WO2023232227A1 - Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil - Google Patents

Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil Download PDF

Info

Publication number
WO2023232227A1
WO2023232227A1 PCT/EP2022/064727 EP2022064727W WO2023232227A1 WO 2023232227 A1 WO2023232227 A1 WO 2023232227A1 EP 2022064727 W EP2022064727 W EP 2022064727W WO 2023232227 A1 WO2023232227 A1 WO 2023232227A1
Authority
WO
WIPO (PCT)
Prior art keywords
trace
entity
network entity
network
model
Prior art date
Application number
PCT/EP2022/064727
Other languages
English (en)
Inventor
Borislava GAJIC
Anna Pantelidou
Peter Rost
Original Assignee
Nokia Solutions And Networks Oy
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nokia Solutions And Networks Oy filed Critical Nokia Solutions And Networks Oy
Priority to PCT/EP2022/064727 priority Critical patent/WO2023232227A1/fr
Publication of WO2023232227A1 publication Critical patent/WO2023232227A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • 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
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • 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
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/06—Generation of reports
    • H04L43/065—Generation of reports related to network devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports

Definitions

  • the present disclosure relates generally to the field of wireless communications, and particularly to techniques for using extended trace records to collect Machine Learning (ML) data from network entities of a wireless communication network.
  • ML Machine Learning
  • NWDAF Network Data Analytics Function
  • CN Core Network
  • MDT Minimization of Drive Tests
  • the AI/ML algorithms are first trained, for example, by using a simulator that generates synthetic data and models the real behaviour of the wireless communication network; subsequently, the AI/ML algorithms are fine-tuned over the live environment of the wireless communication network. This is a very time-consuming process that also requires human supervision.
  • Radio Access Network (RAN) and CN network entities may have different ML capabilities.
  • RAN Radio Access Network
  • CN Network entities
  • ML capabilities there is no generic framework for utilizing such ML capabilities in the rest of the network entities of the wireless communication network.
  • ML data e.g., inference output data
  • an 0AM entity in a wireless communication network comprises at least one processor and at least one memory.
  • the at least one memory comprises a computer program code.
  • the at least one memory and the computer program code are configured to, with the at least one processor, cause the 0AM entity to operate at least as follows.
  • the 0AM entity is caused to create a trace configuration for at least one network entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a Trace Collection Entity (TCE) during the trace session.
  • TCE Trace Collection Entity
  • the 0AM entity is then caused to transmit the trace configuration to the at least one network entity.
  • trace configuration it is possible to provide a generic framework/means for utilizing ML capabilities of different network entities (e.g., RAN and/or CN entities) in the wireless communication network.
  • the inference output data provided in the trace record(s) from one network entity to the TCE may be then forwarded by the TCE to one or more other network entities for the purpose of improving the overall performance of the wireless communication system.
  • the forwarding of the inference output data may enable the so-called transparent support for ML and provide a means for smooth transition towards a fully ML (native) wireless communication network.
  • the trace configuration further comprises a start trigger event and a stop trigger event.
  • the second instruction causes the at least one network entity to report the at least one trace record to the TCE during the trace session between the start trigger event and the stop trigger event.
  • the trace record(s) may be reported to the TCE more efficiently (e.g., in terms of time, availability and confidence of the inference output data, etc.).
  • the trace configuration further comprises a reporting rate.
  • the second instruction further causes the at least one network entity to report the at least one trace record to the TCE between the start trigger event and the stop trigger event with the reporting rate. By indicating the reporting rate, it is possible to control a signalling load in the wireless communication network.
  • the trace configuration further comprises at least one trigger event.
  • the second instruction causes the at least one network entity to report the at least one trace record to the TCE during the trace session whenever the at least one trigger event occurs.
  • the trace record(s) may be reported to the TCE more efficiently (e.g., in terms of time, availability and confidence of the inference output data, etc.).
  • the trace configuration further comprises an indication of a target ML model among the at least one ML model.
  • the second instruction further causes the at least one network entity to: (i) select, among the at least one trace record, at least one target trace record associated with the target ML model; and (ii) report the at least one target trace record to the TCE during the trace session.
  • the trace configuration further comprises an indication of a target optimization problem among the at least one optimization problem.
  • the second instruction further causes the at least one network entity to: (i) select, among the at least one trace record, at least one target trace record associated with the target optimization problem; and (ii) report the at least one target trace record to the TCE during the trace session.
  • the first instruction further causes the at least one network entity to store, in the at least one trace record, at least one of: non-ML communication data; information on an inference confidence of the at least one ML model; a training accuracy of the at least one ML model; and at least one optimization problem to be solved by the at least one ML model.
  • This additional information contained in the trace record(s) may help optimize (e.g., improve the overall performance of) the wireless communication network.
  • the at least one network entity comprises a network entity that does not support the at least one ML model
  • the at least one memory and the computer program code are further configured to, with the at least one processor, cause the 0AM entity to receive, from the network entity, an indication that the network entity does not support the at least one ML model.
  • the 0AM entity may be informed of ML-incapable network entities among the network entities of the wireless communication network.
  • a network entity in a wireless communication network comprises at least one processor and at least one memory.
  • the at least one memory comprises a computer program code.
  • the at least one memory and the computer program code are configured to, with the at least one processor, cause the network entity to operate at least as follows.
  • the network entity is caused to receive a trace configuration from an 0AM entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the network entity is then caused to decide to perform the trace configuration if the network entity supports the at least one ML model.
  • the network entity thus configured may provide its inference output data in the trace records to the TCE which may then forward them to one or more other (e.g., even ML-incapable) network entities.
