Method and device for reducing power consumption of UE in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate than a 4G communication system such as LTE. An operation method of a UE according to an embodiment of the present disclosure includes the steps of: receiving, from a base station, configuration information related to RRM measurement relaxation; using an AI / ML model to determine whether an RRM measurement relaxation condition is satisfied on the basis of the configuration information related to the RRM measurement relaxation; and performing relaxed RRM measurement or unrelaxed (normal) RRM measurement on the basis of the determination.

Description

Method and device for reducing power consumption of a terminal in a wireless communication system

[0001] The present disclosure relates to operations of terminals and base stations in a wireless communication system, and more particularly, to a method and device for an AI / ML-based terminal to perform relaxed RRM (Radio Resource Measurement) operations in a next-generation mobile communication system.

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

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

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

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

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

[0007] In a wireless communication system according to one embodiment, a method of a user equipment (UE) is provided. The method of the UE may include: obtaining, from a base station, configuration information related to AI / ML-based RRM (Radio Resource Measurement) relaxation; obtaining information including predicted cell measurement results using AI / ML; determining, based on the information including the predicted cell measurement results, whether at least one RRM relaxation condition is satisfied; and performing relaxed RRM measurement or normal RRM measurement based on the determination.

[0008] According to one embodiment, the method of the UE may further include the step of receiving, from a base station, information indicating whether to allow performing AI / ML-based RRM relaxation.

[0009] According to one embodiment, the method of the UE may further include: a step of obtaining parameters associated with an RRM relaxation condition or the RRM relaxation condition itself using AI / ML; and a step of determining whether to perform relaxed RRM measurement or normal RRM measurement based on the parameters associated with the obtained RRM relaxation condition or the obtained RRM relaxation condition itself.

[0010] According to one embodiment, the parameters associated with the RRM relaxation condition may include at least one of: parameters indicating measurement-related threshold values ​​for the serving cell; or parameters included in the AI / ML-based RRM-related configuration information.

[0011] According to one embodiment, the method of the UE may further include: a step of obtaining information indicating whether to perform RRM relaxation using AI / ML; and a step of performing relaxed RRM measurement or normal RRM measurement based on the obtained information indicating whether to perform RRM relaxation.

[0012] According to one embodiment, the method of the UE may further include: obtaining information related to an RRM relaxation scheme using AI / ML; performing relaxed RRM measurement based on the obtained information related to the RRM relaxation scheme when the information related to the RRM relaxation scheme is successfully obtained; and performing normal RRM measurement when the information related to the RRM relaxation scheme is failed to be obtained. According to one embodiment, the information related to the RRM relaxation scheme may include at least one of information related to a measurement period, information related to a measurement frequency, or information related to a relaxation activation time interval.

[0013] In one embodiment, the UE may be in an inactive or idle state. In this case, in one embodiment, the step of acquiring AI / ML-based RRM relaxation-related configuration information from the base station may include the step of acquiring system information including AI / ML-based RRM relaxation-related configuration information from the base station.

[0014] In one embodiment, the UE may be in a connected state. In this case, in one embodiment, the step of acquiring the AI / ML-based RRM relaxation-related configuration information from the base station may further include the steps of: transmitting, to the base station, UE capability information including information regarding AL / ML-based RRM relaxation-related capabilities; and receiving, from the base station, an RRC reconfiguration message including the AI / ML-based RRM relaxation-related configuration information.

[0015] According to one embodiment, the method of the UE may further include, when performing relaxed RRM measurement, transmitting information indicating that relaxed RRM measurement has been performed to the base station through a measurement report, a Radio Link Failure (RLF) report, or a Handover Failure (HOF) report.

[0016] According to one embodiment, information related to an RRM relaxation method applied when performing relaxed RRM measurement may be determined based on which of at least one RRM relaxation condition is satisfied. The information related to the RRM relaxation method may include at least one of information related to a measurement period, information related to a measurement frequency, or information related to a relaxation activation time interval.

[0017] In one embodiment, when acquiring information using AI / ML, the accuracy of the acquired information can be derived together. In this case, according to one embodiment, the UE method may further include performing relaxed RRM measurement using the information acquired using AI / ML if the accuracy exceeds a specific threshold.

[0018] In a wireless communication system according to one embodiment, a user equipment (UE) is provided. The UE may include a memory storing one or more commands and at least one processor. The at least one processor may, by executing one or more commands stored in the memory, obtain AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information from a base station; obtain information including predicted cell measurement results using AI / ML; determine whether at least one RRM relaxation condition is satisfied based on the information including the predicted cell measurement results; and perform relaxed RRM measurement or normal RRM measurement based on the determination.

[0019] According to one embodiment, at least one processor may receive information from a base station indicating whether to allow performing AI / ML-based RRM relaxation by executing one or more instructions stored in memory.

[0020] According to one embodiment, at least one processor may obtain parameters associated with an RRM relaxation condition or the RRM relaxation condition itself by executing one or more instructions stored in a memory using AI / ML; and determine whether to perform relaxed RRM measurement or normal RRM measurement based on the parameters associated with the obtained RRM relaxation condition or the obtained RRM relaxation condition itself.

[0021] According to one embodiment, at least one processor may obtain information indicating whether to perform RRM relaxation using AI / ML by executing one or more instructions stored in a memory; and perform relaxed RRM measurement or normal RRM measurement based on the obtained information indicating whether to perform RRM relaxation.

[0022] According to one embodiment, at least one processor may obtain information related to an RRM relaxation scheme using AI / ML by executing one or more instructions stored in a memory; if the information related to the RRM relaxation scheme is successfully obtained, perform relaxed RRM measurement based on the obtained information related to the RRM relaxation scheme; and if the information related to the RRM relaxation scheme is not obtained, perform normal RRM measurement. The information related to the RRM relaxation scheme may include at least one of information related to a measurement period, information related to a measurement frequency, or information related to a relaxation activation time interval.

[0023] In one embodiment, the UE may be in an inactive or idle state. At this time, at least one processor may obtain system information including AI / ML-based RRM relaxation-related configuration information from the base station by executing one or more commands stored in memory.

[0024] In one embodiment, the UE may be in a connected state. At this time, at least one processor may transmit UE capability information including information regarding AL / ML-based RRM relaxation-related capabilities to the base station by executing one or more commands stored in memory; and receive an RRC reconfiguration message including AI / ML-based RRM relaxation-related configuration information from the base station.

[0025] In a wireless communication system according to one embodiment, a method of a base station is provided. The method of the base station may include: broadcasting, to a user equipment (UE), AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information via system information or via an RRC reconfiguration message; and receiving, from the UE, at least one of: information including a cell measurement result predicted using AI / ML; parameters associated with an RRM relaxation condition predicted using AI / ML; or information indicating that relaxed RRM measurement has been performed.

[0026] In a wireless communication system according to one embodiment, a base station is provided. The base station may include a memory storing one or more commands and at least one processor. The at least one processor may, by executing one or more commands stored in the memory, broadcast AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information to a UE (user equipment) via system information or via an RRC reconfiguration message; and receive from the UE at least one of: information including a cell measurement result predicted using AI / ML; parameters associated with an RRM relaxation condition predicted using AI / ML; or information indicating that relaxed RRM measurement has been performed.

[0027] FIG. 1a is a diagram illustrating the structure of a next-generation mobile communication system according to an embodiment of the present disclosure.

[0028] FIG. 1b is a diagram illustrating a wireless connection state transition of a terminal in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0029] FIG. 1c is a diagram illustrating a process in which frequency-specific priority information for cell reselection is broadcast through a system information block (SIB) or applied to a specific terminal through an RRC Release message, which is dedicated RRC signaling, in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0030] FIG. 1d is a diagram illustrating a method for a terminal to perform cell reselection in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0031] FIG. 1e is a diagram illustrating a method for a terminal and a base station to perform relaxed RRM measurement according to an embodiment of the present disclosure.

[0032] FIG. 1f is a diagram illustrating an example of a process in which a terminal selects and performs either normal RRM measurement or relaxed RRM measurement according to an embodiment of the present disclosure.

[0033] FIG. 1g is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation using a prediction measurement result using AI / ML according to one embodiment of the present disclosure.

[0034] FIG. 1h is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation through determination / update of relaxation condition parameters using AI / ML according to one embodiment of the present disclosure.

[0035] FIG. 1i is a diagram illustrating a process of determining whether a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation using AI / ML according to one embodiment of the present disclosure, and performing RRM relaxation through the same.

[0036] FIG. 1J is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation through determining / updating a relaxation method using AI / ML according to one embodiment of the present disclosure.

[0037] FIG. 1k is a diagram illustrating a process in which a terminal in a connection mode performs s-MeasureConfig-based RRM relaxation according to one embodiment of the present disclosure.

[0038] FIG. 1l is a diagram illustrating an operation of a terminal according to an embodiment of the present disclosure to determine whether to measure a cell based on s-MeasureConfig.

[0039] FIG. 1m is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs s-MeasureConfig-based RRM relaxation using a prediction measurement result using AI / ML.

[0040] FIG. 1n is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs RRM relaxation through s-MeasureConfig determination / update using AI / ML.

[0041] FIG. 1o is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure uses AI / ML to determine whether to perform RRM relaxation and thereby performs RRM relaxation.

[0042] FIG. 1p is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs relaxation condition-based RRM relaxation.

[0043] FIG. 1q is a diagram illustrating an operation of a terminal performing relaxed RRM measurement based on a relaxation condition or reporting whether a relaxation condition is satisfied, according to an embodiment of the present disclosure.

[0044] FIG. 1r is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs RRM relaxation based on relaxation conditions using a prediction measurement result using AI / ML.

[0045] [Revised 26.05.2025 under Rule 91] Figure 1s is a block diagram showing the structure of a terminal according to one embodiment of the present disclosure.

[0046] [Revised 26.05.2025 under Rule 91] Figure 1t is a block diagram showing the structure of a base station according to one embodiment of the present disclosure.

[0047] The operating principles of the present disclosure are described in detail below with reference to the attached drawings. In the following description of the present disclosure, detailed descriptions of related known functions or configurations will be omitted if they are deemed to unnecessarily obscure the gist of the present disclosure. Furthermore, the terms described below are defined based on the functions of the present disclosure and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the overall content of this specification.

[0048] The terms used in the following description to identify connection nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, and terms referring to various identification information are provided for convenience of explanation. Therefore, the present invention is not limited to the terms described below, and other terms referring to objects with equivalent technical meanings may be used.

[0049] Hereinafter, the base station is an entity that performs resource allocation of the terminal, and may be at least one of a gNode B, an eNode B, a Node B, a BS (Base Station), a wireless access unit, a base station controller, or a node on a network. The terminal may include a UE (User Equipment), an MS (Mobile Station), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing a communication function. In the present disclosure, downlink (DL) refers to a wireless transmission path of a signal transmitted from a base station to a terminal, and uplink (UL) refers to a wireless transmission path of a signal transmitted from a terminal to a base station. In addition, although the LTE or LTE-A system may be described below as an example, the embodiments of the present disclosure may also be applied to other communication systems having similar technical backgrounds or channel types. For example, the 5th generation mobile communication technology (5G, new radio, NR) or the 5G advanced system developed after LTE-A may be included in a system to which the embodiments of the present disclosure may be applied, and 5G below may also be a concept that includes existing LTE, LTE-A, and other similar services.

