Method for managing external nwdaf id
A new ID management method for client NWDAF optimizes resource allocation across diverse wireless access technologies, addressing cost and efficiency challenges in 3GPP LTE and NR systems, enhancing service availability and system capacity for eMBB, mMTC, and URLLC scenarios.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-09-15
- Publication Date
- 2026-04-02
AI Technical Summary
Existing mobile communication technologies face challenges in achieving reduced costs, improved service availability, flexible frequency band use, and efficient power consumption while supporting diverse deployment scenarios and usage scenarios, including eMBB, mMTC, and URLLC, as required by 3GPP LTE and NR systems.
The implementation of a new ID management method for client NWDAF through NEF assignment, enabling efficient communication protocols and resource allocation across various wireless access technologies, including LTE, NR, and future 5G systems, with support for multiple numerologies and subcarrier spacings to enhance system capacity and coverage.
This approach enhances communication efficiency, reduces costs, and improves service availability by optimizing resource utilization and power consumption, supporting diverse deployment and usage scenarios, including eMBB, mMTC, and URLLC, within 3GPP LTE and NR systems.
Smart Images

Figure KR2025014309_02042026_PF_FP_ABST
Abstract
Description
External NWDAF ID Management Method
[0001] This specification relates to mobile communication.
[0002] 3GPP (3rd generation partnership project) LTE (long-term evolution) is a technology designed to enable high-speed packet communication. Many methods have been proposed to achieve LTE goals, such as reducing costs for users and operators, improving service quality, expanding coverage, and increasing system capacity. As high-level requirements, 3GPP LTE demands reduced cost per bit, improved service availability, flexible use of frequency bands, a simple structure, open interfaces, and appropriate power consumption of terminals.
[0003] Work has begun at the ITU (International Telecommunication Union) and 3GPP to develop requirements and specifications for new radio (NR) systems. 3GPP must identify and develop the technical components necessary to successfully standardize NR in a timely manner, satisfying both urgent market demands and the longer-term requirements presented by the ITU-R (ITU Radio Communication Sector) IMT (International Mobile Telecommunications)-2020 process. Furthermore, NR must be able to utilize any spectrum band up to at least 100 GHz so that it can be used for wireless communication even in the distant future.
[0004] NR targets a single technical framework that covers all deployment scenarios, usage scenarios, and requirements, including eMBB (enhanced mobile broadband), mMTC (massive machine type communications), and URLLC (ultra-reliable and low latency communications). NR must inherently be forward compatible.
[0005] NEF assigns a new ID to client NWDAF and sends it to server AF.
[0006] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.
[0007] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.
[0008] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.
[0009] Figure 4 is a structural diagram of a next-generation mobile communication network.
[0010] FIG. 5 shows an example of a 5G system structure to which the implementation of the present specification is applied.
[0011] FIGS. 6, FIGS. 7, and FIGS. 8 illustrate examples of procedures according to the disclosure of the present specification.
[0012] FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12 illustrate examples of procedures according to the disclosure of the present specification.
[0013] FIG. 13 illustrates the procedure of the NEF according to the disclosure of the present specification.
[0014] FIG. 14 illustrates the procedure of a VFL server AF according to the disclosure of the present specification.
[0015] The following techniques, devices, and systems may be applied to various wireless multiple access systems. 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, single carrier frequency division multiple access (SC-FDMA) systems, and multicarrier frequency division multiple access (MC-FDMA) systems. CDMA may be implemented through wireless technologies such as universal terrestrial radio access (UTRA) or CDMA2000. TDMA may be implemented through wireless technologies such as global system for mobile communications (GSM), general packet radio service (GPRS), or enhanced data rates for GSM evolution (EDGE). OFDMA can be implemented through wireless technologies such as IEEE (Institute of Electrical and Electronics Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or E-UTRA (evolved UTRA). UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long-term evolution) is part of E-UMTS (evolved UMTS) using E-UTRA.3GPP LTE uses OFDMA in the downlink (DL) and SC-FDMA in the uplink (UL). Evolutions of 3GPP LTE include LTE-A (advanced), LTE-A Pro, and / or 5G NR (new radio).
[0016] For convenience of explanation, the implementation of this specification is described primarily in relation to 3GPP-based wireless communication systems. However, the technical characteristics of this specification are not limited thereto. For example, the following detailed description is provided based on a mobile communication system corresponding to a 3GPP-based wireless communication system, but aspects of this specification that are not limited to 3GPP-based wireless communication systems may be applied to other mobile communication systems.
[0017] For terms and technologies used in this specification that are not specifically described, reference may be made to wireless communication standard documents published prior to this specification.
[0018] In this specification, "A or B" may mean "only A," "only B," or "both A and B." Alternatively, in this specification, "A or B" may be interpreted as "A and / or B." For example, in this specification, "A, B or C" may mean "only A," "only B," "only C," or "any combination of A, B and C."
[0019] A slash ( / ) or a comma used in this specification may mean "and / or." For example, "A / B" may mean "A and / or B." Accordingly, "A / B" may mean "only A," "only B," or "both A and B." For example, "A, B, C" may mean "A, B or C."
[0020] In this specification, "at least one of A and B" may mean "only A," "only B," or "both A and B." Additionally, in this specification, the expressions "at least one of A or B" or "at least one of A and / or B" may be interpreted as synonymous with "at least one of A and B."
[0021] Additionally, in this specification, "at least one of A, B and C" may mean "only A," "only B," "only C," or "any combination of A, B and C." Furthermore, "at least one of A, B or C" or "at least one of A, B and / or C" may mean "at least one of A, B and C."
[0022] Additionally, parentheses used in this specification may mean "for example." Specifically, when indicated as "control information (PDCCH)," "PDCCH" may be proposed as an example of "control information." In other words, "control information" in this specification is not limited to "PDCCH," and "PDCCH" may be proposed as an example of "control information." Furthermore, even when indicated as "control information (i.e., PDCCH)," "PDCCH" may be proposed as an example of "control information."
[0023] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.
[0024] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification may be applied to various fields where wireless communication and / or connectivity between devices (e.g., 5G) is required.
[0025] The present specification will be described in more detail below with reference to the drawings. In the following drawings and / or description, the same reference numerals may refer to the same or corresponding hardware blocks, software blocks, and / or function blocks unless otherwise indicated.
[0026] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.
[0027] The 5G usage scenario shown in FIG. 1 is merely an example, and the technical features of this specification may be applied to other 5G usage scenarios not shown in FIG. 1.
[0028] The three main requirements categories for 5G are (1) enhanced mobile broadband (eMBB) category, (2) massive machine type communication (mMTC) category, and (3) ultra-reliable and low latency communications (URLLC) category.
[0029] Referring to FIG. 1, the communication system (1) includes wireless devices (100a to 100f), a base station (BS; 200), and a network (300). FIG. 1 illustrates a 5G network as an example of the network of the communication system (1), but the implementation of the present specification is not limited to a 5G system and may be applied to future communication systems beyond a 5G system.
[0030] The base station (200) and the network (300) can be implemented as wireless devices, and a specific wireless device can operate as a base station / network node in relation to another wireless device.
[0031] Wireless devices (100a to 100f) represent devices that perform communication using radio access technology (RAT) (e.g., 5G NR or LTE) and may also be referred to as communication / wireless / 5G devices. Wireless devices (100a to 100f) may include, but are not limited to, robots (100a), vehicles (100b-1 and 100b-2), extended reality (XR) devices (100c), portable devices (100d), home appliances (100e), IoT devices (100f), and artificial intelligence (AI) devices / servers (400). For example, vehicles may include vehicles with wireless communication capabilities, autonomous vehicles, and vehicles capable of performing communication between vehicles. Vehicles may include unmanned aerial vehicles (UAVs) (e.g., drones). XR devices may include AR / VR / mixed reality (MR) devices and may be implemented in the form of head-mounted devices (HMDs) and head-up displays (HUDs) mounted on vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signs, vehicles, robots, etc. Portable devices may include smartphones, smart pads, wearable devices (e.g., smartwatches or smart glasses), and computers (e.g., laptops). Home appliances may include TVs, refrigerators, and washing machines. IoT devices may include sensors and smart meters.
[0032] In this specification, wireless devices (100a to 100f) may be referred to as user equipment (UE). The UE may include, for example, a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a PDA (personal digital assistant), a PMP (portable multimedia player), a navigation system, a slate PC, a tablet PC, an ultrabook, a vehicle, a vehicle with autonomous driving capabilities, a connected car, a UAV, an AI module, a robot, an AR device, a VR device, an MR device, a hologram device, a public safety device, an MTC device, an IoT device, a medical device, a fintech device (or financial device), a security device, a weather / environment device, a 5G service-related device, or a device related to the Fourth Industrial Revolution.
[0033] For example, a UAV can be an aircraft that is not on board and is navigated by radio control signals.
[0034] For example, a VR device may include a device for implementing objects or backgrounds in a virtual environment. For example, an AR device may include a device that implements objects or backgrounds in a virtual world by connecting them to objects or backgrounds in a real world. For example, an MR device may include a device that implements objects or backgrounds in a virtual world by merging them with objects or backgrounds in a real world. For example, a holographic device may include a device for implementing a 360-degree stereoscopic image by recording and playing back stereoscopic information using the phenomenon of light interference that occurs when two laser lights called holograms meet.
[0035] For example, a public safety device may include an image relay device or an image device that can be worn on a user's body.
[0036] For example, MTC devices and IoT devices may be devices that do not require direct human intervention or operation. For instance, MTC devices and IoT devices may include smart meters, vending machines, thermometers, smart light bulbs, door locks, or various sensors.
[0037] For example, a medical device may be a device used for the purpose of diagnosing, treating, alleviating, curing, or preventing a disease. For example, a medical device may be a device used to diagnose, treat, alleviate, or correct an injury or damage. For example, a medical device may be a device used for the purpose of examining, replacing, or modifying a structure or function. For example, a medical device may be a device used for the purpose of regulating pregnancy. For example, a medical device may include a therapeutic device, a driving device, a (in vitro) diagnostic device, a hearing aid, or a surgical device.
[0038] For example, a security device may be a device installed to prevent potential risks and maintain safety. For example, a security device may be a camera, closed-circuit TV (CCTV), a recorder, or a black box.
[0039] For example, a fintech device may be a device capable of providing financial services such as mobile payments. For example, a fintech device may include a payment device or a POS system.
[0040] For example, a weather / environment device may include a device for monitoring or predicting the weather / environment.
[0041] Wireless devices (100a to 100f) can be connected to a network (300) through a base station (200). AI technology may be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) through the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, and a network after 5G. The wireless devices (100a to 100f) may communicate with each other through the base station (200) / network (300), but they may also communicate directly (e.g., sidelink communication) without going through the base station (200) / network (300). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle-to-vehicle) / V2X (vehicle-to-everything) communication). Also, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).
