UE Measurement Reporting with Dynamic ML Model Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems lack efficient methods for measurement reporting that leverage machine learning (ML) models to optimize performance and reduce power consumption in user equipment (UE).
Innovation Solution
Implementing a method and apparatus for measurement reporting in wireless communication systems using multiple ML models, where UE receives configurations from a network, determines a set of ML models, obtains measurement results, and transmits them back, optimizing performance and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple ML models are configured for measurement reporting, then measurement accuracy and reliability are improved, but device complexity and power consumption increase
Solution Approach 1:
The patent divides the ML model configuration into multiple independent models, each specialized for specific measurement tasks. The network configures a plurality of ML models with different architectures and parameters, allowing the UE to select and execute only the relevant models for current measurement conditions, thereby improving reliability while managing complexity through functional segmentation
Solution Approach 2:
The patent implements dynamic model selection where the UE determines which subset of configured ML models to use based on current measurement requirements, channel conditions, and power availability. This dynamic adaptation allows the system to maintain high reliability when needed while reducing operational complexity and power consumption during normal operation
2Measurement precision
If multiple ML models are configured for measurement reporting, then measurement precision is improved, but power consumption increases
Solution Approach 1:
The patent applies partial action by configuring multiple ML models but executing only the necessary subset for each measurement task. The UE determines which models to activate based on current precision requirements, avoiding the power consumption of running all models continuously while maintaining measurement precision when needed
Solution Approach 2:
The patent changes operational parameters by adjusting which ML models are active based on power availability and measurement precision requirements. The network can modify model configuration parameters, and the UE adapts model selection based on battery status, allowing precision to be maintained during high-power states while conserving energy during low-power states
3Reliability
If ML models are used for measurement reporting, then service quality is improved, but device complexity increases
Solution Approach 1:
The patent implements self-service by enabling the UE to autonomously determine which ML models to execute based on configured criteria and current conditions. The UE automatically selects appropriate models without requiring manual configuration or complex user intervention, maintaining service quality while simplifying operation through automated model management
Data Source
AI summary
The present disclosure relates to measurement reporting based on machine learning in wireless communications. According to an embodiment of the present disclosure, a method performed by a user equipment (UE) configured to operate in a wireless communication system comprises: receiving, from a network, a configuration for measurement reporting related to a plurality of machine learning (ML) models; determining a set of ML models for measurement reporting among the plurality of ML models configured for the UE, based on the configuration; obtaining measurement results by taking inputs to the set of ML models; and transmitting, to the network, at least one of the measurement results.