Congestion control event notification method and apparatus in wireless communication system

Abstract

The present disclosure relates to a network function operation method in a wireless communication system, the method comprising the steps of: receiving, for one or more terminals, a subscription request for an information event related to an application of congestion control; applying congestion control to the one or more terminals; and notifying an information event related to the application of the congestion control based on the applied congestion control, in which the one or more terminals may be terminals selected based on federated learning operations.

Description

Technical Field

[0001] The following description relates to a wireless communication system and a congestion control event notification method. Specifically, the following description relates to a setting and notification method of an event based on non-access stratum (NAS) level congestion control in an artificial intelligence / machine learning (AI / ML) based federated learning (FL) operation. Background Art

[0002] Wireless communication systems have been widely deployed to provide various types of communication services, such as voice or data. Generally speaking, wireless communication systems are multiple access systems that support communication for multiple users by sharing available system resources (bandwidth, transmit power, etc.). Examples of multiple access systems include code division multiple access (CDMA) systems, frequency division multiple access (FDMA) systems, time division multiple access (TDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, and single carrier frequency division multiple access (SC-FDMA) systems.

[0003] Specifically, because a large number of communication devices require a large communication capacity, an enhanced mobile broadband (eMBB) communication technology is being proposed compared to a conventional radio access technology (RAT). In addition, not only a large-scale machine type communication (massive MTC) that provides various services anytime and anywhere by connecting multiple devices and objects is being proposed, but also a communication system that takes into account services / user terminal equipment (UE) that are sensitive to reliability and latency is being proposed. Various technical configurations are proposed for this purpose. Summary of the invention

[0004] Technical issues

[0005] The present disclosure relates to a congestion control event notification method and device in a wireless communication system

[0006] The present disclosure relates to a method and apparatus for setting an event based on NAS level congestion control by considering an AI / ML-based FL operation in a wireless communication system.

[0007] The present disclosure relates to a method and apparatus for preventing learning iteration delay through FL operation in a wireless communication system.

[0008] The present disclosure relates to a method and apparatus for preventing skipping of training result reporting within a learning iteration through FL operation in a wireless communication system.

[0009] The technical objectives to be achieved by the present disclosure are not limited to the contents mentioned above, and those skilled in the art who apply the technical configuration of the present disclosure can consider other technical objectives not mentioned herein from the embodiments of the present disclosure to be described below.

[0010] Technical Solution

[0011] As an example of the present disclosure, a method for operating a network function in a wireless communication system may include: receiving a subscription request for a congestion control application related information event for at least one terminal; applying congestion control to the at least one terminal; and performing a notification of the congestion control application related information event based on the applied congestion control. The at least one terminal may be a terminal selected based on a federated learning (FL) operation.

[0012] In addition, as an example of the present disclosure, a network function operating in a wireless communication system may include: at least one transceiver; at least one processor; and at least one memory, the at least one memory being operatively connected to the at least one processor and configured to store instructions, the instructions causing the at least one processor to perform specific operations when executed. The specific operations may control the at least one transceiver to receive a subscription request for congestion control application related information events for at least one terminal, apply congestion control to the at least one terminal, and perform notification of congestion control application related information events based on the applied congestion control. The at least one terminal may be a terminal selected based on a federated learning (FL) operation.

[0013] In addition, as an example of the present disclosure, a method for operating a terminal in a wireless communication system may include: sending a request message to a network function; receiving a response message including a backoff timer from the network function based on congestion control; and postponing the operation based on the backoff timer. The terminal may be a terminal selected for FL operation, and the network function may apply congestion control based on a congestion control application related information event and perform notification of the congestion control application related information event.

[0014] In addition, as an example of the present disclosure, a terminal operating in a wireless communication system may include: at least one transceiver; at least one processor; and at least one memory, the at least one memory being operatively connected to the at least one processor and configured to store instructions, the instructions causing the at least one processor to perform specific operations when executed. The specific operations may control the transceiver to send a request message to a network function, control the transceiver to receive a response message including a backoff timer from the network function based on congestion control, and postpone the operation based on the backoff timer. The terminal may be a terminal selected for FL operation, and the network function may apply congestion control and perform notification of congestion control application related information events.

[0015] In addition, as an example of the present disclosure, the device may include at least one memory and at least one processor functionally connected to the at least one memory. The at least one processor may control the device to receive a subscription request for a congestion control application related information event for at least one other device, apply congestion control to the at least one other device, and perform notification of the congestion control application related information event based on the applied congestion control. The at least one other device may be a device selected based on the FL operation.

[0016] In addition, as an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction may include at least one instruction that can be executed by a processor. The at least one instruction may control a device to receive a subscription request for a congestion control application related information event for at least one other device, apply congestion control to the at least one other device, and perform notification of the congestion control application related information event based on the applied congestion control. The at least one other device may be a device selected based on the FL operation.

[0017] In addition, the following contents may be commonly applied.

[0018] In addition, as an example of the present disclosure, the network function may be an access and mobility management function (AMF), and the AMF may receive a subscription request for congestion control application related information events from a network exposure function (NEF), and the NEF may send a subscription request for congestion control application related information events to the AMF based on an application function (AF) request.

[0019] In addition, as an example of the present disclosure, based on the AMF applying congestion control to at least one terminal, the AMF may send a non-access stratum (NAS) message including a mobility management back-off timer value to the at least one terminal, and each of the at least one terminal may postpone operation based on the mobility management back-off timer.

[0020] In addition, as an example of the present disclosure, based on the notification of a congestion control application related information event based on the applied congestion control execution, the AMF may send the congestion control application related information to the NEF, and the NEF may send the congestion control application related information to the AF.

[0021] In addition, as an example of the present disclosure, congestion control application related information may include at least one of the following information: information indicating that congestion control is applied to at least one terminal, information indicating that a mobility management backoff timer value is provided to at least one terminal, mobility management backoff timer information provided to at least one terminal, information indicating that a rejection message for an MM (mobility management) NAS message is sent to at least one terminal, or congestion control level information.

[0022] In addition, as an example of the present disclosure, the AF may select at least one terminal for each learning iteration based on the FL operation, and the AF may provide FL model information to the at least one terminal in the learning iteration to obtain training result information from the at least one terminal, and update the FL model based on the training result information, and based on notifying the AF of information related to the application of congestion control, the FL model may be updated without the training result information of at least one terminal to which congestion control is applied.

[0023] In addition, as an example of the present disclosure, the AF may send a request to newly determine at least one terminal to participate in the learning iteration based on the FL operation.

[0024] In addition, as an example of the present disclosure, a subscription request for congestion control application-related information events may be received from an artificial intelligence / machine learning (AI / ML) network function (NF) based on an application function (AF) request.

[0025] In addition, as an example of the present disclosure, the network function may be a session management function (SMF), and the SMF may receive a subscription request for congestion control application related information events from a network open function (NEF) based on at least one terminal and a PDU (protocol data unit) session, and the NEF may send a subscription request for congestion control application related information events to the SMF based on an AF request.

[0026] In addition, as an example of the present disclosure, the PDU session may be a PDU session for at least one of an AI / ML service, operation, business, or application or a PDU session for a FL operation.

[0027] In addition, as an example of the present disclosure, based on the SMF applying congestion control to at least one terminal and a PDU session, the SMF may send a NAS message including a backoff timer value to the at least one terminal, and each of the at least one terminal may postpone operation based on the mobility management backoff timer.

[0028] In addition, as an example of the present disclosure, the SMF may receive a PDU session modification request message from at least one terminal, and send a PDU session modification reject message including a backoff timer value to the at least one terminal based on the applied congestion control.

[0029] In addition, as an example of the present disclosure, according to the notification of a congestion control application related information event based on the applied congestion control execution, the SMF can send the congestion control application related information to the NEF, and the NEF can send the congestion control application related information to the AF.

[0030] In addition, as an example of the present disclosure, congestion control application related information may include at least one of the following: information indicating that congestion control is applied to at least one terminal, information indicating that a mobility management backoff timer value is provided to at least one terminal, mobility management backoff timer information provided to at least one terminal, information indicating that a rejection message for an SM (session management) NAS message is sent to at least one terminal, congestion control level information, congestion control application indication information based on DNN (Data Network Name), or congestion control indication information based on S-NSSAI (Single Network Slice Selection Assistance Information).

[0031] In addition, as an example of the present disclosure, the AF may select at least one terminal for each learning iteration based on the FL operation, and the AF may provide FL model information to the at least one terminal in the learning iteration to obtain training result information from the at least one terminal, and update the FL model based on the training result information, and based on notifying the AF of information related to the application of congestion control, the FL model may be updated without the training result information of at least one terminal to which congestion control is applied.

[0032] In addition, as an example of the present disclosure, the AF may send a request to newly determine at least one terminal to participate in the learning iteration based on the FL operation.

[0033] Beneficial Effects

[0034] The present disclosure may provide a method of performing notification of a congestion control event in a wireless communication system.

[0035] The present disclosure may provide a method for setting an event based on NAS level congestion control by considering an AI / ML-based FL operation in a wireless communication system.

[0036] The present disclosure may provide a method for preventing learning iteration delay through FL operation in a wireless communication system.

[0037] The present disclosure may provide a method for preventing skipping of training result reporting within a learning iteration through FL operation in a wireless communication system.

[0038] The technical objectives to be achieved in the present disclosure are not limited to the above contents, and those skilled in the art who apply the technical configuration of the present disclosure may consider other unmentioned technical objectives from the embodiments of the present disclosure described below.

[0039] Those skilled in the art will appreciate that the effects that can be achieved through the embodiments of the present disclosure are not limited to the above effects, and other advantageous effects of the present disclosure will be more clearly understood through the following detailed description. That is, those skilled in the art can derive unexpected effects according to the implementation of the present disclosure from the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are provided to help understand the present disclosure, and embodiments of the present disclosure may be provided together with the detailed description. However, the technical features of the present disclosure are not limited to specific drawings, and the features disclosed in each drawing may be combined with each other to form new embodiments. The reference numerals in each drawing may refer to structural elements.

[0041] Figure 1 is a diagram showing an example of a communication system applicable to the present disclosure.

[0042] Figure 2 is a view showing an example of a UE to which an embodiment of the present disclosure is applied.

[0043] Figure 3 is a view showing an example of functional separation of a general NG-RAN and a fifth generation core (5GC).

[0044] Figure 4 is a view showing an example of a general architecture of a fifth generation (5G) system.

[0045] Figure 5 is a diagram illustrating an AI / ML-based endpoint splitting operation applicable to the present disclosure.

[0046] Figure 6 is a diagram illustrating an AI / ML model distribution method applicable to the present disclosure.

[0047] Figure 7 is a diagram illustrating a method of performing federated learning-based learning applicable to the present disclosure.

[0048] Figure 8 A method for receiving event notification after subscribing to congestion control application related information events provided by AMF at AF applicable to the present disclosure is shown.

[0049] Fig. 9 A method for receiving event notification after subscribing to a congestion control application information event provided by an SMF at an AF applicable to the present disclosure is shown.

[0050] Fig.10 A method for receiving event notification after subscribing to congestion control application related events provided by SMF at an AF applicable to the present disclosure is shown.

[0051] Fig.11 A method for receiving event notification after subscribing to congestion control application related events provided by SMF at an AF applicable to the present disclosure is illustrated.

[0052] Fig.12 is a flowchart illustrating an event notification method based on NAS-level congestion control applicable to the present disclosure. DETAILED DESCRIPTION

[0053] The following embodiments are achieved by combining the structural elements and features of the present disclosure in a predetermined manner. Unless specified separately, each structural element or feature should be selectively considered. Each structural element or feature can be performed without being combined with other structural elements or features. In addition, some structural elements and / or features can be combined with each other to form embodiments of the present disclosure. The order of the operations described in the embodiments of the present disclosure can be changed. Some structural elements or features of an embodiment may be included in another embodiment, or may be replaced by corresponding structural elements or features of another embodiment.

[0054] In the description of the drawings, processes or steps that render the scope of the present disclosure unnecessarily ambiguous will be omitted, and processes or steps that can be understood by those skilled in the art will be omitted.