[0042] Wireless communication / connections (150a, 150b, 150c) can be established between wireless devices (100a to 100f) and / or between wireless devices (100a to 100f) and base station (200) and / or between base station (200). Here, the wireless communication / connections can be established through various RATs (e.g., 5G NR), such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D (device-to-device) communication), and communication between base stations (150c) (e.g., relay, IAB (integrated access and backhaul)). Through the wireless communication / connections (150a, 150b, 150c), wireless devices (100a to 100f) and base station (200) can transmit / receive wireless signals to / from each other. For example, wireless communication / connection (150a, 150b, 150c) may transmit / receive signals through various physical channels. To this end, based on various proposals in this specification, at least some of the following may be performed: a process for setting various configuration information for transmitting / receiving wireless signals, a process for various signal processing (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and a resource allocation process.
[0043] AI refers to the field of researching artificial intelligence or the methodologies to create it, while machine learning refers to the field of researching methodologies to define and solve various problems within the realm of artificial intelligence. Machine learning is also defined as an algorithm that improves performance on a task through continuous experience.
[0044] A robot can refer to a machine that automatically processes or operates given tasks based on its own capabilities. In particular, a robot equipped with the ability to perceive its environment, make independent judgments, and perform actions can be called an intelligent robot. Robots can be classified into industrial, medical, domestic, and military types depending on their purpose or field of use. Robots are equipped with drive units, including actuators or motors, to perform various physical movements, such as moving robot joints. Additionally, mobile robots include wheels, brakes, propellers, etc., in their drive units, enabling them to drive on the ground or fly in the air.
[0045] Autonomous driving refers to technology that drives itself, and an autonomous vehicle refers to a vehicle that drives without user intervention or with minimal user intervention. For example, autonomous driving can include technologies such as maintaining the driving lane, automatically adjusting speed like adaptive cruise control, driving automatically along a predetermined route, and automatically setting a route and driving once a destination is set. The term "vehicle" encompasses vehicles equipped solely with internal combustion engines, hybrid vehicles equipped with both internal combustion engines and electric motors, and electric vehicles equipped solely with electric motors; it can include not only automobiles but also trains and motorcycles. An autonomous vehicle can be viewed as a robot equipped with autonomous driving capabilities.
[0046] Augmented Reality is a collective term for VR, AR, and MR. VR technology provides real-world objects or backgrounds solely as CG images, AR technology provides virtual CG images superimposed on images of real objects, and MR technology is a CG technology that mixes and combines virtual objects with the real world. MR technology is similar to AR technology in that it displays real-world and virtual objects together. However, there is a difference in that while virtual objects in AR technology are used to complement real-world objects, virtual and real objects in MR technology are used as equal entities.
[0047] NR supports multiple numerologies or subcarrier spacings (SCS) to support various 5G services. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban areas, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.
[0048] The NR frequency band can be defined by two types of frequency ranges (FR1, FR2). The numerical values of the frequency ranges may change. For example, the two types of frequency ranges (FR1, FR2) may be as shown in Table 1 below. For convenience of explanation, among the frequency ranges used in the NR system, FR1 may mean "sub 6GHz range" and FR2 may mean "above 6GHz range" and may be referred to as millimeter wave (mmW).
[0049] Frequency Range Definition Frequency Range Subcarrier Spacing FR1 450 MHz - 6000 MHz 15, 30, 60 kHz FR2 24 250 MHz - 52600 MHz 60, 120, 240 kHz
[0050] As described above, the numerical value of the frequency range of the NR system may change. For example, FR1 may include a band of 410 MHz to 7125 MHz as shown in Table 2 below. That is, FR1 may include a frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher. For example, the frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher included within FR1 may include an unlicensed band. The unlicensed band may be used for various purposes, for example, for communication for vehicles (e.g., autonomous driving).
[0051] Frequency Range Definition Frequency Range Subcarrier Spacing FR1 4 10 MHz - 7 125 MHz 15, 30, 60 kHz FR2 24 250 MHz - 5 2600 MHz 60, 120, 240 kHz
[0052] Here, the wireless communication technology implemented in the wireless device of this specification may include LTE, NR, and 6G, as well as narrowband IoT (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of low-power wide-area network (LPWAN) technology and may be implemented according to standards such as LTE Cat NB1 and / or LTE Cat NB2, but is not limited to the names mentioned above. Additionally, or generally, the wireless communication technology implemented in the wireless device of this specification may perform communication based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology and may be referred to by various names such as enhanced MTC (eMTC). For example, LTE-M technology may be implemented in at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-bandwidth limited), 5) LTE-MTC, 6) LTE MTC, and / or 7) LTE M, and is not limited to the names mentioned above. Additionally or generally, wireless communication technology implemented in the wireless device of this specification may include at least one of ZigBee, Bluetooth, and / or LPWAN for low-power communication, and is not limited to the names mentioned above. For example, ZigBee technology may create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and may be referred to by various names.
[0053] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.
[0054] In FIG. 2, the first wireless device (100) and / or the second wireless device (200) may be implemented in various forms depending on the use example / service. For example, {the first wireless device (100) and the second wireless device (200)} may correspond to at least one of {wireless devices (100a–100f) and base station (200)}, {wireless devices (100a–100f) and wireless devices (100a–100f)} and / or {base station (200) and base station (200)} of FIG. 1. The first wireless device (100) and / or the second wireless device (200) may be composed of various components, devices / parts and / or modules.
[0055] The first wireless device (100) may include at least one transceiver such as a transceiver (106), at least one processing chip such as a processing chip (101), and / or one or more antennas (108).
[0056] The processing chip (101) may include at least one processor, such as a processor (102), and at least one memory, such as a memory (104). Additionally and / or generally, the memory (104) may be placed outside the processing chip (101).
[0057] The processor (102) can control the memory (104) and / or the transceiver (106) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. For example, the processor (102) may process information within the memory (104) to generate a first information / signal and transmit a wireless signal containing the first information / signal through the transceiver (106). The processor (102) may receive a wireless signal containing a second information / signal through the transceiver (106) and process the second information / signal to store the obtained information in the memory (104).
[0058] Memory (104) may be connected to the processor (102) so as to be operable. Memory (104) may store various types of information and / or instructions. Memory (104) may store firmware and / or software code (105) that implements code, instructions, and / or a set of instructions that perform the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (102). For example, firmware and / or software code (105) may implement instructions that perform the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (102). For example, firmware and / or software code (105) may control the processor (102) to perform one or more protocols. For example, firmware and / or software code (105) may control the processor (102) to perform one or more wireless interface protocol layers.
[0059] Here, the processor (102) and memory (104) may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). A transceiver (106) may be connected to the processor (102) and may transmit and / or receive a wireless signal through one or more antennas (108). Each transceiver (106) may include a transmitter and / or receiver. The transceiver (106) may be interchangeably used with an RF (radio frequency) unit. In this specification, the first wireless device (100) may represent a communication modem / circuit / chip.
[0060] The second wireless device (200) may include at least one transceiver such as a transceiver (206), at least one processing chip such as a processing chip (201), and / or one or more antennas (208).
[0061] The processing chip (201) may include at least one processor, such as a processor (202), and at least one memory, such as a memory (204). Additionally and / or alternatively, the memory (204) may be placed outside the processing chip (201).
[0062] The processor (202) can control the memory (204) and / or the transceiver (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. For example, the processor (202) may process information within the memory (204) to generate a third information / signal and transmit a wireless signal containing the third information / signal through the transceiver (206). The processor (202) may receive a wireless signal containing a fourth information / signal through the transceiver (206) and process the fourth information / signal to store the obtained information in the memory (204).
[0063] Memory (204) may be connected to the processor (202) so as to be operable. Memory (204) may store various types of information and / or instructions. Memory (204) may store firmware and / or software code (205) that implements instruction code, instructions, and / or sets of instructions that perform descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (202). For example, firmware and / or software code (205) may implement instructions that perform descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (202). For example, firmware and / or software code (205) may control the processor (202) to perform one or more protocols. For example, firmware and / or software code (205) may control the processor (202) to perform one or more wireless interface protocol layers.
[0064] Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). A transceiver (206) may be connected to the processor (202) and transmit and / or receive a wireless signal through one or more antennas (208). Each transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeably used with an RF unit. In this specification, the second wireless device (200) may represent a communication modem / circuit / chip.
[0065] Hereinafter, hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as a PHY (physical) layer, a MAC (media access control) layer, a RLC (radio link control) layer, a PDCP (packet data convergence protocol) layer, a RRC (radio resource control) layer, and an SDAP (service data adaptation protocol) layer). One or more processors (102, 202) may generate one or more PDUs (protocol data units), one or more SDUs (service data units), messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification. One or more processors (102, 202) may generate a signal (e.g., baseband signal) including a PDU, SDU, message, control information, data, or information according to the description, function, procedure, proposal, method, and / or operation flowchart disclosed in this specification and provide it to one or more transceivers (106, 206). One or more processors (102, 202) may receive a signal (e.g., baseband signal) from one or more transceivers (106, 206) and may obtain a PDU, SDU, message, control information, data, or information according to the description, function, procedure, proposal, method, and / or operation flowchart disclosed in this specification.
[0066] One or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, and / or a microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, and / or a combination thereof. For example, one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), and / or one or more field programmable gate arrays (FPGAs) may be included in one or more processors (102, 202). For example, one or more processors (102, 202) may be composed of a set of communication control processors, application processors (APs), electronic control units (ECUs), central processing units (CPUs), graphic processing units (GPUs), and memory control processors.
[0067] One or more memories (104, 204) may be connected to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. One or more memories (104, 204) may consist of random access memory (RAM), dynamic RAM (DRAM), read-only memory (ROM), erasable programmable ROM (EPROM), flash memory, volatile memory, non-volatile memory, hard drives, registers, cache memory, computer read storage media, and / or combinations thereof. One or more memories (104, 204) may be located inside and / or outside of one or more processors (102, 202). Additionally, one or more memories (104, 204) may be connected to one or more processors (102, 202) through various technologies such as wired or wireless connections.
[0068] One or more transceivers (106, 206) may transmit user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification to one or more other devices. One or more transceivers (106, 206) may receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification from one or more other devices. For example, one or more transceivers (106, 206) may be connected to one or more processors (102, 202) and may transmit and receive wireless signals. For example, one or more processors (102, 202) may control one or more transceivers (106, 206) to transmit user data, control information, wireless signals, etc., to one or more other devices. Additionally, one or more processors (102, 202) can control one or more transceivers (106, 206) to receive user data, control information, wireless signals, etc. from one or more other devices.
[0069] One or more transceivers (106, 206) may be connected to one or more antennas (108, 208). Additionally and / or generally, one or more transceivers (106, 206) may include one or more antennas (108, 208). One or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein through one or more antennas (108, 208). In this specification, one or more antennas (108, 208) may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports).
[0070] One or more transceivers (106, 206) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process received user data, control information, wireless signals / channels, etc. using one or more processors (102, 202). One or more transceivers (106, 206) can convert processed user data, control information, wireless signals / channels, etc. from baseband signals to RF band signals using one or more processors (102, 202). To this end, one or more transceivers (106, 206) may include (analog) oscillators and / or filters. For example, one or more transceivers (106, 206) can up-convert an OFDM baseband signal into an OFDM signal through an (analog) oscillator and / or filter under the control of one or more processors (102, 202) and transmit the up-converted OFDM signal at a carrier frequency. One or more transceivers (106, 206) can receive an OFDM signal at a carrier frequency and down-convert the OFDM signal into an OFDM baseband signal through an (analog) oscillator and / or filter under the control of one or more processors (102, 202).
