A target candidate base station can indicate permission for a prediction-based handover request for each target candidate cell. For example, a target candidate base station can indicate permission for a prediction-based handover request by including a specific indicator (or related setting) in a HANDOVER REQUEST ACKNOWLEDGE message or setting it to a specific value (e.g., “true”). For example, a target candidate base station can indicate disapproval for a prediction-based handover request by omitting a corresponding indicator (or related setting) in the HANDOVER REQUEST ACKNOWLEDGE message or setting it to a specific value (e.g., “false”). For example, a target candidate base station can indicate permission for a prediction-based handover request by replying a HANDOVER REQUEST ACKNOWLEDGE message, and can indicate disapproval for a prediction-based handover request by replying a HANDOVER PREPARATION FAILURE message.

[0205] In one embodiment of the present disclosure, the target base station may indicate to the source base station permission for a conventional handover (e.g., by including configuration information for the target cell in a HANDOVER REQUEST ACKNOWLEDGE message) even if the target base station indicates disallowance of a prediction-based handover request.

[0206] In step 1i-37, if the source base station is instructed to grant permission for a prediction-based handover request, the source base station may start a new timer (e.g., timer 3 or TXnRELOCoveral_prediction). If the source base station is instructed to disallow the prediction-based handover request, the source base station may not start a new timer (e.g., timer 3 or TXnRELOCoveral_prediction). The length of the timer 3 that the source base station starts may be a longer value than the conventional timer 1 (e.g., a value set by OAM or a fixed value defined in the standard). This is because the prediction-based handover may take longer time (e.g., 1i-45, 1i-50, 1i-55) than the conventional handover.

[0207] In step 1i-40, the source base station may select some or all of the target candidate cells (e.g., based on cell measurement result reports) that have been instructed to grant permission for the prediction-based handover request.

[0208] In step 1i-45, the source base station may transmit a prediction request for the target candidate cells selected in step 1i-40 to the terminal. The operation for step 1i-45 refers to the description of the operation (partial or entire) related to the prediction request for step 1h-25 of FIG. 1h, and any redundant description is omitted here.

[0209] The operations for Step 1i-50 refer to the description of (partial or complete) the operations for Step 1h-30 of FIG. 1h, and any duplicate description is omitted here. In one embodiment of the present disclosure, the terminal can derive information to be used for prediction reporting for each target candidate cell set in Step 1i-45.

[0210] The operation for step 1i-55 refers to the description related to the operation (partial or entire) for step 1h-35, and the redundant description is omitted here. In one embodiment of the present disclosure, if the above-described prediction report transmission condition (for each target candidate cell set in step 1i-45) is satisfied, the terminal can transmit a prediction report including the above-described prediction report information (for each target candidate cell set in step 1i-45).

[0211] In step 1i-60, the source base station may determine the target cell to which the terminal will be handed over. For example, the source base station may determine the target cell to which the terminal will be handed over based on the cell measurement and / or prediction report transmitted by the terminal in step 1i-15 and / or step 1i-55.

[0212] In step 1i-65, the source base station can transmit to the terminal via an RRC Reconfiguration message including the target cell configuration information stored in step 1i-30.

[0213] In step 1i-70, the source base station may request a handover cancellation (e.g., by transmitting a HANDOVER CANCEL message) to cells among the target candidate cells that are not determined as target cells (target cells determined in step 1i-60). This may be for the purpose of releasing the settings and resources allocated by the cells for the handover of the terminal without further maintenance. In one embodiment of the present disclosure, the source base station may perform the operation for step 1i-70 at a time point between (or after) steps 1i-65 and 1i-85.

[0214] In step 1i-75, the terminal may receive the RRC Reconfiguration message including target cell configuration information and, using the configuration information, attempt a handover to the target cell. To this end, the terminal may perform random access to the target cell and transmit an RRC Reconfiguration Complete message.

