Method and apparatus for predicting radio link failure on basis of artificial intelligence in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a data transmission rate higher than that of a 4G communication system such as LTE. An operation method of a terminal, according to embodiments of the present disclosure, comprises the steps of: receiving, from a base station, a first message for requesting a report of a prediction based on an artificial intelligence (AI) / ML model; in response to the first message, generating, on the basis of the AI / ML model, prediction information about a radio link failure; and transmitting, to the base station, a second message for reporting the prediction information, wherein the first message includes information indicating at least one cause value related to the radio link failure, and the prediction information includes a probability of occurrence of the radio link failure for each of the at least one cause value.

Description

Method and device for predicting wireless link failure based on artificial intelligence in a wireless communication system

[0001] The present disclosure relates to a method and device for artificial intelligence-based radio link failure (RLF) prediction in a wireless 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 the 5G (5th Generation) communication system, 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 also expected to evolve into diverse form factors, such as augmented reality glasses, virtual reality headsets, and holographic devices. In the 6G (6th Generation) 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 (i.e., 1,000 gigabits) per second (bps) 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 and 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 (THz) 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 have more severe path loss and atmospheric absorption, making it more important to develop technologies that can guarantee signal reach, or coverage. Key technologies to ensure coverage include Radio Frequency (RF) components, antennas, new waveforms that offer better coverage than Orthogonal Frequency Division Multiplexing (OFDM), 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 Surface (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 at the same time for uplink and downlink; network technology that integrates satellites and HAPS (High-Altitude Platform Stations); 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 AI (Artificial Intelligence) 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 (XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems through enhanced security and reliability, will be applied in diverse fields such as industry, medicine, automobiles, and home appliances.

[0007] The present disclosure may have as its primary purpose a method and device for predicting radio link failure (RLF) based on artificial intelligence in communication systems such as 5G, 5G-Advanced, and 6G.

[0008] A method performed by a terminal in a wireless communication system, comprising: receiving a first message requesting a report of a prediction based on an artificial intelligence (AI) / ML model from a base station; generating prediction information for a radio link failure (RLF) based on the AI / ML model based on the first message; and transmitting a second message for reporting the prediction information to the base station, wherein the first message includes information indicating at least one cause value related to the radio link failure, and the prediction information includes a probability of occurrence of the radio link failure for each of the at least one cause value.

[0009] A method performed by a base station in a wireless communication system, comprising: a step of transmitting a first message requesting a report of a prediction based on an artificial intelligence (AI) / ML model to a terminal; and a step of receiving a second message including prediction information on a radio link failure (RLF) from the terminal, wherein the first message includes information indicating at least one cause value related to the radio link failure, and the prediction information includes a probability of occurrence of the radio link failure for each of the at least one cause value.

[0010] The method and device according to embodiments of the present disclosure can effectively predict radio link failure (RLF) based on artificial intelligence in a wireless communication system.

[0011] Specifically, embodiments of the present disclosure have the effect of improving the accuracy of prediction and effectively reducing power consumption by transmitting and receiving information for artificial intelligence-based wireless link failure prediction between a terminal and a base station.

[0012] In addition, embodiments of the present disclosure have the effect of improving the communication quality of a network by effectively predicting wireless link failure.

[0013] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0014] The features and advantages of the embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0015] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0016] FIG. 2 is a drawing for explaining the structure of a terminal according to embodiments of the present disclosure.

[0017] FIG. 3 is a diagram for explaining the structure of a network entity (or base station) according to embodiments of the present disclosure.

[0018] FIG. 4 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0019] FIG. 5 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0020] FIG. 6 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0021] FIG. 7 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0022] FIG. 8 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0023] FIG. 9 illustrates the operation of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0024] FIG. 10 illustrates a terminal operation flowchart for a wireless link failure prediction method according to embodiments of the present disclosure.

[0025] FIG. 11 illustrates an operation flowchart of a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0026] Embodiments of the present disclosure may address the problems and / or disadvantages described above and provide the advantages described below. One aspect of the present disclosure may provide a network entity (or node) and a communication method thereof in a wireless communication system.

[0027] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0028] The various embodiments of the present disclosure described below illustrate hardware-based approaches. However, since the various embodiments of the present disclosure encompass techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude software-based approaches.

[0029] Additionally, although various embodiments of the present disclosure describe various embodiments using terminology used in certain communication standards (e.g., 3rd generation partnership project (3GPP)), this is merely an example for illustrative purposes. Various embodiments of the present disclosure can be easily modified and applied to other communication systems.

[0030] Hereinafter, various embodiments of the present disclosure are described.

[0031] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0032] FIG. 1 illustrates some of the nodes utilizing a wireless channel in a wireless communication system, including a base station (110), a first terminal (120), and / or a second terminal (130). Although FIG. 1 illustrates only one base station, this is merely an example. The wireless communication system of FIG. 1 may further include other base stations identical or similar to the base station (110).

[0033] The base station (110) is a network infrastructure that provides wireless access to terminals (120, 130). The base station (110) has coverage defined as a certain geographical area based on the distance at which a signal can be transmitted. In addition to the base station, the base station (110) may be referred to as an 'access point (AP)', 'evolved Node B (eNB)', 'next generation node B (gNB)', '5G node (5th generation node)', 'wireless point', 'transmission / reception point (TRP)', or other terms having equivalent technical meanings.

[0034] The first terminal (120) and the second terminal (130) are each devices used by a user and can communicate with the base station (110) via a wireless channel. At least one of the first terminal (120) or the second terminal (130) can be operated without the user's intervention. For example, at least one of the first terminal (120) or the second terminal (130) may be a device that performs machine type communication (MTC) and may not be carried by the user. Each of the first terminal (120) and the second terminal (130) may be referred to as a terminal, or other terms having equivalent technical meanings, such as 'user equipment (UE),' 'mobile station,' 'subscriber station,' 'customer premises equipment (CPE),' 'remote terminal,' 'wireless terminal,' 'electronic device,' or 'user device.'

[0035] The base station (110), the first terminal (120), and the second terminal (130) can transmit and / or receive wireless signals in the millimeter wave (mmWave) band (e.g., 28 GHz, 30 GHz, 38 GHz, 60 GHz). At this time, in order to improve channel gain, the base station (110), the first terminal (120), and / or the second terminal (130) can perform beamforming.

[0036] Beamforming may include transmit beamforming and / or receive beamforming. That is, the base station (110), the first terminal (120), and / or the second terminal (130) may impart directionality to the transmit signal or the receive signal. To impart directionality to the receive signal, the base station (110) and / or the terminals (120, 130) may select serving beams (112, 113, 121, 131) through a beam search or beam management procedure. After the serving beams (112, 113, 121, 131) are selected, subsequent communication may be performed through resources that are in a quasi-co-located (QCL) relationship with the resources that transmitted the serving beams (112, 113, 121, 131).

[0037] The base station (110), the first terminal (120), and the second terminal (130) of the present disclosure may each be a transmitting apparatus, a transmitting node, a receiving apparatus, and / or a receiving node. For example, the base station (110) may transmit an RF (radio frequency) signal to the first terminal (120). The base station (110) may receive the RF signal from the first terminal (120). As another example, the first terminal (120) may transmit an RF signal to the base station (110) or the second terminal (130). The first terminal (120) may receive the RF signal from the base station (110) or the second terminal (130).

[0038] Figure 2 is a drawing for explaining the structure of a terminal according to embodiments.

[0039] Referring to FIG. 2, a terminal (200) according to embodiments may include a transceiver (transmitting and receiving unit) (210), a memory (220), and / or a processor (230). In the present disclosure, the terminal (200) is described as including the transceiver (210), the memory (220), and / or the processor (230), but this is merely an example. For example, the terminal (200) may further include other components in addition to the transceiver (210), the memory (220), and the processor (230).

[0040] According to embodiments, the transceiver (210), memory (220), and processor (230) may be implemented or formed as separate chips. However, this is merely an example, and the transceiver (210), memory (220), and / or processor (230) may be implemented or formed as a single chip.

[0041] According to embodiments, the transceiver (210) may include at least one transmitter and / or at least one receiver. For example, the transceiver (210) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (210) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0042] The configurations of the transceiver (210) described in the present disclosure are merely examples, and the configuration of the transceiver (210) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (210) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0043] According to embodiments, the transceiver (210) may transmit or receive a signal to the processor (230). For example, the transceiver (210) may transmit or deliver an RF signal received via a wireless communication channel to the processor (230). The transceiver (210) may receive or deliver an RF signal from the processor (230).

[0044] According to embodiments, the transceiver (210) may be referred to as a UE transmitter or a UE receiver.

[0045] According to embodiments, the transceiver (210) may transmit a signal to a base station (e.g., base station (110) of FIG. 1) or a network entity (e.g., access and mobility management function (AMF) entity) or receive a signal from the base station or the network entity. In embodiments, the transmitted or received signal may include a control signal and data.

[0046] According to embodiments, the memory (220) may include or store programs and data necessary for the operations of the terminal (200). For example, the memory (220) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration of the terminal (200) (e.g., a processor (230) or a transceiver (210)). The memory (220) may store control information or data including a signal acquired by the terminal (200). In embodiments, the memory (220) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0047] According to embodiments, the processor (230) may include one processor or multiple processors. For example, the processor (230) may include a communication processor. For example, the processor (230) may include a communication processor and / or an application processor.

[0048] According to embodiments, the processor (230) may control a series of processes performed by the terminal (200). For example, the transceiver (210) may receive a data signal including control information transmitted by a base station or network entity. The processor (230) may process the received control signal and data signal.

[0049] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of the terminal (200). For example, the term "processor" may be replaced with a controller or a computing circuit.

[0050] The terminal (200) of the present disclosure may correspond to the first terminal (120) and / or the second terminal (130) of FIG. 1.

[0051] FIG. 3 is a drawing for explaining the structure of a base station (or network entity) according to embodiments.

[0052] Referring to FIG. 3, a base station (300) according to embodiments may include a transceiver (transmitting and receiving unit) (310), a memory (320), and / or a processor (330). Although the base station (300) is described in the present disclosure as including the transceiver (310), the memory (320), and / or the processor (330), this is merely an example. For example, the base station (300) may further include other components in addition to the transceiver (310), the memory (320), and the processor (330). The base station (300) may represent network functions included in the base station or other core networks.

