Method and apparatus for determining machine learning model based on network congestion information in wireless communication system

Abstract

According to one embodiment of the present invention, there is provided a method performed by an access and mobility management function (AMF) node in a wireless communication system. The method includes receiving a first control message including information on a registration request from a terminal, transmitting a registration response message including information on whether network analysis of the terminal is acceptable to the terminal, transmitting a message requesting the information on the network analysis to a network data collection and analysis function (NWDAF) node based on the first control message, and transmitting a registration response message including the information on the network analysis to the terminal based on the registration response message. Receiving information about the network analysis from the NWDAF node, identifying information about network congestion of the terminal based on the information about the network analysis, and transmitting a second control message including the information about the network congestion to the terminal.

Description

Technical Field

[0001] The present disclosure relates to a method and apparatus for determining a machine learning model and algorithm in a wireless communication system. More specifically, the present disclosure relates to a method and apparatus in which a machine learning application of a terminal receives network congestion information from a network, and determines a machine learning model to be applied to the application based on the received information in the wireless communication system. Background Art

[0002] The fifth generation (5G) mobile communication technology defines a wide frequency band, making high transmission rates and new services possible, and can be implemented not only in "sub-6 gigahertz (GHz)" frequency bands such as 3.5 GHz, but also in "higher than 6 GHz" frequency bands called millimeter waves (mmWave) including 28 GHz and 39 GHz. In addition, the implementation of the sixth generation (6G) mobile communication technology (called a super 5G system) in the terahertz (THz) frequency band (e.g., 95 GHz to 3 THz frequency band) has been considered to achieve a transmission rate fifty times faster than that of 5G mobile communication technology and an ultra-low latency of one tenth of that of 5G mobile communication technology.

[0003] At the beginning of the development of 5G mobile communication technology, in order to support services and meet performance requirements related to enhanced Mobile BroadBand (eMBB), Ultra Reliable Low Latency Communication (URLLC) and massive Machine-Type Communication (mMTC), standardization is underway on beamforming and massive multiple-input multiple-output (MIMO) for mitigating radio wave path loss in millimeter waves and increasing millimeter wave transmission distances, supporting parameter sets for dynamic operation of millimeter wave resources and time slot formats for efficient utilization (e.g., operating multiple subcarrier spacings), initial access technology for supporting multi-beam transmission and broadband, definition and operation of BandWidth Part (BWP), new channel coding methods such as Low Density Parity Check (LDPC) codes for large amounts of data transmission and polar codes for highly reliable transmission of control information, L2 preprocessing, and network slicing for providing dedicated networks dedicated to specific services.

[0004] Currently, discussions are underway regarding improvements and performance enhancements to initial 5G mobile communication technologies in view of the services they support, and there is already standardization of the physical layer of the technologies, such as Vehicle-to-everything (V2X) for assisting driving determination of autonomous vehicles based on information about the location and status of the vehicle sent by the vehicle and for enhancing user convenience, New Radio Unlicensed (NR-U) for system operations designed to comply with various regulatory requirements in unlicensed bands, new radio (NR) user equipment (UE) power saving, Non-Terrestrial Network (NTN) (which is UE-satellite direct communication for providing coverage in areas where communication with terrestrial networks is unavailable), and positioning.

[0005] In addition, there is ongoing standardization in the air interface architecture / protocol on technologies such as the Industrial Internet of Things (IIoT) for supporting new services through interworking and convergence with other industries, Integrated Access and Backhaul (IAB) for providing nodes for network service area expansion by supporting wireless backhaul links and access links in an integrated manner, mobility enhancements including conditional switching and dual-active protocol stack (DAPS) switching, and two-step random access (i.e., 2-step random access channel (RACH) for NR) for simplifying the random access process. There is also ongoing standardization on 5G baseline architecture (e.g., service-based architecture or service-based interface) for combining Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies and system architecture / services for Mobile Edge Computing (MEC) for receiving services based on UE location.

[0006] As 5G mobile communication systems are commercialized, the number of connected devices, which has been growing exponentially, will be connected to the communication network, and it is therefore expected that enhanced functionality and performance of the 5G mobile communication system and integrated operation of connected devices will be necessary. To this end, new research related to extended reality (eXtended Reality, XR) is arranged to effectively support augmented reality (Augmented Reality, AR), virtual reality (Virtual Reality, VR), mixed reality (Mixed Reality, MR), etc., by utilizing artificial intelligence (Artificial Intelligence, AI) and machine learning (Machine Learning, ML), AI service support, metaspace service support and drone communication to improve 5G performance and reduce complexity.

[0007] In addition, such development of 5G mobile communication systems will serve as a foundation for developing not only new waveforms for providing coverage in the terahertz band of 6G mobile communication technology, multi-antenna transmission technologies such as full Dimensional MIMO (FD-MIMO), array antennas, and massive antennas, metamaterial-based lenses and antennas for improving coverage of terahertz band signals, high-dimensional spatial multiplexing technology using orbital angular momentum (OAM), and reconfigurable intelligent surfaces (RIS), but also full-duplex technology for improving the frequency efficiency of 6G mobile communication technology and improving system networks, AI-based communication technology for achieving system optimization by utilizing satellite and artificial intelligence models (AI) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for implementing services at a complexity level that exceeds the limits of UE operating capabilities by utilizing ultra-high performance communication and computing resources.

[0008] The Internet is a human-centric connected network where humans generate and consume information, and is now evolving into the Internet of Things (IoT), where distributed entities (such as things) exchange and process information without human intervention. The Internet of Everything (IoE) can be an example of a combination of IoT technology and big data processing technology through connection with cloud servers.

[0009] Since IoT implementation requires technical elements such as “sensing technology”, “wired / wireless communication and network infrastructure”, “service interface technology” and “security technology”, sensor networks, machine-to-machine (M2M) communication, machine type communication (MTC), etc. have been studied recently.

[0010] Such an IoT environment can provide intelligent Internet technology (IT) services that create new value for human life by collecting and analyzing data generated between connected things. Through the integration and combination between existing information technology (IT) and various industrial applications, IoT can be applied to various fields, including smart homes, smart buildings, smart cities, smart cars or connected cars, smart grids, healthcare, smart appliances, and advanced medical services.

[0011] In line with this, various attempts have been made to apply 5G communication systems to IoT networks. For example, technologies such as sensor networks, machine type communications (MTC), and machine-to-machine (M2M) communications can be implemented through beamforming, MIMO, and array antennas. The application of cloud radio access networks (cloud RANs) as the above-mentioned big data processing technology can also be considered as an example of the fusion of 5G technology and IoT technology.

[0012] With the development of mobile communication systems as described above, terminals can easily use the computing power provided by the server of the network through the mobile communication system as needed, so AI applications that use machine learning (ML) algorithms are increasingly considered, which require complex calculations that are considered impossible in the terminal. These AI applications use methods that utilize the resources of the network server through the wireless communication system, and the application performance experienced by the user is greatly affected by the communication state of the wireless communication system. Therefore, a method that can control the ML model and algorithm according to the state of the wireless communication system is needed.

