WO2024101729A1 - 무선 통신 시스템에서 페이징 절차를 위한 방법 및 장치 - Google Patents
무선 통신 시스템에서 페이징 절차를 위한 방법 및 장치 Download PDFInfo
- Publication number
- WO2024101729A1 WO2024101729A1 PCT/KR2023/016744 KR2023016744W WO2024101729A1 WO 2024101729 A1 WO2024101729 A1 WO 2024101729A1 KR 2023016744 W KR2023016744 W KR 2023016744W WO 2024101729 A1 WO2024101729 A1 WO 2024101729A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- base station
- period
- data
- mobility data
- mobility
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W68/00—User notification, e.g. alerting and paging, for incoming communication, change of service or the like
- H04W68/02—Arrangements for increasing efficiency of notification or paging channel
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W60/00—Affiliation to network, e.g. registration; Terminating affiliation with the network, e.g. de-registration
- H04W60/04—Affiliation to network, e.g. registration; Terminating affiliation with the network, e.g. de-registration using triggered events
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W68/00—User notification, e.g. alerting and paging, for incoming communication, change of service or the like
- H04W68/04—User notification, e.g. alerting and paging, for incoming communication, change of service or the like multi-step notification using statistical or historical mobility data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W68/00—User notification, e.g. alerting and paging, for incoming communication, change of service or the like
- H04W68/06—User notification, e.g. alerting and paging, for incoming communication, change of service or the like using multi-step notification by changing the notification area
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/02—Processing of mobility data, e.g. registration information at HLR [Home Location Register] or VLR [Visitor Location Register]; Transfer of mobility data, e.g. between HLR, VLR or external networks
Definitions
- This disclosure relates to wireless communication systems, and more particularly to methods and devices for reducing paging load.
- the 5G communication system or pre-5G communication system is called a Beyond 4G Network communication system or a Post LTE (Long Term Evolution) system.
- 5G communication systems are being considered for implementation in ultra-high frequency (mmWave) bands (such as the 60 GHz band).
- mmWave ultra-high frequency
- the 5G communication system uses beamforming, massive array multiple input/output (massive MIMO), and full dimension multiple input/output (FD-MIMO). ), array antenna, analog beamforming, and large scale antenna technologies are being discussed.
- the 5G communication system includes advanced small cells, advanced small cells, cloud radio access networks (cloud RAN), ultra-high density networks, and devices.
- D2D Device to Device communication
- wireless backhaul moving network
- cooperative communication Coordinated Multi-Points (CoMP)
- CoMP Coordinated Multi-Points
- interference cancellation etc.
- the 5G system uses FQAM (Hybrid Frequency Shift Keying and Quadrature Amplitude Modulation) and SWSC (Sliding Window Superposition Coding), which are advanced coding modulation (ACM) methods, and FBMC (Filter Bank Multi Carrier), which is an advanced access technology. ), NOMA (Non Orthogonal Multiple Access), and SCMA (Sparse Code Multiple Access) are being developed.
- FQAM Hybrid Frequency Shift Keying and Quadrature Amplitude Modulation
- SWSC Small Cell Multi Carrier
- NOMA Non Orthogonal Multiple Access
- SCMA Synchrom Code Multiple Access
- a plurality of terminals registered with an access and mobility management function (AMF) Receiving mobility data related to the movement frequency of the plurality of terminals from a learning algorithm learned to derive a candidate paging area based on the mobility data and mobility data for a first period among the mobility data, 1 Deriving a candidate paging area, determining reliability of the derived first candidate paging area using test data for the first period, and based on the reliability, a paging message transmitted from the network node identifying at least one base station to receive, and transmitting the paging message to the at least one base station, wherein the test data for the first period includes the plurality of base stations after the first period. It may include mobility data about terminals.
- AMF access and mobility management function
- a network node in a wireless communication system includes at least one transceiver, and at least one processor operably coupled to the at least one transceiver, At least one processor receives mobility data related to the movement frequency of the plurality of terminals from a plurality of terminals registered in the AMF, and uses a learning algorithm learned to derive a candidate paging area based on the mobility data and the mobility data. Based on the mobility data for the first period, a first candidate paging area is derived, using test data for the first period, reliability of the derived first candidate paging area is determined, and the reliability is determined.
- Methods and devices according to various embodiments of the present disclosure can reduce paging load by sequentially attempting paging to base stations where the terminal is likely to move.
- FIG. 1 illustrates the configuration of a wireless communication system according to various embodiments of the present disclosure.
- Figure 2 shows the configuration of a terminal in a wireless communication system according to various embodiments of the present disclosure.
- Figure 3 shows the configuration of a base station in a wireless communication system according to various embodiments of the present disclosure.
- FIG. 4 illustrates the configuration of an access and mobility management function (AMF) according to various embodiments of the present disclosure.
- AMF access and mobility management function
- Figure 5 illustrates the mobility of a terminal between base stations according to various embodiments of the present disclosure.
- FIG. 6 shows a transition probability matrix according to various embodiments of the present disclosure.
- FIG. 7 illustrates a smart paging algorithm according to various embodiments of the present disclosure.
- FIG. 8 illustrates a candidate tracking area (TA) through machine learning according to various embodiments of the present disclosure.
- Figure 9 shows performance evaluation results according to various embodiments of the present disclosure.
- FIG. 10 illustrates the configuration of a network entity for smart paging according to various embodiments of the present disclosure.
- Figure 11 shows the operation sequence of AMF for smart paging according to various embodiments of the present disclosure.
- FIG. 12 illustrates an AI (artificial intelligence)-based performance evaluation sequence according to various embodiments of the present disclosure.
- the base station is an entity that performs resource allocation for the terminal and may be at least one of gNode B, eNode B, Node B, BS (Base Station), wireless access unit, base station controller, or node on the network.
- a terminal may include a user equipment (UE), a mobile station (MS), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing communication functions.
- UE user equipment
- MS mobile station
- UL uplink
- UL refers to a wireless transmission path of a signal transmitted from a terminal to a base station.
- LTE or LTE-A system may be described below as an example, embodiments of the present disclosure can also be applied to other communication systems with similar technical background or channel types.
- this may include the 5th generation mobile communication technology (5G, new radio, NR) developed after LTE-A, and the term 5G hereinafter may also include the existing LTE, LTE-A, and other similar services.
- 5G new radio
- this disclosure may be applied to other communication systems through some modifications without significantly departing from the scope of the present disclosure at the discretion of a person with skilled technical knowledge.
- each block of the processing flow diagrams and combinations of the flow diagram diagrams can be performed by computer program instructions.
- These computer program instructions can be mounted on a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, so that the instructions performed through the processor of the computer or other programmable data processing equipment are described in the flow chart block(s). It creates the means to perform functions.
- These computer program instructions may also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular manner, so that the computer-usable or computer-readable memory
- the instructions stored in may also produce manufactured items containing instruction means that perform the functions described in the flow diagram block(s).
- Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a process that is executed by the computer, thereby generating a process that is executed by the computer or other programmable data processing equipment. Instructions that perform processing equipment may also provide steps for executing the functions described in the flow diagram block(s).
- each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s).
- each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s).
- 'unit or part' used in this disclosure refers to software or a hardware component such as a field-programmable gate array (FPGA) or application specific integrated circuit (ASIC), and 'unit' refers to a specific unit or part. Can be configured to perform roles.
- ' ⁇ part' is not limited to software or hardware.
- ' ⁇ part' may be configured to reside on an addressable storage medium and may be configured to execute one or more processors. Therefore, as an example, ' ⁇ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
- components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card. Additionally, in an embodiment, ' ⁇ unit' may include one or more processors and/or devices.
- 3GPP 3rd Generation Partnership Project Long Term Evolution
- 5G Fifth Generation Partnership Project
- NR Long Term Evolution
- LTE Long Term Evolution
- present disclosure is not limited by terms and names, and can be equally applied to systems that comply with other standards.
- connection node a term referring to network entities
- a term referring to messages a term referring to an interface between network objects
- various identification information a term referring to an interface between network objects. Terms are illustrated for convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms referring to objects having equivalent technical meaning may be used.
- This disclosure relates to a machine learning method and device for reducing paging load in a wireless communication system.
- a network node e.g., a mobility management entity (MME) or an access and mobility management function (AMF)
- MME mobility management entity
- AMF access and mobility management function
- a technique for reducing paging load by transmitting a paging message is explained.
- the base station to which the terminal is expected to move that is, the base station transmitting the paging message, is referred to as a paging base station.
