UE Measurement Logging Across RRC States for AI/ML Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legacy MDT systems are inadequate for wireless communication systems supporting AI/ML, as they limit data logging to the RRC idle state and allow only a single measurement configuration, which restricts the flexibility needed for dynamic conditions and AI/ML model training.
Innovation Solution
The system enables simultaneous multiple data collection configurations for network performance measurement, logging, and reporting in both RRC idle and connected states, allowing flexibility and continuity across RRC states, with conditions for activating, deactivating, or suspending configurations based on network or UE conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If legacy MDT systems use a single measurement configuration and limit logging to RRC idle state, then device complexity is reduced, but adaptability and versatility are insufficient for AI/ML training requirements
Solution Approach 1:
The patent segments the measurement configuration into multiple independent configurations (first measurement configuration and second measurement configuration), each with distinct measurement objects, reporting configurations, and logging parameters. This segmentation allows the system to collect diverse measurement data suitable for different AI/ML training scenarios while maintaining manageable complexity through modular organization of measurement tasks.
Solution Approach 2:
The patent implements dynamic configuration management by introducing activation and deactivation mechanisms for different measurement configurations based on RRC states. The system can dynamically switch between configurations depending on whether the UE is in RRC idle or connected state, and can activate or deactivate specific configurations based on network conditions, thereby achieving adaptability without permanent complexity overhead.
2Adaptability or versatility
If multiple data collection configurations are implemented simultaneously, then adaptability for AI/ML training is improved, but memory usage increases
Solution Approach 1:
The patent implements dynamic configuration management by introducing activation and deactivation mechanisms for different measurement configurations based on RRC states. The system can dynamically switch between configurations depending on whether the UE is in RRC idle or connected state, and can activate or deactivate specific configurations based on network conditions, thereby achieving adaptability without permanent complexity overhead.
Solution Approach 2:
The patent applies discarding and recovering principles by implementing state-based management where measurement configurations are activated only when needed for specific RRC states. When transitioning between RRC states, the system can deactivate or discard configurations that are no longer relevant, freeing up memory resources while maintaining the capability to recover and activate them when needed again.
3Productivity
If measurement configurations are limited to single configuration, then device complexity is reduced, but productivity for data collection is insufficient
Solution Approach 1:
The patent segments the measurement configuration into multiple independent configurations (first measurement configuration and second measurement configuration), each with distinct measurement objects, reporting configurations, and logging parameters. This segmentation allows the system to collect diverse measurement data suitable for different AI/ML training scenarios while maintaining manageable complexity through modular organization of measurement tasks.
Solution Approach 2:
The patent implements multi-functionality by designing a unified measurement framework that can handle multiple measurement configurations simultaneously. The system provides universal capabilities for configuring, activating, deactivating, and managing multiple measurement tasks through a common interface and control mechanism, thereby improving productivity without proportionally increasing device complexity.
Data Source
AI summary
Various aspects of the present disclosure relate to a UE for wireless communication with at least one memory and at least one processor coupled with the at least one memory and configured to cause the UE to receive a first message comprising a data collection configuration from a network entity, the data collection configuration comprising at least one measurement configuration, at least one logging configuration, and at least one reporting configuration, perform measurements according to a measurement configuration of the at least one measurement configuration, log measurement data associated with the measurements according to a logging configuration of the at least one logging configuration by storing the measurement data in the at least one memory, and transmit a second message to the network entity based on a reporting configuration of the at least one reporting configuration, the second message comprising the logged measurement data.