[0215] In step 1i-80, the target base station may indicate the success of the handover to the source base station (e.g., by transmitting a HANDOVER SUCCESS message) (e.g., after a successful handover of the UE or after receiving an RRC Reconfiguration Complete message). Alternatively, the target base station may transmit a UE CONTEXT RELEASE (COMMAND) message to inform the source base station of the successful handover. The target base station may change the downlink data path and establish the NG interface by exchanging a PATH SWITCH REQUEST message (e.g., a message transmitted from the target base station to the AMF) and a PATH SWITCH REQUEST ACKNOWLEDGE message (e.g., a message transmitted from the AMF to the target base station) before transmitting the UE CONTEXT RELEASE (COMMAND) message.

[0216] In step 1i-85, the source base station may release configuration information or context regarding the terminal after receiving a UE CONTEXT RELEASE (COMMAND) message or a HANDOVER SUCCESS message from the target cell or the target base station (e.g., after a successful handover). The source base station may stop the above-mentioned timer 3 for the corresponding cell after receiving a UE CONTEXT RELEASE (COMMAND) message or a HANDOVER SUCCESS message from the target cell or the target base station.

[0217] In one embodiment of the present disclosure, if the terminal reconnects to the source base station or source cell (e.g., after a handover failure) before the timer expires (e.g., before receiving a UE CONTEXT RELEASE message), the source base station may stop the timer 3.

[0218] In one embodiment of the present disclosure, if timer 3 expires (e.g., if the source base station did not provide configuration information or context regarding the terminal before timer 3 expired), the source base station may release the configuration information or context regarding the terminal.

[0219] In one embodiment of the present disclosure, if timer 3 expires (e.g., if the source base station did not provide configuration information or context regarding the UE before timer 3 expires), the source base station may request the AMF to release UE-associated configuration and connection (UE-associated logical NG-connection) information. That is, timer 3 may be a timer for the source base station and / or the AMF to release the configuration and / or connection and / or context information regarding the UE without continuing to store it (e.g., when the UE connects to another base station through an RRC Reestablishment procedure after a handover failure).

[0220] In one embodiment of the present disclosure, a base station (e.g., step 1g-15, step 1h-35) that receives a prediction report including prediction information (e.g., predicted HOF probability, predicted RLF probability, predicted TOS value) from a terminal may transmit this prediction information to a target candidate base station. For example, this information may be included and transmitted when sending a HANDOVER REQUEST (e.g., step 1g-25, step 1h-45) or a new Xn interface message. For example, the target candidate base station that received this may make a decision by taking this information into consideration when deciding whether to permit or reject a handover request from the terminal.

[0221] FIG. 1j is a diagram illustrating the structure of a terminal (1j-00) according to one embodiment of the present disclosure.

[0222] Referring to FIG. 1j, a terminal (1j-00) according to one embodiment of the present disclosure may include an RF (Radio Frequency) processing unit (1j-10), a baseband processing unit (1j-20), a storage unit (1j-30), and a control unit (1j-40).

[0223] The RF processing unit (1j-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 (1j-10) up-converts the baseband signal provided from the baseband processing unit (1j-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 (1j-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 Fig. 1j, only one antenna is illustrated, but the terminal may be equipped with multiple antennas. In addition, the RF processing unit (1j-10) may include multiple RF chains. Furthermore, the RF processing unit (1j-10) may perform beamforming. For the above beamforming, the RF processing unit (1j-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.

[0224] The baseband processing unit (1j-20) 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 (1j-20) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (1j-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (1j-10). For example, in the case of following the OFDM (orthogonal frequency division multiplexing) method, when transmitting data, the baseband processing unit (1j-20) generates complex symbols by encoding and modulating a transmission bit stream, maps the complex symbols to subcarriers, and then configures OFDM symbols by performing an inverse fast Fourier transform (IFFT) operation and inserting a cyclic prefix (CP). In addition, when receiving data, the baseband processing unit (1j-20) divides the baseband signal provided from the RF processing unit (1j-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.

[0225] The baseband processing unit (1j-20) and the RF processing unit (1j-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (1j-20) and the RF processing unit (1j-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 (1j-20) and the RF processing unit (1j-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 (1j-20) and the RF processing unit (1j-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.

[0226] The storage unit (1j-30) stores data such as basic programs, application programs, and setting information for the operation of the terminal (1j-00) according to one embodiment of the present disclosure. The storage unit (1j-30) provides the stored data upon request from the control unit (1j-40). The storage unit (1j-30) may be referred to as a memory.