- 1 shows an example of a wireless communication system according to various embodiments of the present disclosure. 1 shows some of the nodes that use a wireless channel in a wireless communication system, including AMF 130, base station 112, base station 114, base station 116, base station 122, base station 124, and base station. (126), exemplifies the terminal 140.
- the terminal 140 is a device used by a user and can communicate through a wireless channel formed with the base stations 112, 114, 116, 122, 124, and 126, that is, an access network. .
- the terminal 140 may be operated without user involvement. That is, at least one of the terminals 140 is a device that performs machine type communication (MTC) and may not be carried by the user.
- the terminal 140 is a 'terminal', 'user equipment (UE)', 'mobile station', 'subscriber station', and 'customer premises equipment (CPE). )', 'remote terminal', 'wireless terminal', 'vehicle terminal', 'user device' or other terms with equivalent technical meaning. You can.
- Base stations 112, 114, 116, 122, 124, and 126 are network infrastructure that provides wireless connectivity. Base stations 112, 114, 116, 122, 124, and 126 have coverage defined as a certain geographic area based on the distance over which signals can be transmitted. Hereinafter, the term 'coverage' used may refer to a service coverage area in the base stations 112, 114, 116, 122, 124, and 126.
- the base stations 112, 114, 116, 122, 124, and 126 may cover one cell or multiple cells. Here, multiple cells can be divided by the frequency they support and the area of the sector they cover.
- the base stations 112, 114, 116, 122, 124, and 126 are 'access point (AP)', 'eNodeB (eNB)', and 5G node ( 5th generation node). ', '5G NodeB', 'gNB (next generation node B)', 'wireless point', 'transmission/reception point (TRP)', 'distributed unit , DU)', 'radio unit (RU)', remote radio head (RRH), or other terms with equivalent technical meaning.
- base stations 112, 114, 116, 122, 124, and 126 may be connected to one or more TRPs.
- the base stations 112, 114, 116, 122, 124, and 126 may transmit a downlink signal or receive an uplink signal to the electronic device 101 through one or more TRPs.
- the AMF 130 provides functions for terminal access and mobility management, and each terminal can be basically connected to one AMF.
- the AMF 130 provides signaling between core network nodes for mobility between 3 rd generation partnership project (3GPP) access networks, and a CP interface between radio access networks (e.g., 5G radio access network (RAN)).
- 3GPP 3 rd generation partnership project
- RAN 5G radio access network
- N2 interface radio access networks
- NAS signaling with the terminal 101 identification of the SMF
- provision of delivery of a session management message between the terminal and the SMF may be performed.
- Some or all of the functions of AMF can be supported within a single instance of AMF.
- the terminal 101 can transmit or receive messages through the AMF 130 and NAS signaling.
- NAS signaling may refer to a functional layer for exchanging signaling and traffic messages between a terminal and the core network in the 5GS (5G system) protocol stack.
- the terminal 101 can transmit a message to the AMF or receive a message from the AMF via the base station.
- the base station may transmit the message to the terminal 101 or the AMF without interpreting it. Mobility of the terminal 101 may be supported through NAS signaling.
- AMF Access Mobility Management Entity
- LTE long term evolution
- MME mobility management entity
- the communication system includes a stand alone (SA) deployment structure that performs communication only with 5G communication entities, or an NSA (NSA) that uses 4G entities and 5G entities for 5G communication. It may also include a non-stand alone) batch structure.
- the communication system of the present disclosure may include a network deployment structure composed of 4G entities.
- SA stand alone
- NSA NSA
- the present disclosure describes embodiments assuming a 5G communication network, but if the same concept is applicable to other systems within a range that can be understood by those with ordinary skill in the art, other systems may be applied.
- Figure 2 shows the configuration of a terminal according to various embodiments of the present disclosure.
- the configuration illustrated in FIG. 3 can be understood as the configuration of the terminal 101 in FIG. 1.
- Terms such as '... unit' and '... unit' used hereinafter refer to a unit that processes at least one function or operation, and may be implemented as hardware, software, or a combination of hardware and software. .
- the terminal 101 may include a communication unit 210, a storage unit 220, and a control unit 230.
- the communication unit 210 may perform functions for transmitting and receiving signals through a wireless channel.
- the communication unit 210 may perform a conversion function between a baseband signal and a bit string according to the physical layer standard of the system.
- the communication unit 210 may generate complex symbols by encoding and modulating the transmission bit string.
- the communication unit 210 can restore the baseband signal to a received bit stream through demodulation and decoding.
- the communication unit 210 may up-convert the baseband signal into a radio frequency (RF) band signal and transmit it through an antenna, and down-convert the RF band signal received through the antenna into a baseband signal.
- the communication unit 210 may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), etc.
- DAC digital-to-analog converter
- ADC analog-to-digital converter
- the communication unit 210 may include multiple transmission and reception paths. Furthermore, the communication unit 210 may include an antenna unit. The communication unit 210 may include at least one antenna array composed of multiple antenna elements. In terms of hardware, the communication unit 210 may be composed of digital and analog circuits (eg, radio frequency integrated circuit (RFIC)). Here, the digital circuit and analog circuit can be implemented in one package. Additionally, the communication unit 210 may include multiple RF chains. The communication unit 210 may perform beamforming. The communication unit 210 may apply a beamforming weight to the signal to be transmitted and received in order to give directionality according to the settings of the control unit 230.
- RFIC radio frequency integrated circuit
- the communication unit 210 can transmit and receive signals.
- the communication unit 210 may include at least one transceiver.
- the communication unit 210 may receive a downlink signal.
- the downlink signal may include a synchronization signal, a reference signal, a configuration message, control information, or downlink data.
- the communication unit 210 can transmit an uplink signal.
- Uplink signals may include random access-related signals (e.g., random access preamble (RAP), Msg3 (message 3)), reference signals, power headroom report (PHR), etc. there is.
- RAP random access preamble
- Msg3 messagessage 3
- PHR power headroom report
- the communication unit 210 may include different communication modules to process signals in different frequency bands. Furthermore, the communication unit 210 may include multiple communication modules to support multiple different wireless access technologies. For example, different wireless access technologies include bluetooth low energy (BLE), wireless fidelity (Wi-Fi), WiFi gigabyte (WiGig), and cellular networks (e.g., long term evolution (LTE), new radio (NR)). ), etc. may be included. Additionally, different frequency bands may include super high frequency (SHF) (e.g., 2.5 GHz, 5 GHz) bands and millimeter wave (e.g., 38 GHz, 60 GHz, etc.) bands. . In addition, the communication unit 210 uses the same wireless access technology on different frequency bands (e.g., unlicensed band for licensed assisted access (LAA), citizens broadband radio service (CBRS) (e.g., 3.5 GHz)). You can also use .
- different wireless access technologies include bluetooth low energy (BLE), wireless fidelity (Wi-Fi), WiFi gigabyte (WiGig), and
- the communication unit 210 can transmit and receive signals as described above. Accordingly, all or part of the communication unit 210 may be referred to as a 'transmitting unit', a 'receiving unit', or a 'transmitting/receiving unit'. Additionally, in the following description, transmission and reception performed through a wireless channel may be used to mean that the above-described processing is performed by the communication unit 210.
- the storage unit 220 may store data such as basic programs, application programs, and setting information for the operation of the terminal 101.
- the storage unit 220 may be comprised of volatile memory, non-volatile memory, or a combination of volatile memory and non-volatile memory. Additionally, the storage unit 220 may provide stored data upon request from the control unit 230.
- the control unit 230 can control the overall operations of the terminal 101.
- the control unit 230 may transmit and receive signals through the communication unit 210.
- the control unit 230 can record and read data in the storage unit 220.
- the control unit 230 can perform protocol stack functions required by communication standards.
- the control unit 230 may include at least one processor.
- the control unit 230 may include at least one processor or microprocessor, or may be part of a processor. Additionally, a portion of the communication unit 210 and the control unit 230 may be referred to as CP.
- the control unit 230 may include various modules for performing communication. According to various embodiments, the control unit 230 may control the terminal to perform operations according to various embodiments described later.
- Figure 3 shows the configuration of a base station according to various embodiments of the present disclosure.
- the configuration illustrated in FIG. 2 may be understood as the configuration of the base station 112 in FIG. 1 .
- Terms such as '... unit' and '... unit' used hereinafter refer to a unit that processes at least one function or operation, and may be implemented as hardware, software, or a combination of hardware and software.