[0013] The above information is presented as background information only to assist with an understanding of the present disclosure. No determination has been made, and no assertion is made, as to whether any of the above may be applicable as prior art with respect to the present disclosure. Summary of the invention

[0014] Solution to the problem

[0015] Aspects of the present disclosure address at least the above-mentioned problems and / or disadvantages and provide at least the advantages described below. Therefore, one aspect of the present disclosure is to provide an apparatus and method capable of providing improved application efficiency in a wireless communication system.

[0016] Another aspect of the present disclosure is to provide a method and apparatus in which a terminal requests and receives network status information, and determines a machine learning model and algorithm to be applied to an application based on the information in a wireless communication system.

[0017] Another aspect of the present disclosure is to provide a method and apparatus in which a network entity for providing data analysis and collection functions provides network status information requested by a user equipment (UE) in a wireless communication system.

[0018] Another aspect of the present disclosure is to provide a method and apparatus for controlling a signal flow between network function (NF) entities to transmit data required for analyzing a network congestion state.

[0019] Another aspect of the present disclosure is to provide a method and apparatus for controlling a signal flow between a terminal and a network function entity to transmit network status information to the terminal.

[0020] Additional aspects will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the presented embodiments.

[0021] According to one aspect of the present disclosure, a method performed by an access and mobility management function (AMF) node in a wireless communication system is provided. The method includes receiving a first control message including information about a registration request from a terminal, sending a registration response message including information about whether a network analysis of the terminal is acceptable to the terminal, sending a message requesting information about network analysis to a network data collection and analysis function (NWDAF) node based on the first control message, receiving information about network analysis from the NWDAF node, identifying information about network congestion of the terminal based on the information about network analysis, and sending a second control message including information about network congestion to the terminal.

[0022] According to another aspect of the present disclosure, a method performed by a terminal in a wireless communication system is provided. The method includes sending a first control message including information about a registration request to an access and mobility management function (AMF) node, receiving a registration response message including information about whether a network analysis of the terminal is acceptable from the AMF node, receiving a second control message including information about network congestion from the AMF node, the second control message being identified based on information about network analysis sent from a network data collection and analysis function (NWDAF) node, and identifying an artificial intelligence (AI) / machine learning (ML) model used by the terminal based on the information about network congestion.

[0023] Various embodiments of the present disclosure may provide an apparatus and method capable of effectively providing a service in a wireless communication system.

[0024] Other aspects, advantages, and salient features of the present disclosure will become apparent to those skilled in the art from the following detailed description which, in conjunction with the accompanying drawings, discloses various embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings, in which:

[0026] Figure 1 A communication network including a core network entity in a wireless communication system according to an embodiment of the present disclosure is shown;

[0027] Figure 2A A wireless environment including a core network in a wireless communication system according to an embodiment of the present disclosure is shown;

[0028] Figure 2B The configuration of the core network object in the wireless communication system according to the embodiment of the present disclosure is shown;

[0029] Figure 2C The configuration of a UE in a wireless communication system according to an embodiment of the present disclosure is shown;

[0030] Figure 3 A communication network including network data collection and analysis functions according to an embodiment of the present disclosure is shown;

[0031] Figure 4 A general structure of a wireless communication system according to an embodiment of the present disclosure is shown, wherein a UE receives and applies network congestion information;

[0032] Figure 5 is a signal flow illustrating collection and analysis of network data by a UE according to an embodiment of the present disclosure;

[0033] Figure 6 is a signal flow showing a change in a model and algorithm to be applied based on network congestion information received by a UE according to an embodiment of the present disclosure;

[0034] Figure 7 is a flowchart illustrating the operation of an AMF for determining a machine learning model based on network congestion information according to an embodiment of the present disclosure; and

[0035] Figure 8 is a flowchart illustrating the operation of a UE for determining a machine learning model based on network congestion information according to an embodiment of the present disclosure.

[0036] Throughout the drawings, it should be noted that like reference numbers are used to depict the same or similar elements, features, and structures. DETAILED DESCRIPTION

[0037] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of the various embodiments of the present disclosure as defined by the claims and their equivalents. It includes various specific details to assist in understanding, but these details should be considered as merely exemplary. Therefore, it will be appreciated by those of ordinary skill in the art that various changes and modifications may be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and structures may be omitted for clarity and conciseness.

[0038] The terms and words used in the following description and claims are not limited to the bibliographical meanings, but are merely used by the inventor to enable a clear and consistent understanding of the present disclosure. Therefore, it will be apparent to those skilled in the art that the following description of various embodiments of the present disclosure is provided for illustrative purposes only and not for the purpose of limiting the present disclosure as defined by the appended claims and their equivalents.

[0039] It should be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more of such surfaces.

[0040] When describing the embodiments of the present disclosure, when it is determined that the description may make the subject matter of the present disclosure unnecessarily unclear, the detailed description of the known functions or configurations incorporated herein will be omitted. The terms to be described below are defined in consideration of the functions in the present disclosure and may differ depending on the user, the user's intention or custom. Therefore, the definition of the terms should be based on the content in the entire specification.

[0041] For the same reason, in the accompanying drawings, some elements may be exaggerated, omitted or schematically shown. In addition, the size of each element does not fully reflect the actual size. In the accompanying drawings, the same or corresponding elements have the same reference numerals.

[0042] By referring to the embodiments described in detail below in conjunction with the accompanying drawings, the advantages and features of the present disclosure and the ways to achieve them will be apparent. However, the present disclosure is not limited to the embodiments set forth below, but can be implemented in various different forms. The following embodiments are provided only to fully disclose the present disclosure and inform those skilled in the art of the scope of the present disclosure, and the present disclosure is limited only by the scope of the appended claims.

[0043] Here, it should be understood that each box of the flowchart diagram and the combination of boxes in the flowchart diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a device for implementing the function specified in one or more flowchart boxes. These computer program instructions can also be stored in a computer-usable or computer-readable memory, which can instruct the computer or other programmable data processing device to act in a specific way, so that the instructions stored in the computer-usable or computer-readable memory produce a product including an instruction device that implements the function specified in one or more flowchart boxes. The computer program instructions can also be loaded on a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the function specified in one or more flowchart boxes.

[0044] In addition, each frame of the flowchart diagram can represent a module, a fragment or a portion of a code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions mentioned in the frame may not occur in order. For example, two frames shown in succession can actually be performed substantially simultaneously, or these frames can sometimes be performed in reverse order, depending on the functions involved.

[0045] As used in the embodiments of the present disclosure, "unit" refers to a software element or hardware element that performs a predetermined function, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). However, "unit" does not always have a meaning limited to software or hardware. "Unit" can be constructed to be stored in an addressable storage medium or to execute one or more processors. Therefore, "unit" includes, for example, software elements, object-oriented software elements, class elements or task elements, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcodes, circuits, data, databases, data structures, tables, arrays and parameters. The elements and functions provided by "unit" can be combined into a smaller number of elements or "units", or divided into a larger number of elements or "units". In addition, elements and "units" can be implemented as one or more central processing units (CPUs) in a reproduction device or a secure multimedia card. In addition, "unit" in an embodiment can include one or more processors.

