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

Abstract

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

Description

Technical Field

[0001] This disclosure relates to the operation of terminals and base stations in wireless communication systems, and more specifically, to methods and apparatus for performing relaxed radio resource measurement (RRM) operations in next-generation mobile communication systems using artificial intelligence / machine learning (AI / ML) based terminals. Background Technology

[0002] Throughout successive generations of wireless communication, technologies have been developed primarily for human-centric services such as voice, multimedia, and data services. With the commercialization of fifth-generation (5G) communication systems, a rapidly growing number of connected devices are expected to connect to communication networks. Examples of objects connected to the network can include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction machinery, and factory equipment. Mobile devices are expected to evolve into various form factors, such as augmented reality glasses, virtual reality headsets, or holographic devices. In the sixth-generation (6G) communication era, efforts are underway to develop advanced 6G communication systems that will connect hundreds of billions of devices and objects to provide a diverse range of services. For this purpose, 6G communication systems are referred to as "super 5G" systems.

[0003] The 6G communication system, expected to be realized around 2030, is projected to achieve a maximum transmission rate of terabits per second (Tbps) (i.e., 1000 gigabits per second) and a radio latency of 100 microseconds (μsec). In other words, compared to 5G communication systems, 6G communication systems will have a transmission rate 50 times faster and radio latency reduced to one-tenth.

[0004] To achieve such high data transmission rates and ultra-low latency, 6G communication systems have been considered for implementation in the terahertz band (e.g., from 95 GHz to 3 THz). In the terahertz band, due to more severe path loss and atmospheric absorption compared to the millimeter-wave (mmWave) band introduced in 5G, technologies to ensure signal arrival (i.e., coverage) are expected to become increasingly important. As key technologies for ensuring coverage, the development of radio frequency (RF) components, antennas, novel waveforms with better coverage performance than orthogonal frequency division multiplexing (OFDM), and multi-antenna transmission technologies such as beamforming, massive MIMO, full-dimensional MIMO (FD-MIMO), array antennas, or massive MIMO is required. Furthermore, new technologies for improving the coverage of terahertz band signals have been discussed, such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing technologies using orbital angular momentum (OAM), or reconfigurable smart surfaces (RIS).

[0005] Furthermore, to improve frequency efficiency and system networks, the following technologies have been developed for 6G communication systems: full-duplex technology enabling uplink and downlink to use the same frequency resources simultaneously; network technologies for integrated utilization of satellites, high-altitude platform stations (HAPS), etc.; innovative network architecture technologies to support mobile base stations and achieve network operation optimization and automation; dynamic spectrum sharing technology for conflict avoidance based on spectrum usage prediction; AI-based communication technologies for system optimization and internalization of end-to-end AI support functions by using AI from the design stage; and next-generation distributed computing technologies for enabling services with complexity exceeding terminal computing capabilities by using ultra-high-performance communication and computing resources (mobile edge computing (MEC), cloud, etc.). In addition, continuous efforts are being made to further enhance connectivity between devices, further optimize networks, promote the software implementation of network entities, and increase the openness of wireless communication by designing new protocols for use in 6G communication systems, developing mechanisms for achieving hardware-based secure environments and secure data usage, and developing technologies for privacy maintenance methods.

[0006] The research and development of 6G communication systems is expected to enable a new dimension of hyper-connected experiences through their hyper-connectivity, encompassing connections between objects and between people and objects. Specifically, it is anticipated that 6G communication systems will provide services such as truly immersive extended reality (XR), high-fidelity mobile holograms, and digital replicas. Furthermore, with enhanced security and reliability, 6G communication systems will provide services such as remote surgery, industrial automation, and emergency response, thus expanding their application to various sectors including industry, healthcare, automotive, and home appliances. Summary of the Invention

[0007] Solution to the problem

[0008] According to an embodiment, a method performed by a user equipment (UE) in a wireless communication system is provided. The method performed by the UE may include: obtaining configuration information related to radio resource measurement (RRM) relaxation based on artificial intelligence / machine learning (AI / ML) from a base station; 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 criterion is met; and performing a relaxed RRM measurement or a normal RRM measurement based on the determination.

[0009] According to an embodiment, the method performed by the UE may further include: receiving information from the base station indicating whether AI / ML-based RRM relaxation is permitted.

[0010] According to an embodiment, the method performed by the UE may further include: acquiring parameters associated with the RRM relaxation standard or the RRM relaxation standard itself using AI / ML; and determining whether to perform a relaxed RRM measurement or a normal RRM measurement based on the acquired parameters associated with the RRM relaxation standard or the acquired RRM relaxation standard itself.

[0011] According to an embodiment, the parameters associated with the RRM relaxation criteria may include at least one of the following: parameters indicating measurement-related thresholds for the serving cell; or parameters included in the configuration information related to AI / ML-based RRM.

[0012] According to an embodiment, the method performed by the UE may further include: obtaining information indicating whether to perform RRM relaxation by using the AI / ML; and performing relaxed RRM measurement or normal RRM measurement based on the obtained information indicating whether to perform RRM relaxation.

[0013] According to an embodiment, the method performed by the UE may further include: acquiring information related to the RRM relaxation method using AI / ML; performing relaxed RRM measurements based on the acquired information related to the RRM relaxation method in response to successfully acquiring such information; and performing normal RRM measurements in response to failing to acquire such information. According to an embodiment, the information related to the RRM relaxation method may include at least one of information about the measurement period, information about the measurement frequency, or information about the relaxation activation time interval.

[0014] According to an embodiment, the UE may be in an inactive or idle state. In this case, according to an embodiment, obtaining configuration information related to AI / ML-based RRM relaxation from the base station may include obtaining system information from the base station that includes configuration information related to AI / ML-based RRM relaxation.

[0015] According to an embodiment, the UE may be in a connected state. In this case, according to an embodiment, obtaining configuration information related to AI / ML-based RRM relaxation from the base station may further include: sending UE capability information to the base station, the UE capability information including information about capabilities related to AI / ML-based RRM relaxation; and receiving a Radio Resource Control (RRC) reconfiguration message from the base station including configuration information related to AI / ML-based RRM relaxation.

[0016] According to an embodiment, the method performed by the UE may further include: in the case of performing relaxed RRM measurements, sending information indicating that relaxed RRM measurements have been performed to the base station via a measurement report, a radio link failure (RLF) report, or a handover failure (HOF) report.

[0017] According to an embodiment, information related to the RRM relaxation method to be applied when performing a relaxed RRM measurement can be determined based on which of at least one RRM relaxation criterion is met. Information related to the RRM relaxation method may include at least one of information about the measurement cycle, information about the measurement frequency, or information about the relaxation activation time interval.

[0018] According to an embodiment, when information is acquired using AI / ML, the accuracy of the acquired information can be derived. In this case, according to an embodiment, the method performed by the UE may further include: in response to the accuracy exceeding a certain threshold, performing a relaxed RRM measurement using the information acquired using AI / ML.

[0019] According to an embodiment, a UE in a wireless communication system is provided. The UE may include a memory storing one or more instructions and at least one processor. The at least one processor may execute one or more instructions stored in the memory to: obtain configuration information related to AI / ML-based RRM relaxation from a base station; obtain information including predicted cell measurement results using AI / ML; determine, based on the information including the predicted cell measurement results, whether at least one RRM relaxation criterion is met; and perform relaxed RRM measurement or normal RRM measurement based on the determination.

[0020] According to an embodiment, at least one processor can execute one or more instructions stored in memory to receive information from the base station indicating whether AI / ML-based RRM relaxation is permitted.

[0021] According to an embodiment, at least one processor can execute one or more instructions stored in memory to: obtain parameters associated with the RRM relaxation standard or the RRM relaxation standard itself using AI / ML; and determine, based on the obtained parameters associated with the RRM relaxation standard or the obtained RRM relaxation standard itself, whether to perform a relaxed RRM measurement or a normal RRM measurement.

[0022] According to an embodiment, at least one processor can execute one or more instructions stored in memory to: obtain information indicating whether to perform RRM relaxation by using the AI / ML; and perform relaxed RRM measurement or normal RRM measurement based on the obtained information indicating whether to perform RRM relaxation.

[0023] According to an embodiment, at least one processor can execute one or more instructions stored in memory to: acquire information related to the RRM relaxation method using AI / ML; perform relaxed RRM measurements based on the acquired information related to the RRM relaxation method in response to successful acquisition of such information; and perform normal RRM measurements in response to failure to acquire such information. The information related to the RRM relaxation method may include at least one of information about the measurement cycle, information about the measurement frequency, or information about the relaxation activation time interval.

[0024] According to an embodiment, the UE may be in an inactive or idle state. In this case, at least one processor may execute one or more instructions stored in memory to obtain system information from the base station, including configuration information related to AI / ML-based RRM relaxation.

[0025] According to an embodiment, the UE may be in a connected state. In this case, at least one processor may execute one or more instructions stored in memory to: send UE capability information to the base station, the UE capability information including information about capabilities related to AI / ML-based RRM relaxation; and receive an RRC reconfiguration message from the base station including configuration information related to AI / ML-based RRM relaxation.

[0026] According to an embodiment, a method performed by a base station in a wireless communication system is provided. The method performed by the base station may include: broadcasting configuration information related to AI / ML-based RRM relaxation to a UE via system information, or sending the configuration information to the UE via an RRC reconfiguration message; and receiving from the UE at least one of the following: information including cell measurement results predicted using AI / ML; parameters associated with the RRM relaxation criteria predicted using the AI / ML; or information indicating that relaxed RRM measurements have been performed.

[0027] According to an embodiment, a base station in a wireless communication system is provided. The base station may include a memory storing one or more instructions and at least one processor. The at least one processor may execute one or more instructions stored in the memory to: broadcast configuration information related to AI / ML-based RRM relaxation to a UE via system information, or send the configuration information to the UE via an RRC reconfiguration message; and receive from the UE at least one of the following: information including cell measurement results predicted using AI / ML; parameters associated with RRM relaxation criteria predicted using the AI / ML; or information indicating that relaxed RRM measurements have been performed. Attached Figure Description

[0028] Figure 1a This is a diagram illustrating the structure of a next-generation mobile communication system according to an embodiment of the present disclosure.

[0029] Figure 1b This is a diagram illustrating the radio access state transition of a terminal in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0030] Figure 1c This is a diagram illustrating the process of applying priority information for each frequency used for cell reselection to a specific terminal in a next-generation mobile communication system according to embodiments of the present disclosure, either by broadcasting priority information for each frequency used for cell reselection via a System Information Block (SIB) or by applying priority information for each frequency used for cell reselection to a specific terminal via an RRC Release (RRCRelease) message as a dedicated Radio Resource Control (RRC) signaling.

[0031] Figure 1d This is a diagram illustrating a method for performing cell reselection in a next-generation mobile communication system, executed by a terminal according to an embodiment of the present disclosure.

[0032] Figure 1e This is a diagram illustrating a method for performing relaxed radio resource measurement (RRM) measurements by a terminal and a base station according to an embodiment of the present disclosure.

[0033] Figure 1f This is a diagram illustrating an example of a process performed by a terminal, according to an embodiment of the present disclosure, to select and perform one of a normal RRM measurement or a relaxed RRM measurement.

[0034] Figure 1g This is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode according to an embodiment of the present disclosure, using predictive measurement results based on artificial intelligence / machine learning (AI / ML).

[0035] Figure 1h This is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode, according to an embodiment of the present disclosure, by using AI / ML to determine / update relaxation criteria parameters.

[0036] Figure 1i This is a diagram illustrating a process performed by a terminal in an inactive or idle mode according to an embodiment of the present disclosure, using AI / ML to determine whether to perform RRM relaxation and perform RRM relaxation accordingly.

[0037] Figure 1j This is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode, according to an embodiment of the present disclosure, using an AI / ML-based method to determine / update the relaxation.