[0053] According to embodiments, the transceiver (310), memory (320), and processor (330) may be implemented or formed as separate chips, respectively. However, this is merely an example, and the transceiver (310), memory (320), and / or processor (330) may be implemented or formed as a single chip.

[0054] According to embodiments, the transceiver (310) may include at least one transmitter and / or at least one receiver. For example, the transceiver (310) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (310) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0055] The configurations of the transceiver (310) described in the present disclosure are merely examples, and the configuration of the transceiver (310) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (310) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0056] According to embodiments, the transceiver (310) may transmit or receive a signal to the processor (330). For example, the transceiver (310) may transmit or deliver an RF signal received via a wireless communication channel to the processor (330). The transceiver (310) may receive or deliver an RF signal from the processor (230).

[0057] According to embodiments, the transceiver (310) may be referred to as a base station transmitter or a base station receiver.

[0058] According to embodiments, the transceiver (310) may transmit a signal to the terminal (200) or receive a signal from the terminal (200). In embodiments, the transmitted or received signal may include a control signal and data.

[0059] According to embodiments, the memory (320) may include programs and data necessary for the operations of the base station (300). For example, the memory (320) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration of the base station (300) (e.g., a processor (330) or a transceiver (310)). The memory (320) may store control information or data including a signal acquired by the base station (300). In embodiments, the memory (320) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0060] According to embodiments, the processor (330) may include one processor or multiple processors. For example, the processor (330) may include a communication processor. For example, the processor (330) may include a communication processor and / or an application processor.

[0061] According to embodiments, the processor (330) may control a series of processes performed by the base station (300). For example, the transceiver (310) may receive a data signal including control information transmitted by the base station. The processor (330) may process the received control signal and data signal.

[0062] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of the base station (300). For example, the term "processor" may be replaced with a controller or a computing unit.

[0063] The base station (300) of the present disclosure can correspond to the base station (110) of FIG. 1.

[0064] The devices described in FIGS. 2 and 3 may correspond to devices of a transmitter or receiver. A terminal or base station according to embodiments of the present disclosure may be a transmitter if it is a transmitter, and may be a receiver if it is a receiver.

[0065] Hereinafter, the transmitter and receiver may refer to the terminals or base stations described in FIGS. 1 to 3, respectively. When describing downlink signals, the base station will be the transmitter and the terminal will be the receiver, and when describing uplink signals, the terminal will be the transmitter and the base station will be the receiver.

[0066] FIG. 4 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. The terminal and base station for performing the operations described in FIG. 4 may correspond to the terminal of FIG. 2 and the base station of FIG. 3 , respectively.

[0067] A base station according to embodiments of the present disclosure may correspond to a primary cell (pcell) or a primary secondary cell (pscell), or may correspond to a special cell (spcell) that refers to a primary cell (pcell) and a primary secondary cell (pscell).

[0068] Referring to FIG. 4, transmission and reception operations for predicting radio link failure (RLF) and reporting it to a base station by a terminal (UE) (410) based on an artificial intelligence model (deep learning model or machine learning model) are described.

[0069] In operation 432, the terminal (410) may receive an RRC reconfiguration message from the base station (420). The RRC reconfiguration message may include configuration information related to the operation of the terminal (410). For example, the configuration information may include information regarding radio link failure prediction, and the information regarding radio link failure prediction may include various configuration information such as information regarding criteria for declaring radio link failure, information regarding an artificial intelligence model required for predicting radio link failure, and input information regarding an artificial intelligence model for predicting radio link failure. In addition, the configuration information included in the RRC reconfiguration message may include configuration information regarding reporting of radio link failure prediction results of the terminal (410). For example, information regarding reporting conditions, reporting cycles, and reporting counts for radio link failure prediction results may be included in the configuration information.

[0070] In operation 434, the terminal (410) may transmit an RRC reconfiguration complete message to the base station (420). The RRC reconfiguration complete message may indicate that the terminal (410) has received the RRC reconfiguration message and that the configuration information included in the RRC reconfiguration message has been applied.

[0071] In operation 436, the terminal (410) may receive an artificial intelligence (AI) information message from the base station (420). The AI ​​information message may include messages for settings related to an AI model, inference performance of the AI ​​model, and / or inference result reporting of the AI ​​model. The AI ​​information message may include a message for requesting a report based on an AI / ML (machine learning) model from the terminal (410). According to one embodiment, the AI ​​information message may include a message for requesting the base station (420) to report a prediction result based on the AI / ML model to the terminal (410). According to another embodiment, the AI ​​information message may include a message for requesting the base station (420) to request the terminal (410) to perform a prediction on an RLF based on the AI / ML model and report the result. The AI ​​information message may include information on the criteria for the terminal (410) to declare a wireless link failure, information on the AI / ML model required to predict the wireless link failure, input information for the AI / ML model, etc., and may include configuration information for the terminal (410) to report the wireless link failure prediction result to the base station (420). For example, configuration information on the reporting conditions, reporting cycle, and number of reports for the wireless link failure prediction result may be included in the AI ​​information message.

[0072] In one embodiment, the configuration information for the terminal (410) to perform wireless link failure prediction and reporting may be included in an RRC reset message by operation 432 or may be included in an artificial intelligence information message by operation 436 and transmitted from the base station (420) to the terminal (410).

[0073] In one embodiment, the AI ​​information message may include type information (e.g., cause value) for a radio link failure. The type information for the radio link failure may include type information that is distinguished according to the cause of the radio link failure. For example, the type information may be distinguished based on the cause of the radio link failure, such as a radio link failure related to the expiration of a T310 timer, a radio link failure related to a random access channel (RACH) problem probability, a radio link failure related to the maximum number of uplink retransmissions in the RLC (Radio link control) layer, or a radio link failure related to an uplink Listen before talk (LBT) failure. Accordingly, the terminal (410) may perform a prediction for the type of radio link failure indicated by the type information for the radio link failure received from the base station (420).

[0074] In one embodiment, the AI ​​information message may include input information for an AI / ML model for each wireless link failure type. The input information for the AI / ML model for each wireless link failure type may indicate information that the terminal must input into the AI / ML model to generate wireless link failure prediction information for each wireless link failure type (e.g., cause value).

[0075] In one embodiment, the type information for a wireless link failure may correspond to information in an AI / ML model for predicting a wireless link failure. For example, an AI / ML model for predicting a wireless link failure associated with the expiration of a T310 timer may exist. Accordingly, the terminal (410) may receive AI / ML model information (e.g., an AI / ML model identifier) ​​for predicting a specific type of wireless link failure from the base station (420), and the terminal (410) may generate prediction information for the corresponding type of wireless link failure using the AI / ML model indicated by the received AI / ML model information.

[0076] In one embodiment, the terminal (410) may receive an AI / ML model from the base station (420). Specifically, the terminal (410) may receive the AI / ML model itself, or may receive information necessary for the terminal (410) to configure the AI / ML model from the base station (420). That is, the base station (420) may transmit to the terminal (410) at least one AI / ML model for predicting a specific wireless link failure type or information for configuring at least one AI / ML model, and may receive prediction information for a specific wireless link failure type from the terminal (410). Accordingly, the base station (420) may change the setting information for the terminal (410) based on the prediction information for each wireless link failure type received from the terminal (410).

[0077] In one embodiment, the terminal (410) may receive a separate downlink RRC message or RRC reconfiguration message from the base station (420) that includes an instruction to terminate radio link failure prediction and reporting. The radio link failure prediction and reporting operation of the terminal (410) may be activated or deactivated by Downlink control information (DCI) or Medium Access Control (MAC) Control element (CE) received from the base station. When the terminal (410) receives the instruction to terminate radio link failure prediction and reporting, the terminal (410) may delete previously stored configuration information for radio link failure prediction and reporting. Optionally, when radio link failure prediction and reporting is terminated, the terminal (410) may transmit an instruction to the AI / ML model to stop inference and may stop transmitting input information to the AI / ML model.

[0078] Operation 438 may represent an operation in which the terminal (410) performs wireless link failure prediction and generates wireless link failure prediction information. The terminal (410) may perform wireless link failure prediction and generate prediction information based on information received in operation 432 or operation 436.

[0079] In one embodiment, the terminal (410) can predict a radio link failure for a cause indicated by the type information based on the type information for the received radio link failure. For example, if the radio link failure type information indicates a radio link failure related to the expiration of a T310 timer and a radio link failure related to a random access procedure (e.g., RACH problem probability), the terminal (410) can calculate the probability of a radio link failure related to the expiration of the T310 timer and the probability of a radio link failure related to a random access procedure based on an AI / ML model corresponding to each type information. The AI / ML model corresponding to the radio link failure type information may be stored in the memory of the terminal (410) or may be received from the base station (420).

[0080] Operation 440 may represent an operation in which the terminal (410) transmits the prediction information generated in operation 438 to the base station (420). The terminal (410) may report the radio link failure prediction information generated in operation 438 to the base station (420) based on the information received in operations 432 and 436. The radio link failure prediction information may include information on the possibility of occurrence of radio link failure for each radio link failure type. For example, when the base station (420) transmits first type information, second type information, and third type information to the terminal, the terminal (410) may report to the base station (420) the possibility of radio link failure for the first type, the possibility of radio link failure for the second type, and the possibility of radio link failure for the third type.

[0081] Operation 442 may represent an operation in which the base station (420) determines whether to reset related parameters based on the radio link failure prediction report received in operation 440. For example, if the base station (420) determines that there is a high possibility of a radio link failure for the first type, it may determine whether to transmit changed configuration information to the terminal (410) (serving cell configuration via an RRC reset message) so as to reduce the possibility of a radio link failure for the first type. In other words, the base station (420) may perform radio resource management based on the radio link failure prediction report received from the terminal (410).

[0082] In one embodiment, if the base station (420) determines that there is a high probability of a radio link failure type due to expiration of the T310 timer, the base station (420) may adjust the value of the T310 timer or reset the RLM (Radio link monitoring) RS (Reference signal) settings.

[0083] In one embodiment, if the base station (420) determines that there is a high possibility of a type of radio link failure related to the random access procedure, the base station (420) may reset settings related to the random access channel (RACH). Specifically, the base station (420) may reset RACH resources, transmission power, random access preamble (RA preamble) retransmission timer, etc.