- the base station 112 may include a communication unit 310, a backhaul communication unit 320, a storage unit 330, and a control unit 340.
- the communication unit 310 may perform functions for transmitting and receiving signals through a wireless channel. Accordingly, the communication unit 310 may also be called a wireless communication unit. For example, the communication unit 310 may perform a conversion function between a baseband signal and a bit string according to the physical layer standard of the system. For example, when transmitting data, the communication unit 310 may generate complex symbols by encoding and modulating the transmission bit string. Additionally, when receiving data, the communication unit 310 can restore the baseband signal to a received bit stream through demodulation and decoding. Additionally, the communication unit 310 may up-convert the baseband signal into a radio frequency (RF) band signal and transmit it through an antenna, and down-convert the RF band signal received through the antenna into a baseband signal. To this end, the communication unit 310 may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), etc.
- RF radio frequency
- the communication unit 310 may include multiple transmission and reception paths. Furthermore, the communication unit 310 may include at least one antenna array composed of multiple antenna elements. In terms of hardware, the communication unit 310 may be composed of a digital unit and an analog unit, and the analog unit is composed of a number of sub-units depending on operating power, operating frequency, etc. It can be.
- the communication unit 310 can transmit and receive signals.
- the communication unit 310 may include at least one transceiver.
- the communication unit 310 may transmit a synchronization signal, reference signal, system information, configuration message, control information, or data. Additionally, the communication unit 310 may perform beamforming.
- the communication unit 310 can transmit and receive signals as described above. Accordingly, all or part of the communication unit 310 may be referred to as a ‘transmitting unit’, a ‘receiving unit’, or a ‘transmitting/receiving unit’. Additionally, in the following description, transmission and reception performed through a wireless channel may be used to mean that the processing as described above is performed by the communication unit 310.
- the backhaul communication unit 320 provides an interface for communicating with other nodes in the network. That is, the backhaul communication unit 320 converts a bit string transmitted from the base station 112 to another node, for example, another access node, another base station, upper node, core network, etc., into a physical signal, and Physical signals can be converted into bit strings.
- the storage unit 330 may store data such as basic programs, application programs, and setting information for operation of the base station 112.
- the storage unit 330 may include memory.
- the storage unit 330 may be comprised of volatile memory, non-volatile memory, or a combination of volatile memory and non-volatile memory. Additionally, the storage unit 330 may provide stored data upon request from the control unit 340.
- the control unit 340 can control the overall operations of the base station 112. For example, the control unit 340 may transmit and receive signals through the communication unit 310 or the backhaul communication unit 320. Additionally, the control unit 340 can write and read data to and from the storage unit 330. Additionally, the control unit 340 can perform protocol stack functions required by communication standards. For this purpose, the control unit 340 may include at least one processor.
- the configuration of the base station 112 shown in FIG. 3 is only an example of a base station, and examples of base stations that perform various embodiments of the present disclosure are not limited to the configuration shown in FIG. 3. That is, according to various embodiments, some configurations may be added, deleted, or changed.
- the base station is described as one entity, but the present disclosure is not limited to this.
- a base station may be implemented to form an access network with distributed deployment as well as integrated deployment.
- the base station is divided into a central unit (CU) and a digital unit (DU), with the CU performing upper layer functions (e.g., packet data convergence protocol (PDCP), radio resource control (RRC)), and the DU
- the DU of the base station may be implemented to perform lower layer functions (e.g., medium access control (MAC), physical (PHY)).
- MAC medium access control
- PHY physical
- FIG. 4 illustrates the configuration of an access and mobility management function (AMF) according to various embodiments of the present disclosure.
- the configuration illustrated in FIG. 4 may be understood as AMF 130 of FIG. 1 .
- Terms such as '... unit' and '... unit' used hereinafter refer to a unit that processes at least one function or operation, and may be implemented as hardware, software, or a combination of hardware and software.
- the AMF may include a communication unit 410, a storage unit 420, and a control unit 430.
- the communication unit 410 may perform functions for transmitting and receiving signals in a wired communication environment.
- the communication unit 410 may include a wired interface for controlling direct connection between devices through a transmission medium (eg, copper wire, optical fiber).
- a transmission medium eg, copper wire, optical fiber
- the communication unit 410 may transmit an electrical signal to another device through a copper wire or perform conversion between an electrical signal and an optical signal.
- the communication unit 410 can transmit and receive signals between network entities forming a core network according to wired communication interface standards.
- the communication unit 410 may perform functions for transmitting and receiving signals through a wireless channel.
- the communication unit 410 may perform a conversion function between a baseband signal and a bit string according to the physical layer standard of the system.
- the communication unit 410 may generate complex symbols by encoding and modulating the transmission bit string.
- the communication unit 410 can restore the baseband signal to a received bit stream through demodulation and decoding.
- the communication unit 410 may up-convert the baseband signal into a radio frequency (RF) band signal and transmit it through an antenna, and down-convert the RF band signal received through the antenna into a baseband signal.
- the communication unit 410 may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), etc.
- DAC digital-to-analog converter
- ADC analog-to-digital converter
- the communication unit 410 can transmit and receive signals as described above. Accordingly, all or part of the communication unit 410 may be referred to as a ‘transmitting unit’, a ‘receiving unit’, or a ‘transmitting/receiving unit’. Additionally, in the following description, transmission and reception performed through a wireless channel may be used to mean that the processing as described above is performed by the communication unit 410.
- the storage unit 420 may store data such as basic programs, applications, and setting information for the operation of network entities.
- the storage unit 420 may be comprised of volatile memory, non-volatile memory, or a combination of volatile memory and non-volatile memory. Additionally, the storage unit 420 may provide stored data upon request from the control unit 430.
- the control unit 430 can control the overall operations of the AMF.
- the control unit 430 may transmit and receive signals through the communication unit 410.
- the control unit 430 can write and read data into the storage unit 420.
- the control unit 430 can perform protocol stack functions required by communication standards.
- the protocol stack may be included in the communication unit 410.
- the control unit 430 may include at least one processor.
- AMF may be a network entity that manages the mobility of the terminal.
- AMF can identify the location of a terminal based on a tracking area (TA), which is a set of one or more cells.
- TA tracking area
- RRC radio resource control
- the AMF can know the location of the terminal on a cell basis.
- the core network recognizes that the core and the terminal are connected, and since RAN (radio access network) paging is performed, the AMF is also in the terminal's You can know the location.
- the terminal is in the RRC idle state, the AMF only knows the registered TA and does not know the location of the terminal, so the AMF may need to transmit a paging message to connect to the terminal.
- a conventional paging method (for example, paging order 3) is described with reference to FIG. 1 as follows. In the description below, it can be assumed that TA1 (110) and TA2 (120) are included in the TAL.
- AMF 130 may transmit a first paging message to the base station 112 that terminal 101 last connected to. If there is no response to the first paging message, the AMF 130 may transmit a second paging message to the base stations 112, 114, and 116 included in TA1 110 to which the base station 112 belongs. If there is no response to the second paging message, the AMF 130 will transmit a third paging message to the base stations 112, 114, 116, 122, 124, and 126 included in the TAL to which the base station 112 belongs. You can.
- the AMF includes the base station that most recently transmitted a paging message (hereinafter referred to as the reference base station), base stations belonging to the TA of the reference base station (hereinafter referred to as the reference TA), and base stations belonging to the TAL of the reference TA (hereinafter referred to as the reference TAL).
- Paging messages can be sequentially transmitted to base stations.
- the first may be a tracking area update (TAU) load where the terminal reports its location to the AMF. For example, if the number of cells included in the TA is small, the energy consumption of the terminal may be high due to frequent TAU.
- the second may be the paging load transmitted by the AMF to the terminal. For example, if a large number of base stations included in the TA are configured, the number of paging messages (e.g., S1 application protocol (S1AP) or NG application protocol (NGAP)) may increase, consuming a lot of network resources. . That is, the TAU load and paging load are affected by the configuration of the TA and may be in a trade-off relationship. Therefore, there is a need to reduce resource waste by reducing the number of unnecessary paging message transmissions within the network.
- S1AP S1 application protocol
- NGAP NG application protocol
- the present disclosure relates to a method and apparatus for reducing paging load by obtaining the optimal number of base stations (ie, paging base stations) for paging message transmission in each step. If the paging attempt by all paging base stations fails in this step, AMF configures the paging base stations again in the next step. At this time, since the range of the paging base station increases as the stage progresses, it may be required to design which base station to set as the paging base station in a specific stage, considering the total number of paging messages.