[0046] In the following description, for the convenience of description, some terms and names defined in a communication standard based on the Third Generation Partnership Project Long Term Evolution (3GPP LTE) (e.g., a standard for 5G, NR, LTE, or similar systems) may be used. However, the present disclosure is not limited to these terms and names and can be applied to systems conforming to other standards in the same manner.

[0047] In the following description, for the sake of convenience of description, terms for identifying access nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, terms referring to various identification information, etc. are illustratively used. Therefore, the present disclosure is not limited to the terms used below, and other terms relating to subjects with equivalent technical meanings may be used.

[0048] Hereinafter, the present disclosure relates to an apparatus and method for determining a machine learning (ML) model in a wireless communication system. Specifically, the present disclosure describes a technology in which a machine learning application of a terminal receives network congestion information from a network, and determines a machine learning model to be applied to the application based on the received information in the wireless communication system.

[0049] Figure 1 A communication network 100 including a core network entity in a wireless communication system according to an embodiment of the present disclosure is shown. A 5G mobile communication network may include a 5G user equipment (UE) 110, a 5G radio access network (RAN) 120, and a 5G core network.

[0050] The 5G core network may include network functions such as an access and mobility management function (AMF) 150 for providing a mobility management function for a UE, a session management function (SMF) 160 for providing a session management function, a user plane function (UPF) 170 for performing data transmission, a policy control function (PCF) 180 for providing a policy control function, a unified data management (UDM) 153 for providing a function of managing data such as subscriber data and policy control data, or a unified data repository (UDR) for storing data of various network functions.

[0051] refer to Figure 1, a user equipment (UE) 110 may perform communication through a radio channel (i.e., access network) established with a base station (e.g., eNodeB (eNB) or next generation Node B (gNB)). In some embodiments, the UE 110 is a device used by a user and may be a device configured to provide a user interface (UI). As an example, the UE 110 may be a device installed on a vehicle for driving. In some other embodiments, the UE 110 may be a device that performs machine type communication (MTC) that operates without user participation, or may be an autonomous vehicle. In addition to electronic devices, the UE may also be referred to as terms such as "terminal", "vehicle terminal", "user equipment (UE)", "mobile station", "user station", "remote terminal", "wireless terminal", "user equipment", or other terms with equivalent technical meanings. In addition to the UE, a customer-premises equipment (CPE) or a dongle type terminal may be used as a terminal. The customer-premises equipment may provide a network to other communication devices (e.g., a laptop) while being connected to a next generation radio access network (NG-RAN) node (such as a UE).

[0052] refer to Figure 1 , the AMF 150 provides functions for access and mobility management in units of UE 110, and each UE 110 may be basically connected to one AMF 150. Specifically, the AMF 150 may perform at least one function of signaling between core network nodes for mobility between 3GPP access networks, an interface (N2 interface) between the radio access network (e.g., 5G RAN) 120, NAS signaling with the UE 110, identification of the SMF 160, and transmission and provision of session management (SM) messages between the UE 110 and the SMF 160. Some or all functions of the AMF 150 may be supported within a single instance of one AMF 150.

[0053] refer to Figure 1, SMF 160 provides session management functions, and when UE 110 has multiple sessions, each session may be managed by a different SMF 160. Specifically, SMF 160 may perform at least one of session management (e.g., establishment, modification, and release of sessions, including maintenance of channels between UPF 170 and access network nodes), selection and control of user plane (UP) functions, configuration of traffic steering for routing traffic from UPF 170 to an appropriate destination, termination of the SM part of NAS messages, downlink data notification (DDN), and initiator of AN-specific SM information (e.g., transmitted to the access network via AMF 150 through the N2 interface). Some or all functions of SMF 160 may be supported within a single instance of one SMF 160.

[0054] In the 3GPP system, the conceptual link connecting between network functions (NFs) in the 5G system may be referred to as a reference point. A reference point may also be referred to as an interface. Figure 1 , FIG. 2A to FIG. 2C and Figures 3 to 7 The reference points included in the 5G system architecture are described as follows.

[0055] -N1: Reference point between UE 110 and AMF 150

[0056] -N2: Reference point between (R)AN 120 and AMF 150

[0057] -N3: Reference point between (R)AN 120 and UPF 170

[0058] -N4: Reference point between SMF 160 and UPF 170

[0059] -N5: Reference point between PCF 180 and application function (AF) 130

[0060] -N6: Reference point between UPF 170 and data network (DN) 140

[0061] -N7: Reference point between SMF 160 and PCF 180

[0062] -N8: Reference point between UDM 153 and AMF 150

[0063] -N9: Reference point between two cores UPF 170

[0064] -N10: Reference point between UDM 153 and SMF 160

[0065] -N11: Reference point between AMF 150 and SMF 160

[0066] - N12: Reference point between AMF 150 and authentication server function (AUSF) 151

[0067] -N13: Reference point between UDM 153 and authentication server function 151

[0068] -N14: Reference point between two AMF 150

[0069] -N15: Reference point between PCF 180 and AMF 150 in case of non-roaming scenario, and between PCF 180 and AMF 150 within the visited network in case of roaming scenario

[0070] Figure 2A A wireless environment including a core network 200 in a wireless communication system according to an embodiment of the present disclosure is shown.

[0071] refer to Figure 2A , the wireless communication system includes a radio access network (RAN) 120 and a core network (CN) 200.

[0072] The radio access network 120 is a network directly connected to a user equipment (e.g., UE 110) and is an infrastructure that provides wireless access to UE 110. The radio access network 120 includes a set of multiple base stations including a base station 125, and the multiple base stations can perform communication through interfaces established between the base stations. At least some of the interfaces between the multiple base stations can be formed in a wired or wireless manner. The base station 125 may have a structure in which a central unit (CU) and a distributed unit (DU) are separated. In this case, one CU can control multiple DUs. In addition to a base station, the base station 125 may also be referred to as an 'access point (AP)', 'next generation node B (gNB)', 'fifth generation node (5G node)', 'radio point', 'transmission / reception point (TRP)' or other terms with equivalent technical meanings. UE 110 accesses the radio access network 120 and communicates with the base station 125 through a radio channel. In addition to terminal, UE 110 may also be referred to as terms including "user equipment (UE)", "mobile station", "subscriber station", "remote terminal", "wireless terminal", "user device" or other terms with equivalent technical meanings.

[0073] The core network 200 is a network that manages the entire system, controls the radio access network 120, and processes data and control signals for the UE 110 that are sent and received through the radio access network 120. The core network 200 performs various functions, such as controlling the user plane and the control plane, processing mobility, managing subscriber information, charging, and interworking with other types of systems (e.g., a long term evolution (LTE) system). In order to perform the above-mentioned various functions, the core network 200 may include a plurality of functionally separated entities having different network functions (NFs). For example, the core network 200 may include an access and mobility management function (AMF) 150, a session management function (SMF) 160, a user plane function (UPF) 170, a policy and charging function (PCF) 180, a network repository function (NRF) 159, a user data management (UDM) 153, a network exposure function (NEF) 155, and a unified data repository (UDR) 157.