[0038] Figure 1k This is a diagram illustrating the process of performing RRM relaxation based on s-MeasureConfig by a terminal in connected mode according to an embodiment of the present disclosure.

[0039] Figure 11 This is a diagram illustrating the operation performed by a terminal, based on s-MeasureConfig, to determine whether to perform a cell measurement according to an embodiment of the present disclosure.

[0040] Figure 1m This is a diagram illustrating a process performed by a terminal in connected mode, according to an embodiment of the present disclosure, of performing RRM relaxation based on s-MeasureConfig by predicting measurement results based on AI / ML.

[0041] Figure 1n This is a diagram illustrating the process of performing RRM relaxation by a terminal in connected mode according to an embodiment of the present disclosure, using AI / ML to determine / update s-MeasureConfig.

[0042] Figure 1o This is a diagram illustrating a process performed by a terminal in connected mode according to an embodiment of the present disclosure, using AI / ML to determine whether to perform RRM relaxation and perform RRM relaxation accordingly.

[0043] Figure 1p This is a diagram illustrating the process of performing RRM relaxation based on a relaxed standard, executed by a terminal in connected mode according to an embodiment of the present disclosure.

[0044] Figure 1q This is a diagram illustrating the operation performed by a terminal according to an embodiment of the present disclosure, performing a relaxed RRM measurement or reporting on whether the relaxed criteria are met.

[0045] Figure 1r This is a diagram illustrating a process performed by a terminal in connected mode, according to an embodiment of the present disclosure, of performing RRM relaxation based on a relaxation standard using AI / ML-based predictive measurement results.

[0046] Figure 1s This is a block diagram illustrating the structure of a terminal according to an embodiment of the present disclosure.

[0047] Figure 1t This is a block diagram illustrating the structure of a base station according to an embodiment of the present disclosure. Detailed Implementation

[0048] The operating principles of this disclosure will now be described in detail with reference to the accompanying drawings. In describing this disclosure, detailed descriptions of relevant known functions or configurations may be omitted where such omissions would unnecessarily obscure the essence of the disclosure. Furthermore, the terminology used herein is defined in consideration of its function within this disclosure and may vary according to the intent or practice of the user or operator. Therefore, its definition should be determined based on the entirety of this specification.

[0049] For ease of description, terms are provided in the following description for identifying access nodes, referring to network entities, referring to messages, referring to interfaces between network entities, and referring to various types of identification information. Therefore, this disclosure is not limited to the terms described below, and other terms may be used to refer to objects with equivalent technical meanings.

[0050] In the following text, the base station, as the entity that performs resource allocation for the terminal, can be at least one of a gNode B, eNode B, Node B, base station (BS), radio access unit, base station controller, or node on a network. The terminal can include a user equipment (UE), mobile station (MS), cellular phone, smartphone, computer, or multimedia system capable of performing communication functions. In this disclosure, downlink (DL) refers to the radio transmission path of a signal transmitted from the base station to the terminal, and uplink (UL) refers to the radio transmission path of a signal transmitted from the terminal to the base station. Furthermore, although Long Term Evolution (LTE) or LTE Advanced (LTE-A) systems are described below as examples, embodiments of this disclosure can also be applied to other communication systems with similar technical backgrounds or channel configurations. For example, systems to which embodiments of this disclosure can be applied may include fifth-generation mobile communication technology (5G, New Radio (NR)) or 5G Advanced systems developed after LTE-A, and in the following text, 5G can be a concept encompassing existing LTE, LTE-A, and other similar services.

[0051] Furthermore, as those skilled in the art will recognize, this disclosure can be applied to other communication systems with partial modifications without departing from its scope. Here, it is understood that each block in the process flowchart and combinations of flowcharts can be executed by computer program instructions.

[0052] These computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, and thus, the instructions, which are executed by the processor of the computer or other programmable data processing apparatus, can generate means configured to perform the functions described in the flowchart block. These computer program instructions can also be stored in a computer-usable or computer-readable storage medium capable of orienting the computer or other programmable data processing apparatus to implement the functions in a particular mode, and thus, the instructions stored in the computer-usable or computer-readable storage medium can also produce a production item relating to instruction means configured to perform the functions described in the flowchart block. The computer program instructions can also be loaded into a computer or other programmable data processing apparatus, and thus, a computer-executable process can also be generated by performing a series of operational steps on the computer or other programmable data processing apparatus, such that the instructions, which execute in the computer or other programmable data processing apparatus, provide steps for performing the functions described in the flowchart block.

[0053] Additionally, each box may indicate a module, segment, or portion of code comprising one or more executable instructions for performing a specific logical function. Furthermore, in several alternative embodiments, the functions described in the boxes may be performed out of order. For example, two consecutively shown boxes may be executed substantially simultaneously, or sometimes these boxes may be executed in reverse order according to their respective functions. The term “…unit” as used in the embodiments indicates a component comprising software or hardware, such as a field-programmable gate array (FPGA) or application-specific integrated circuit (ASIC), and a “…unit” may perform certain roles. However, the term “…unit” is not limited to software or hardware. A “…unit” may be configured to be stored in addressable storage media or to execute one or more processors. Thus, for example, a “…unit” may include elements such as software elements, object-oriented software elements, class elements and task elements, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. The functionality provided by elements and “…units” may be combined into a smaller number of elements and “…units”, or may be divided into additional elements and “…units”. Furthermore, the component and the “…unit” can be implemented as one or more central processing units (CPUs) within a playback device or secure multimedia card. Additionally, in embodiments, the “…unit” may include one or more processors.

[0054] For ease of description, this disclosure uses the terms and names defined in the 3GPP 5GS and NR standards. However, this disclosure is not limited to these terms and names and can be applied equivalently to wireless communication networks conforming to other standards. For example, this disclosure can be applied to 3GPP 5G Systems (5GS) / NR or 3GPP 5G Advanced standards.

[0055] Figure 1a This is a diagram illustrating the structure of a next-generation mobile communication system according to an embodiment of the present disclosure.

[0056] refer to Figure 1a The radio access network for next-generation mobile communication systems (New Radio (NR)) may include next-generation base stations (NR Node Bs, hereinafter referred to as gNBs) 1a-10 and Access and Mobility Management Functions (AMFs) 1a-05 (NR core network). User terminals (NR user equipment, hereinafter referred to as NR UEs, UEs, or terminals) 1a-15 may access external networks via gNBs 1a-10 and AMFs 1a-05.

[0057] exist Figure 1a In this context, the gNB corresponds to the Evolved Node B (eNB) in a traditional LTE system. The gNB connects to the NR UE via a radio channel and can provide superior service compared to the traditional Node B (1a-20). Since all user services in next-generation mobile communication systems are served through a shared channel, the equipment needs to collect UE status information, such as buffer status, available transmit power status, or channel status, and perform scheduling; gNBs 1a-10 handle this function. A single gNB can typically control multiple cells. To achieve ultra-high-speed data transmission compared to traditional LTE, Orthogonal Frequency Division Multiplexing (OFDM) is used as the radio access technology, exceeding the traditional maximum bandwidth, and beamforming technology can be further incorporated. Furthermore, an Adaptive Modulation and Coding (AMC) scheme can be applied, which determines the modulation scheme and channel coding rate based on the terminal's channel status.

[0058] The AMF 1a-05 can perform functions such as mobility support, bearer configuration, and Quality of Service (QoS) configuration. The AMF 1a-05 is responsible for various control functions and the mobility management functions of the terminal, and can connect to multiple base stations. Next-generation mobile communication systems can also interoperate with legacy LTE systems, and the AMF 1a-05 can connect to the Mobility Management Entity (MME) 1a-25 via a network interface. The MME can connect to the eNB 1a-30, which acts as a legacy base station. Terminals supporting LTE-NR dual connectivity can maintain connectivity not only with the gNB but also with the eNB, and send and receive data (1a-35).

[0059] Figure 1b This is a diagram illustrating the radio access state transition of a terminal in a next-generation mobile communication system according to an embodiment of the present disclosure.

[0060] In next-generation mobile communication systems, terminals can have three radio access states (Radio Resource Control (RRC) states). Connected mode (RRC_CONNECTED) 1b-05 refers to a radio access state where the terminal can send and receive data. Idle mode (RRC_IDLE) 1b-30 refers to a radio access state where the terminal monitors whether it is being paged. Connected mode 1b-05 and idle mode 1b-30 are also radio access states applicable to conventional LTE systems, and their detailed descriptions are the same as those for conventional LTE systems. In next-generation mobile communication systems, an inactive radio access state or inactive mode (RRC_INACTIVE) 1b-15 has been newly defined. In this disclosure, the newly defined RRC_INACTIVE state 1b-15 in next-generation mobile communication systems can correspond to the inactive radio access state, inactive mode, etc.

[0061] In Inactive Mode 1b-15, the UE context is maintained in both the base station and the terminal, and paging based on the Radio Access Network (RAN) can be supported. The characteristics of the new Inactive (RRC_INACTIVE) state 1b-15 are listed below.

[0062] -Cell reselection mobility; - A CN-NR RAN connection (C / U plane) has been established for the UE; - The UE AS context is stored in at least one gNB and UE; - Paging is initiated by NR RAN; - RAN-based notification areas are managed by NR RAN; -NR RAN knows the RAN-based notification area to which the UE belongs; According to an embodiment, the inactive state can be transitioned to either connected mode 1b-05 or idle mode 1b-30 using a specific procedure. According to the recovery procedure, a transition from inactive mode 1b-15 to connected mode 1b-05 can be performed, and a transition from connected mode 1b-05 to inactive mode 1b-15 can be performed using a release procedure that includes suspend configuration information (1b-10). In the above procedure (1b-10), one or more RRC messages can be sent and received between the terminal and the base station, and the above procedure (1b-10) can include one or more operations. Alternatively, a transition from inactive mode 1b-15 to idle mode 1b-30 can be performed using a recovery and then release procedure (1b-20).

[0063] The switching between connected mode 1b-05 and idle mode 1b-30 can be performed based on existing LTE technology. That is, the switching between connected mode 1b-05 and idle mode 1b-30 can be performed through the establishment or release procedure (1b-25).

[0064] Figure 1c This is a diagram illustrating the process of broadcasting priority information for each frequency used for cell reselection via a System Information Block (SIB) or applying priority information for each frequency used for cell reselection to a specific terminal in a next-generation mobile communication system according to embodiments of the present disclosure.

[0065] Cell reselection refers to the process of reselecting a serving cell, enabling a mobile terminal (in RRC_INACTIVE or RRC_IDLE state) to connect to a cell with optimal channel conditions. The network can control cell reselection for terminals in idle mode by assigning priorities based on each frequency. For example, when a terminal has received priority information for two frequencies, f1 and f2, and frequency f1 has a higher priority than frequency f2, the probability of the terminal remaining in the cell on frequency f1 increases. Furthermore, even if the terminal is in a cell on frequency f2, if the channel conditions on frequency f2 are poor, the terminal will attempt to switch to a cell on frequency f1.

[0066] Frequency priority information can be broadcast via SIB or provided to a specific terminal via the RRCRelease message, which is a dedicated RRC signaling. Even if a terminal already has frequency priority information via the SIB, it can ignore the SIB priority information in response to receiving UE-specific priority information via the RRCRelease message through RRC signaling. As shown in [Table 1] below, the priority information for each frequency can be transmitted via the cellReselectionPriority information element (IE), and currently can be assigned one of a total of eight priorities. Lower values ​​indicate lower priorities. That is, '0' indicates the lowest priority.

[0067] [Table 1]

[0068] Frequency across different Radio Access Technologies (RATs) cannot be assigned the same priority. When the terminal's idle state is "camping in any cell state," the terminal can apply frequency priority information received via the SIB and can store priority information received via RRC signaling without using it. The cellReselectionPriority IE is an optional IE and may not exist. The absence of the cellReselectionPriority IE indicates that priority information for the corresponding frequency has not yet been assigned. In this case, the terminal can consider the priority of the corresponding frequency as the lowest level. In Operation 1c-00, the terminal can receive priority information for frequencies used not only in the NR but also in other RATs via the SIB. However, priority information is not necessarily provided for all frequencies. Priority information for the frequency of the serving cell to which the terminal is currently camped may also not be provided. In Operation 1c-05, the terminal can check the existence of such priority information. When priority information for the frequency of the current serving cell has not yet been provided, the frequency priority can be considered the lowest level, as in Operation 1c-10.