- base stations ie, paging base stations
- the minimum paging load can be obtained by sequentially attempting paging to base stations with a high probability of movement.
- the paging order of the present disclosure may be limited.
- the paging order is described as 3 as an example, but embodiments of the present disclosure are not limited thereto.
- the paging order is
- the network entity may be AMF.
- the number of paging messages generated in the AMF 130 is defined as an objective function, and a procedure for minimizing the number of paging messages based on the objective function is described.
- AMF 130 may acquire mobility data.
- the AMF 130 may obtain mobility data from a plurality of terminals registered with the AMF.
- mobility data may include data on the actual movement frequency of all terminals registered in the AMF moving from a specific base station to the same or different base station.
- Figure 5 illustrates the mobility of a terminal between base stations according to various embodiments of the present disclosure.
- the mobility of the terminal may mean the probability of the terminal moving between base stations.
- the probability that a terminal moves from one base station to another within n base stations can be expressed as P.
- UE mobility is not limited to only including the probability that the UE moves from one base station to another base station.
- the mobility of the terminal may include the probability that the terminal moves within one base station belonging to n base stations.
- FIG. 6 shows a transition probability matrix according to various embodiments of the present disclosure.
- a transition probability matrix can be represented.
- the above-described mobility of the terminal that is, the probability of the terminal moving from one base station to another base station within n base stations and the probability of the terminal moving within one base station may be a function representing the probability of the terminal moving within one base station as a matrix.
- AMF 130 can obtain movement probability.
- the AMF 130 may obtain a movement probability based on a Markov model.
- the AMF 130 may obtain the probability of movement of the terminal based on the acquired mobility data. For example, when moving from base station j to base station k, the probability can be expressed as P j,k .
- the AMF 130 may obtain P , which is a movement probability matrix, based on the acquired mobility data.
- the AMF 130 may obtain a sequence for the probability that the terminal moves from base station j, which was last registered with the AMF 130, to base station k.
- the sequence for the probability of moving from base station j to base station k is It can be expressed as
- the base station j that the terminal last registered with the AMF 130 may be the base station that the terminal in the RRC connected state was connected to before switching to the RRC idle state.
- the base station j that the terminal last registered with the AMF 130 may be the base station that the terminal in the RRC inactive state was connected to before switching to the RRC idle state.
- the AMF 130 may obtain a partial sequence excluding the case where the terminal does not move from base station j.
- the partial sequence is It can be expressed as
- subsequence may be a sequence sorted in descending order (i.e. ).
- Obtained partial sequence Based on, if the terminal leaves base station j, the base station The probability of moving to can be determined. For example, if the terminal leaves base station j, the base station Probability of moving to ( ) can be expressed as the equation below.
- equation 1 may represent the probability of leaving base station j. That is, since the primary paging message is transmitted only to base station j, is the probability that the first paging fails ( ) can be expressed.
- the failure probability of secondary paging can be expressed using . for example, If defined as , the probability of secondary paging failing ( ) can be expressed as the equation below.
- Equation 3 It can be. thus, may be a strictly decreasing function in the interval [0, M-1]. Additionally, referring to Equation 4 below, may be a convex function.
- AMF 130 may determine an objective function. According to one embodiment, the AMF 130 may determine an objective function based on movement probability. According to one embodiment, the objective function may represent the number of paging messages transmitted by the AMF 130.
- the generalized objective function ( ) can be defined as the equation below.
- the base stations selected for paging are It can be determined from the definition of (e.g., sorted in descending order starting from the gNB with the highest probability of moving). Accordingly, once the number of base stations to transmit the paging message in each paging order (h) is determined, the number of base stations to transmit the paging message can be determined.
- the number of paging messages transmitted by the AMF 130 in paging orders 2 and 3 can be defined as the equation below.
- the AMF 130 transmits primary paging only to base station j, It can be. If primary paging fails, secondary paging is performed. Is It can be decided based on .
- the AMF 130 determines the number of base stations to transmit a paging message in paging order 2 ( ), the base stations that will transmit the paging message, that is, the paging base stations, can be identified.
- the number of base stations to transmit a paging message ( ) the following equation can be defined.
- AMF 130 may determine the number of base stations to transmit the paging message. According to one embodiment, the AMF 130 may determine the number of base stations to transmit a paging message through a machine learning algorithm. According to one embodiment, the AMF 130 sets the initial value of the number of base stations ( ) and the initial value of the objective function accordingly ( ), the machine learning algorithm can be started. At this time, the number of base stations ( ) may be input data of the objective function. According to one embodiment, the AMF 130 may estimate the number of base stations in the next learning order. For example, the equation for estimating the number of base stations in the next learning order can be defined as follows.
- the AMF 130 may set the value of the objective function of the next learning order.
- the AMF 130 may set the value of the objective function of the next learning order based on the result of comparing the value of the objective function of the estimated next learning order with the value of the objective function of the current learning order. .
- AMF 130 estimates the value of the objective function of the next learning order ( ) and the value of the objective function of the current learning order ( ) can be set as the value of the objective function of the next learning order. That is, the value of the objective function represents the number of paging messages, so the number of base stations ( ) can be set in a direction that minimizes the value of the objective function.
- the equation for setting the objective function of the next learning order can be defined as follows.
- AMF 130 may determine the number of base stations in the next learning order. According to one embodiment, the AMF 130 may determine the number of base stations in the next learning order based on a result of comparing the value of the objective function of the estimated next learning order with the value of the objective function of the current learning order. For example, when the objective function of the estimated next learning order is smaller than the objective function of the current learning order, the AMF 130 divides the number of base stations of the estimated next learning order in Equation 10 into the number of base stations of the next learning order. You can decide ( ). That is, since learning has been performed in a way that reduces the number of paging messages, the AMF 130 can determine the number of base stations in the estimated next learning order as the number of base stations for next learning.
- the AMF 130 may determine the number of base stations in the current learning order as the number of base stations in the next learning order. (for example, ). That is, when the value of the objective function increases, the AMF 130 increases the number of base stations ( ) may not be updated.
- the AMF 130 performs an operation to minimize the number of paging messages described above a specified number of times (e.g., ) can be repeated as many times as At this time, may be a pre-designated value representing the number of repetitions required to minimize the number of paging messages transmitted by the AMF 130.
- Can be determined based on the number of base stations included in the TA.
- Can be determined based on the number of base stations included in the TAL.
- FIG. 7 illustrates a smart paging algorithm according to various embodiments of the present disclosure.
- the algorithm of FIG. 7 may be called a smart paging algorithm.
- the algorithm is not limited to any one name.
- AMF 130 may identify base stations to transmit a paging message. According to one embodiment, the AMF 130 may identify base stations to transmit a paging message based on the partial sequence sorted in descending order from the base station with the highest probability of movement and the number of base stations to transmit the paging message. According to one embodiment, a partial sequence sorted in descending order starting from the base station with the highest probability of movement may be identified for each paging order. According to one embodiment, the number of base stations to transmit a paging message can be identified for each paging order. According to one embodiment, the AMF 130 may sequentially transmit paging messages to identified base stations according to the paging order. According to one embodiment, the paging message may be transmitted by broadcasting. That is, when the primary paging fails, the AMF 130 transmits the paging message only to the identified optimal base stations instead of transmitting the paging message to all base stations belonging to the TA or TAL, thereby reducing the paging load. .
- AMF performing the operations as a mobility management entity.
- another core network entity eg, MME
- MME may perform the following operations.
- some of the above-described operations may be performed in the AMF, and others may be performed in an external device (eg, a server) connected to the AMF.
- the above-described operations that is, paging base station design operations for each order, are performed in an external device, and the AMF may obtain and apply only the performance results.
- Figure 8 illustrates a candidate TA through machine learning according to various embodiments of the present disclosure.
- TA3 may be a new candidate TA that includes at least one base station identified through the above-described procedures (eg, smart paging algorithm) among the base stations included in TA1 and TA2.
- the candidate TA may refer to the TA predicted by AMF (or MME) through the above-described procedures.
- Figure 9 shows performance evaluation results according to various embodiments of the present disclosure.
- Methods for evaluating the reliability of base stations that will transmit a paging message derived by the algorithm of FIG. 7 can be described.
- Methods for evaluating the reliability of base stations that will transmit paging messages may be methods for evaluating the performance of the machine learning results (eg, smart paging algorithm) of FIG. 7 described above.