[0074] The UE 110 is connected to the radio access network 120 and accesses the AMF 150 that performs a mobility management function of the core network 200. The AMF 150 is a function or device responsible for both access to the radio access network 120 and mobility management of the UE 110. The SMF 160 is an NF for managing sessions. The AMF 150 is connected to the SMF 160 and routes messages related to the sessions of the UE 110 to the SMF 160. The SMF 160 is connected to the UPF 170, allocates user plane resources to be provided to the UE 110, and establishes a channel to transmit data between the base station 125 and the UPF 170. The PCF 180 controls information related to policies and charging of sessions used by the UE 110. The NRF 159 performs a function of storing information about NFs installed in the mobile communication service provider network and notifying the stored information. The NRF 159 can be connected to all NFs. When starting operation in the service provider network, each NF provides notification that the corresponding NF is operating in the network to the NRF 159 by performing registration in the NRF 159. The UDM 153 is an NF for performing a function similar to that of a home subscriber server (HSS) of a fourth generation (4G) network, and stores subscription information of the UE 110 or a context used by the UE 110 in the network.

[0075] NEF 155 is used to connect a third-party server and NF in the 5G mobile communication system. In addition, NEF is used to provide data to UDR 157, or to update or obtain data. UDR 157 performs the functions of storing subscription information of UE 110, storing policy information, storing data exposed to the outside, or storing information required by third-party applications. In addition, UDR 157 is also used to provide stored data to another NF.

[0076] Figure 2B The configuration of the core network object in the wireless communication system according to an embodiment of the present disclosure is shown. Figure 2B The configuration 200 shown in FIG. 2 may be understood as having Figure 1 The term "unit" or "device" used hereinafter may refer to a unit for processing at least one function or operation and may be implemented in hardware, software, or a combination of hardware and software.

[0077] refer to Figure 2B , the core network object includes a communication unit 210 , a memory 230 , and a controller 220 .

[0078] The communication unit 210 provides an interface for communicating with other devices in the network. That is, the communication unit 210 converts a bit string sent from a core network object to another device into a physical signal, and converts a physical signal received from another device into a bit string. That is, the communication unit 210 can send or receive a signal. Therefore, the communication unit 210 can be referred to as a modem, a transmitter, a receiver, or a transceiver. Here, the communication unit 210 enables the core network object to communicate with other devices or systems via a backhaul connection (e.g., a wired backhaul or a wireless backhaul) or via a network.

[0079] The memory 230 stores data such as basic programs, application programs, and configuration information for the operation of core network objects. The memory 230 may include a volatile memory, a nonvolatile memory, or a combination of volatile and nonvolatile memories. In addition, the memory 230 provides stored data according to a request of the controller 220.

[0080] The controller 220 is used to control the overall operation of the core network object. For example, the controller 220 is configured to send or receive a signal through the communication unit 210. In addition, the controller 220 is configured to write data to the memory 230 and read data from the memory 230. To this end, the controller 220 may include at least one processor. According to various embodiments of the present disclosure, the controller 220 may be configured to perform control to achieve synchronization using a wireless communication network. For example, the controller 220 may be configured to control the core network object to perform operations according to the various embodiments described below.

[0081] Figure 2C The configuration of a UE in a wireless communication system according to an embodiment of the present disclosure is shown. Figure 2C The configuration shown in may be understood as the configuration of UE 110. The term "unit" or "device" used hereinafter may refer to a unit for processing at least one function or operation and may be implemented in hardware, software, or a combination of hardware and software.

[0082] refer to Figure 2C , the UE includes a communication unit 240, a memory 250 and a controller 260.

[0083] The communication unit 240 performs a function for sending or receiving a signal through a wireless channel. For example, the communication unit 240 performs a conversion function between a baseband signal and a bit stream according to the physical layer standard of the system. For example, when sending data, the communication unit 240 generates a complex symbol by encoding and modulating the transmission bit stream. In addition, when receiving data, the communication unit 240 recovers the received bit stream by demodulating and decoding the baseband signal. In addition, the communication unit 240 up-converts the baseband signal to an RF band signal and transmits the RF band signal through an antenna, and down-converts the RF band signal received by the antenna to a baseband signal. For example, the communication unit 240 may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), etc.

[0084] In addition, the communication unit 240 may include multiple transmit / receive paths. In addition, the communication unit 240 may include at least one antenna array having multiple antenna elements. In terms of hardware, the communication unit 240 may include digital circuits and analog circuits (e.g., radio frequency integrated circuits (RFIC)). The digital circuits and analog circuits may be implemented in a single package. In addition, the communication unit 240 may include multiple RF chains. In addition, the communication unit 240 may perform beamforming.

[0085] The communication unit 240 transmits and receives signals as described above. Therefore, all or part of the communication unit 240 may be referred to as a "transmitter," "receiver," or "transceiver." In addition, the transmission and reception performed through the wireless channel described in the following description may be understood to imply that the above-mentioned processing is performed by the communication unit 240.

[0086] The memory 250 may store data such as basic programs, applications, configuration information, etc. for the operation of the UE. The memory 250 may include a volatile memory, a nonvolatile memory, or a combination of a volatile memory and a nonvolatile memory. The memory 250 provides stored data in response to a request of the controller 260.

[0087] The controller 260 is configured to control the overall operation of the UE. For example, the controller 260 is configured to send and receive signals via the communication unit 240. In addition, the controller 260 is configured to record data in the memory 250 and read the recorded data. The controller 260 can be configured to perform the functions of the protocol stack required by the communication standard. To this end, the controller 260 may include at least one processor or microprocessor, or may be a part of a processor. A part of the communication unit 240 and the controller 260 may be referred to as a communication processor (CP). According to various embodiments, the controller 260 may be configured to perform control to achieve synchronization using a wireless communication network. For example, the controller 260 may be configured to control the UE to perform operations according to the various embodiments described below.

[0088] In the following description, for the sake of convenience of description, terms for identifying access nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, terms referring to various identification information, etc. are illustratively used. Therefore, the present disclosure is not limited to the terms used below, and other terms relating to subjects with equivalent technical meanings may be used.

[0089] The following detailed description of an embodiment of the present disclosure relates to a new RAN (NR) as a radio access network and a packet core (5G system, 5G core network or next generation core (NG core)) as a core network, which is specified in the 5G mobile communication standard defined by the Third Generation Partnership Project Long Term Evolution (3GPP LTE) as a mobile communication standardization group, but based on the determination of those skilled in the art, the main concepts of the present disclosure can be applied to other communication systems with similar backgrounds or channel types with some modifications without significantly departing from the scope of the present disclosure.

[0090] In the 5G system, in order to support network automation, a network data collection and analysis function (NWDAF) may be defined, which is a network function that provides functions for analyzing and providing data collected from the 5G network. The NWDAF may collect / store / analyze information from the 5G network and provide its results to at least one network function (NF), and the analysis results may be used independently in each NF.