[0055] Throughout the specification, when a part "comprises" or "includes" a component, this indicates that other components are not excluded, but may be further included, unless otherwise specified. The terms "unit", "-or / er" and "module" described in this specification indicate a unit for processing at least one function or operation, which can be implemented by hardware, software and a combination thereof. In addition, "a" or "an", "one", "the" and similar related words can be used to include both singular and plural expressions, unless in the context of describing this specification (especially in the context of the following claims) it indicates something different from this specification or is obviously contradictory to the context.

[0056] In this specification, the embodiments of the present disclosure are described focusing on the relationship between data reception and transmission between a base station and a mobile station. Here, a base station means a terminal node of a network that performs direct communication with a mobile station. In this document, a specific operation described as being performed by a base station may be performed by an upper node of the base station in some cases.

[0057] That is, in a network consisting of a plurality of network nodes including a base station, various operations for communicating with a mobile station may be performed by a base station or a network node other than a base station. Here, "base station" may be replaced by terms such as "fixed station", "Node (Node) B", "eNode B (eNB)", "gNode B (gNB)", "ng-eNB", "advanced base station (ABS)" or "access point".

[0058] In addition, in an embodiment of the present disclosure, “terminal” may be replaced by terms such as “user terminal equipment (UE)”, “mobile station (MS)”, “subscriber station (SS)”, “mobile subscriber station (MSS)”, “mobile terminal” or “advanced mobile station (AMS)”.

[0059] In addition, the transmitting end refers to a fixed and / or mobile node that provides data services or voice services, and the receiving end means a fixed and / or mobile node that receives data services or voice services. Therefore, in the case of an uplink, the mobile station can be the transmitting end, and the base station can be the receiving end. Similarly, in the case of a downlink, the mobile station can be the receiving end, and the base station can be the transmitting end.

[0060] The embodiments of the present disclosure may be supported by standard documents disclosed in at least one of the following radio access systems: IEEE802xx system, 3rd Generation Partnership Project (3GPP) system, 3GPP Long Term Evolution (LTE) system, 3GPP Fifth Generation (5G) New Radio (NR) system and 3GPP2 system, and specifically, the embodiments of the present disclosure may be supported by the following documents: 3GPP TS (Technical Specification) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS38.321 and 3GPP TS 38.331.

[0061] In addition, the embodiments of the present disclosure are applicable to other radio access systems, but are not limited to the above-mentioned systems. As an example, they are applicable to systems applied after the 3GPP 5G NR system, and are not limited to a specific system.

[0062] That is to say, obvious steps and parts not described in the embodiments of the present disclosure can be described with reference to the above documents. In addition, all terms disclosed in this document can be interpreted by standard documents.

[0063] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Figure 1 The detailed description disclosed above is intended to describe example embodiments of the present disclosure, and is not intended to illustrate any only embodiment of the technical configuration capable of implementing the present disclosure.

[0064] In addition, specific terms used in the embodiments of the present disclosure are provided to help understanding of the present disclosure, and these specific terms can be used in any other modified forms without departing from the technical idea of ​​the present disclosure.

[0065] The following technology can be applied to various radio access systems such as code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), etc.

[0066] For the purpose of explanation, the following description is based on a 3GPP communication system (e.g., LTE, NR, etc.), but the technical idea of ​​the present disclosure is not limited thereto. LTE may refer to technology after 3GPP TS 36.xxx version 8. Specifically, LTE technology after 3GPP TS 36.xxx version 10 may be referred to as LTE-A, and technology after 3GPP TS 36.xxx version 13 may be referred to as pre-LTE-A. 3GPP NR may refer to technology after TS 38.xxx version 15. 3GPP 6G may refer to technology after TS version 17 and / or version 18. "xxx" means the specific number of a standard document. LTE / NR / 6G may be collectively referred to as a 3GPP system.

[0067] Contents described in standard documents issued earlier than the present disclosure may be referenced for background technology, terminology and abbreviations used in the present disclosure. As an example, 36.xxx and 38.xxx standard documents may be referenced.

[0068] For terms, abbreviations and other backgrounds that may be used in this document, reference may be made to the following standard document descriptions published prior to this document. Specifically, terms, abbreviations and other background technologies related to LTE / EPS (Evolved Packet System) may refer to the 36.xxx series, 23.xxx series and 24.xxx series, and NR (New Radio) / 5GS related terms and abbreviations and other backgrounds may refer to the 38.xxx series, 23.xxx series and 24.xxx series.

[0069] Hereinafter, the present disclosure is described based on the terms defined above.

[0070] The three main demand areas of 5G include (1) enhanced mobile broadband (eMBB), (2) massive machine type communication (mMTC), and (3) ultra-reliable low latency communication (URLLC).

[0071] Some use cases may require multiple areas to be optimized, and others may focus on just one key performance indicator (KPI). 5G supports these different use cases in a flexible and reliable way.

[0072] Communication system applicable to the present disclosure

[0073] Although not limited thereto, the various descriptions, functions, processes, proposals, methods and / or operational flowcharts of the present disclosure disclosed herein may be applied to various fields requiring wireless communication / connection (e.g., 5G) between devices.

[0074] In the following, a more detailed description will be given with reference to the accompanying drawings. In the following drawings / descriptions, unless otherwise mentioned, the same reference numerals may illustrate the same or corresponding hardware blocks, software blocks or functional blocks.

[0075] Figure 1 An example communication system suitable for use with the present disclosure is illustrated.

[0076] refer to Figure 1 , the communication system applied to the present disclosure includes a wireless device, a base station and a network. Here, a wireless device refers to a device for performing communication using a wireless connection technology (e.g., 5G NR, LTE), and may be referred to as a communication / wireless / 5G device. Without being limited thereto, the wireless device may include a robot 100a, a vehicle 100b-1 and 100b-2, an extended reality (XR) device 100c, a handheld device 100d, a home appliance 100e, an Internet of Things (IoT) device 100f, and an artificial intelligence (AI) device / server 100g. For example, a vehicle may include a vehicle equipped with a wireless communication function, an autonomous driving vehicle, a vehicle capable of performing vehicle-to-vehicle communication, and the like. Here, vehicles 100b-1 and 100b-2 may include an unmanned aerial vehicle (UAV)) (e.g., a drone). The XR device 100c may include an augmented reality (AR) / virtual reality (VR) / mixed reality (MR) device and may be implemented in the form of a head-up display (HUD) mounted on a vehicle, a television, a smartphone, a computer, a wearable device, a home appliance, a digital signage, a vehicle, a robot, etc. The handheld device 100d may include a smartphone, a smart tablet, a wearable device (e.g., a smart watch, smart glasses), a computer (e.g., a laptop, etc.), etc. The home appliance 100e may include a television, a refrigerator, a washing machine, etc. The IoT device 100f may include a sensor, a smart meter, etc. For example, the base station 120 and the network 130 may be implemented as wireless devices, and a specific wireless device 120a may operate as a base station / network node for another wireless device.

[0077] The wireless devices 100a to 100f may be connected to the network 130 through the base station 120. AI technology may be applied to the wireless devices 100a to 100f, and the wireless devices 100a to 100f may be connected to the AI ​​server 100g through the network 130. The network 130 may be configured using a 3G network, a 4G (e.g., LTE) network, or a 5G (e.g., NR) network. The wireless devices 100a to 100f may communicate with each other through the base station 120 / network 130, but perform direct communication (e.g., side link communication) that does not pass through the base station 120 / network 130. For example, the vehicles 100b-1 and 100b-2 may perform direct communication (e.g., vehicle-to-vehicle (V2V) / vehicle-to-everything (V2X) communication). In addition, the IoT device 100f (e.g., a sensor) may perform direct communication with another IoT device (e.g., a sensor) or other wireless devices 100a to 100f.

[0078] Wireless communication / connection 150a, 150b and 150c can be established between wireless devices 100a to 100f / base station 120 and base station 120 / base station 120. Here, wireless communication / connection, such as uplink / downlink communication 150a, side link communication 150b (or D2D communication) and base station to base station communication 150c (e.g., relay, integrated access backhaul (IAB)), can be established through various wireless connection technologies (e.g., 5G NR). The wireless device and the base station / wireless device, and the base station and the wireless device can send / receive radio signals through wireless communication / connection 150a, 150b and 150c. For example, wireless communication / connection 150a, 150b and 150c can send / receive signals through various physical channels. To this end, based on various proposals of the present disclosure, various configuration information setting processes for sending / receiving radio signals, various signal processing processes (e.g., channel coding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and at least a part of the resource allocation process can be performed.

[0079] Figure 2 is a view showing an example of a UE to which an embodiment of the present disclosure is applied.

[0080] refer to Figure 2 UE 200 may include a processor 202, a memory 204, a transceiver 206, one or more antennas 208, a power management module 241, a battery 242, a display 243, a keyboard 244, a subscriber identity module (SIM) card 245, a speaker 246, and a microphone 247.

[0081] The processor 202 may be configured to implement the descriptions, functions, processes, proposals, methods and / or operational flow charts disclosed in this specification. The processor 202 may be configured to control one or more different components of the UE 200 to implement the descriptions, functions, processes, proposals, methods and / or operational flow charts disclosed in this specification. The layers of the wireless interface protocol may be embodied in the processor 202. The processor 202 may include an ASIC, other chipsets, logic circuits and / or data processing devices. The processor 202 may be an application processor. The processor 202 may include at least one of a DSP, a central processing unit (CPU), a graphics processing unit (GPU), and a modem (modulator and demodulator).

[0082] The memory 204 may be operably coupled to the processor 202 and store various information for operating the processor 202. The memory 204 may include ROM, RAM, flash memory, memory card, storage medium and / or other storage devices. In the case of software implementation, the technology described herein may be implemented using a module (e.g., process, function, etc.) that executes the description, function, process, proposal, method and / or operation flow chart disclosed in this specification. The module may be stored in the memory 204 and executed by the processor 202. The memory 204 may be implemented in the processor 202 or outside the processor 202, in which case the memory 204 may be communicatively coupled to the processor 202 by various methods known in the art.

[0083] The transceiver 206 can be operably coupled to the processor 202 and send and / or receive radio signals. The transceiver 206 can include a transmitter and a receiver. The transceiver 206 can include a baseband circuit for processing radio frequency signals. The transceiver 206 can send and / or receive radio signals by controlling one or more antennas 208.

[0084] The power management module 241 may manage power of the processor 202 and / or the transceiver 206. The battery 242 may supply power to the power management module 241.

[0085] The display 243 may output a result processed by the processor 202. The keyboard 244 may receive an input to be used in the processor 202. The keyboard 244 may be displayed on the display 243.

[0086] SIM card 245 is an integrated circuit for securely storing an International Mobile Subscriber Identity (IMSI) and related keys, and can be used to identify and authenticate a user in a handheld telephone device such as a mobile phone or computer. In addition, contact information can be stored in many SIM cards.

[0087] The speaker 246 may output sound-related results processed in the processor 202. The microphone 247 may receive sound-related input to be used in the processor 202.

[0088] In an embodiment of the present specification, a UE may operate as a transmitting device in an uplink and as a receiving device in a downlink. In an embodiment of the present specification, a base station may operate as a receiving device in an UL and as a transmitting device in a DL. In the present specification, a base station may be referred to as a Node B (Node B), an eNode B (eNB), and a gNB, and may not be limited to a specific form.

[0089] In addition, as an example, the UE can be embodied in various forms according to the use example / service. The UE can be configured by various components, devices / components and / or modules. For example, each UE may include a communication device, a control device, a storage device and additional components. The communication device may be a communication circuit and a transceiver. For example, the communication circuit may include one or more processors and / or one or more memories. For example, the transceiver may include one or more transceivers and / or one or more antennas. The control device may be electrically coupled to the communication device, the storage device and the additional components, and control the overall operation of each UE. For example, the control device may control the electrical / mechanical operation of each UE based on the program / code / instruction / information stored in the storage device. The control device may send the information stored in the storage device to the outside (e.g., another communication device) via the communication device through a wireless / wired interface, or store the information received from the outside (e.g., another communication device) through the wireless / wired interface in the storage device.