[0071] Although not illustrated in FIG. 2, the wireless device (100, 200) may include additional components. The additional components (140) may be configured in various ways depending on the type of the wireless device (100, 200). For example, the additional components (140) may include at least one of a power unit / battery, an input / output (I / O) device (e.g., audio I / O port, video I / O port), a driving unit, and a computing unit. The additional components (140) may be connected to one or more processors (102, 202) through various technologies, such as wired or wireless connections.
[0072] In an implementation of this specification, the UE may operate as a transmitting device in the uplink (UL; uplink) and as a receiving device in the downlink (DL; downlink). In an implementation of this specification, the base station may operate as a receiving device in the UL and as a transmitting device in the DL. For technical convenience, it is generally assumed that the first wireless device (100) operates as a UE and the second wireless device (200) operates as a base station. For example, a processor (102) connected to, mounted on, or released to the first wireless device (100) may be configured to perform UE operations according to an implementation of this specification or to control a transceiver (106) to perform UE operations according to an implementation of this specification. A processor (202) connected to, mounted on, or released to the second wireless device (200) may be configured to perform base station operations according to an implementation of this specification or to control a transceiver (206) to perform base station operations according to an implementation of this specification.
[0073] In this specification, the base station may be referred to as Node B, eNode B, or gNB.
[0074] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.
[0075] Referring to FIG. 3, the UE (100) can correspond to the first wireless device (100) of FIG. 2.
[0076] The UE (100) includes a processor (102), memory (104), transceiver (106), one or more antennas (108), a power management module (141), a battery (142), a display (143), a keypad (144), a SIM (Subscriber Identification Module) card (145), a speaker (146), and a microphone (147).
[0077] The processor (102) may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. The processor (102) may be configured to control one or more other components of the UE (100) to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. Layers of a wireless interface protocol may be implemented in the processor (102). The processor (102) may include an ASIC, other chipsets, logic circuits, and / or data processing devices. The processor (102) may be an application processor. The processor (102) may include at least one of a DSP, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a modem (modulator and demodulator). An example of the processor (102) is the SNAPDRAGON manufactured by Qualcomm®. TM Series processor, EXYNOS made by Samsung® TM Series processors, A Series processors made by Apple®, HELIO made by MediaTek® TM Series processors, ATOM made by Intel® TM It can be found in series processors or corresponding next-generation processors.
[0078] Memory (104) is coupled to the processor (102) so as to be operable and stores various information for operating the processor (102). Memory (104) may include ROM, RAM, flash memory, memory card, storage medium and / or other storage device. When the implementation is implemented in software, the technology described herein may be implemented using modules (e.g., procedures, functions, etc.) that perform the descriptions, functions, procedures, proposals, methods and / or operation flowcharts disclosed herein. Modules may be stored in memory (104) and executed by the processor (102). Memory (104) may be implemented within the processor (102) or outside the processor (102), in which case it may be communicatively coupled to the processor (102) through various methods known in the technology.
[0079] A transceiver (106) is coupled to operate with a processor (102) and transmits and / or receives a wireless signal. The transceiver (106) includes a transmitter and a receiver. The transceiver (106) may include a baseband circuit for processing a wireless frequency signal. The transceiver (106) controls one or more antennas (108) to transmit and / or receive a wireless signal.
[0080] The power management module (141) manages the power of the processor (102) and / or the transceiver (106). The battery (142) supplies power to the power management module (141).
[0081] The display (143) outputs the result processed by the processor (102). The keypad (144) receives input to be used by the processor (102). The keypad (144) can be displayed on the display (143).
[0082] A SIM card (145) is an integrated circuit for securely storing an International Mobile Subscriber Identity (IMSI) and associated keys, and is used to identify and authenticate a subscriber in a mobile device such as a mobile phone or computer. Additionally, contact information can be stored on many SIM cards.
[0083] The speaker (146) outputs sound-related results processed by the processor (102). The microphone (147) receives sound-related input to be used by the processor (102).
[0084] Figure 4 is a structural diagram of a next-generation mobile communication network.
[0085] 5GC (5G Core) may include various components, and FIG. 5 includes some of them, such as AMF (Access and Mobility Management Function) (410), SMF (Session Management Function) (420), PCF (Policy Control Function) (430), UPF (User Plane Function) (440), AF (Application Function) (450), UDM (Unified Data Management) (460), and N3IWF (Non-3GPP (3rd Generation Partnership Project) Inter Working Function) (490).
[0086] The UE (100) is connected to the data network via the UPF (440) through the NG-RAN (Next Generation Radio Access Network) including the gNB (20).
[0087] The UE (100) can also receive data services through untrusted non-3GPP access, such as a WLAN (Wireless Local Area Network). To connect the non-3GPP access to the core network, an N3IWF (490) may be deployed.
[0088] The illustrated N3IWF (490) performs the function of managing interworking between non-3GPP access and 5G systems. When the UE (100) is connected to non-3GPP access (e.g., WiFi referred to as IEEE 801.11), the UE (100) can be connected to the 5G system through the N3IWF (490). The N3IWF (490) performs control signing with the AMF (410) and connects to the UPF (440) via the N3 interface for data transmission.
[0089] The illustrated AMF (410) can manage access and mobility in a 5G system. The AMF (410) can perform the function of managing Non-Access Stratum (NAS) security. The AMF (410) can perform the function of handling mobility in an idle state.
[0090] The illustrated UPF (440) is a type of gateway through which user data is transmitted and received. The UPF node (440) can perform all or part of the user plane functions of the S-GW (Serving Gateway) and P-GW (Packet Data Network Gateway) of 4th generation mobile communication.
[0091] The UPF (440) acts as a boundary point between the next generation radio access network (NG-RAN) and the core network, and is an element that maintains the data path between the gNB (20) and the SMF (420). Additionally, when the UE (100) moves across the area served by the gNB (20), the UPF (440) acts as a mobility anchor point. The UPF (440) can perform the function of handling PDUs. For mobility within the NG-RAN (Next Generation Radio Access Network defined in 3GPP Release-15 or later), packets can be routed through the UPF. Additionally, the UPF (440) may also function as an anchor point for mobility with other 3GPP networks (RANs defined prior to 3GPP Release-15, e.g., UTRAN, E-UTRAN (Evolved-UMTS (Universal Mobile Telecommunications System) Terrestrial Radio Access Network)) or GERAN (GSM (Global System for Mobile Communication) / EDGE (Enhanced Data rates for Global Evolution) Radio Access Network). The UPF (440) may correspond to a termination point of a data interface toward a data network.
[0092] The illustrated PCF (430) is a node that controls the operator's policy.
[0093] The illustrated AF (450) is a server for providing various services to the UE (100).
[0094] The illustrated UDM (460) is a type of server that manages subscriber information, such as the HSS (Home subscriber Server) of 4th generation mobile communication. The UDM (460) stores and manages the subscriber information in a Unified Data Repository (UDR).
[0095] The illustrated SMF (420) can perform the function of assigning the IP (Internet Protocol) address of the UE. Also, the SMF (420) can control the PDU (protocol data unit) session.
[0096] For reference, the reference numerals for AMF (410), SMF (420), PCF (430), UPF (440), AF (450), UDM (460), N3IWF (490), gNB (20), or UE (100) may be omitted below.
[0097] Fifth-generation mobile communication supports multiple numerologies or subcarrier spacings (SCS) to support various 5G services. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban environments, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.
[0098] FIG. 5 shows an example of a 5G system structure to which the implementation of the present specification is applied.
[0099] The 5G system (5GS) structure consists of the following network functions (NF).
[0100] - AUSF (Authentication Server Function)
[0101] - AMF (Access and Mobility Management Function)
[0102] - DN (Data Network), 예를 들어 운영자 서비스, 인터넷 접속 또는 타사 서비스
[0103] - USDF (Unstructured Data Storage Function)
[0104] - NEF (Network Exposure Function)
[0105] - I-NEF (Intermediate NEF)
[0106] - NRF (Network Repository Function)
[0107] - NSSF (Network Slice Selection Function)
[0108] - PCF (Policy Control Function)
[0109] - SMF (Session Management Function)
[0110] - UDM (Unified Data Management)
[0111] - UDR (Unified Data Repository)
[0112] - UPF (User Plane Function)
[0113] - UCMF (UE radio Capability Management Function)
[0114] - AF (Application Function)
[0115] - UE (User Equipment)
[0116] - (R)AN ((Radio) Access Network)
[0117] - 5G-EIR (5G-Equipment Identity Register)
[0118] - NWDAF (Network Data Analytics Function)
[0119] - CHF (CHarging Function)
[0120] In addition, the following network functions may be considered.
[0121] - N3IWF (Non-3GPP InterWorking Function)
[0122] - TNGF (Trusted Non-3GPP Gateway Function)
[0123] - W-AGF (Wireline Access Gateway Function)
[0124] Figure 5 shows the 5G system structure in a non-roaming case using a reference point representation showing how various network functions interact with each other.
[0125] In Fig. 5, for clarity of the point-to-point diagram, UDSF, NEF, and NRF are not described. However, all network functions shown can interact with UDSF, UDR, NEF, and NRF as needed.
[0126] For clarity, the connection between UDR and other NFs (e.g., PCF) is not shown in FIG. 4. For clarity, the connection between NWDAF and other NFs (e.g., PCF) is not shown in FIG. 4.
[0127] The 5G system structure includes the following reference points.
[0128] - N1: Reference point between UE and AMF.
[0129] - N2: Reference point between (R)AN and AMF.
[0130] - N3: Reference point between (R)AN and UPF.
[0131] - N4: Reference point between SMF and UPF.
[0132] - N6: Reference point between the UPF and the data network.
[0133] - N9: Reference point between two UPFs.
[0134] The following reference points show the interactions that exist between the NF services of NF.
[0135] - N5: Reference point between PCF and AF.
[0136] - N7: Reference point between SMF and PCF.
[0137] - N8: Reference point between UDM and AMF.
[0138] - N10: Reference point between UDM and SMF.
[0139] - N11: Reference point between AMF and SMF.
[0140] - N12: Reference point between AMF and AUSF.
[0141] - N13: Reference point between UDM and AUSF.
[0142] - N14: Reference point between two AMFs.
[0143] - N15: Reference point between PCF and AMF for non-roaming scenarios, reference point between PCF and AMF of the visited network for roaming scenarios.
[0144] - N16: Reference point between two SMFs (in the case of roaming, between the SMF of the visited network and the SMF of the home network)
[0145] - N22: Reference point between AMF and NSSF.
[0146] In some cases, two NFs may need to be connected to each other to service the UE.
[0147] <VFL (Vertical Federated Learning)>
[0148] In the VFL scenario, NWDAF or AF can act as the server.
[0149] In the case of untrusted AFs, interaction between NWDAFs and AFs can occur through the Network Exposure Function (NEF).
[0150] When an AF acts as a server, multiple NWDAFs can be clients.
[0151] If the NEF directly exposes the NWDAF instance ID to the VFL, information about the network function (NF) is exposed to untrusted AFs. This may result in a security risk. Therefore, to hide the NWDAF instance ID, the NEF can convert it into a temporary NWDAF ID and provide it to the AF.