[0091] The 5G mobile communication system can support NF to use the results of collecting and analyzing network-related data (hereinafter referred to as network data) through NWDAF. This support is performed to provide the collection and analysis of necessary network data in a centralized form so that each NF can effectively provide its own functions. NWDAF can use network slices as basic units to collect and analyze network data. However, the scope of the present disclosure is not limited to the network slice unit, and NWDAF can additionally analyze user equipment (UE), protocol data unit (PDU) sessions, NF status and / or various information (e.g., quality of service) obtained from an external service server.

[0092] The results analyzed by NWDAF are delivered to each NF that has requested the analysis results, and the delivered analysis results can be used to optimize network management functions such as guarantee / improvement of quality of service (QoS), traffic control, mobility management, and load balancing.

[0093] A unit node that performs each function provided by the 5G network system may be defined as an NF (e.g., an NF entity or an NF node). Each NF may include at least one of the following: an access and mobility management function (AMF) that manages access and mobility to an access network (AN) of a UE, a session management function (SMF) that performs session-related management, a user plane function (UPF) that manages a user data plane, and a network slice selection function (NSSF) 190( Figure 1 ).

[0094] Figure 3 A communication network including a network data collection and analysis function (NWDAF) according to an embodiment of the present disclosure is shown.

[0095] refer to Figure 3, the NWDAF 305 may collect network data from at least one source NF (e.g., NF in the 5G core network, such as AMF 310, SMF 315, or UPF 325, 330, 335, an application function (AF) for effective service provision, a network exposure function (NEF), or operation, administration, and maintenance (OAM)) in various ways. The AMF 310 may be connected to the UE 300 and the radio access network (RAN) 320. The UPF 325, 330, 335 may connect the user traffic of the UE 300 to at least one data network (DN) 340 through the RAN 320.

[0096] The NWDAF 305 may provide at least one consumer NF with analysis of network data collected from the network or externally. The NWDAF 305 may collect and analyze the load levels of network slice instances and provide them to the NSSF for selection by a specific UE. The service-based interface defined in the 5G network may be used to request analysis information or to transmit analysis information including analysis results between NFs 310 and 315 (such as AMF and SMF) and the NWDAF 305. Hypertext transfer protocol (HTTP) and / or javascript object notation (JSON) documents may be used as a transmission method for analysis information.

[0097] According to an embodiment, the collected data of NWDAF 305 may include an application identifier (ID) from a point coordination function (PCF), Internet Protocol (IP) filter information or media / application bandwidth, a UE identifier or location information from AMF 310, a destination data network name (DNN) from SMF, UE IP, QoS flow bit rate, QoS flow ID (QFI), QoS flow error rate or QoS flow delay, or at least one of a traffic usage report from UPF.

[0098] In addition to the NFs constituting the core network, the NWDAF 305 may also collect at least one of NF resource status, NF throughput, or service level agreement (SLA) information provided from the OAM which is an entity that may affect the connection between the UE 300 and the service server, at least one of UE status, UE application information, or UE usage pattern provided from the UE 300, or at least one of application identifiers, service experiences, or business patterns of services provided by the AF, and may use them for analysis.

[0099] In the following, Tables 1 to 3 show examples of network data collected by NWDAF. However, according to various embodiments of the present disclosure, this is only an example, and the network data collected by NWDAF is not limited to Tables 1 to 3. The period and time point at which NWDAF 305 collects network data from each entity may be different for each entity. Based on the association ID for associating the data to be collected and the timestamp for recording the collection time, the association of the collected data can be distinguished.

[0100] Table 1

[0101]

[0102] Table 2

[0103]

[0104]

[0105] Table 3

[0106]

[0107] Figure 4 The general structure of a wireless communication system according to an embodiment of the present disclosure is shown, in which a UE receives and applies network congestion information. Specifically, Figure 4 A general structure of a wireless communication system is shown, in which an artificial intelligence (AI) / machine learning (ML) application 410 of a UE receives network congestion information provided by a communication service provider and applies the received information to an ML model.

[0108] refer to Figure 4, the AI / ML application 410 of the UE may request network status information from the wireless communication network in order to determine the ML model and algorithm for learning or inference. The ML model used by the application 410 may be configured by models requiring different accuracy (e.g., inference performance) and calculation levels to enable selection according to the network state. According to an embodiment, different models may be configured by increasing or decreasing the number of layers of the deep learning model or changing the depth of each layer constituting each network state. According to an embodiment, a model of another algorithm, such as a deep neural network (DNN), a convolutional neural network (CNN), or reinforcement learning (RL), may be applied according to each network state. According to an embodiment, information about these ML models in the application 410 may be configured in the form of priorities of models available for each network state. In the process of requesting network status information, the application 410 of the UE 420 may send the minimum data transmission rate and delay level information required by each ML model and algorithm to the network together with the request for network status information. When the network delivers network congestion information to the UE, the information sent by the application 410 of the UE 420 may be used as a criterion for reporting the congestion level. The control message requesting network status information sent by the application 410 of the UE 420 may include information related to at least one of an AI / ML application identifier, UE location information, a reporting period, a reporting standard, or accuracy. The reporting standard included in the network status information request message may include at least one of a congestion level, a single network slice selection auxiliary information (S-NSSAI), a data network name (DNN), or a prediction level. The request for network status information of the AI / ML application 410 may be sent to the modem (indicated by reference numeral 415) of the UE by the operating system (OS) or system application of the UE 420. The modem of the UE 420 may separately store the request information received from the application 410, or directly use the request information to request network status information from the network. In the case where the modem of the UE 420 provides an application programming interface (API), the AI / ML application 410 may also directly send a request for network status information to the modem through the API of the modem.

[0109] The modem of the UE 420 may transmit information about the request for network status information that has been received from the AI / ML application 410 to a network (e.g., a core network (CN)) of the wireless communication system through a separate designated control message or using a registration request message (indicated by reference numeral 435) in a network registration procedure. The network status information request message sent by the modem of the UE 420 may include at least one of an AI / ML application identifier, UE location information, a reporting period, a reporting criterion, or accuracy.

[0110] Upon receiving a network status information request from the UE 420 through a registration request message or a designated control message, the AMF 430 may request the subscription information of the UE from the UDM. The AMF 430 may receive the subscription information based on the registration request message from the UDM. The AMF 430 may identify from the received subscription information whether the AI / ML application 410 of the UE is an application that is allowed to receive status information or which status information is allowed.