  • a generic framework/means for utilizing the ML capabilities of the network entity (e.g., configured as a RAN or CN entity) in the wireless communication network may be provided.
  • the inference output data collected by using the trace records may be used for improving the overall performance of the wireless communication system.
  • the trace configuration further comprises a start trigger event and a stop trigger event.
  • the second instruction causes the network entity to report the at least one trace record to the TCE during the trace session between the start trigger event and the stop trigger event.
  • the network entity may report the trace record(s) to the TCE more efficiently (e.g., in terms of time, availability and confidence of the inference output data, etc.).
  • the trace configuration further comprises a reporting rate.
  • the second instruction further causes the network entity to report the at least one trace record to the TCE between the start trigger event and the stop trigger event with the reporting rate.
  • the trace configuration further comprises at least one trigger event.
  • the second instruction further causes the network entity to report the at least one trace record to the TCE during the trace session whenever the at least one trigger event occurs.
  • the network entity may report the trace record(s) to the TCE more efficiently (e.g., in terms of time, availability and confidence of the inference output data, etc.).
  • the trace configuration further comprises an indication of a target ML model among the at least one ML model.
  • the second instruction further causes the network entity to: (i) select, among the at least one trace record, at least one target trace record associated with the target ML model; and (ii) report the at least one target trace record to the TCE during the trace session.
  • the network entity may report the trace record(s) of interest (e.g., those trace records which are required to improve the overall performance of the wireless communication network).
  • the trace configuration further comprises an indication of a target optimization problem among the at least one optimization problem.
  • the second instruction further causes the network entity to: (i) select, among the at least one trace record, at least one target trace record associated with the target optimization problem; and (ii) report the at least one target trace record to the TCE during the trace session.
  • the network entity may report the trace record(s) of interest (e.g., those trace records which are required to improve the overall performance of the wireless communication network).
  • the first instruction further causes the network entity to store, in the at least one trace record, at least one of: non-ML communication data; information on an inference confidence of the at least one ML model; a training accuracy of the at least one ML model; and at least one optimization problem to be solved by the at least one ML model.
  • This additional information contained in the trace record(s) may help optimize (e.g., improve the overall performance of) the wireless communication network.
  • the at least one memory and the computer program code are further configured to, with the at least one processor, cause the network entity to: (i) decide not to perform the trace configuration if the network entity does not support the at least one ML model; and (ii) provide, to the 0AM entity, an indication that the network entity does not support the at least one ML model.
  • the network entity may inform the OAM entity about its ML incapability (i.e., the network entity may indicate that it cannot provide any inference output data to the TCE not because of their unavailability but due to its ML incapability).
  • a method for operating an OAM entity in a wireless communication network starts with the step of creating a trace configuration for at least one network entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the method then goes on to the step of transmitting the trace configuration to the at least one network entity.
  • the inference output data provided in the trace records from one network entity to the TCE may be then forwarded by the TCE to one or more other network entities for the purpose of improving the overall performance of the wireless communication system.
  • the forwarding of the inference output data (collected by using the trace records) even to network entities that do not support per se any ML model (i.e., are not ML-capable network entities) may enable the so-called transparent support for ML and provide a means for smooth transition towards a fully ML (native) wireless communication network.
  • a method for operating a network entity in a wireless communication network starts with the step of receiving a trace configuration from an OAM entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the method then goes on to the step of deciding to perform the trace configuration if the network entity supports the at least one ML model.
  • the network entity may provide its inference output data in the trace records to the TCE which may then forward them to one or more other (e.g., even ML-incapable) network entities.
  • the network entity may provide its inference output data in the trace records to the TCE which may then forward them to one or more other (e.g., even ML-incapable) network entities.
  • a generic framework/means for utilizing the ML capabilities of the network entity (e.g., configured as a RAN or CN entity) in the wireless communication network may be provided.
  • the inference output data collected by using the trace records may be used for improving the overall performance of the wireless communication system.
  • a computer program product comprises a computer-readable storage medium that stores a computer code. Being executed by at least one processor, the computer code causes the at least one processor to perform the method according to the third aspect.
  • a computer program product comprises a computer-readable storage medium that stores a computer code. Being executed by at least one processor, the computer code causes the at least one processor to perform the method according to the fourth aspect.
  • an 0AM entity in a wireless communication network comprises a means for creating a trace configuration for at least one network entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the 0AM entity further comprises a means for transmitting the trace configuration to the at least one network entity.
  • the inference output data provided in the trace records from one network entity to the TCE may be then forwarded by the TCE to one or more other network entities for the purpose of improving the overall performance of the wireless communication system.
  • the forwarding of the inference output data may enable the so-called transparent support for ML and provide a means for smooth transition towards a fully ML (native) wireless communication network.
  • a network entity in a wireless communication network comprises a means for receiving a trace configuration from an 0AM entity in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of at least one ML model in at least one trace record during the trace session.
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the network entity further comprises a means for deciding to perform the trace configuration if the network entity supports the at least one ML model.
  • the network entity thus configured may provide its inference output data in the trace records to the TCE which may then forward them to one or more other (e.g., even ML- incapable) network entities.
  • a generic framework/means for utilizing the ML capabilities of the network entity (e.g., configured as a RAN or CN entity) in the wireless communication network may be provided.