[0227] The above control unit (1j-40) controls the overall operations of the terminal (1j-00). For example, the control unit (1j-40) transmits and receives signals through the baseband processing unit (1j-20) and the RF processing unit (1j-10). In addition, the control unit (1j-40) records and reads data in the storage unit (1j-30). For this purpose, the control unit (1j-40) may include at least one processor. For example, the control unit (1j-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 (1j-42) as illustrated in the drawing. The control unit (1j-40) can control the overall operation of the terminal (1j-00) according to the embodiments proposed in the present disclosure by executing one or more commands stored in the memory (1j-30).

[0228] The processor (1j-40) may include various processing circuits and / or multiple processors. For example, the term “processor” as used herein, including in the claims, may include various processing circuits, including at least one processor. One or more processors in at least one processor may be configured to perform various functions described herein, individually and / or collectively, in a distributed fashion. As used herein, “processor,” “at least one processor,” and “one or more processors” may be configured to perform multiple functions. However, these terms encompass, without limitation, situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor may perform all of the functions. Furthermore, the at least one processor may include a combination of processors that perform various of the disclosed functions in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions.

[0229] In one embodiment, at least one processor (1j-40) may be a general-purpose processor, such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-only processor, such as a GPU or VPU (Vision Processing Unit), or an AI-only processor, such as an NPU. For example, if one or more processors are AI-only processors, the AI-only processors may be designed with a hardware structure specialized for processing a specific AI model.

[0230] The predefined operation rules or artificial intelligence model are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model (or deep learning model) is trained using a plurality of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0231] An artificial intelligence model (or deep learning model) may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0232] FIG. 1k is a diagram illustrating the structure of a base station (1k-00) according to one embodiment of the present disclosure.

[0233] Referring to FIG. 1k, a base station (1k-00) according to an example of the present disclosure may include an RF processing unit (1k-10), a baseband processing unit (1k-20), a backhaul communication unit (1k-30), a storage unit (1k-40), and a control unit (1k-50).

[0234] The RF processing unit (1k-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 (1k-10) up-converts the baseband signal provided from the baseband processing unit (1k-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 (1k-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc. In FIG. k, only one antenna is illustrated, but the base station may have multiple antennas. In addition, the RF processing unit (1k-10) may include multiple RF chains. Furthermore, the RF processing unit (1k-10) may perform beamforming. For the above beamforming, the RF processing unit (1k-10) can adjust the phase and magnitude 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.

[0235] The baseband processing unit (1k-20) 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 (1k-20) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (1k-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (1k-10). For example, in the case of OFDM, when transmitting data, the baseband processing unit (1k-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 (1k-20) divides the baseband signal provided from the RF processing unit (1k-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 (1k-20) and the RF processing unit (1k-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (1k-20) and the RF processing unit (1k-10) may be referred to as a transmitter, a receiver, a transceiver, a communication unit, or a wireless communication unit.

[0236] The above backhaul communication unit (1k-30) provides an interface for performing communication with other nodes within the network. That is, the backhaul communication unit (1k-30) converts a bit string transmitted from the 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.

[0237] The storage unit (1k-40) stores data such as basic programs, application programs, and setting information for the operation of the base station (1k-00). In particular, the storage unit (1k-40) can store information on bearers assigned to connected terminals, measurement results reported from connected terminals, and the like. In addition, the storage unit (1k-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 (1k-40) provides the stored data upon request from the control unit (1k-50). The storage unit (1k-40) can be referred to as a memory.

[0238] The control unit (1k-50) controls the overall operations of the base station (1k-00). For example, the control unit (1k-50) transmits and receives signals through the baseband processing unit (1k-20) and the RF processing unit (1k-10) or through the backhaul communication unit (1k-30). In addition, the control unit (1k-50) records and reads data in the storage unit (1k-40). For this purpose, the control unit (1k-50) may include at least one processor, and may include a multi-connection processing unit (1k-52) as illustrated in the drawing. The control unit (1k-50) may control the overall operations of the base station (1k-00) according to the embodiments proposed in the present disclosure by executing one or more commands stored in the memory (1k-40).