[0152] The VFL server can assign a VFL Correlation ID to a VFL process. The assigned VFL Correlation ID can be used to associate participants (e.g., VFL Server, VFL Client(s)) of VFL training and a subsequent VFL Inference process. This can be linked to distributed ML models in VFL's joint model training process.
[0153] In this specification, a VFL Correlation ID may be information associated with a specific VFL process. For example, a specific VFL Correlation ID may identify a VFL process. For example, one or more client NWDAFs participating in a specific VFL process may receive a single VFL Correlation ID representing said specific VFL process.
[0154] An Untrusted AF acts as a server, and VFL training / inference can be performed via the NEF. In this case, the NEF can assign a Temporary NWDAF ID to the client NWDAFs and notify them. VFL training / inference can be performed using the assigned Temporary NWDAF ID.
[0155] Additionally, when performing VFL with the corresponding client NWDAFs, the Untrusted AF can be assigned a VFL Correlation ID. The assigned VFL Correlation ID can subsequently form associations with the client NWDAFs trained together during the inference process. Each client NWDAF can also perform inference using the ML Model associated with the VFL Correlation ID.
[0156] However, if the NEF assigns a temporary NWDAF ID, since the temporary NWDAF ID is a temporary ID, it may have an expiration date or the information may be deleted at a specific point in time, taking into account memory capacity and security risks.
[0157] After VFL training is finished, the VFL server may need to retrain or inference the associated VFL servers and VFL clients (and each model used) with the corresponding VFL association ID.
[0158] A VFL server (e.g., untrusted AF) can store VFL association IDs and temporary NWDAF IDs of VFL clients (e.g., NWDAFs). When inference is performed, the VFL server can use these temporary NWDAF IDs to inference with the corresponding client NWDAFs. However, the VFL server (e.g., AF) cannot know whether the temporary NWDAF IDs are still being stored (or are valid) on the network. Furthermore, when performing retraining or inference later, these temporary NWDAF IDs may no longer be valid.
[0159] When performing retraining or inference later, it is necessary to map the VFL processes corresponding to the VFL association IDs to the client NWDAFs used in the actual training, and it may be necessary to reassign temporary NWDAF IDs to those clients. Therefore, a method to handle this is required.
[0160] In a Vertical Federated Learning (VFL) scenario where an untrusted AF acts as a server and NWDAFs act as clients, methods for managing temporary NWDAF IDs assigned by an NEF to an untrusted AF and for reassigning temporary NWDAF IDs may be proposed in this specification.
[0161] The temporary NWDAF ID management method for VFL proposed in this specification may be composed of a combination of one or more operations / configurations / steps proposed in this specification.
[0162] The procedures and / or messages described in this specification may use conventional procedures / messages, extend conventional procedures / messages, or define and use new procedures / messages.
[0163] In this specification, AF may be an untrusted AF.
[0164] This specification focuses on the proposed content.
[0165] The VFL Correlation ID in this specification may refer to a VFL Model Correlation ID, a VFL Session ID, etc.
[0166] The method proposed in this specification can be applied to a scenario (e.g., a scenario in which an untrusted AF operates as a VFL Server and performs VFL training and inference with NWDAFs operating as VFL Clients through an NEF).
[0167] In this specification, Temporary NWDAF ID may refer to External NWDAF ID.
[0168] In this specification, the terms VFL process, VFL operation, VFL task, etc. are used interchangeably.
[0169] In this specification, a VFL process may include one or more operations of VFL training and VFL inference. However, a VFL process is not limited thereto and may include various operations related to VFL (e.g., aggregation of results from other VFL clients by a VFL Client).
[0170] An AF, which is a VFL server, can assign a VFL association ID in relation to VFL processes with VFL clients. If the VFL association ID includes information about the Application ID, the network can uniquely identify the VFL process (e.g., distinguish it from other VFL processes) using only the VFL association ID. Otherwise, since duplicate VFL association IDs may be assigned per AF, in this case, the network can uniquely identify the VFL process by considering both the VFL association ID and the Application ID together.
[0171] The VFL associated ID (+ Application ID) can be stored per Analytics ID or together with the Analytics ID.
[0172] Considering security risks, the NEF can assign and transmit temporary (external) NWDAF IDs to client NWDAFs. The AF can perform VFL training / inference using the temporary (external) NWDAF ID instead of the actual NWDAF ID. The NEF can map the temporary (external) NWDAF ID to the actual NWDAF ID to facilitate the transfer of training (and / or inference) results between the actual NWDAF and the AF. During the training (and / or inference) process, the NEF may retain information regarding the temporary (external) NWDAF ID and / or mapping (mapping between the temporary (external) NWDAF ID and the actual NWDAF ID) assigned to each client NWDAF during the training (and / or inference) process without deleting it.
[0173] An untrusted AF, acting as a VFL server, can associate itself with clients currently performing VFL by assigning a VFL association ID to the VFL. Each server and client can also associate the ML models used in the VFL with each other through the VFL association ID. After VFL training, each client and ML model can be used through the corresponding VFL association ID during re-training (and / or inference).
[0174] In this specification, the NEF may assign a new Temporary (External) NWDAF ID as needed. Through the Temporary (External) NWDAF ID and the VFL association ID, the relationships between clients and servers regarding the VFL process can be maintained while hiding information within the network.
[0175] A management method for Temporary (External) NWDAF IDs can be proposed so that the network can delete related information for VFL-associated IDs that are no longer in use. To this end, the methods of the first to fourth embodiments can be proposed.
[0176] In the case of the first and second embodiments, when the training / inference process is performed, the NEF may assign a new temporary (external) NWDAF ID.
[0177] 1. First embodiment
[0178] According to the first embodiment, clients (e.g., multiple client NWDAFs) can register a VFL correlation ID in the NF profile of the NRF.
[0179] Each of the clients (e.g., multiple client NWDAFs) can update the NRF's NF profile by sending an update message containing the VFL association ID (and / or application ID) to the NRF during training (or before / after training). Based on this, the NRF can store the corresponding VFL association ID (and / or application ID) in the NF profile.
[0180] The VFL associated ID (and / or application ID) can be stored together with the Analytics ID or per Analytics ID.
[0181] In this case, when training is finished, the NEF may not need to store the VFL association ID and mapping information (mapping information between the Temporary (External) NWDAF ID and the actual NWDAF ID).
[0182] If retraining (and / or inference) is required by the VFL server AF thereafter, the VFL server AF may send a discovery request to the NEF for the clients that participated in the previous VFL process (e.g., multiple client NWDAFs). The discovery request may include VFL association IDs (+application IDs), analytics IDs, and / or VFL-related information related to the previous VFL process.
[0183] Based on this, the NEF can transmit the request details (e.g., VFL association ID (+application ID), analytics ID, VFL related information) to the NRF to perform discovery (discovery of client NWDAFs that have previously performed training (clients associated with VFL association ID (+application ID) and analytics ID).
[0184] Based on this, the NRF can transmit information (e.g., one or more NWDAF IDs) regarding the IDs of NWDAFs associated with the relevant VFL process (e.g., associated with the VFL association ID (+application ID)) to the NEF.
[0185] Based on this, the NEF can assign a Temporary (External) NWDAF ID to each NWDAF(s) associated with the corresponding VFL process (e.g., associated with the VFL association ID (+application ID)).
[0186] The NEF can send one or more assigned temporary (external) NWDAF IDs to the VFL server AF.
[0187] The VFL server AF can perform VFL retraining (and / or inference) with the client(s) (e.g., one or more client NWDAFs) associated with the VFL association ID (+application ID) based on one or more received temporary (external) NWDAF IDs.
[0188] 2. Second embodiment
[0189] According to the second embodiment, the NEF can store mapping information between the VFL association ID and the actual NWDAF ID.
[0190] Once training is complete, the server AF may request the NEF to save the Analytics ID, VFL association ID (+Application ID), and / or the NWDAF ID List corresponding to the VFL association ID (+Application ID).
[0191] NEF can store the actual NWDAF ID list without needing to store the Analytics ID, VFL association ID (+Application ID), and / or the Temporary (External) NWDAF ID for the VFL association ID (+Application ID).
[0192] Subsequently, if retraining (and / or inference) is required by the VFL server AF, the VFL server AF may send a VFL training / inference request message to the NEF requesting discovery for existing clients (e.g., clients that participated in the previous VFL process, multiple client NWDAFs) based on the analytics ID and VFL association ID (+application ID).
[0193] The VFL server AF can implicitly request discovery for existing clients by including a Preparation Flag in the VFL training / inference request message.
[0194] Alternatively, the VFL server AF may request discovery for existing clients by including a separate indication in the VFL training / inference request message requesting a list of client NWDAFs.
[0195] The NEF that receives the request can check the list of NWDAF IDs stored for the VFL association ID (+Application ID) and Analytics ID. The NEF can newly assign a temporary (external) NWDAF ID to the NWDAFs belonging to the NWDAF ID list (or each of the multiple NWDAFs in the case of multiple NWDAFs).
[0196] NEF can transmit information about newly assigned temporary NWDAF IDs (e.g., a list of new temporary NWDAF IDs) to a server (e.g., VFL server AF).
[0197] According to the second embodiment, since the NEF stores the NWDAF list, the discovery process through the NRF can be omitted for the NEF.
[0198] Based on information regarding newly assigned temporary NWDAF IDs (e.g., a list of new temporary NWDAF IDs), the VFL server AF can perform VFL retraining (and / or inference) with clients associated with VFL association IDs (e.g., one or more client NWDAFs).
[0199] Alternatively, the NEF may continue to store the mapping between the list of temporary (external) NWDAF IDs used and the list of actual NWDAF IDs even after training is completed. Additionally, the AF may also store the list of used temporary (external) NWDAF IDs. Subsequently, the NEF can verify the validity of these lists of temporary (external) NWDAF IDs during the preparation process for training / inference. If the NEF determines internally that all temporary (external) NWDAF IDs are valid, the VFL server AF can perform training / inference using the previously used temporary (external) NWDAF IDs as they are. If some or all of the temporary (external) NWDAF IDs are determined to be invalid (e.g., if the temporary / external NWDAF ID is in use by another VFL process, or if the temporary / external NWDAF ID is outdated and requires updating), the NEF may assign new temporary (external) NWDAF IDs to some or all of the relevant NWDAFs. NEF can send the newly assigned temporary / external NWDAF ID to the VFL server AF.
[0200] 3. Third embodiment
[0201] According to the third embodiment, the NEF can provide a validity time for a temporary (external) NWDAF ID.
[0202] When the NEF assigns temporary (external) NWDAF IDs to client NWDAFs to the VFL server AF, the NEF may also provide the validity time for said temporary (external) NWDAF ID.
[0203] Until the validity time expires, NEF can store (retain without deleting) mapping information (mapping information between temporary (external) NWDAF IDs and actual NWDAF IDs) related to VFL processes (VFL processes for the VFL associated ID (+Application ID) and Analytics ID).
[0204] Until the validity time expires, the VFL server AF can continue to perform VFL retraining (and / or inference) with the corresponding client NWDAFs (clients associated with the VFL association ID) using the temporary (external) NWDAF ID.