[0069] In Operation 1c-15, the terminal can apply priority information for each frequency. In response to receiving an RRC Release message from the base station, the terminal 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 typically takes precedence over frequency priority information received from the SIB. Therefore, in Operation 1c-20, the terminal can determine whether frequency priority information exists in the RRC message. When frequency priority information exists in the RRC message, in Operation 1c-25, the terminal can apply a first timer value, also included therein, to start a first timer. In Operation 1c-30, the terminal can determine whether the current idle mode state is "camping in any cell state" or "normal camping state." "Normal camping state" refers to the state where the terminal is camped on a suitable cell. A suitable cell is a cell that can provide normal service to the terminal and meets the following detailed conditions.

[0070] - The cell belongs to the selected Public Land Mobile Network (PLMN), a registered PLMN, or a PLMN in the equivalent PLMN list; -The community is not prohibited; - The community meets the community selection criteria. "Standing in any cell state" refers to the state where the terminal is unable to camp on a suitable cell but is camped on an acceptable cell. In an acceptable cell, normal service is unavailable, and the terminal can only attempt emergency calls. An acceptable cell is a cell that meets the following conditions.

[0071] -The community is not prohibited; - The community meets the community selection criteria. When the terminal's idle state is "camping on any cell," the terminal may not apply the priority information received from the RRCRelease message, but instead can return to operation 1c-15 and apply the frequency priority information received from the SIB. Additionally, when the terminal is in the "normal camping" idle state, in operation 1c-35, the terminal can determine whether at least one of the following three conditions is met. The three conditions are as follows.

[0072] -The terminal has been switched to connection mode; - The first timer has expired; - The PLMN selection process has been performed based on the Non-Access Stratum (NAS) request. When any of the above conditions are met, in operation 1c-40, the priority information received from the RRCRelease message can be discarded, and the terminal can return to operation 1c-15 and apply the frequency priority information received from the SIB. Otherwise, when the above conditions are not met, in operation 1c-45, the terminal can apply the priority information received from the RRCRelease message.

[0073] Frequency priority information can affect 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, for frequencies that are the same as the serving cell (within the frequency range) or other frequencies with the same or lower priority, the terminal may not always perform measurements on such frequencies in order to save power.

[0074] Measurements can be performed when the serving cell's channel QoS is less than or equal to a specific threshold. Cell reselection is then performed to switch to a cell with good channel conditions, and there is no reason to switch to a frequency with the same or lower priority when the current serving cell's channel QoS is good. Therefore, the terminal can determine whether to perform measurements based on specific thresholds to reduce power consumption due to unnecessary channel measurements. Within the same frequency (intra-frequency), channel measurements can be performed on other cells at the same frequency when the serving cell's QoS (i.e., Srxlev or Squal) is less than or equal to a specific threshold SintraSearch (s-IntraSearchP and s-IntraSearchQ). s-IntraSearchP is a threshold based on Reference Signal Received Power (RSRP), and s-IntraSearchQ is a threshold based on Reference Signal Received Quality (RSRQ). Intra-frequency measurements are not performed when both the measured serving cell's RSRP and RSRQ are greater than their respective thresholds. For other frequencies with the same or lower priority (inter-frequency), channel measurements can be performed on cells on these other frequencies when the serving cell's QoS (i.e., Srxlev or Squal) is lower than or equal to a specific threshold SnonintraSearch (s-NonIntraSearchP and s-NonIntraSearchQ). s-NonIntraSearchP is a threshold based on RSRP, and s-NonIntraSearchQ is a threshold based on RSRQ. Inter-frequency measurements are not performed when both the measured serving cell's RSRP and RSRQ are greater than their respective thresholds.

[0075] In this disclosure, the state in which intra-frequency or inter-frequency channel measurements are performed by comparing with a threshold is referred to as the normal measurement state, and the state in which no such channel measurement is performed is referred to as the no-measurement state. Serving cell measurements can always be performed regardless of the measurement state.

[0076] While performing measurements in this manner, when the channel QoS of a cell on a high-priority frequency becomes higher than a specific threshold ThreshX-high, the terminal can reselect a cell on the high-priority frequency as the serving cell. When the channel QoS of a cell on a low-priority frequency becomes higher than a specific threshold ThreshX-low and the QoS of the serving cell becomes lower than ThreshServing-low, the terminal can reselect a cell on the low-priority frequency as the serving cell.

[0077] Figure 1d This is a diagram illustrating a method for performing cell reselection in a next-generation mobile communication system, executed by a terminal according to an embodiment of the present disclosure.

[0078] The terminal can always perform inter-frequency measurements and RAT measurements on frequencies or RATs with high priority, regardless of the measurement signal strength of the serving cell.

[0079] When the measured signal strength 1d-05 of the serving cell is lower than SintraSearch 1d-25, the terminal can perform intra-frequency measurements. When the measured signal strength 1d-05 of the serving cell is lower than SintraSearch 1d-30, the terminal can perform inter-frequency / RAT measurements on frequencies with the same or lower priority as the current serving cell.

[0080] Conversely, when the measured signal strength 1d-05 of the serving cell is higher than SintraSearch 1d-25, the terminal may not perform intra-frequency measurements, and when the measured signal strength 1d-05 of the serving cell is higher than SintraSearch 1d-30, the terminal may not perform inter-frequency / RAT measurements on frequencies with the same or lower priority as the current serving cell.

[0081] The reason for triggering this operation of reducing terminal measurements (RRM measurement relaxation or relaxed RRM measurement) may be to reduce the power consumption of the terminal caused by neighboring cell measurements.

[0082] When the channel QoS of cell 1d-10 on a high-priority frequency becomes higher than a specific threshold ThreshX-high 1d-35, the terminal can reselect a cell on the high-priority frequency as the serving cell. When the channel QoS of cell 1d-00 on a low-priority frequency is 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 a cell on the low-priority frequency as the serving cell.

[0083] During cell reselection, received signal strength (RSRP) or received signal quality (RSRQ) can be considered. For each, Srxlev or Squal can be calculated as follows.

[0084]

[0085] The meanings of each variable are described in Table 2 below.

[0086] [Table 2]

[0087]

[0088] Figure 1eThis is a diagram illustrating a method performed by a terminal and a base station in an inactive or idle mode according to an embodiment of the present disclosure, whereby the measurement is relaxed.

[0089] In inactive or idle mode, the terminal can receive system information (1e-05) and then camp on the corresponding cell (1e-10). The terminal in inactive or idle mode can perform RRM measurements for cell selection or reselection. Figure 1e In this context, the terminal performing RRM measurements can determine whether RRM measurement relaxation parameters or configurations have been set by using information (e.g., relaxedMeasurement) included in system information (e.g., SIB2) 1e-05 received from the base station. For example, relaxedMeasurement may include multiple parameters for RRM relaxation, as shown in [Table 3] below.

[0090] [Table 3]

[0091] When relaxedMeasurement is configured in the system information and the terminal supports relaxed measurements, the terminal uses the parameters mentioned above to determine whether relaxed RRM (measurement) can be performed (1e-15). When the relaxation criteria (relaxation criteria or relaxation conditions, or relaxed measurement criteria or relaxed measurement conditions) in 1e-15 are met, the terminal can perform relaxed RRM measurements (1e-20). When the relaxation criteria (relaxation criteria or relaxation conditions) in 1e-15 are not met, the terminal cannot perform relaxed RRM measurements, but can perform regular or normal RRM measurements (1e-20).

[0092] In procedure 1e-15, based on the base station's system information, the terminal can be configured with some or all of four relaxed measurement criteria. These four relaxed criteria are: 1) Low Mobility Evaluation (corresponding to `lowMobilityEvaluation` in Table 3), 2) Non-Cell Edge Evaluation (corresponding to `cellEdgeEvaluation` in Table 3), 3) Stationary Mobility Evaluation (corresponding to `stationaryMobilityEvaluation` in Table 3), and 4) Stationary and Non-Cell Edge Evaluation (corresponding to `cellEdgeEvaluationWhileStationary` in Table 3). The 3) Stationary Evaluation criterion and 4) Stationary and Non-Cell Edge Evaluation criterion can be used by Reduced Capability (RedCap) terminals or Enhanced RedCap terminals. The base station can configure only one criterion or multiple criteria. Using the 1) Low Mobility Evaluation criterion and the 3) Stationary Evaluation criterion, the terminal can determine that its mobility level is low, and using the 2) Non-Cell Edge Evaluation criterion, the terminal can determine that it is not located at the edge of the serving cell. In other words, because terminals with low mobility and not located at the cell edge receive a stable signal strength from the serving cell, the need for cell reselection to another neighboring cell is lower, and therefore the terminal can relax RRM measurements for neighboring cells. Relaxed RRM measurements can reduce energy consumption by measuring at longer intervals (i.e., less frequently) than normal RRM measurements.

[0093] The above is for reference only. Figure 1d The operations described related to SintraSearch and SnonintraSearch can also be applied as part of relaxed measurement or RRM relaxation. Figure 1eSpecifically, in inactive or idle mode, the terminal can receive system information (1e-05) and then camp on a cell (1e-10). Through the system information (e.g., SIB2), the terminal can receive SintraSearch and / or SnonintraSearch (1e-05). Subsequently, in 1e-15, when the measured signal strength of the serving cell is lower than that of SintraSearch, the terminal can perform intra-frequency measurements (e.g., normal measurements). When the measured signal strength of the serving cell is lower than that of SnonintraSearch, the terminal can perform inter-frequency / RAT measurements (e.g., normal measurements) on frequencies with the same or lower priority as the current serving cell. Conversely, when the measured signal strength of the serving cell is higher than that of SintraSearch, the terminal may not perform intra-frequency measurements (e.g., relaxed measurements), and when the measured signal strength of the serving cell is higher than that of SnonintraSearch, the terminal may not perform inter-frequency / RAT measurements (e.g., relaxed measurements) on frequencies with the same or lower priority as the current serving cell.

[0094] Figure 1f This is a diagram illustrating an example of a process performed by a terminal, according to an embodiment of the present disclosure, to select and perform one of a normal RRM measurement or a relaxed RRM measurement.

[0095] The terminal can receive SIBs and obtain configuration information for RRM measurement relaxation (e.g., SintraSearch, SnonintraSearch, and / or relaxedMeasurement) (1f-05).

[0096] The terminal can reside on a serving cell (1f-10).

[0097] The terminal can perform RRM measurements for cell reselection based on each frequency (within NR frequency, between NR frequency, or between RAT frequencies) and / or based on each frequency priority, and can determine whether the relaxation criteria (1f-15) are met based on the RRM measurement relaxation configuration information.

[0098] When predetermined relaxation criteria are met, the terminal can perform relaxed RRM measurements (1f-20). In this case, the terminal can reduce power consumption by performing measurements at longer intervals (i.e., less frequently) than the normal measurement cycle or by avoiding measurements altogether. The measurement cycle for relaxed RRM measurements can be described in sections of 3GPP TS 38.133 and 3GPP TS 38.304. When predetermined relaxation criteria are not met, the terminal can perform normal RRM measurements (1f-25) at the corresponding frequency. The measurement cycle for normal RRM measurements can be described in 3GPP TS 38.133.

[0099] This disclosure proposes an RRM relaxation method for endpoints using prediction or inference based on artificial intelligence / machine learning (AI / ML).