  • the inference output data collected by using the trace records may be used for improving the overall performance of the wireless communication system.
  • FIG. 1 shows a block diagram of an Operations Administration and Maintenance (0AM) entity in accordance with one example embodiment
  • FIG. 2 shows a flowchart of a method for operating the 0AM entity shown in FIG. 1 in accordance with one example embodiment
  • FIG. 3 shows a block diagram of a network entity in accordance with one example embodiment
  • FIG. 4 shows a flowchart of a method for operating the network entity shown in FIG. 3 in accordance with one example embodiment
  • FIG. 5 shows an interaction diagram that explains how a trace session may be activated at different network entities during a Protocol Data Unit (PDU) session establishment procedure in accordance with one exemplary embodiment
  • FIG. 6 shows an interaction diagram that explains a procedure for reporting trace records from a network entity to a Trace Collection Entity (TCE) in accordance with one exemplary embodiment.
  • TCE Trace Collection Entity
  • any embodiment recited herein as “example embodiment” should not be construed as preferable or having an advantage over other embodiments.
  • numerative terminology such as “first”, “second”, “third”, etc., may be used herein to describe various elements or features, these elements or features should not be limited by this numerative terminology. This numerative terminology is used herein only to distinguish one element or feature from another element or feature. For example, a first instruction discussed below could be called a second instruction, and vice versa, without departing from the teachings of the present disclosure.
  • a User Equipment may refer to an electronic computing device that is configured to perform wireless communications.
  • the UE may be implemented as a mobile station, a mobile terminal, a mobile subscriber unit, a mobile phone, a cellular phone, a smart phone, a cordless phone, a personal digital assistant (PDA), a wireless communication device, a desktop computer, a laptop computer, a tablet computer, a gaming device, a netbook, a smartbook, an ultra book, a medical mobile device or equipment, a biometric sensor, a wearable device (e.g., a smart watch, smart glasses, a smart wrist band, etc.), an entertainment device (e.g., an audio player, a video player, etc.), a vehicular component or sensor (e.g., a driver-assistance system), a smart meter/sensor, an unmanned vehicle (e.g., an industrial robot, a quadcopter, etc.) and its component (e.g., a self-
  • an unmanned vehicle e.g
  • a network entity may refer to an entity or node in any of a Radio Access Network (RAN) and a Core Network (CN).
  • RAN Radio Access Network
  • CN Core Network
  • the CN may refer to a network intended for connecting different RAN entities or nodes by providing proper interfaces therebetween.
  • the CN may also provide a gateway to other networks, for example, a Data Network (DN).
  • DN Data Network
  • the network entity may also be a UE receiving and executing a trace configuration indirectly after the trace configuration is forwarded by a receiving RAN node.
  • the network entity may also be a newly defined entity in the network architecture, which is configured to receive and execute a trace configuration.
  • the network entity may be implemented as a fixed point of communication/communication node for a UE in a particular wireless communication network. More specifically, the RAN network entity may be used to connect the UE to the DN through the CN and may be referred to as a base transceiver station (BTS) in terms of the 2G communication technology, a NodeB in terms of the 3G communication technology, an evolved NodeB (eNodeB or eNB) in terms of the 4G communication technology, and a gNB in terms of the 5G New Radio (NR) communication technology.
  • BTS base transceiver station
  • NodeB in terms of the 3G communication technology
  • eNodeB or eNB evolved NodeB
  • gNB 5G New Radio
  • the network entity may be, for example, a gNB Central Unit Control Plane (gNB-CU-CP) node, a gNB CU User Plane (gNB-CU-UP) node, or a gNB Distributed Unit (gNB-DU).
  • the RAN network entity may serve different cells, such as a macrocell, a microcell, a picocell, a femtocell, and/or other types of cells.
  • the macrocell may cover a relatively large geographic area (for example, at least several kilometers in radius).
  • the microcell may cover a geographic area less than two kilometers in radius, for example.
  • the picocell may cover a relatively small geographic area, such, for example, as offices, shopping malls, train stations, stock exchanges, etc.
  • the femtocell may cover an even smaller geographic area (for example, a home).
  • the network entity may also refer to any of CN network functions, such as an Access and Mobility Management Function (AMF), a Session Management Function (SMF), Unified Data Management (UDM), User Plane Function (UPF), Policy Control Function (PCF), etc.
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • UDM Unified Data Management
  • UPF User Plane Function
  • PCF Policy Control Function
  • the AMF supports termination of Non-Access Stratum (NAS) signalling, NAS ciphering and integrity protection, registration management, connection management, mobility management, access authentication and authorization, security context management.
  • the SMF supports session management (session establishment, modification, release), UE IP address allocation and management, Dynamic Host Configuration Protocol (DHCP) functions, termination of NAS signalling related to the session management, downlink (DL) data notification, traffic steering configuration for the UPF for proper traffic routing.
  • NAS Non-Access Stratum
  • DHCP Dynamic Host Configuration Protocol
  • UDM supports Authentication and Key Agreement (AKA) credentials generation, user identification handling, access authorization, subscription management.
  • the UPF supports packet routing and forwarding, packet inspection, Quality of Service (QoS) handling, acts as an external Protocol Data Unit (PDU) session point of interconnect to the DN, and is an anchor point for intra- and inter- Radio Access Technology (RAT) mobility.
  • the PCF supports a unified policy framework, providing policy rules to Control Plane (CP) functions, access subscription information for policy decisions in a Unified Data Repository (UDR).
  • AKA Authentication and Key Agreement
  • the UPF supports packet routing and forwarding, packet inspection, Quality of Service (QoS) handling, acts as an external Protocol Data Unit (PDU) session point of interconnect to the DN, and is an anchor point for intra- and inter- Radio Access Technology (RAT) mobility.
  • the PCF supports a unified policy framework, providing policy rules to Control Plane (CP) functions, access subscription information for policy decisions in a Unified Data Repository (UDR).
  • an 0AM entity may refer to an entity that is configured to use different data as a basis for optimizing network management, customer experience analytics, service assurance, incident management, etc.
  • the 0AM entity may use, among others, ML data (e.g., inference output data) from different network entities, which may be collected by using trace records at a Trace Collection Entity (TCE).
  • ML data e.g., inference output data
  • the TCE may be an entity residing in the 0AM itself or may be a network entity or node outside 0AM control. In the latter case, the TCE is defined by the IP address of the node which is responsible for performing the trace record collection.