[0050] Furthermore, the present disclosure may be applied to other communication systems with some modifications, as determined by a person skilled in the art, without significantly departing from the scope of the present disclosure. It will be appreciated that each block of the processing flow diagrams and combinations of the flow diagrams can be executed by computer program instructions.

[0051] These computer program instructions may be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the instructions executed by the processor of the computer or other programmable data processing apparatus create means for performing the functions described in the flowchart block(s). These computer program instructions may also be stored in a computer-available or computer-readable memory that can be directed to a computer or other programmable data processing apparatus to implement functions in a particular manner, so that the instructions stored in the computer-available or computer-readable memory can produce an article of manufacture that includes instruction means for performing the functions described in the flowchart block(s). The computer program instructions may also be installed on a computer or other programmable data processing apparatus, so that a series of operational steps are performed on the computer or other programmable data processing apparatus to create a computer-implemented process, so that the instructions executing on the computer or other programmable data processing apparatus can provide steps for performing the functions described in the flowchart block(s).

[0052] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for executing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order depending on the corresponding function. In this case, the term '~unit' used in the present embodiment means software or a hardware component such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit), and the '~unit' may perform certain roles. However, the '~unit' is not limited to software or hardware. The '~unit' may be configured to be on an addressable storage medium and may be configured to execute one or more processors. Thus, as an example, the '~ unit' includes components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, the components and '~ units' may be implemented to reproduce one or more CPUs within a device or a secure multimedia card. Also, in an embodiment, the '~ unit' may include one or more processors.

[0053] For convenience of explanation, this disclosure uses terms and names defined in the 5GS and NR standards defined by the 3rd Generation Partnership Project (3GPP). However, the present invention is not limited to these terms and names and can be equally applied to wireless communication networks conforming to other standards. For example, the present invention can be applied to the 3GPP 5GS / NR (5th generation mobile communication standard) or the 3GPP 5G advanced standard.

[0054] FIG. 1a is a diagram illustrating the structure of a next-generation mobile communication system according to an embodiment of the present disclosure.

[0055] Referring to FIG. 1a, a wireless access network of a next-generation mobile communication system (new radio, NR) may be composed of a next-generation base station (new radio node B, hereinafter referred to as gNB) (1a-10) and an AMF (1a-05, new radio core network). A user equipment (new radio user equipment, hereinafter referred to as NR UE or terminal) (1a-15) may access an external network through the gNB (1a-10) and the AMF (1a-05).

[0056] In Figure 1a, the gNB corresponds to the eNB (evolved node B) of the existing LTE system. The gNB is connected to the NR UE via a wireless channel and can provide superior services than the existing node B (1a-20). In the next-generation mobile communication system, all user traffic is serviced through a shared channel, so a device that collects status information such as the buffer status of UEs, available transmission power status, and channel status and performs scheduling is required, and this is handled by the gNB (1a-10). A single gNB can typically control multiple cells. In order to implement ultra-high-speed data transmission compared to the existing LTE, it can have a bandwidth exceeding the existing maximum, and beamforming technology can be additionally incorporated using orthogonal frequency division multiplexing (OFDM) as a wireless access technology. In addition, an adaptive modulation & coding (AMC) method that determines the modulation scheme and channel coding rate according to the channel status of the terminal can be applied.

[0057] AMF (1a-05) can perform functions such as mobility support, bearer setup, and QoS setup. AMF (1a-05) is a device that handles various control functions as well as mobility management functions for terminals and can be connected to multiple base stations. In addition, the next-generation mobile communication system can be interoperable with the existing LTE system, and AMF (1a-05) can be connected to MME (1a-25) through a network interface. MME can be connected to eNB (1a-30), which is an existing base station. Terminals that support LTE-NR dual connectivity can transmit and receive data while maintaining connection to both gNB and eNB (1a-35).

[0058] FIG. 1b is a diagram illustrating a wireless connection state transition of a terminal in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0059] In the next-generation mobile communication system, a terminal may have three radio connection states (radio resource control (RRC) states). The connected mode (RRC_CONNECTED, 1b-05) may refer to a radio connection state in which the terminal can transmit and receive data. The standby mode or idle mode (RRC_IDLE, 1b-30) may refer to a radio connection state in which the terminal monitors whether a paging is transmitted to it. The connected mode (1b-05) and the standby mode (1b-30) are radio connection states that are also applied to the existing LTE system, and the detailed technology is the same as that of the existing LTE system. In the next-generation mobile communication system, a new inactive radio connection state or inactive mode (RRC_INACTIVE, 1b-15) is defined. In the present disclosure, the newly defined RRC_INACTIVE radio connection state (1b-15) in the next-generation mobile communication system may correspond to an inactive radio connection state, an INACTIVE mode, an inactive mode, etc.

[0060] In the inactive mode (1b-15) wireless connection state, the UE context is maintained between the base station and the terminal, and RAN (radio access network)-based paging can be supported. The characteristics of the new inactive (RRC_INACTIVE) wireless connection state (1b-15) are listed as follows.

[0061] - Cell re-selection mobility;

[0062] - CN - NR RAN connection (both C / U-planes) has been established for UE;

[0063] - The UE AS context is stored in at least one gNB and the UE;

[0064] - Paging is initiated by NR RAN;

[0065] - RAN-based notification area is managed by NR RAN;

[0066] - NR RAN knows the RAN-based notification area which the UE belongs to;

[0067] According to one embodiment, the INACTIVE wireless connection state can be transitioned to a connected mode (1b-05) or a standby mode (1b-30) using a specific procedure. The INACTIVE mode (1b-15) can be transitioned to a connected mode (1b-05) by a Resume procedure, and the connected mode (1b-05) can be transitioned to an INACTIVE mode (1b-15) by using a Release procedure including suspend configuration information (1b-10). In the above-described procedure (1b-10), one or more RRC messages can be transmitted and received between the terminal and the base station, and the above-described procedure (1b-10) can consist of one or more steps. In addition, the INACTIVE mode (1b-15) can be transitioned to a standby mode (1b-30) by a Release procedure after the Resume procedure (1b-20).

[0068] Switching between connected mode (1b-05) and standby mode (1b-30) can be performed according to existing LTE technology. That is, switching between connected mode (1b-05) and standby mode (1b-30) can be performed through an establishment or release procedure (1b-25).

[0069] FIG. 1c is a diagram illustrating a process in which frequency-specific priority information for cell reselection is broadcast through a system information block (SIB) or applied to a specific terminal through an RRCRelease message, which is dedicated RRC signaling, in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0070] Cell reselection is the process of reselecting a serving cell so that a mobile terminal (a terminal in RRC_INACTIVE or RRC_IDLE state) can connect to the cell with the best channel condition. The network can control cell reselection of terminals in standby mode by assigning priorities by frequency. For example, if a terminal receives priority information for two frequencies f1 and f2, and frequency f1 has a higher priority than frequency f2, the terminal is more likely to stay in the cell with frequency f1. Furthermore, even if the terminal is in the cell with frequency f2, if the channel condition of frequency f2 is poor, it will attempt to change to the cell with frequency f1.

[0071] Priority information for a frequency can be broadcast via a system information block (SIB) or provided to a specific UE via a dedicated RRC signaling RRCRelease message. Even if a UE already has priority information for frequencies via SIB, if it receives UE-specific priority information via RRC signaling via an RRCRelease message, the priority information in the SIB can be ignored. Priority information for each frequency can be conveyed via the cellReselectionPriority IE, as shown in [Table 1] below, and can be assigned one of eight priority levels. A lower value may indicate a lower priority. That is, '0' may indicate the lowest priority.

[0072] [Table 1]

[0073]

[0074] Frequencies across RATs (radio access technologies) cannot be assigned the same priority. If the UE's IDLE state is 'camped on any cell state,' the frequency priority information received via SIB is applied, and the priority information received via RRC signaling is not used and can only be stored. The cellReselectionPriority IE is an optional IE and may not be present. If the cellReselectionPriority IE is not present, priority information for the corresponding frequency has not been assigned. In this case, the UE can regard the frequency as having the lowest priority. In step 1c-00, the UE can receive priority information for frequencies used by other RATs as well as NR via SIB. However, priority information is not necessarily provided for all frequencies. Priority information for the frequency of the currently camped serving cell may also not be provided. The UE can check this in step 1c-05. If priority information for the frequency of the current serving cell is not provided, the priority of the frequency may be considered as the lowest level, as in step 1c-10.

[0075] The UE can apply priority information of each frequency in step 1c-15. When the UE receives an RRCRelease message from the base station, the UE can switch from connected mode to idle mode or inactive mode. The RRC message may include frequency priority information. This is UE-specific information and can generally be applied with priority over frequency priority information provided from SIB. Therefore, the UE can check whether the RRC message includes frequency priority information in step 1c-20. If the RRC message includes frequency priority information, the first timer value included therein can be applied to start the first timer in step 1c-25. The UE can determine whether the current idle mode state is a 'camped on any cell state' or a 'camped normally state' in step 1c-30. The 'camped normally state' refers to a state in which the UE is camping on a suitable cell. A suitable cell is a cell that can provide normal service to a terminal and satisfies the detailed conditions below.

[0076] - The cell corresponds to a selected PLMN (public land mobile network), a registered PLMN, or a PLMN within the equivalent PLMN list.

[0077] - Unbarred cells

[0078] - Cells that satisfy the cell selection criterion

[0079] The "camped on any cell" state refers to a state in which a terminal is unable to camp on a suitable cell and is instead camped on an acceptable cell. In an acceptable cell, general services are unavailable, and only emergency calls can be attempted. An acceptable cell is one that satisfies the following conditions:

[0080] - Unbarred cells

[0081] - Cells that satisfy the cell selection criterion

[0082] If the terminal is in the 'camped on any cell state' standby state, the priority information provided in the RRCRelease message may not be applied, and instead, the terminal may return to step 1c-15 and apply the frequency priority information provided in the SIB. Furthermore, if the terminal is in the 'camped normally' standby state, the terminal may determine in step 1c-35 whether at least one of the following three conditions is satisfied. The three conditions are as follows:

[0083] - The terminal switches to connection mode.

[0084] - The first timer expired

[0085] - PLMN selection process is performed according to NAS (non-access stratum) request

[0086] If any of the above conditions are met, the UE may discard the priority information provided in the RRCRelease message in step 1c-40 and return to step 1c-15 to apply the frequency priority information provided in the SIB. Otherwise, if none of the above conditions are met, the UE may apply the priority information provided in the RRCRelease message in step 1c-45.

[0087] Frequency priority information can influence how a terminal measures a specific frequency. A terminal can always perform measurements on frequencies with a higher priority than the current serving cell. Conversely, a terminal may not always perform measurements on frequencies within the same frequency as the serving cell or on other frequencies with the same or lower priority to conserve power.

