AI Model Switching for Wireless Feedback and Beam Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication systems face challenges in efficiently utilizing AI/ML models for wireless communication, particularly in reducing overhead and power consumption while maintaining accurate channel state information feedback, beam management, and positioning accuracy.
Innovation Solution
Implementing AI/ML models in user equipment and network nodes to optimize resource usage by training and inferring models for reduced reference signals, such as CSI-RS and PRS, enabling efficient feedback and power management through model switching between training and inference modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI/ML models are implemented in user equipment and network nodes to optimize resource usage, then productivity and efficiency are improved, but device complexity increases
Solution Approach 1:
The patent introduces a model management entity that acts as an intermediary between network nodes and user equipment. This entity handles the complex tasks of model distribution, selection, and coordination, allowing the AI/ML models to improve productivity without directly increasing the complexity burden on individual devices. The intermediary abstracts and centralizes the management complexity.
2Adaptability or versatility
If multiple AI/ML models are deployed for different functions, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal model management framework that can handle multiple different AI/ML models through a single standardized interface and coordination mechanism. This allows the system to support diverse functionalities (channel state information feedback, beam management, positioning) without requiring separate management systems for each model type, thereby improving adaptability while controlling complexity.
3Use of energy by moving object
If AI/ML models are used for reduced reference signals, then loss of information increases, but use of energy decreases
Solution Approach 1:
The patent utilizes AI/ML models to change the parameters of reference signals, transforming them from traditional formats to compressed or reduced representations. The models learn optimal parameter transformations that maintain essential channel state information while reducing signal overhead, thereby achieving energy savings without significant information loss.
4Productivity
If model switching between training and inference modes is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent implements dynamic model switching between training and inference modes based on real-time system conditions and requirements. The model management entity dynamically selects appropriate operational modes for different AI/ML models, allowing the system to adapt its complexity and processing demands according to current needs, thereby improving productivity without requiring permanently high complexity.
Data Source
AI summary
In an aspect, a communication control method is a communication control method in a mobile communication system. The communication control method includes a step of transmitting to a user equipment, by a base station, at least either of model information indicating information relating to a plurality of respective first AI/ML models or an execution condition indicating a condition for executing a predetermined operation for a plurality of respective second AI/ML models. Here, the base station holds the plurality of first AI/ML models, and the user equipment holds the plurality of second AI/ML models.