[0090] The additional components may be configured in various ways depending on the type of UE. For example, the additional components may include at least one of a power supply device / battery, an input / output (I / O) device (e.g., an audio I / O port, a video I / O port), a drive device, and a computing device. In addition, without limitation, the UE may be configured in a variety of ways. Figure 1 The robot 100a, Figure 1 The vehicles 100b-1 and 100b-2, Figure 1 XR device 100c, Figure 1 Handheld device 100d, Figure 1 Home appliances 100e, Figure 1 IoT devices 100f, digital broadcast terminals, hologram devices, public safety devices, MTC devices, medical devices, fintech devices (or financial devices), security devices, climate / environmental devices, Figure 1 AI server / device 100g, Figure 1 The UE may be implemented in the form of a base station 120 and a network node. The UE may be used in a mobile or fixed location depending on the use case / service.

[0091] Various components, devices / components and / or all modules of the UE may be interconnected via a wired interface, or at least a portion thereof may be wirelessly connected via a communication device. In addition, each component, device / component and / or module of the UE may further include one or more components. For example, the control device may be configured by a collection of one or more processors. As an example, the control device may be configured by a collection of a communication control processor, an application processor (AP), an electronic control unit (ECU), a GPU, and a memory control processor. As another example, the storage device may be configured by RAM, dynamic RAM (DRAM), ROM, flash memory, volatile memory, non-volatile memory and / or a combination thereof.

[0092] 5G system architecture to which the present disclosure is applicable

[0093] The 5G system is an advanced technology derived from 4G LTE mobile communication technology, and supports new radio access technologies (RATs), extended long term evolution (eLTE) as an extension technology of LTE, non-3GPP access (for example, wireless local area network (WLAN) access), etc. through the evolution of the existing mobile communication network structure or net state structure.

[0094] The 5G system is defined based on services, and the interactions between network functions (NFs) in the architecture of the 5G system can be represented in the following two ways.

[0095] Reference point representation: indicates the interaction between NF services in NFs described by a point-to-point reference point (e.g., N11) between two NFs (e.g., AMF and SMF).

[0096] Service-based representation: A network function (e.g. AMF) within the control plane (CP) allows other authenticated network functions to access its services. This representation also includes point-to-point reference points if necessary.

[0097] 5GC (5G Core) can include various components, Figure 6 Some of the various components are shown, including Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), Prose User Plane Function (UPF), Application Function (AF), Unified Data Management (UDM) and Non-3GPP Interworking Function (N3IWF).

[0098] The UE is connected to the data network via the UPF via the Next Generation Radio Access Network (NG-RAN) including the gNB. The UE can even be provided with data services through untrusted non-3GPP access, such as a wireless local area network (WLAN). In order to connect non-3GPP access to the core network, the N3IWF can be deployed.

[0099] N3IWF performs the function of managing the interworking between non-3GPP access and 5G system. When the UE is connected to non-3GPP access (e.g., WiFi called IEEE 801.11), the UE can connect to the 5G system through N3IWF. N3IWF performs control signaling with AMF and connects to UPF through N3 interface for data transmission.

[0100] AMF can manage access and mobility in the 5G system. AMF can perform the function of managing (non-access layer) NAS security. AMF can perform the function of handling mobility in idle state.

[0101] The UPF performs the function of sending and receiving user data by the gateway. The UPF node 440 can perform all or part of the user plane functions of the serving gateway (S-GW) and the packet data network gateway (P-GW) of 4G mobile communication.

[0102] UPF is a component that operates as a boundary point between the Next Generation Radio Access Network (NG-RAN) and the core network and maintains the data path between the gNB and the SMF. In addition, when the UE moves over the area served by the gNB, the UPF acts as a mobility anchor. The UPF can perform the function of processing PDUs. For mobility within the NG-RAN (which is defined after 3GPP Release 15), the UPF can route packets. In addition, the UPF can also use another 3GPP network (RAN defined before 3GPP Release-15, such as the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), Evolved (E)-UTRAN, or Global System for Mobile Communications (GERAN) / Enhanced Data Rates for Global Evolution (EDGE) RAN) as a mobility anchor. The UPF may correspond to the termination point of the data interface toward the data network.

[0103] PCF is a node that controls the operator's policies. AF is a server for providing various services to UE. UDM is a server that manages subscriber information, such as the Home Subscriber Server (HSS) of 4G mobile communications. UDM stores subscriber information in a unified data repository (UDR) and manages the subscriber information.

[0104] SMF can perform the function of allocating the Internet Protocol (IP) address of the UE. In addition, SMF can control the packet data unit (PDU) session.

[0105] For ease of explanation, in the following, the figure marks may be omitted for AMF, SMF, PCF, UPF, AF, UDM, N3IWF, gNB or UE, which may operate with reference to the contents described in the standard documents released earlier than this document.

[0106] Figure 3 : is a diagram showing an example of expressing a structure of a wireless communication system applied to the present disclosure from a node perspective.

[0107] refer to Figure 3 , the UE is connected to the data network (DN) through the next generation RAN. The control plane function (CPF) node performs all or part of the functions of the mobility management entity (MME) of 4G mobile communication and all or part of the serving gateway (S-GW) and PDN gateway (P-GW) functions. CPF nodes include AMF and SMF.

[0108] The UPF node performs the function of a gateway for sending and receiving user data.

[0109] The Authentication Server Function (AUSF) authenticates and manages the UE. The Network Slice Selection Function NSSF is a node of the following network slices.

[0110] The Network Open Function (NEF) provides a mechanism to securely open services and functions of the 5G core.

[0111] Figure 3 The reference points in are described as follows. N1 represents the reference point between UE and AMF. N2 represents the reference point between (R)AN and AMF. N3 represents the reference point between (R)AN and UPF. N4 represents the reference point between SMF and UPF. N5 represents the reference point between PCF and AF. N6 represents the reference point between UPF and DN. N7 represents the reference point between SMF and PCF. N8 represents the reference point between UDM and AMF. N9 represents the reference point between UPFs. N10 represents the reference point between UDM and SMF. N11 represents the reference point between AMF and SMF. N12 represents the reference point between AMF and AUSF. N13 represents the reference point between UDM and AUSF. N14 represents the reference point between AMFs. N15 represents the reference point between PCF and AMF in non-roaming scenarios and between AMF and PCF of the visited network in roaming scenarios. N16 represents the reference point between SMFs. N22 represents the reference point between AMF and NSSF. N30 represents the reference point between PCF and NEF. N33 may denote a reference point between AF and NEF, and the above-mentioned entities and interfaces may be configured with reference to contents described in a standard document released earlier than this document.

[0112] The radio interface protocol is based on the 3GPP radio access network standard. The radio interface protocol is horizontally divided into a physical layer, a data link layer, and a network layer, and vertically divided into a user plane for transmission of data information and a control plane (signaling) for transmission of control signals.

[0113] The protocol layer may be divided into L1 (layer 1), L2 (layer 2), and L3 (layer 3) based on three lower layers of an open system interconnection (OSI) reference model widely known in communication systems.

[0114] Hereinafter, the present disclosure describes each layer of the wireless protocol. Figure 4 is a view showing an example of the structure of a radio interface protocol between a UE and a gBN.

[0115] refer to Figure 4 The access stratum (AS) layer may include a physical (PHY) layer, a medium access control layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, and a radio resource control (RRC) layer, and operations based on each layer may be performed with reference to the contents described in a standard document released earlier than the current document.

[0116] AI / ML technology can be applied to the application layer and the network layer. As an AI / ML technology, deep learning technology can be applied to the field of wireless resource management and allocation, but is not limited to this. In addition, AI / ML technology can also be applied to the MAC layer and the physical layer. In particular, attempts are being made to combine deep learning with wireless transmission at the physical layer.

[0117] For example, an AI / ML algorithm based on deep learning in a machine learning manner may require a large amount of training data to optimize training parameters. However, there may be limitations in obtaining data as training data in a specific channel environment, and a method for applying AI / ML technology to a network while taking this into consideration will be described below.

[0118] Machine learning refers to a series of operations to train a machine to create a machine that can perform tasks that are difficult or impossible for humans to perform. Machine learning requires data and a learning model. In machine learning, data learning methods can be mainly divided into three types: supervised learning, unsupervised learning, and reinforcement learning. Neural network learning is to minimize output errors. Neural network learning is a process of repeatedly inputting training data into a neural network, calculating the error between the target and the output of the neural network for the training data, and backpropagating the error of the neural network from the output layer of the neural network to the input layer in the direction of reducing the error, thereby updating the weight of each node of the neural network. Supervised learning uses training data marked with the correct answer, and unsupervised learning may use training data that is not marked with the correct answer. That is, for example, in the case of supervised learning for data classification, the training data may be data in which each training data is marked with a category. The labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. The calculated error is backpropagated from the neural network in the opposite direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each node to be updated can be determined according to the learning rate. The calculation of the input data by the neural network and the back propagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, in the early stages of learning of the neural network, a high learning rate can be used so that the neural network can quickly acquire a certain level of performance, thereby improving efficiency, and in the later stages of learning, a low learning rate can be used to increase accuracy. In addition, as an example, the learning method can vary according to the characteristics of the data. For example, if the purpose is to accurately predict the data sent from the transmitter in the communication system at the receiver, it is preferred to use supervised learning rather than unsupervised learning or reinforcement learning to perform learning. The learning model corresponds to the human brain, and the most basic linear model can be considered, but the machine learning paradigm using a highly complex neural network structure (such as an artificial neural network) as a learning model can be referred to as deep learning. The neural network core used as a learning method can mainly include a deep neural network (DNN), a convolutional deep neural network (CNN) and a recursive Boltzmann machine (RNN), and these learning models can be applied.

[0119] Hereinafter, a method for performing AI / ML services and application support and AI / ML traffic transmission by supporting 5GS considering the above-mentioned AI / ML technology will be described. For example, learning can be performed on a learning model based on AI / ML technology, and reasoning can be performed by a learning model on which learning has been performed. Here, the network can support the above-mentioned learning and reasoning operations. As a more specific example, the AI / ML operation of the application layer can support the operations of Table 1 below. With reference to Table 1 below, the AI / ML task division point of the AI / ML endpoint can be determined by considering the relationship between entities. As another example, AI / ML models and data can be distributed and shared through 5GS. For another example, 5GS can support federated learning (federated learning, FL), and the model parameters of FL can be applied, but are not limited to this.

[0120] [Table 1]

[0121]

[0122] In addition, the network can support network resource utilization monitoring operations to support AI / ML functions at the application layer. In addition, the network can perform support by determining whether to expose the acquired information to support AI / ML functions (e.g., location, QoS, load, congestion, etc.) and to which entity to expose the information. In addition, the network can acquire and manage information to support AI / ML functions and is not limited to a specific implementation.

[0123] As another example, the network may support federated learning (FL) and apply the model parameters of FL. That is, the model parameters of FL may adapt to the communication environment and may perform signal transmission. The network may perform at least one of the functions of protecting personal privacy, reducing the load of the base station through distributed processing, or reducing the traffic between the base station and the terminal through FL, but may not be limited thereto. For the above operations, the network may set the FL model parameters and send the set FL model parameters to multiple terminals. Then, each of the multiple terminals may update the acquired model parameters based on the acquired training data and send the updated model parameter information to the network. The network may eventually update the model parameters based on the model parameter information acquired from each of the multiple terminals. However, in the above process, since the transmission and reception of local model parameters are required between the network and the terminal, the traffic of the local model parameters may cause a large burden in the wireless communication environment, and a method for solving this problem will be described.

[0124] Figure 5is a diagram showing an AI / ML-based endpoint split operation applicable to the present disclosure. AI / ML can be used in a range of application areas and can replace existing algorithms (e.g., speech recognition, image recognition, video processing, etc.) of devices (e.g., smart phones, vehicles, robots, etc.) within a communication system. For example, the communication system may support at least one of the AI / ML operation splitting between the AI / ML endpoints of Table 1 above, the distribution / sharing of AI / ML models / data via the communication system, or the FL support via the communication system.