[0111] After recognizing that the AI / ML application 410 of the UE 420 is allowed to receive the network status information according to the subscription information received from the UDM, the AMF 430 may send a message requesting at least one of the analysis information or the resource status information of each session to the NWDAF 450, the SMF, or the UPF 440, so as to collect information required to determine the network status information requested by the UE 420 (indicated by reference numerals 445, 455). The AMF 430 may receive at least one of the analysis information or the resource status information of each session based on the request message from the NWDAF 450, the SMF, or the UPF 440. The AMF 430 may determine the congestion level of the network according to the received information (indicated by reference numeral 465). In the case where a condition requested by the UE 420 based on the determined network congestion level is satisfied (for example, the resource usage level exceeds 70% or the total number of UEs predicted to use the corresponding slice exceeds a predetermined standard within a specified time, etc.), the AMF 430 may send network congestion prediction information to the UE through a control message (indicated by reference numeral 475). The network congestion prediction information included in the control message received by the UE 420 may be transmitted from the UE modem to the AI / ML application 410 (indicated by reference numeral 425). Based on the received control message, the AI / ML application 410 may identify the network congestion prediction information. The AI / ML application 410 may determine the AI / ML model and algorithm for learning and inference based on the identified network congestion prediction information. According to an embodiment, when the predicted congestion level is low, the application 410 may select a model with high accuracy and high computational requirements as a model for learning and inference (indicated by reference numeral 405). According to an embodiment, when the predicted congestion level is high, the application may select a model with low accuracy and low computational requirements as a model for learning and inference, or may delay the execution of learning and inference operations. According to an embodiment, the AI / ML application 410 may request the AI / MLAF 460 to modify the AI / ML model to be applied and change the size of the training data (indicated by reference numeral 485).

[0112] Figure 5 is a signal flow showing the collection and analysis of network data by a UE according to an embodiment of the present disclosure. Specifically, Figure 5is a signal flow diagram illustrating operations of collecting and analyzing network data in order to analyze network congestion information requested by an AI / ML application of a UE.

[0113] Referring to operation 501, in the case where the AI / ML application of the UE 510 requests network status information, the UE may transmit information indicating that the network status information needs to be transmitted during the network registration process of the UE to the network. According to an embodiment, the UE 510 may send a registration request message requesting the network status information to the AMF 520. The UE registration request message sent by the UE 510 may include at least one of the following: an identifier of an application having requested network status information, information indicating a request for network status information, a standard for reporting status information, a network slice requiring status reporting, or DNN information.

[0114] Referring to operations 503 and 505, AMF 520 may receive a UE registration request message from the UE. Upon receiving the registration request, AMF 520 may request the subscription information of the UE from UDM 550 based on the registration request message. AMF 520 may receive a response message including the subscription information of the UE based on the request for the UE subscription information received from UDM 550. Referring to operation 505, the response message received by AMF 520 from UDM 550 is part of the subscription information of the UE or separate information, and may include at least one of a list of network status information allowed to be provided to the UE by the mobile communication service provider, a list of application identifiers allowed to use the network status information, information about network slices, and DNN information.

[0115] Referring to operation 507 , the AMF 520 may determine whether the network status information requested by the UE is acceptable / allowable based on the response message including the subscription information of the UE received from the UDM 550 .

[0116] Referring to operation 509, the AMF 520 may send a registration response message to the UE. The registration response message sent by the AMF 520 may include a list of applications allowed to provide network information, and whether the network status information requested by the UE is allowed, or a list of allowed status information.

[0117] Referring to operation 511, the AMF 520 may send a message to the SMF, UPF 530, and NWDAF 540 requesting at least one of network performance analysis information or resource status information of each slice, DNN, and NF related to the network status information requested by the UE.

[0118] Referring to operation 513 , the AMF 520 may receive at least one of resource status information or network performance analysis information from the SMF, the UPF 530 , and the NWDAF 540 based on the request message sent in operation 511 .

[0119] Referring to operation 515, the AMF 520 may identify at least one of a current congestion level of the network or a congestion level in a predicted period specified by the UE based on information received from the SMF, UPF 530, and NWDAF 540. According to an embodiment, the AMF 520 may predict a congestion level of the network based on the received information.

[0120] Referring to operation 517, the AMF 520 may send a warning indicator or a control message to the UE 510, which notifies that congestion may occur when the analyzed or identified network congestion level corresponds to the congestion level specified by the UE or has changed. According to an embodiment, the AMF 520 may send a warning indicator or a control message notifying that congestion may occur to the UE in each reporting period specified by the UE. The warning indicator or control message sent by the AMF 520 to the UE may include at least one of the congestion level information identified by the AMF 520 and the supportable QoS level information.

[0121] Referring to operation 519, the UE 510 may send the received network congestion prediction information to the AI / ML application. The AI / ML application may determine the AI / ML model and algorithm to be applied for learning and inference based on the network congestion prediction information received from the UE. According to an embodiment, when the congestion level is identified or predicted to increase, the AI / ML application may determine to use a simpler and less computationally demanding model for faster operation. According to an embodiment, if the congestion level is identified or predicted to decrease, the AI / ML application may determine to use a more complex and computationally demanding model to improve accuracy.

[0122] Referring to operation 521, the AI / ML application of the UE may send at least one of information of the AI / ML model to be applied or network status information to the AI / ML server 560. The AI / ML model information sent by the AI / ML application of the UE may include at least one of a model identifier, a size of the model to be applied, or a model parameter. The network status information sent by the AI / ML application of the UE may include network congestion prediction information.

[0123] Figure 6 is a signal flow illustrating changing a model and an algorithm to be applied based on network congestion information received by a UE according to an embodiment of the present disclosure.

[0124] refer to Figure 6In operation 601, the communication module 615 of the UE 610 may receive network congestion prediction information from the network. Figure 5 The operation of the communication module 615 of the UE 610 receiving the network congestion prediction information is performed by the process described in the.

[0125] In operation 602, the UE's AI / ML application 611 may request network status information from the UE's communication module 615 in order to determine a suitable AI / ML model or algorithm. The AI / ML application 611 may send a network status information request message including information about a network congestion request to the communication module 615.

[0126] In operation 603, the communication module 615 of the UE may identify whether network status information that is allowed to be used for the AI / ML application 611 of the UE is stored. If necessary, the communication module 615 of the UE may perform Figure 5 The process described in is used to perform operations for receiving network congestion prediction information from a network.

[0127] In operation 604, the communication module 615 of the UE may transmit the network congestion prediction information received from the network to the AI / ML application 611. The communication module 615 of the UE may send a network status information response message including information about at least one of congestion notification, level, or supported QoS to the AI / ML application 611.

[0128] In operation 605, the AI / ML application 611 of the UE may determine an AI / ML model or algorithm to be used for learning and inference based on the network congestion prediction information received from the communication module 615 of the UE. According to an embodiment, when a high probability of network congestion is predicted, the AI / ML application 611 may determine to use a simple learning and inference model with a small model size (e.g., a model with a small number of layers or each layer is designed to use a small number of parameters) for learning and inference. According to an embodiment, when it is predicted that there will be no network congestion, the AI / ML application 611 may determine to use a learning and inference model with a large model size and applying a complex algorithm.

[0129] In operation 606, the AI / ML application 611 of the UE may request the AI / ML server 620 to make necessary changes to use the learning and inference model determined in operation 605. The AI / ML application 611 of the UE may send an ML model change request message to the AI / ML server 620, the ML model change request message including information about at least one of an identifier (ID), size, or network status of a model based on the learning and inference model determined in operation 604.