[0239] The processor (1k-50) may include various processing circuits and / or multiple processors. For example, the term “processor” as used herein, including in the claims, may include various processing circuits, including at least one processor. One or more processors in at least one processor may be configured to perform various functions described herein, individually and / or collectively, in a distributed fashion. As used herein, “processor,” “at least one processor,” and “one or more processors” may be configured to perform various functions. However, these terms encompass, without limitation, situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor may perform all of the functions. Furthermore, at least one processor may include a combination of processors that perform various functions of the disclosed functions in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions.

[0240] In one embodiment, at least one processor (1k-50) may be a general-purpose processor, such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-only processor, such as a GPU or VPU (Vision Processing Unit), or an AI-only processor, such as an NPU. For example, if one or more processors are AI-only processors, the AI-only processor may be designed with a hardware structure specialized for processing a specific AI model.

[0241] The predefined operation rules or artificial intelligence model are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model (or deep learning model) is trained using a plurality of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0242] An artificial intelligence model (or deep learning model) may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0243] Meanwhile, the embodiments of the present disclosure disclosed in this disclosure and the 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.

[0244] 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.

[0245] The specific examples used to explain embodiments according to the present disclosure are merely one combination of each criterion, method, detailed method, and operation, and through a combination of at least two or more of the various techniques described, a terminal or base station can perform an AI / ML-based handover operation in a next-generation mobile communication system. Furthermore, at this time, the operation may be performed according to a method determined through one or a combination of at least two of the aforementioned techniques. For example, it may be possible to perform a portion of the operation of one embodiment in combination with a portion of the operation of another embodiment.

[0246] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, a 'non-transitory storage medium' means only that it is a tangible device and does not contain signals (e.g., electromagnetic waves), and this term does not distinguish between cases where data is permanently stored in the storage medium and cases where it is temporarily stored. For example, a 'non-transitory storage medium' may include a buffer in which data is temporarily stored. In one embodiment, the method according to various embodiments disclosed in the present document may be provided as a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read only memory (CD-ROM)), or may be distributed online (e.g., by download or upload) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be temporarily stored or temporarily created in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

Claims

1. In a method of UE (user equipment) in a wireless communication system, A step of transmitting a UE capability information message including capability information regarding AI / ML-based prediction to a base station; A step of receiving handover-related prediction setting information from the base station; A step of performing handover performance prediction using AI / ML based on the above handover-related prediction setting information; and A step of transmitting a prediction report including predicted handover performance related information to the base station; A method in which a target cell for handover is determined based on the above prediction report.

2. In the method of paragraph 1, The above handover-related prediction setting information includes information about one or more first target candidate cells, A step of performing handover performance prediction for each of the one or more first target candidate cells using the AI / ML based on the handover-related prediction setting information; and A method wherein the above prediction report includes predicted handover performance related information for each of the one or more first target candidate cells.

3. In the method of paragraph 1, The above handover-related prediction setting information includes information about one or more second target candidate cells, The above second target candidate cell is a cell that has instructed permission for an AI / ML-based handover request, A step of performing handover performance prediction for each of the one or more second target candidate cells using the AI / ML based on the handover-related prediction setting information; and A method wherein the above prediction report includes predicted handover performance related information for each of the one or more second target candidate cells.