[0205] If the validity time expires, the VFL server AF may be assigned a new temporary (external) NWDAF ID from the NEF through the method of the first or second embodiment. At this time, the NEF may set / determine a new validity time for the new temporary (external) NWDAF ID and transmit it to the VFL server AF. Until the newly set / determined validity time expires, the VFL server AF may perform VFL retraining (and / or inference) using the new temporary (external) NWDAF ID.
[0206] The VFL server AF may anticipate or determine that the validity time will expire before (or during) performing training (and / or inference). In this case, through the method of the first or second embodiment, the VFL server AF may receive a new temporary (external) NWDAF ID and a new validity time for the VFL process from the NEF.
[0207] 4. Fourth embodiment
[0208] According to the fourth embodiment, AF can provide information related to the validity time for the VFL association ID for retraining / inference.
[0209] In the first embodiment, the NEF may store a list of actual NWDAF IDs for VFL processes. In the second embodiment, the NRF may store VFL process-related information in the NF profile of each client NWDAF.
[0210] However, the network cannot know how long the server will use the VFL process corresponding to the VFL association ID. Therefore, considering the storage capacity of NEF / NRF, information is needed regarding how long this information should be stored or when it should be deleted. For example, if an AF decides not to use or execute the VFL process for a VFL association ID any longer, the network can free up unnecessary storage capacity by deleting information regarding that VFL process and the corresponding NWDAF ID list.
[0211] To this end, AF (VFL server AF) may provide information regarding the validity time for the VFL associated ID (+application ID). Alternatively, AF (VFL server AF) may provide information that the VFL associated ID (+application ID) will no longer be used.
[0212] Such information (e.g., information regarding the validity period of VFL association IDs, information indicating that VFL association IDs will no longer be used) can be transmitted to the NEF (or client NWDAF) via VFL training / inference messages.
[0213] If an update to the Validity Time for a previously transmitted VFL Association ID is required, the AF may provide information regarding the new Validity Time. Even if the Validity Time has not expired, the AF may decide not to perform VFL training / inference for the VFL Association ID (+Application ID) any further. In this case, the AF may notify the NEF and / or client NWDAF of such information.
[0214] Information indicating that VFL training / inference will no longer be performed for VFL associated IDs (+application IDs) can be expressed in the following form and in other forms:
[0215] - Information indicating deletion for VFL association ID (+application ID)
[0216] - Information indicating the end of use for the VFL associated ID (+application ID)
[0217] If the Validity Time provided by AF expires, or if AF decides to no longer use the VFL process identified by the VFL association ID (+Application ID) and notifies the Network (e.g., in the case of the first embodiment, when the client NWDAF receives such information; in the case of the second embodiment, when the NEF receives such information), the Network may apply the method of the first or second embodiment as follows to delete the relevant information:
[0218] - In the case of the first embodiment, each of the plurality of client NWDAFs can delete information related to the VFL association ID (+application ID) by performing an NF profile update with the NRF.
[0219] - In the case of the second embodiment, the NEF can delete information related to the stored VFL associated ID (+application ID) and the mapping information with the actual NWDAF ID associated therewith.
[0220] The first embodiment and the second embodiment may be performed independently. Alternatively, the first embodiment and the second embodiment may be performed in combination.
[0221] The third and fourth embodiments may be performed independently. Alternatively, the third and fourth embodiments may be performed in combination.
[0222] The third embodiment may be performed in combination with the first embodiment or the second embodiment.
[0223] The fourth embodiment may be performed in combination with the first embodiment or the second embodiment.
[0224] For example, the first, third, and fourth embodiments may be performed in combination.
[0225] For example, the second, third, and fourth embodiments may be performed in combination.
[0226] For example, the first and third embodiments may be performed in combination.
[0227] For example, the first embodiment and the fourth embodiment may be performed in combination.
[0228] For example, the second and third embodiments may be performed in combination.
[0229] For example, the second and fourth embodiments may be performed in combination.
[0230] In this specification, VFL client discovery and selection methods may be proposed in relation to temporary (external) NWDAF ID assignment. Additionally, VFL training and inference methods may be proposed.
[0231] The procedure according to the disclosure of this specification will be described below.
[0232] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.
[0233] FIGS. 6, FIGS. 7, and FIGS. 8 illustrate examples of procedures according to the disclosure of the present specification.
[0234] In FIGS. 6, FIGS. 7 and FIGS. 8, the content related to the first embodiment is represented by [1].
[0235] In FIGS. 6, FIGS. 7 and FIGS. 8, the content related to the second embodiment is represented as [2].
[0236] In FIGS. 6, FIGS. 7 and FIGS. 8, the content related to the third embodiment is represented as [3].
[0237] In FIGS. 6, FIGS. 7 and FIGS. 8, the content related to the fourth embodiment is represented as [4].
[0238] 1-2) Step 1 - Step 2
[0239] When an untrusted AF acts as a VFL server, the AF may send a request for client discovery to the NEF for client discovery and selection for the VFL. Such request may be sent via a VFL client Discovery message.
[0240] VFL client Discovery messages may include service area, NF type (e.g., NWDAF), VFL client capability, VFL-related information, etc.
[0241] NEF can forward the message to NRF to request information about the client NWDAF.
[0242] 3-4) Step 3 - Step 4
[0243] Based on the received message, the NRF can send information about candidate client NWDAFs (e.g., one or more NWDAF IDs) to the NEF.
[0244] For security purposes (to hide information within the core network), the NEF may provide the AF with a temporary (external) NWDAF ID instead of the actual NWDAF ID. The temporary (external) NWDAF ID can be mapped to the actual NWDAF ID.
[0245] NEF can send one or more temporary (external) NWDAF IDs to AF (VFL server AF).
[0246] NEF stores mapping information between a temporary (external) NWDAF ID and an actual NWDAF ID, which can be used in subsequent training (or retraining) processes.
[0247] According to the third embodiment, the following operation may be performed:
[0248] - In Step 4, the NEF can determine the validity time for the temporary (external) NWDAF ID. The NEF can transmit information regarding the validity time for the temporary (external) NWDAF ID. In this case, even if the ongoing VFL training / inference ends, the AF can perform retraining / inference through Steps 5 to 7 using the temporary (external) NWDAF ID received in Step 4 until the validity time expires. At this time, the AF may not perform the discovery and selection process of additional client NWDAFs.
[0249] - When the validity time for a temporary (external) NWDAF ID expires, the NEF may assign a new temporary (external) NWDAF ID and validity time by the method of the first embodiment (steps 8 to 12) or the second embodiment (steps 8' to 10').
[0250] 5) Step 5
[0251] The AF can finally select the client NWDAF to perform the VFL process from among the NWDAFs received from the NEF.
[0252] And, AF can assign a VFL association ID to the corresponding VFL process.
[0253] Subsequently, AF can send a VFL training request containing the information required for VFL training and the VFL associated ID (+application ID) to the finally selected clients, NWDAFs.
[0254] A VFL training request (or subscription) may include an Analytics ID, a VFL association ID (+Application ID), and VFL-related information.
[0255] The request may be transmitted via NEF. Therefore, the Analytics ID, VFL association ID (+Application ID), and VFL-related information included in the request may be transmitted to NEF.
[0256] 6) Step 6
[0257] Each client NWDAF can train its own local ML model based on information received from AF and information collected locally.
[0258] Each client NWDAF can transmit information about the intermediate training result to the AF.
[0259] The step 6 operation can be performed via NEF.
[0260] 7) Step 7
[0261] AF can aggregate information on intermediate training results received from each client NWDAF and train AF's local ML model.
[0262] AF can calculate / determine intermediate training information (e.g., Gradient information, loss information) and update the local ML model based on it.
[0263] AF can calculate / determine intermediate training information (e.g., Gradient information, loss information) for each client NWDAF and transmit it to each client NWDAF. Based on this, each client NWDAF can update its local ML model.
[0264] AF can send a termination request message to each client NWDAF to terminate the VFL process.
[0265] The step 7 operation can be performed via NEF.
[0266] Steps 6 and 7 can be performed repeatedly until AF determines that VFL training has converged.
[0267] For example, if the loss function or loss value reaches a degree of convergence (or a preset number of iterations), the AF may determine that training is complete. In this case, to terminate the current VFL process, the AF may send a termination indication to the client NWDAF. Based on this, the client NWDAF may terminate the VFL training process.
[0268] According to the fourth embodiment, the following operation may be performed:
[0269] - When training starts in Step 5 (or when training ends in Step 7), AF can determine the validity time for the VFL associated ID (+Application ID). AF can transmit information regarding the validity time for the VFL associated ID (+Application ID) to the client NWDAF. Based on this information, the client NWDAF (in the case of the first embodiment) or NEF (in the case of the second embodiment) may decide to maintain information related to the mapping of the VFL associated ID (+Application ID) to the NWDAF ID list for that time.
[0270] According to the first embodiment, Steps 8 to 12 may be performed.
[0271] 8) Step 8
[0272] After training ends, each client NWDAF can send information such as the Analytics ID, VFL association ID (+Application ID), etc. to the NRF. The NRF can update the NF profile based on this information. The NRF may store the updated NF profile.
[0273] 9-10) step 9 - step 10
[0274] If retraining (or inference) for a VFL process is required, AF can perform discovery on VFL client NWDAFs (e.g., client NWDAF(s) involved in the VFL process) through NEF. To do this, AF can send a VFL client discovery request message to NEF. The VFL client discovery request message may include a VFL association ID (+application ID), an analytics ID, and VFL-related information.
[0275] The NEF can send an NF discovery request message to the NRF (step 10). The NF discovery request message may include the VFL association ID (+application ID), Analytics ID, and VFL-related information. 11-12) step 11 - step 12
[0276] NRF can find client NWDAFs corresponding to the Analytics ID, VFL association ID (+Application ID) and / or VFL association ID (+Application ID) based on the NF profile updated in step 8 and notify the NEF.
[0277] For example, the NEF can send an NF discovery request message to the NRF (step 10). The NF discovery request message may include a VFL association ID (+application ID), an analytics ID, and VFL-related information. Based on this, the NRF can determine the client NWDAF(s) involved in a specific VFL process through the NF profile updated in step 8. The NRF can send information about the determined client NWDAF(s) (e.g., NWDAF ID) to the NEF (step 11).
[0278] NEF can assign a new temporary (external) NWDAF ID to the corresponding client NWDAF(s).
[0279] The NEF can send the assigned new temporary (external) NWDAF ID to the AF (step 12).
[0280] The NEF can store mapping information between a new temporary (external) NWDAF ID and an actual NWDAF ID (the NWDAF ID received in step 11). Based on this, retraining or inference with the corresponding client NWDAF(s) can be performed.
[0281] According to the third embodiment, the NEF can determine the validity time for a new temporary (external) NWDAF ID. In Step 12, the NEF can transmit information about the validity time for the new temporary (external) NWDAF ID to the server AF.
[0282] 13) Step 13
[0283] AF can perform VFL retraining or inference using the temporary (external) NWDAF ID received through step 12.