- the machine learning results eg, smart paging algorithm
- the source base station (eg, source gNB) that provides services to the terminal before the terminal moves may be set to X.
- Area.ML.X (eg, based on gNB X) may mean a set of predicted gNBs derived through a proposed algorithm (eg, smart paging algorithm).
- Area.ML.X may mean a set of optimized (or predicted) destination base stations (eg, destination gNB) for source gNB X.
- Area.Real.X (for example, based on gNB X) may be a set of base stations to which the terminal actually moved.
- it may mean a set of destination base stations (eg, destination gNB) that actually sent a paging response to a source base station (eg, source gNB X). and may mean the relationship concentration (or cardinality) of the set, that is, the number of elements included in the set. for example, It can be.
- the performance evaluation method for machine learning results can be expressed as the following equation.
- Equation 12 may mean the number of base stations to which the terminal actually moved among the base stations (e.g., gNB) included in the predicted paging area divided by the base station (e.g., gNB) to which the terminal actually moved. .
- Eval_succ is evaluated based on the area the terminal moved to, and can be evaluated through very fast calculations.
- Equation 13 can mean the total number of times the terminal moves to base stations corresponding to the intersection of the set of predicted base stations and the set of base stations to which the terminal actually moved divided by the total number of times the terminal moved to the base stations to which it actually moved. there is.
- Eval_succ_weight may be a more accurate performance evaluation method because it includes the total number of actual UE movements.
- the results of the performance evaluation (e.g., Eval_succ_weight) derived based on Equation 13 can represent more accurate result values than the results of the performance evaluation (e.g., Eval_succ) derived based on Equation 12. .
- the performance evaluation method for machine learning may not have to be evaluated only using the performance evaluation method of Equation 13 described above. Additionally, the above-described performance evaluation methods are merely examples, and the performance evaluation method for machine learning may be evaluated by methods other than Equation 12 or Equation 13 described above. In addition, both the performance evaluation methods according to Equation 12 and Equation 13 described above may be considered.
- evaluation of the predicted paging area through machine learning can be performed by an AI model.
- the AI model for determining the reliability of the predicted paging area derived through machine learning can perform operations to increase the reliability of the predicted paging area through the above-described machine learning based on the results of the performance evaluation.
- the AMF determines that the result of the performance evaluation derived by at least one of the above-described performance evaluation methods is less than or equal to an arbitrary threshold (for example, the lowest threshold of performance determined by the network operator).
- the AI model can enable AMF to re-perform the aforementioned smart paging algorithm based on more mobility data.
- an AI model may allow AMF to derive a new predicted paging area using mobility data for a longer period than the mobility data used to derive the predicted paging area being evaluated. At this time, mobility data for a longer period may mean mobility data of the terminal accumulated over a longer period of time.
- the AMF when the result value of the performance evaluation derived by at least one of the above-described performance evaluation methods is greater than an arbitrary threshold (e.g., the lowest threshold of performance determined by the network operator), the AMF The AI model can enable AMF to perform paging procedures based on already derived predicted paging areas. However, the AI model may allow AMF to perform a paging procedure based on the derived expected paging area even if the result value of the performance evaluation derived by at least one of the above-mentioned performance evaluation methods is equal to an arbitrary threshold value. there is.
- an arbitrary threshold e.g., the lowest threshold of performance determined by the network operator
- the AI model may determine whether to perform the above-described operations based on requirements including at least one of an arbitrary threshold, the communication environment of the cell where the terminal is located, or the average movement area distribution of the terminals. Additionally, the AI model may be included in the control unit 430 of the AMF, and operations of the AI model may be performed by at least one processor included in the control unit 430. Alternatively, the AI model may be included in a network entity included in the AMF separately from the control unit 430 of the AMF.
- FIG. 10 illustrates the configuration of a network entity for smart paging according to various embodiments of the present disclosure.
- configurations of a network entity eg, control unit 430 that performs a smart paging operation and interactions between configurations may be described.
- the call processing module 1010 can collect the mobility of the terminal and transmit the collected data to the communication module 1020 of the machine learning server (ML server).
- ML server machine learning server
- the communication module 1020 may transmit collected data (eg, mobility data) received from the call processing module 1010 to the data processing module 1030. Additionally, the communication module 1020 may transmit information about the optimized paging area for each base station received from the training & evaluation module 1060 to the call processing module 1010.
- collected data eg, mobility data
- the communication module 1020 may transmit information about the optimized paging area for each base station received from the training & evaluation module 1060 to the call processing module 1010.
- the data processing module 1030 may periodically merge collected data (eg, mobility data) received from the communication module 1020 and store them on the disk 1080.
- collected data eg, mobility data
- the DB manager module 1070 can read network configuration information (for example, including at least one of gNB, TA, or TAL settings) stored in the DB, and the read network configuration information can be read by the learning & evaluation module 1060. It can be passed on.
- network configuration information for example, including at least one of gNB, TA, or TAL settings
- the training & evaluation module 1060 can perform machine learning algorithm operations and evaluation operations based on data stored in the disk 1080.
- the learning & evaluation module 1060 can periodically store the predicted paging area in the disk 1080 and transmit it to the communication module 1020.
- the disk manager module 1070 may periodically delete data stored on the disk 1080 according to a set value.
- Figure 11 shows the operation sequence of AMF for smart paging according to various embodiments of the present disclosure.
- the call processing module 1010 may collect mobility data and transmit it to the communication module 1020.
- the data may refer to mobility data transmitted by the terminal through the base station.
- the mobility data of the terminal may be stored in the storage unit 420 of the AMF. Accordingly, the mobility data of the terminal that AMF will use to derive the optimal paging area may be part or all of the mobility data stored in the storage unit 420. Additionally, the overlap period of mobility data for deriving the optimal paging area among the mobility data stored in the storage unit 420 may be determined by an AI model.
- the data processing module 1030 converts the mobility data of the terminal into a form for machine learning (e.g., an objective function ) can be converted to Specifically, the data processing module 1030 may calculate and convert the probability of the terminal moving to the destination base stations based on the source base station. And AMF can create learning data by collecting mobility data (e.g., Equations 1 to 9).
- the training and evaluation module 1060 may perform the smart paging algorithm of FIG. 7 using the refined data output through step 1020 as input data.
- the data output through step 1020 may have various values depending on the overlapping method. For example, there may be a method of overlapping data collected over a week, overlapping data collected over a day, or overlapping three weeks' worth of data on an hourly basis.
- the overlapping method is not limited to the above-described examples, and the data output through step 1020 may be output as overlaid values using various methods other than the above-described examples.
- AMF may request additional information required for learning (e.g., the number of base stations included in the TAL) from the DB manager module 1050.
- the training and evaluation module 1060 may evaluate the reliability of the predicted paging area derived from the learning algorithm in step 1030 through test data (e.g., the example in FIG. 9).
- the optimized paging area derived through the learning algorithm may be affected by the data overlap method.
- the optimized paging area derived through a learning algorithm may have differences in reliability depending on at least one of the period or unit of data overlap.
- step 1150 information about the optimized paging area derived in step 1040 may be transmitted to the call processing module 1010 to perform a paging procedure based on the optimized paging area derived in step 1040.
- FIG. 12 shows a performance evaluation procedure based on artificial intelligence (AI) according to various embodiments of the present disclosure.
- AI artificial intelligence
- the machine learning algorithm of FIG. 12 may include an AI model.
- the AI model may be a model trained to output a predicted paging area using mobility data for a predetermined period and input data generated from the mobility data.
- AMF may receive mobility data from a plurality of terminals registered with AMF.
- the mobility data may include mobility data of a plurality of terminals for a specific period of time in the past (e.g., time before using a learning algorithm to derive a paging area) for all terminals registered with the AMF. .
- AMF may generate input data based on mobility data for a specific period among the collected mobility data. For example, the AMF may select mobility data for a first period from among the received mobility data and generate input data based on the mobility data for the selected first period. At this time, the input data may be data input to perform a learning algorithm. Alternatively, input data may refer to learning data needed for an AI model to derive the optimal predicted paging area based on a learning algorithm.
- AMF may derive a predicted paging area through machine learning based on the generated input data.
- AMF can derive a predicted paging area from input data based on mobility data for the first period by using a learning algorithm learned to derive a predicted paging area based on mobility data.
- AMF may perform a reliability evaluation on the predicted paging area derived through a machine learning algorithm.
- the AMF may determine the reliability of the derived first candidate paging area using test data for the first period.
