QCL-Based AI Model Switching for Wireless Signal Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communications systems face challenges in efficiently switching between AI/ML models for network entities and user equipment without causing detection errors or degraded performance, requiring substantial coordination between vendors and lacking clear functionality identification and signaling for model switching.
Innovation Solution
Implement a QCL-based relationship between AI/ML models to facilitate model switching, using metadata parameters and channel/environment-related parameters to identify correlations and enable pairing across different network vendors and UE vendors, independent of public model IDs, with a robust framework for functionality-based model switching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI/ML models are switched between network entities and user equipment, then communication performance can be optimized, but detection errors and performance degradation occur due to lack of coordination
Solution Approach 1:
The patent implements feedback mechanisms where the UE reports measurements (RSRP, SINR, channel autocorrelation) to the network entity, which uses this feedback to select appropriate AI/ML models. This closed-loop feedback ensures coordinated model switching that maintains detection accuracy while optimizing communication performance.
Solution Approach 2:
The patent introduces QCL (Quasi-Co-Location) relationships as an intermediary concept to bridge network entity and UE model selection. By establishing QCL relationships between reference signals and AI/ML models, the system enables coordinated switching without direct vendor-specific coordination, resolving the reliability issue.
2Measurement precision
If vendor-specific model identification is used, then model selection can be precise, but substantial coordination between vendors is required
Solution Approach 1:
The patent creates a universal model identification framework using QCL relationships that works across different network and UE vendors. Instead of vendor-specific identifiers, the system uses standardized QCL relationships between reference signals and models, enabling multi-vendor compatibility without sacrificing identification precision.
Solution Approach 2:
The patent changes the identification parameters from vendor-specific model IDs to physics-based parameters (QCL relationships, reference signal characteristics). This parameter transformation maintains measurement precision while eliminating the need for complex vendor coordination.
3Reliability
If explicit model switching signaling is implemented, then model changes can be coordinated, but signaling overhead and processing complexity increase
Solution Approach 1:
The patent performs preliminary model configuration where network entities and UEs pre-establish QCL relationships between reference signals and AI/ML models. This preliminary setup eliminates the need for complex real-time switching signaling, as models can be activated based on simple QCL condition matching.
Solution Approach 2:
The system enables self-service model selection where the UE autonomously measures channel conditions and selects appropriate models based on QCL relationships without requiring explicit network signaling for each model switch. This reduces signaling overhead while maintaining coordination reliability.
Data Source
AI summary
Various aspects of the present disclosure relate to quasi co-location (QCL) indication for AI/ML-based model configuration. An apparatus, such as a UE, receives, from a network entity, an artificial intelligence (AI)-based configuration corresponding to signal transmission and/or signal reception by the UE, where the AI-based configuration is associated with one or more AI models, and an AI model is associated with a dataset that is configured with a set of condition parameters. The UE measures a set of report parameters responsive to a signal received from the network entity, and the set of report parameters are associated with the set of condition parameters of the dataset of the AI model. The UE transmits, to the network entity, one or more feedback parameters based at least in part on the set of report parameters, and the one or more feedback parameters usable by the network entity to select the AI model.