[0088] Measurement can be performed when the channel quality of service (QoS) of the serving cell is less than or equal to a specific threshold. Cell reselection is performed to move to a cell with a good channel condition, but if the channel QoS of the current serving cell is good, there is no reason to move to a frequency with the same or lower priority. Therefore, to reduce power consumption due to unnecessary channel measurement, it is possible to determine whether to perform measurement based on a specific threshold. In the case of the same frequency (intra-frequency), if the QoS of the serving cell (i.e., Srxlev or Squal) is equal to or lower than a specific threshold SintraSearch (s-IntraSearchP and s-IntraSearchQ), channel measurement can be performed for other cells of the same frequency. s-IntraSearchP is a threshold based on RSRP (reference signal received power), and s-IntraSearchQ is a threshold based on RSRQ (reference signal received quality). If both the RSRP and RSRQ of the measured serving cell are greater than the threshold, intra-frequency measurement is not performed. For other frequencies (inter-frequency) with the same or lower priority, if the QoS (i.e., Srxlev or Squal) of the serving cell is equal to or lower than a specific threshold Snonintrasearch (s-NonIntraSearchP and s-NonIntraSearchQ), channel measurement can be performed for cells of the other frequencies. s-NonIntraSearchP is an RSRP-based threshold, and s-NonIntraSearchQ is an RSRQ-based threshold. If both the RSRP and RSRQ of the measured serving cell are greater than the threshold, inter-frequency measurement is not performed.

[0089] In this disclosure, a state in which channel measurements are performed intra-frequency or inter-frequency based on comparison with the above thresholds is referred to as a normal measurement state, and a state in which no measurement is performed is referred to as a no measurement state. Regardless of the state in which channel measurements are performed (measurement state), serving cell measurements can always be performed.

[0090] When performing the measurement in this way, if the channel QoS of the cell of the frequency with the higher priority becomes higher than a specific threshold ThreshX-high, the terminal can reselect the cell of the frequency with the higher priority as the serving cell. If the channel QoS of the cell of the frequency with the lower priority becomes higher than a specific threshold ThreshX-low and the QoS of the serving cell becomes lower than ThreshServing-low, the terminal can reselect the cell of the frequency with the lower priority as the serving cell.

[0091] FIG. 1d is a diagram illustrating a method for a terminal to perform cell reselection in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0092] The terminal can always perform inter-freq measurements and RAT measurements for high priority frequencies or RATs regardless of the measurement signal strength for the serving cell.

[0093] If the measured signal strength (1d-05) for the serving cell is lower than SintraSearch (1d-25), the terminal can perform intra-freq measurements. If the measured signal strength (1d-05) for the serving cell is lower than SnonintraSearch (1d-30), the terminal can perform inter-freq / RAT measurements for frequencies with the same or lower priority than the frequency of the current serving cell.

[0094] Conversely, if the measured signal strength (1d-05) for the serving cell is higher than SintraSearch (1d-25), the terminal may not perform intra-freq measurements, and if the measured signal strength (1d-05) for the serving cell is higher than SnonintraSearch (1d-30), the terminal may not perform inter-freq / RAT measurements for frequencies whose priority is equal to or lower than that of the current serving cell.

[0095] The reason for triggering this action of reducing the above terminal measurements (RRM measurement relaxation or relaxed RRM measurement) may be to reduce the power consumption of the terminal due to measurements of surrounding cells.

[0096] If the channel QoS of a cell (1d-10) of a frequency with a high priority becomes higher than a specific threshold ThreshX-high (1d-35), the terminal can reselect the cell of the frequency with a high priority as the serving cell. If the channel QoS of a cell (1d-00) of a frequency with a low priority becomes higher than a specific threshold ThreshX-low (1d-15) and the QoS of the serving cell becomes lower than ThreshServing-low (1d-20), the terminal can reselect the cell of the frequency with a low priority as the serving cell.

[0097] When reselecting a cell, the received signal strength (RSRP, reference signal received power) or the received signal quality (RSRQ, reference signal received quality) can be considered. For each, Srxlev or Squal can be calculated as follows.

[0098]

[0099] Here, the meaning of each variable is as described in [Table 2] below.

[0100] [Table 2]

[0101]

[0102] FIG. 1e is a diagram illustrating a method for a terminal and a base station to perform relaxed RRM measurement in an inactive mode or standby mode according to one embodiment of the present disclosure.

[0103] In inactive or standby mode, a terminal can camp on a corresponding cell (1e-10) after receiving system information (1e-05). A terminal in inactive or standby mode for cell selection or reselection can perform RRM measurement. In FIG. 1e, a terminal performing RRM measurement can check whether an RRM measurement relaxation parameter or configuration is set through information (e.g., relaxedMeasurement) included in system information (e.g., SIB2) (1e-05) received from a base station. For example, relaxedMeasurement may include multiple parameters for RRM relaxation, as shown in [Table 3] below.

[0104] [Table 3]

[0105]

[0106] If relaxedMeasurement is set in the system information and the terminal supports relaxed measurement, the terminal determines whether it can perform RRM (measurement) relaxation using the above parameters (1e-15). If the conditions for performing RRM relaxation (Relaxation criteria or relaxation conditions or relaxed measurement criteria or relaxed measurement conditions) through 1e-15 are satisfied, the terminal can perform relaxed RRM measurement (1e-20). If the conditions for performing RRM relaxation (Relaxation criteria or relaxation conditions) through 1e-15 are not satisfied, the terminal cannot perform relaxed RRM measurement and can perform conventional or normal RRM measurement (1e-20).

[0107] In the 1e-15 process, depending on the system information settings of the base station, the terminal can be configured with some or all of the four relaxed measurement criteria, respectively: 1) low mobility criterion (corresponding to lowMobilityEvaluation in Table 3), 2) not-at-cell-edge criterion (corresponding to cellEdgeEvaluation in Table 3), 3) stationary criterion (corresponding to stationaryMobilityEvaluation in Table 3), and 4) stationary and not-at-cell-edge criterion (corresponding to cellEdgeEvaluationWhileStationary in Table 3). Among these, 3) stationary criterion and 4) stationary and not-at-cell-edge criterion can be used by RedCap (Reduced Capability) terminals or enhanced RedCap terminals. The base station can configure only one criterion or multiple criterions. 1) Low mobility criterion and 3) Stationary criterion allow a terminal to determine that its mobility level is low, and 2) Not-at-cell-edge criterion allows a terminal to determine that it is not located at the edge of its serving cell. In other words, a terminal with low mobility and located outside the cell edge has stable signal strength from its serving cell, and thus has less need for cell reselection to other neighboring cells, allowing relaxation of RRM measurement for neighboring cells.The above relaxed RRM measurement can reduce energy consumption by measuring frequencies at a larger period (i.e., more rarely) than normal RRM measurement.

[0108] The operations related to SintraSearch and SnonintraSearch in the description of Fig. 1d can also be applied to Fig. 1e as part of relaxed measurement or RRM relaxation. Specifically, in the inactive mode or standby mode, the terminal can camp on a cell (1e-10) after receiving system information (1e-05). Through the system information (e.g., SIB2), the terminal can receive SintraSearch and / or SnonintraSearch (1e-05). Thereafter, at 1e-15, if the measured signal strength for the serving cell is lower than SintraSearch, the terminal can perform intra-freq measurement (e.g., normal measurement). If the measured signal strength for the serving cell is lower than SnonintraSearch, the terminal can perform inter-freq / RAT measurement on a frequency with a priority equal to or lower than the frequency of the current serving cell (e.g., normal measurement). Conversely, if the measured signal strength for the serving cell is higher than SintraSearch, the terminal may not perform intra-freq measurements (e.g., relaxed measurement), and if the measured signal strength for the serving cell is higher than SnonintraSearch, the terminal may not perform inter-freq / RAT measurements for frequencies whose priority is equal to or lower than that of the current serving cell (e.g., relaxed measurement).

[0109] FIG. 1f is a diagram illustrating an example of a process in which a terminal selects and performs either normal RRM measurement or relaxed RRM measurement according to an embodiment of the present disclosure.

[0110] The terminal can receive the SIB and obtain configuration information for RRM measurement relaxation (e.g., SintraSearch and / or SnonintraSearch and / or relaxedMeasurement) (1f-05).

[0111] A terminal can camp on one serving cell (1f-10).

[0112] The terminal can perform RRM measurement for cell reselection by frequency (NR intra frequency or NR inter frequency or inter-RAT frequency) and / or by frequency priority, and at this time, it can determine whether relaxation criteria (relaxation conditions) are satisfied according to the RRM measurement relaxation setting information. (1f-15).

[0113] If a given relaxation condition is satisfied, the terminal can perform relaxed RRM measurement. (1f-20) In this case, the terminal can reduce energy consumption by performing measurements with a longer value (i.e., less frequently) than the normal measurement period or by not performing measurements at all. The measurement period for relaxed RRM measurement may be the same as some of the contents of 3GPP TS 38.133 and 3GPP TS 38.304. If the given relaxation condition is not satisfied, the terminal can perform normal RRM measurement at the corresponding frequency (1f-25). The measurement period for normal RRM measurement may be the same as the contents of 3GPP TS 38.133.

[0114] In this disclosure, we propose a terminal RRM relaxation method using prediction or inference utilizing AI / ML (Artificial Intelligence / Machine Learning).

[0115] According to one embodiment of the present disclosure, a terminal may use, as inputs of an AI / ML model, current serving cell and neighboring cell measurement value (RSRP / RSRQ / SINR) information, past serving cell and neighboring cell measurement value (RSRP / RSRQ / SINR) information, location information of the terminal, speed information of the terminal, serving cell history information of the terminal, neighboring cell history information of the terminal, remaining power information of the terminal, configuration information (e.g., RRC configuration information) history of the terminal, capabilities of the terminal, etc.

[0116] A terminal according to an embodiment of the present disclosure can obtain future cell measurement value information (e.g., RSRP / RSRQ / SINR) as an output of an AI / ML model.

[0117] Through this, for example, the terminal can reduce the energy usage of the terminal by preemptively performing RRM relaxation by predicting through AI / ML that the relaxation condition will be satisfied for the future cell measurement value even if the current cell measurement value does not satisfy the relaxation condition (e.g., in a situation where the terminal is moving toward the center of the serving cell, or in a situation where the terminal's mobility is decreasing).

[0118] Conversely, for example, the terminal can perform normal measurement without performing RRM relaxation by predicting through AI / ML that the relaxation condition will not be satisfied for future cell measurement values ​​(RSRP / RSRQ / SINR) even if the current cell measurement value satisfies the relaxation condition (e.g., in a situation where the terminal is moving outside the serving cell, or in a situation where the terminal is becoming more mobile), and thus perform the correct cell (re)selection through sufficient cell measurements.

[0119] FIG. 1g is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation using a prediction measurement result using AI / ML according to one embodiment of the present disclosure.