[0100] According to embodiments of this disclosure, a terminal may use current serving cell and neighboring cell measurement results (RSRP / RSRQ / SINR) information, past serving cell and neighboring cell measurement results (RSRP / RSRQ / SINR) information, terminal location information, terminal speed information, terminal serving cell history information, terminal neighboring cell history information, terminal remaining power information, terminal configuration information (e.g., RRC configuration information) history, terminal capabilities, etc., as input to an AI / ML model.

[0101] According to embodiments of this disclosure, a terminal can obtain future cell measurement result information (e.g., RSRP / RSRQ / SINR) from the output of an AI / ML model.

[0102] In this way, for example, even if the current cell measurement results do not meet the relaxation criteria, the terminal can use AI / ML to predict that the future cell measurement results will meet the relaxation criteria (e.g., the terminal is moving towards the center of the serving cell or the terminal's mobility is decreasing) and preemptively implement RRM relaxation to reduce its energy usage.

[0103] Conversely, for example, even when the current cell measurement results meet the relaxation criteria, the terminal can use AI / ML to predict that future cell measurement results (RSRP / RSRQ / SINR) will not meet the relaxation criteria (e.g., when the terminal is moving outside the serving cell or when the terminal's mobility is increasing) and perform normal measurements instead of RRM relaxation, thereby performing appropriate cell (re)selection through sufficient cell measurements.

[0104] Figure 1g This is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode according to an embodiment of the present disclosure, using AI / ML-based predictive measurement results.

[0105] In Operation 1g-05, the terminal can receive system information in inactive or idle mode. This system information may include configurations related to RRM measurement relaxation (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Furthermore, the terminal can receive configurations from the base station related to RRM relaxation using predicted cell measurement results. Additionally, the terminal can receive information from the base station regarding whether RRM relaxation is permitted using predicted cell measurement results. Operation 1g-05 may correspond to... Figure 1f Operation 1f-05.

[0106] In Operation 1g-10, the terminal can camp on the corresponding cell. Operation 1g-10 can correspond to... Figure 1f Operation 1f-10.

[0107] In Operation 1g-15, the terminal can execute AI / ML models to derive (output) predicted future cell measurements (e.g., RSRP / RSRQ / SINR).

[0108] In Operation 1g-20, the terminal can determine whether to implement RRM relaxation based on actual cell measurement results and / or predicted cell measurement results. Operation 1g-20 can correspond to Figure 1f Operation 1f-15. For example, a terminal can determine that it meets the RRM relaxation criteria when at least one of the following conditions is met.

[0109] -Condition 1. The predicted cell measurement result meets the non-cell edge criteria. For example, the predicted value is greater than the cell measurement threshold configured by the base station in 1g-05.

[0110] - Condition 2. The predicted cell measurement results meet the low mobility criterion or the stationary criterion. For example, the variation in the predicted value is greater than the cell measurement threshold configured by the base station in 1g-05.

[0111] -Condition 3. The actual cell measurement result meets the non-cell edge criteria. For example, the actual measurement result is greater than the cell measurement threshold configured by the base station in 1g-05.

[0112] - Condition 4. The actual cell measurement results meet the low mobility criterion or the stationary criterion. For example, the variation in the actual measurement results is greater than the cell measurement threshold configured by the base station in 1g-05.

[0113] - Condition 5. For example, in 1g-05, the base station has already allowed the implementation of RRM relaxation using predicted cell measurement results, or has already received the relevant configuration from the base station.

[0114] - Condition 6. For example, in 1g-05, the base station has already allowed the use of actual cell measurement results to perform RRM relaxation, or has already received the relevant configuration from the base station.

[0115] In Operation 1g-25, in response to determining that the RRM relaxation criteria are met, the terminal can perform a relaxed RRM measurement. This can correspond to... Figure 1f Operation 1f-20. Conversely, in response to determining that the RRM relaxation criteria are not met, the terminal can perform a normal RRM measurement. This can correspond to Figure 1f Operation 1f-25.

[0116] In embodiments of this disclosure, when RRM relaxation is triggered by predicted cell measurement results, the terminal can report the predicted cell measurement results to the base station. For example, the terminal can report the predicted cell measurement results to the base station via UEinformationResponse, MeasurementReport, or UEAssistanceInformation messages. This information can be useful when the base station subsequently configures new RRM relaxation parameters for the terminal.

[0117] In embodiments of this disclosure, the terminal can obtain parameters of the RRM relaxation standard (e.g., parameters within SintraSearch, SnonintraSearch, and / or relaxedMeasurement) from the output of the AI / ML model.

[0118] In related RRM relaxation methods, all terminals within a serving cell receive common parameters related to a common RRM relaxation standard in the system information (e.g., parameters within SintraSearch, SnonintraSearch, and / or relaxedMeasurement), and determine the same RRM relaxation standard accordingly. However, the actual state and circumstances of each terminal (such as values ​​used as inputs to AI / ML models) may differ, and a customized RRM relaxation standard configuration may be required for each terminal's specific situation. For example, when many cells surround a terminal, enabling the terminal to find the optimal cell through sufficient RRM measurements using a strict RRM relaxation standard can help improve throughput when the terminal switches to connected mode. Conversely, when there are no other cells around the terminal besides the serving cell, the terminal's RRM measurements can be minimized by using a less strict RRM relaxation standard, allowing the terminal to remain on the serving cell for as long as possible and reducing energy consumption due to unnecessary RRM measurements.

[0119] Figure 1hThis is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode, according to an embodiment of the present disclosure, by using AI / ML to determine / update relaxation criteria parameters.

[0120] In Operation 1h-05, the terminal can receive system information in inactive or idle mode. This system information may include configurations related to RRM measurement relaxation (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Additionally, the terminal can receive information from the base station regarding whether to allow the determination / updating of relaxed criterion parameters. Operation 1h-05 can correspond to... Figure 1f Operation 1f-05.

[0121] During operation 1h-10, the terminal can camp on the corresponding cell. Operation 1h-10 can correspond to... Figure 1f Operation 1f-10.

[0122] During operation 1h-15, the terminal can execute an AI / ML model to derive (output) the relaxation standard parameters to be used for RRM relaxation. These can be parameters used in the relaxation standards configured by the base station. Alternatively, not only can the relaxation standard parameters to be used be exported, but the relaxation standard to be used can also be exported as the output of the AI / ML. In this case, if the base station has not yet configured a relaxation standard, the terminal can use the exported relaxation standard, or if the base station has already configured a relaxation standard, the terminal can use the exported relaxation standard instead of the configured one.

[0123] In embodiments of this disclosure, the terminal may report derived relaxed standard parameters (e.g., thresholds) to the base station when subsequently switching to connected mode. For example, the terminal may report the derived relaxed standard parameters (e.g., thresholds) to the base station via a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message when subsequently switching to connected mode. In this way, the base station can obtain information about the RRM relaxed standard parameters used by the terminal and use the obtained information for network configuration.

[0124] In Operation 1h-20, the terminal can determine whether to perform RRM relaxation based on the derived relaxation criteria and / or derived relaxation criterion parameters (e.g., thresholds). Operation 1h-20 can correspond to... Figure 1f Operation 1f-15. For example, a terminal can determine that it meets the RRM relaxation criteria when at least one of the following conditions is met.

[0125] -Condition 1. Actual or predicted cell measurement results meet the derived relaxed criteria.

[0126] -Condition 2. For example, in 1h-05, the base station has already allowed the determination / update of the relaxation criteria, or has already received the relevant configuration from the base station.

[0127] In Operation 1h-25, in response to determining that the RRM relaxation criteria are met, the terminal can perform a relaxed RRM measurement. This corresponds to Operation 1f-20. Conversely, in response to determining that the RRM relaxation criteria are not met, the terminal can perform a normal RRM measurement. This also corresponds to Operation 1f-25.

[0128] In embodiments of this disclosure, the terminal can obtain an indication from the output of the AI / ML model whether to perform RRM relaxation.

[0129] In RRM relaxation methods of related technologies, terminals can determine whether to perform RRM relaxation based on relaxation criteria specified in the standard and configured by the network (e.g., low mobility, non-cell edge, and stationary criteria). However, it may be difficult for the network to configure the optimal criteria for each terminal. Furthermore, in addition to the relaxation criteria specified in the standard, there may be important conditions for determining whether a terminal should perform relaxation. For example, when many cells are around a terminal, enabling the terminal to find the optimal cell through sufficient RRM measurements by using strict RRM relaxation criteria can help improve throughput when the terminal switches to connected mode. Conversely, when there are no other cells around the terminal besides the serving cell, the terminal's RRM measurements can be minimized by using less stringent RRM relaxation criteria, allowing the terminal to remain on the serving cell for as long as possible and reducing energy consumption due to unnecessary RRM measurements. In such cases, cell density around the terminal can be an important indicator for determining whether to perform relaxation. As another example, when the terminal has high remaining power, enabling the terminal to find the optimal cell through sufficient RRM measurements can help improve throughput when the terminal switches to connected mode. Conversely, when the terminal's remaining power is low, RRM measurements can be minimized, allowing the terminal to remain on the serving cell for as long as possible and reducing energy consumption due to unnecessary RRM measurements. In such cases, the terminal's remaining power can also be an important indicator for determining whether to implement RRM relaxation. Therefore, instead of applying the relaxation criteria specified in the standard or configured by the network, the terminal can autonomously and freely (independent of the specifications in the standard or the network configuration) perform AI / ML by considering various collected information (e.g., cell measurement / prediction results, remaining power, or cell density) to determine whether to implement RRM relaxation and then implement it.

[0130] Figure 1i This is a diagram illustrating a process performed by a terminal in an inactive or idle mode according to an embodiment of the present disclosure, using AI / ML to determine whether to perform RRM relaxation and perform RRM relaxation accordingly.

[0131] In Operation 1i-05, the terminal can receive system information in inactive or idle mode. This system information may include configurations related to RRM measurement relaxation (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Furthermore, the terminal can receive information from the base station regarding whether AI / ML export is permitted, whether RRM relaxation is performed, and how that export is used. Operation 1i-05 can correspond to... Figure 1f Operation 1f-05.

[0132] In Operation 1i-10, the terminal can camp on the corresponding cell. Operation 1i-10 can correspond to... Figure 1f Operation 1f-10.

[0133] In Operation 1i-15, the terminal can execute an AI / ML model to derive (output) whether RRM relaxation should be performed. According to embodiments of this disclosure, the terminal can use RRM relaxation configuration criteria and parameters configured by the base station as one of the input values ​​for the AI / ML model.

[0134] In Operation 1i-20, the terminal can determine whether to perform RRM relaxation based on the derived results regarding whether to perform RRM relaxation. Operation 1i-20 can correspond to Figure 1f Operation 1f-15. For example, a terminal can determine that it meets the RRM relaxation criteria when at least one of the following conditions is met.

[0135] -Condition 1. "Execute RRM relaxation" has been exported and confirmed.

[0136] -Condition 2. For example, in 1i-05, the base station has already allowed the export of whether to perform RRM relaxation and use the exported information, or has already received the relevant configuration from the base station.

[0137] In Operation 1i-20, when the RRM relaxation criteria are met, the terminal can perform relaxed RRM measurements. This corresponds to Operation 1f-20. Conversely, when the RRM relaxation criteria are not met, the terminal can perform normal RRM measurements. This corresponds to Operation 1f-25.

[0138] In embodiments of this disclosure, the terminal can obtain the RRM relaxation method (e.g., measurement period or whether to perform a measurement) from the output of the AI / ML model.