[0284] According to the fourth embodiment, the following operation may be performed:
[0285] - When retraining / inference starts (or ends), AF can determine a new validity time for the VFL association ID (+application ID). AF can send a message (e.g., a training / inference request message) containing information about the new validity time for the VFL association ID (+application ID) to the client NWDAF. Through this, the validity time for the VFL association ID (+application ID) can be updated.
[0286] - If the updated validity time has expired, or if the client NWDAF receives information from AF via a training / inference message that the VFL association ID (+application ID) is no longer in use, the NWDAF (client NWDAF) can update the NF profile to delete the information associated with the VFL association ID (+application ID).
[0287] According to the second embodiment, Step 8' to Step 10' can be performed.
[0288] 8') step 8'
[0289] NEF can store a list of actual NWDAF IDs for VFL association IDs (+application IDs).
[0290] The NWDAFs belonging to the above list of actual NWDAF IDs may be client NWDAFs that were involved in the VFL process associated with the VFL association ID (+application ID).
[0291] The operation (the operation of saving the actual NWDAF ID list) may be performed based on a message from the AF in step 7 (e.g., a termination request message). Alternatively, the operation (the operation of saving the actual NWDAF ID list) may be performed based on the NEF receiving a separate request message from the AF.
[0292] 9') step 9'
[0293] To find clients for the VFL process corresponding to the VFL association ID (+application ID), the AF may send a request (or subscription) message for training / inference to the NEF along with a VFL preparation flag indicating that it is in the preparation phase for the VFL.
[0294] Alternatively, AF may send a request (or subscription) message for training / inference that includes a separate indication requesting the Client NWDAF list.
[0295] AF can include the Analytics ID and VFL association ID (+Application ID) together in the request (or subscription) message for training / inference and send it.
[0296] Alternatively, in step 8', the NEF may continue to store information regarding the mapping between the list of temporary (external) NWDAF IDs used and the actual NWDAF ID list even after training is finished, and the AF may also store the list of temporary (external) NWDAF IDs used. In this case, in Step 9', the NEF can check whether all NWDAFs in the list of temporary (external) NWDAF IDs are valid. If all are valid, the VFL server AF can perform training / inference using the previously used temporary (external) NWDAF IDs as they are. If the NEF determines internally that some or all of the temporary (external) NWDAF IDs in the list are invalid, the NEF may assign a new temporary (external) NWDAF ID to replace the invalid temporary (external) NWDAF IDs in Step 10' and send it to the AF.
[0297] According to the fourth embodiment, the AF can determine / update the validity time of the VFL association ID (+application ID). In this case, the AF may also send a request (or subscription) message for training / inference to the NEF, which includes information regarding the updated validity time for the VFL association ID (+application ID). Based on this information, the NEF can update the retention time of the mapping information of the NWDAF ID.
[0298] 10') step 10'
[0299] The NEF can check the list of stored NWDAF IDs corresponding to the Analytics ID, VFL association ID (+Application ID), and / or VFL association ID (+Application ID), and newly assign temporary (external) NWDAF IDs to the corresponding NWDAFs and send them to the AF.
[0300] According to the third embodiment, in Step 10', the NEF may also provide the validity time for the newly assigned temporary (external) NWDAF ID.
[0301] 11') step 11'
[0302] AF can perform retraining or inference using the temporary (external) NWDAF ID received through step 10'.
[0303] According to the fourth embodiment, the following operation may be performed:
[0304] - The AF can update the validity period of the VFL association ID (+application ID) (determine a new validity period). If the validity period of the VFL association ID (+application ID) is updated, the AF can send a training / inference request message containing the updated validity period for the VFL association ID (+application ID) to client NWDAFs (or NEFs).
[0305] - If the updated validity period has expired, or if information is received via a training / inference message that the VFL association ID (+application ID) is no longer in use, the NEF may delete the information associated with the VFL association ID (+application ID).
[0306] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.
[0307] FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12 illustrate examples of procedures according to the disclosure of the present specification.
[0308] In FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12, the content related to the first embodiment is represented by [1].
[0309] In FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12, the content related to the second embodiment is represented as [2].
[0310] In FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12, the content related to the third embodiment is represented as [3].
[0311] In FIGS. 9, FIGS. 10, FIGS. 11 and FIGS. 12, the content related to the fourth embodiment is represented by [4].
[0312] In this specification, the NEF can convert an Nnef message received from the AF into an Nnwdaf message. The NEF can transmit the converted Nnwdaf message to each NWDAF client. The NEF can convert an Nnwdaf message received from each NWDAF client into an Nnef message. The NEF can transmit the converted Nnef message to the AF.
[0313] 1-2) step 1- step 2
[0314] The descriptions in Figs. 6, 7, and 8 may apply.
[0315] 3-4) Step 3- Step 4
[0316] Based on the received message, the NRF can send information about candidate client NWDAFs (e.g., one or more NWDAF IDs) to the NEF.
[0317] For security purposes (to hide information within the core network), the NEF may provide the AF with an External NWDAF ID instead of the actual NWDAF ID. The External NWDAF ID can be mapped to the actual NWDAF ID.
[0318] NEF can send external NWDAF IDs for candidate client NWDAFs to AF (VFL server AF).
[0319] NEF stores mapping information between the external NWDAF ID and the actual NWDAF ID, which can be used in subsequent training (or retraining) processes.
[0320] According to the third embodiment, the following operation may be performed:
[0321] - In Step 4, the NEF can determine the validity time for the external NWDAF ID. The NEF can transmit information regarding the validity time for the external NWDAF ID. In this case, even if the ongoing VFL training / inference ends, the AF can perform retraining / inference via Step 15 or Step 13' using the external NWDAF ID received in Step 4 until the validity time expires. At this time, the AF may not perform the discovery and selection process for additional client NWDAFs.
[0322] - If the validity time for an external NWDAF ID has expired, the NEF may assign a new temporary (external) NWDAF ID and validity time by the method of the first embodiment (steps 10 to 15) or the second embodiment (steps 10' to 13').
[0323] 5-6) step 5- step 6
[0324] AF can perform a preparation process to verify whether candidate client NWDAFs received from NEF satisfy the ML Model Training requirement.
[0325] To perform this process, AF can make a request to AF through the Nnef_VFLTraining_Request service operation. Based on this, Nnef can send requests to each of multiple clients using the Nnwdaf_VFLTraining_Request service operation. Each of the multiple clients can send a response to AF.
[0326] 7) Step 7
[0327] AF can finally select the client NWDAF to perform the VFL process from among candidate clients such as NWDAF received from NEF.
[0328] AF can assign a VFL association ID to the corresponding VFL process.
[0329] Subsequently, AF can send a training request message containing the information required for VFL training and the assigned VFL association ID (+application ID) to the corresponding client NWDAFs through the Nnef_VFLTraining_Subscribe service operation.
[0330] 8) Step 8
[0331] Each client NWDAF can train its own local ML model based on information received from AF and information collected locally.
[0332] Each client NWDAF can send information about the intermediate training result to the NEF through the Nnwdaf_VFLTraining_Notify service operation. Based on this, the NEF can send information about the intermediate training result to the AF through the Nnef_VFLTraining_Notify service operation.
[0333] AF can aggregate information on intermediate training results received from each client NWDAF and train AF's local ML model.
[0334] AF can calculate / determine intermediate training information (e.g., Gradient information, loss information) and update the local ML model based on it.
[0335] AF can calculate / determine intermediate training information (e.g., Gradient information, loss information) for each client NWDAF and transmit it to each client NWDAF. Based on this, each client NWDAF can update its local ML model.
[0336] Steps 7 and 8 can be performed repeatedly. Through step 7, AF can deliver intermediate training information for each client to each client and request the next training round. Each client can update its local ML model based on the information and perform the next training round.
[0337] Steps 7 and 8 can be performed repeatedly until AF determines that VFL training has converged.
[0338] For example, if the loss function or loss value reaches a degree of convergence (or a preset number of iterations), the AF may determine that training is complete. In this case, to terminate the current VFL process, the AF may send a termination indication to the client NWDAF. Based on this, the client NWDAF may terminate the VFL training process.
[0339] According to the fourth embodiment, the following operation may be performed:
[0340] - When training starts in Step 7 (or when training ends in Step 9), AF can determine the validity time for the VFL associated ID (+Application ID). AF can transmit information regarding the validity time for the VFL associated ID (+Application ID) to the client NWDAF. Based on this information, the client NWDAF (in the case of the first embodiment) or NEF (in the case of the second embodiment) may decide to maintain information related to the mapping of the VFL associated ID (+Application ID) to the NWDAF ID list for that time.
[0341] According to the first embodiment, Steps 10 to 15 may be performed.
[0342] 10) Step 10
[0343] After training ends, each client NWDAF can send information such as the Analytics ID, VFL association ID (+Application ID), etc. to the NRF. The NRF can update the NF profile based on this information. The NRF may store the updated NF profile.
[0344] 11-12) step 11 -step 12
[0345] If retraining (or inference) for a VFL process is required, AF can perform discovery on VFL client NWDAFs (e.g., client NWDAF(s) involved in the VFL process) through NEF. To do this, AF can send a VFL client discovery request message to NEF. The VFL client discovery request message may include a VFL association ID (+application ID), an analytics ID, and VFL-related information.
[0346] NEF can send an NF discovery request message to NRF (step 12). The NF discovery request message may include a VFL association ID (+application ID), an analytics ID, and VFL-related information.
[0347] 13-14) Step 13 - Step 14
[0348] NRF can find client NWDAFs corresponding to the Analytics ID and VFL association ID (+Application ID) based on the NF profile updated in step 10 and notify the NEF.
[0349] For example, the NEF can send an NF discovery request message to the NRF (step 12). The NF discovery request message may include a VFL association ID (+application ID), an analytics ID, and VFL-related information. Based on this, the NRF can determine the client NWDAF(s) involved in a specific VFL process through the NF profile updated in step 10. The NRF can send information about the determined client NWDAF(s) (e.g., NWDAF ID) to the NEF (step 13).
[0350] NEF can assign a new temporary (external) NWDAF ID to the corresponding client NWDAF(s).
[0351] The NEF can send the assigned new external NWDAF ID to the AF (step 14).
[0352] The NEF can store mapping information between a new external NWDAF ID and an actual NWDAF ID (the NWDAF ID received in step 13). Based on this, retraining or inference with the corresponding client NWDAF(s) can be performed.
[0353] According to the third embodiment, the NEF can determine a new validity time for the external NWDAF ID. In Step 14, the NEF can transmit information regarding the validity time for the external NWDAF ID to the server AF.
[0354] 15) Step 15
[0355] AF can perform VFL retraining or inference using the temporary (external) NWDAF ID received through step 14.
[0356] According to the fourth embodiment, the following operation may be performed:
[0357] - When retraining / inference starts (or ends), AF can determine a new validity time for the VFL association ID (+application ID). AF can send a message (e.g., a training / inference request message) containing information about the new validity time for the VFL association ID (+application ID) to the client NWDAF. Through this, the validity time for the VFL association ID (+application ID) can be updated.
[0358] - If the updated validity time has expired, or if the client NWDAF receives information from AF via a training / inference message that the VFL association ID (+application ID) is no longer in use, the NWDAF (client NWDAF) can update the NF profile to delete the information associated with the VFL association ID (+application ID).
