AI/ML TRP Subset Positioning for Lower Wireless Signaling Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently performing wireless signal transmission and reception processes.
Innovation Solution
The implementation of artificial intelligence/machine learning (AI/ML) models for configuring transmission and reception points (TRPs) in user equipment (UE) to optimize positioning-related reports, allowing for dynamic adjustment of TRP subsets based on line-of-sight/non-line-of-sight information, signal measurements, and UE location, with performance monitoring and reconfiguration when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI/ML models are configured for multiple TRPs to improve positioning accuracy, then positioning precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the TRP set into multiple subsets, with each AI/ML model configured for a specific subset rather than all TRPs. This segmentation allows the system to manage complexity by handling smaller groups separately while still achieving accurate positioning through coordinated use of multiple subsets.
Solution Approach 2:
The patent enables dynamic selection and configuration of TRP subsets based on current positioning requirements and environmental conditions. The system can adaptively adjust which TRP subsets are active and which AI/ML models are deployed, optimizing the balance between positioning accuracy and computational complexity in real-time.
2Measurement precision
If TRP subset configuration is optimized for positioning performance, then positioning accuracy is improved, but signaling overhead increases
Solution Approach 1:
The patent extracts and reports only the essential positioning information from the TRP subset configurations, rather than transmitting complete configuration details. This selective reporting reduces signaling overhead while maintaining the necessary information for accurate positioning calculations.
Solution Approach 2:
The system uses reference configurations and templates for TRP subset setups, allowing the network to define standardized patterns that can be reused. This copying approach reduces the need for extensive individual configuration signaling for each TRP subset while maintaining positioning accuracy.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
A method performed by a terminal in a wireless communication system, according to at least one of embodiments disclosed in the present specification, may comprise: configuring at least one artificial intelligence/machine learning (AI/ML) model related to multiple transmission and reception points (TRPs) for positioning; acquiring input data subsets on the basis of TRP subsets of the multiple TRPs; acquiring positioning information output from the at least one AI/ML model on the basis of the input data subsets; and transmitting a positioning-related report to a network on the basis of the positioning information, wherein the positioning-related report may include information on at least one of the TRP subsets or the input data subsets.