[0125] Here, refer to Figure 5 , the AI / ML operation splitting for AI / ML reasoning can be considered. Considering the current task and environment, the AI / ML operation / model can be split into multiple parts. Specifically, the endpoint (e.g., terminal) can transfer computationally intensive operations and energy-intensive operations to the network part, and directly handle privacy-sensitive operations and delay-sensitive operations. More specifically, part of the AI / ML operation / model can be located in the terminal device 510 and the network AI / ML endpoint 520, respectively. That is, the entire AI / ML model is not configured in one entity, but can be split and located in multiple entities. Here, when reasoning is performed based on the AI / ML model, input can be provided as input to the AI / ML operation / model part in the terminal device 510. Thereafter, intermediate data can be derived from the corresponding AI / ML operation / model part by the terminal device 510 as output. The intermediate data can be sent to the network AI / ML endpoint (520) and provided as input to the AI / ML operation / model part within the network. The AI / ML operation / model part within the network can derive the final reasoning output data based on the provided input. That is, AI / ML operations / models can be split into each entity and appropriate operations are performed considering each entity’s tasks and environment.

[0126] Figure 6 is a diagram illustrating an AI / ML model distribution method applicable to the present disclosure. For example, considering the task and environment, a device with various functions (e.g., a smart phone, a vehicle, a robot, etc.) needs to use multiple AI / ML models. In other words, considering the task and environment, the device needs to switch to a suitable AI / ML model and apply it. Here, since the storage space of the device may be limited, it may not be desirable to configure all candidate AI / ML models in the device. In view of the above, the candidate AI / ML models of the multiple AI / ML models may be configured as an AI / ML model pool. For example, an AI / ML model pool may be provided in a network and may be distributed to the devices from network endpoints. To this end, the device 610 may continuously monitor the performance of the AI / ML model. As a more specific example, refer to Figure 6(a), the first device 610 may receive an AI / ML model update request from the second device 620, and acquire a suitable AI / ML model through a network endpoint based on the AI / ML model update request. Here, the second device 620 may continuously monitor the AI / ML model, and if the AI / ML model is not suitable in view of the new task and environment, the second device 620 may request an AI / ML model update from the first device 610. The first device 610 may acquire a suitable AI / ML model from the network and send information about the AI / ML model to the second device 620.

[0127] As another example, refer to Figure 6 (b), the DNN (deep neural network) of FL may exist in the cloud. Here, the model information of the DNN may be sent to the first device 610. The first device 610 may perform some training on the DNN using a subset of the training data based on the model information, and send the new gradient information to the cloud. The above cycle may be repeated, so that the DNN of FL in the cloud may be updated. In addition, the model information of the DNN may also be sent to the second device 620. The second device 620 may perform some training on the DNN using a subset of the training data based on the model information, and send the new gradient information to the cloud. The above cycle may be repeated, so that the DNN of FL in the cloud may be updated. That is, the cloud may obtain updated learning model information based on the training data owned by each of the multiple devices 610 and 620, and integrate the information to update the overall model information. For example, the device may apply the training data to a local model constructed based on the sent model information and send the gradient to the cloud, and the cloud may update the global model based on the gradient received from the device.

[0128] Figure 7 is a diagram showing a method for performing learning based on federated learning applicable to the present disclosure. Figure 7 , the FL training server 710 may determine at least one terminal participating in FL learning (or operation). For example, the FL training server 710 may be configured in a network, but may not be limited thereto. Figure 7 , the learning of the FL training server 710 may be iterated at regular intervals. For example, in the Nth learning iteration at a specific interval, the FL training server 710 may receive a training resource report from at least one terminal 721, 722, 723, 724, and 725. The training resource report may include information related to FL training in each of the at least one terminal 721, 722, 723, 724, and 725, and may not be limited to a specific form. The FL training server 710 may select a terminal to perform learning in a given cycle based on the training resource report information obtained from each of the at least one terminal 721, 722, 723, 724, and 725. For example, in Figure 7 Terminal A 721, terminal C 723, and terminal D 724 are selected in the Nth learning iteration, but this is merely an example for ease of explanation and may not be limited thereto. For example, the FL training server 710 may send a global model and learning configuration information to the terminals 721, 723, and 724 selected in the model distribution and training configuration. The global model is a learning model constructed based on FL, and the selected terminals 721, 723, and 724 may construct a local model based on the global model information. Thereafter, each of the selected terminals 721, 723, and 724 may perform learning by applying the acquired training data to the constructed local model, and report the training result to the FL training server 710. For example, the training result may be the gradient of the DNN, but may not be limited thereto. The FL training server 710 may receive a training result report from each of the selected terminals 721, 723, and 724 in the training result reporting step, and update the global model. For example, the terminal participating in the FL operation (or learning) provides a training result report to the FL training server 710 at a preset time for each learning iteration, and the next learning iteration can be initiated based on this. The above operation can be iterated for each learning iteration. Here, for example, if the learning environment or conditions (e.g., computing resources of the device, wireless channel conditions, other services of the learning device, etc.) do not change, the learning terminal reselection and training reconfiguration may not be required for each learning iteration in which learning is performed. That is, the learning terminals of the same group can participate in learning with the same configuration through multiple iterations. However, for example, independent and identical sampling implementations from all terminals may be required, and considering the above points, the learning terminals may be configured differently according to the iteration, but may not be limited thereto.

[0129] Here, as an example, a method of applying NAS (Non Access Stratum) level congestion control to a terminal participating in FL operation (or learning) (or a terminal selected for FL operation (or learning)) is described below.

[0130] As a specific example, a terminal participating in FL operation (or learning) needs to provide training results to the server for each learning iteration, but may not be able to provide training results to the server at a preset timing based on network congestion. In the above case, the FL training server may not be able to terminate the learning iteration, resulting in a delay or exceeding the preset time. Here, if the FL training server does not obtain the training results from the terminal, the FL training server may perform global model updates or FL model aggregation without results, which may adversely affect the FL model convergence. As an example, the terminal may obtain a backoff timer value based on NAS-level congestion control to postpone signal reception, and the above delay may occur based on this. Here, the backoff timer value may be several (tens) minutes or several (tens) hours, but may not be limited thereto. That is, since the network conditions of the communication system (e.g., network congestion conditions, etc.) may affect the operation of the AI / ML service / application, a method for effectively supporting the AI / ML service by considering the characteristics of the AI / ML service may be required, which will be described below.

[0131] For example, based on NAS level congestion control, the network may provide a back-off timer value to the terminal, and the terminal may postpone signal transmission based on the back-off timer value. The network may determine the back-off timer differently for each terminal, so that each terminal may transmit a signal at a different timing after the back-off timer. That is, a terminal that has received a back-off timer may not transmit a NAS signal unless the back-off timer expires, a request is received from the network, or a service with a high priority should be performed.

[0132] For example, in the case of network overload, AMF may reject NAS messages from terminals using 5G to access the network. If the NAS request is rejected, AMF may send a mobility management back-off timer to the terminal. Except for the deregistration process or the process not affected by congestion control (e.g., high priority access, emergency services) and mobile terminal services, the terminal may not initiate any other NAS requests until the back-off time expires.

[0133] Here, as an example, if the terminal performs a deregistration procedure while the backoff timer is running, the backoff timer may continue to run even after the deregistration procedure. In addition, as an example, if the terminal is already in the CM-CONNECTED state while the backoff timer is running, the terminal may perform a mobility registration update. In addition, if the terminal receives a paging request or a NAS notification message from the AMF while the backoff timer is running, the terminal may stop the backoff timer and start a service request procedure or a mobility registration update procedure through the corresponding access.

[0134] In addition, as an example, if the terminal is in the CM-IDLE state and has not left the registration area, the terminal may send a service request message indicating that the message is excluded from NAS congestion control. As another example, if the terminal is in the CM-IDLE state and has left the registration area, the terminal may send a mobility registration update request message including a request indicating that the message is excluded from NAS congestion control.

[0135] As another example, if the terminal is in the CM-CONNECTED state, the terminal may send a PDU session modification request with a PS data off state change via a UL NAS transport message while the backoff timer continues. Here, the message may be sent with an indication that it is excluded from NAS congestion control.

[0136] In addition, when NAS MM (mobility management) congestion control is activated in the AMF, if the terminal sends a NAS MM message to the AMF indicating that the NAS MM message is excluded from NAS congestion control, the AMF may not reject the NAS MM message, but may forward the NAS SM (session management) message to the corresponding SMF. Here, the forwarded message may be forwarded together with an indication that it is excluded from NAS congestion control. The SMF may confirm that the NAS SM message is not subject to congestion control, and if it is subject to congestion control, it may reject the message. In addition, as an example, even if a cell / RAT / access type and PLMN change is performed, the mobility management back-off timer may not be stopped. That is, the cell / RAT / TA / access type change may not stop the mobility management back-off timer.

[0137] As another example, if a 5GSM core network function change or an always-on PDU session request indication needs to be reported while the NAS MM congestion control timer of the terminal is running and MM signaling cannot be initiated, the terminal can postpone initiating the relevant MM signaling until the MM congestion control timer expires. In addition, if there is a reserved communication mode in the terminal, the AMF can select the fallback timer value considering the communication mode of the terminal so that the terminal does not miss the reserved mode.

[0138] In addition, if the terminal is in the CM-CONNECTED state, the AMF may not reject the registration request message for mobility registration update. On the other hand, the AMF may reject the service request message sent by the terminal already in the CM-CONNECTED state and the UL NAS transmission message containing the mobility management backoff timer.

[0139] As another example, if the terminal receives a DL NAS transport message from the AMF while the backoff timer is still running, the backoff timer may be stopped. In addition, considering CM-IDLE mobility, the AMF may reject the registration request for mobility registration update by sending a registration reject message including the mobility management backoff timer to the terminal.

[0140] For example, as described above, the back-off timer value is provided to the terminal, and the terminal may perform NAS-level congestion control by deferring reception of a NAS message based on the back-off timer value.

[0141] As another example, DNN (Data Network Name)-based congestion control may be performed. For example, the SMF may reject a PDU session establishment request message or a PDU session modification request message, except for a PS data off state change for reporting a specific DNN for which a backoff timer is running. Thus, DNN-based congestion control may be applied to the terminal. In addition, as an example, the SMF may send a PDU session release command message with a DNN backoff timer to the terminal to release a PDU session belonging to a congested DNN. For example, if the DNN backoff timer is included in the PDU session release command message, the reactivation request may not be set as the cause value.

[0142] As another example, when the network data analysis function (NWDAF) is configured, the SMF may determine the back-off timer to be provided to the terminal based on the session management congestion control information provided from the NWDAF. For example, when the DNN back-off timer is activated, the terminal may not initiate a session management process for a congested DNN. On the other hand, the terminal may perform a session management process for another DNN. For example, when there is no DNN associated with the back-off timer, the terminal may initiate a session management request for all PDU session types for a specific DNN. In addition, as an example, in the event of a cell / TA / PLMN / RAT change, an unreliable non-3GPP access network change, or an access type change, the terminal may not stop the back-off timer. That is, the DNN back-off timer may work regardless of the above process.

[0143] As another example, the terminal can initiate a session management process for high priority access and emergency services even when the DNN backoff timer is activated. In addition, the terminal can initiate a session management process to report the data closing state change to the network. In addition, as an example, if the terminal receives a network-initiated session management message for a congested DNN associated with the backoff timer instead of a PDU session release command, the terminal can stop the backoff timer and respond to the network. In addition, if the terminal receives a PDU session release command message for a congested DNN, the terminal can stop the backoff timer unless it receives a new backoff timer from the SMF. The terminal can initiate a PDU session release process and may not stop the backoff timer when the associated PDU session is released.