[0084] In one embodiment, when the base station (420) determines that there is a high possibility of a radio link failure type related to the maximum number of uplink retransmissions (max UL ReTx) in the RLC (Radio link control) layer of the terminal (410), the base station (420) may reset the RLC-related settings by adjusting the retransmission timer.

[0085] In one embodiment, if the base station (420) determines that there is a high probability of a type of radio link failure associated with an uplink LBT (Listen before talk) failure, the base station (420) may change the settings of the terminal (410) by adjusting parameters for the LBT operation.

[0086] In one embodiment, the determination of whether each type of wireless link failure is likely by the base station (420) may be performed based on a predetermined threshold value or a determination by the base station (420) itself.

[0087] In one embodiment, when the base station (420) determines that it is difficult to avoid a radio link failure based on a radio link failure prediction report, the base station (420) may determine a handover (HO) to cause the terminal (410) to change cells and transmit a handover command to the terminal (410).

[0088] The 444 operation may represent an operation in which the terminal (410) receives changed setting information from the base station (420) through an RRC reset message.

[0089] Action 446 represents an action in which the terminal (410) transmits an RRC reset completion message to the base station (420).

[0090] FIG. 5 illustrates the operations of a terminal and a base station for a method for predicting radio link failure according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 5 may represent a process in which a terminal predicts and reports radio link failure for a candidate cell (or neighboring cell) associated with a conditional handover (CHO).

[0091] A base station according to embodiments of the present disclosure may correspond to a primary cell (pcell) or a primary secondary cell (pscell), or may correspond to a special cell (spcell) that refers to a primary cell (pcell) and a primary secondary cell (pscell).

[0092] The terminal and base station performing the operation described in Fig. 5 may correspond to the terminal and base station of Figs. 2 and 3, respectively.

[0093] Base station 1 and base station 2 described in FIG. 5 may be physically the same base station or different base stations. For example, if one base station simultaneously provides a serving cell and a candidate cell, base station 1 and base station 2 may be the same base station. Furthermore, for example, the serving cell may be provided by base station 1, the candidate cell may be provided by base station 2, and base station 1 and base station 2 may be different base stations.

[0094] Referring to FIG. 5, transmission and reception operations for predicting radio link failure (RLF) for a base station (520) for a serving cell and a base station (530) for a candidate cell based on an artificial intelligence model (deep learning model or machine learning model) and reporting it to the base station for the serving cell are described.

[0095] The 532 operation represents the transmission and reception of configuration information related to conditional handover between a base station (520) for a serving cell (hereinafter, a first base station) and a base station (530) for a candidate cell (hereinafter, a second base station).

[0096] In operation 534, the terminal (510) may receive an RRC reconfiguration message from the first base station (520). The RRC reconfiguration message may include configuration information related to the operation of the terminal (510). For example, the configuration information may include information regarding radio link failure prediction, and the information regarding radio link failure prediction may include various configuration information such as information regarding criteria for declaring radio link failure, information regarding an AI / ML model required for predicting radio link failure, and input information regarding an AI / ML model for predicting radio link failure. In addition, the configuration information included in the RRC reconfiguration message may include configuration information regarding reporting of radio link failure prediction results of the terminal (510). For example, information regarding reporting conditions, reporting cycles, and reporting counts for radio link failure prediction results may be included in the configuration information.

[0097] In operation 536, the terminal (510) may transmit an RRC reconfiguration complete message to the first base station (520). The RRC reconfiguration complete message may indicate that the terminal (510) has received the RRC reconfiguration message and that the configuration information included in the RRC reconfiguration message has been applied.

[0098] In operation 538, the terminal (510) may receive an artificial intelligence (AI) model configuration message from the first base station (520). The AI ​​information message may include a message requesting the terminal (510) to report based on an AI / ML (machine learning) model. According to one embodiment, the AI ​​information message may include a message requesting the base station (520) to report a prediction result based on the AI / ML model to the terminal (510). According to another embodiment, the AI ​​information message may include a message requesting the base station (520) to perform a prediction on an RLF based on the AI / ML model and report the result to the terminal (510). The AI ​​information message may include information on the criteria for the terminal (510) to declare a wireless link failure, information on the AI / ML model required to predict the wireless link failure, input information for the AI / ML model, etc., and may include configuration information for the terminal (510) to report the wireless link failure prediction result to the first base station (520). For example, information on the reporting conditions, reporting cycle, and number of reports for the wireless link failure prediction result may be included in the AI ​​information message.

[0099] In one embodiment, the AI ​​information message may include a radio link failure prediction instruction for the second base station (530). Accordingly, the terminal (510) may generate radio link failure prediction information for the second base station (530) based on the radio link failure prediction instruction for the second base station (530). The AI ​​information message may include information about an AI / ML model for the terminal to perform radio link failure prediction for the second base station (530), input information about the AI / ML model, radio link failure type information (e.g., cause value), etc. The second base station (530) may correspond to a neighboring cell or a candidate cell for handover.

[0100] In one embodiment, the AI ​​information message may include a Physical Cell ID (PCI) or an Absolute Radio Frequency Channel Number (ARFCN), which may indicate the cell(s) where radio link failure prediction is to be performed. Furthermore, the AI ​​information message may include configuration information for the terminal to perform radio link failure prediction for the cell indicating radio link failure prediction.

[0101] In one embodiment, the terminal (510) can identify parameters for predicting wireless link failure by type of wireless link failure through a SIB (System information block) received from the second base station (530) (e.g., T310 timer, N311 / N310, default MAC, L2 parameters for inputting into an AI / ML model), and perform wireless link failure prediction for the second base station (530) (or, may be referred to as a neighboring cell, a candidate cell, etc.) based on the identified parameters.

[0102] In one embodiment, the configuration information for the terminal (510) to perform wireless link failure prediction and reporting may be included in an RRC reset message by operation 534 or may be included in an artificial intelligence information message by operation 538 and transmitted from the first base station (520) to the terminal (510).

[0103] In one embodiment, the AI ​​information message may include type information (e.g., cause value) for a radio link failure. The type information for the radio link failure may include type information differentiated according to the cause of the radio link failure. For example, the type information may be differentiated based on the cause of the radio link failure, such as a radio link failure related to the expiration of a T310 timer, a radio link failure related to a random access channel (RACH) problem probability, a radio link failure related to the maximum number of uplink retransmissions in the RLC (Radio link control) layer, or a radio link failure related to an uplink Listen before talk (LBT) failure. Accordingly, the terminal (510) may perform a prediction for the type of radio link failure indicated by the type information for the radio link failure received from the first base station (520). If the type information for the radio link failure includes information for the second base station (530), the terminal (510) may generate radio link failure prediction information for each type of radio link failure for the second base station (530).

[0104] In one embodiment, the AI ​​information message may include input information for an AI / ML model for each wireless link failure type. The input information for the AI / ML model for each wireless link failure type may indicate information that the terminal must input into the AI / ML model to generate wireless link failure prediction information for each wireless link failure type.

[0105] In one embodiment, the type information for a wireless link failure may correspond to AI / ML model information for predicting the wireless link failure. For example, an AI / ML model may exist for predicting a wireless link failure associated with the expiration of a T310 timer. Accordingly, the terminal (510) may receive AI / ML model information (e.g., an AI / ML model identifier) ​​for predicting a specific type of wireless link failure from the first base station (520), and the terminal (510) may generate prediction information for the corresponding type of wireless link failure using the AI / ML model indicated by the received AI / ML model information.

[0106] In one embodiment, the terminal (510) may receive an AI / ML model from the base station (520). Specifically, the terminal (510) may receive the AI / ML model itself, or may receive information necessary for the terminal (510) to configure the AI / ML model from the first base station (520). That is, the first base station (520) may transmit to the terminal (510) at least one AI / ML model for predicting a specific wireless link failure type or information for configuring at least one AI / ML model, and may receive prediction information for a specific wireless link failure type from the terminal (510). Accordingly, the first base station (520) may change the setting information for the terminal (510) based on the prediction information for each wireless link failure type received from the terminal (510).

[0107] In one embodiment, the terminal (410) may receive a separate downlink RRC message or RRC reconfiguration message from the base station (420) that includes an instruction to terminate radio link failure prediction and reporting. The radio link failure prediction and reporting operation of the terminal (410) may be activated or deactivated by Downlink control information (DCI) or Medium Access Control (MAC) Control element (CE) received from the base station. When the terminal (410) receives the instruction to terminate radio link failure prediction and reporting, the terminal (410) may delete previously stored configuration information for radio link failure prediction and reporting. Optionally, when radio link failure prediction and reporting is terminated, the terminal (410) may transmit an instruction to the AI / ML model to stop inference and may stop transmitting input information to the AI / ML model.

[0108] Operation 540 may represent an operation in which the terminal (510) performs wireless link failure prediction and generates wireless link failure prediction information. The terminal (510) may perform wireless link failure prediction and generate prediction information based on information received in operation 534 or operation 536.

[0109] In one embodiment, the terminal (510) can predict a radio link failure for a cause indicated by the type information based on the type information for the received radio link failure. For example, if the radio link failure type information indicates a radio link failure related to the expiration of a T310 timer and a radio link failure related to a random access procedure (e.g., RACH problem probability), the terminal (510) can calculate the probability of a radio link failure related to the expiration of the T310 timer and the probability of a radio link failure related to a random access procedure based on an AI / ML model corresponding to each type information. The AI / ML model corresponding to the radio link failure type information may be stored in the memory of the terminal (510) or received from the base station (520).

[0110] In one embodiment, the terminal (510) may generate radio link failure prediction information for each radio link failure type for the first base station (520) and the second base station (530) based on radio link failure type information for the first base station (520) and the second base station (530).

