Electronics and Telecommunications Research Institute

Soohwan Lee

Myung Ki Shin

Seung-Ik Lee

Dongmyoung Kim

Jihoon Sung

A method and apparatus for performing AI/ML job through the steps of: receiving expected completion time and available resources of UE for a plurality of candidate combinations of a plurality of tasks included in a job from the UE via a cellular network; determining a candidate combination from among the plurality of candidate combinations based on the expected completion time and available resources of the UE for the plurality of candidate combinations; and assigning a task according to determined candidate combination to the UE through a PDU session of the cellular network.

Apparatus and method for assigning a task in an AI/ML job

A method and apparatus for providing analytics to UE through steps of receiving a UE ID of UE and an analytics ID requested by the UE and transmitting analytics corresponding to the analytics ID to the UE are provided.

Apparatus and method for providing analytics to user equipment

Provided is a method of a time synchronization service for federated learning (FL) in a fifth generation (5G) network. The method includes receiving, by an artificial intelligence/machine learning function (AIMLF), a subscription request for UE capability information for an FL time synchronization service from an artificial intelligence/machine learning application function (AIML AF) and transmitting, by the AIMLF, the UE capability information to the AIML AF, in response to the subscription request.

Method of time synchronization service for federated learning in 5G network

A distributed training method performed between a terminal and an edge cloud server is disclosed. The distributed training method may include identifying a plurality of user terminals located in a local network coverage of the edge cloud server, providing machine learning models to the plurality of user terminals for training and aggregating results of the training of the machine learning models from the plurality of user terminals when the training of the machine learning models is completed.

Distributed training method between terminal and edge cloud server

A machine learning (ML) model management method for a network data analytics function (NWDAF) device is disclosed. The NWDAF device performs at least one of an analytics logical function (AnLF) for network data and an ML model training logical function (MTLF).

Management method of machine learning model for network data analytics function device

Disclosed is a session management method based on protocol data unit (PDU) session anchor (PSA) relocation, and a device performing the session management method. The session management method may include determining to perform PSA relocation, establishing a new PSA device through the PSA relocation, and releasing an existing PSA device, in which the PSA relocation may allow traffic moving towards the existing PSA device to move to the new PSA device.

Session management method based on reallocation of PDU session anchor device, and device performing the session management method

A federated learning-based network data analysis method and an apparatus for performing the same are provided. An operating method of a federation learning (FL) server includes performing an FL operation trigger in response to a request of a first network function (NF), selecting a plurality of second NFs on an analytics identifier (ID) in response to the FL operation trigger, and requesting the plurality of second FLs for FL, wherein the first NF is an FL consumer, and the plurality of second NFs is an FL client.

Network data analysis method and system based on federated learning

A method and an apparatus for supporting service continuity between a first network and a second network are provided, which include: requesting slice analytics for selection of a slice from a network data analytics function (NWDAF) of the first network before a terminal moves from the first network to the second network; and selecting a slice to be used in the second network to provide a service to the terminal based on the slice analytics received from the NWDAF of the first network.

Method and apparatus for supporting service continuity in NPN using NWDAF

A terminal for performing an onboarding procedure for remote provisioning through steps of: receiving an onboarding enabled indication from at least one onboarding network; selecting an onboarding network based on the onboarding enabled indication and onboarding network selection information; and attempting registration for the selected onboarding network is provided.

Apparatus and method for performing onboarding procedure for remote provisioning

An application function (AF) in a first network and a method for providing a service by the AF via a second network including: requesting quality of service (QoS) related information to a network exposure function (NEF) of a second network different from the first network in which the AF is located, wherein the QoS related information is used to guarantee the QoS of a service to be provided to a terminal; and receiving the QoS related information from the NEF of the second network are provided.

Method and apparatus for guaranteeing quality of service between a public network and a non- public network

A network data collection method from application function device for network data analytic function is disclosed. The network data collection method includes transmitting a Naf_EventExposure_Subscribe message for a subscription of an event into an application function (AF) device; and receiving a Naf_EventExposure_Notify message from the AF device when the NWDAF subscribes the event.

Network data collection method from application function device for network data analytic function

A network device divided into a training plane and a control plane, model management server that controls a network device, and processing methods of a network device and model management server are disclosed. A processing method may include receiving a machine learning model from a model management server, obtaining network data to generate analytics information, generating analytics information by inputting the network data to a machine learning model, feeding back the analytics information to the model management server, and generating a control command of the network device using the analytics information, wherein the analytics information is generated by a training plane function and the control command is generated by a control plane function.

Management server that controls network devices, and processing methods of network devices and model management servers

Disclosed is a session management method based on protocol data unit (PDU) session anchor (PSA) relocation, and an device performing the session management method. The session management method may include determining to perform PSA relocation, establishing a new PSA device through the PSA relocation, and releasing an existing PSA device, in which the PSA relocation may allow traffic moving towards the existing PSA device to move to the new PSA device.

A method and system for providing communication analysis of the user equipment (UE) based on network analysis is disclosed. The method provides communication analysis of the UE in a form as UE communication statistics or UE communication prediction by analyzing network data collected from the network function (NF) device.

Method and system for providing communication analysis of user equipment based on network data analysis

Disclosed herein are a method and an NWDAF for collecting network data, including: transmitting a network exposure subscription request message including an event reporting granularity parameter to the NF; receiving a data set determined by the NF based on the event reporting granularity parameter from the NF through an event exposure notification message in at least one reporting cycle; and performing network data analysis using received data set.

Growing community of inventors

Daejeon, South Korea

Soohwan Lee