[0144] In addition, as an example, congestion control based on S-NSSAI (Single Network Slice Selection Assistance Information) may be performed. Congestion control based on S-NSSAI may be applied to handle NAS signal congestion of a terminal with a backoff timer associated with S-NSSAI, regardless of the presence of a DNN. For example, if it is determined that the S-NSSAI is in a congested state, the SMF may apply congestion control based on S-NSSAI to the terminal for an SM request that does not include a PS data off state change report, and may provide a backoff timer and a home public land mobile network (HPLMN) congestion indication. If the terminal receives an S-NSSAI-based backoff timer without an HPLMN congestion indication, the terminal may apply the S-NSSAI backoff timer only to the PLMN from which the backoff time is received. On the other hand, if the terminal receives an S-NSSAI-based backoff timer together with an HPLMN congestion indication, the terminal may apply the S-NSSAI-based backoff timer to both the PLMN from which the backoff time is received and other PLMNs. As another example, the SMF may release a PDU session belonging to a congested S-NSSAI. Here, the SMF may send a PDU session release request message to the terminal, the PDU session release request message including a backoff timer associated with the S-NSSAI or a combination of the S-NSSAI and a specific DNN. For example, if NWDAF is deployed, the SMF may utilize the session management congestion message provided by the NWDAF to determine the backoff timer to be provided to the terminal.

[0145] As described above, NAS-level congestion control can be considered, and DNN-based congestion control and S-NSSAI congestion control can be considered. Here, as an example, the above-mentioned NAS-level congestion control can be applied to a terminal participating in FL operation (or learning) (or a terminal selected for FL operation (or learning)). As an example, a terminal participating in FL operation (learning) can switch to the CM-IDLE state while performing learning. The terminal needs to switch to the CM-CONNECTED state to complete the learning and send the training results to the server. Here, the terminal sends a service request message to the AMF, but the AMF can apply NAS mobility management congestion control. Therefore, the AMF can send a service rejection message including mobility management backoff time information to the terminal, and the terminal can switch to the CM-CONNECTED state after the backoff timer expires.

[0146] As another example, while the terminal participating in FL operation (learning) performs learning, the user plane of the PDU session used to send the training results to the FL training server may be deactivated. When the learning is completed, the terminal needs to activate the user plane of the PDU session to send the training results to the server. Therefore, the terminal can send a service request message to the AMF. However, the AMF may apply NAS mobility management congestion control and send a service rejection message including mobility management backoff timer information to the terminal. Here, the PDU session may be a PDU session for AI / ML services / operations / businesses / applications or a PDU session for FL operation (learning), and may not be limited to a specific form.

[0147] As another example, a terminal participating in FL operation (learning) may need to change the PDU session to send the training results to the server. For example, PDU session modification may be required to modify the QoS (quality of service) of the PDU session or add a QoS flow. Here, the terminal sends a PDU session modification request message to the SMF, but the SMF may send a PDU session modification rejection message including backoff timer information by applying DNN-based congestion control or S-NSSAI-based congestion control. Here, the PDU session can be a PDU session for AI / ML services / operations / businesses / applications or a PDU session for FL operation (learning), and may not be limited to a specific form.

[0148] As described above, if the terminal postpones the sending of the training result based on the backoff timer based on NAS congestion control, the FL training server may not be able to obtain the training result from the corresponding learning iteration. Therefore, the FL training server may terminate the corresponding learning iteration and perform a global model update without receiving the training result. In other words, the FL training server will skip the corresponding training result and perform a global model update, which may adversely affect the model update convergence. As another example, the FL training server may wait to receive the training result while the terminal postpones the sending and terminate the learning iteration after receiving the training result, but this may cause a delay. As an example, the backoff timer value may be several (tens) minutes or several (tens) hours, but may not be limited thereto.

[0149] That is, in the above situation, since network congestion may affect the operation of AI / ML services / applications, a method for effectively supporting AI / ML services by considering the characteristics of AI / ML services may be required, which will be described below.

[0150] For example, considering that the congestion control related event support method of AI / ML service may be composed of a combination of one or more of the following operations / configurations / steps, and is not limited to a specific form.

[0151] For example, AI / ML services may be used interchangeably with the following AI / ML-based services, AI / ML businesses, AI / ML applications, AI / ML transmissions, AI / ML operations, and AI / ML operation businesses, and are not limited to a specific form.

[0152] In addition, as an example, it can be used interchangeably with the following FL (Federated Learning) operation, FL training, FL training operation, and distributed learning operation, and is not limited to a specific form.

[0153] In addition, UE (user equipment) and terminal may be used interchangeably below, but are not limited to this. In addition, as an example, AF (application function), AS (application server) and server may be used interchangeably, and are not limited to a specific form. As an example, AF and AS may be AI / ML AF and AI / ML AS, but may not be limited to this. As an example, although a congestion control-related event support method based on AI / ML services is described below, it is not limited to AI / ML services and may be applicable to other services and is not limited to a specific form.

[0154] As an example, the content described below may refer to but is not limited to the operation of a 5G system (e.g., TS23.501, TS23.502, TS23.503).

[0155] AMF provides information related to congestion control applications

[0156] For example, AMF can provide a notification service based on a congestion control application related information event to provide congestion control application related information. Here, a new event can be provided through the "Namf_EventExposure Service". For example, when setting and subscribing to an event, AMF can provide a notification service corresponding to the occurrence of the event to a service consumer or service subscriber based on an event ID. That is, AMF can notify information corresponding to the event that occurred based on the event ID, and for this purpose, operations related to the event can be supported. As a specific example, "Namf_EventExposure_Subscribe" for event subscription, "Namf_EventExposure_UnSubscribe" for event unsubscription, and "Namf_EventExposure_Notify" for event provision operations according to events can be supported. That is, subscription, unsubscription, and indication operations for event provision can be supported. For example, the "Namf_EventExposure Service Operation" as an event-related operation can refer to the TS23.502 document, but is not limited thereto. In addition, as an example, a new event can be defined as a type of UE access and mobility information event. Here, an event ID can be assigned and granted to a new event.

[0157] As a more specific example, the above-mentioned congestion control application related information may be one of the information based on event notification. That is, the congestion control application related information may be provided to a service consumer or a service subscriber as a notification service according to a congestion control event based on "Namf_EventExposure_Notify". Here, the event name is not limited to the congestion control application related information and may be referred to as other names. As an example, the above-mentioned information may be included / provided in a combination form of at least one of the information in the following Table 2, an explicit form, an implicit form, a compressed form, and other various forms, and is not limited to a specific form.

[0158] As a specific example, referring to Table 2, information indicating that congestion control is applied to the terminal based on the congestion control event may be notified. As another example, information indicating that a backoff timer value and information have been provided to the terminal based on the congestion control event may be notified. As another example, information indicating that a rejection message for an MM NAS message is sent to the terminal based on the congestion control event may be notified. As another example, the backoff timer value (or information) itself provided to the terminal based on the congestion control event may be notified. Alternatively, the backoff timer value (or information) operated (or initiated) by the terminal based on the congestion control event may be notified.

[0159] As another example, congestion control information may be notified based on a congestion control event. As an example, the congestion control information may indicate the degree of congestion as high / medium / low as congestion control level information. As another example, the degree of congestion may be indicated by an index (e.g., 0 to 100) as congestion control level information, but is not limited thereto.

[0160] [Table 2]

[0161]

[0162] As another example, the AF may subscribe to a congestion control application related information event provided by the AMF for a specific terminal. Here, the event name may be a congestion control application related information event, but this is a name used only for ease of explanation and may not be limited thereto. Here, event subscription may be made directly to the AMF. As another example, event subscription may be performed through the NEF. When subscribing to an event through the NEF, the NEF may subscribe to the event for the AF to the AMF. Here, the NEF may subscribe to the event directly to the AMF or through another network function (e.g., UDM, PCF).

[0163] For event subscription, the above-mentioned event operations (e.g., Namf_EventExposure, Nnef_EventExposure, Nudm_EventExposure) may be considered, and these operations may be extended (or modified) and used by considering the following. For example, the terminal may be a terminal selected (or determined) for FL operation (or learning). Here, the information indicating the terminal may be target information of the event report (e.g., GPSI, SUPI, etc.). For example, the target information of the event report may consider the "Nnef_EventExposure_Subscribe operation" operation of TS23.502, but may not be limited thereto.

[0164] That is, the terminal selected for the FL operation may refer to the target terminal and subscribe to the corresponding event. Here, the corresponding event subscription may be a request for congestion control application related information. For example, when the AF obtains congestion control related information based on the notification service of the congestion control application related information event, the AF may perform at least one of the operations in Table 3 below.

[0165] For example, the AF may recognize that a learning iteration requires a longer time than the time previously set by the congestion control. As another example, the AF may update the global model without the training results for the terminal to which the congestion control is applied. In other words, the AF may skip the training results for the terminal to which the congestion control is applied and update the global model. As an example, the global model update may mean FL model aggregation. As another example, the AF may recognize that a new member terminal needs to be selected / determined for FL operation (or learning). Afterwards, the AF may request the network to provide the new member terminal.

[0166] [Table 3]

[0167]

[0168]

[0169] Figure 8 A method for receiving event notification after subscribing to congestion control application related information events provided by AMF at AF applicable to the present disclosure is shown.

[0170] refer to Figure 8 , the terminal 810 may perform registration in the network and establish a PDU session. For example, the PDU session may be a PDU session set up for at least one of an AI / ML service, operation, business, or application. As another example, the PDU session may be a PDU session for FL operation (or learning). As another example, the PDU session may be a PDU session for services other than AI / ML services, and is not limited to a specific implementation. Thereafter, the AF 850 ​​may select (or determine) a member terminal for FL operation (or learning). As an example, the AF 850 ​​may interact with other network functions and terminals for FL operation (or learning). As an example, refer to Figure 7 The terminal may perform a learning resource report, and may determine a member terminal that performs FL operation (or learning) based on the report, but may not be limited thereto. As an example, member terminal selection may refer to, but is not limited to, TR 23.700-80.

[0171] Thereafter, AF 850 ​​may send a subscription request for events related to congestion control application information to NEF 840 of a member terminal for FL operation (or learning). For example, the subscription request for an event may be performed for each terminal, or may be performed together for multiple terminals, and is not limited to a specific form. Thereafter, NEF may send a subscription request for events related to congestion control application information to AMF 820 for a terminal that has made a subscription request for an event. For example, NEF may query the service AMF information of the terminal using UDM, and in response to this, the service AMF of each terminal may be confirmed. For example, when the AMF serving 3GPP access and the AMF serving non-3GPP access are different, NEF 840 may send the above-mentioned subscription request for the event to the two AMFs. As another example, NEF may send a subscription request for an event to one AMF (e.g., an AMF serving 3GPP access), and is not limited to a specific form. Thereafter, AMF 840 may send a response message to NEF 840 for the received subscription request, and NEF 840 may send a response message to AF 850 ​​for the received subscription request. Thereafter, AF 850 ​​may distribute the model to the terminals participating in the FL operation (or learning) and set up the learning. That is, AF 850 ​​may send FL model information to the terminals participating in the learning, and send the setting information required for the learning. For example, the operation may be performed through application layer signaling / messages, but is not limited thereto.

[0172] Thereafter, the terminal 810 may perform learning on the local model constructed based on the received model information, and after learning, the terminal 810 may terminate the local learning and send the training result to the AF. However, when the terminal 810 performs learning, it may be in the CM-IDEL state, or the user plane of the PDU session may be in a deactivated state.

[0173] Therefore, the terminal 810 may switch to the CM-CONNECTED state or send a service request message to the AMF 820 for user plane activation of the PDU session. Here, as an example, the AMF 820 may apply congestion control based on the network congestion state. When the AMF 820 applies congestion control, the AMF 820 may send a service rejection message including a backoff timer value to the terminal 810. In addition, the AMF 820 may send a notification of an event to the NEF 840 based on the congestion control application related information event. As an example, the AMF 820 may send a notification of an event to the NEF 840 after sending the service rejection message to the terminal 810. As another example, the AMF 820 may send a notification of an event to the NEF 840 while sending the service rejection message to the terminal 810. Thereafter, the NEF 840 may send a notification of the congestion control application related information event to the AF 850. As another example, the NEF 840 may select a new member terminal for FL operation (or learning) and send it to the AF 850, but is not limited to a specific implementation.