[0120] In step 1g-05, the terminal may receive system information in an inactive or standby mode. The system information may include RRM measurement relaxation-related settings (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Furthermore, the terminal may receive RRM relaxation-related settings from the base station using predicted cell measurement results. Furthermore, the terminal may receive information from the base station regarding whether to allow RRM relaxation using predicted cell measurement results. Step 1g-05 may correspond to step 1f-05 of FIG. 1f.

[0121] In step 1g-10, the terminal can camp on the corresponding cell. Step 1g-10 may correspond to step 1f-10 of FIG. 1f.

[0122] In step 1g-15, the terminal can run an AI / ML model to output predicted cell measurement results (e.g., RSRP / RSRQ / SINR) in the future.

[0123] In step 1g-20, the terminal may determine whether to perform RRM relaxation based on actual cell measurement results and / or predicted cell measurement results. Step 1g-20 may correspond to step 1f-15 of FIG. 1f. For example, the terminal may determine that the RRM relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0124] - Condition 1. If the predicted cell measurement result satisfies the not-at-cell-edge condition. For example, if the predicted value is greater than the cell measurement threshold set by the base station in 1g-05.

[0125] - Condition 2. If the predicted cell measurement results satisfy low mobility or stationary conditions. For example, if the change in the predicted value is greater than the cell measurement threshold set by the base station in 1g-05.

[0126] - Condition 3. When the actual cell measurement result satisfies the not-at-cell-edge condition. For example, when the actual measurement value is greater than the cell measurement threshold set by the base station in 1g-05.

[0127] Condition 4. When the actual cell measurement results satisfy the low mobility or stationary conditions. For example, when the change in the actual measurement value is greater than the cell measurement threshold set by the base station in 1g-05.

[0128] - Condition 5. If RRM relaxation using cell measurement results predicted from the base station is permitted or related settings are received, for example, if permitted or related settings are received in 1g-05.

[0129] - Condition 6. If RRM relaxation using actual cell measurement results is permitted or related settings are received from the base station, for example, if permitted or related settings are received in 1g-05.

[0130] In step 1g-25, if the terminal determines that the RRM relaxation condition is satisfied, relaxed RRM measurement can be performed. This may correspond to step 1f-20 of FIG. 1f. Conversely, if the terminal determines that the RRM relaxation condition is not satisfied, normal RRM measurement can be performed. This may correspond to step 1f-25 of FIG. 1f.

[0131] In one embodiment of the present disclosure, when RRM relaxation is triggered by a predicted cell measurement result, the terminal may report the predicted cell measurement value to the base station. For example, the terminal may report the predicted cell measurement value to the base station via a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message. This may be useful information when the base station configures new RRM relaxation parameters for the terminal in the future.

[0132] In one embodiment of the present disclosure, the terminal can obtain parameters for RRM relaxation conditions (e.g., parameters within SintraSearch and / or SnonintraSearch and / or relaxedMeasurement) as an output of an AI / ML model.

[0133] In conventional RRM relaxation methods, all terminals within a serving cell receive common parameters related to common RRM relaxation conditions in system information (e.g., parameters within SintraSearch and / or SnonintraSearch and / or relaxedMeasurement) and determine the same RRM relaxation conditions accordingly. However, the actual status and circumstances of each terminal (such as the values ​​used as inputs to the AI / ML model) may differ, and each terminal may need to set RRM relaxation conditions appropriate for its situation. For example, when many cells are located around a terminal, using a strict RRM relaxation condition can help improve throughput when the terminal transitions to connected mode by allowing the terminal to perform sufficient RRM measurements to find the best cell. Conversely, when there are no other cells around the terminal other than the serving cell, using a lenient RRM relaxation condition can minimize RRM measurements by the terminal, allowing the terminal to remain in the serving cell as long as possible and reducing energy consumption due to unnecessary RRM measurements.

[0134] FIG. 1h is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation through determination / update of relaxation condition parameters using AI / ML according to one embodiment of the present disclosure.

[0135] In step 1h-05, the terminal may receive system information in an inactive or standby mode. This system information may include RRM measurement relaxation-related settings (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Additionally, the terminal may receive information from the base station regarding whether relaxation condition parameter determination / update is permitted. Step 1h-05 may correspond to step 1f-05 of FIG. 1f.

[0136] In step 1h-10, the terminal can camp on the cell. Step 1h-10 may correspond to step 1f-10 of FIG. 1f.

[0137] In step 1h-15, the terminal can derive (output) relaxation condition parameters to be used for RRM relaxation by running the AI / ML model. These may be parameters used for the relaxation conditions set by the base station. Alternatively, relaxation conditions to be used may be derived as well as relaxation condition parameters to be used as output of AI / ML. In this case, if the base station has not set a relaxation condition, the terminal can use the derived relaxation condition, or if the base station has set a relaxation condition, the terminal can use the derived relaxation condition instead of the configured relaxation condition.

[0138] In one embodiment of the present disclosure, the terminal may report the derived relaxation condition parameter (e.g., threshold value) to the base station when transitioning to a connected mode later. For example, the terminal may report the derived relaxation condition parameter (e.g., threshold value) to the base station when transitioning to a connected mode later through a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message. Through this, the base station may obtain information about the RRM relaxation condition parameter used by the terminal and utilize it for network configuration.

[0139] In step 1h-20, the terminal may determine whether to perform RRM relaxation based on the derived relaxation condition and / or derived relaxation condition parameters (e.g., threshold values). Step 1h-20 may correspond to step 1f-15 of FIG. 1f. For example, the terminal may determine that the RRM relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0140] - Condition 1. If the actual measured or predicted cell measurement results satisfy the derived relaxation conditions.

[0141] - Condition 2. If permission is granted or related settings are received for relaxation condition determination / update from the base station, for example, if permission is granted or related settings are received in 1h-05.

[0142] In step 1h-25, if the terminal determines that the RRM relaxation condition is satisfied, relaxed RRM measurement may be performed. This may correspond to step 1f-20. Conversely, if the terminal determines that the RRM relaxation condition is not satisfied, normal RRM measurement may be performed. This may correspond to step 1f-25.

[0143] In one embodiment of the present disclosure, the terminal can obtain whether RRM relaxation is performed as an output of an AI / ML model.

[0144] In conventional RRM relaxation methods, a UE can determine whether to perform RRM relaxation based on relaxation conditions defined by the standard and set by the network (e.g., low mobility, not-at-cell-edge, stationary criteria). However, the network may find it difficult to set optimal conditions for each UE. Furthermore, other conditions beyond the relaxation conditions defined by the standard may be important in determining whether a UE performs relaxation. For example, when a UE is surrounded by numerous cells, using stringent RRM relaxation conditions can help improve throughput when the UE transitions to connected mode by allowing the UE to perform sufficient RRM measurements to find the best cell. Conversely, when there are no other cells surrounding the UE besides the serving cell, using less stringent RRM relaxation conditions can minimize RRM measurements, allowing the UE to remain in the serving cell as long as possible and reducing energy consumption from unnecessary RRM measurements. In such cases, the density of surrounding cells can be an important indicator for the UE in determining whether to perform relaxation. As another example, when a terminal's residual power is high, finding the best cell through sufficient RRM measurements can improve throughput when the terminal transitions to connected mode. Conversely, when the terminal's residual power is low, minimizing RRM measurements can help ensure that the terminal remains in the serving cell as long as possible, reducing energy consumption from unnecessary RRM measurements. In such cases, the terminal's residual power can also be an important indicator for determining whether to perform relaxation.Therefore, instead of specifying relaxation conditions stipulated in the standard or set by the network, the terminal can freely determine whether to perform RRM relaxation and perform RRM relaxation by considering various collected information (e.g., cell measurement / prediction values, remaining power, cell density) (e.g., as input to the model) on its own (without being stipulated in the standard and without the need for the network to set them).

[0145] FIG. 1i is a diagram illustrating a process of determining whether a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation using AI / ML according to one embodiment of the present disclosure, and performing RRM relaxation through the same.

[0146] In step 1i-05, the terminal may receive system information in an inactive or standby mode. This system information may include RRM measurement relaxation-related settings (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Furthermore, the terminal may use AI / ML to determine whether RRM relaxation is performed and receive permission for its use from the base station. Step 1i-05 may correspond to step 1f-05 of FIG. 1f .

[0147] In steps 1i-10, the terminal can camp on the corresponding cell. Step 1i-10 may correspond to step 1f-10 of FIG. 1f.

[0148] In steps 1i-15, the terminal may drive an AI / ML model to determine whether RRM relaxation is performed (output). According to one embodiment of the present disclosure, the terminal may use RRM relaxation configuration conditions and parameters set by the base station as one of the input values ​​of the AI / ML model.

[0149] In steps 1i-20, the terminal may determine whether to perform RRM relaxation based on whether the derived RRM relaxation is performed. Step 1i-20 may correspond to step 1f-15 of FIG. 1f. For example, the terminal may determine that the RRM relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0150] - Condition 1. If “RRM relaxation is performed” is derived

[0151] - Condition 2. If permission is obtained from the base station to perform RRM relaxation and use it or if related settings are obtained, for example, if permission is obtained in 1i-05 or related settings are obtained.

[0152] In steps 1i-20, if the terminal satisfies the RRM relaxation condition, relaxed RRM measurement can be performed. This may correspond to step 1f-20. Conversely, if the terminal does not satisfy the RRM relaxation condition, normal RRM measurement can be performed. This may correspond to step 1f-25.

[0153] In one embodiment of the present disclosure, the terminal can obtain an RRM relaxation method (e.g., measurement period or whether to measure) as an output of an AI / ML model.

[0154] In conventional RRM relaxation methods, a UE can determine the degree of relaxation based on the relaxation method specified in the standard (e.g., the measurement cycle described in 3GPP TS 38.331). Therefore, the network cannot set the optimal relaxation method (e.g., measurement cycle) for each UE. Furthermore, a relaxation method that does not follow the relaxation degree or method specified in the standard may be the optimal relaxation method for the UE. For example, when many cells are located around a UE, using a relatively short measurement cycle during relaxation can help improve throughput when the UE transitions to connected mode by allowing sufficient RRM measurements to determine the best cell. Conversely, when there are no other cells around the UE besides the serving cell, using a relatively long measurement cycle during relaxation minimizes RRM measurements, allowing the UE to remain on the serving cell as much as possible and reducing energy consumption due to unnecessary RRM measurements. In such cases, the density of surrounding cells can be an important indicator for the UE in determining the degree and method of relaxation. As another example, when the terminal's residual power is high, using a relatively short measurement period during relaxation can help improve throughput when the terminal transitions to connected mode by performing sufficient RRM measurements to find the best cell. Conversely, when the terminal's residual power is low, using a relatively long measurement period during relaxation can minimize the terminal's RRM measurements, thereby ensuring that the terminal remains in the serving cell as long as possible and reducing energy consumption through unnecessary RRM measurements. In such cases, the terminal's residual power can also be an important indicator for determining the degree and method of relaxation.Therefore, instead of following the relaxation method (measurement cycle) specified in the standard, the terminal can freely determine the degree and method (e.g., measurement cycle) of RRM relaxation by driving AI / ML (e.g., as input to the model) by considering various collected information (e.g., cell measurement / prediction values, residual power, cell density) (not specified in the standard).