[0130] According to an embodiment, the units (AI / ML application 611, operating system 613, or communication module 615) included in the UE may be implemented as a controller of the UE. The controller implemented by each unit may be included in one logical unit, but is not limited thereto, and may be distributed and implemented in each logical unit.

[0131] Figure 7 is a flowchart illustrating the operation of an AMF for determining a machine learning model based on network congestion information according to an embodiment of the present disclosure.

[0132] refer to Figure 7 In operation 705, the AMF may receive a UE registration request message from the UE. According to an embodiment, the UE registration request message received by the AMF may include an identifier of an application requesting network status information, information indicating a request for network status information, a standard for reporting status information, a network slice requiring status reporting, or at least one of DNN information. Figure 7 Not shown, but the AMF that has received the registration request may request the UE's subscription information from the UDM based on the registration request message. The AMF may receive a response message including the UE's subscription information based on the request for the UE's subscription information received from the UDM. The response message received by the AMF from the UDM corresponds to a part of the UE's subscription information or separate information, and may include a list of network status information allowed to be provided to the UE by the mobile communication service provider, a list of application identifiers allowed to use the network status information, information about network slices, and at least one of DNN information. The AMF may determine whether the network status information requested by the UE is acceptable / allowable based on the response message including the UE's subscription information and received from the UDM. The AMF may send a registration response message to the UE. The registration response message sent by the AMF may include a list of applications allowed to provide network information, and whether the network status information requested by the UE is allowed, or a list of allowed status information.

[0133] In operation 715, the AMF may send a message to the SMF, UPF, and NWDAF requesting at least one of network performance analysis information or resource status information of each slice, DNN, and NF related to the network status information requested by the UE.

[0134] In operation 725, the AMF may receive at least one of resource status information or network performance analysis information from the SMF, UPF, and NWDAF based on the transmitted request message.

[0135] In operation 735, the AMF may identify at least one of the current congestion level of the network or the congestion level in the prediction period specified by the UE based on the information received from the SMF, UPF, and NWDAF. According to an embodiment, the AMF may predict the congestion level of the network based on the received information.

[0136] In operation 745, the AMF may send a warning indicator or a control message to the UE, which notifies that congestion may occur when the analyzed or identified (or predicted) network congestion level corresponds to the congestion level specified by the UE or has changed. According to an embodiment, the AMF may send a warning indicator or a control message to the UE notifying that congestion may occur in each reporting period specified by the UE. The warning indicator or control message sent by the AMF to the UE may include at least one of the congestion level information identified by the AMF and the supportable QoS level information.

[0137] Figure 8 is a flowchart illustrating the operation of a UE for determining a machine learning model based on network congestion information according to an embodiment of the present disclosure.

[0138] refer to Figure 8 , in operation 805, the UE may send a UE registration request message to the AMF. Specifically, when the AI / ML application of the UE requests network status information, the UE may send information indicating that the network status information needs to be sent to the network during the network registration process of the UE. According to an embodiment, the UE may send a registration request message requesting network status information to the AMF. The UE registration request message sent by the UE may include an identifier of an application having requested network status information, information indicating a request for network status information, a standard for reporting status information, a network slice requiring status reporting, or at least one of DNN information.

[0139] Despite Figure 8 Not shown, but the AMF that has received the registration request can request the UE's subscription information from the UDM based on the registration request message. The AMF can receive a response message including the UE's subscription information based on the request for the UE subscription information received from the UDM. The response message received by the AMF from the UDM corresponds to a part of the UE's subscription information or separate information, and may include a list of network status information allowed to be provided to the UE by the mobile communication service provider, a list of application identifiers allowed to use the network status information, information about network slices, and at least one of DNN information. The AMF can determine whether the network status information requested by the UE is acceptable / allowable based on the UE's subscription information and the response message received from the UDM.

[0140] In operation 815, the UE may receive a registration response message from the AMF. The registration response message received by the UE may include a list of applications allowed to provide network information, and whether the network status information requested by the UE is allowed, or a list of allowed status information.

[0141] although Figure 8 Although not shown in the figure, the AMF may send a message to the SMF, UPF, and NWDAF requesting at least one of network performance analysis information or resource status information of each slice, DNN, and NF related to the network status information requested by the UE. The AMF may receive at least one of resource status information or network performance analysis information from the SMF, UPF, and NWDAF based on the send request message sent in operation 511. The AMF may identify at least one of the current congestion level of the network or the congestion level in the predicted period specified by the UE based on the information received from the SMF, UPF, and NWDAF. According to an embodiment, the AMF may predict the congestion level of the network based on the received information.

[0142] In operation 825, the UE may receive a warning indicator or a control message from the AMF, which notifies that congestion may occur when the network congestion level analyzed or identified by the AMF corresponds to the congestion level specified by the UE or has changed. According to an embodiment, the AMF may send a warning indicator or a control message notifying that congestion may occur to the UE at each reporting period specified by the UE. The warning indicator or control message sent by the AMF to the UE may include at least one of the congestion level information identified by the AMF and the supportable QoS level information.

[0143] In operation 835, the UE may send the received network congestion prediction information to the AI / ML application. The AI / ML application may determine the AI / ML model and algorithm to be applied for learning and inference based on the network congestion prediction information received from the UE. According to an embodiment, when the congestion level is identified or predicted to increase, the AI / ML application may determine to use a simpler and less computationally demanding model for faster operation. According to an embodiment, when the congestion level is identified or predicted to decrease, the AI / ML application may determine to use a more complex and computationally demanding model to improve accuracy.

[0144] In operation 845, the AI / ML application of the UE may send at least one of information of the AI / ML model to be applied or network status information to the AI / ML server. The AI / ML model information sent by the AI / ML application of the UE may include at least one of a model identifier, a size of the model to be applied, or a model parameter. The network status information sent by the AI / ML application of the UE may include network congestion prediction information.

[0145] According to various embodiments of the present disclosure, an access and mobility management function (AMF) node device in a wireless communication system may include a transceiver and a controller coupled to the transceiver, wherein the controller is configured to receive a first control message including information about a registration request from a terminal, send a registration response message including information about whether a network analysis of the terminal is acceptable to the terminal, send a message requesting information about network analysis to a network data collection and analysis function (NWDAF) node based on the first control message, receive information about network analysis from the NWDAF node, identify information about network congestion of the terminal based on the information about the network analysis, and send a second control message including information about network congestion to the terminal.

[0146] According to an embodiment, the controller may be further configured to receive a message including subscription information of the terminal based on the first control message from a unified data management (UDM) node, and identify whether network analysis of the terminal is acceptable based on the subscription information.

[0147] According to an embodiment, the first control message may include information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), or a reporting period of the terminal.

[0148] According to an embodiment, the second control message may be transmitted based on a reporting period included in the first control message.

[0149] According to an embodiment, information about network congestion may be used to identify an artificial intelligence (AI) / machine learning (ML) model used by a terminal.