[0359] According to the second embodiment, Step 10' to Step 13' can be performed.
[0360] 10') step 10'
[0361] NEF can store a list of actual NWDAF IDs for VFL association IDs (+application IDs).
[0362] The NWDAFs belonging to the above list of actual NWDAF IDs may be client NWDAFs that were involved in the VFL process associated with the VFL association ID (+application ID).
[0363] The operation (the operation of saving the actual NWDAF ID list) can be performed based on a message (e.g., an unsubscribe message) that AF sends to the client in step 9. Alternatively, the operation (the operation of saving the actual NWDAF ID list) can be performed based on NEF receiving a separate request message from AF.
[0364] 11') step 11'
[0365] The AF may send a request message to the NEF requesting a VFL process (retraining or inference) corresponding to the VFL association ID (+application ID). Alternatively, the AF may send a request message to the NEF containing a separate indication requesting a list of client NWDAFs. The AF may send a request message to the NEF containing the Analytics ID and the VFL association ID (+application ID).
[0366] According to the fourth embodiment, AF can determine / update the validity time of the VFL association ID (+application ID). In this case, AF may send a request message to NEF containing information about the updated validity time for the VFL association ID (+application ID). Based on this information, NEF can update the retention time of the mapping information of the NWDAF ID.
[0367] 12') step 12'
[0368] The NEF can check the list of stored NWDAF IDs corresponding to the Analytics ID, VFL association ID (+Application ID), and / or VFL association ID (+Application ID), and newly assign temporary (external) NWDAF IDs to the corresponding NWDAFs and send them to the AF.
[0369] According to the third embodiment, the NEF can determine the validity time for the newly assigned temporary (external) NWDAF ID. In Step 12', the NEF can also provide the validity time for the newly assigned temporary (external) NWDAF ID.
[0370] Alternatively, in step 10', the NEF may continue to store information regarding the mapping between the list of temporary (external) NWDAF IDs used for the VFL associated ID (+application ID) and the actual NWDAF ID list even after training is finished, and the AF may also store the list of temporary (external) NWDAF IDs used. In this case, in Step 11', the AF may send a request message to the NEF including the previously used list of external NWDAF IDs. In this case, in Step 11', the NEF may check whether all NWDAFs in the corresponding list of temporary (external) NWDAF IDs are valid. If all are valid, the VFL server AF may perform training / inference using the previously used temporary (external) NWDAF IDs as they are. If the NEF determines, based on an internal judgment, that some or all of the temporary (external) NWDAF IDs in the list are invalid, the NEF may assign a new temporary (external) NWDAF ID in place of the invalid temporary (external) NWDAF ID in Step 12' and send it to the AF.
[0371] 13') step 13'
[0372] AF can perform retraining or inference using the temporary (external) NWDAF ID received through step 12'.
[0373] According to the fourth embodiment, the following operation may be performed:
[0374] - The AF can determine / update the validity period of the VFL association ID (+application ID). If the validity period of the VFL association ID (+application ID) is updated, the AF can send a training / inference request message containing the updated validity period for the VFL association ID (+application ID) to client NWDAFs (or NEFs).
[0375] - If the updated validity period has expired, or if information is received via a training / inference message that the VFL association ID (+application ID) is no longer in use, the NEF may delete the information associated with the VFL association ID (+application ID).
[0376] The effects according to the embodiments of the present specification are as follows:
[0377] - By assigning a new temporary (external) NWDAF ID while maintaining the association with the client(s) and server(s) of the existing VFL process, retraining / inference for the corresponding VFL process can be performed in the future. Additionally, unnecessary VFL association ID (+application ID) related information that is no longer used by the AF can be deleted from the network.
[0378] In this specification, a method for updating and managing a temporary (external) NWDAF ID provided by an NEF to an AF may be proposed when an untrusted AF operates as a server for Vertical Federated Learning (VFL) and an NWDAF operates as a client.
[0379] According to the first embodiment, the following operation may be performed:
[0380] - Each client can save the VFL associated ID (+application ID) by updating the NRF's NF profile during training or before / after completion.
[0381] - If retraining and inference by the VFL server AF are required, the VFL server AF may request discovery of clients that participated in the previous VFL process, including the VFL association ID (+application ID) and analytics ID.
[0382] - NEF can forward the request to NRF to perform discovery on client NWDAFs associated with VFL associated IDs (+Application IDs) and Analytics IDs that have previously performed training.
[0383] - And the NEF can assign a new temporary (external) NWDAF ID to the corresponding client NWDAFs received from the NRF and send it to the VFL server AF.
[0384] According to the second embodiment, the following operation may be performed:
[0385] - Once training is complete, the Server AF may request the NEF to store the Analytics ID, VFL Association ID (+Application ID), and / or the list of actual NWDAF IDs corresponding to the VFL Association ID (+Application ID). The NEF may store the list of actual NWDAF IDs without storing temporary (external) NWDAF IDs.
[0386] - Subsequently, if retraining and inference by AF are required, the VFL server can request discovery of existing clients from the NEF using the Analytics ID and VFL association ID (+Application ID). This request can be made by including a ready flag in the VFL training / inference request message, or by including a separate indication requesting a list of client NWDAFs.
[0387] - NEF can check the list of NWDAF IDs stored for VFL associated IDs (+Application IDs) and Analytics IDs, and newly assign a temporary (external) list of NWDAF IDs for the corresponding list and send it to the server.
[0388] Alternatively, the NEF may continue to store the mapping between the list of temporary (external) NWDAF IDs used and the actual NWDAF ID list even after training is completed. The AF may also store the list of used temporary (external) NWDAF IDs. Subsequently, the NEF can check whether the relevant lists of temporary (external) NWDAF IDs are valid during the preparation process for training / inference. If the NEF determines internally that all temporary (external) NWDAF IDs are valid, the VFL server AF can perform training / inference using the previously used temporary (external) NWDAF IDs as they are. If some or all of the temporary (external) NWDAF IDs are invalid, some or all of the temporary (external) NWDAF IDs may be newly assigned.
[0389] According to the third embodiment, the following operation may be performed:
[0390] When the NEF assigns a temporary (external) NWDAF ID to client NWDAFs to the AF, the NEF may also provide an expiration time. Until the expiration time, the NEF may store mapping information between the temporary NWDAF ID of the VFL process and the actual NWDAF ID for the corresponding VFL associated ID (+Application ID) and Analytics ID.
[0391] - Until the validity period expires, the VFL server AF can continue to perform retraining or inference with clients associated with the VFL association ID using the corresponding temporary (external) NWDAF.
[0392] - If the validity period of the VFL server AF has expired, or if the validity period is expected to expire before (or during) training / inference, the NEF may receive a new temporary (external) NWDAF ID from the AF through the method of the first or second embodiment. In this case, the validity period may also be received from the NEF along with the temporary (external) NWDAF ID.
[0393] According to the fourth embodiment, the following operation may be performed:
[0394] - The AF can provide validity time information for a VFL association ID or information that the VFL association ID will no longer be used. This can be conveyed to the NEF or client NWDAF via VFL training / inference messages.
[0395] - AF may also provide new validity time information if an update to the validity time for the previously transmitted VFL association ID is required.
[0396] - Even if the validity period has not expired, if AF decides not to perform VFL training / inference for the VFL association ID (+application ID) any further, it can notify the NEF and the client NWDAF of this.
[0397] - The AF can express information that it will no longer perform VFL training / inference for the VFL associated ID (+application ID) in various forms (e.g., information indicating deletion of the VFL associated ID (+application ID), information indicating termination of use of the VFL associated ID (+application ID)).
[0398] - If the validity period provided by AF expires or AF decides to no longer use the VFL process represented by the VFL association ID (+application ID) and notifies the network, the relevant information may be deleted for the method of the first embodiment or the second embodiment as follows.
[0399] In the case of the first embodiment, each client NWDAF can update the NF profile to delete information related to the VFL association ID (+application ID).
[0400] In the case of the second embodiment, the NEF can delete information including the stored VFL associated ID (+application ID), mapping information with the associated actual NWDAF ID, and the actual NWDAF ID.
[0401] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.
[0402] FIG. 13 illustrates the procedure of the NEF according to the disclosure of the present specification.
[0403] 1. The NEF (Network Exposure Function) can receive a discovery request message for a client of the VFL process from the VFL (Vertical Federated Learning) server AF (Application Function).
[0404] 2. Based on the above discovery request message, the NEF can obtain information about the client NWDAF (Network Data Analytics Function) for the VFL process from the NRF (Network Repository Function).
[0405] 3. The above NEF can determine an external NWDAF ID for the above client NWDAF.
[0406] 4. The NEF may send a discovery response message containing the external NWDAF ID to the VFL server AF.
[0407] 5. The above NEF can receive a first request message of the VFL process from the above VFL server AF.
[0408] The first request message above may include a VFL correlation ID for the VFL process.
[0409] 6. The above NEF can store information about the above VFL association ID and the above client NWDAF.
[0410] 7. The above NEF may receive a second request message for the VFL process from the above VFL server AF.
[0411] The second request message above may include the VFL association ID.
[0412] 8. Based on the second request message above, the NEF can determine a new external NWDAF ID for the client NWDAF.
[0413] 9. Based on the second request message above, the NEF may send a VFL process response message containing the new external NWDAF ID to the VFL server AF.
[0414] The second request message above may be a message for retraining or inference of the VFL process.
[0415] The above NEF can determine the validity time for the above external NWDAF ID.
[0416] The discovery response message above may include information about the determined validity time for the external NWDAF ID.
[0417] The above NEF can determine a new validity time for the above new external NWDAF ID.
[0418] The above VFL process response message may include information regarding the determined new validity time for the new external NWDAF ID.
[0419] The first request message above may include information regarding the validity period for the VFL association ID.
[0420] The second request message above may include information about a new validity time for the VFL association ID.
[0421] Based on the expiration of the new validity period for the above VFL association ID, the NEF may delete the above VFL association ID, the actual ID of the client NWDAF, and mapping information.
[0422] The above mapping information may be i) mapping information between the external NWDAF ID and the actual ID or ii) mapping information between the new external NWDAF ID and the actual ID.
[0423] The above NEF can receive information from the above VFL server AF that the above VFL association ID is no longer in use.
[0424] Based on the information that the above VFL association ID is no longer in use, the above NEF can delete the above VFL association ID, the actual ID of the client NWDAF, and mapping information.
[0425] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.
[0426] FIG. 14 illustrates the procedure of a VFL server AF according to the disclosure of the present specification.
[0427] 1. A step in which the VFL server AF sends a discovery request message to the NEF regarding the client of the VFL process;
[0428] 2. The above VFL server AF can receive a discovery response message containing an external NWDAF ID from the above NEF.
[0429] The above external NWDAF ID may be information about the client NWDAF for the above VFL process.
[0430] 3. The above VFL server AF can send a first request message of the VFL process to the above NEF.
[0431] The first request message above may include a VFL association ID for the VFL process.
[0432] 4. The above VFL server AF can send a second request message of the VFL process to the above NEF.
[0433] 5. Based on the second request message above, the VFL server AF may receive a VFL process response message from the NEF containing a new external NWDAF ID.
[0434] From the above, the new external NWDAF ID may be information about the client NWDAF.
