Base Station AI Model Signaling for Low-Latency Mobility Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for deploying AI/ML models on terminals in mobile communication systems face inefficiencies due to overhead and latency issues during mobility, particularly when switching between cells or transmission and reception points, which can hinder the effective utilization of AI/ML technology for improving communication efficiency and quality.
Innovation Solution
A method where a base station determines whether to deliver or share an AI/ML model configuration on a terminal based on the terminal's request, using mapping information to manage AI/ML model updates and switches efficiently, reducing unnecessary data transfer and latency by allowing terminals to update models without new model delivery during mobility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI/ML model configuration is delivered to terminal during mobility, then model update reliability is improved, but overhead and latency increase
Solution Approach 1:
The base station performs preliminary actions by determining in advance whether to deliver AI/ML model configuration based on terminal capability information and mobility state. The terminal performs preliminary actions by requesting model delivery only when necessary, avoiding unnecessary data transfer during mobility events, thus reducing latency while maintaining reliability.
2Reliability
If AI/ML model configuration is delivered to terminal during mobility, then model update reliability is improved, but communication overhead increases
Solution Approach 1:
The patent extracts and processes only the essential information - terminal capability information and mobility state - to determine whether model delivery is necessary. By extracting only relevant data and avoiding unnecessary full model transfers during mobility, the system reduces communication overhead while maintaining update reliability through selective delivery.
Solution Approach 2:
The terminal performs self-service by autonomously determining when model delivery is needed based on its own capability information and mobility state. The base station also autonomously determines delivery necessity, eliminating unnecessary overhead while ensuring reliable updates only when required.
3Reliability
If AI/ML model configuration is delivered to terminal during mobility, then model update reliability is improved, but processing time increases
Solution Approach 1:
The base station and terminal perform preliminary determination actions before actual model delivery, assessing capability information and mobility state in advance. This preliminary action filters out unnecessary processing and data transfer, improving productivity while maintaining reliability through targeted updates.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This base station comprises: a control circuit that determines, on the basis of the presence/absence of a request from a terminal, whether to notify a terminal about an artificial-intelligence-model-related configuration on the terminal side for a wireless interface; and a transmission circuit that transmits a signal relating to the configuration in cases where it has been determined that the terminal is to be notified about the configuration.