[0155] FIG. 1J is a diagram illustrating a process in which a terminal in an inactive mode or a terminal in a standby mode performs RRM relaxation through determining / updating a relaxation method using AI / ML according to one embodiment of the present disclosure.

[0156] In step 1j-05, the terminal may receive system information in an inactive or standby mode. This system information may include RRM measurement relaxation-related settings (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Additionally, the terminal may receive information from the base station regarding whether relaxation method determination / update is permitted. Step 1j-05 may correspond to step 1f-05 of FIG. 1f.

[0157] In step 1j-10, the terminal can camp on the corresponding cell. Step 1j-10 may correspond to step 1f-10 of FIG. 1f.

[0158] In step 1j-15, the terminal can determine that the RRM relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0159] - Condition 1. When the relaxation conditions according to the RRM measurement relaxation settings set by the base station (e.g., not-at-cell-edge, low mobility, stationary criterion) are satisfied.

[0160] - Condition 2. If permission is granted to determine / update the relaxation method from the base station or if related settings are received.

[0161] In step 1j-20, if the terminal determines that the relaxation condition is satisfied, it can drive the AI / ML model to derive (output) the degree and / or method of relaxation to be used (e.g., measurement period, measurement frequency, measurement frequency type, time interval to perform relaxation operation).

[0162] In step 1j-25, if the terminal determines that the above RRM relaxation condition is satisfied and the AI / ML model is successfully driven to derive a relaxation method, relaxed RRM measurement can be performed based on the derived result. This may correspond to step 1f-20.

[0163] If the terminal determines that the above RRM relaxation condition is satisfied but fails to derive a relaxation method, the terminal may perform relaxed RRM measurement according to a fixed relaxation method defined in the standard (e.g., a measurement period described in 3GPP TS 38.133). Here, the fixed relaxation method defined in the standard may be a method that does not use an AI / ML model. This may correspond to step 1f-20. For example, if the terminal determines that the above RRM relaxation condition is satisfied but fails to derive a relaxation method by running the AI / ML model within a time limit set by the network or defined in the standard, the terminal may perform relaxed RRM measurement according to a fixed relaxation method defined in the standard (e.g., a measurement period described in 3GPP TS 38.133).

[0164] If the terminal determines that the above RRM relaxation condition is not satisfied, normal RRM measurement can be performed, which may correspond to step 1f-25.

[0165] FIG. 1k is a diagram illustrating a process in which a terminal in a connection mode performs s-MeasureConfig-based RRM relaxation according to one embodiment of the present disclosure.

[0166] At step 1k-05, the terminal may be in a connection mode with the base station.

[0167] In step 1k-07, after receiving a UE capability enquiry message from the base station, the terminal may transmit information about its capabilities to the base station through a UE capability information message. At this time, the terminal may include / transmit information regarding whether it supports RRM relaxation in connected mode in / with the UE capability information. At this time, the terminal may include / transmit information regarding whether it supports RRM relaxation or cell measurement selection based on s-MeasureConfig in / with the UE capability information.

[0168] In step 1k-10, the terminal receives an RRC Reconfiguration message from the base station. The message may include settings for cell measurement (e.g., MeasConfig), and the terminal may receive s-MeasureConfig as one of its parameters. The s-MeasureConfig may indicate an RSRP (or RSRQ or SINR) threshold used by the terminal in step 1k-15 when determining whether to perform measurements on non-serving cells or neighboring cells.

[0169] In step 1k-15, the terminal may perform signal (e.g., CSI-RS, SSB) measurement for the serving cell (or SpCell) and compare the signal measurement value (e.g., RSRP) for the serving cell (or SpCell) with the configured s-MeasureConfig.

[0170] In step 1k-20, if the terminal determines that the s-MeasureConfig condition is not satisfied (i.e., if the signal measurement value for the serving cell or SpCell is less than the configured s-MeasureConfig), the terminal may perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values. Conversely, if the terminal determines that the s-MeasureConfig condition is satisfied (i.e., if the signal measurement value for the serving cell or SpCell is not less than the configured s-MeasureConfig), the terminal may not perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values.

[0171] In step 1k-25, the terminal can transmit a measurement report to the base station including only measurement results that satisfy the above s-MeasureConfig conditions.

[0172] FIG. 1l is a diagram illustrating an operation of a terminal according to an embodiment of the present disclosure to determine whether to measure a cell based on s-MeasureConfig.

[0173] In step 1l-05, the terminal can receive system information.

[0174] In step 1l-10, the terminal can camp on the cell.

[0175] In step 1l-15, the terminal can establish an RRC connection with the base station and transition to connected mode.

[0176] In step 11-17, after receiving a UE capability enquiry message from a base station, the terminal can transmit information about the terminal's capabilities to the base station through a UE capability information message.

[0177] In step 11-20, the terminal receives an RRC Reconfiguration message from the base station. The message may include settings for cell measurement (e.g., MeasConfig), and the terminal may receive s-MeasureConfig as one of its parameters. The s-MeasureConfig may indicate an RSRP (or RSRQ or SINR) threshold used by the terminal when determining whether to measure non-serving cells or neighboring cells in step 11-25.

[0178] In step 1l-25, the terminal may perform signal (e.g., CSI-RS, SSB) measurement for the serving cell (or SpCell) and compare the signal measurement value (e.g., RSRP) for the serving cell (or SpCell) with the configured s-MeasureConfig.

[0179] In step 1l-30, if the terminal determines that the s-MeasureConfig condition is not satisfied (i.e., if the measurement value for the serving cell or SpCell is less than the configured s-MeasureConfig), the terminal may perform cell measurements on the corresponding neighboring cell(s) and derive cell measurement values.

[0180] In step 1l-35, if the terminal determines that the s-MeasureConfig condition is satisfied (i.e., if the measurement value for the serving cell or SpCell is not less than the configured s-MeasureConfig), the terminal may not perform cell measurements for the corresponding neighboring cell(s) and may not derive cell measurement values.

[0181] Through this, the terminal can achieve energy savings by reducing measurements for unnecessary neighboring cells and simplifying measurement reporting when the measurement values ​​for the serving cell or SpCell are good.

[0182] FIG. 1m is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs s-MeasureConfig-based RRM relaxation using a prediction measurement result using AI / ML.

[0183] In step 1m-05, the terminal may be in connection mode with the base station.

[0184] In step 1m-07, after receiving a UE capability enquiry message from the base station, the terminal may transmit information regarding its capabilities to the base station via a UE capability information message. At this time, the terminal may report to the base station information regarding its RRM relaxation performance capability, including / along with the UE capability information, based on a comparison of the predicted cell measurement results with s-MeasureConfig.

[0185] In steps 1m-10, the terminal receives an RRC Reconfiguration message from the base station. The message may include settings for cell measurement (e.g., MeasConfig), and the terminal may receive s-MeasureConfig as one of the parameters. In addition, the terminal may receive settings related to performing RRM relaxation from the base station by comparing the predicted cell measurement results with s-MeasureConfig. In addition, the terminal may receive information from the base station regarding whether to allow performing RRM relaxation by comparing the predicted cell measurement results with s-MeasureConfig.

[0186] In steps 1m-15, the terminal may run an AI / ML model to output predicted future serving cell (or SpCell) measurement results (e.g., RSRP / RSRQ / SINR).

[0187] In steps 1m-20, the terminal may compare the measurement values ​​for the serving cell (or SpCell) obtained as a result of performing signal (e.g., CSI-RS, SSB) measurement for the serving cell (or SpCell) and / or the predicted values ​​(e.g., RSRP) for the serving cell (or SpCell) obtained as a result of performing prediction by running an AI / ML model, with the s-MeasureConfig configured from the base station. For example, the terminal may determine that the s-MeasureConfig condition is satisfied if at least one of the following conditions is satisfied.

[0188] - Condition 1. If the predicted cell measurement result satisfies the s-MeasureConfig condition. For example, if the predicted value for the serving cell or SpCell is not less than the configured s-MeasureConfig.

[0189] - Condition 2. If the actual cell measurement result satisfies the s-MeasureConfig condition. For example, if the measurement value for the serving cell or SpCell is not less than the configured s-MeasureConfig.

[0190] - Condition 3. If RRM relaxation is allowed by comparing the cell measurement results predicted from the base station with s-MeasureConfig, for example, if allowed at 1m-10.

[0191] - Condition 4. If RRM relaxation is permitted or related settings are received through comparison of actual cell measurement results with s-MeasureConfig from the base station, for example, if it is permitted or related settings are received at 1m-10.

[0192] In steps 1m-25, if the terminal determines that the s-MeasureConfig condition is not satisfied, it may perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values. Conversely, if the terminal determines that the s-MeasureConfig condition is satisfied, it may not perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values.

[0193] In step 1m-30, the terminal can transmit a measurement report to the base station including only measurement results that satisfy the above s-MeasureConfig conditions.

[0194] In one embodiment of the present disclosure, when RRM relaxation is triggered by a predicted cell measurement result (when the s-MeasureConfig condition is satisfied), the terminal may report the predicted cell measurement value to the base station. For example, the terminal may report the predicted cell measurement value to the base station via a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message. This may be useful information when the base station configures a new s-MeasureConfig for the terminal in the future.

[0195] FIG. 1n is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs RRM relaxation through s-MeasureConfig determination / update using AI / ML.

[0196] In step 1n-05, the terminal may be in a connection mode with the base station.

[0197] In step 1n-07, after receiving a UE capability enquiry message from the base station, the terminal may transmit information about its capabilities to the base station via a UE capability information message. At this time, the terminal may report to the base station information about its capabilities for determining / updating s-MeasureConfig values ​​by including / along with the UE capability information.

[0198] In step 1n-10, the terminal receives an RRC Reconfiguration message from the base station. The message may include settings for cell measurement (e.g., MeasConfig), and the terminal may receive s-MeasureConfig as one of its parameters. The s-MeasureConfig may indicate an RSRP (or RSRQ or SINR) threshold used by the terminal in step 1n-20 when determining whether to measure non-serving cells or neighboring cells. In addition, the terminal may receive information from the base station regarding whether to allow determination / update of the s-MeasureConfig value.

[0199] In steps 1n-15, the terminal may derive (output) an s-MeasureConfig value by running an AI / ML model. At this time, the s-MeasureConfig value set by the base station may be used as one of the input values ​​of the AI / ML model. In one embodiment of the present disclosure, the terminal may report the derived s-MeasureConfig value to the base station. For example, the terminal may report the derived s-MeasureConfig value to the base station through a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message. Through this, the base station may obtain information about the s-MeasureConfig value used by the terminal and utilize it for network configuration.