[0111] Operation 542 may represent an operation in which the terminal (510) transmits the prediction information generated in operation 540 to the first base station (520). The terminal (510) may report the radio link failure prediction information generated in operation 540 to the first base station (520) based on the information received in operations 534 and 538. The radio link failure prediction information may include information on the possibility of occurrence of radio link failure for each radio link failure type. For example, when the first base station (520) transmits first type information, second type information, and third type information to the terminal, the terminal (510) may report to the first base station (520) the possibility of radio link failure for the first type, the possibility of radio link failure for the second type, and the possibility of radio link failure for the third type. In addition, for example, if the first base station (520) transmits the first type information, the second type information, and the third type information about the second base station (530) to the terminal, the terminal (510) can report to the first base station (520) the possibility of a radio link failure for the first type, the possibility of a radio link failure for the second type, and the possibility of a radio link failure for the third type about the second base station (530). The first base station (520) can determine a handover from the serving cell (e.g., spcell) of the terminal (510) to the candidate cell based on the received report contents.

[0112] Operation 544 may represent an operation in which the first base station (520) determines whether to reset related parameters based on the radio link failure prediction report received in operation 542. For example, if the first base station (520) determines that there is a high possibility of a radio link failure for the first type, it may determine whether to transmit changed configuration information to the terminal (510) (serving cell configuration via an RRC reset message) so as to reduce the possibility of a radio link failure for the first type. In other words, the first base station (520) may perform radio resource management based on the radio link failure prediction report received from the terminal (510).

[0113] In one embodiment, the first base station (520) may determine a handover from the serving cell (e.g., spcell) of the terminal (510) to a candidate cell based on the received report.

[0114] In one embodiment, if the first base station (520) determines that there is a high possibility of a radio link failure type due to expiration of the T310 timer, the first base station (520) may adjust the value of the T310 timer or reset the RLM (Radio link monitoring) RS (Reference signal) settings.

[0115] In one embodiment, if the first base station (520) determines that there is a high possibility of a type of radio link failure related to the random access procedure, the first base station (520) may reset settings related to the random access channel (RACH). Specifically, the first base station (520) may reset RACH resources, transmission power, a random access preamble (RA preamble) retransmission timer, etc.

[0116] In one embodiment, when the first base station (520) determines that there is a high possibility of a radio link failure type related to the maximum number of uplink retransmissions (max UL ReTx) in the RLC (Radio link control) layer of the terminal (510), the first base station (520) may reset the RLC-related settings by adjusting the retransmission timer.

[0117] In one embodiment, if the first base station (520) determines that there is a high probability of a type of radio link failure associated with an uplink LBT (Listen before talk) failure, the first base station (520) may change the settings of the terminal (510) by adjusting parameters for the LBT operation.

[0118] In one embodiment, the determination of whether each type of wireless link failure is likely to occur by the first base station (520) may be performed based on a predetermined threshold value or a determination by the first base station (520) itself.

[0119] In one embodiment, when the first base station (520) determines that it is difficult to avoid a radio link failure based on a radio link failure prediction report, the first base station (520) may determine a handover (HO) to cause the terminal (510) to change cells and transmit a handover command to the terminal (510).

[0120] Action 546 may represent an action in which the terminal (510) receives changed setting information from the base station (520) through an RRC reset message.

[0121] Action 548 represents an action in which the terminal (510) transmits an RRC reset completion message to the base station (520).

[0122] FIG. 6 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 6 may represent prediction and reporting operations and termination operations based on an identifier or timer condition for an RRC (Radio Resource Control) reset message.

[0123] The terminal and base station performing the operations described in FIG. 6 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0124] Referring to FIG. 6, transmission and reception operations for predicting radio link failure (RLF) based on a timer and reporting it to a base station by a terminal (UE) (610) are described.

[0125] In operation 632, the terminal (610) may receive an RRC reconfiguration message from the base station (620). The RRC reconfiguration message may include configuration information related to the operation of the terminal (610). For example, the configuration information may include information regarding radio link failure prediction, and the information regarding radio link failure prediction may include various configuration information such as information regarding criteria for declaring radio link failure, information regarding an AI / ML model required for predicting radio link failure, and input information regarding an AI / ML model for predicting radio link failure. In addition, the configuration information included in the RRC reconfiguration message may include configuration information regarding reporting of radio link failure prediction results of the terminal (610). For example, information regarding reporting conditions, reporting cycles, and reporting counts for radio link failure prediction results may be included in the configuration information.

[0126] In one embodiment, the RRC reset message may include an identifier (e.g., transaction identifier; Trid). For example, if the identifier (Trid) of the RRC reset message received by the terminal (610) is 2, the terminal (610) may perform radio link failure prediction based on the configuration information included in the RRC reset message with Trid of 2, and may include the identifier information (e.g., Trid: 2) of the RRC reset message when reporting to the base station (620). Accordingly, the base station (620) may identify which configuration information the prediction information included in the received report is based on, and may determine whether to change the configuration information accordingly.

[0127] In operation 634, the terminal (610) may transmit an RRC reconfiguration complete message to the base station (620). The RRC reconfiguration complete message may indicate that the terminal (610) has received the RRC reconfiguration message and that the configuration information included in the RRC reconfiguration message has been applied.

[0128] In operation 636, the terminal (610) may receive an artificial intelligence (AI) model configuration message from the base station (620). The AI ​​information message may include a message for requesting a report based on an AI / ML (machine learning) model from the terminal (610). According to one embodiment, the AI ​​information message may include a message for requesting the base station (620) to report a prediction result based on the AI / ML model to the terminal (610). According to another embodiment, the AI ​​information message may include a message for the base station (620) to request the terminal (610) to perform a prediction for an RLF based on the AI / ML model and report the result. The AI ​​information message may include information on criteria for the terminal (610) to declare a radio link failure, information on an AI / ML model required to predict the radio link failure, input information for the AI / ML model, etc., and may include configuration information for the terminal (610) to report a radio link failure prediction result to the base station (620). For example, information about reporting conditions, reporting cycle, and number of reports for wireless link failure prediction results may be included in the configuration information.

[0129] In one embodiment, the AI ​​information message may include timer information for the terminal (610) to perform radio link failure prediction and reporting. The timer may be started when the terminal (610) receives the AI ​​information message. The terminal (610) may perform radio link failure prediction from the start until the timer expires, and may report the predicted result to the base station (620). When the base station (620) determines to change the configuration information based on the report of the terminal (610) and transmits the changed configuration information to the terminal (610) as an RRC reconfiguration message, the terminal (610) may perform radio link failure prediction based on the changed configuration information, and report the prediction result based on the changed configuration information to the base station (620). That is, the radio link failure prediction and reporting operation of the terminal (610) may be repeatedly performed while the timer is running.

[0130] In one embodiment, the configuration information for the terminal (610) to perform wireless link failure prediction and reporting may be included in an RRC reset message by operation 632 or may be included in an artificial intelligence information message by operation 636 and transmitted from the base station (620) to the terminal (610).

[0131] In one embodiment, the AI ​​information message may include type information (e.g., cause value) for a radio link failure. The type information for the radio link failure may include type information that is differentiated according to the cause of the radio link failure. For example, the type information may be differentiated based on the cause of the radio link failure, such as a radio link failure related to the expiration of a T310 timer, a radio link failure related to a random access channel (RACH) problem probability, a radio link failure related to the maximum number of uplink retransmissions in the RLC (Radio link control) layer, or a radio link failure related to an uplink Listen before talk (LBT) failure. Accordingly, the terminal (610) may perform a prediction for the type of radio link failure indicated by the type information for the radio link failure received from the base station (620).

[0132] In one embodiment, the AI ​​information message may include input information for an AI / ML model for each wireless link failure type. The input information for the AI / ML model for each wireless link failure type may indicate information that the terminal must input into the AI / ML model to generate wireless link failure prediction information for each wireless link failure type.

[0133] In one embodiment, the type information for a wireless link failure may correspond to AI / ML model information for predicting the wireless link failure. For example, an AI / ML model may exist for predicting a wireless link failure associated with the expiration of a T310 timer. Accordingly, the terminal (610) may receive AI / ML model information (e.g., an AI / ML model identifier) ​​for predicting a specific type of wireless link failure from the base station (620), and the terminal (610) may generate prediction information for the corresponding type of wireless link failure using the AI / ML model indicated by the received AI / ML model information.

[0134] In one embodiment, the terminal (610) may receive an AI / ML model from the base station (620). Specifically, the terminal (610) may receive the AI / ML model itself, or may receive information necessary for the terminal (610) to configure the AI / ML model from the base station (620). That is, the base station (620) may transmit to the terminal (610) at least one AI / ML model for predicting a specific wireless link failure type or information for configuring at least one AI / ML model, and may receive prediction information for a specific wireless link failure type from the terminal (610). Accordingly, the base station (620) may change the setting information for the terminal (610) based on the prediction information for each wireless link failure type received from the terminal (610).

[0135] In one embodiment, the terminal (410) may receive a separate downlink RRC message or RRC reconfiguration message from the base station (420) that includes an instruction to terminate radio link failure prediction and reporting. The radio link failure prediction and reporting operation of the terminal (410) may be activated or deactivated by Downlink control information (DCI) or Medium Access Control (MAC) Control element (CE) received from the base station. When the terminal (410) receives the instruction to terminate radio link failure prediction and reporting, the terminal (410) may delete previously stored configuration information for radio link failure prediction and reporting. Optionally, when radio link failure prediction and reporting is terminated, the terminal (410) may transmit an instruction to the AI / ML model to stop inference and may stop transmitting input information to the AI / ML model.

[0136] Operation 638 may represent an operation in which the terminal (610) performs radio link failure prediction and generates radio link failure prediction information. The terminal (610) may perform radio link failure prediction and generate prediction information based on information received in operation 632 or operation 636. If the terminal (610) receives an RRC reconfiguration message with a Trid of 2 in operation 632, the terminal (610) may generate radio link failure prediction information based on configuration information included in the RRC reconfiguration message with a Trid of 2 in operation 638.

[0137] In one embodiment, when the terminal (610) receives configuration information through an artificial intelligence information message, the terminal (610) may perform radio link failure prediction based on the configuration information received through the artificial intelligence information message and report the result to the base station (620). At this time, the prediction result report message transmitted by the terminal (610) may include information indicating that the terminal (610) performed prediction based on the configuration information indicated through the artificial intelligence information message. That is, the prediction result report message may include information indicating which configuration information the terminal (610) applied (e.g., identifier information of an RRC reconfiguration message).

