JP-7856769-B2 - Communication methods, user devices, and network nodes

JP7856769B2JP 7856769 B2JP7856769 B2JP 7856769B2JP-7856769-B2

Inventors

藤代真人

Assignees

京セラ株式会社

Dates

Publication Date: 20260511
Application Date: 20230721
Priority Date: 20220722

Claims (12)

A communication method that applies machine learning technology to wireless communication between a user device and a network node in a mobile communication system, The communication device of the user device and the network node receives wireless signals transmitted by each of the multiple communication resources of the other communication device of the user device and the network node. The one communication device communicates information indicating a combination of communication resources having a predetermined correlation among the plurality of communication resources to the other communication device, The aforementioned communication device receives a mode switching notification as control data that notifies of a mode switch between learning mode and inference mode, and performs a mode switch between learning mode and inference mode in response to the mode switching notification. The one communication device, in the learning mode, receives the wireless signal transmitted from the other communication device using all of the multiple communication resources, performs machine learning, and obtains a trained model. The one communication device, in the inference mode, receives the wireless signal transmitted from the other communication device using some of the multiple communication resources, and uses the trained model to derive the state of the communication resources other than the some resources as inference result data. A communication method comprising the above-mentioned communication device performing machine learning processing using the above-mentioned combination.
The communication method according to claim 1, wherein the plurality of communication resources are a plurality of antenna ports of the other communication device.
The communication method according to claim 2, wherein the information indicating the combination includes identification information for each antenna port constituting the combination.
The communication method according to claim 1, wherein the plurality of communication resources are a plurality of beams formed by the other communication device.
The communication method according to claim 2, wherein the information indicating the combination includes identification information for each beam constituting the combination.
The communication method according to claim 1, wherein the communication includes one communication device receiving a notification from the other communication device that includes information indicating the combination.
The communication method according to claim 1, wherein the communication includes one communication device transmitting to the other communication device a notice containing information indicating the combination and/or information about a communication resource that can stop transmitting the radio signal.
The aforementioned communication device identifies the combination to communicate by communicating, The communication method according to claim 1, wherein one of the communication devices acquires a trained model based on the identified combination and the received radio signal.
The communication method according to claim 8, wherein the trained model is a model for deriving the inference result data for another communication resource constituting the combination based on the reception status data of the wireless signal of one communication resource constituting the combination.
The communication method according to claim 9, further comprising the one communication device using the trained model to derive the inference result data for the other communication resource based on the reception status data of the radio signal of the one communication resource.
A user device that performs wireless communication with a network node to which machine learning technology is applied, Processing to receive wireless signals transmitted by each of the multiple communication resources of the aforementioned network node, A process of communicating information indicating a combination of communication resources having a predetermined correlation among the aforementioned plurality of communication resources to the network node, The process involves receiving a mode switching notification as control data that indicates a mode switch between learning mode and inference mode, and performing a mode switch between learning mode and inference mode in response to the said mode switching notification. The user device and one of the network nodes, in the learning mode, receive the wireless signal transmitted from the other communication device of the network node using all of the multiple communication resources, perform machine learning, and acquire a trained model. The one communication device, in the inference mode, receives the wireless signal transmitted from the other communication device using some of the multiple communication resources, and uses the trained model to derive the state of the communication resources other than the some resources as inference result data. A user device comprising a processor that performs machine learning processing using the aforementioned combination.
A network node that performs wireless communication with user equipment to which machine learning technology is applied, Processing to receive wireless signals transmitted by each of the multiple communication resources of the user device, A process of communicating information indicating a combination of communication resources having a predetermined correlation among the aforementioned plurality of communication resources to the user device, The process involves receiving a mode switching notification as control data that indicates a mode switch between learning mode and inference mode, and performing a mode switch between learning mode and inference mode in response to the said mode switching notification. The user device and one of the network nodes, in the learning mode, receive the wireless signal transmitted from the other communication device of the network node using all of the multiple communication resources, perform machine learning, and acquire a trained model. The one communication device, in the inference mode, receives the wireless signal transmitted from the other communication device using some of the multiple communication resources, and uses the trained model to derive the state of the communication resources other than the some resources as inference result data. A network node comprising a processor that performs machine learning processing using the aforementioned combination.

Description

This disclosure relates to communication methods and communication devices used in mobile communication systems. In recent years, the 3GPP (Third Generation Partnership Project) (registered trademark; hereinafter the same), a standardization project for mobile communication systems, has been considering applying artificial intelligence (AI) technology, particularly machine learning (ML) technology, to wireless communication (air interface) in mobile communication systems. 3GPP contribution: RP-213599, “New SI: Study on Artificial Intelligence (AI)/Machine Learning (ML) for NR Air Interface” The first aspect of the communication method is a method for applying machine learning technology to wireless communication between a user device and a base station in a mobile communication system. The communication method includes the steps of: one communication device, which is either the user device or the base station, receiving a wireless signal transmitted from each of a plurality of communication resources of the other communication device, which is either the user device or the base station; one communication device communicating information to the other communication device indicating a combination of communication resources having a predetermined correlation among the plurality of communication resources; and one communication device executing a machine learning process using the combination. The communication device according to the second embodiment is one of the user device and the base station in a mobile communication system that applies machine learning technology to wireless communication between a user device and a base station. The communication device includes a processor that performs the following: receiving wireless signals transmitted by each of a plurality of communication resources of the other communication device of the user device and the base station; communicating information indicating a combination of communication resources having a predetermined correlation among the plurality of communication resources with the other communication device; and machine learning processing using the combination. This diagram shows the configuration of a mobile communication system according to an embodiment.This diagram shows the configuration of the UE (User Equipment) according to the embodiment.This diagram shows the configuration of a gNB (base station) according to the embodiment.This diagram shows the protocol stack configuration of the user plane wireless interface that handles data.This diagram shows the protocol stack configuration of the wireless interface of the control plane that handles signaling (control signals).This diagram shows the functional block configuration of AI/ML technology (machine learning technology) in a mobile communication system according to the embodiment.This diagram shows an overview of the operation for each operation scenario according to the embodiment.This is a diagram showing a first operation scenario according to the embodiment.This figure shows a first example of reducing CSI-RS according to the embodiment.This figure shows a second example of reducing CSI-RS according to the embodiment.This is an operation flow diagram showing a first operation pattern related to a first operation scenario according to the embodiment.This is an operation flow diagram showing a second operation pattern related to the first operation scenario according to the embodiment.This is an operation flowchart showing a third operation pattern related to the first operation scenario according to the embodiment.This figure shows a second operation scenario according to the embodiment.This is an operation flowchart showing an example of operation related to the second operation scenario according to the embodiment.This is a diagram showing a third operation scenario according to this embodiment.This is an operation flowchart showing an example of operation related to the third operation scenario according to the embodiment.This figure shows a first operation pattern relating to model transfer according to the embodiment.This figure shows an example of a configuration message including a model and additional information according to the embodiment.This figure shows a second operation pattern relating to model transfer according to the embodiment.This figure shows a third operation pattern related to model transfer according to the embodiment.This figure shows an example of model management according to the embodiment.This figure shows the details of model management according to the embodiment.This figure shows a first operation pattern related to model monitoring according to the embodiment.This figure shows an example of a second operation pattern related to model monitoring according to the embodiment, in which AI/ML technology is applied to CSI feedback.This figure shows another example of a second operation pattern relating to model monitoring according to the embodiment, in which AI/ML