[0200] In steps 1n-20, the terminal may compare the measurement values ​​(e.g., RSRP) for the serving cell (or SpCell) obtained as a result of performing measurements on signals (e.g., CSI-RS, SSB) for the serving cell (or SpCell) with the newly derived s-MeasureConfig by running an AI / ML model. For example, the terminal may determine that the s-MeasureConfig condition is satisfied if at least one of the following conditions is satisfied.

[0201] - Condition 1. If the actual measured or predicted cell measurement results satisfy the derived s-MeasureConfig condition. For example, if the measurement value for the serving cell or SpCell is not less than the derived s-MeasureConfig.

[0202] - Condition 2. If the decision / update of the s-MeasureConfig value is permitted from the base station or if the related settings are received, for example, if the decision / update is permitted from 1n-10 or if the related settings are received.

[0203] In step 1n-25, if the terminal determines that the s-MeasureConfig condition is not satisfied, it may perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values. Conversely, if the terminal determines that the s-MeasureConfig condition is satisfied, it may not perform cell measurement on the corresponding neighboring cell(s) and derive cell measurement values.

[0204] In step 1n-30, the terminal can transmit a measurement report to the base station including only measurement results that satisfy the above s-MeasureConfig conditions.

[0205] FIG. 1o is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure uses AI / ML to determine whether RRM relaxation is performed and performs RRM relaxation through this.

[0206] In step 1o-05, the terminal may be in a connection mode with the base station.

[0207] In step 1o-07, after receiving a UE capability inquiry message from the base station, the terminal may transmit information regarding its capabilities to the base station via a UE capability information message. At this time, the terminal may use AI / ML to derive whether to perform RRM relaxation and include / report to the base station information regarding its capabilities regarding its use in the UE capability information.

[0208] In step 1o-10, the terminal receives an RRC Reconfiguration message from the base station. The message may include settings for cell measurement (e.g., MeasConfig), and the terminal may receive s-MeasureConfig as one of its parameters. The s-MeasureConfig may indicate an RSRP (or RSRQ or SINR) threshold used by the terminal in step 1o-20 when determining whether to perform measurement on the serving cell. In addition, the terminal may use AI / ML to derive whether to perform RRM relaxation and receive information from the base station regarding whether to allow its use.

[0209] In steps 1o-15, the terminal may drive an AI / ML model to determine whether RRM relaxation is performed (output). In one embodiment of the present disclosure, the terminal may use the s-MeasureConfig value set by the base station as one of the input values ​​of the AI / ML model.

[0210] In steps 1o-20, the terminal may determine whether to perform RRM relaxation based on whether the derived RRM relaxation is performed. For example, the terminal may determine that the RRM relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0211] - Condition 1. If “RRM relaxation is performed” is derived

[0212] - Condition 2. If permission is obtained from the base station to perform RRM relaxation and use it or if related settings are received, for example, if permission is obtained from 1o-10 or if related settings are received

[0213] If the terminal determines that the above RRM relaxation condition is not satisfied, it may perform cell measurement on the corresponding surrounding cell(s) and derive cell measurement values. Conversely, if the terminal determines that the above RRM relaxation condition is satisfied, it may not perform cell measurement on the corresponding surrounding cell(s) and derive cell measurement values.

[0214] In step 1o-25, the terminal may transmit a measurement report to the base station including only measurement results that satisfy the RRM relaxation condition.

[0215] FIG. 1p is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs relaxation condition-based RRM relaxation.

[0216] In step 1p-05, the terminal may be in a connection mode with the base station.

[0217] In step 1p-07, after receiving a UE capability enquiry message from a base station, the terminal may transmit information about its capabilities to the base station through a UE capability information message. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information regarding whether it supports RRM relaxation in connected mode, in the UE capability information. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information regarding whether it supports reporting on whether relaxation conditions (e.g., stationary conditions) are satisfied, in the UE capability information.

[0218] In steps 1p-10, the terminal may receive relaxation conditions and related parameters (e.g., thresholds for reading stationary conditions) from the base station via an RRC Reconfiguration message. In addition, the terminal may receive cell measurement configurations (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via the RRC Reconfiguration message.

[0219] In step 1p-15, the terminal can perform measurements on signals (e.g., CSI-RS, SSB) for the serving cell (or SpCell) and determine whether the relaxation condition (e.g., stationary condition) set through the measurements (e.g., RSRP, RSRQ, SINR) for the serving cell (or SpCell) is satisfied.

[0220] In one embodiment of the present disclosure, after step 1p-15, the terminal / base station may perform Option 1 (1p-20, 1p-25) and may not perform Option 2 (1p-30).

[0221] In one embodiment of the present disclosure, after step 1p-15, the terminal / base station may perform Option 2 (1p-30) and may not perform Option 1 (1p-20, 1p-25).

[0222] In steps 1p-20, if the terminal determines that the relaxation condition is not satisfied (e.g., if the variation in the measurement values ​​for the serving cell or SpCell is large), it may report to the base station that the relaxation condition is not satisfied. For example, the terminal may report to the base station that it does not include an indicator indicating whether the relaxation condition is satisfied or indicates it as false.

[0223] Conversely, if the terminal determines that the relaxation condition is satisfied (e.g., if the variation in the measurement values ​​for the serving cell or SpCell is small), it can report to the base station that the relaxation condition is satisfied. For example, the terminal can report to the base station by including an indicator indicating whether the relaxation condition is satisfied or indicating it as true.

[0224] In step 1p-25, if the base station receives a report from the terminal that the relaxation condition is satisfied, the base station may provide the terminal with a more relaxed cell measurement configuration (e.g., cell measurement configuration 2) than the cell measurement configuration 1 set in step 1p-10 (e.g., via an RRC Reconfiguration message). Conversely, if the base station receives a report from the terminal that the relaxation condition is not satisfied, the base station may not provide the terminal with a relaxed cell measurement configuration (e.g., cell measurement configuration 2) (e.g., via an RRC Reconfiguration message).

[0225] In step 1p-30, if the terminal determines that the relaxation condition is not satisfied (e.g., if the amount of change in the measurement value for the serving cell or SpCell is large), the terminal may perform normal measurement according to cell measurement configuration 1. Conversely, if the terminal determines that the relaxation condition is satisfied (e.g., if the amount of change in the measurement value for the serving cell or SpCell is small), the terminal may perform relaxed measurement according to cell measurement configuration 1 (e.g., measure only some of the measurements corresponding to the measurement object or measurement identity set in cell measurement configuration 1, or perform measurement and reporting at a longer cycle than the reporting configuration cycle set in cell measurement configuration 1).

[0226] FIG. 1q is a diagram illustrating an operation of a terminal performing relaxed measurement based on a relaxation condition or reporting whether a relaxation condition is satisfied, according to an embodiment of the present disclosure.

[0227] In step 1q-05, the terminal can receive system information.

[0228] In step 1q-10, the terminal can camp on the cell.

[0229] In step 1q-15, the terminal can establish an RRC connection with the base station and transition to connected mode.

[0230] In step 1q-17, after receiving a UE capability enquiry message from a base station, the terminal may transmit information about its capabilities to the base station through a UE capability information message. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information regarding whether it supports RRM relaxation in connected mode, in the UE capability information. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information regarding whether it supports reporting on whether relaxation conditions (e.g., stationary conditions) are satisfied, in the UE capability information.

[0231] In step 1q-20, the terminal may receive relaxation conditions and related parameters (e.g., thresholds for reading stationary conditions) from the base station via an RRC Reconfiguration message. In addition, the terminal may receive cell measurement configuration (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via the RRC Reconfiguration message.

[0232] In step 1q-25, the terminal can perform measurements on signals (e.g., CSI-RS, SSB) for the serving cell (or SpCell) and determine whether the relaxation condition (e.g., stationary condition) set through the measurements (e.g., RSRP, RSRQ, SINR) for the serving cell (or SpCell) is satisfied.

[0233] In one embodiment of the present disclosure, after step 1q-25, the terminal / base station may perform Option 1 in 1q-30 and 1q-35, and may not perform Option 2 in 1q-30 and 1q-35.

[0234] In one embodiment of the present disclosure, after step 1p-15, the terminal / base station may perform Option 2 in 1q-30 and 1q-35, and may not perform Option 1 in 1q-30 and 1q-35.

[0235] In step 1q-30, if the terminal determines that the relaxation condition is satisfied, it can report to the base station that the relaxation condition is satisfied as Option 1. For example, the terminal can report to the base station by including an indicator indicating whether the relaxation condition is satisfied or indicating true. If the terminal determines that the relaxation condition is satisfied, it can perform relaxed measurement of cell measurement configuration 1 as Option 2 (e.g., measuring only some of the measurements corresponding to the measurement object or measurement identity set in cell measurement configuration 1, or performing measurement and reporting at a longer cycle than the reporting configuration cycle set in cell measurement configuration 1).

[0236] In step 1q-35, if the terminal determines that the relaxation condition is not satisfied, it can report to the base station that the relaxation condition is not satisfied as Option 1. For example, the terminal can report to the base station by omitting / not including the relaxation condition satisfaction indicator or indicating it as false. If the terminal determines that the relaxation condition is not satisfied, it can perform normal measurements according to cell measurement configuration 1 as Option 2.

[0237] FIG. 1r is a diagram illustrating a process in which a terminal in a connection mode according to one embodiment of the present disclosure performs RRM relaxation based on relaxation conditions using a prediction measurement result using AI / ML.

[0238] In step 1r-05, the terminal may be in a connection mode with the base station.

[0239] In step 1r-07, after receiving a UE capability enquiry message from a base station, the terminal may transmit information about the terminal's capabilities to the base station through a UE capability information message. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information on whether it supports RRM relaxation in connected mode, in the UE capability information. At this time, the terminal (e.g., RedCap terminal) may include / transmit to the base station information on whether it supports reporting on whether a relaxation condition (e.g., stationary condition) is satisfied, in the UE capability information. At this time, the terminal may include / report to the base station information on the RRM relaxation performance capability using predicted cell measurement results, in the UE capability information.

[0240] In step 1r-10, the terminal can receive relaxation conditions and related parameters (e.g., thresholds for reading stationary conditions) from the base station via an RRC Reconfiguration message. In addition, the terminal can receive cell measurement configuration (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via the RRC Reconfiguration message. In addition, the terminal can receive settings related to performing RRM relaxation using predicted cell measurement results (e.g., RRM relaxation conditions) from the base station. In addition, the terminal can receive information from the base station regarding whether to allow performing RRM relaxation using predicted cell measurement results.

[0241] In step 1r-15, the terminal can run an AI / ML model to output predicted future serving cell (or SpCell) measurement results (e.g., RSRP / RSRQ / SINR).

[0242] In step 1r-20, the terminal may determine the relaxation condition set by the base station using the measurement value for the serving cell (or SpCell) obtained as a result of performing signal (e.g., CSI-RS, SSB) measurement for the serving cell (or SpCell) and / or the predicted value (e.g., RSRP, RSRQ, SINR) for the serving cell (or SpCell) obtained as a result of performing prediction by running an AI / ML model. For example, the terminal may determine that the relaxation condition is satisfied if at least one of the following conditions is satisfied.

[0243] - Condition 1. If the predicted cell measurement results satisfy the relaxation condition.