- Test data for the first period may include mobility data for a plurality of terminals after the first period.
- Mobility data in step 1210 may include mobility data for a first period and a period after the first period, and mobility data for the first period may be input to a learning algorithm and used to derive a candidate paging area. .
- Mobility data after the first period may be used to evaluate the reliability of the candidate paging area derived from the mobility data for the first period.
- the candidate paging area may be used in the same sense as the predicted paging area.
- step 1240 may refer to a performance evaluation operation for a learning algorithm for deriving a predicted paging area. Accordingly, the AI model may evaluate the performance of the learning algorithm and omit, change, and/or add at least one step of the smart paging algorithm of FIG. 7.
- the AMF may check whether the result of the performance evaluation in step 1240 is greater than an arbitrary threshold (for example, the lowest threshold of performance determined by the network operator). If the performance evaluation result value is less than or equal to an arbitrary threshold value, AMF returns to step 1220 and performs an operation (e.g., steps 1220 to 1250) to derive a re-optimized paging area based on the new mobility data. You can.
- the AMF may select mobility data for a second period from among mobility data and generate new input data based on the mobility data for the selected second period.
- the mobility data for the second period may mean data that overlaps (or is collected) in a different manner from the mobility data for the first period used to derive the predicted paging area that is the evaluation target.
- the overlapping (or collection) method may be at least one of a method of varying the collection period of mobility data or a method of varying the unit of the collection period.
- step 1260 if the performance evaluation result value is greater than a certain threshold, the AMF can identify base stations included in the candidate (predicted) paging area and perform a paging procedure by transmitting a paging message to the identified base stations.
- the performance evaluation result value is greater than an arbitrary threshold, other requirements (for example, include at least one of the communication environment of the cell where the terminal is located or the distribution of the average moving area of the terminals) ), you may return to step 1220 and perform an operation (for example, steps 1220 to 1250) to derive a re-optimized paging area based on new mobility data.
- the AI model satisfies other requirements (for example, at least one of the communication environment of the cell where the terminal is located or the distribution of the average moving area of the terminals) even if the performance evaluation result value is greater than an arbitrary threshold value. Including), at least one step of the smart paging algorithm of FIG. 7 may be omitted, changed, and/or added. And the AI model can derive the optimal paging area based on the improved smart paging algorithm.
- An AI model may be composed of multiple neural network layers.
- Each of the plurality of neural network layers has a plurality of weight values, and neural network calculation is performed through calculation between the calculation result of the previous layer and the plurality of weights.
- Multiple weights of multiple neural network layers can be optimized based on the learning results of the AI model. For example, a plurality of weights may be updated so that loss or cost values obtained from the AI model are reduced or minimized during the learning process.
- DNN deep neural networks
- CNN Convolutional Neural Network
- DNN Deep Neural Network
- RNN Recurrent Neural Network
- RBM Restricted Boltzmann Machine
- DBN Deep Belief Network
- BNN Bidirectional Recurrent Deep Neural Network
- DNN Deep Q-Networks
- the method according to various embodiments according to the present disclosure has a reduction effect in the number of paging messages.
- the method according to various embodiments of the present disclosure organizes base stations with a high probability of movement of the terminal based on mobility data in descending order and determines the number of base stations to transmit a paging message in the paging order through a machine learning algorithm, The number of paging messages can be reduced. Since the number of paging messages required for mobility management is reduced, the wired and/or wireless resources of the communication network can be operated more efficiently. Additionally, in a 5G communication system in which the number of base stations included in the same area is greater than in the case of LTE, a greater benefit in terms of cost may occur if the same rate of performance gain as that of the LTE communication system is obtained.
- the method of transmitting a paging message to all base stations belonging to the TA and/or TAL may result in a paging load and consume a large amount of network resources. Accordingly, a technology for reducing paging load by transmitting paging messages only to a specific number of base stations with a high probability that the terminal has moved, using terminal mobility data and machine learning algorithms, has been described.
- the base station uses logical channels (e.g., paging control channel (PCCH)), transport channels (e.g., paging channel (PCH)), and physical channels ( For example, this results in a reduction in the number of RRC paging messages transmitted to the terminal through PDSCH (physical downlink shared channel). That is, according to various embodiments of the present disclosure, by reducing the number of unnecessary paging message transmissions. While maintaining or improving service quality, the efficiency of wired and wireless resources required for the operation of a wireless communication system can be increased. Meanwhile, the present disclosure has been described based on a static tracking area list (S-TAL), but may also be applied to a dynamic tracking area list (D-TAL) by expanding the machine learning algorithm.
- S-TAL static tracking area list
- D-TAL dynamic tracking area list
- the data overlap method is diversified through simulation using an AI model, better performance can be achieved in terms of paging success rate.
- a specific number of base stations with a high probability that the terminal has moved can be identified through the terminal's mobility data and a machine learning algorithm, and the data overlap method can be changed through a performance evaluation method through an AI model.
- the optimal paging area can be derived.
- the movement frequency of the plurality of terminals is related to the plurality of terminals registered in the AMF.
- Receiving mobility data deriving a first candidate paging area based on mobility data for a first period of the mobility data and a learning algorithm learned to derive a candidate paging area based on the mobility data, Using test data for a first period, determining reliability of the derived first candidate paging area, based on the reliability, identifying at least one base station to receive a paging message transmitted from the network node. and transmitting the paging message to the at least one base station, wherein the test data for the first period may include mobility data regarding the plurality of terminals after the first period. there is.
- a base station included in the first candidate paging area may be identified as the at least one base station.
- the second period when the reliability is less than a certain threshold, deriving a second candidate paging area based on mobility data for a second period among the mobility data and the learning algorithm, the second period Further comprising: additionally determining reliability of the second candidate paging area using test data for, and additionally identifying the at least one base station based on the additionally determined reliability,
- the test data for two periods may include mobility data regarding the plurality of terminals after the second period.
- deriving the first candidate paging area includes identifying movement probabilities of the plurality of terminals between base stations belonging to the TAL based on mobility data for the first period, It may include generating an objective function based on the identified movement probabilities, and deriving the first candidate paging area using the objective function and the learning algorithm.
- the mobility data for the first period and the mobility data for the second period may be at least one of mobility data collected during different periods or mobility data collected in different time units.
- the objective function may be generated based on the number of paging messages transmitted by the network node.
- the step of identifying movement probabilities of the plurality of terminals between base stations belonging to the TAL includes identifying the base station that transmitted the registration request message received from the plurality of terminals to the network node. , and identifying probabilities of the plurality of terminals moving from a base station registered to the network node to another base station, wherein the other base station may be a base station that is not registered in the network node among base stations belonging to the TAL. .
- the network node may be AMF or MME.
- a network node includes at least one transceiver, and at least one processor operably coupled to the at least one transceiver, and the at least one The processor receives mobility data related to the movement frequency of the plurality of terminals from a plurality of terminals registered in the AMF, a learning algorithm learned to derive a candidate paging area based on the mobility data, and a first of the mobility data.
- test data for the first period is: It may include mobility data regarding the plurality of terminals.
- a base station included in the first candidate paging area may be identified as the at least one base station.
- a second candidate paging area is derived based on mobility data for a second period among the mobility data and the learning algorithm, and in the second period Reliability of the second candidate paging area is additionally determined using test data for the second candidate paging area, and based on the additionally determined reliability, the at least one base station is additionally identified, and the test data for the second period is , may include mobility data regarding the plurality of terminals after the second period.
- the step of deriving the first candidate paging area includes identifying movement probabilities of the plurality of terminals between base stations belonging to the TAL based on mobility data for the first period, and identifying An objective function may be generated based on the movement probabilities, and the first candidate paging area may be derived using the objective function and the learning algorithm.
- the mobility data for the first period and the mobility data for the second period may be at least one of mobility data collected during different periods or mobility data collected in different time units.
- the objective function may be generated based on the number of paging messages transmitted by the network node.
- the at least one processor identifies a base station that transmitted the registration request message received from the plurality of terminals to the network node, and the plurality of terminals are registered from the base station to the network node. Probabilities of moving to another base station are identified, and the other base station may be a base station that is not registered with the network node among base stations belonging to the TAL.
- the network node may be AMF or MME.
- AI-related functions are operated through a processor and memory.
- the processor may consist of one or multiple processors.
- one or more processors may be a general-purpose processor such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-specific processor such as a GPU or VPU (Vision Processing Unit), or an AI-specific processor such as an NPU.