[0174] As another example, a network function (NF) that performs operations related to selecting (or determining) a member terminal for FL operation (or learning) may subscribe to a congestion control application related information event provided by the AMF. As an example, for ease of explanation, the event name is only an example and may not be limited thereto.

[0175] In addition, the above-mentioned NF may be an NF that performs the above-mentioned event subscription for FL operation (learning) as an existing NF (e.g., NEF, PCF, NWDAF, etc.). As another example, the NF may be a newly defined NF related to member terminal selection (or determination) for FL operation (learning). As an example, the newly defined NF may be an AI / ML NF, but this is only configured for ease of explanation and is not limited to the name. In addition, as an example, the operation related to member terminal selection (or determination) for FL operation (or learning) may include providing a member terminal list for FL operation to the AF. As an example, the terminal list may be a candidate terminal list, but is not limited thereto. As an example, the operation of member terminal selection (or determination) for FL operation (learning) may refer to TR 23.700-80, but may not be limited thereto.

[0176] As another example, the operation related to selecting (or determining) a member terminal for FL operation (or learning) may include providing auxiliary information related to FL operation (or learning) to the AF. As an example, the FL operation (or learning) may be an AI / ML operation (or learning) and is not limited to a specific form.

[0177] In addition, the NF that performs operations related to selecting (or determining) a member terminal for FL operation (or learning) may subscribe to the congestion control application related information events provided by the AMF. For example, the AF may request the NF to provide a list of member terminals for FL operation (or learning) (or auxiliary information related to FL operation (or learning)), and may subscribe to events for the above terminals from the AMF for selection (or determination) of member terminals (or candidate terminals).

[0178] As another example, the NF may provide the above-mentioned terminal list to the AF, and then receive the terminal list finally selected (or determined) from the AF, and subscribe to the above-mentioned events to the AMF for the corresponding terminals without being limited to a specific form.

[0179] In addition, as an example, the above event subscription can be performed directly to AMF. As another example, event subscription can be performed through NEF. When event subscription is performed via NEF, events can be subscribed directly to AMF, or events can be subscribed through another NF (e.g., UDM, PCF).

[0180] For example, event subscription can be performed based on existing event related operations (e.g., Namf_EventExposure, Nnef_EventExposure, Nudm_EventExposure), and can be extended (or modified) and used for the purposes proposed in this article. In addition, for example, event subscription can be a request for congestion control application related information.

[0181] For example, when the NF performing the operation of selecting (or determining) a member terminal for FL operation (or learning) receives information according to a notification service based on a congestion control application related information event, the NF may perform at least one of the operations in Table 4 below. For example, the NF may send an event notification to the AF. As another example, the NF may recognize that a new member terminal for FL operation (or learning) needs to be selected (or determined), and may select (or determine) the new member terminal and provide the corresponding information to the AF.

[0182] [Table 4]

[0183]

[0184] SMF provides information related to congestion control applications

[0185] For example, SMF can provide notification services based on congestion control application related information events to provide congestion control application related information. Here, new events can be provided through the event operation "Nsmf_EventExposure service".

[0186] For example, when setting and subscribing to events, SMF can provide notification services based on the occurrence of events based on event IDs. That is, SMF can notify information corresponding to the events that occurred based on event IDs, and for this purpose, event-related operations can be supported. As a specific example, "Nsmf_EventExposure_Subscribe" for event subscription, "Nsmf_EventExposure_UnSubscribe" for event unsubscription, and "Nsmf_EventExposure_Notify" for providing operations of events according to events can be supported. That is, subscription, unsubscription, and indication operations for event provision can be supported. As an example, the "Nsmf_EventExposure service operation" as an event-related operation can refer to the TS23.502 document, but it is not limited to this.

[0187] In addition, as an example, an event ID may be assigned and granted to a new event. As a more specific example, the above-mentioned congestion control application related information may be notified as one or more pieces of information during the event. That is, the congestion control application related information may be provided to a service consumer or a service subscriber through "Nsmf_EventExposure_Notify". Here, the event name is not limited to the congestion control application related information and may be referred to as other names. As an example, the above-mentioned information may be included / provided in a combination form, an explicit form, an implicit form, a compressed form, and various other forms of at least one of the information in the following Table 5, and is not limited to a specific form. As a specific example, information indicating that congestion control has been applied to the terminal based on the congestion control event may also be notified. As another example, information indicating that a backoff timer value and information based on the congestion control event have been provided to the terminal may be notified. As another example, information indicating that a rejection message for an SM NAS message is sent to the terminal based on the congestion control event may be notified. As another example, the backoff timer value (or information) itself provided to the terminal based on the congestion control event may be notified. Alternatively, the backoff timer value (or information) operated (or initiated) by the terminal based on the congestion control event may be notified.

[0188] As another example, congestion control information may be notified based on a congestion control event. As an example, the congestion control information may indicate the degree of congestion as high / medium / low as congestion control level information. As another example, the degree of congestion may be indicated by an index (e.g., 0 to 100) as congestion control level information, but may not be limited thereto. As another example, information indicating that DNN-based congestion control has been applied based on a congestion control event may be notified. Here, as an example, DNN information may also be included, but may not be limited thereto. As another example, information indicating that S-NSSAI-based congestion control has been applied based on a congestion control event may be notified. Here, as an example, S-NSSAI information may also be included, but may not be limited thereto.

[0189] [Table 5]

[0190]

[0191] For example, the AF may subscribe to a congestion control application related information event provided by the SMF for at least one of a PDU session or a specific terminal. Here, the event name may be a congestion control application related information event, but this is only a name used for ease of explanation and may not be limited thereto. Here, event subscription may be made directly to the SMF. As another example, event subscription may be performed through the NEF. When subscribing to an event through the NEF, the NEF may subscribe to the event for the AF to the SMF. Here, the NEF may subscribe to the event directly to the SMF, or may subscribe through another network function (e.g., UDM, PCF).

[0192] For event subscription, the above-mentioned event operation can be considered, and the following content can be considered to expand (or modify) and use the operation. For example, the terminal can be a terminal selected (or determined) for FL operation (or learning). In addition, for example, the PDU session can be a PDU session for AI / ML service / operation / business / application. As another example, the PDU session can be a PDU session for FL operation (or learning). For example, information indicating at least one of the PDU session or the terminal can be target information of the event report (e.g., GPSI, SUPI, etc.). For example, the target information of the event report can consider the "Nnef_EventExposure_Subscribe operation" operation of TS23.502, but is not limited to this. As another example, the target information of the event report can be but is not limited to the terminal address (i.e., IP address or MAC address) information of the "Nnef_AFsessionWithQoS_Create service operation" of TS23.502.

[0193] That is, the terminal selected for the FL operation may refer to a target terminal and subscribe to a corresponding event. Here, the event subscription may be a request for information related to the congestion control application.

[0194] For example, when the AF obtains congestion control related information according to the notification service based on the congestion control application related information event, the AF may perform at least one operation in the following Table 6.

[0195] For example, the AF may recognize that the learning iteration takes longer than the time preset by the congestion control. As another example, the AF may update the global model without the training results for the terminal to which the congestion control is applied. In other words, the AF may skip the training results for the terminal to which the congestion control is applied and update the global model. As an example, the global model update may mean FL model aggregation. As another example, the AF may recognize that a new member terminal needs to be selected / determined for FL operation (or learning). Afterwards, the AF may request that the new member terminal be provided to the network.

[0196] [Table 6]

[0197]

[0198] Fig. 9 A method for receiving event notification after subscribing to a congestion control application information event provided by an SMF at an AF applicable to the present disclosure is shown.

[0199] refer to Fig. 9 , the terminal 910 may perform registration in the network and establish a PDU session. For example, the PDU session may be a PDU session set for at least one of an AI / ML service, operation, business, and application. As another example, the PDU session may be a PDU session for FL operation (or learning). As another example, the PDU session may be a PDU session for a service other than an AI / ML service, and is not limited to a specific implementation.

[0200] Thereafter, the AF 950 may select (or determine) a member terminal for FL operation (or learning). For example, the AF 950 may interact with other network functions and terminals to perform FL operation (or learning). Figure 7 The terminal may perform a learning resource report, and may determine a member terminal that performs FL operation (or learning) based on the report based on the report, but may not be limited thereto. For example, member terminal selection may refer to TR 23.700-80, but may not be limited thereto.

[0201] Thereafter, AF 950 may send a subscription request for congestion control application related information events to NEF 940 for member terminals used for FL operation (or learning). For example, the subscription request for the event may be performed for each terminal, or may be performed by multiple terminals together, and is not limited to a specific form. Thereafter, NEF may send a subscription request for congestion control application related information events to SMF 930 for the terminal that has made a subscription request for the event. For example, NEF may query the service SMF information of the terminal using UDM, and as a response to this, confirm the service SMF of each terminal. Thereafter, SMF 930 may send a response message to NEF 940 for the received subscription request, and NEF 940 may send a response message to AF 950 for the subscription request received from AF 850. Thereafter, AF 950 may distribute the model to the terminals participating in FL operation (or learning) and establish learning. That is, AF 950 may send FL model information to the terminals participating in the learning, and send the setting information required for the learning. For example, the operation may be performed via application layer signaling / messages, but is not limited thereto.

[0202] Thereafter, the terminal 910 may perform learning on the local model constructed based on the received model information, and after learning, the terminal 910 may terminate the local learning and send the training result to the AF. Here, as an example, the terminal 910 needs to perform PDU session modification. As an example, the terminal 910 may perform PDU session modification to modify QoS or add QoS flow. To this end, the terminal 910 may send a PDU session modification request message to the SMF 930. Thereafter, the SMF 930 may apply congestion control based on the network congestion state. When the SMF 930 applies congestion control, the SMF 930 may send a PDU session modification rejection message including a backoff timer value to the terminal 910. In addition, the SMF 930 may send a notification of an event to the NEF 940 based on the congestion control application related information event. For example, the SMF 930 may send a notification of an event to the NEF 940 after sending a PDU session modification rejection message to the terminal 910. As another example, the SMF 930 may send a notification of the event to the NEF 940 while sending a PDU session modification reject message to the terminal 910. Thereafter, the NEF 940 may send a notification of the congestion control application related information event to the AF 950. As another example, the NEF 940 may select a new member terminal for FL operation (or learning) and send it to the AF 950, but is not limited to a specific implementation.

[0203] As another example, the NF performing operations related to selecting (or determining) a member terminal for FL operation (or learning) may subscribe to a congestion control application related information event provided by the SMF. As an example, for ease of explanation, the event name is only an example and may not be limited thereto.

[0204] In addition, the above-mentioned NF may also be an NF that subscribes to the event of the above-mentioned FL operation (learning) as an existing NF (such as NEF, PCF, NWDAF, etc.). As another example, the NF may be a newly defined NF related to the selection (or determination) of a member terminal for FL operation (learning). As an example, the newly defined NF may be an AI / ML NF, but this is only configured for ease of explanation and is not limited to the name. In addition, as an example, the operation related to the selection (or determination) of a member terminal for FL operation (or learning) may include providing a member terminal list for FL operation to the AF. As an example, the terminal list may be a candidate terminal list, but is not limited thereto. As an example, the operation of member terminal selection (or determination) for FL operation (learning) may refer to TR 23.700-80, but may not be limited thereto.

[0205] As another example, the operation related to selecting (or determining) a member terminal for FL operation (or learning) may include providing auxiliary information related to FL operation (or learning) to the AF. As an example, the FL operation (or learning) may be an AI / ML operation (or learning) and is not limited to a specific form.

[0206] In addition, the NF that performs operations related to selecting (or determining) member terminals for FL operation (or learning) can subscribe to congestion control application related information events provided by the SMF. For example, the AF can request the NF to provide a list of member terminals for FL operation (or learning) (or auxiliary information related to FL operation (or learning)), and can subscribe to events for the above terminals to the SMF for selection (or determination) of member terminals (or candidate terminals).

[0207] As another example, the NF may provide the above terminal list to the AF, then receive the terminal list finally selected (or determined) from the AF, and subscribe to the above events to the SMF for the corresponding terminals without being limited to a specific form.