[0139] In RRM relaxation methods of related technologies, terminals can determine the degree of relaxation based on the relaxation method specified in the standard (e.g., the measurement period described in 3GPP TS 38.331). Therefore, the network cannot configure an optimal relaxation method (e.g., measurement period) for each terminal. Furthermore, a scheme that does not follow the relaxation degree or method specified in the standard may be the optimal relaxation operation for the terminal. For example, when many cells are located around the terminal, enabling the terminal to find the optimal cell through sufficient RRM measurements even when performing relaxation can help improve throughput when the terminal switches to connected mode by using a relatively short measurement period. Conversely, when there are no other cells around the terminal besides the serving cell, the terminal's RRM measurements can be minimized by using a relatively long measurement period when performing relaxation, allowing the terminal to remain on the serving cell for as long as possible and reducing energy consumption due to unnecessary RRM measurements. In such cases, the cell density around the terminal can be an important indicator for determining the degree and method of relaxation. As another example, when a terminal has high remaining power, even when the terminal performs relaxation, finding the optimal cell through sufficient RRM measurements using a relatively short measurement cycle can help improve throughput when the terminal switches to connected mode. Conversely, when the terminal has low remaining power, RRM measurements can be minimized by using a relatively long measurement cycle when performing relaxation, allowing the terminal to remain on the serving cell for as long as possible and reducing energy consumption due to unnecessary RRM measurements. In such cases, the terminal's remaining power can be an important indicator for determining the extent and method of relaxation. Therefore, instead of following the relaxation method (measurement cycle) specified in the standard, the terminal can autonomously and freely (without relying on the specifications in the standard) determine the extent and method of RRM relaxation (e.g., measurement cycle) by performing AI / ML, considering various collected information (e.g., cell measurement / prediction results, remaining power, or cell density) (e.g., as input to the model).

[0140] Figure 1j This is a diagram illustrating the process of performing RRM relaxation by a terminal in an inactive or idle mode, according to an embodiment of the present disclosure, using an AI / ML-based method to determine / update the relaxation.

[0141] In Operation 1j-05, the terminal can receive system information in inactive or idle mode. This system information may include configurations related to RRM measurement relaxation (e.g., relaxedMeasurement and / or SintraSearch and SnonintraSearch). Additionally, the terminal can receive information from the base station regarding whether the relaxation method can be determined / updated. Operation 1j-05 can correspond to... Figure 1f Operation 1f-05.

[0142] In Operation 1j-10, the terminal can camp on the corresponding cell. Operation 1j-10 can correspond to... Figure 1f Operation 1f-10.

[0143] In Operation 1j-15, a terminal can be determined to meet the RRM relaxation criteria when at least one of the following conditions is met.

[0144] -Condition 1. Meet the relaxation criteria (e.g., non-cell edge, low mobility, or stationary criteria) provided by the base station in relation to the RRM measurement relaxation configuration.

[0145] -Condition 2. The base station has already allowed the determination / update of the relaxation method, or has already received the relevant configuration from the base station.

[0146] In Operation 1j-20, in response to determining that the relaxation criteria are met, the terminal can execute an AI / ML model to derive (output) the degree of relaxation and / or method to be used (e.g., measurement period, measurement frequency, measurement frequency type, time interval for performing the relaxation operation).

[0147] In Operation 1j-25, when the terminal determines that the RRM relaxation criteria are met and has successfully derived the relaxation method by executing the AI / ML model, the terminal can perform relaxed RRM measurements based on the derived method. This corresponds to Operation 1f-20.

[0148] When a terminal determines that it meets the RRM relaxation criteria but fails to derive the relaxation method, the terminal may perform relaxed RRM measurements according to a fixed relaxation method defined in the standard (e.g., the 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 Operation 1f-20. For example, when a terminal determines that it meets the RRM relaxation criteria but fails to derive the relaxation method by executing an AI / ML model within the time limits defined in the standard, the terminal may perform relaxed RRM measurements according to a fixed relaxation method defined in the standard (e.g., the measurement period described in 3GPP TS 38.133).

[0149] In response to the determination that the RRM relaxation criteria are not met, the terminal can perform a normal RRM measurement, which can correspond to operation 1f-25.

[0150] Figure 1k This is a diagram illustrating the process of performing RRM relaxation based on s-MeasureConfig by a terminal in connected mode according to an embodiment of the present disclosure.

[0151] In Operation 1k-05, the terminal can be in connection mode with the base station.

[0152] In Operation 1k-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal can include information about whether RRM relaxation is supported in connected mode, either in the UE capability information message or together with it. Specifically, the terminal can include information about whether RRM relaxation based on s-MeasureConfig is supported, or whether cell measurement needs to be performed, either in the UE capability information message or together with it.

[0153] In Operation 1k-10, the terminal receives an RRC reconfiguration message from the base station. This message may include configuration for cell measurements (e.g., MeasConfig), and the terminal may configure s-MeasureConfig as one of the configuration parameters. s-MeasureConfig may indicate the RSRP (or RSRQ or SINR) threshold used by the terminal in 1k-15 to determine whether to perform measurements on non-serving cells or neighboring cells.

[0154] In Operation 1k-15, the terminal can perform signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) and compare the signal measurement results (e.g., RSRP) of the serving cell (or SpCell) with the configured s-MeasureConfig.

[0155] In Operation 1k-20, in response to determining that the s-MeasureConfig condition is not met (i.e., when the signal measurement result of the serving cell or SpCell is less than the configured s-MeasureConfig), the terminal can perform cell measurements on the corresponding neighboring cells and export the cell measurement results. Conversely, in response to determining that the s-MeasureConfig condition is met (i.e., when the signal measurement result of the serving cell or SpCell is not less than the configured s-MeasureConfig), the terminal may not perform cell measurements on the corresponding neighboring cells and may not export the cell measurement results.

[0156] In Operation 1k-25, the terminal can send a measurement report to the base station that includes only measurement results that meet the s-MeasureConfig conditions.

[0157] Figure 11 This is a diagram illustrating the operation performed by a terminal, based on s-MeasureConfig, to determine whether to perform a cell measurement according to an embodiment of the present disclosure.

[0158] In operation 1l-05, the terminal can receive system information.

[0159] In Operation 1l-10, the terminal can reside on the cell.

[0160] In operation 1l-15, the terminal can establish an RRC connection with the base station and switch to connection mode.

[0161] In Operation 1l-17, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station through a UE capability information message.

[0162] In operation 1l-20, the terminal receives an RRC reconfiguration message from the base station. This message may include configuration for cell measurements (e.g., MeasConfig), and the terminal may configure s-MeasureConfig as one of the configuration parameters. s-MeasureConfig may indicate the RSRP (or RSRQ or SINR) threshold used by the terminal in 1l-25 to determine whether to perform measurements on non-serving cells or neighboring cells.

[0163] In Operation 1l-25, the terminal can perform signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) and compare the signal measurement results (e.g., RSRP) of the serving cell (or SpCell) with the configured s-MeasureConfig.

[0164] In operation 1l-30, in response to determining that the s-MeasureConfig condition is not met (i.e., when the measurement result of the serving cell or SpCell is less than the configured s-MeasureConfig), the terminal can perform cell measurement on the corresponding neighboring cell and export the cell measurement result.

[0165] In operation 1l-35, in response to determining that the s-MeasureConfig condition is met (i.e., when the measurement result of 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 and may not export the cell measurement result.

[0166] In this way, when the measurement results of the serving cell or SpCell are good, the terminal can save energy by reducing unnecessary measurements of neighboring cells and simplifying measurement reports.

[0167] Figure 1m This is a diagram illustrating a process performed by a terminal in connected mode, according to an embodiment of the present disclosure, of performing RRM relaxation based on s-MeasureConfig by predicting measurement results based on AI / ML.

[0168] In operation 1m-05, the terminal can be in connection mode with the base station.

[0169] In Operation 1m-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal can report to the base station information about its ability to perform RRM relaxation by including or combining this information with the UE capability information message.

[0170] In Operation 1m-10, the terminal receives an RRC reconfiguration message from the base station. This message may include configuration for cell measurements (e.g., MeasConfig), and the terminal may configure s-MeasureConfig as one of the configuration parameters. Furthermore, the terminal can receive configurations from the base station related to performing RRM relaxation by comparing predicted cell measurement results with s-MeasureConfig. Additionally, the terminal can receive information from the base station regarding whether RRM relaxation is permitted by comparing predicted cell measurement results with s-MeasureConfig.

[0171] In Operation 1m-15, the terminal can execute AI / ML models to derive (output) predicted future measurements of the serving cell (or SpCell) (e.g., RSRP / RSRQ / SINR).

[0172] In Operation 1m-20, the terminal can compare the measurement results of the serving cell (or SpCell) obtained by performing signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) and / or the predicted values ​​(e.g., RSRP) of the serving cell (or SpCell) obtained by performing predictions using an AI / ML model with the s-MeasureConfig configured by the base station. For example, the terminal can determine that the s-MeasureConfig condition is met when at least one of the following conditions is satisfied.

[0173] -Condition 1. The predicted cell measurement results satisfy the s-MeasureConfig conditions. That is, for example, the predicted value for the serving cell or SpCell is not less than the configured s-MeasureConfig.

[0174] -Condition 2. The actual cell measurement results satisfy the s-MeasureConfig conditions. That is, for example, the measurement results for the serving cell or SpCell are not less than the configured s-MeasureConfig.

[0175] - Condition 3. For example, in 1m-10, the base station is already allowed to perform RRM relaxation by comparing the predicted cell measurement results with s-MeasureConfig.

[0176] -Condition 4. For example, in 1m-10, the base station has already allowed RRM relaxation to be performed by comparing the actual cell measurement results with s-MeasureConfig, or has already received the relevant configuration from the base station.

[0177] In Operation 1m-25, in response to determining that the s-MeasureConfig condition is not met, the terminal can perform cell measurements on the corresponding neighboring cells and export the cell measurement results. Conversely, in response to determining that the s-MeasureConfig condition is met, the terminal may not perform cell measurements on the corresponding neighboring cells and may not export the cell measurement results.

[0178] In Operation 1m-30, the terminal can send a measurement report to the base station that includes only measurement results that meet the s-MeasureConfig conditions.

[0179] In embodiments of this disclosure, when RRM relaxation is triggered by predicted cell measurement results (i.e., when the s-MeasureConfig condition is met), the terminal can report the predicted cell measurement results to the base station. For example, the terminal can report the predicted cell measurement results to the base station via UEinformationResponse, MeasurementReport, or UEAssistanceInformation messages. This information may be useful when the base station subsequently configures a new s-MeasureConfig for the terminal.

[0180] Figure 1n This is a diagram illustrating the process of performing RRM relaxation by a terminal in connected mode according to an embodiment of the present disclosure, using AI / ML to determine / update s-MeasureConfig.

[0181] In Operation 1n-05, the terminal can be in connection mode with the base station.

[0182] In Operation 1n-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal can report information about its ability to determine / update the s-MeasureConfig value to the base station by including or including this information in the UE capability information message.

[0183] In operation 1n-10, the terminal receives an RRC reconfiguration message from the base station. This message may include configuration for cell measurements (e.g., MeasConfig), and the terminal may configure s-MeasureConfig as one of the configuration parameters. s-MeasureConfig may indicate the RSRP (or RSRQ or SINR) threshold used by the terminal in 1n-20 to determine whether to perform measurements on non-serving cells or neighboring cells. Additionally, the terminal may receive information from the base station regarding whether determining / updating the s-MeasureConfig value is permitted.

[0184] In operation 1n-15, the terminal can execute an AI / ML model to derive (output) the s-MeasureConfig value. Here, the s-MeasureConfig value configured by the base station can be used as one of the input values ​​of the AI / ML model. In embodiments of this disclosure, the terminal can report the derived s-MeasureConfig value to the base station. For example, the terminal can report the derived s-MeasureConfig value to the base station via a UEinformationResponse, MeasurementReport, or UEAssistanceInformation message. In this way, the base station can obtain information about the s-MeasureConfig value used by the terminal and use the obtained information for network configuration.

[0185] In operation 1n-20, the terminal can compare the measurement results (e.g., RSRP) of the serving cell (or SpCell) obtained by performing signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) with the s-MeasureConfig newly derived by performing an AI / ML model. For example, the terminal can determine that the s-MeasureConfig condition is met when at least one of the following conditions is satisfied.