[0150] According to various embodiments of the present disclosure, a terminal device in a wireless communication system may include a transceiver and a controller coupled to the transceiver, wherein the controller is configured to send a first control message including information about a registration request to an access and mobility management function (AMF) node, receive a registration response message including information about whether a network analysis of the terminal is acceptable from the AMF node, receive a second control message including information about network congestion from the AMF node, the information about network congestion is identified based on information about network analysis sent from a network data collection and analysis function (NWDAF) node, and identify an artificial intelligence (AI) / machine learning (ML) model used by the terminal based on the information about the network congestion.

[0151] According to an embodiment, the registration response message may be received based on subscription information of the terminal transmitted from a unified data management (UDM) node.

[0152] According to an embodiment, the first control message may include information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), or a reporting period of the terminal.

[0153] According to an embodiment, the second control message may be received based on a reporting period included in the first control message.

[0154] According to an embodiment, the controller may also be configured to send information about the identified AI / ML model to the ML server.

[0155] According to various embodiments of the present disclosure, a method performed by an access and mobility management function (AMF) node in a wireless communication system may include: receiving a first control message including information about a registration request from a terminal, sending a registration response message including information about whether a network analysis of the terminal is acceptable to the terminal, sending a message requesting information about network analysis to a network data collection and analysis function (NWDAF) node based on the first control message, receiving information about network analysis from the NWDAF node, identifying information about network congestion of the terminal based on the information about the network analysis, and sending a second control message including information about network congestion to the terminal.

[0156] According to an embodiment, the method may further include: receiving a message including subscription information of the terminal based on the first control message from a unified data management (UDM) node, and identifying whether network analysis of the terminal is acceptable based on the subscription information.

[0157] According to an embodiment, the first control message may include information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), or a reporting period of the terminal.

[0158] According to an embodiment, the second control message may be transmitted based on a reporting period included in the first control message.

[0159] According to an embodiment, information about network congestion may be used to identify an artificial intelligence (AI) / machine learning (ML) model used by a terminal.

[0160] According to various embodiments of the present disclosure, a method performed by a terminal in a wireless communication system may include: sending a first control message including information about a registration request to an access and mobility management function (AMF) node, receiving a registration response message including information about whether a network analysis of the terminal is acceptable from the AMF node, receiving a second control message from the AMF node including information about network congestion identified based on information about network analysis sent from a network data collection and analysis function (NWDAF) node, and identifying an artificial intelligence (AI) / machine learning (ML) model used by the terminal based on the information about network congestion.

[0161] According to an embodiment, the registration response message may be received based on subscription information of the terminal transmitted from a unified data management (UDM) node.

[0162] According to an embodiment, the first control message may include information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), or a reporting period of the terminal.

[0163] According to an embodiment, the second control message may be received based on a reporting period included in the first control message.

[0164] According to an embodiment, the method may further include sending information about the identified AI / ML model to the ML server.

[0165] The embodiments of the present disclosure described and shown in the specification and the drawings are only specific examples presented to easily explain the technical content of the present disclosure and help understand the present disclosure, and are not intended to limit the scope of the present disclosure. That is, it is obvious to those skilled in the art that other variations based on the technical concept of the present disclosure can be implemented. In addition, as required, the above-mentioned various embodiments can be used in combination. For example, the various embodiments of the present disclosure can be at least partially combined with each other to operate a base station and a terminal.

[0166] In the above detailed embodiments of the present disclosure, the elements included in the present disclosure are expressed in the singular or plural, depending on the detailed embodiments presented. However, for ease of description, the singular form or plural form is appropriately selected for the presented situation, and the present disclosure is not limited to the elements expressed in the singular or plural. Therefore, an element expressed in the plural may also include a single element, or an element expressed in the singular may also include multiple elements.

[0167] While the present disclosure has been shown and described with reference to various embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents.

Claims

1. An access and mobility management function (AMF) node in a wireless communication system, the AMF node include: Transceiver; as well as a controller coupled to the transceiver, Wherein, the controller is configured as: receiving a first control message including information about a registration request from a user equipment (UE), sending a registration response message to the UE, the registration response message including information about whether network analysis of the UE is allowed, sending a message requesting information about the network analysis to a network data collection and analysis function (NWDAF) node based on the first control message, receiving said information regarding said network analysis from said NWDAF node, identifying information about network congestion for the UE based on the information about the network analysis, and A second control message including the information about the network congestion is sent to the UE.

2. The AMF node according to claim 1, in, The controller is also configured to: Based on the first control message, receiving a message including subscription information of the UE from a unified data management (UDM) node; and Whether the network analysis of the UE is allowed is identified based on the subscription information.

3. The AMF node according to claim 1, in, The first control message includes information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), and a reporting period of the UE.

4. The AMF node according to claim 3, in, The second control message is sent based on the reporting period included in the first control message.

5. The AMF node according to claim 1, in, The information about the network congestion is used to identify an artificial intelligence (AI) / machine learning (ML) model used by the UE.

6. A user equipment (UE) in a wireless communication system, the UE include: Transceiver; as well as a controller coupled to the transceiver, Wherein, the controller is configured as: sending a first control message including information about a registration request to an access and mobility management function (AMF) node, receiving a registration response message from the AMF node, the registration response message including information on whether network analysis of the UE is allowed, receiving, from the AMF node, a second control message including information about network congestion identified based on information about network analysis sent from a Network Data Collection and Analysis Function (NWDAF) node, and An artificial intelligence (AI) / machine learning (ML) model used by the UE is identified based on the information about the network congestion.

7. The UE according to claim 6, in, The registration response message is received based on subscription information of the UE transmitted from a unified data management (UDM) node.

8. The UE according to claim 6, in, The first control message includes information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), and a reporting period of the UE.

9. The UE according to claim 8, in, The second control message is received based on the reporting period included in the first control message.

10. The UE according to claim 6, in, The controller is also configured to: Send information about the identified AI / ML model to the ML server.

11. A method performed by an access and mobility management function (AMF) node in a wireless communication system, the method include: receiving a first control message including information about a registration request from a user equipment (UE); Sending a registration response message to the UE, where the registration response message includes information about whether network analysis of the UE is allowed; sending a message requesting information about the network analysis to a network data collection and analysis function (NWDAF) node based on the first control message; receiving the information about the network analysis from the NWDAF node; identifying information about network congestion for the UE based on the information about the network analysis; as well as A second control message including the information about the network congestion is sent to the UE.

12. The method according to claim 11, further comprising: include: Based on the first control message, receiving a message including subscription information of the UE from a unified data management (UDM) node; as well as Whether the network analysis of the UE is allowed is identified based on the subscription information.

13. The method according to claim 11, in, The first control message includes information about at least one of single network slice selection assistance information (S-NSSAI), a data network name (DNN), and a reporting period of the UE.

14. The method according to claim 13, in, The second control message is sent based on the reporting period included in the first control message.

15. The method according to claim 11, in, The information about the network congestion is used to identify an artificial intelligence (AI) / machine learning (ML) model used by the UE.

Images