[0208] In addition, as an example, the above event subscription can be performed directly to SMF. As another example, event subscription can be performed through NEF. When event subscription is performed through NEF, events can be subscribed directly to SMF or through another NF (e.g., UDM, PCF).

[0209] For example, event subscription can be performed based on existing event related operations (e.g., Nsmf_EventExposure, Nnef_EventExposure, Nudm_EventExposure), and can be extended (or modified) and used for the purposes proposed in this article. In addition, for example, event subscription can be a request for congestion control application related information.

[0210] For example, when the NF performing the operation of selecting (or determining) a member terminal for FL operation (or learning) receives information according to the notification service of the event based on the congestion control application related information, the NF may perform at least one of the operations of Table 7 below. For example, the NF may send an event notification to the AF. As another example, the NF may recognize that a new member terminal for FL operation (or learning) needs to be selected (or determined), and may select (or determine) the new member terminal and provide the corresponding information to the AF.

[0211] [Table 7]

[0212]

[0213] Fig.10 A method for receiving event notification after subscribing to congestion control application related events provided by SMF at AF applicable to the present disclosure is shown. Fig.10 , AF 1010 may send a request message for resource reservation for an AF session to NEF 1020. Here, the request message may include at least one of a terminal address, an AF identifier, a flow description or an external application identifier, a QoS reference, an alternative service requirement, a DNN, or an S-NSSAI. In addition, the request message may include information about the time period or traffic volume of the requested QoS. In addition, as an example, AF 1010 may provide individual QoS parameters instead of a QoS reference. The QoS individual parameters may include at least one of a requested 5GS delay, a requested priority, a requested guaranteed flow bit rate (GFBR), a requested maximum flow bit rate (MFBR), a flow direction, a burst size, a time when a burst arrives at the UE (uplink) or UPF (downlink), a periodicity, a time domain, or a lifetime information.

[0214] Here, as an example, in addition to the above-mentioned request message (e.g., Nnef_AFsessionWithQoS_Create request message), AF 1010 may also include at least one of the information in the following Table 8 in a combined form, an implicit form, an explicit form, or a compressed form. As an example, the information in Table 8 may be request information for indications related to congestion control applications. As a specific example, the request message may include information requesting notification of the application of congestion control when congestion control is applied. The request may be subdivided based on the type of congestion control applied. That is, it may be requested to notify whether it is congestion control based on DNN or congestion control based on S-NSSAI.

[0215] In addition, as an example, the request message may request notification of the provided back-off timer value / information to the UE. That is, the request message may request notification of whether congestion control is applied and information about the back-off timer value provided when congestion control is applied.

[0216] [Table 8]

[0217]

[0218] Thereafter, the NEF 1020 may perform authentication based on the request message received from the AF 1010. Here, the NEF 1020 may authenticate the request of the AF 1010 after assigning a transaction reference ID to the request message. Thereafter, the NEF 1020 may apply a QoS control policy to the AF. For example, if the authentication requested for the AF 1010 is rejected, the NEF 1020 may send a result value indicating authentication failure to the AF 1020.

[0219] Here, if the NEF 1020 does not receive the above-mentioned individual QoS parameters from the AF 1010, the NEF 1020 may search for the PCF in the BSF (binding support function) based on the terminal address. The NEF 1020 may trigger a PCF policy authentication creation request (e.g., Npcf_PolicyAuthorization_Create) and forward it to the PCF 1030. Thereafter, the NEF 1020 may receive a response message from the PCF 1030, and provide the AF 1010 with at least one of the terminal address, the AF identifier, the flow description, the QoS reference, or the optional alternative service requirement based on the response message. In addition, as an example, the received time period or traffic volume information may also be included in the sponsored data connection information and provided to the AF 1010. Thereafter, the NEF 1020 may send a policy authentication subscription message (e.g., Npcf_PolicyAuthorization_Subscribe) to the PCF 1030, and based thereon receive a notification message (e.g., Npcf_PolicyAuthorization_Notification) from the PCF 1030. Here, the NEF 1020 may provide the congestion control application related notification request information to the PCF 1030 in the step of sending the policy authentication request message. As another example, some information on the congestion control application related notification request may be sent to the PCF 1030 through the policy authentication request message, and some request information may be sent to the PCF 1030 through the policy authentication subscription message.

[0220] For example, if AF 1010 is a subject authenticated by an operator, AF 1010 may directly send a policy authentication creation request message (e.g., Npcf_PolicyAuthorization_Create) to PCF 1030, and directly request reserved resources for AF session from PCF 1030 based on the policy authentication creation request message. Here, AF 1010 may send a congestion control application related notification request by including the congestion control application related notification request in the policy authentication creation request message. As described above, the request message (Nnef_AFsessionWithQoS_Create request message) sent by AF 1010 to NEF 1020 may be replaced by the policy authentication creation request message. As another example, AF 1010 may provide congestion control application related notification request information through a policy authentication subscription message (e.g., Npcf_PolicyAuthorization_Subscribe). As another example, some of the congestion control application related notification request information may be included in the policy authentication creation request message, and other information may be provided via a policy authentication subscription message, without limitation to a specific implementation.

[0221] In addition, for example, when the PCF 1030 receives a policy authentication creation request from the NEF 1020 as described above, the PCF 1030 may determine whether the request is approved. Here, if the request is not approved, the PCF 1030 may indicate to the NEF 1020 that the request is not approved. On the other hand, if the request is approved, the PCF 1030 may obtain the required QoS parameters based on the information provided by the NEF 1020, determine whether the QoS is allowed, and indicate the result to the NEF 1020. In addition, if an alternative service requirement is provided, the PCF 1030 may obtain an alternative QoS parameter set in the same priority order from one or more QoS reference parameters included in the alternative service requirement, and notify the NEF 1020 of the result. As an example, the above operation may refer to, but is not limited to, TS23.503. Here, as an example, if the AF 1010 is considered to be trusted by the operator, the PCF 1030 may directly send a policy authentication creation response message to the AF 1010 based on the AF 1010 request.

[0222] For example, the alternative QoS parameter set obtained by the PCF for the PCC rule may be used to subsequently establish an alternative QoS profile. The alternative QoS profile parameters provided to the NG-RAN may refer to, but not be limited to, TS23.501. For example, if the PCF 1030 determines that updated policy information of the SMF is required, the PCF 1030 may send an SM policy control update notification (e.g., Npcf_SMPolicyControl_UpdateNotify) request with updated policy information for the PDU session based on the SM policy connection modification procedure initiated by the PCF.

[0223] In addition, after NEF 1020 receives the response message from PCF 1030, NEF 1020 may send a response message (e.g., Nnef_AFsessionWithQoS_Create request message) to AF 1010. Here, the response message may include a transaction reference ID and result information. For example, the result information may be information about whether the request is authorized. Thereafter, NEF 1020 may provide resource allocation and other event information to PCF 1030 through a policy authentication subscription message (e.g., Npcf_PolicyAuthorization_Subscribe). Here, when PCF 1030 generates a PCC rule provided to SMF after receiving a request message from NEF 1020, PCF 1030 may include the congestion control application related notification request information in the PCC rule based on one or more of the congestion control application related notification request information provided by AF 1010, the information provided by NEF 1020 through a request or subscription message, the terminal subscription information, and the policy set in PCF 1030. Here, the congestion control application related notification request information included in the PCC rule may be a request for the SMF to notify when an event occurs.

[0224] In addition, as an example, even if the AF does not provide congestion control application related notification request information and only provides some of the request information, the policy set in the PCF or the terminal subscriber information may determine that the congestion control application related notification request information is required. As an example, if the AF is an AI / ML or FL server, the AF request may enable various information (or policies) to be generated based on at least one of the AI / ML (or FL) service, the AI / ML (or FL) application, the AI / ML (or FL) service of the DNN and / or S-NSSAI, and whether the terminal performs the AI / ML (or FL) service.

[0225] In addition, as an example, when an event condition is met, the PCF 1030 may perform event-based notification by sending a policy authentication notification message (e.g., Npcf_PolicyAuthorization_Notify) to the NEF 1020. In addition, the NEF 1020 may send an event notification from the PCF 1030 to the AF 1010 through a notification message (e.g., Nnef_AFsessionWithQoS_Notify).

[0226] Fig.11 A method for receiving event notification after subscribing to congestion control application related events provided by SMF at AF applicable to the present disclosure is shown. Fig.11 , AF 1110 may send a request message for resource reservation for an AF session to NEF 1120. Here, the request message may include at least one of a terminal address, an AF identifier, a flow description or an external application identifier, a QoS reference, an alternative service requirement, a DNN, or an S-NSSAI. In addition, the request message may include information about the time period or traffic volume of the requested QoS. AF 1110 may provide individual QoS parameters instead of a QoS reference. For example, the QoS individual parameters may include at least one of a requested 5GS delay, a requested priority, a requested GFBR, a requested MFBR, a flow direction, a burst size, a time when a burst arrives at the UE (uplink) or UPF (downlink), a periodicity, a time domain, and a lifetime information.

[0227] Here, as an example, in addition to the above-mentioned request message (e.g., Nnef_AFsessionWithQoS_Create request message), AF 1110 may also further include at least one of the information in Table 8 above in a combined form, an implicit form, an explicit form, or a compressed form. As an example, the information in Table 8 may be request information for congestion control application-related indications. As a specific example, the request message may include information requesting notification of the application of congestion control when congestion control is applied. As an example, the request may be subdivided based on the type of congestion control applied. That is, it may be requested whether the notification is DNN-based congestion control or S-NSSAI-based congestion control.

[0228] In addition, as an example, the request message may request notification of the provided back-off timer value / information to the terminal. That is, the request message may request notification of whether congestion control is applied and the back-off timer value provided when congestion control is applied.

[0229] Thereafter, the NEF 1120 may perform authentication based on the request message received from the AF 1110. Here, the NEF 1120 may authenticate the request of the AF 1110 after assigning a transaction reference ID to the request message. Thereafter, the NEF 1120 may apply a policy to control the QoS amount for the AF. For example, if the authentication requested by the AF 1110 is rejected, the NEF 1120 may send a result value indicating authentication failure to the AF 1110.

[0230] Here, as an example, if the NEF 1120 receives the above-mentioned individual QoS parameters from the AF 1110, the NEF 1120 may send a request message (e.g., Ntsctsf_QoSandTSCAssistance_Create) including the received individual QoS parameters to the TSCTSF (Time Sensitive Communication Time Synchronization Function) 1130. As an example, if the operator considers the AF 1110 to be trustworthy, the AF 1110 may send the request message directly to the TSCTSF 1130. As an example, there may be one TSCTSF per DNN / S-NNAI, and the TSCTSF address may be set to the NEF 1120. Thereafter, the TSCTSF 1130 may send a policy authentication update (e.g., Npcf_PolicyAuthorization_Update) request to the PCF 1140. Thereafter, the TSCTSF 1130 may receive a policy authentication update (e.g., Npcf_PolicyAuthorization_Update) response from the PCF 1140. Here, the PCF 1140 may determine whether the request received from the TSCTSF 1130 is authenticated, and if not authenticated, may notify the TSCTSF 1130 of corresponding information. On the other hand, if the request is authenticated, the PCF 1140 may obtain required QoS parameters based on the information provided by the TSCTSF 1130, determine whether the corresponding QoS is allowed, and then present the result information to the TSCTSF 1130. In addition, for example, if an alternative service requirement is provided, the PCF 1140 may obtain an alternative QoS parameter set in the same priority order from one or more QoS reference parameters included in the alternative service requirement, and notify the TSCTSF 1130 of the obtained information.