[0186] -Condition 1. The actual or predicted cell measurement results satisfy the derived s-MeasureConfig conditions. That is, for example, the measurement results for the serving cell or SpCell are not less than the derived s-MeasureConfig.

[0187] -Condition 2. For example, in 1n-10, the base station has already been allowed to determine / update the s-MeasureConfig value, or has already received the relevant configuration from the base station.

[0188] In operation 1n-25, in response to determining that the s-MeasureConfig condition is not met, the terminal may perform cell measurements on the corresponding neighboring cells and export the cell measurement results. Conversely, in response to determining that the s-MeasureConfig condition is met, the terminal may not perform cell measurements on the corresponding neighboring cells and may not export the cell measurement results.

[0189] In Operation 1n-30, the terminal can send a measurement report to the base station that includes only measurement results that meet the s-MeasureConfig conditions.

[0190] Figure 1o This is a diagram illustrating a process performed by a terminal in connected mode according to an embodiment of the present disclosure, using AI / ML to determine whether to perform RRM relaxation and perform RRM relaxation accordingly.

[0191] In Operation 1o-05, the terminal can be in connection mode with the base station.

[0192] In Operation 1o-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal can report to the base station, either by including information in the UE capability information message or by using it together with the UE capability information message, whether RRM relaxation has been performed and whether the derived capability has been used through AI / ML export.

[0193] In Operation 1o-10, the terminal receives an RRC reconfiguration message from the base station. This message may include configuration for cell measurements (e.g., MeasConfig), and the terminal may configure s-MeasureConfig as one of the configuration parameters. s-MeasureConfig may indicate the RSRP (or RSRQ or SINR) threshold used by the terminal in 1o-20 to determine whether to perform measurements on the serving cell. Furthermore, the terminal may receive information from the base station regarding whether to allow the terminal to use AI / ML exports, whether to perform RRM relaxation, and how to use those exports.

[0194] In operation 1o-15, the terminal can execute an AI / ML model to derive (output) whether RRM relaxation is performed. In embodiments of this disclosure, the terminal can use the s-MeasureConfig value configured by the base station as one of the input values ​​for the AI / ML model.

[0195] In operation 1o-20, the terminal can determine whether to perform RRM relaxation based on the derived results regarding whether to perform RRM relaxation. For example, the terminal can determine that the RRM relaxation criteria are met when at least one of the following conditions is satisfied.

[0196] -Condition 1. "Execute RRM relaxation" has been exported and confirmed.

[0197] -Condition 2. For example, in 1o-10, the base station has already allowed the export of whether to perform RRM relaxation and use the exported information, or has already received the relevant configuration from the base station.

[0198] In response to the determination that the RRM relaxation criteria are not met, the terminal can perform cell measurements on the corresponding neighboring cells and export the cell measurement results. Conversely, in response to the determination that the RRM relaxation criteria are met, the terminal may not perform cell measurements on the corresponding neighboring cells and may not export the cell measurement results.

[0199] In Operation 1o-25, the terminal can send a measurement report to the base station that includes only measurement results that meet the RRM relaxation criteria.

[0200] Figure 1p This is a diagram illustrating the process of performing RRM relaxation based on a relaxed standard, executed by a terminal in connected mode according to an embodiment of the present disclosure.

[0201] In Operation 1p-05, the terminal can be in connection mode with the base station.

[0202] In Operation 1p-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal (e.g., a RedCap terminal) can send information about whether RRM relaxation is supported in connected mode by including or sending such information in the UE capability information message. Similarly, the terminal (e.g., a RedCap terminal) can send information about whether a relaxation criterion satisfaction report (e.g., for static criteria) is supported in connected mode by including or sending such information in the UE capability information message.

[0203] In Operation 1p-10, the terminal can receive relaxation criteria and related parameters (e.g., thresholds for evaluating the static criterion) from the base station via RRC reconfiguration messages. Additionally, the terminal can receive cell measurement configurations (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via RRC reconfiguration messages.

[0204] In Operation 1p-15, the terminal can perform signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) and determine whether the configured relaxed criteria (e.g., stationary criteria) are met based on the measurement results of the serving cell (or SpCell) (e.g., RSRP, RSRQ, SINR).

[0205] In embodiments of this disclosure, after operation 1p-15, the terminal / base station may execute option 1 (1p-20 and 1p-25) and may not execute option 2 (1p-30).

[0206] In embodiments of this disclosure, after operation 1p-15, the terminal / base station may execute option 2 (1p-30) and may not execute option 1 (1p-20 and 1p-25).

[0207] In Operation 1p-20, in response to determining that the relaxation criteria are not met (e.g., when the measurement results of the serving cell or SpCell vary greatly), the terminal can report the non-compliance of the relaxation criteria to the base station. For example, the terminal can report this to the base station by omitting the relaxation criterion compliance indicator or by setting it to false.

[0208] Conversely, in response to determining that the relaxation criteria are met (e.g., when the variation in the measurement results of the serving cell or SpCell is small), the terminal can report that the relaxation criteria are met to the base station. For example, the terminal can report to the base station by including a relaxation criteria met indicator or by setting it to true.

[0209] In operation 1p-25, in response to receiving a report from the terminal indicating that the relaxed criteria are met, the base station can configure the terminal with a more relaxed cell measurement configuration than cell measurement configuration 1 configured in 1p-10 (e.g., cell measurement configuration 2) (e.g., via an RRC reconfiguration message). Conversely, in response to receiving a report from the terminal indicating that the relaxed criteria are not met, the base station may not configure a relaxed cell measurement configuration (e.g., cell measurement configuration 2) for the terminal (e.g., via an RRC reconfiguration message).

[0210] In Operation 1p-30, in response to determining that the relaxed criteria are not met (e.g., when the measurement results of the serving cell or SpCell change significantly), the terminal can perform normal measurements according to Cell Measurement Configuration 1. Conversely, in response to determining that the relaxed criteria are met (e.g., when the measurement results of the serving cell or SpCell change slightly), the terminal can perform measurements under a relaxed version of Cell Measurement Configuration 1 (e.g., performing measurements only on some of the measurement objects or measurement identifiers configured in Cell Measurement Configuration 1, or performing measurements and reporting at a longer period than the reporting configuration period configured in Cell Measurement Configuration 1).

[0211] Figure 1q This is a diagram illustrating the operation performed by a terminal according to an embodiment of the present disclosure, performing a relaxed measurement or reporting whether the relaxed criteria are met based on relaxed criteria.

[0212] In operation 1q-05, the terminal can receive system information.

[0213] In Operation 1q-10, the terminal can reside on the cell.

[0214] In Operation 1q-15, the terminal can establish an RRC connection with the base station and switch to connection mode.

[0215] In Operation 1q-17, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal (e.g., a RedCap terminal) can send information about whether RRM relaxation is supported in connected mode by including or sending such information in the UE capability information message. Similarly, the terminal (e.g., a RedCap terminal) can send information about whether a relaxation criterion satisfaction report (e.g., for static criteria) is supported in connected mode by including or sending such information in the UE capability information message.

[0216] In Operation 1q-20, the terminal can receive relaxation criteria and related parameters (e.g., thresholds for evaluating the stationary criterion) from the base station via RRC reconfiguration messages. Additionally, the terminal can receive cell measurement configurations (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via RRC reconfiguration messages.

[0217] In Operation 1q-25, the terminal can perform signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell) and determine whether the configured relaxed criteria (e.g., stationary criteria) are met based on the measurement results of the serving cell (or SpCell) (e.g., RSRP, RSRQ, SINR).

[0218] In embodiments of this disclosure, after operation 1q-25, the terminal / base station may execute option 1 of 1q-30 and 1q-35, and may not execute option 2 of 1q-30 and 1q-35.

[0219] In embodiments of this disclosure, after operation 1p-15, the terminal / base station may execute option 2 of 1q-30 and 1q-35, and may not execute option 1 of 1q-30 and 1q-35.

[0220] In Operation 1q-30, in response to determining that the relaxed criteria are met, under Option 1, the terminal can report to the base station that the relaxed criteria are met. For example, the terminal can report to the base station by including a relaxed criteria met indicator or by setting it to true. In response to determining that the relaxed criteria are met, under Option 2, the terminal can perform measurements under a relaxed version of Cell Measurement Configuration 1 (e.g., perform measurements only on some of the measurement objects or measurement identifiers configured in Cell Measurement Configuration 1, or perform measurements and reports at a longer period than the reporting configuration period configured in Cell Measurement Configuration 1).

[0221] In operation 1q-35, in response to determining that the relaxation criteria are not met, under option 1, the terminal can report the lack of relaxation criteria to the base station. For example, the terminal can report this to the base station by omitting the relaxation criteria fulfillment indicator or by setting it to false. In response to determining that the relaxation criteria are not met, under option 2, the terminal can perform normal measurements according to cell measurement configuration 1.

[0222] Figure 1r This is a diagram illustrating a process performed by a terminal in connected mode, according to an embodiment of the present disclosure, of performing RRM relaxation based on a relaxation standard using AI / ML-based predictive measurement results.

[0223] In Operation 1r-05, the terminal can be in connection mode with the base station.

[0224] In Operation 1r-07, after receiving a UE capability query message from the base station, the terminal can send information about its capabilities to the base station via a UE capability information message. Here, the terminal (e.g., a RedCap terminal) can send information about whether RRM relaxation is supported in connected mode by including or sending such information in the UE capability information message. Here, the terminal (e.g., a RedCap terminal) can send information about whether it supports a relaxation criterion satisfaction report (e.g., for static criteria) in connected mode by including or sending such information in the UE capability information message. Here, the terminal can report to the base station information about its ability to perform RRM relaxation using predicted cell measurement results by including or sending such information in the UE capability information message.

[0225] In Operation 1r-10, the terminal can receive relaxation criteria and related parameters (e.g., thresholds for evaluating the stationary criterion) from the base station via RRC reconfiguration messages. Additionally, the terminal can receive cell measurement configurations (e.g., cell measurement configuration 1) (e.g., MeasConfig) from the base station via RRC reconfiguration messages. Furthermore, the terminal can receive configurations related to performing RRM relaxation using predicted cell measurement results (e.g., RRM relaxation criteria) from the base station. Additionally, the terminal can receive information from the base station regarding whether RRM relaxation is permitted using predicted cell measurement results.

[0226] In Operation 1r-15, the terminal can execute AI / ML models to derive (output) predicted future measurements of the serving cell (or SpCell) (e.g., RSRP / RSRQ / SINR).

[0227] In Operation 1r-20, the terminal can determine whether the relaxation criteria configured by the base station are met based on the measurement results of the serving cell (or SpCell) obtained by performing signal (e.g., CSI-RS, SSB) measurements on the serving cell (or SpCell), and / or the predicted values ​​(e.g., RSRP, RSRQ, SINR) of the serving cell (or SpCell) obtained by performing predictions using an AI / ML model. For example, the terminal can determine that the relaxation criteria are met when at least one of the following conditions is met.

[0228] -Condition 1. The predicted cell measurement results meet the relaxed criteria.

[0229] -Condition 2. The actual measurement results of the community meet the relaxed standards.

[0230] - Condition 3. For example, in 1r-10, the base station has already allowed the implementation of RRM relaxation using predicted cell measurement results, or has already received the relevant configuration from the base station.

[0231] - Condition 4. For example, in 1r-10, the base station has already allowed the implementation of RRM relaxation using actual cell measurement results, or has already received the relevant configuration from the base station.

[0232] In embodiments of this disclosure, after operation 1r-20, the terminal / base station may execute option 1 (1r-25 and 1r-30) and may not execute option 2 (1r-35).

[0233] In embodiments of this disclosure, after operation 1r-20, the terminal / base station may execute option 2 (1r-35) and may not execute option 1 (1r-25 and 1r-30).

[0234] In Operation 1r-25, in response to the determination that the relaxation criteria are not met (e.g., when the measurement results of the serving cell or SpCell vary greatly), the terminal can report the non-compliance of the relaxation criteria to the base station. For example, the terminal can report this to the base station by omitting the relaxation criterion compliance indicator or by setting it to false.