  • a wireless communication network in which an 0AM entity and one or more network entities communicate with each other, may refer to a cellular or mobile network, a Wireless Local Area Network (WLAN), a Wireless Personal Area Networks (WPAN), a Wireless Wide Area Network (WWAN), a satellite communication (SATCOM) system, or any other type of wireless communication networks.
  • WLAN Wireless Local Area Network
  • WPAN Wireless Personal Area Networks
  • WWAN Wireless Wide Area Network
  • SATCOM satellite communication
  • the cellular network may operate according to the Global System for Mobile Communications (GSM) standard, the Code-Division Multiple Access (CDMA) standard, the Wide-Band Code-Division Multiple Access (WCDM) standard, the Time-Division Multiple Access (TDMA) standard, or any other communication protocol standard
  • GSM Global System for Mobile Communications
  • CDMA Code-Division Multiple Access
  • WDM Wide-Band Code-Division Multiple Access
  • TDMA Time-Division Multiple Access
  • the WLAN may operate according to one or more versions of the IEEE 802.11 standards
  • the WPAN may operate according to the Infrared Data Association (IrDA), Wireless USB, Bluetooth, or ZigBee standard
  • the WWAN may operate according to the Worldwide Interoperability for Microwave Access (WiMAX) standard.
  • WiMAX Worldwide Interoperability for Microwave Access
  • a trace record or simply a trace may refer to a subscriber, equipment and service trace.
  • the general concept of trace definition and management is given in the 3GPP. More specifically, a trace record at a network entity may be a set of traceable data collected based on trace control and configuration parameters.
  • the trace record may have two dimensions, i.e., a scope and a depth.
  • the trace scope may identify the network entity and an interface to be traced, whereas the trace depth may define the level of details of the traceable data to be retrieved.
  • the trace depth is specified during the activation of a trace session.
  • the trace depth may have following levels: Maximum, Minimum, Medium, MaximumWithoutVendorSpecificExtension,
  • the Maximum, Minimum and Medium levels allow for vendor specific data to be traced.
  • the Maximum (or MaximumWithoutVendorSpecificExtension) level allows all traceable data to be recorded in encoded format.
  • the Minimum (or MinimumWithoutVendorSpecificExtension) level allows for retrieval of a decoded subset of traceable data contained in signalling interface messages.
  • a management system e.g., an 0AM entity
  • a configured network entity shall propagate the activation to selected network entities in the entire network, i.e., RAN and CN entities.
  • the network entity Upon receiving the trace control and configuration parameters, the network entity shall activate the trace session.
  • the collected trace records are reported towards the TCE.
  • a trace reporting method may be file-based or streamingbased.
  • an ML model may be trained by the 0AM entity, and the trained ML model may be then used either on the UE side or on the network side.
  • the trained ML model may be configured to predict when to prepare a handoverand towards which cell.
  • ML data inferred by a certain ML model (also referred to as inference output data) at a certain network entity cannot be used by other network entities to improve the overall network performance.
  • - ML inference performed at different CN and/or RAN network entities may consider many different features that should not be individually specified and should not utilize separate channels/interfaces for distribution of inference output data;
  • - ML inference performed at certain CN and/or RAN network entities may be efficiently utilized by other CN and/or RAN network entities;
  • Extensive dedicated ML capability signaling should be avoided, e.g., to inform which network entities are ML-capable and which other network entities would be able to utilize their inference output data;
  • the utilization of available inference output data in the wireless communication network even at the network entities that do not support per se any ML model (i.e., are ML-incapable network entities) may enable the so-called transparent support for ML and provide a means for smooth transition towards fully ML (native) wireless communication networks.
  • the technical solution disclosed herein provides a technical solution that allows mitigating or even eliminating the above-sounded drawbacks peculiar to the prior art.
  • the technical solution disclosed herein relates to a mechanism for collecting ML data by using extended trace records from one or more network entities (e.g., RAN and/or CN entities) of a wireless communication network.
  • an 0AM entity is used, which creates and transmits a trace configuration to the network entity (entities) in the wireless communication network.
  • the trace configuration instructs each network entity to activate a trace session and store inference output data of one or more available ML models in one or more trace records during the trace session.
  • the trace configuration further instructs network entity (entities) as to when the trace record(s) should be reported to a TCE during the trace session.
  • network entity entities
  • the inference output data obtained by one network entity may be forwarded by the TCE to one or more other (e.g., even ML-incapable) network entities for the purpose of improving the overall network performance.
  • FIG. 1 shows a block diagram of an 0AM entity 100 in accordance with one example embodiment.
  • the 0AM entity 100 is intended to communicate with one or more network entities (e.g., RAN and/or CN entities) in any of the above-described wireless communication networks.
  • the 0AM entity 100 comprises a processor 102, a memory 104, and a transceiver 106.
  • the memory 104 stores processor-executable instructions 108 which, when executed by the processor 102, cause the processor 102 to perform the aspects of the present disclosure, as will be described below in more detail. It should be noted that the number, arrangement, and interconnection of the constructive elements constituting the 0AM entity 100, which are shown in FIG.
  • the processor 102 may be replaced with several processors, as well as the memory 104 may be replaced with several removable and/or fixed storage devices, depending on particular applications.
  • the transceiver 106 may be implemented as two individual devices, with one for a receiving operation and another for a transmitting operation. Irrespective of its implementation, the transceiver 106 is intended to be capable of performing different operations required to perform the data reception and transmission, such, for example, as signal modulation/demodulation, encoding/decoding, etc. In other embodiments, the transceiver 106 may be part of the processor 102 itself.
  • the processor 102 may be implemented as a CPU, general-purpose processor, singlepurpose processor, microcontroller, microprocessor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), digital signal processor (DSP), complex programmable logic device, etc. It should be also noted that the processor 102 may be implemented as any combination of one or more of the aforesaid. As an example, the processor 102 may be a combination of two or more microprocessors.
  • the memory 104 may be implemented as a classical nonvolatile or volatile memory used in the modern electronic computing machines.
  • the nonvolatile memory may include Read-Only Memory (ROM), ferroelectric Random-Access Memory (RAM), Programmable ROM (PROM), Electrically Erasable PROM (EEPROM), solid state drive (SSD), flash memory, magnetic disk storage (such as hard drives and magnetic tapes), optical disc storage (such as CD, DVD and Blu-ray discs), etc.