[0244] - Condition 2. When the actual cell measurement results satisfy the relaxation condition.

[0245] - Condition 3. If permission is granted or related settings are set for performing RRM relaxation using cell measurement results predicted from the base station, for example, if permission is granted or related settings are set in 1r-10.

[0246] - Condition 4. If permission is received from the base station to perform RRM relaxation using actual cell measurement results, for example, permission is received in 1r-10 or related settings are received.

[0247] In one embodiment of the present disclosure, after step 1r-20, the terminal / base station may perform Option 1 (1r-25, 1r-30) and may not perform Option 2 (1r-35).

[0248] In one embodiment of the present disclosure, after step 1r-20, the terminal / base station may perform Option 2 (1r-35) and may not perform Option 1 (1r-25, 1r-30).

[0249] In step 1r-25, if the terminal determines that the relaxation condition is not satisfied (e.g., if the variation in the measurement values ​​for the serving cell or SpCell is large), it may report to the base station that the relaxation condition is not satisfied. For example, the terminal may report to the base station that it does not include an indicator indicating whether the relaxation condition is satisfied or indicates it as false.

[0250] Conversely, if the terminal determines that the relaxation condition is satisfied (e.g., if the variation in the measurement values ​​for the serving cell or SpCell is small), it can report this fact to the base station. For example, the terminal can report to the base station whether the relaxation condition is satisfied by including an indicator indicating whether the relaxation condition is satisfied or indicating it as true.

[0251] In step 1r-30, if the base station receives a report from the terminal that the relaxation condition is satisfied, the base station may provide the terminal with a more relaxed cell measurement configuration (e.g., cell measurement configuration 2) than the cell measurement configuration 1 set in step 1r-10 (e.g., via an RRC Reconfiguration message). Conversely, if the base station receives a report from the terminal that the relaxation condition is not satisfied, the base station may not provide the terminal with a relaxed cell measurement configuration (e.g., cell measurement configuration 2) (e.g., via an RRC Reconfiguration message).

[0252] In step 1r-35, if the terminal determines that the relaxation condition is not satisfied (e.g., if the amount of change in the measurement value for the serving cell or SpCell is large), the terminal may perform normal measurement according to cell measurement configuration 1. Conversely, if the terminal determines that the relaxation condition is satisfied (e.g., if the amount of change in the measurement value for the serving cell or SpCell is small), the terminal may perform relaxed measurement according to cell measurement configuration 1 (e.g., measure only some of the measurements corresponding to the measurement object or measurement identity set in cell measurement configuration 1, or perform measurement and reporting at a longer cycle than the reporting configuration cycle set in cell measurement configuration 1).

[0253] In one embodiment of the present disclosure, a terminal may indicate, upon measurement reporting (e.g., 1k-25), whether the terminal has performed AI / ML-based RRM relaxation or relaxed measurement. Upon receiving the measurement report, the base station may be informed of the terminal's performance of RRM relaxation or relaxed measurement, and may calculate the impact on the network and terminal, thereby utilizing this information for network optimization and resource management.

[0254] In one embodiment of the present disclosure, a terminal may store, as RLF report information, whether it performed AI / ML-based RRM relaxation or relaxed measurement in the event of a radio link failure (RLF) or handover failure (HOF) and report this to a base station. This information may be helpful for the base station to determine that the cause of the RLF or HOF was due to the RRM relaxation of the terminal.

[0255] In one embodiment of the present disclosure, the RRM relaxation method performed by the terminal may differ depending on whether the terminal satisfies any RRM relaxation condition.

[0256] For example, the relaxed measurement period used in step 1g-25 of FIG. 1g when the terminal satisfies one condition (e.g., condition 1) in step 1g-20 of FIG. 1g may be different from the relaxed measurement period used in step 1g-25 of FIG. 1g when the terminal satisfies another condition (e.g., condition 3) in step 1g-20 of FIG. 1g.

[0257] For example, if the terminal satisfies one condition (e.g., condition 3) in step 1g-20 of FIG. 1g, the relaxed measurement period used in step 1g-25 of FIG. 1g may be longer than if the terminal satisfies multiple conditions (e.g., condition 1 and condition 3) in step 1g-20 of FIG. 1g.

[0258] In one embodiment of the present disclosure, information derived as an output value of an AI / ML model (e.g., predicted cell measurement value, RRM relaxation condition, parameters related to RRM relaxation condition, whether RRM relaxation is performed, RRM relaxation method), along with the accuracy and / or occurrence probability of the corresponding information derived as an output value, can be derived as an output value of the AI / ML model.

[0259] According to one embodiment of the present disclosure, a terminal may perform RRM relaxation using the information derived as an output value only if the accuracy and / or occurrence probability of the information derived as an output value is greater than a specific threshold value (e.g., a variable value set by the network or a fixed value defined by a standard). Otherwise, the terminal may not perform RRM relaxation using the information derived as an output value.

[0260] In one embodiment of the present disclosure, a terminal may perform RRM relaxation related operations for neighboring cells based on measurement values ​​(e.g., RSRP and / or RSRQ and / or SINR) of a serving cell.

[0261] In one embodiment of the present disclosure, a terminal may perform RRM relaxation-related operations for a specific cell (e.g., cell 1) based on measurement values ​​(e.g., RSRP and / or RSRQ and / or SINR) of the same cell. It may be most accurate to determine whether to perform RRM relaxation for a specific cell based on the measurement results for the specific cell.

[0262] For example, if the change in the measurement value for the serving cell is small (e.g., because it satisfies the low-mobility criterion), performing RRM relaxation (e.g., by increasing the measurement period) on the neighboring cells may include the assumption that the neighboring cells will also not experience significant changes compared to their currently measured values. However, even if the change in the measurement value for the serving cell is small, the actual measurement value for the neighboring cells may change significantly. In this case, performing RRM relaxation on the neighboring cells may cause the UE to make incorrect judgments about the neighboring cells (e.g., an inactive or idle UE may perform RRM relaxation when its RSRP value for a neighboring cell decreases rapidly, but may not obtain the latest RSRP value for that cell, and may reselect and camp on that cell). Therefore, it may be desirable to determine whether to perform RRM relaxation on a neighboring cell based on the measurement value for that cell. Similarly, it is possible to determine whether to perform RRM relaxation for a serving cell based on measurements for that serving cell. This allows the UE to determine and perform different RRM relaxation methods (e.g., different measurement cycles) for each cell.

[0263] [Revised 26.05.2025 under Rule 91] Figure 1s is a block diagram showing the internal structure of a terminal (1s-00) according to one embodiment of the present disclosure.

[0264] [Revised 26.05.2025 under Rule 91] Referring to FIG. 1s, a terminal (1s-00) according to an embodiment of the present disclosure may include an RF (radio frequency) processing unit (1s-10), a baseband processing unit (1s-20), a storage unit (1s-30), and a control unit (1s-40).

[0265] [Revised 26.05.2025 by Article 91 of the Rules] The RF processing unit (1s-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (1s-10) up-converts the baseband signal provided from the baseband processing unit (1s-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (1s-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital to analog convertor (DAC), an analog to digital convertor (ADC), etc. In Fig. 1s, only one antenna is illustrated, but the terminal may be equipped with multiple antennas. In addition, the RF processing unit (1s-10) may include multiple RF chains. Furthermore, the RF processing unit (1s-10) can perform beamforming. For the beamforming, the RF processing unit (1s-10) can adjust the phase and magnitude of each signal transmitted and received through multiple antennas or antenna elements. In addition, the RF processing unit can perform MIMO, and can receive multiple layers when performing the MIMO operation.

[0266] [Revised 26.05.2025 by Article 91 of the Rules] The baseband processing unit (1s-20) performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the baseband processing unit (1s-20) generates complex symbols by encoding and modulating the transmission bit stream. In addition, when receiving data, the baseband processing unit (1s-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (1s-10). For example, in the case of OFDM (orthogonal frequency division multiplexing), when transmitting data, the baseband processing unit (1s-20) generates complex symbols by encoding and modulating a transmission bit stream, maps the complex symbols to subcarriers, and then configures OFDM symbols through an inverse fast Fourier transform (IFFT) operation and a cyclic prefix (CP) insertion. In addition, when receiving data, the baseband processing unit (1s-20) divides the baseband signal provided from the RF processing unit (1s-10) into OFDM symbol units, restores signals mapped to subcarriers through an FFT (fast Fourier transform) operation, and then restores the received bit stream through demodulation and decoding.

[0267] [Revised 26.05.2025 by Article 91 of the Rules] The baseband processing unit (1s-20) and the RF processing unit (1s-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (1s-20) and the RF processing unit (1s-10) may be referred to as a transmitter, a receiver, a transceiver, or a communication unit. Furthermore, at least one of the baseband processing unit (1s-20) and the RF processing unit (1s-10) may include a plurality of communication modules to support a plurality of different wireless access technologies. In addition, at least one of the baseband processing unit (1s-20) and the RF processing unit (1s-10) may include different communication modules to process signals of different frequency bands. For example, the different wireless access technologies may include wireless LAN (e.g., IEEE 802.11), cellular networks (e.g., LTE), etc. In addition, the different frequency bands may include super high frequency (SHF) (e.g., 2.NRHz, NRhz) bands, millimeter wave (mm wave) (e.g., 60GHz) bands.

[0268] [Revised 26.05.2025 under Article 91 of the Rules] The storage unit (1s-30) stores data such as basic programs, application programs, and setting information for the operation of a terminal (1s-00) according to one embodiment of the present disclosure. In particular, the storage unit (1s-30) may store information related to a second access node that performs wireless communication using a second wireless access technology. In addition, the storage unit (1s-30) provides the stored data upon request from the control unit (1s-40). The storage unit (1s-30) may be referred to as a memory.

[0269] [Revised 26.05.2025 by Article 91 of the Rules] The control unit (1s-40) controls the overall operations of the terminal (1s-00). For example, the control unit (1s-40) transmits and receives signals through the baseband processing unit (1s-20) and the RF processing unit (1s-10). In addition, the control unit (1s-40) records and reads data in the storage unit (1s-30). For this purpose, the control unit (1s-40) may include at least one processor. For example, the control unit (1s-40) may include a communication processor (CP) that performs control for communication and an application processor (AP) that controls upper layers such as application programs. The control unit (1s-40) can control the overall operation of the terminal (1s-00) according to the embodiments proposed in the present disclosure by executing one or more commands stored in the memory (1s-30).

[0270] [Revised 26.05.2025 by Rule 91] The processor (1s-40) may include various processing circuits and / or multiple processors. For example, the term “processor” as used herein, including in the claims, may include various processing circuits, including at least one processor. One or more processors in at least one processor may be configured to perform various functions described herein, individually and / or collectively, in a distributed manner. As used herein, “processor,” “at least one processor,” and “one or more processors” may be configured to perform multiple functions. However, these terms encompass, without limitation, situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor may perform all of the functions. Furthermore, at least one processor may include a combination of processors that perform various of the disclosed functions in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions.