[0138] In one embodiment, the terminal (610) can predict a radio link failure for a cause indicated by the type information based on the type information for the received radio link failure. For example, if the radio link failure type information indicates a radio link failure related to the expiration of a T310 timer and a radio link failure related to a random access procedure (e.g., RACH problem probability), the terminal (610) can calculate the probability of a radio link failure related to the expiration of the T310 timer and the probability of a radio link failure related to a random access procedure based on an AI / ML model corresponding to each type information. The AI / ML model corresponding to the radio link failure type information may be stored in the memory of the terminal (610) or received from the base station (620).

[0139] Operation 640 may represent an operation in which the terminal (610) transmits the prediction information generated in operation 638 to the base station (620). The terminal (610) may report the radio link failure prediction information generated in operation 638 to the base station (620) based on the information received in operations 632 and 636. The radio link failure prediction information may include information on the possibility of occurrence of radio link failure for each radio link failure type. For example, if the base station (620) transmits first type information, second type information, and third type information to the terminal, the terminal (610) may report to the base station (620) the possibility of radio link failure for the first type, the possibility of radio link failure for the second type, and the possibility of radio link failure for the third type.

[0140] In one embodiment, the radio link failure prediction report may include identifier information of an RRC reconfiguration message including configuration information on which the radio link failure prediction result of the terminal (610) is based. Accordingly, the base station (620) receiving the report may identify which RRC reconfiguration message the terminal used to perform the radio link failure prediction based on the configuration information included in the report. The radio link failure prediction report may include the generation time of the radio link failure prediction result, the time at which the terminal received the RRC reconfiguration message including the configuration information on which the generated prediction result is based, or time index information included in the RRC reconfiguration message received by the terminal.

[0141] Operation 642 may represent an operation in which the base station (620) determines whether to reset related parameters based on the radio link failure prediction report received in operation 640. For example, if the base station (620) determines that there is a high possibility of a radio link failure for the first type, it may determine whether to transmit changed configuration information to the terminal (610) (serving cell configuration via an RRC reset message) so as to reduce the possibility of a radio link failure for the first type. In other words, the base station (620) may perform radio resource management based on the radio link failure prediction report received from the terminal (610).

[0142] In one embodiment, if the base station (620) determines that there is a high probability of a radio link failure type due to expiration of the T310 timer, the base station (620) may adjust the value of the T310 timer or reset the RLM (Radio link monitoring) RS (Reference signal) settings.

[0143] In one embodiment, if the base station (620) determines that there is a high possibility of a type of radio link failure related to the random access procedure, the base station (620) may reset settings related to the random access channel (RACH). Specifically, the base station (620) may reset RACH resources, transmission power, a random access preamble (RA preamble) retransmission timer, etc.

[0144] In one embodiment, when the base station (620) determines that there is a high possibility of a radio link failure type related to the maximum number of uplink retransmissions (max UL ReTx) in the RLC (Radio link control) layer of the terminal (610), the base station (620) may reset the RLC-related settings by adjusting the retransmission timer.

[0145] In one embodiment, if the base station (620) determines that there is a high probability of a type of radio link failure associated with an uplink LBT (Listen before talk) failure, the base station (620) may change the settings of the terminal (610) by adjusting parameters for the LBT operation.

[0146] In one embodiment, the determination of whether each type of wireless link failure is likely by the base station (620) may be performed based on a predetermined threshold value or a determination by the base station (620) itself.

[0147] In one embodiment, when the base station (620) determines that it is difficult to avoid a radio link failure based on a radio link failure prediction report, the base station (620) may determine a handover (HO) to cause the terminal (610) to change cells and transmit a handover command to the terminal (610).

[0148] Operation 644 may represent an operation in which the terminal (610) receives changed configuration information from the base station (620) through an RRC reset message. At this time, the identifier information (e.g., Trid:3) of the RRC reset message received by the terminal (610) may be different from the identifier information (e.g., Trid:2) of the RRC reset message received by the terminal (610) in the aforementioned operation 632.

[0149] Action 646 represents an action in which the terminal (610) transmits an RRC reset completion message to the base station (620).

[0150] In operation 648, the terminal (610) can perform radio link failure prediction based on the configuration information included in the RRC reset message with Trid equal to 3.

[0151] In operation 650, the terminal (610) may report the radio link failure prediction information generated by operation 648 to the base station (620). At this time, the report may include identifier information of an RRC reset message that transmitted configuration information used by the terminal (610) to generate the radio link failure prediction information.

[0152] In operation 652, the terminal (610) may terminate the wireless link failure prediction and reporting operation when the timer expires.

[0153] Figure 7 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. Specifically, the embodiment of Figure 7 can indicate conditions under which the terminal's prediction and reporting operations are terminated. For example, the terminal may terminate the prediction and reporting operations when a wireless link failure occurs.

[0154] The terminal and base station performing the operations described in FIG. 7 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0155] Referring to FIG. 7, transmission and reception operations for predicting radio link failure (RLF) and reporting it to a base station by a terminal (UE) (710) based on an artificial intelligence model (deep learning model or machine learning model) are described.

[0156] In operation 732, the terminal (710) may receive an RRC reconfiguration message from the base station (720). The RRC reconfiguration message may include configuration information related to the operation of the terminal (710). For example, the configuration information may include information regarding radio link failure prediction, and the information regarding radio link failure prediction may include various configuration information such as information regarding criteria for declaring radio link failure, information regarding an AI / ML model required for predicting radio link failure, and input information regarding an AI / ML model for predicting radio link failure. In addition, the configuration information included in the RRC reconfiguration message may include configuration information regarding reporting of radio link failure prediction results of the terminal (710). For example, information regarding reporting conditions, reporting cycles, and reporting counts for radio link failure prediction results may be included in the configuration information.

[0157] In operation 734, the terminal (710) may transmit an RRC reconfiguration complete message to the base station (720). The RRC reconfiguration complete message may indicate that the terminal (710) has received the RRC reconfiguration message and that the configuration information included in the RRC reconfiguration message has been applied.

[0158] In operation 736, the terminal (710) may receive an artificial intelligence (AI) model configuration message from the base station (720). The AI ​​information message may include a message for requesting a report based on an AI / ML (machine learning) model from the terminal (710). According to one embodiment, the AI ​​information message may include a message for requesting the base station (720) to report a prediction result based on the AI / ML model to the terminal (710). According to another embodiment, the AI ​​information message may include a message for the base station (720) to request the terminal (710) to perform a prediction on an RLF based on the AI / ML model and report the result. The AI ​​information message may include information on a criterion for the terminal (710) to declare a radio link failure, information on an AI / ML model required to predict the radio link failure, input information for the AI / ML model, etc., and may include configuration information for the terminal (710) to report a radio link failure prediction result to the base station (720). For example, information about reporting conditions, reporting cycle, and number of reports for wireless link failure prediction results may be included in the configuration information.

[0159] In one embodiment, the RRC reconfiguration message or the AI ​​information message may include information regarding conditions under which the terminal must terminate radio link failure prediction and reporting (termination conditions). Termination conditions may include conditions under which the terminal receives a handover command, conditions under which the terminal receives an RRC release message, conditions under which a radio link failure occurs, conditions based on the signal strength of the serving cell (Reference signal received power, Reference signal received quality; RSRP, RSRQ, etc.), and / or event conditions related to measurement report configuration. In this case, the condition based on the signal strength of the serving cell may be a condition under which the terminal terminates radio link failure prediction and reporting when the signal strength of the serving cell is above or below a threshold value. The aforementioned termination conditions may be embodied as actions of the terminal without explicit conditions.

[0160] In one embodiment, the RRC reset message or AI information message may include information regarding the terminal's radio link failure reporting conditions. The reporting conditions may be configured to allow the terminal to transmit representative information from among the prediction information generated over a certain period to the base station. For example, the terminal may repeatedly transmit the most recently generated prediction information from among the prediction information generated over a certain period as the representative value to the base station at each period. In addition, the reporting conditions may be configured to allow the terminal to report to the base station when the probability of a radio link failure exceeds a predetermined threshold based on the prediction information generated by the terminal. For example, if the threshold is 80%, the terminal may not report if the probability of a radio link failure is calculated to be 75%, and may be configured to report if the probability of a radio link failure is 90%.

[0161] In one embodiment, the terminal (710) may be configured to perform radio link failure prediction and reporting at least once each time the terminal (710) receives a prediction request from the base station (720). For example, the terminal (710) may be configured to receive a prediction request and repeatedly perform radio link failure prediction and reporting operations three times. Furthermore, the number of repetitions of the prediction operation and the number of repetitions of the reporting operation may be set differently. For example, the terminal may report the prediction result to the base station once after performing two prediction operations.

[0162] In one embodiment, the wireless link failure reporting of the terminal (710) may be performed based on the predicted probability of wireless link failure. For example, the terminal (710) may be configured to perform a wireless link failure reporting when the probability of wireless link failure is 80% or greater.

[0163] In one embodiment, the configuration information for the terminal (710) to perform wireless link failure prediction and reporting may be included in an RRC reset message by operation 732 or may be included in an artificial intelligence information message by operation 736 and transmitted from the base station (720) to the terminal (710). The configuration information for the terminal (710) to perform wireless link failure prediction and reporting may also be indicated in a new Downlink RRC message.

[0164] In one embodiment, the AI ​​information message may include type information (e.g., cause value) for a radio link failure. The type information for the radio link failure may include type information differentiated according to the cause of the radio link failure. For example, the type information may be differentiated based on the cause of the radio link failure, such as a radio link failure related to the expiration of a T310 timer, a radio link failure related to a random access procedure (e.g., RACH problem probability), a radio link failure related to the maximum number of uplink retransmissions in the RLC (Radio Link Control) layer, or a radio link failure related to an uplink LBT (Listen Before Talk) failure. Accordingly, the terminal (710) may perform a prediction for the type of radio link failure indicated by the type information for the radio link failure received from the base station (720).

[0165] In one embodiment, the AI ​​information message may include input information for an AI / ML model for each wireless link failure type. The input information for the AI / ML model for each wireless link failure type may indicate information that the terminal must input into the AI / ML model to generate wireless link failure prediction information for each wireless link failure type.

[0166] In one embodiment, the type information for a wireless link failure may correspond to AI / ML model information for predicting the wireless link failure. For example, an AI / ML model may exist for predicting a wireless link failure associated with the expiration of a T310 timer. Accordingly, the terminal (710) may receive AI / ML model information (e.g., an AI / ML model identifier) ​​for predicting a specific type of wireless link failure from the base station (720), and the terminal (710) may generate prediction information for the corresponding type of wireless link failure using the AI / ML model indicated by the received AI / ML model information.