  • ROM Read-Only Memory
  • RAM ferroelectric Random-Access Memory
  • PROM Programmable ROM
  • EEPROM Electrically Erasable PROM
  • SSD solid state drive
  • flash memory magnetic disk storage (such as hard drives and magnetic tapes), optical disc storage (such as CD, DVD and Blu-ray discs), etc.
  • the volatile memory examples thereof include Dynamic RAM, Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Static RAM, etc.
  • the processor-executable instructions 108 stored in the memory 104 may be configured as a computer-executable program code which causes the processor 102 to perform the aspects of the present disclosure.
  • the computer-executable program code for carrying out operations or steps for the aspects of the present disclosure may be written in any combination of one or more programming languages, such as Java, C++, or the like.
  • the computer-executable program code may be in the form of a high-level language or in a pre-compiled form and be generated by an interpreter (also pre-stored in the memory 104) on the fly.
  • FIG. 2 shows a flowchart of a method 200 for operating the 0AM entity 100 in accordance with one example embodiment.
  • the method 200 starts with a step S202, in which the processor 102 creates a trace configuration for one or more network entities in the wireless communication network.
  • the trace configuration comprises a first instruction to activate a trace session and store inference output data of one or more ML models in one or more trace records during the trace session.
  • the term "inference” is used herein in its ordinary meaning accepted in the field of ML, i.e., refers to the process of using a trained ML algorithm to make a prediction.
  • the inference output data used in the embodiments disclosed herein are those data which are obtained as a result of this inference process.
  • each inference result of each ML model may be stored in an individual trace record.
  • the ML model(s) may be downloaded or configured at each network entity by the 0AM 100 itself, so that the 0AM 100 may request the corresponding inference output data for specific one or more ML models.
  • the 0AM 100 may request the inference output data over the ML model(s) described in a generic way (e.g., which may refer to a generic problem under consideration, such as "ML energy saving", "ML Load Balancing", “ML Mobility Enhancements", etc.).
  • the trace configuration further comprises a second instruction on whether and when to report the at least one trace record to a TCE during the trace session.
  • the second instruction may be an instruction that causes each configured network entity to report the inference output data whenever they are generated by the ML model(s). It is also assumed that the trace configuration also comprises all parameters required for trace session activation; these parameters may be, for example, the same as defined in the 3GPP.
  • the method 200 then proceeds to a step S204, in which the processor 102 transmits (e.g., by means of the transceiver 106) the trace configuration to each of the network entities.
  • the second instruction is an instruction not to report the trace record(s) to the TCE during the trace session, it is also possible that each configured network entity does not report the trace record(s) but logs them instead for future reporting (e.g., after the trace session is deactivated).
  • the trace configuration may comprise additional information
  • the second instruction may be an instruction that causes each configured network entity to report the trace record(s) in accordance with said additional information.
  • the trace configuration may additionally indicate at least one of the following:
  • the trace configuration may comprise start and stop trigger events between which the trace record(s) should be reported to the TCE; such start and stop trigger events may be associated with the occurrence/availability of the inference output data at the configured network entities, confidence values for the inference output data, etc.
  • a reporting rate with which said reporting should be done e.g., every certain number of milliseconds, or every time a new inference result is available/obtained
  • each configured network entity may report the trace record(s) to the TCE during the trace session (again, such separate trigger events may be associated with the occurrence/availability of the inference output data at each configured network entity, confidence values for the inference output data, etc.).
  • the trace configuration may further comprise an indication of a target ML model among the ML model(s) available at the configured network entity (entities).
  • the trace configuration may indicate from which ML model available at each configured network entity the inference output data are requested. This could be indicated implicitly by using any of the existing trace parameters (e.g., a trace reference value) or by adding a new trace parameter to the existing trace configuration defined in the 3GPP.
  • the inference output data may be requested from ML model xl, version 3.
  • the 0AM entity 100 may store (e.g., in the memory 104) a catalogue of all ML models available in the RAN and/or the CN.
  • each configured network entity may select, among the trace records, one or more target trace records associated with the target ML model and report the target trace record(s) to the TCE during the trace session. Since the ML models may be re-trained or updated over time, the 0AM entity 100 may also receive information about said updating or re-training of the ML model(s) from each configured network entity and, in response, update its catalogue of all ML models accordingly.
  • the target ML model may, for example, correspond to a new version of one of the past ML models. When the 0AM becomes aware of retraining of a certain ML model, this may trigger the initiation of further collection of the inference output data.
  • the inference output data may be requested alternatively with respect to their quantity/type (e.g., the inference output data pertaining to load predictions; in this case, load predictions from any ML model available at the configure network entity (entities) may be provided to the TCE).
  • quantity/type e.g., the inference output data pertaining to load predictions; in this case, load predictions from any ML model available at the configure network entity (entities) may be provided to the TCE.
  • the inference output data may be requested alternatively based on an optimization problem which they are related to.
  • the optimization problem may relate to mobility optimization, energy saving, etc.
  • the optimization problem may be indicated implicitly through the trace reference value or through a new trace parameter added to the existing trace configuration defined in the 3GPP.
  • each configured network entity may also select, among the trace records, one or more target trace records associated with the indicated optimization problem and report the target trace record(s) to the TCE during the trace session.
  • the first instruction may further cause each configured network entity to store, in the trace record(s), at least one of: regular data; information on an inference confidence of the ML model(s); a training accuracy of the ML model(s); and at least one optimization problem (e.g., mobility optimization, energy saving, etc.) to be solved by the ML model(s).
  • the regular data may refer to any data which are not inferred by means of the ML model(s).
  • the regular data are non-ML communication data.
  • the regular data may include data exchanged over a certain communication interface between different network entities without any involvement of ML.
