UE AI Model Selection for Accurate CSI Measurement Reports
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in accurately generating measurement reports, such as CSI reports, due to the large size of the data which leads to reduced accuracy when compressed, and the need to switch between different reporting configurations for varying channel conditions.
Innovation Solution
Implementing multiple AI models trained on different conditions like UE location, orientation, and LoS/NLoS status, allowing the UE to select the appropriate model for generating measurement reports based on current conditions, thereby maintaining consistent CSI reporting without introducing compression distortion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If compression is applied to reduce the size of measurement report data, then data size is reduced, but accuracy of the measurement report deteriorates
Solution Approach 1:
The patent segments the AI model into multiple specialized models, each trained on specific channel conditions (LoS, NLoS, indoor, outdoor). Instead of compressing a single large model, the system selects and applies the most appropriate segmented model for each condition, maintaining accuracy while managing data requirements through selective application.
Solution Approach 2:
The patent changes the parameter of model selection based on channel conditions. The UE determines which AI model to apply by assessing current channel conditions (LoS/NLoS, indoor/outdoor), thereby adapting the model parameters to match the current environment and maintain measurement accuracy without unnecessary compression.
2Adaptability or versatility
If multiple reporting configurations are used to handle varying channel conditions, then adaptability to different conditions is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal AI model selection mechanism that handles multiple channel conditions through a single framework. The UE assesses current conditions and selects the appropriate pre-trained model, providing multi-functionality without requiring separate complex processing paths for each condition.
Solution Approach 2:
The patent applies preliminary action by pre-training multiple AI models for different channel conditions before actual measurement report generation. This allows the UE to quickly select the appropriate model based on current conditions without complex real-time training or configuration switching, reducing operational complexity.
3Measurement precision
If AI models are trained on specific channel conditions, then measurement accuracy for those conditions is improved, but the ability to handle unknown conditions deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the UE reports not only the measurement results but also indicates which AI model was used for generation. This feedback allows the network to understand the conditions under which measurements were taken and adjust subsequent measurements or model selections accordingly, improving accuracy while maintaining adaptability through continuous learning.
Data Source
AI summary
Various aspects of the present disclosure relate to a use equipment (UE) configured with multiple artificial intelligence (AI) models each of which has been configured (e.g., trained) based on training data sets corresponding to one or more of different conditions, such as location of the UE, orientation of the UE, whether the UE is indoors or outdoors, whether the UE is line-of-sight or non-line-of-sight with a base station, and so forth. A network entity (e.g., a gNB) configures the UE with a set of reference signals for measurement of at least one quantity. The UE generates the measurement report based at least in part on the set of reference signals and one of the multiple AI models, and transmits the measurement report to the network entity (e.g., gNB).