[0271] [Revised on May 26, 2025, pursuant to Article 91 of the Rules] In one embodiment, at least one processor (1s-40) may be a general-purpose processor, such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-only processor, such as a GPU or VPU (Vision Processing Unit), or an artificial intelligence-only processor, such as an NPU. For example, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0272] The predefined operation rules or artificial intelligence model are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model (or deep learning model) is trained using a plurality of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0273] An artificial intelligence model (or deep learning model) may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0274] [Revised 26.05.2025 under Rule 91] Figure 1t is a block diagram showing the configuration of a base station (1t-00) according to one embodiment of the present disclosure.

[0275] [Revised 26.05.2025 by Rule 91] Referring to FIG. 1t, a base station (1t-00) according to one embodiment of the present disclosure may include an RF processing unit (1t-10), a baseband processing unit (1t-20), a backhaul communication unit (1t-30), a storage unit (1t-40), and a control unit (1t-50).

[0276] [Revised 26.05.2025 by Article 91 of the Rules] The RF processing unit (1t-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (1t-10) up-converts the baseband signal provided from the baseband processing unit (1t-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (1t-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc. In the drawing, only one antenna is shown, but the first access node may have multiple antennas. In addition, the RF processing unit (1t-10) may include multiple RF chains. Furthermore, the RF processing unit (1t-10) may perform beamforming. For the above beamforming, the RF processing unit (1t-10) can adjust the phase and magnitude of each signal transmitted and received through multiple antennas or antenna elements. The RF processing unit can perform a downlink MIMO operation by transmitting one or more layers.

[0277] [Revised 26.05.2025 by Article 91 of the Rules] The baseband processing unit (1t-20) performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the first wireless access technology. For example, when transmitting data, the baseband processing unit (1t-20) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (1t-20) restores the reception bit stream by demodulating and decoding the baseband signal provided from the RF processing unit (1t-10). For example, in the case of OFDM, when transmitting data, the baseband processing unit (1t-20) generates complex symbols by encoding and modulating a transmission bit stream, maps the complex symbols to subcarriers, and then configures OFDM symbols through IFFT operation and CP insertion. In addition, when receiving data, the baseband processing unit (1t-20) divides the baseband signal provided from the RF processing unit (1t-10) into OFDM symbol units, restores the signals mapped to subcarriers through FFT operation, and then restores the received bit string through demodulation and decoding. The baseband processing unit (1t-20) and the RF processing unit (1t-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (1t-20) and the RF processing unit (1t-10) may be referred to as a transmitter, a receiver, a transceiver, a communication unit, or a wireless communication unit.

[0278] [Revised 26.05.2025 by Article 91 of the Rules] The backhaul communication unit (1t-30) provides an interface for communicating with other nodes within the network. That is, the backhaul communication unit (1t-30) converts a bit string transmitted from the main base station to another node, such as an auxiliary base station or core network, into a physical signal, and converts a physical signal received from the other node into a bit string.

[0279] [Revised 26.05.2025 by Article 91 of the Rules] The storage unit (1t-40) stores data such as basic programs, application programs, and setting information for the operation of the base station (1t-00). In particular, the storage unit (1t-40) can store information on bearers assigned to connected terminals, measurement results reported from connected terminals, and the like. In addition, the storage unit (1t-40) can store information that serves as a judgment criterion for whether to provide or terminate multiple connections to a terminal. In addition, the storage unit (1t-40) provides the stored data upon request from the control unit (1t-50). The storage unit (1t-40) may be referred to as a memory.

[0280] [Revised 26.05.2025 by Article 91 of the Rules] The control unit (1t-50) controls the overall operations of the base station (1t-00). For example, the control unit (1t-50) transmits and receives signals through the baseband processing unit (1t-20) and the RF processing unit (1t-10) or through the backhaul communication unit (1t-30). In addition, the control unit (1t-50) records and reads data in the storage unit (1t-40). For this purpose, the control unit (1t-50) may include at least one processor. The control unit (1t-50) may control the overall operations of the base station (1t-00) according to the embodiments proposed in the present disclosure by executing one or more commands stored in the memory (1t-40).

[0281] [Revised 26.05.2025 by Rule 91] The processor (1t-50) may include various processing circuits and / or multiple processors. For example, the term “processor” as used herein, including in the claims, may include various processing circuits, including at least one processor. One or more processors in at least one processor may be configured to perform various functions described herein, individually and / or collectively, in a distributed manner. As used herein, “processor,” “at least one processor,” and “one or more processors” may be configured to perform multiple functions. However, these terms encompass, without limitation, situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor may perform all of the functions. Furthermore, at least one processor may include a combination of processors that perform various of the disclosed functions in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions.

[0282] [Revised on May 26, 2025, pursuant to Article 91 of the Rules] In one embodiment, at least one processor (1t-50) may be a general-purpose processor, such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-only processor, such as a GPU or VPU (Vision Processing Unit), or an artificial intelligence-only processor, such as an NPU. For example, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0283] The predefined operation rules or artificial intelligence model are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model (or deep learning model) is trained using a plurality of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0284] An artificial intelligence model (or deep learning model) may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0285] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed in the singular or plural form, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in the plural form may be composed of singular elements, or components expressed in the singular form may be composed of plural elements.

[0286] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims described below, but also by equivalents thereof.

[0287] A specific example for explaining an embodiment according to the present disclosure is only one combination of each criterion, method, detailed method, and operation, and through a combination of at least two or more techniques among the various techniques described, a terminal or base station can perform an AI / ML-based relaxed RRM (Radio Resource Measurement) operation in a next-generation mobile communication system. In addition, at this time, the operation may be performed according to a method determined through one or a combination of at least two or more of the above-described techniques. For example, it may be possible to perform a part of the operation of one embodiment in combination with a part of the operation of another embodiment.

[0288] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, a 'non-transitory storage medium' means only that it is a tangible device and does not contain signals (e.g., electromagnetic waves), and this term does not distinguish between cases where data is permanently stored in the storage medium and cases where it is temporarily stored. For example, a 'non-transitory storage medium' may include a buffer in which data is temporarily stored. In one embodiment, the method according to various embodiments disclosed in the present document may be provided as a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read only memory (CD-ROM)), or may be distributed online (e.g., by download or upload) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be temporarily stored or temporarily created in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

Claims

1. In a wireless communication system, a method of UE (user equipment), A step of obtaining AI / ML-based RRM (Radio Resource Measurement) relaxation-related setting information from a base station; A step of obtaining information including predicted cell measurement results using AI / ML; A step of determining whether at least one RRM relaxation condition is satisfied based on information including the predicted cell measurement results; and A method comprising: performing relaxed RRM measurement or normal RRM measurement based on the above determination.

2. In the method of paragraph 1, A method further comprising: receiving information indicating whether to allow AI / ML-based RRM relaxation performance from the base station.

3. In the method of paragraph 1, A step of obtaining parameters associated with the RRM relaxation condition or the RRM relaxation condition itself using the above AI / ML; and A method further comprising: a step of performing the relaxed RRM measurement or the normal RRM measurement based on parameters related to the acquired RRM relaxation condition or the acquired RRM relaxation condition itself.

4. In the method of the third clause, the parameters associated with the RRM relaxation condition are: Parameters indicating measurement-related thresholds for the serving cell; or A method comprising at least one of the parameters included in the AI / ML-based RRM-related setting information.

5. In the method of paragraph 1, A step of obtaining information indicating whether to perform RRM relaxation using the above AI / ML; and A method further comprising: a step of performing the relaxed RRM measurement or the normal RRM measurement based on the information indicating whether to perform the acquired RRM relaxation.

6. In the method of paragraph 1, A step of obtaining information related to the RRM relaxation method using the above AI / ML; The information related to the RRM relaxation method includes at least one of information about a measurement period, information about a measurement frequency, or information about a relaxation activation time interval; If information related to the RRM relaxation method is successfully obtained, a step of performing the relaxed RRM measurement based on the information related to the obtained RRM relaxation method; and A method further comprising: a step of performing the normal RRM measurement when obtaining information related to the RRM relaxation method fails.

7. In any one of the methods of paragraphs 1 to 6, The above UE is in an inactive or idle state, and The step of obtaining the AI / ML-based RRM relaxation-related setting information from the base station is as follows: A method comprising: obtaining system information including AI / ML-based RRM relaxation-related setting information from the base station.

8. In any one of the methods of paragraphs 1 to 5, The above UE is in a connected state, and The step of obtaining the AI / ML-based RRM relaxation-related setting information from the base station is as follows: A step of transmitting UE capability information including information on AL / ML-based RRM relaxation-related capabilities to the base station; and A method further comprising: receiving an RRC reconfiguration message including the AI / ML-based RRM relaxation-related configuration information from the base station.

9. In the method of paragraph 1, when performing the relaxed RRM measurement, A method further comprising: a step of transmitting information indicating that relaxed RRM measurement has been performed to the base station through a measurement report, an RLF (Radio Link Failure) report, or an HOF (Handover Failure) report.

10. In the method of paragraph 1, Based on which of the above at least one RRM relaxation condition is satisfied, information related to the RRM relaxation method applied when performing the relaxed RRM measurement is determined, and A method wherein the information related to the RRM relaxation method includes at least one of information about a measurement period, information about a measurement frequency, or information about a relaxation activation time interval.

11. In the method of paragraph 1, When acquiring information using the above AI / ML, the accuracy of the acquired information is also derived, and A method further comprising: performing the relaxed RRM measurement using information obtained using the AI / ML when the accuracy exceeds a specific threshold.

12. In a wireless communication system, in UE (user equipment), memory for storing one or more instructions; and At least one processor; wherein the at least one processor executes the one or more instructions stored in the memory by: Obtain AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information from the base station; Using AI / ML, information including predicted cell measurement results is obtained; Based on information including the predicted cell measurement results, determining whether at least one RRM relaxation condition is satisfied; and Based on the above decision, the UE performs relaxed RRM measurement or normal RRM measurement.

13. In the UE of paragraph 12, the at least one processor further executes one or more instructions stored in the memory: A UE receiving information from the base station indicating whether to allow AI / ML-based RRM relaxation performance.

14. In a method of a base station in a wireless communication system, A step of broadcasting AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information to a UE (user equipment) through system information or transmitting it through an RRC reconfiguration message; and A method comprising: receiving, from the UE, at least one of: information including a cell measurement result predicted using AI / ML; parameters associated with an RRM relaxation condition predicted using AI / ML; or information indicating that relaxed RRM measurement has been performed.

15. In a base station in a wireless communication system, memory for storing one or more instructions; and At least one processor; wherein the at least one processor executes the one or more instructions stored in the memory by: To UE (user equipment), AI / ML-based RRM (Radio Resource Measurement) relaxation-related configuration information is broadcasted through system information or transmitted through an RRC reconfiguration message; and A base station receiving, from the UE, at least one of: information including a cell measurement result predicted using AI / ML; parameters associated with an RRM relaxation condition predicted using AI / ML; or information indicating that relaxed RRM measurement has been performed.

Images