  • the regular data may be also reported either in the same trace record(s) as the inference output data or in one or more separate trace records.
  • one or more ML- incapable network entities may either:
  • the ML-incapable network entities may further signal to the 0AM entity that the inference output data are not reported, not because of their absence (e.g., any of the above-mentioned trigger events are not met yet), but due to the ML incapability of the network entities).
  • FIG. 3 shows a block diagram of a network entity 300 in accordance with one example embodiment.
  • the network entity 300 may be implemented as any RAN (e.g., a gNB) or CN entity (e.g., an AMF) and is intended to communicate with the 0AM entity 100 and any other network entities in any of the above-described wireless communication networks.
  • the network entity 300 comprises a processor 302, a memory 304, and a transceiver 306.
  • the memory 304 stores processor-executable instructions 308 which, when executed by the processor 302, cause the processor 302 to implement the aspects of the present disclosure, as will be described below in more detail.
  • the number, arrangement, and interconnection of the constructive elements constituting the network entity 300 which are shown in FIG. 3, are not intended to be any limitation of the present disclosure, but merely used to provide a general idea of how the constructive elements may be implemented within the network entity 300.
  • the processor 302, the memory 304, the transceiver 306, and the processor-executable instructions 308 may be implemented in the same or similar manner as the processor 102, the memory 104, the transceiver 106, and the processor-executable instructions 108, respectively.
  • FIG. 4 shows a flowchart of a method 400 for operating the network entity 300 in accordance with one example embodiment.
  • the method 400 starts with a step S402, in which the processor 302 receives the trace configuration from the 0AM entity 100 (i.e., the processor 102).
  • the trace configuration may comprise the above-described first and second instructions.
  • the trace configuration may, for example, comprise any of the above-described additional information (e.g., the start and stop trigger events, one or more separate trigger events, the reporting rate with which the trace record(s) is(are) to be reported to the TCE, etc.).
  • the method 400 then goes on to a step S404, in which the processor 302 decides to perform or implement the trace configuration if the network entity 300 supports (any of) the ML models indicated in the trace configuration.
  • the processor 302 may transmit (e.g., by means of the transceiver 306) a corresponding indication of its ML incapability to the 0AM entity 100 (i.e., the processor 102).
  • the ML incapability may also mean that the network entity is ML-capable but has not fully trained yet the ML model(s) for which the inference output data are requested.
  • the ML incapability may also be determined if the ML model that was trained and in execution needs retraining, so that at the current time instant no inference output data are possible.
  • the ML incapability may also be indicated if the ML functionality at the network entity is switched off (e.g., for energy saving purposes, etc.).
  • this could trigger the network entity 300 to put the ML model(s) in execution to produce the inference output data.
  • FIG. 5 shows an interaction diagram 500 that explains how a trace session may be activated at different network entities during a PDU session establishment procedure in accordance with one exemplary embodiment.
  • a UE is already registered in a wireless communication network
  • an 0AM entity is configured as the 0AM entity 100
  • each of an AMF, an UPF, an SMF, a PCF and a gNB is configured as the network entity 300.
  • the signalling-based trace activation approach is performed in the diagram 500. Similar concepts are applicable to the management-based trace activation approach.
  • the diagram 500 is true for both the file-based and streaming type of trace reporting.
  • the interaction diagram 500 starts with a step S502, in which the 0AM entity transmits a trace session activation indication to a UDM.
  • the trace session activation indication is implied to comprise the above-described trace configuration which indicates, among others, whether and how to report trace records.
  • the following trace control and configuration parameters may be included in the trace session activation indication transmitted by the 0AM entity:
  • SUPI Subscription Permanent Identifier
  • IMEISV International Mobile Equipment Identity Software Version
  • trigger events for example, for the AMF, the SMF, the UPF and the PCF, including the above-described trigger events referring to the inference-output-data reporting (e.g., the availability of the inference output data, their certain confidence level or value, and/or validity time, etc.).
  • Table 1 below gives a non-exhaustive list of such trigger events for the AMF.
  • the trigger events for the AMF may be related to the existing standardized events for collecting regular data (e.g., "predicted/inferred N2 or Xn handover"), but they are not limited to the mere extensions of the existing events.
  • the trace recording and/or reporting may be activated if there are inference output data which are related to any event/state in the wireless communication network.
  • one option may be to re-use a spare bit from the standardized bitmap (which is shown in Table 2 bellow) and indicate that the inference output data is to be reported (for certain standardized and nonstandardized trigger events) in addition to the regular data (the bit set to 1) or only the regular data (or measurements) will be performed (the bit set to 0).
  • Table 2 Table 3 below gives a non-exhaustive list of the trigger events for the SMF.
  • bitmap extension for the SMF may be performed similarly to the AMF where two spare bits may be used to encode if the reported data should be regular data, inference output data or both types of data should be included (see Table 4 below).
  • the trace session activation indication transmitted by the OAM entity in the step S502 may also comprise at least one of the following additional parameters: - a trace depth including the indication to which level of details the inference output data should be recorded in the network entity of interest (some non-restrictive examples of the trace depth are given below in Table 5);
  • gNB-CU-CP Central Unit Control Plane
  • gNB-CU-UP gNB CU User Plane
  • gNB-DU gNB Distributed Unit
  • URI Uniform Resource Identifier
  • trace reporting format/job type (trace only if numeric value "2" is specified - this parameter may be extended with an additional numeric value to indicate that the inference output data should be collected);
  • URL Uniform Resource Locator
  • FQDN Fully Qualified Domain Name
  • an indicator to associate the inference output data to be collected with an optimization problem e.g., a standardized trace reference field may be reused for this purpose, or a new indicator may be introduced.
  • the interaction diagram 500 proceeds to a step S504, in which the UDM stores the trace control and configuration parameters (hereinafter referred to as the trace parameters for short) retrieved from the 0AM entity, including the indication on which inference output data should be recorded/reported and how.
  • the interaction diagram 500 goes on to a step S506, in which the UDM sends a Nudm_SDM_Notification message to the AMF together with the trace parameters.
  • a step S508 is initiated, in which the AMF stores the trace parameters received from the UDM, including the indication on which inference output data should be recorded/reported and how.