[0167] In one embodiment, the terminal (710) may receive an AI / ML model from the base station (720). Specifically, the terminal (710) may receive the AI / ML model itself, or may receive information from the base station (720) necessary for the terminal (710) to configure the AI / ML model. That is, the base station (720) may transmit to the terminal (710) at least one AI / ML model for predicting a specific wireless link failure type or information for configuring at least one AI / ML model, and may receive prediction information for a specific wireless link failure type from the terminal (710). Accordingly, the base station (720) may change the setting information for the terminal (710) based on the prediction information for each wireless link failure type received from the terminal (710).

[0168] Operation 738 may represent an operation in which the terminal (710) performs wireless link failure prediction and generates wireless link failure prediction information. The terminal (710) may perform wireless link failure prediction and generate prediction information based on information received in operation 732 or operation 736.

[0169] In one embodiment, the terminal (710) can predict a radio link failure for a cause indicated by the type information based on the type information for the received radio link failure. For example, if the radio link failure type information indicates a radio link failure related to the expiration of a T310 timer and a radio link failure related to a random access procedure (e.g., RACH problem probability), the terminal (710) can calculate the probability of a radio link failure related to the expiration of the T310 timer and the probability of a radio link failure related to a random access procedure based on an AI / ML model corresponding to each type information. The AI / ML model corresponding to the radio link failure type information may be stored in the memory of the terminal (710) or received from the base station (720).

[0170] In one embodiment, the terminal (710) may receive a separate downlink RRC message or RRC reconfiguration message from the base station (720) that includes an instruction to terminate radio link failure prediction and reporting. The radio link failure prediction and reporting operation of the terminal (710) may be activated or deactivated by Downlink control information (DCI) or Medium Access Control (MAC) Control element (CE) received from the base station. When the terminal (710) receives the instruction to terminate radio link failure prediction and reporting, the terminal (710) may delete previously stored configuration information for radio link failure prediction and reporting. Optionally, when radio link failure prediction and reporting is terminated, the terminal (710) may transmit an instruction to the AI / ML model to stop inference and may stop transmitting input information to the AI / ML model.

[0171] Operation 740 may represent an operation in which the terminal (710) transmits the prediction information generated in operation 738 to the base station (720). The terminal (710) may report the radio link failure prediction information generated in operation 738 to the base station (720) based on the information received in operations 732 and 736. The radio link failure prediction information may include information on the possibility of occurrence of radio link failure for each radio link failure type. For example, if the base station (720) transmits first type information, second type information, and third type information to the terminal, the terminal (710) may report to the base station (720) the possibility of radio link failure for the first type, the possibility of radio link failure for the second type, and the possibility of radio link failure for the third type.

[0172] Operation 742 may represent an operation in which the base station (720) determines whether to reset related parameters based on the radio link failure prediction report received in operation 740. For example, if the base station (720) determines that there is a high possibility of a radio link failure for the first type, it may determine whether to transmit changed configuration information to the terminal (710) (serving cell configuration via an RRC reset message) so as to reduce the possibility of a radio link failure for the first type. In other words, the base station (720) may perform radio resource management based on the radio link failure prediction report received from the terminal (710).

[0173] In one embodiment, if the base station (720) determines that there is a high probability of a radio link failure type due to expiration of the T310 timer, the base station (720) may adjust the value of the T310 timer or reset the Radio link monitoring (RLM) Reference signal (RS) settings.

[0174] In one embodiment, if the base station (720) determines that there is a high possibility of a type of radio link failure related to the random access procedure, the base station (720) may reset settings related to the random access channel (RACH). Specifically, the base station (720) may reset RACH resources, transmission power, random access preamble (RA preamble) retransmission timer, etc.

[0175] In one embodiment, when the base station (720) determines that there is a high possibility of a radio link failure type related to the maximum number of uplink retransmissions (max UL ReTx) in the RLC (Radio link control) layer of the terminal (710), the base station (720) may reset the RLC-related settings by adjusting the retransmission timer.

[0176] In one embodiment, if the base station (720) determines that there is a high probability of a type of radio link failure associated with an uplink LBT (Listen before talk) failure, the base station (720) may change the settings of the terminal (710) by adjusting parameters for the LBT operation.

[0177] In one embodiment, the determination of whether each type of wireless link failure is likely by the base station (720) may be performed based on a predetermined threshold value or a determination by the base station (720) itself.

[0178] In one embodiment, when the base station (720) determines that it is difficult to avoid a radio link failure based on a radio link failure prediction report, the base station (720) may determine a handover (HO) to cause the terminal (710) to change cells and transmit a handover command to the terminal (710).

[0179] Action 744 may represent an action in which the terminal (710) receives changed setting information from the base station (720) through an RRC reset message.

[0180] Action 746 represents an action in which the terminal (710) transmits an RRC reset completion message to the base station (720).

[0181] In operation 748, the terminal (710) can perform radio link failure prediction based on the configuration information included in the RRC reset message received in operation 744.

[0182] In operation 750, the terminal (710) may report the radio link failure prediction information generated by operation 748 to the base station (720). At this time, the report may include identifier information of an RRC reset message that transmitted configuration information used by the terminal (710) to generate the radio link failure prediction information.

[0183] Action 752 may represent an action by which the terminal (710) identifies that a termination condition for a wireless link prediction and reporting operation is satisfied.

[0184] Action 754 indicates that the terminal (710) terminates the wireless link failure prediction and reporting operation upon satisfaction of the termination condition.

[0185] Figure 8 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. Specifically, the embodiment of Figure 8 can indicate conditions under which the terminal's prediction and reporting operations are terminated. For example, the terminal may terminate the prediction and reporting operations upon receiving a handover command from the base station.

[0186] The description of the operations illustrated in FIG. 8 corresponds to the operations described in FIG. 7. In addition, in operation 752 of FIG. 7, the operation in which the terminal identifies satisfaction of the wireless link failure prediction and reporting termination condition may correspond to the operation in which the terminal (810) receives a handover command from the base station (820) in FIG. 8. That is, the embodiment illustrated in FIG. 8 may indicate that the terminal (810) terminates the prediction and reporting operation when one of the termination conditions, reception of the handover command, is satisfied.

[0187] In operation 852, the terminal (810) can receive a handover command from the base station (820).

[0188] Action 854 represents an action by which the terminal (810) terminates radio link failure prediction and reporting upon receipt of a handover command.

[0189] Action 856 represents an action in which the terminal (810) transmits an RRC reset completion message to the target base station (830) in relation to the handover procedure upon receipt of a handover command.

[0190] FIG. 9 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 9 can be used to illustrate an embodiment in which wireless link failure prediction by a terminal is performed based on whether a performance condition is satisfied.

[0191] In one embodiment, the terminal may perform wireless link failure prediction and reporting using an AI / ML model when the likelihood of a wireless link failure occurrence increases based on parameter values ​​associated with the occurrence of a wireless link failure.

[0192] In operation 932, the terminal (910) may receive an RRC reconfiguration message from the base station (920). The RRC reconfiguration message may include configuration information related to the operation of the terminal (910). For example, the configuration information may include information regarding radio link failure prediction, and the information regarding radio link failure prediction may include various configuration information such as information regarding criteria for declaring radio link failure, information regarding an AI / ML model required for predicting radio link failure, and input information regarding an AI / ML model for predicting radio link failure. In addition, the configuration information included in the RRC reconfiguration message may include configuration information regarding reporting of radio link failure prediction results of the terminal (910). For example, information regarding reporting conditions, reporting cycles, and reporting counts for radio link failure prediction results may be included in the configuration information. In addition, condition information for performing radio link failure prediction may be included in the configuration information.

[0193] In operation 934, the terminal (910) may transmit an RRC reconfiguration complete message to the base station (920). The RRC reconfiguration complete message may indicate that the terminal (910) has received the RRC reconfiguration message and that the configuration information included in the RRC reconfiguration message has been applied.

[0194] In operation 936, the terminal (910) may receive an artificial intelligence (AI) model configuration message from the base station (920). The AI ​​information message may include a message for requesting a report based on an AI / ML (machine learning) model from the terminal (910). According to one embodiment, the AI ​​information message may include a message for requesting the base station (920) to report a prediction result based on the AI / ML model to the terminal (910). According to another embodiment, the AI ​​information message may include a message for the base station (920) to request the terminal (910) to perform a prediction for an RLF based on the AI / ML model and report the result. The AI ​​information message may include information on criteria for the terminal (910) to declare a radio link failure, information on an AI / ML model required to predict the radio link failure, input information for the AI / ML model, etc., and may include configuration information for the terminal (910) to report a radio link failure prediction result to the base station (920). For example, information regarding reporting conditions, reporting cycles, and reporting counts for wireless link failure prediction results may be included in the configuration information. In addition, information regarding conditions for performing wireless link failure prediction may be included in the configuration information.

[0195] In one embodiment, the AI ​​information message may include performance condition information for the terminal (910) to perform wireless link failure prediction. For example, the condition for the terminal (910) to perform wireless link failure prediction may be based on a threshold value of the Reference Signal Received Power (RSRP) or the Reference Signal Received Quality (RSRQ) of the RLM-RS. Specifically, the performance condition information may include a condition for performing wireless link failure prediction when the RSRP or RSRQ is below a specific threshold value.

[0196] In one embodiment, the performance condition information may include a condition based on the Block Error Rate (BLER) of a Physical Downlink Control Channel (PDCCH). For example, the performance condition information may include a condition under which radio link failure prediction is performed when the BLER of the PDCCH exceeds or falls below a specific threshold.

[0197] In one embodiment, the performance condition information may include a condition based on the signal strength of the serving cell. For example, the performance condition information may include a condition under which the terminal (910) performs radio link failure prediction when the signal strength of the serving cell exceeds or falls below a certain threshold value.

[0198] In one embodiment, the performance condition information may include a condition that the terminal (910) performs radio link failure prediction when a specific number of consecutive out of sync signals are received at the physical layer of the terminal (910).

[0199] In one embodiment, the performance condition information may include a condition under which the terminal (910) performs radio link failure prediction when the T310 timer starts.

