AI-Driven Reference Signal Management for 5G UE Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems face challenges in efficiently managing reference signals and beams for measurement and reporting, leading to resource overhead and power consumption issues, especially in 6G communication systems operating in the terahertz band, where severe path loss and atmospheric absorption necessitate improved coverage and spectral efficiency.
Innovation Solution
The implementation of an AI-based method for managing reference signals and beams, where AI models are used to determine optimal measurement and reporting sets, reducing the need for exhaustive measurements and improving resource allocation and power efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If exhaustive reference signal measurements are performed for all beams, then measurement precision is improved, but device complexity and power consumption increase
Solution Approach 1:
The patent segments the complete beam measurement task into two phases: first, a reduced set of candidate beams is identified using AI/ML models based on historical data and current channel conditions; second, measurements are performed only on these candidate beams. This segmentation reduces the measurement set from all possible beams to a manageable subset, lowering device complexity while maintaining measurement precision for the most relevant beams.
Solution Approach 2:
The patent applies preliminary action by using AI/ML models to predict and identify candidate beams before actual measurements are performed. The model pre-processes historical measurement data and current channel state information to generate a predicted set of candidate beams, so that when measurements are taken, only the most promising beams are measured. This preliminary identification step reduces the overall measurement complexity while preserving measurement precision.
2Measurement precision
If exhaustive reference signal measurements are performed for all beams, then measurement precision is improved, but power consumption increases
Solution Approach 1:
The patent segments the power-consuming measurement operations by dividing beams into two groups: candidate beams identified by AI/ML models and non-candidate beams. Measurements are performed only on the segmented candidate beam subset, significantly reducing the number of power-intensive measurement operations while maintaining precision for the most relevant beams through intelligent selection.
Solution Approach 2:
The patent applies partial action by performing measurements on only a partial set of candidate beams rather than all beams. The AI/ML model determines the optimal subset of beams that are most likely to be useful based on historical data and current conditions, so measurements are performed partially on the full beam set, reducing power consumption while maintaining sufficient measurement precision for network operation.
3Productivity
If AI models are used to determine optimal measurement sets, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent introduces an intermediary AI/ML model that acts as a mediator between historical measurement data and current beam selection decisions. The model is trained offline using historical data and then deployed to generate candidate beam predictions. This intermediary component translates complex historical patterns into simple candidate beam recommendations, improving productivity while containing implementation complexity through the use of pre-trained models rather than real-time complex computation.
Data Source
AI summary
The present disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates beyond a 4G communication system such as long term evolution (LTE). A user equipment (UE), a base station and a method performed by the same in a wireless communication system are provided. The method includes determining a first reference signal set for measurement, performing measurement to obtain one or more measurement results based on the determined first reference signal set, and performing reporting based on the one or more measurement results. The first reference signal set is generated based on a first artificial intelligence (AI) model, or the one or more measurement results are generated based on a second AI model. The present disclosure can reduce resource overhead and power consumption of the UE.