  • the interaction diagram 500 proceeds to a step S510, in which the AMF starts or activates the trace session according to the received trace parameters (or, in other words, the received trace configuration).
  • the UE sends a PDU session establishment request to the AMF.
  • the AMF sends a 'start trace' message over an NG interface (e.g., an N2 interface from the 5GC perspective) in a next step S514.
  • an NG interface e.g., an N2 interface from the 5GC perspective
  • the interaction diagram 500 goes on to a step S516, in which the gNB stores the trace parameters received from the AMF, including the indication on which inference output data should be recorded/reported and how.
  • the gNB starts the trace session according to the received trace configuration.
  • the trace session should be activated in the gNB when the gNB receives the TRACE START, INITIAL CONTEXT SETUP REQUEST or HANDOVER REQUEST message with the IE 'Trace Activation' from the AMF and if some activities have been started on the interfaces that have been requested to be traced, including the case that the inference output data with certain confidence is available and/or when their validity time has not expired.
  • the AMF selects an appropriate SMF and sends a Nsmf_PDUSession_CreateSI ⁇ /IContext request to the selected SMF in steps S518 and S520, respectively.
  • the SMF performs a NuDM_UECM_Registration procedure with the UDM and receives the trace parameters from the UDM in a next step S522.
  • the SMF stores the trace parameters received from the UDM, including the indication on which inference output data should be recorded/reported and how, and starts the trace session according to the received trace configuration.
  • the SMF selects an appropriate PCF, establishes Session Management Policy Association with the PCF and provides the trace parameters information to the PCF in steps S526 and S528, respectively.
  • the interaction diagram 500 proceeds to a step S530, in which the PCF stores the trace parameters received from the SMF, including the indication on which inference output data should be recorded/reported and how.
  • the trace parameters are stored as part of Policy Association. Once the trace parameters are stored, the PCF starts the trace session according to the received trace configuration.
  • the interaction diagram 500 goes on to steps S532 and S534, in which the SMF selects an appropriate UPF and performs N4 Session Establishment with the UPF and provides the trace parameters information to the UPF.
  • the interaction diagram 500 ends up with a step S536, in which the UPF stores the trace parameters received from the SMF, including the indication on which inference output data should be recorded/reported and how.
  • the trace parameters are stored as part of N4 Session Establishment, whereafter the UPF starts the trace session according to the received trace configuration.
  • FIG. 6 shows an interaction diagram 600 that explains a procedure for reporting trace records from a network entity to a TCE in accordance with one exemplary embodiment.
  • the network entity may be any of the network entities shown in the interaction diagram 500 (e.g., the AMF or the SMF).
  • the interaction diagram 600 starts with a step S602, in which the network entity performs the trace configuration (i.e., activates a trace session) in accordance with trace parameters obtained, for example, as discussed above with reference to the interaction diagram 500. After that, the network entity starts recording or storing traceable data (i.e., inference output data of its ML model(s)) in trace records.
  • traceable data i.e., inference output data of its ML model(s)
  • the trace records are sent by the network entity to the TCE, either directly or via a management system (i.e., an entity manager (EM)) of the network entity.
  • EM entity manager
  • the first option i.e., sending the trace records directly to the TCE
  • the second option i.e., sending the trace records to the TCE via the management system
  • the trace records may include only regular or only inference output data, as well as both regular data and inference output data.
  • each trace record may be extended by adding inference lEs, for specific interfaces, based on the trace configuration, or by using the trace record extensions, as shown in Tables 6 and 7 below (it should be noted that Tables 6 and 7 are extensions of Table 4.18.1 and Table 4.30.1 from 3GPP TS 32.423, respectively; moreover, "Encoded*" in Tables 6 and 7 means that the messages are left encoded in the format they were received).
  • each step or operation of the methods 200 and 400, and the interaction diagrams 500 and 600, or any combinations of the steps or operations can be implemented by various means, such as hardware, firmware, and/or software.
  • one or more of the steps or operations described above can be embodied by processor executable instructions, data structures, program modules, and other suitable data representations.
  • the processor-executable instructions which embody the steps or operations described above can be stored on a corresponding data carrier and executed by the processor 102 or 302, respectively.
  • This data carrier can be implemented as any computer-readable storage medium configured to be readable by said at least one processor to execute the processor executable instructions.
  • Such computer-readable storage media can include both volatile and nonvolatile media, removable and nonremovable media.
  • the computer-readable media comprise media implemented in any method or technology suitable for storing information.
  • the practical examples of the computer-readable media include, but are not limited to information-delivery media, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile discs (DVD), holographic media or other optical disc storage, magnetic tape, magnetic cassettes, magnetic disk storage, and other magnetic storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente divulgation concerne un mécanisme de collecte de données d'apprentissage automatique (ML) à l'aide d'enregistrements de trace auprès d'une ou de plusieurs entités de réseau d'un réseau de communication sans fil. À cette fin, une entité d'opérations, d'administration et de maintenance (OAM) est utilisée, laquelle crée une configuration de trace et la transmet à l'entité (aux entités) de réseau. La configuration de trace ordonne à chaque entité de réseau d'activer une session de trace et de stocker des données de sortie d'inférence d'un ou de plusieurs modèles d'apprentissage automatique dans un ou plusieurs enregistrements de trace durant la session de trace. La configuration de trace ordonne en outre à l'entité de réseau (aux entités) si et quand le ou les enregistrements de trace devraient être rapportés à une entité de collecte de trace (TCE) durant la session de trace. De cette façon, il est possible de fournir une structure générique pour utiliser des capacités d'apprentissage automatique de différentes entités de réseau dans tout le réseau de communication sans fil. En particulier, les données d'inférence obtenues par une entité de réseau peuvent être transférées par l'entité TCE à une ou plusieurs autres entités de réseau (par exemple, même à celles sans capacités d'apprentissage automatique) dans le but d'améliorer les performances globales du réseau.
PCT/EP2022/064727 2022-05-31 2022-05-31 Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil WO2023232227A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2022/064727 WO2023232227A1 (fr) 2022-05-31 2022-05-31 Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2022/064727 WO2023232227A1 (fr) 2022-05-31 2022-05-31 Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil

Publications (1)

Publication Number Publication Date
WO2023232227A1 true WO2023232227A1 (fr) 2023-12-07

Family

ID=82258548

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/064727 WO2023232227A1 (fr) 2022-05-31 2022-05-31 Extension d'enregistrements de trace pour collecter des données d'apprentissage automatique dans un réseau de communication sans fil

Country Status (1)

Country Link
WO (1) WO2023232227A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2439977A2 (fr) * 2010-10-06 2012-04-11 Telefonaktiebolaget LM Ericsson (publ) Procédé, appareil et système de suivi flexible de l'utilisateur dans des réseaux mobiles
US20130196640A1 (en) * 2010-08-10 2013-08-01 Telefonaktiebolaget L M Ericsson (Publ) Network Elements for End-to-End (E2E) Circuit Service (CS) Call Tracing Functionality
US20210065225A1 (en) * 2019-09-03 2021-03-04 Toyota Jidosha Kabushiki Kaisha Information processing method and information processing apparatus
WO2021047781A1 (fr) * 2019-09-13 2021-03-18 Nokia Technologies Oy Appareil de collecte de données de réseau d'accès radio

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130196640A1 (en) * 2010-08-10 2013-08-01 Telefonaktiebolaget L M Ericsson (Publ) Network Elements for End-to-End (E2E) Circuit Service (CS) Call Tracing Functionality
EP2439977A2 (fr) * 2010-10-06 2012-04-11 Telefonaktiebolaget LM Ericsson (publ) Procédé, appareil et système de suivi flexible de l'utilisateur dans des réseaux mobiles
US20210065225A1 (en) * 2019-09-03 2021-03-04 Toyota Jidosha Kabushiki Kaisha Information processing method and information processing apparatus
WO2021047781A1 (fr) * 2019-09-13 2021-03-18 Nokia Technologies Oy Appareil de collecte de données de réseau d'accès radio

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Telecommunication management; Subscriber and equipment trace; Trace data definition and management (Release 17)", vol. SA WG5, no. V17.3.0, 23 December 2021 (2021-12-23), pages 1 - 109, XP052083345, Retrieved from the Internet <URL:https://ftp.3gpp.org/Specs/archive/32_series/32.423/32423-h30.zip 32423-h30.doc> [retrieved on 20211223] *
3GPP TS 32.423

Similar Documents

Publication Publication Date Title
US11425225B2 (en) Method, apparatus, and equipment for exposing edge network capability, and storage medium
KR20200136985A (ko) 통신 방법 및 장치
KR20120024875A (ko) 로컬 인터넷 프로토콜 액세스에 의한 홈 네트워크 기지국으로부터의 외향 핸드오버 동안의 서비스 지속성
JP7275325B2 (ja) アプリケーション機能とコアネットワークとの間でネゴシエーションされたバックグラウンドデータ伝送ポリシを更新する方法、ポリシ制御機能、およびアプリケーション機能
US20230147409A1 (en) Apparatus and method for network automation in wireless communication system
US20210329504A1 (en) Communication method and apparatus
US11601866B2 (en) Systems and methods for enabling optimized reporting related to policy control request triggers
US11516728B2 (en) Method and system for access control with differentiated service
US20230127601A1 (en) Dynamic update of path selection policy for user equipment in wireless communication network
EP3522668B1 (fr) Procédé et dispositif d&#39;établissement de relation de confiance
US11929938B2 (en) Evaluating overall network resource congestion before scaling a network slice
US11889588B2 (en) Systems and methods for receiving indications of network access technologies, network services, and network capabilities by a user device
KR20220021410A (ko) 네트워크에서 타이머 값 설정 방법 및 장치
WO2023232227A1 (fr) Extension d&#39;enregistrements de trace pour collecter des données d&#39;apprentissage automatique dans un réseau de communication sans fil
WO2023143806A1 (fr) Mise à jour d&#39;indicateur de routage par l&#39;intermédiaire d&#39;une procédure de mise à jour de paramètres d&#39;ue (upu)
US11805022B2 (en) Method and device for providing network analytics information in wireless communication network
CN116803052A (zh) 用于akma的路由指示符检索
US11722717B1 (en) Systems and methods for network-based adaptive uplink data transfer for large volume data
WO2023143258A1 (fr) Procédé et appareil de traitement de données
US12016075B2 (en) Systems and methods for transferring multiple packet data unit sessions with a same data network name configuration between networks
US20240089205A1 (en) Systems and methods for monitoring network devices based on predictive analysis
US20240089887A1 (en) Systems and methods for providing a radio access network fallback for multimedia priority services
US11489970B2 (en) Systems and methods for providing policy control of parallel signaling in a fifth generation (5G) network
US20240196355A1 (en) Recovery from Errors during Network Slice Specific Authentication and Authorization (NSSAA)
WO2023171210A1 (fr) Nœud de ran et procédé

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: 22734168

Country of ref document: EP

Kind code of ref document: A1