AI/ML User Equipment CSI Feedback for Reduced Reference Signal Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication systems face challenges in efficiently utilizing artificial intelligence and machine learning (AI/ML) technologies for wireless communication, particularly in optimizing channel state information (CSI) feedback and reducing overhead in reference signal transmission.
Innovation Solution
Implementing AI/ML models on user equipment (UE) for intelligent CSI feedback and reference signal reduction by performing model training and inference, enabling accurate CSI feedback using partial reference signals and optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI/ML models are implemented on user equipment for intelligent CSI feedback and reference signal reduction, then CSI accuracy is improved and overhead is reduced, but device complexity increases
Solution Approach 1:
The patent introduces AI/ML models as intermediary components between the reference signal reception and CSI feedback generation processes. These models act as mediators that process reference signal data and environment information to produce accurate CSI feedback with reduced overhead, thereby resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent changes the parameters of the communication system by implementing AI/ML-based processing instead of traditional signal processing methods. This parameter change enables the system to achieve higher CSI accuracy with reduced reference signal overhead, while the complexity increase is managed through efficient model design and selection
2Productivity
If AI/ML processing is performed at user equipment, then productivity is improved through optimized resource utilization, but use of energy increases
Solution Approach 1:
The patent implements dynamic AI/ML model selection and configuration at the user equipment, allowing the system to adaptively choose between different model complexities based on current communication conditions. This dynamic approach optimizes resource utilization while managing power consumption by using simpler models when appropriate and more complex models only when necessary for performance
Solution Approach 2:
The patent applies partial AI/ML processing by selectively using AI/ML models for specific CSI feedback scenarios rather than all scenarios. This partial action approach improves productivity in critical situations while limiting energy consumption by avoiding unnecessary AI/ML processing in situations where traditional methods suffice
Data Source
AI summary
A communication method for applying an artificial intelligence or machine learning (AI/ML) technology to wireless communication between a user equipment and a network in a mobile communication system includes receiving, by the user equipment, environment information from the network, the environment information indicating an communication environment of a coverage area corresponding to a location of the user equipment, and performing, by the user equipment, AI/ML processing among learning processing and/or inference processing using an AI/ML model, based on the environment information.