[0435] The second request message above may be a message for retraining or inference of the VFL process.
[0436] The above discovery response message may include information regarding the validity period for the external NWDAF ID.
[0437] The above VFL process response message may include information regarding the validity period for the new external NWDAF ID.
[0438] The above VFL server AF can determine the validity time for the above VFL association ID.
[0439] The first request message above may include information regarding the determined validity time for the VFL association ID.
[0440] The above VFL server AF can determine a new validity time for the above VFL association ID.
[0441] The second request message above may include information about the determined new validity time for the VFL association ID.
[0442] The above VFL server AF may decide not to use the above VFL association ID anymore.
[0443] Based on the above decision, the VFL server AF can transmit information to the NEF that the VFL association ID is no longer used.
[0444] Hereinafter, a device for performing communication according to some embodiments of the present specification will be described.
[0445] For example, the device may include a processor, a transceiver, and memory.
[0446] For example, the processor can be configured to be operablely coupled with memory and the processor.
[0447] The operation performed by the processor comprises: a step in which a Network Exposure Function (NEF) receives a discovery request message regarding a client of a VFL process from a Vertical Federated Learning (VFL) server Application Function (AF); a step in which, based on the discovery request message, the NEF obtains information regarding a client Network Data Analytics Function (NWDAF) for the VFL process from a Network Repository Function (NRF); a step in which the NEF determines an external NWDAF ID for the client NWDAF; a step in which the NEF transmits a discovery response message containing the external NWDAF ID to the VFL server AF; a step in which the NEF receives a first request message for the VFL process from the VFL server AF; a step in which the first request message includes a VFL correlation ID for the VFL process, and the NEF stores information regarding the VFL correlation ID and the client NWDAF; and a step in which the NEF receives a second request message regarding the VFL process from the VFL server AF. The second request message may include the VFL association ID, and based on the second request message, the NEF may determine a new external NWDAF ID for the client NWDAF; and based on the second request message, the NEF may transmit a VFL process response message including the new external NWDAF ID to the VFL server AF.
[0448] Hereinafter, a processor of a device for providing communication according to some embodiments of the present specification will be described.
[0449] The operation performed by the processor comprises: a step in which a Network Exposure Function (NEF) receives a discovery request message regarding a client of a VFL process from a Vertical Federated Learning (VFL) server Application Function (AF); a step in which, based on the discovery request message, the NEF obtains information regarding a client Network Data Analytics Function (NWDAF) for the VFL process from a Network Repository Function (NRF); a step in which the NEF determines an external NWDAF ID for the client NWDAF; a step in which the NEF transmits a discovery response message containing the external NWDAF ID to the VFL server AF; a step in which the NEF receives a first request message for the VFL process from the VFL server AF; a step in which the first request message includes a VFL correlation ID for the VFL process, and the NEF stores information regarding the VFL correlation ID and the client NWDAF; and a step in which the NEF receives a second request message regarding the VFL process from the VFL server AF. The second request message may include the VFL association ID, and based on the second request message, the NEF may determine a new external NWDAF ID for the client NWDAF; and based on the second request message, the NEF may transmit a VFL process response message including the new external NWDAF ID to the VFL server AF.
[0450] Hereinafter, a non-volatile computer-readable medium storing one or more instructions for providing mobile communication according to some embodiments of the present specification will be described.
[0451] According to some embodiments of the present disclosure, the technical features of the present disclosure may be directly implemented in hardware, software executed by a processor, or a combination of both. For example, a method performed by a wireless device in wireless communication may be implemented in hardware, software, firmware, or any combination thereof. For example, software may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or other storage media.
[0452] In some examples, storage media are coupled to the processor so that the processor can read information from the storage media. Alternatively, the storage media can be integrated into the processor. The processor and storage media can reside in an ASIC. In other examples, the processor and storage media can reside as separate components.
[0453] Computer-readable media may include tangible and non-volatile computer-readable storage media.
[0454] For example, non-volatile computer-readable media may include RAM (Random Access Memory) such as SDRAM (Synchronization Dynamic Random Access Memory), ROM (Read-Only Memory), and NVRAM (Non-Volatile Random Access Memory); read-only memory (EEPROM); flash memory; magnetic or optical data storage media; or other media that can be used to store instructions or data structures. Non-volatile computer-readable media may also include combinations of the above.
[0455] Additionally, the method described herein may be realized at least partially by a computer-readable communication medium that transmits or transmits code in the form of instructions or data structures and can be accessed, read, and / or executed by a computer.
[0456] According to some embodiments of the present disclosure, a non-transient computer-readable medium stores one or more instructions thereon. The stored one or more instructions can be executed by a processor of a base station.
[0457] One or more stored commands include the steps of: a Network Exposure Function (NEF) receiving a discovery request message for a client of a VFL process from a Vertical Federated Learning (VFL) server Application Function (AF); based on the discovery request message, the NEF obtaining information about a client Network Data Analytics Function (NWDAF) for the VFL process from a Network Repository Function (NRF); the NEF determining an external NWDAF ID for the client NWDAF; the NEF transmitting a discovery response message containing the external NWDAF ID to the VFL server AF; the NEF receiving a first request message for the VFL process from the VFL server AF; the first request message including a VFL correlation ID for the VFL process, and the NEF storing information about the VFL correlation ID and the client NWDAF; and the NEF receiving a second request message for the VFL process from the VFL server AF. The second request message may include the VFL association ID, and based on the second request message, the NEF may determine a new external NWDAF ID for the client NWDAF; and based on the second request message, the NEF may transmit a VFL process response message including the new external NWDAF ID to the VFL server AF.
[0458] This specification may have various effects.
[0459] For example, the management of external NWDAF IDs for untrusted AFs is clearly defined.
[0460] The effects obtainable through the specific examples of this specification are not limited to those listed above. For example, there may be various technical effects that a person with ordinary skill in the related art can understand or derive from this specification. Accordingly, the specific effects of this specification are not limited to those explicitly described herein, but may include various effects that can be understood or derived from the technical features of this specification.
[0461] The claims described in this specification may be combined in various ways. For example, the technical features of the method claims in this specification may be combined to be implemented as a device, and the technical features of the device claims in this specification may be combined to be implemented as a method. Furthermore, the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a device, and the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a method. Other implementations are within the scope of the following claims.
Claims
1. As a method, A step in which the NEF (Network Exposure Function) receives a discovery request message for a client of the VFL process from the VFL (Vertical Federated Learning) server AF (Application Function); Based on the above discovery request message, the step of the NEF obtaining information about the client NWDAF (Network Data Analytics Function) for the VFL process from the NRF (Network Repository Function); The step of the above NEF determining an external NWDAF ID for the above client NWDAF; The step of the NEF transmitting a discovery response message containing the external NWDAF ID to the VFL server AF; The step of the NEF receiving a first request message of the VFL process from the VFL server AF; The first request message above includes a VFL correlation ID for the VFL process, and The step of the above NEF storing information about the above VFL association ID and the above client NWDAF; The step of the NEF receiving a second request message for the VFL process from the VFL server AF; The above second request message includes the above VFL association ID, and A step in which the NEF determines a new external NWDAF ID for the client NWDAF based on the second request message; A method comprising the step of, based on the second request message, the NEF transmitting a VFL process response message containing the new external NWDAF ID to the VFL server AF.
2. In Paragraph 1, The above second request message is a message for retraining or inference of the above VFL process.
3. In Paragraph 1 or 2, The above NEF further includes a step of determining the validity time for the external NWDAF ID, and A method in which the above discovery response message includes information about the determined validity time for the above external NWDAF ID.
4. In any one of paragraphs 1 through 3, The above NEF further includes the step of determining a new validity time for the new external NWDAF ID, and A method in which the above VFL process response message includes information about the determined new validity time for the above new external NWDAF ID.
5. In Paragraph 1 or 2, The above first request message is a method that includes information about the validity time for the above VFL association ID.
6. In Paragraph 5, The above second request message is a method that includes information about a new validity time for the above VFL association ID.
7. In Paragraph 6, Based on the expiration of the new validity period for the above VFL association ID, the NEF further includes the step of deleting the VFL association ID, the actual ID of the client NWDAF, and mapping information. A method in which the above mapping information is i) mapping information between the external NWDAF ID and the actual ID or ii) mapping information between the new external NWDAF ID and the actual ID.
8. In any one of paragraphs 1 through 7, The step of the NEF receiving information from the VFL server AF that the VFL association ID is no longer in use; and A method further comprising the step of the NEF deleting the VFL association ID, the actual ID of the client NWDAF, and mapping information based on information that the above VFL association ID is no longer used.
9. As a method, A step in which the VFL server AF sends a discovery request message to the NEF regarding the client of the VFL process; The step of the VFL server AF receiving a discovery response message containing an external NWDAF ID from the NEF; The above external NWDAF ID is information about the client NWDAF for the above VFL process, and The step of the above VFL server AF transmitting a first request message of the VFL process to the above NEF; The first request message above includes a VFL association ID for the VFL process, and The step of the above VFL server AF transmitting a second request message of the VFL process to the above NEF; Based on the second request message, the VFL server AF receives a VFL process response message from the NEF containing a new external NWDAF ID, and A method in which a new external NWDAF ID from the above is information about the client NWDAF.
10. In Paragraph 9, The above second request message is a message for retraining or inference of the above VFL process.
11. In Paragraph 9 or 10, A method in which the above discovery response message includes information regarding the validity time for the above external NWDAF ID.
12. In any one of paragraphs 9 through 11, A method in which the above VFL process response message includes information regarding the validity time for the new external NWDAF ID.
13. In Paragraph 9 or 10, The above VFL server AF further includes the step of determining the validity time for the above VFL association ID, and A method in which the first request message includes information about the determined validity time for the VFL association ID.
14. In Paragraph 13, The above VFL server AF further includes the step of determining a new validity time for the above VFL association ID, and The above second request message is a method that includes information about the determined new validity time for the above VFL association ID.
15. In any one of paragraphs 9 through 14, The step of the above VFL server AF deciding not to use the above VFL association ID anymore; and A method further comprising the step of, based on the above decision, transmitting information to the NEF that the VFL server AF no longer uses the VFL association ID.
16. As a Network Exposure Function (NEF) that performs communication, At least one transmitter / receiver; It includes at least one processor, The operation performed by the above at least one processor is a method according to any one of claims 1 to 8, NEF.
17. As a VFL server AF performing communication, At least one transmitter / receiver; It includes at least one processor, The operation performed by the above-mentioned at least one processor is a VFL server AF, which is a method according to any one of claims 9 to 15.
18. As an apparatus in mobile communication, At least one processor; and It includes at least one memory that stores instructions and is operablely electrically connected to at least one processor, and A device in which the operation performed based on the execution of the above instruction by the at least one processor is a method according to any one of claims 1 to 8.
19. A non-volatile computer-readable storage medium that records instructions, A non-volatile computer-readable storage medium that, when the above instructions are executed by one or more processors, causes the one or more processors to perform a method according to any one of claims 1 through 8.
Citation Information
Patent Citations
Method for improving fidelity of simulator
KR1020230026770A
Diaphragm sheet for solar cell module laminating process and laminating apparatus including the same
KR102215257B1