[0200] In one embodiment, the performance condition information may include a condition for the terminal (910) to perform radio link failure prediction when the number of uplink retransmissions of the RLC (Radio link control) layer of the terminal (910) reaches a specific number.

[0201] In one embodiment, the performance condition information may include a condition for the terminal (910) to perform radio link failure prediction when the number of transmissions of a random access preamble attempted by the terminal (910) in an RRC connection state reaches a specific number.

[0202] In one embodiment, the terminal (910) may perform wireless link failure prediction when a performance condition is satisfied, report the result to the base station (920), and may not perform any further prediction operations thereafter.

[0203] In one embodiment, the configuration information for the terminal (910) to perform wireless link failure prediction and reporting may be included in an RRC reset message by operation 932 or may be included in an artificial intelligence information message by operation 936 and transmitted from the base station (920) to the terminal (910).

[0204] In one embodiment, the AI ​​information message may include type information (e.g., cause value) for a radio link failure. The type information for the radio link failure may include type information differentiated according to the cause of the radio link failure. For example, the type information may be differentiated based on the cause of the radio link failure, such as a radio link failure related to the expiration of a T310 timer, a radio link failure related to a random access procedure (e.g., RACH problem probability), a radio link failure related to the maximum number of uplink retransmissions in the RLC (Radio Link Control) layer, or a radio link failure related to an uplink LBT (Listen Before Talk) failure. Accordingly, the terminal (910) may perform a prediction for the type of radio link failure indicated by the type information for the radio link failure received from the base station (920).

[0205] In one embodiment, the AI ​​information message may include input information for an AI / ML model for each wireless link failure type. The input information for the AI / ML model for each wireless link failure type may indicate information that the terminal must input into the AI / ML model to generate wireless link failure prediction information for each wireless link failure type.

[0206] In one embodiment, the type information for a wireless link failure may correspond to AI / ML model information for predicting the wireless link failure. For example, an AI / ML model may exist for predicting a wireless link failure associated with the expiration of a T310 timer. Accordingly, the terminal (910) may receive AI / ML model information (e.g., an AI / ML model identifier) ​​for predicting a specific type of wireless link failure from the base station (920), and the terminal (910) may generate prediction information for the corresponding type of wireless link failure using the AI / ML model indicated by the received AI / ML model information.

[0207] In one embodiment, the terminal (910) may receive an AI / ML model from the base station (920). Specifically, the terminal (910) may receive the AI / ML model itself, or may receive information from the base station (920) necessary for the terminal (910) to configure the AI / ML model. That is, the base station (920) may transmit to the terminal (910) at least one AI / ML model for predicting a specific wireless link failure type or information for configuring at least one AI / ML model, and may receive prediction information for a specific wireless link failure type from the terminal (910). Accordingly, the base station (920) may change the setting information for the terminal (910) based on the prediction information for each wireless link failure type received from the terminal (910).

[0208] In one embodiment, the terminal (910) may receive a separate downlink RRC message or RRC reconfiguration message from the base station (920) that includes an instruction to terminate radio link failure prediction and reporting. The radio link failure prediction and reporting operation of the terminal (910) may be activated or deactivated by Downlink control information (DCI) or Medium Access Control (MAC) Control element (CE) received from the base station. When the terminal (910) receives the instruction to terminate radio link failure prediction and reporting, the terminal (910) may delete previously stored configuration information for radio link failure prediction and reporting. Optionally, when radio link failure prediction and reporting is terminated, the terminal (910) may transmit an instruction to the AI / ML model to stop inference and may stop transmitting input information to the AI / ML model.

[0209] Operation 938 indicates that the terminal (910) determines whether the conditions for performing radio link failure prediction set in operation 932 or operation 936 are satisfied and determines that the conditions are not satisfied. Accordingly, the terminal (910) does not perform radio link failure prediction. Operation 940 indicates that the terminal (910) does not report to the base station (920) because it did not perform radio link failure prediction.

[0210] Operation 942 indicates that the terminal (910) determines whether the wireless link failure prediction performance condition set in operation 932 or operation 936 is satisfied and identifies that the condition is satisfied. Accordingly, the terminal (910) can perform wireless link failure prediction.

[0211] In one embodiment, the terminal (910) can predict the radio link failure for the cause indicated by the type information based on the type information for the received radio link failure. For example, if the radio link failure type information indicates a radio link failure related to the expiration of a T310 timer and a radio link failure related to a random access procedure (e.g., RACH problem probability), the terminal (910) can calculate the probability of the radio link failure related to the expiration of the T310 timer and the probability of the radio link failure related to the random access procedure based on an AI / ML model corresponding to each type information. The AI / ML model corresponding to the radio link failure type information may be stored in the memory of the terminal (910) or may be received from the base station (920).

[0212] Operation 944 represents an operation in which the terminal (910) performs radio link failure prediction and transmits the generated prediction information to the base station (920). The terminal (910) may report the radio link failure prediction information generated based on the information received in operations 932 and 936 to the base station (920). The radio link failure prediction information may include information on the possibility of occurrence of radio link failure for each radio link failure type. For example, if the base station (920) transmits first type information, second type information, and third type information to the terminal, the terminal (910) may report to the base station (920) the possibility of radio link failure for the first type, the possibility of radio link failure for the second type, and the possibility of radio link failure for the third type.

[0213] In one embodiment, the terminal (910) may perform wireless link failure prediction based on wireless link failure prediction performance conditions and reporting conditions and report the prediction results to the base station (920). The terminal (910) may perform prediction when the prediction performance conditions are satisfied, and transmit the prediction results to the base station when the reporting conditions are satisfied.

[0214] Operation 946 indicates that the terminal (910) repeatedly performs wireless link failure prediction and reporting operations. Depending on the contents of the configuration information set for the terminal (910), the terminal (910) may report the wireless link failure prediction result once and stop prediction, or may perform prediction and reporting repeatedly.

[0215] FIG. 10 illustrates the operation of a terminal for a wireless link failure prediction method according to embodiments of the present disclosure.

[0216] The terminal performing the operation described in Fig. 10 can correspond to the terminal of Fig. 2.

[0217] Referring to FIG. 10, in operation 1010, a terminal may receive an artificial intelligence (AI) information message from a base station for a serving cell. The AI ​​information message may include an instruction requesting a report of a radio link failure prediction based on an AI / ML model. In addition, the AI ​​information message may include configuration information for the terminal to perform radio link failure prediction and reporting operations. For example, the configuration information may include information on the type of radio link failure requesting a prediction, prediction execution conditions, reporting execution conditions, information on an AI model (AI / ML model) for radio link failure prediction, input information for the AI ​​model (AI / ML model), etc.

[0218] In one embodiment, the conditions for performing radio link failure prediction of the terminal may include at least one of a threshold condition for the strength of a reference signal of a serving cell, a threshold condition for a block error rate (BLER) of a physical downlink control channel (PDCCH), a condition for the number of times out of sync is received from a physical layer, a start condition of a T310 timer, a condition for the number of uplink retransmissions of a radio link control (RLC) layer, or a condition for the number of preamble transmissions for random access.

[0219] In one embodiment, the wireless link failure reporting condition of the terminal may include at least one of threshold information regarding the probability of occurrence of a wireless link failure, information regarding the number of reports, or information regarding the reporting cycle.

[0220] In one embodiment, the configuration information may further include condition information for the predicted termination. The condition information for the predicted termination may include at least one of: reception of a handover command message, reception of a radio resource control (RRC) release message, occurrence of a radio link failure, or a threshold value for the signal strength of the serving cell.

[0221] In one embodiment, the AI ​​information message may further include information about a candidate cell associated with the conditional handover of the terminal.

[0222] In one embodiment, the terminal may receive the aforementioned configuration information via an RRC reset message.

[0223] In operation 1020, the terminal may generate wireless link failure prediction information based on an artificial intelligence model (AI / ML model) based on an artificial intelligence information message. The wireless link failure prediction information may include information on the probability of wireless link failure occurrence based on the wireless link failure type (e.g., cause value) according to the contents of the configuration information.

[0224] In one embodiment, operation 1020 may be performed when a performance condition included in the setup information is satisfied.

[0225] In one embodiment, when a terminal receives a radio link failure prediction request for a candidate cell related to a conditional handover, the radio link failure prediction information may include radio link failure occurrence probability information for a radio link failure type for the candidate cell.

[0226] In operation 1030, the terminal may transmit a radio link failure prediction report message including the generated prediction information to the base station.

[0227] In one embodiment, operation 1030 may be performed when a reporting condition included in the setup information is satisfied.

[0228] FIG. 11 illustrates an operation flowchart of a base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0229] A base station performing the operation described in FIG. 11 may correspond to a network entity of FIG. 3.

[0230] A method performed by a base station in a wireless communication system may be composed of operations of the base station corresponding to operations of the terminal described above.

[0231] Referring to FIG. 11, in operation 1110, a base station may transmit an artificial intelligence (AI) information message to a terminal. The AI ​​information message may include a wireless link failure prediction request instruction. Additionally, the AI ​​information message may include configuration information for the terminal to perform wireless link failure prediction and reporting operations. For example, the configuration information may include information on the type of wireless link failure requesting prediction, prediction execution conditions, reporting execution conditions, information on an artificial intelligence (AI / ML) model for wireless link failure prediction, input information for the artificial intelligence (AI / ML) model, etc.

[0232] In one embodiment, the conditions for performing radio link failure prediction of the terminal may include at least one of a threshold condition for the strength of a reference signal of a serving cell, a threshold condition for a block error rate (BLER) of a physical downlink control channel (PDCCH), a condition for the number of times out of sync is received from a physical layer, a start condition of a T310 timer, a condition for the number of uplink retransmissions of a radio link control (RLC) layer, or a condition for the number of preamble transmissions for random access.

[0233] In one embodiment, the wireless link failure reporting condition of the terminal may include at least one of threshold information regarding the probability of occurrence of a wireless link failure, information regarding the number of reports, or information regarding the reporting cycle.

[0234] In one embodiment, the configuration information may further include condition information for the predicted termination. The condition information for the predicted termination may include at least one of: reception of a handover command message, reception of a radio resource control (RRC) release message, occurrence of a radio link failure, or a threshold value for the signal strength of the serving cell.