- One or more processors control input data to be processed according to predefined operation rules or AI models stored in memory.
- the AI-specific processors may be designed with a hardware structure specialized for processing a specific AI model.
- Predefined operation rules or AI models are characterized by being created through learning.
- being created through learning means that the basic AI model is learned using a large number of learning data by a learning algorithm, thereby creating a predefined operation rule or AI model set to perform the desired characteristics (or purpose). do.
- This learning may be performed on the device itself on which the AI according to the present disclosure is performed, or may be performed through a separate server and/or system.
- Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.
- a computer-readable storage medium that stores one or more programs (software modules) may be provided.
- One or more programs stored in a computer-readable storage medium are configured to be executable by one or more processors in an electronic device (configured for execution).
- One or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.
- These programs may include random access memory, non-volatile memory, including flash memory, read only memory (ROM), and electrically erasable programmable ROM. (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other forms of disk storage. It can be stored in an optical storage device or magnetic cassette. Alternatively, it may be stored in a memory consisting of a combination of some or all of these. Additionally, multiple configuration memories may be included.
- non-volatile memory including flash memory, read only memory (ROM), and electrically erasable programmable ROM. (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other forms of disk storage. It can be stored in an optical storage device or magnetic cassette. Alternatively, it may be stored in a memory consisting of a combination of some or all of these. Additionally, multiple configuration memories may
- the program may be distributed through a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that is accessible. This storage device can be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to the device performing an embodiment of the present disclosure.
- a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that is accessible. This storage device can be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to the device performing an embodiment of the present disclosure.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
Description
Claims (15)
- 무선 통신 시스템에서 네트워크 노드(network node)가 페이징 메시지를 송신할 기지국을 식별하는 방법에 있어서,AMF(access and mobility management function)에 등록된 복수의 단말들로부터 상기 복수의 단말들의 이동 빈도에 관련된 이동성 데이터를 수신하는 동작;이동성 데이터에 기초하여 후보 페이징 영역을 도출하기 위하여 학습된 학습 알고리즘 및 상기 이동성 데이터 중 제1 기간에 대한 이동성 데이터에 기반하여, 제1 후보 페이징 영역을 도출하는 동작;상기 제1 기간에 대한 테스트 데이터를 이용하여, 상기 도출된 제1 후보 페이징 영역의 신뢰도를 판단하는 동작;상기 신뢰도에 기반하여, 상기 네트워크 노드로부터 송신되는 페이징 메시지를 수신할 적어도 하나의 기지국을 식별하는 동작; 및상기 적어도 하나의 기지국에게 상기 페이징 메시지를 송신하는 동작을 포함하며,상기 제1 기간에 대한 상기 테스트 데이터는, 상기 제1 기간 이후의 상기 복수의 단말들에 관한 이동성 데이터를 포함하는, 방법.
- 청구항 1에 있어서,상기 신뢰도가 임의의 임계 값 이상인 경우, 상기 제1 후보 페이징 영역에 포함된 기지국을 상기 적어도 하나의 기지국으로 식별하는, 방법.
- 청구항 1에 있어서,상기 신뢰도가 임의의 임계 값보다 작은 경우, 상기 이동성 데이터 중 제2 기간에 대한 이동성 데이터 및 상기 학습 알고리즘에 기반하여, 제2 후보 페이징 영역을 도출하는 동작;상기 제2 기간에 대한 테스트 데이터를 이용하여, 상기 제2 후보 페이징 영역의 신뢰도를 추가적으로 판단하는 동작; 및상기 추가적으로 판단된 신뢰도에 기초하여, 상기 적어도 하나의 기지국을 추가로 식별하는 동작을 더 포함하며,상기 제2 기간에 대한 상기 테스트 데이터는, 상기 제2 기간 이후의 상기 복수의 단말들에 관한 이동성 데이터를 포함하는, 방법.
- 청구항 1에 있어서,상기 제1 후보 페이징 영역을 도출하는 동작은,상기 제1 기간에 대한 이동성 데이터에 기반하여, TAL(tracking area list)에 속한 기지국들 간 상기 복수의 단말들의 이동 확률들을 식별하는 동작;상기 식별된 이동 확률들에 기반하여 목적 함수(objective function)을 생성하는 동작; 및상기 목적 함수 및 상기 학습 알고리즘을 이용하여, 상기 제1 후보 페이징 영역을 도출하는 동작을 포함하는, 방법.
- 청구항 3에 있어서,상기 제1 기간에 대한 이동성 데이터와 상기 제2 기간에 대한 이동성 데이터는 서로 다른 기간 동안 수집된 이동성 데이터 또는 서로 다른 시간 단위로 수집된 이동성 데이터 중 적어도 하나인, 방법.
- 청구항 4에 있어서,상기 목적 함수는 상기 네트워크 노드가 전송하는 페이징 메시지의 개수에 기초하여 생성되는, 방법.
- 청구항 4에 있어서,상기 TAL에 속한 기지국들 간 상기 복수의 단말들의 이동 확률들을 식별하는 동작은,상기 복수의 단말들로부터 수신한 등록 요청 메시지를, 상기 네트워크 노드로 송신한 기지국을 식별하는 동작; 및상기 복수의 단말들이 상기 네트워크 노드에 등록된 기지국으로부터 다른 기지국으로 이동할 확률들을 식별하는 동작을 포함하며,상기 다른 기지국은 상기 TAL에 속한 기지국들 중에서 상기 네트워크 노드에 등록되지 않은 기지국인, 방법.
- 청구항 1에 있어서,상기 네트워크 노드는 AMF(access and mobility management function) 엔티티 또는 MME(mobility management entity)인, 방법.
- 네트워크 노드(network node)에 있어서,송수신기; 및상기 송수신기에 결합된 적어도 하나의 프로세서를 포함하고,상기 적어도 하나의 프로세서는,AMF(access and mobility management function)에 등록된 복수의 단말들로부터 상기 복수의 단말들의 이동 빈도에 관련된 이동성 데이터를 수신하고,이동성 데이터에 기초하여 후보 페이징 영역을 도출하기 위하여 학습된 학습 알고리즘 및 상기 이동성 데이터 중 제1 기간에 대한 이동성 데이터에 기반하여, 제1 후보 페이징 영역을 도출하고,상기 제1 기간에 대한 테스트 데이터를 이용하여, 상기 도출된 제1 후보 페이징 영역의 신뢰도를 판단하고,상기 신뢰도에 기반하여, 상기 네트워크 노드로부터 송신되는 페이징 메시지를 수신할 적어도 하나의 기지국을 식별하고,상기 적어도 하나의 기지국에게 상기 페이징 메시지를 송신하며,상기 제1 기간에 대한 상기 테스트 데이터는, 상기 제1 기간 이후의 상기 복수의 단말들에 관한 이동성 데이터를 포함하는, 장치.
- 청구항 9에 있어서,상기 신뢰도가 임의의 임계 값 이상인 경우, 상기 제1 후보 페이징 영역에 포함된 기지국을 상기 적어도 하나의 기지국으로 식별하는, 장치.
- 청구항 9에 있어서,상기 신뢰도가 임의의 임계 값보다 작은 경우, 상기 이동성 데이터 중 제2 기간에 대한 이동성 데이터 및 상기 학습 알고리즘에 기반하여, 제2 후보 페이징 영역을 도출하고,상기 제2 기간에 대한 테스트 데이터를 이용하여, 상기 제2 후보 페이징 영역의 신뢰도를 추가적으로 판단하고,상기 추가적으로 판단된 신뢰도에 기초하여, 상기 적어도 하나의 기지국을 추가로 식별하며,상기 제2 기간에 대한 상기 테스트 데이터는, 상기 제2 기간 이후의 상기 복수의 단말들에 관한 이동성 데이터를 포함하는, 장치.
- 청구항 9에 있어서,상기 적어도 하나의 프로세서는,상기 제1 기간에 대한 이동성 데이터에 기반하여, TAL(tracking area list)에 속한 기지국들 간 상기 복수의 단말들의 이동 확률들을 식별하고,상기 식별된 이동 확률들에 기반하여 목적 함수(objective function)을 생성하고,상기 목적 함수 및 상기 학습 알고리즘을 이용하여, 상기 제1 후보 페이징 영역을 도출하는, 장치.
- 청구항 11에 있어서,상기 제1 기간에 대한 이동성 데이터와 상기 제2 기간에 대한 이동성 데이터는 서로 다른 기간 동안 수집된 이동성 데이터 또는 서로 다른 시간 단위로 수집된 이동성 데이터 중 적어도 하나인, 장치.