4. In the method of the first clause, the capability information regarding the AI / ML-based prediction included in the UE capability information message is Whether the above UE supports AI / ML-based handover failure (HOF) related information prediction and reporting; Whether the UE supports AI / ML-based radio link failure (RLF) information prediction and reporting; Whether the UE supports AI / ML-based prediction and reporting of cell time of stay (TOS) related information; Whether the above UE supports AI / ML-based handover interruption time-related information prediction and reporting; Whether the UE supports response prediction and reporting for AI / ML-based handover instructions; or A method comprising at least one of: whether the UE supports prediction and reporting of AI / ML-based preferred network settings; 5. In the method of the first clause, the handover-related prediction setting information is: A threshold for the probability that a UE will fail a handover; A threshold for the probability that a UE will fail a wireless connection; Threshold for the UE's cell residence time; "reference time" at which prediction is performed; Information indicating whether each piece of information that the UE may include in the prediction report is included; or A method comprising at least one of: a length value for a timer related to prediction and reporting of the UE; 6. In the method of paragraph 1, the prediction report is: A list of one or more cells for which HOF is predicted; A list of one or more cells for which HOF is not predicted; A list of one or more cells for which RLF is predicted; A list of one or more cells for which RLF is not predicted; A list of one or more cells with predicted TOS values ​​lower than a threshold; A list of one or more cells with predicted TOS values ​​higher than a threshold; Information indicating whether a HOF probability higher than a threshold, an RLF probability higher than a threshold, or a TOS lower than a threshold is predicted for each cell; Predicted HOF probability or RLF probability or TOS value per cell; Predicted handover interruption time per cell; Cell measurement values ​​predicted cell by cell; Information indicating the UE's preference for handover on a cell-by-cell basis; or A method comprising at least one of the following: a network setting preferred by a terminal when assuming a handover on a cell-by-cell basis; 7. In the method of the first clause, the step of transmitting the prediction report to the base station comprises: A step of determining whether at least one condition for triggering a prediction report is satisfied; and A method comprising: transmitting the prediction report to the base station when at least one condition for triggering the prediction report is satisfied; 8. In a wireless communication system, in UE (user equipment), memory for storing one or more instructions; and At least one processor; wherein the at least one processor executes the one or more instructions stored in the memory by: Transmitting a UE capability information message including capability information regarding AI / ML-based prediction to the base station; Receive handover-related prediction setting information from the above base station; Based on the above handover-related prediction setting information, handover performance prediction is performed using AI / ML; and Transmitting a prediction report containing predicted handover performance related information to the above base station, A UE for which a target cell for handover is determined based on the above prediction report.

9. In the UE of Article 8, The above handover-related prediction setting information includes information about one or more first target candidate cells, The at least one processor further executes the one or more commands stored in the memory to: perform handover performance prediction for each of the one or more first target candidate cells using the AI / ML based on the handover-related prediction setting information, and The above prediction report includes information related to handover performance predicted for each of the one or more first target candidate cells.

10. In the UE of Article 8, The above handover-related prediction setting information includes information about one or more second target candidate cells, The above second target candidate cell is a cell that has instructed permission for an AI / ML-based handover request, The at least one processor performs handover performance prediction for each of the one or more second target candidate cells by executing the one or more commands stored in the memory: based on the handover-related prediction setting information, using the AI / ML, and The above prediction report includes information related to handover performance predicted for each of the one or more second target candidate cells.

11. In a method of a base station in a wireless communication system, A step of receiving a UE capability information message including capability information regarding AI / ML-based prediction from a UE (user equipment); A step of transmitting handover-related prediction setting information to the UE; A step of receiving a prediction report including handover performance-related information predicted using AI / ML from the UE; and A method comprising: a step of determining a target cell for handover based on the above prediction report; 12. In the method of Article 11, further comprising a step of determining one or more first target candidate cells; The above handover-related prediction setting information includes information about the one or more first target candidate cells, and A method wherein the above prediction report includes predicted handover performance related information for each of the one or more first target candidate cells.

13. In the method of Article 11, A step of determining one or more first target candidate cells; A step of transmitting a handover request message to one or more first target candidate cells; A step of receiving a permission message for a handover request from at least one cell among the one or more first target candidate cells; further comprising a step of determining at least one cell as a second target candidate cell; The above handover-related prediction setting information includes information about one or more second target candidate cells, and A method wherein the above prediction report includes predicted handover performance related information for each of the one or more second target candidate cells.

14. In a wireless communication system, at a base station, memory for storing one or more instructions; and At least one processor; wherein the at least one processor executes the one or more instructions stored in the memory by: Receive a UE capability information message including capability information regarding AI / ML-based prediction from a UE (user equipment); Transmit handover-related prediction setting information to the above UE; Receive a prediction report including handover performance-related information predicted using AI / ML from the UE; and A base station that determines a target cell for handover based on the above prediction report.

15. In the base station of Article 14, At least one processor; comprising: further comprising: determining one or more first target candidate cells by further executing one or more instructions stored in the memory; The above handover-related prediction setting information includes information about the one or more first target candidate cells, and A base station, wherein the above prediction report includes predicted handover performance related information for each of the one or more first target candidate cells.

Images