[0235] Conversely, in response to determining that the relaxation criteria are met (e.g., when the variation in the measurement results of the serving cell or SpCell is small), the terminal can report that the relaxation criteria are met to the base station. For example, the terminal can report to the base station by including a relaxation criteria met indicator or by setting it to true.

[0236] In Operation 1r-30, in response to receiving a report from the terminal indicating that the relaxed criteria are met, the base station can configure the terminal with a more relaxed cell measurement configuration than the cell measurement configuration 1 configured in 1r-10 (e.g., cell measurement configuration 2) (e.g., via an RRC reconfiguration message). Conversely, in response to receiving a report from the terminal indicating that the relaxed criteria are not met, the base station may not configure a relaxed cell measurement configuration (e.g., cell measurement configuration 2) for the terminal (e.g., via an RRC reconfiguration message).

[0237] In Operation 1r-35, in response to determining that the relaxed criteria are not met (e.g., when the measurement results of the serving cell or SpCell change significantly), the terminal can perform normal measurements according to Cell Measurement Configuration 1. Conversely, in response to determining that the relaxed criteria are met (e.g., when the measurement results of the serving cell or SpCell change slightly), the terminal can perform measurements under a relaxed version of Cell Measurement Configuration 1 (e.g., performing measurements only on some of the measurement objects or measurement identifiers configured in Cell Measurement Configuration 1, or performing measurements and reporting at a longer period than the reporting configuration period configured in Cell Measurement Configuration 1).

[0238] In embodiments of this disclosure, when a measurement report is sent (e.g., in 1k-25), the terminal can indicate whether it has performed an AI / ML-based RRM relaxation or a relaxed measurement. In response to receiving the measurement report, the base station can recognize that the terminal has performed an RRM relaxation or a relaxed measurement, calculate its impact on the network and the terminal, and use the result for network optimization and resource management.

[0239] In embodiments of this disclosure, upon a Radio Link Failure (RLF) or Handover Failure (HOF), the terminal can store information about whether AI / ML-based RRM relaxation or a relaxation measurement has been performed as RLF report information and report this information to the base station. This may be useful information for the base station to determine whether the cause of the RLF or HOF stems from the terminal's RRM relaxation.

[0240] In embodiments of this disclosure, the RRM relaxation method executed by the terminal may vary depending on the RRM relaxation criteria already met by the terminal.

[0241] For example, when the terminal is Figure 1g In operation 1g-20, if a condition (e.g., condition 1) is met, then... Figure 1g The relaxed measurement period used in operation 1g-25 can differ from that when the terminal is... Figure 1g When another condition (e.g., condition 3) is met in operation 1g-20, Figure 1g The relaxed measurement cycle used in operation 1g-25.

[0242] For example, when the terminal is Figure 1g When multiple conditions are met in operation 1g-20 (e.g., condition 1 and condition 3), Figure 1g The relaxed measurement cycle used in operation 1g-25 can be longer than when the terminal is in Figure 1g In operation 1g-20, if a condition (e.g., condition 3) is met, then... Figure 1g The relaxed measurement cycle used in operation 1g-25.

[0243] In embodiments of this disclosure, along with information derived as the output of the AI / ML model (e.g., predicted cell measurement results, RRM relaxation criteria, parameters related to RRM relaxation criteria, whether RRM relaxation or RRM relaxation method is performed), the accuracy and / or probability of occurrence of the corresponding information can also be derived as the output of the AI / ML model.

[0244] According to embodiments of this disclosure, a terminal may perform RRM relaxation by using the corresponding information derived as output only when the accuracy and / or probability of occurrence of the corresponding information derived as output is greater than a certain threshold (e.g., a variable value configured by the network, or a fixed value defined in a standard). Otherwise, the terminal may not perform RRM relaxation by using the corresponding information derived as output.

[0245] In embodiments of this disclosure, a terminal may perform RRM relaxation-related operations on neighboring cells based on the measurement results of the serving cell (e.g., RSRP, RSRQ, and / or SINR).

[0246] In embodiments of this disclosure, a terminal may perform RRM relaxation-related operations on the same cell (e.g., cell 1) based on measurement results (e.g., RSRP, RSRQ, and / or SINR) of a specific cell (e.g., cell 1). Determining whether to perform RRM relaxation on a specific cell based on the measurement results of that specific cell is likely the most accurate method.

[0247] For example, applying RRM relaxation (e.g., by extending the measurement period) to a neighboring cell because the serving cell's measurement results change little (e.g., because it meets low mobility criteria) may include the assumption that the neighboring cell will not change significantly compared to the current measurement value. However, even when the serving cell's measurement results change little, the actual measurement results of the neighboring cells may change significantly. In this case, when applying RRM relaxation to a neighboring cell, the terminal may make an incorrect decision about the neighboring cell (e.g., if the neighboring cell's RSRP value decreases rapidly, a terminal in inactive or idle mode may apply RRM relaxation, thus failing to obtain the latest RSRP value of the corresponding cell, and subsequently reselecting and camping on that cell). Accordingly, to determine whether to apply RRM relaxation to a neighboring cell, it may be desirable to base this determination on the measurement value of the corresponding cell. Similarly, the terminal may determine whether to apply RRM relaxation to the serving cell based on the measurement results of the corresponding serving cell. Thus, the terminal can determine and apply different RRM relaxation methods (e.g., different measurement periods) on a per-cell basis.

[0248] Figure 1s This is a block diagram illustrating the internal structure of a terminal 1s-00 according to an embodiment of the present disclosure.

[0249] refer to Figure 1s According to embodiments of the present disclosure, terminal 1s-00 may include radio frequency (RF) processor 1s-10, baseband processor 1s-20, storage device 1s-30, and controller 1s-40.

[0250] RF processor 1s-10 performs functions for transmitting and receiving signals via a radio channel, such as frequency band conversion and signal amplification. That is, RF processor 1s-10 up-converts the baseband signal provided by baseband processor 1s-20 into an RF band signal and transmits it via an antenna, and down-converts the RF band signal received via the antenna back into a baseband signal. For example, RF processor 1s-10 may include a transmit filter, receive filter, amplifier, mixer, oscillator, digital-to-analog converter (DAC), analog-to-digital converter (ADC), etc. Although... Figure 1s Only one antenna is shown, but the terminal may include multiple antennas. Furthermore, the RF processor 1s-10 may include multiple RF chains. Additionally, the RF processor 1s-10 can perform beamforming. For beamforming, the RF processor 1s-10 can adjust the phase and amplitude of signals transmitted and received through multiple antennas or antenna elements. Furthermore, the RF processor can perform multiple-input multiple-output (MIMO) operation and can receive multiple layers while performing MIMO operation.

[0251] The baseband processor 1s-20 performs the conversion function between baseband signals and bit strings according to the system's physical layer specifications. For example, when transmitting data, the baseband processor 1s-20 generates complex symbols by encoding and modulating the transmitted bit string. Furthermore, when receiving data, the baseband processor 1s-20 recovers the received bit string by demodulating and decoding the baseband signal provided from the RF processor 1s-10. For example, in the case of conforming to the OFDM scheme, when transmitting data, the baseband processor 1s-20 generates complex symbols by encoding and modulating the transmitted bit string, maps the complex symbols to subcarriers, and constructs OFDM symbols through inverse fast Fourier transform (IFFT) operations and cyclic prefix (CP) insertion. Furthermore, when receiving data, the baseband processor 1s-20 divides the baseband signal provided from the RF processor 1s-10 into OFDM symbols, recovers the signal mapped to the subcarrier through fast Fourier transform (FFT) operations, and reconstructs the received bit string by demodulating and decoding the signal.

[0252] As described above, the baseband processor 1s-20 and the RF processor 1s-10 transmit and receive signals. Therefore, the baseband processor 1s-20 and the RF processor 1s-10 can be referred to as a transmitter, receiver, transceiver, or communication unit. Furthermore, at least one of the baseband processor 1s-20 and the RF processor 1s-10 may include multiple communication modules to support various different wireless access technologies. Additionally, at least one of the baseband processor 1s-20 and the RF processor 1s-10 may include different communication modules to process signals in different frequency bands. For example, different wireless access technologies may include wireless LAN (e.g., IEEE 802.11), cellular networks (e.g., LTE), etc. Furthermore, different frequency bands may include ultra-high frequency (SHF) bands (e.g., 2.5 GHz, 5 GHz) and millimeter wave (e.g., 60 GHz) bands.

[0253] Storage device 1s-30 stores data for the operation of terminal 1s-00 according to embodiments of the present disclosure, such as basic programs, application programs, and configuration information. Specifically, storage device 1s-30 may store information related to a second access node performing wireless communication using a second wireless access technology. Furthermore, storage device 1s-30 provides stored data upon request from controller 1s-40. Storage device 1s-30 may also be referred to as a memory.

[0254] Controller 1s-40 controls the overall operation of terminal 1s-00. For example, controller 1s-40 transmits and receives signals via baseband processor 1s-20 and RF processor 1s-10. Furthermore, controller 1s-40 writes data to storage device 1s-30 and reads data from storage device 1s-30. For this purpose, controller 1s-40 may include at least one processor. For example, controller 1s-40 may include a communication processor (CP) that performs control for communication, and a higher-level application processor (AP) that controls applications. Controller 1s-40 can control the overall operation of terminal 1s-00 according to the embodiments presented in this disclosure by executing one or more instructions stored in storage device 1s-30.

[0255] Processor 1s-40 may include various processing circuitry and / or multiple processors. For example, the term "processor" as used herein (including in the claims) may include various processing circuitry comprising at least one processor. One or more of the at least one processor may be configured to perform the 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 various functions. However, these terms cover, but are not limited to, situations where one processor performs some functions while other processors perform other functions, and situations where a single processor can perform all functions. Additionally, at least one processor may include a combination of processors configured to perform the various functions disclosed herein in a distributed manner. At least one processor may execute program instructions to implement or perform various functions.

[0256] In an embodiment, at least one processor 1s-40 may be a general-purpose processor (such as a central processing unit (CPU), an AP, or a digital signal processor (DSP)), a dedicated graphics processor (such as a graphics processing unit (GPU) or a vision processing unit (VPU)), or a dedicated artificial intelligence processor (such as a neural processing unit (NPU)). For example, in the case where one or more processors are dedicated artificial intelligence processors, the dedicated artificial intelligence processor may be designed with a hardware architecture specifically designed to process a particular artificial intelligence model.

[0257] Predefined operating rules or artificial intelligence models are generated via a training process. Here, "generated via a training process" can mean generating predefined operating rules or artificial intelligence models configured to perform desired characteristics (or purposes) by training a basic artificial intelligence model (or deep learning model) using a learning algorithm that utilizes a large amount of training data. The training process can be performed by the device itself that executes the artificial intelligence according to this disclosure, or by a separate server and / or system. Examples of learning algorithms can include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

[0258] Artificial intelligence models (or deep learning models) can include multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and neural network operations are performed by calculating the results of the previous layer and these multiple weight values. As a result of training the artificial intelligence model, the multiple weight values ​​in each of the multiple neural network layers can be optimized. For example, multiple weight values ​​can be updated to reduce or minimize the loss or cost values ​​acquired by the artificial intelligence model during the training process. Artificial neural networks can include, but are not limited to, deep neural networks (DNNs), such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), or deep Q-networks.

[0259] Figure 1t This is a block diagram illustrating the configuration of a base station 1t-00 according to an embodiment of the present disclosure.

[0260] refer to Figure 1t According to embodiments of the present disclosure, the base station 1t-00 may include an RF processor 1t-10, a baseband processor 1t-20, a backhaul communication unit 1t-30, a storage device 1t-40, and a controller 1t-50.