- 청구항 12에 있어서,상기 목적 함수는 상기 네트워크 노드가 전송하는 페이징 메시지의 개수에 기초하여 생성되는, 장치.
- 청구항 12에 있어서,상기 적어도 하나의 프로세서는,상기 복수의 단말들로부터 수신한 등록 요청 메시지를, 상기 네트워크 노드로 송신한 기지국을 식별하고,상기 복수의 단말들이 상기 네트워크 노드에 등록된 기지국으로부터 다른 기지국으로 이동할 확률들을 식별하며,상기 다른 기지국은 상기 TAL에 속한 기지국들 중에서 상기 네트워크 노드에 등록되지 않은 기지국이며,상기 네트워크 노드는 AMF(access and mobility management function) 엔티티 또는 MME(mobility management entity)인, 장치.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP23888991.9A EP4601371A4 (en) | 2022-11-07 | 2023-10-26 | METHOD AND APPARATUS FOR A RADIO MESSAGING PROCEDURE IN A WIRELESS COMMUNICATION SYSTEM |
| US19/192,988 US20250261166A1 (en) | 2022-11-07 | 2025-04-29 | Method and apparatus for paging procedure in a wireless communication system |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR20220147255 | 2022-11-07 | ||
| KR10-2022-0147255 | 2022-11-07 | ||
| KR1020220156597A KR20240066020A (ko) | 2022-11-07 | 2022-11-21 | 무선 통신 시스템에서 페이징 절차를 위한 방법 및 장치 |
| KR10-2022-0156597 | 2022-11-21 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US19/192,988 Continuation US20250261166A1 (en) | 2022-11-07 | 2025-04-29 | Method and apparatus for paging procedure in a wireless communication system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024101729A1 true WO2024101729A1 (ko) | 2024-05-16 |
Family
ID=91032800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2023/016744 Ceased WO2024101729A1 (ko) | 2022-11-07 | 2023-10-26 | 무선 통신 시스템에서 페이징 절차를 위한 방법 및 장치 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20250261166A1 (ko) |
| EP (1) | EP4601371A4 (ko) |
| WO (1) | WO2024101729A1 (ko) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20250317896A1 (en) * | 2024-04-03 | 2025-10-09 | Verizon Patent And Licensing Inc. | Systems and methods for adaptive paging |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8565795B2 (en) * | 2008-09-28 | 2013-10-22 | Huawei Technologies Co., Ltd. | Method and apparatus for allocating paging areas |
| KR20220033384A (ko) * | 2020-09-09 | 2022-03-16 | 삼성전자주식회사 | 무선 통신 시스템에서 페이징 부하를 감소시키기 위한 방법 및 장치 |
| KR102405484B1 (ko) * | 2019-12-04 | 2022-06-03 | 세종대학교산학협력단 | 시계열 분석 간편화를 위한 자동화된 딥러닝 스튜디오 |
| KR102408756B1 (ko) * | 2019-03-18 | 2022-06-15 | 미쓰비시덴키 가부시키가이샤 | 이상 검지 장치 및 이상 검지 방법 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10070412B1 (en) * | 2017-04-20 | 2018-09-04 | At&T Intellectual Property I, L.P. | Paging based on individual user mobility patterns |
| CN110505688B (zh) * | 2018-05-18 | 2022-04-29 | 中国移动通信有限公司研究院 | 寻呼方法、装置、系统、网络设备及存储介质 |
| WO2021190768A1 (en) * | 2020-03-27 | 2021-09-30 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods, apparatus and machine-readable media relating to paging in a communications network |
-
2023
- 2023-10-26 EP EP23888991.9A patent/EP4601371A4/en active Pending
- 2023-10-26 WO PCT/KR2023/016744 patent/WO2024101729A1/ko not_active Ceased
-
2025
- 2025-04-29 US US19/192,988 patent/US20250261166A1/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8565795B2 (en) * | 2008-09-28 | 2013-10-22 | Huawei Technologies Co., Ltd. | Method and apparatus for allocating paging areas |
| KR102408756B1 (ko) * | 2019-03-18 | 2022-06-15 | 미쓰비시덴키 가부시키가이샤 | 이상 검지 장치 및 이상 검지 방법 |
| KR102405484B1 (ko) * | 2019-12-04 | 2022-06-03 | 세종대학교산학협력단 | 시계열 분석 간편화를 위한 자동화된 딥러닝 스튜디오 |
| KR20220033384A (ko) * | 2020-09-09 | 2022-03-16 | 삼성전자주식회사 | 무선 통신 시스템에서 페이징 부하를 감소시키기 위한 방법 및 장치 |
Non-Patent Citations (2)
| Title |
|---|
| "3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Study of Enablers for Network Automation for 5G 5G System (5GS); Phase 3 (Release 18)", 3GPP STANDARD; TECHNICAL REPORT; 3GPP TR 23.700-81, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, no. V0.4.0, 6 September 2022 (2022-09-06), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, pages 1 - 257, XP052210688 * |
| See also references of EP4601371A4 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20250317896A1 (en) * | 2024-04-03 | 2025-10-09 | Verizon Patent And Licensing Inc. | Systems and methods for adaptive paging |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4601371A1 (en) | 2025-08-13 |
| EP4601371A4 (en) | 2025-12-24 |
| US20250261166A1 (en) | 2025-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023277454A1 (en) | Method and apparatus for channel environment classification in wireless network system | |
| WO2021194323A1 (ko) | 무선 통신 시스템에서 단말 정책 적용에 따른 세션 관리 방법 | |
| WO2020060143A1 (ko) | 무선 통신 시스템에서 전송 전력을 제어하는 방법 및 장치 | |
| WO2022060186A1 (ko) | 무선 통신 시스템에서 프론트홀 전송을 위한 장치 및 방법 | |
| EP3213424A1 (en) | Method and apparatus for multiuser beamforming in wireless communication systems | |
| WO2024096355A1 (en) | Method and device for reporting csi based on ai model in wireless communication system | |
| WO2022025382A1 (en) | Method and apparatus for doppler pre-compensation | |
| WO2016068521A1 (en) | Method and apparatus for multiuser beamforming in wireless communication systems | |
| WO2021230570A1 (en) | Methods and apparatus for network load balancing optimization | |
| WO2019124957A1 (en) | Apparatus and method for measurement configuration in wireless communication system | |
| WO2023008979A1 (en) | A system and method for communication load balancing in unseen traffic scenarios | |
| WO2022080935A1 (ko) | 무선 통신 시스템에서 하이브리드 빔포밍 통신을 수행하는 방법 및 장치 | |
| WO2019172683A1 (ko) | 무선 통신 시스템에서 시스템 정보를 획득하기 위한 장치 및 방법 | |
| WO2024101729A1 (ko) | 무선 통신 시스템에서 페이징 절차를 위한 방법 및 장치 | |
| WO2019039886A1 (ko) | 무선 통신 시스템에서 대역을 공유하기 위한 장치 및 방법 | |
| WO2010016714A2 (ko) | 무선 통신 시스템에서 인접 셀 간섭을 제거하기 위한 장치 및 그 방법 | |
| WO2023177240A1 (en) | Method and apparatus for an srs procedure | |
| EP4150956A1 (en) | Apparatus and method for load balancing in wireless communication system | |
| WO2024072121A1 (ko) | 무선 통신 시스템에서 상향링크 신호의 동기화를 지원하기 위한 방법 및 장치 | |
| WO2023013854A1 (en) | Method and apparatus of beam management with measurement aging | |
| WO2020076056A1 (ko) | 트래픽 오프로딩을 제어하기 위한 장치 및 방법 | |
| WO2025100829A1 (en) | Method and apparatus for a diffusion model based on a wireless channel estimation | |
| WO2023008956A1 (en) | Method and apparatus for providing uplink signal-based location service | |
| WO2024155156A1 (ko) | 무선 통신 시스템에서 성능 정보의 송수신을 위한 방법 및 장치 | |
| WO2020055137A1 (ko) | 무선 통신 시스템에서 데이터를 송수신하는 방법 및 장치 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23888991 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2023888991 Country of ref document: EP |
|
| ENP | Entry into the national phase |
Ref document number: 2023888991 Country of ref document: EP Effective date: 20250506 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWP | Wipo information: published in national office |
Ref document number: 2023888991 Country of ref document: EP |













