AI/ML Beam Management with Adaptive Beam Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing beam management systems in 5G wireless communication face challenges in efficiently managing beam failure recovery (BFR) using artificial intelligence and machine learning (AI/ML) models, leading to potential performance degradation due to unreliable models and repeated triggering of BFR.
Innovation Solution
A method and apparatus are provided to trigger beam failure recovery using AI/ML models, deactivate them based on a specific time duration, and transmit deactivation information to the base station, including features like timers and maximum count mechanisms to prevent persistent beam failure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI/ML models are used for beam management, then beam management efficiency is improved, but system reliability deteriorates due to model unreliability causing persistent beam failure
Solution Approach 1:
The patent implements dynamic switching between AI/ML-based beam management and conventional beam management modes. The system monitors beam failure recovery triggering frequency and automatically switches from AI/ML mode to conventional mode when failure thresholds are exceeded, allowing the system to adapt its operational characteristics based on real-time conditions while maintaining the benefits of AI/ML under normal operating conditions
Solution Approach 2:
The system changes the operational parameters of beam management by adjusting the model triggering frequency threshold and time duration parameters. By dynamically modifying these parameters, the system can control when AI/ML models are triggered and deactivated, optimizing the balance between beam management efficiency and system reliability based on current network conditions
2Productivity
If AI/ML models are continuously activated for beam management, then beam management performance is improved, but system complexity increases due to model management overhead
Solution Approach 1:
The patent implements periodic deactivation and activation of AI/ML models based on monitored performance metrics. Instead of continuous operation, the system periodically evaluates beam failure recovery triggering frequency and switches model activation status accordingly, reducing computational overhead and system complexity while maintaining performance benefits during periods when AI/ML models are active
Solution Approach 2:
The system extracts and isolates the AI/ML model management functionality from the core beam management process by implementing separate model activation/deactivation control mechanisms. This allows the main beam management system to operate with reduced complexity while AI/ML capabilities are available when needed, effectively separating the complex AI/ML component from the essential beam management functions
3Speed
If beam failure recovery is frequently triggered, then beam management responsiveness is improved, but system performance deteriorates due to persistent beam failure
Solution Approach 1:
The patent implements a feedback mechanism that monitors beam failure recovery triggering frequency and uses this information to control AI/ML model activation. When the feedback indicates excessive beam failure recovery triggering, the system deactivates the AI/ML model to prevent performance deterioration, while maintaining the capability to quickly respond to legitimate beam failures when conditions are favorable
Data Source
Figure 1~2
Figure 3A~3C
Figure 4~5
AI summary
Provided are a method and an apparatus for performing beam management in a wireless communication system. The method of a terminal may include triggering at least one beam failure recovery (BFR) for a cell that performs beam management using an artificial intelligence and/or machine learning model, deactivating the artificial intelligence and/or machine learning model based on the number of the at least one beam failure recovery triggered during a specific time duration, and transmitting deactivation information of the artificial intelligence and/or machine learning model to a base station. The method of the base station may include transmitting, to the terminal, configuration information related to the artificial intelligence and/or machine learning model, receiving, from the terminal, the deactivation information of the artificial intelligence and/or machine learning model, and, based on the received deactivation information, stopping beam generation related to the artificial intelligence and/or machine learning model.