[0235] In one embodiment, the AI ​​information message may further include information about a candidate cell associated with the conditional handover of the terminal.

[0236] In one embodiment, the base station may transmit the aforementioned configuration information to the terminal via an RRC reset message.

[0237] In operation 1120, the base station may receive a radio link failure prediction report message from the terminal. The radio link failure prediction report message includes radio link failure prediction information, and the radio link failure prediction information may include information on the probability of occurrence of a radio link failure based on the type of radio link failure according to the contents of the configuration information.

[0238] In one embodiment, when a terminal receives a radio link failure prediction request for a candidate cell related to a conditional handover, the radio link failure prediction information may include radio link failure occurrence probability information for a radio link failure type for the candidate cell.

[0239] In operation 1130, the base station may determine whether to change the relevant parameters based on the radio link failure prediction report message.

[0240] In one embodiment, if the base station determines that there is a high probability of a radio link failure type for expiration of the T310 timer based on the radio link failure prediction report message, the base station (420) may adjust the value of the T310 timer or reset the RLM (Radio link monitoring) RS (Reference signal) setting.

[0241] In one embodiment, if the base station determines that there is a high probability of a type of radio link failure related to the random access procedure based on a radio link failure prediction report message, the base station (420) may reset settings related to a random access channel (RACH). Specifically, the base station (420) may reset RACH resources, transmission power, a random access preamble (RA preamble) retransmission timer, etc.

[0242] In one embodiment, when the base station determines that there is a high possibility of a radio link failure type related to the maximum number of uplink retransmissions (max UL ReTx) in the RLC (Radio link control) layer of the terminal (410) based on the radio link failure prediction report message, the base station (420) may reset the RLC-related settings by adjusting the retransmission timer.

[0243] In one embodiment, if the base station determines that there is a high probability of a radio link failure type related to an uplink LBT (Listen before talk) failure based on a radio link failure prediction report message, the base station may change the settings of the terminal (410) by adjusting parameters for the LBT operation.

[0244] In one embodiment, the determination of whether each type of wireless link failure is likely by the base station may be performed based on a predetermined threshold value or a determination by the base station itself.

[0245] In one embodiment, if the base station determines that it is difficult to avoid a radio link failure based on a radio link failure prediction report, the base station may decide to perform a handover (HO) to cause the terminal to change cells and transmit a handover command to the terminal.

[0246] In operation 1140, the base station may transmit configuration information regarding changed parameters to the terminal. For example, the base station may transmit the changed configuration information to the terminal via an RRC reset message.

[0247] While the operations of the communication method according to the embodiments of the present disclosure have been described separately for each embodiment, the operations included in each embodiment can be combined with operations of other embodiments to form a new embodiment. Accordingly, it can be understood that embodiments in which the embodiments of the present disclosure are combined are also described by the present disclosure.

[0248] A communication method according to embodiments of the present disclosure describes transmission and reception operations and transmitted configuration information with a base station for predicting and reporting wireless link failure using an artificial intelligence model by a terminal.

[0249] According to various embodiments of the present disclosure, a terminal can receive a prediction request for each wireless link failure type from a base station, and accordingly, generate a probability of occurrence of a wireless link failure for each wireless link failure type based on an artificial intelligence model. The base station can receive a report including the generated prediction information from the terminal, and determine whether to change related configuration information for each wireless link failure type based on the received prediction information. In other words, since the base station can determine whether to change detailed configuration information for each wireless link failure type and reset it for the terminal, the possibility of a wireless link failure can be reduced, thereby improving communication quality.

[0250] Additionally, according to various embodiments of the present disclosure, a terminal can receive condition information for predicting and reporting wireless link failures from a base station, and perform prediction or reporting when the conditions are met. Therefore, a series of operations for predicting wireless link failure occurrences and changing settings can be minimized, effectively reducing power consumption.

[0251] The various embodiments of the present disclosure and the terminology used therein are not intended to limit the technical features described in the present disclosure to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more items, unless the relevant context clearly indicates otherwise. In the present disclosure, each of the phrases "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among the phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0252] The term "module" as used herein may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally formed component or a minimum unit or part of a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0253] Various embodiments of the present disclosure may be implemented as software (e.g., a program (140)) including one or more commands stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a device (e.g., a processor (e.g., processor (120) of an electronic device (101)) can call at least one command from among one or more commands stored from a storage medium and execute it. This enables the device to operate to perform at least one function according to the called at least one command. The one or more commands may include code generated by a compiler or code executable by an interpreter. A storage medium readable by the device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (e.g., EM wave), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0254] According to one embodiment, the method according to various embodiments disclosed in the present disclosure may be provided as included in 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., downloaded or uploaded) via an application store (e.g., Play 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 may be temporarily stored or temporarily generated in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0255] According to various embodiments, each component (e.g., a module or a program) of the described components may include one or more entities. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In a method performed by a terminal in a wireless communication system, A step of receiving a first message from a base station requesting a report of a prediction based on an AI (artificial intelligence) / ML model; A step of generating prediction information on radio link failure (RLF) based on an AI / ML model based on the first message; and comprising a step of transmitting a second message to the base station for reporting the prediction information, The first message includes information indicating at least one cause value associated with the wireless link failure, The above prediction information includes a probability of occurrence of a wireless link failure for each of the at least one cause value, method.

2. In claim 1, The first message further includes information about at least one candidate cell for conditional handover, The above prediction information includes a probability that a radio link failure will occur for each of the above cause values ​​for the at least one candidate cell. method.

3. In claim 1, The first message further includes first condition information for predicting the wireless link failure, The above first condition information is, At least one of a threshold value for the strength of a reference signal, a threshold value for a block error rate (BLER) of a physical downlink control channel (PDCCH), a number of times an out of sync signal is received from a physical layer, a start of a T310 timer, a number of uplink retransmissions of a radio link control (RLC) layer, or a number of preamble transmissions for random access. method.

4. In claim 1, The first message further includes at least one of second condition information for reporting the prediction information and third condition information for prediction termination, The above second condition information is, At least one of a threshold value, a number of reports, or a reporting cycle regarding the probability of occurrence of the wireless link failure, The above third condition information is: At least one of reception of a handover command message, reception of a radio resource control (RRC) release message, occurrence of a radio link failure, or a threshold value for the signal strength of a serving cell, method.

5. As a terminal of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: Receive a first message from a base station requesting a report of a prediction based on an AI (artificial intelligence) / ML model, Generate prediction information on radio link failure (RLF) based on the AI / ML model based on the first message, is set to transmit a second message to the base station for reporting the prediction information, The first message includes information indicating at least one cause value associated with the wireless link failure, The above prediction information includes a probability of occurrence of a wireless link failure for each of the at least one cause value, Terminal.

6. In claim 5, The first message further includes information about at least one candidate cell for conditional handover, The above prediction information includes a probability that a radio link failure will occur for each of the above cause values ​​for the at least one candidate cell. Terminal.

7. In claim 5, The first message further includes first condition information for predicting the wireless link failure, The above first condition information is, At least one of a threshold value for the strength of a reference signal, a threshold value for a block error rate (BLER) of a physical downlink control channel (PDCCH), a number of times an out of sync signal is received from a physical layer, a start of a T310 timer, a number of uplink retransmissions of a radio link control (RLC) layer, or a number of preamble transmissions for random access. Terminal.

8. In claim 5, The first message further includes at least one of second condition information for reporting the prediction information and third condition information for prediction termination, The above second condition information is, At least one of a threshold value, a number of reports, or a reporting cycle regarding the probability of occurrence of the wireless link failure, The above third condition information is: At least one of reception of a handover command message, reception of a radio resource control (RRC) release message, occurrence of a radio link failure, or a threshold value for the signal strength of a serving cell, Terminal.

9. In a method performed by a base station in a wireless communication system, A step of transmitting a first message to the terminal requesting a report of a prediction based on an AI (artificial intelligence) / ML model; and A step of receiving a second message including prediction information about a radio link failure (RLF) from the terminal, The first message includes information indicating at least one cause value associated with the wireless link failure, The above prediction information includes a probability of occurrence of a wireless link failure for each of the at least one cause value, method.

10. In claim 9, The first message further includes information about at least one candidate cell for conditional handover, The above prediction information includes a probability that a radio link failure will occur for each of the above cause values ​​for the at least one candidate cell. method.

11. In claim 9, The first message further includes first condition information for predicting the wireless link failure, The above first condition information is, At least one of a threshold value for the strength of a reference signal, a threshold value for a block error rate (BLER) of a physical downlink control channel (PDCCH), a number of times an out of sync is received from a physical layer, a start of a T310 timer, a number of uplink retransmissions of a radio link control (RLC) layer, or a number of preamble transmissions for random access. method.

12. In claim 9, The first message further includes at least one of second condition information for reporting the prediction information and third condition information for prediction termination, The above second condition information is, At least one of a threshold value, a number of reports, or a reporting cycle regarding the probability of occurrence of the wireless link failure, The above third condition information is: At least one of receiving a handover command message, receiving a radio resource control (RRC) release message, occurrence of a radio link failure, or a threshold value for the signal strength of the serving cell, method.

13. In a base station of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: Transmitting a first message to the terminal requesting a report of a prediction based on an AI (artificial intelligence) / ML model, and is configured to receive a second message including prediction information on radio link failure (RLF) from the terminal; The first message includes information indicating at least one cause value associated with the wireless link failure, The above prediction information includes a probability of occurrence of a wireless link failure for each of the at least one cause value, Base station.

14. In claim 13, The first message further includes information about at least one candidate cell for conditional handover, The above prediction information includes a probability that a radio link failure will occur for each of the above cause values ​​for the at least one candidate cell. Base station.

15. In claim 13, The first message further includes at least one of first condition information for predicting the wireless link failure and second condition information for reporting the predicted information, The above first condition information is, At least one of a threshold value for the strength of a reference signal, a threshold value for a block error rate (BLER) of a physical downlink control channel (PDCCH), a number of times an out of sync is received from a physical layer, a start of a T310 timer, a number of uplink retransmissions of a radio link control (RLC) layer, or a number of preamble transmissions for random access, The above second condition information is, At least one of a threshold value, a number of reports, or a reporting cycle regarding the probability of occurrence of the wireless link failure, Base station.

Images