MDT Measurement Configuration for UE Trajectory Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is no mechanism for collecting and reporting UE trajectory measurements from RAN nodes to OAM, hindering AI/ML model training for network performance optimization.
Innovation Solution
A solution that enables RAN nodes to collect and report UE trajectory measurements to OAM, using Minimization of Drive Test (MDT) for measurement configuration and reporting, allowing UE trajectory data to be used as input for AI/ML model training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If MDT measurement configuration is implemented for UE trajectory collection, then AI/ML model training capability is improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent extends the existing MDT measurement framework to serve dual purposes: traditional network performance monitoring and new UE trajectory collection for AI/ML training. By making the measurement configuration multi-functional, the system can collect both traditional KPIs and trajectory data using the same infrastructure, avoiding the need for separate complex systems.
Solution Approach 2:
The patent introduces a standardized measurement configuration interface that acts as an intermediary between the OAM and RAN nodes. This interface layer simplifies the complex trajectory collection process by providing standardized commands and data structures, making the system easier to implement and manage.
2Measurement precision
If detailed UE trajectory measurements are collected at high granularity, then AI/ML model training precision is improved, but network signaling overhead and processing burden increase
Solution Approach 1:
The patent applies different measurement granularities to different scenarios and requirements. Instead of uniformly collecting high-resolution trajectory data everywhere, the system selectively adjusts measurement precision based on local needs, AI/ML model requirements, and network conditions, thereby reducing overall data volume while maintaining necessary precision.
Solution Approach 2:
The patent dynamically adjusts measurement parameters such as sampling rate, precision level, and reporting frequency based on network conditions, UE mobility patterns, and AI/ML training requirements. This allows the system to optimize between data precision and volume by changing parameters adaptively rather than using fixed high-granularity settings.
Data Source
AI summary
Embodiments of the present disclosure relate to apparatuses, methods, and computer readable storage media for data collection. A first apparatus prepares a measurement collection configuration comprising a list for Minimization of Drive Test (MDT) measurement collection and a measurement granularity. The list comprises at least one second apparatus and a corresponding cell. The first apparatus transmits, to the at least one second apparatus, the measurement collection configuration for triggering an MDT measurement activation for terminal device trajectory. The first apparatus receives, from the at least one second apparatus, at least one MDT measurement report for a machine learning (ML) model training at the first apparatus, the at least one measurement report comprising terminal device trajectory measurements collected based on the measurement collection configuration.