[0231] For example, if the PCF 1140 receives individual QoS parameters instead of a QoS reference, the PCF 1140 may set the PDB and MDBV based on the requested PBD and burst size received from the TSCTSF 1130. For example, if the requested PDB is not provided, the PCF 1140 may determine a PDB that matches the QoS reference. In addition, the PCF 1140 may set the GFBR and MFBR based on the request value sent by the TSCTSF 1130. The PCF 1140 may determine the QoS flow priority using the requested priority received from the AF 1110. The TSCTSF 1130 may prioritize the individual QoS parameter values ​​over the default value of the 5QI. In addition, as an example, if the request is not authenticated or the required QoS is not allowed, the TSCTSF 1130 may send a response including a result value indicating the reason for the failure to the NEF 1120. Here, the response message may include a transaction reference ID and result information. As an example, the result information may indicate whether the request is authenticated. In addition, as an example, if the operator considers the AF to be trustworthy, the AF 1110 may directly receive a response message from the TSCTSF 1130 and is not limited to a specific implementation.

[0232] Thereafter, the TSCTSF 1130 may send a policy authentication subscription message (e.g., Npcf_PolicyAuthorization_Subscribe) to the PCF 1140 for resource allocation and other event information. Thereafter, if the event condition is met, the PCF 1140 may perform event-based notification by sending a policy authentication notification message (e.g., Npcf_PolicyAuthorization_Notify) to the TSCTSF 1130. In addition, the TSCTSF 1130 may send an event notification from the PCF 1140 to the NEF 1120 through a notification message (e.g., Ntsctsf_QoSandTSCAssistance_Notify). In addition, the NEF 1120 may send an event notification to the AF through a notification message (e.g., Nnef_AFsessionWithQoS_Notify).

[0233] Fig.12 is a flow chart illustrating an event notification method based on NAS-level congestion control applicable to the present disclosure. Fig.12, the network function may receive a subscription request for a congestion control application related information event for at least one terminal. (S1210) Then, the network function may apply congestion control to the at least one terminal. (S1220) Based on the applied congestion control, a notification of the congestion control application related information event may be performed. (S1230) Here, the at least one terminal may be a terminal selected based on a federated learning (FL) operation.

[0234] For example, the network function may be AMF. Here, AMF may receive a subscription request for congestion control application related information events from NEF. That is, as described above, NEF may send a subscription request for congestion control application related information events to AMF based on the AF request.

[0235] When the AMF applies congestion control to at least one terminal, the AMF may send a NAS message including a mobility management back-off timer value to the at least one terminal. For example, each of the at least one terminal may postpone operation based on the mobility management back-off timer.

[0236] In addition, when the notification of the congestion control application related information event is performed based on the applied congestion control, the AMF may send the congestion control application related information to the NEF, and the NEF may send the congestion control application related information to the AF. Here, the congestion control application related information may include at least one of the information indicating that congestion control is applied to at least one terminal, the information indicating that a mobility management backoff timer value is provided to at least one terminal, the information indicating that a rejection message for an MM NAS message is sent to at least one terminal, or the congestion control level information. In addition, the AF may select at least one terminal for each learning iteration based on the FL operation. The AF may obtain training result information from at least one terminal by providing FL model information to at least one terminal in the learning iteration. The AF may update the FL model based on the training result information. Here, when the congestion control application related information is notified to the AF, the FL model may also be updated without the training result information of at least one terminal to which congestion control is applied. As another example, the AF may send a request for at least one terminal newly determined to participate in the learning iteration based on the FL operation. As another example, a subscription request for the congestion control application related information event may be received from the AI / ML NF based on the AF request, but is not limited thereto.

[0237] As another example, the network function is an SMF, and the SMF may receive a subscription request for a congestion control application related information event from the NEF based on at least one terminal and a PDU session. The NEF may send a subscription request for a congestion control application related information event to the SMF based on the AF request. Here, the PDU session may be a PDU session for at least one of an AI / ML service, operation, business, or application or a PDU session for FL operation, as described above.

[0238] In addition, as an example, if the SMF applies congestion control to at least one terminal and the PDU session, the SMF may send a NAS message including a backoff timer value to the at least one terminal. In addition, each of the at least one terminal may postpone operation based on the mobility management backoff timer.

[0239] In addition, as an example, the SMF may receive a PDU session modification request message from at least one terminal, and send a PDU session modification rejection message including a backoff timer value to at least one terminal based on the applied congestion control. In addition, when notification of a congestion control application related information event is performed based on the applied congestion control, the SMF may send the congestion control application related information to the NEF, and the NEF may send the congestion control application related information to the AF.

[0240] Here, as an example, the congestion control application related information may include at least one of the following information: information indicating that congestion control is applied to at least one terminal, information indicating that a mobility management backoff timer value is provided to at least one terminal, mobility management backoff timer information provided to at least one terminal, information indicating that a rejection message for an SM NAS message is sent to at least one terminal, and congestion control level information, DNN-based congestion control application indication information, or S-NSSAI-based congestion control indication information.

[0241] Since the examples of the above-mentioned proposed methods may also be included in one of the implementation methods of the present disclosure, it is obvious that they may be considered as a proposed method. In addition, the above-mentioned proposed methods may be implemented individually or in combination (or merge) of some of them. A rule may be defined so that information on whether to apply the proposed method (or information on the rule of the proposed method) is notified from the base station to the terminal through a predefined signal (e.g., a physical layer signal or an upper layer signal).

[0242] Without departing from the technical ideas and basic features described in the present disclosure, the present disclosure may be embodied in other specific forms. Therefore, the above detailed description should not be interpreted as being restrictive in all aspects and should be considered as illustrative. The scope of the present disclosure should be determined by a reasonable interpretation of the attached claims, and all changes within the equivalent scope of the present disclosure are included in the scope of the present disclosure. In addition, claims that do not have a clear reference relationship in the claims may be combined to form an embodiment or included as a new claim by modification after submission.

[0243] Industrial Applicability

[0244] Embodiments of the present disclosure are applicable to various radio access systems. Examples of various radio access systems include the 3rd Generation Partnership Project (3GPP) or 3GPP2 system.

[0245] The embodiments of the present disclosure are applicable not only to various radio access systems but also to all technical fields to which various radio access systems are applied. In addition, the proposed method is applicable to millimeter wave and terahertz wave communication systems using ultra-high frequency bands.

[0246] Additionally, embodiments of the present disclosure are applicable to a variety of applications, such as autonomous vehicles, drones, and the like.

Claims

1. A method for operating a network function in a wireless communication system, the method comprising: receiving a subscription request for a congestion control application related information event for at least one terminal; applying congestion control to the at least one terminal; as well as performing notification of said congestion control application related information events based on the applied congestion control, The at least one terminal is a terminal selected based on a federated learning (FL) operation.

2. The method according to claim 1, in, The network function is an access and mobility management function (AMF), and The AMF receives the subscription request for the congestion control application related information event from the network open function NEF, and the NEF sends the subscription request for the congestion control application related information event to the AMF based on the application function AF request.

3. The method according to claim 2, in, based on the AMF applying the congestion control to the at least one terminal, the AMF sending a non-access stratum NAS message including a mobility management back-off timer value to the at least one terminal, and Each of the at least one terminal defers operation based on a mobility management back-off timer.

4. The method according to claim 3, wherein: According to the notification of the congestion control application related information event performed based on the applied congestion control, the AMF sends the congestion control application related information to the NEF, and the NEF sends the congestion control application related information to the AF.

5. The method according to claim 4, wherein: The congestion control application related information includes at least one of the following: information indicating that the congestion control is applied to the at least one terminal, information indicating that the mobility management back-off timer value is provided to the at least one terminal, mobility management back-off timer information provided to the at least one terminal, information indicating that a rejection message for a mobility management MM NAS message is sent to the at least one terminal, or congestion control level information.

6. The method according to claim 5, in, The AF selects the at least one terminal for each learning iteration based on the FL operation, and the AF provides FL model information to the at least one terminal in the learning iteration to obtain training result information from the at least one terminal, and updates the FL model based on the training result information, and Wherein, based on notifying the AF of the congestion control application related information, the FL model is updated in the case of the training result information of the at least one terminal to which congestion control is not applied.

7. The method according to claim 6, wherein: The AF sends a request for newly determining at least one terminal to participate in the learning iteration based on the FL operation.

8. The method according to claim 1, wherein: The subscription request for the congestion control application related information event is received from the artificial intelligence / machine learning AI / ML network function NF based on the application function AF request.

9. The method according to claim 1, in, The network function is a session management function SMF, and The SMF receives the subscription request for the congestion control application related information event from the network open function NEF based on the at least one terminal and the protocol data unit PDU session, and the NEF sends the subscription request for the congestion control application related information event to the SMF based on the AF request.

10. The method according to claim 9, wherein: The PDU session is a PDU session for at least one of an AI / ML service, operation, business or application or a PDU session for the FL operation.

11. The method according to claim 9, in, Based on the SMF applying the congestion control to the at least one terminal and the PDU session, the SMF sends a NAS message including a back-off timer value to the at least one terminal, and Each of the at least one terminal defers operation based on a mobility management back-off timer.

12. The method according to claim 11, wherein: The SMF receives a PDU session modification request message from the at least one terminal, and sends a PDU session modification reject message including the backoff timer value to the at least one terminal based on the applied congestion control.

13. The method according to claim 11, wherein: According to the notification of the congestion control application related information event based on the applied congestion control execution, the SMF sends the congestion control application related information to the NEF, and the NEF sends the congestion control application related information to the AF.

14. The method according to claim 13, wherein: The congestion control application related information includes at least one of the following: information indicating that congestion control is applied to the at least one terminal, information indicating that the mobility management backoff timer value is provided to the at least one terminal, mobility management backoff timer information provided to the at least one terminal, information indicating that a rejection message for a session management SM NAS message is sent to the at least one terminal, congestion control level information, congestion control application indication information based on the data network name DNN, or congestion control indication information based on single network slice selection auxiliary information S-NSSAI.

15. The method according to claim 14, in, The AF selects the at least one terminal for each learning iteration based on the FL operation, and the AF provides FL model information to the at least one terminal in the learning iteration to obtain training result information from the at least one terminal, and updates the FL model based on the training result information, and Wherein, based on notifying the AF of the congestion control application related information, the FL model is updated in the case of the training result information of the at least one terminal to which congestion control is not applied.

16. The method according to claim 15, wherein: The AF sends a request for newly determining at least one terminal to participate in the learning iteration based on the FL operation.

17. A network function operating in a wireless communication system, the network function comprising: at least one transceiver; at least one processor; as well as at least one memory operatively connected to the at least one processor and configured to store instructions that, when executed, cause the at least one processor to perform specific operations, Among them, the specific operation: controlling the at least one transceiver to receive a subscription request for a congestion control application related information event for at least one terminal; applying congestion control to the at least one terminal; and performing notification of congestion control application related information events based on the congestion control applied, The at least one terminal is a terminal selected based on a federated learning (FL) operation.

18. A method for operating a terminal in a wireless communication system, the method comprising: Sending a request message to the network function; receiving a response message including a backoff timer from the network function based on congestion control; as well as deferring the operation based on the backoff timer, wherein the terminal is a terminal selected for FL operation, and The network function applies the congestion control based on a congestion control application related information event, and performs notification of the congestion control application related information event.

19. A terminal operating in a wireless communication system, the terminal comprising: at least one transceiver; at least one processor; as well as at least one memory operatively connected to the at least one processor and configured to store instructions that, when executed, cause the at least one processor to perform specific operations, Among them, the specific operation: Controlling the transceiver to send a request message to a network function; controlling the transceiver to receive a response message including a backoff timer from the network function based on congestion control; and deferring the operation based on the backoff timer, wherein the terminal is a terminal selected for FL operation, and The network function applies the congestion control and performs notification of events related to the application of congestion control.

20. An apparatus comprising at least one memory and at least one processor functionally connected to the at least one memory, wherein: The at least one processor controls the device to: receiving a subscription request for congestion control application related information events of at least one other device; applying congestion control to the at least one other device; and performing notification of congestion control application related information events based on the congestion control applied, The at least one other device is a device selected based on the FL operation.

21. A non-transitory computer-readable medium storing at least one instruction, the non-transitory computer-readable medium comprising the at least one instruction executable by a processor, in, The at least one command control device: receiving a subscription request for congestion control application related information events of at least one other device; applying congestion control to the at least one other device; and performing notification of congestion control application related information events based on the congestion control applied, The at least one other device is a device selected based on the FL operation.

Images