[0261] RF processor 1t-10 performs functions for transmitting and receiving signals via a radio channel, such as frequency band conversion and signal amplification. That is, RF processor 1t-10 up-converts the baseband signal provided by baseband processor 1t-20 into an RF band signal and transmits it via an antenna, and down-converts the RF band signal received via the antenna back into a baseband signal. For example, RF processor 1t-10 may include transmit filters, receive filters, amplifiers, mixers, oscillators, DACs, ADCs, etc. Although... Figure 1tOnly one antenna is shown, but the first access node may include multiple antennas. Furthermore, the RF processor 1t-10 may include multiple RF chains. Additionally, the RF processor 1t-10 can perform beamforming. For beamforming, the RF processor 1t-10 can adjust the phase and amplitude of signals transmitted and received through multiple antennas or antenna elements. The RF processor can perform DL MIMO operation by transmitting one or more layers.

[0262] The baseband processor 1t-20 performs the conversion function between baseband signals and bit strings according to the physical layer specification of the first radio access technology. For example, when transmitting data, the baseband processor 1t-20 generates complex symbols by encoding and modulating the transmitted bit string. Furthermore, when receiving data, the baseband processor 1t-20 recovers the received bit string by demodulating and decoding the baseband signal provided from the RF processor 1t-10. For example, in the case of conforming to the OFDM scheme, when transmitting data, the baseband processor 1t-20 generates complex symbols by encoding and modulating the transmitted bit string, maps the complex symbols to subcarriers, and constructs OFDM symbols through IFFT operations and CP insertion. Furthermore, when receiving data, the baseband processor 1t-20 divides the baseband signal provided from the RF processor 1t-10 into OFDM symbols, recovers the signal mapped to the subcarriers through FFT operations, and reconstructs the received bit string by demodulating and decoding the signal. As described above, the baseband processor 1t-20 and the RF processor 1t-10 transmit and receive signals. Therefore, the baseband processor 1t-20 and the RF processor 1t-10 can be referred to as transmitters, receivers, transceivers, communication units, or wireless communication units.

[0263] The backhaul communication unit 1t-30 provides an interface for performing communication with other nodes in the network. That is, the backhaul communication unit 1t-30 converts the bit string to be sent from the main base station to another node (e.g., a secondary base station, core network, etc.) into a physical signal, and converts the physical signal received from another node into a bit string.

[0264] Storage device 1t-40 stores data such as basic programs, application programs, and configuration information for the operation of base station 1t-00. Specifically, storage device 1t-40 can store information about bearers assigned to connected terminals, measurement results reported from connected terminals, etc. Additionally, storage device 1t-40 can store information used as a standard for determining whether to provide or suspend multiple connections to terminals. Furthermore, storage device 1t-40 provides the stored data upon request from controller 1t-50. Storage device 1t-40 may also be referred to as a memory.

[0265] Controller 1t-50 controls the overall operation of main base station 1t-00. For example, controller 1t-50 transmits and receives signals via baseband processor 1t-20 and RF processor 1t-10, or via backhaul communication unit 1t-30. Furthermore, controller 1t-50 writes data to storage device 1t-40 and reads data from storage device 1t-40. For this purpose, controller 1t-50 may include at least one processor. Controller 1t-50 can control the overall operation of base station 1t-00 according to the embodiments presented in this disclosure by executing one or more instructions stored in storage device 1t-40.

[0266] Processor 1t-50 may include various processing circuitry and / or multiple processors. For example, the term "processor" as used herein (including in the claims) may include various processing circuitry comprising at least one processor. One or more of the at least one processor may be configured to perform the 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 various functions. However, these terms cover, but are not limited to, situations where one processor performs some functions while other processors perform other functions, and situations where a single processor can perform all functions. Additionally, at least one processor may include a combination of processors configured to perform the various functions disclosed herein in a distributed manner. At least one processor may execute program instructions to implement or perform various functions.

[0267] In an embodiment, at least one processor 1t-50 may be a general-purpose processor (such as a CPU, AP, or DSP), a dedicated graphics processor (such as a GPU or VPU), or a dedicated artificial intelligence processor (such as an NPU). For example, in the case where one or more processors are dedicated artificial intelligence processors, the dedicated artificial intelligence processor may be designed with a hardware architecture specifically designed to process a particular artificial intelligence model.

[0268] Predefined operating rules or artificial intelligence models are generated via a training process. Here, "generated via a training process" can mean generating predefined operating rules or artificial intelligence models configured to perform desired characteristics (or purposes) by training a basic artificial intelligence model (or deep learning model) using a learning algorithm that utilizes a large amount of training data. The training process can be performed by the device itself that executes the artificial intelligence according to this disclosure, or by a separate server and / or system. Examples of learning algorithms can include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

[0269] Artificial intelligence models (or deep learning models) can include multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and neural network operations are performed by calculating the results of the previous layer and these multiple weight values. As a result of training the artificial intelligence model, the multiple weight values ​​in each of the multiple neural network layers can be optimized. For example, multiple weight values ​​can be updated to reduce or minimize the loss or cost values ​​acquired by the artificial intelligence model during the training process. Artificial neural networks can include, but are not limited to, DNNs, such as CNNs, RNNs, RBMs, DBNs, BRDNNs, or deep Q-networks.

[0270] In the embodiments of this disclosure described above, the elements included in this disclosure have been expressed in singular or plural form according to the proposed embodiments of this disclosure. However, for ease of explanation, the appropriate selection of singular or plural forms of expression as proposed is not intended to limit this disclosure to a single or multiple elements, and even when an element is expressed in plural form, it may have a single element, and even when an element is expressed in singular form, it may have multiple elements.

[0271] Although certain embodiments have been described in the detailed description of this disclosure, various modifications can be made without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the embodiments described above, but should be determined by the appended claims and their equivalents.

[0272] The detailed examples used to describe embodiments according to this disclosure are merely combinations of each standard, method, detailed method, and operation, and through combinations of two or more of the various techniques described above, a terminal or base station can perform AI / ML-based relaxed RRM operations in a next-generation mobile communication system. Here, operations can be performed according to methods determined by one or more of the techniques described above. For example, some operations of an embodiment can be performed in conjunction with some operations of another embodiment.

[0273] Machine-readable storage media can be provided in the form of non-transitory storage media. Here, the term "non-transitory storage media" refers to a tangible device and does not include signals (e.g., electromagnetic waves), and the term "non-transitory storage media" does not distinguish between cases where data is semi-permanently stored in a storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer for temporarily storing data. According to embodiments, methods according to various embodiments disclosed herein can be included in a computer program product and then provided. The computer program product can be traded as a commodity between a seller and a buyer. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., an optical disc read-only memory (CD-ROM)), or can be distributed online through an app store (e.g., downloaded or uploaded) 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 application) can be temporarily stored in a machine-readable storage medium, such as the memory of a manufacturer's server, an app store's server, or a relay server.

Claims

1. A method performed by a user equipment (UE) in a wireless communication system, the method comprising: Obtain configuration information related to the relaxation of Radio Resource Measurement (RRM) based on artificial intelligence / machine learning (AI / ML) from the base station; Information, including predicted cell measurement results, is obtained by using AI / ML. Based on the information including the predicted cell measurement results, determine whether at least one RRM relaxation criterion is met; and Based on the determination, perform either a relaxed RRM measurement or a normal RRM measurement.

2. The method according to claim 1, further comprising: The base station receives information indicating whether the AI / ML-based RRM relaxation is permitted.

3. The method according to claim 1, further comprising: The parameters associated with the RRM relaxation standard or the RRM relaxation standard itself are obtained by using the AI / ML. as well as The relaxed RRM measurement or the normal RRM measurement is performed based on the acquired parameters associated with the RRM relaxation standard or the acquired RRM relaxation standard itself.

4. The method according to claim 3, wherein, The parameters associated with the RRM relaxation criteria include at least one of the following: Parameters indicating the measurement-related thresholds of the serving cell; or Parameters included in the configuration information related to AI / ML-based RRM.

5. The method according to claim 1, further comprising: The AI / ML is used to obtain information indicating whether to perform RRM relaxation; as well as Based on the obtained information indicating whether to perform the RRM relaxation, perform the relaxed RRM measurement or the normal RRM measurement.

6. The method according to claim 1, further comprising: Information related to the RRM relaxation method is obtained by using the AI / ML, and the information related to the RRM relaxation method includes at least one of information about the measurement cycle, information about the measurement frequency, or information about the relaxation activation time interval; In response to successfully acquiring the information related to the RRM relaxation method, the relaxed RRM measurement is performed based on the acquired information related to the RRM relaxation method; as well as In response to the failure to obtain the information related to the RRM relaxation method, the normal RRM measurement is performed.

7. The method according to any one of claims 1 to 6, wherein, The UE is in an inactive or idle state, and Obtaining the configuration information related to AI / ML-based RRM relaxation from the base station includes obtaining system information from the base station that includes the configuration information related to AI / ML-based RRM relaxation.

8. The method according to any one of claims 1 to 5, wherein, The UE is in a connected state, and Obtaining the configuration information related to AI / ML-based RRM relaxation from the base station also includes: The base station sends UE capability information, including information about capabilities related to the AI / ML-based RRM relaxation; and Receive from the base station a Radio Resource Control (RRC) reconfiguration message including configuration information related to the AI / ML-based RRM relaxation.

9. The method according to claim 1, further comprising: When performing the relaxed RRM measurement, information indicating that the relaxed RRM measurement has been performed is sent to the base station via a measurement report, a radio link failure (RLF) report, or a handover failure (HOF) report.

10. The method according to claim 1, wherein, Information related to the RRM relaxation method to be applied when performing the relaxed RRM measurement is determined based on which of the at least one RRM relaxation criteria is met, and The information associated with the RRM relaxation method includes at least one of information about the measurement cycle, information about the measurement frequency, or information about the relaxation activation time interval.

11. The method according to claim 1, wherein, When information is acquired using the AI / ML method, the accuracy of the acquired information is derived, and The method further includes: in response to the accuracy exceeding a certain threshold, performing the relaxed RRM measurement based on the information obtained by using the AI / ML.

12. A user equipment (UE) in a wireless communication system, the UE comprising: A memory that stores one or more instructions; and At least one processor, Wherein, the at least one processor is configured to execute the one or more instructions stored in the memory to: Obtain configuration information related to the relaxation of Radio Resource Measurement (RRM) based on artificial intelligence / machine learning (AI / ML) from the base station; Information, including predicted cell measurement results, is obtained by using AI / ML. Based on the information including the predicted cell measurement results, determine whether at least one RRM relaxation criterion is met; and Based on the determination, perform either a relaxed RRM measurement or a normal RRM measurement.

13. The UE according to claim 12, wherein, The at least one processor is also configured to execute one or more instructions stored in the memory to receive information from the base station indicating whether the AI / ML-based RRM relaxation is permitted.

14. A method performed by a base station in a wireless communication system, the method comprising: The system broadcasts configuration information related to Radio Resource Measurement (RRM) relaxation based on Artificial Intelligence / Machine Learning (AI / ML) to the User Equipment (UE) via system information, or sends the configuration information to the UE via Radio Resource Control (RRC) reconfiguration messages; and The UE receives at least one of the following: information on cell measurement results predicted using AI / ML; parameters associated with RRM relaxation criteria predicted using the AI / ML; or information indicating that relaxed RRM measurements have been performed.

15. A base station in a wireless communication system, the base station comprising: A memory that stores one or more instructions; and At least one processor, Wherein, the at least one processor is configured to execute the one or more instructions stored in the memory to: The system broadcasts configuration information related to Radio Resource Measurement (RRM) relaxation based on Artificial Intelligence / Machine Learning (AI / ML) to the User Equipment (UE) via system information, or sends the configuration information to the UE via Radio Resource Control (RRC) reconfiguration messages; and The UE receives at least one of the following: information on cell measurement results predicted using AI / ML; parameters associated with RRM relaxation criteria predicted using the AI / ML; or information indicating that relaxed RRM measurements have been performed.

Images