AI/ML Handover Configuration Switching in Wireless Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless networks face challenges in efficiently managing handovers between base stations using traditional methods, leading to suboptimal performance due to varying user equipment conditions and network dynamics.
Innovation Solution
Implementing AI/ML models at user equipment and base stations to dynamically update configurations based on UE parameters like speed, location, and signal quality, facilitating seamless handovers by exchanging AI/ML model configuration information through handover command messages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional handover methods are used, then the handover process is simple to implement, but the handover decision accuracy and network performance deteriorate due to inability to adapt to varying UE conditions and network dynamics
Solution Approach 1:
The system performs preliminary actions by pre-configuring multiple AI/ML models with different configurations in the UE before handover occurs. The network provides AI/ML configuration information including multiple model identifiers and configuration parameters in advance, so that when handover is needed, the UE can immediately switch to the appropriate pre-configured model without real-time training or complex selection processes.
Solution Approach 2:
The invention changes parameters by dynamically selecting different AI/ML model configurations based on UE conditions (speed, location, trajectory) and network state. The system varies model parameters such as channel estimation settings, interference cancellation configurations, and beam management parameters according to the specific handover scenario, enabling adaptive optimization without redesigning the entire system.
2Adaptability or versatility
If AI/ML models are updated dynamically during handover, then the adaptability to changing conditions improves, but the signaling overhead and processing time increase
Solution Approach 1:
Multiple AI/ML model configurations are prepared in advance and stored in the UE before handover occurs. The configuration information including model identifiers, parameters, and metadata is provided by the network in prior signaling, enabling instant model switching during handover without real-time generation or selection delays.
Solution Approach 2:
The system uses copied configurations by providing reference information to AI/ML models rather than full model definitions. Configuration identifiers and parameter sets are transmitted instead of complete model data, reducing signaling overhead while enabling rapid deployment of pre-trained models at the target base station.
3Reliability
If multiple AI/ML model configurations are provided for different base stations, then the optimization for specific network conditions improves, but the configuration management complexity increases
Solution Approach 1:
The network acts as an intermediary by centrally managing AI/ML configuration information and providing it to UEs through standardized signaling interfaces. The gNB-configured models and parameters are delivered via RRC signaling, automated message configurations, or other standardized protocols, shielding the UE from the complexity of managing multiple base station-specific configurations while ensuring optimal performance.
4Productivity
If AI/ML configuration information is transmitted in handover command messages, then the handover efficiency improves, but the message size and processing load increase
Solution Approach 1:
Instead of transmitting complete AI/ML model data, the system transmits configuration identifiers, parameter sets, and metadata that reference pre-existing model definitions. This copying approach conveys essential configuration information in compact form, enabling the UE to apply the correct model settings without receiving large volumes of model data in the handover message.
Solution Approach 2:
The invention extracts only the essential configuration elements needed for handover into the handover command message, separating critical parameters (model identifiers, key configuration values) from redundant information. This extraction reduces message size while maintaining the ability to fully configure the AI/ML models at the target base station.
Data Source
AI summary
A method, an apparatus, and a computer readable medium for storing instructions are described for a user terminal and a base station for updating an AI/ML configuration in case of a handover. The method performed by a user equipment comprising operating a first AI/ML configuration in a coverage area of a first base station; receiving an AI/ML configuration information indicating a second AI/ML configuration; operating the second AI/ML configuration indicated by the AI/ML configuration information in the coverage area of a second base station. Operating a first AI/ML configuration comprises operating a first AI/ML Model or a first AI/ML Model with a first AI/ML Model configuration in the coverage area of the first base station. The first AI/ML Model is associated with a first AI/ML Model identifier and the first AI/ML Model configuration is associated with a first AI/ML Model configuration identifier. Operating the second AI/ML configuration comprises operating a second AI/ML Model or the first AI/ML Model with a second configuration in the coverage area of the second base station. The second AI/ML Model is associated with a second AI/ML Model identifier and the second AI/ML Model configuration is associated with a second AI/ML Model configuration identifier. Indicating the second AI/ML configuration comprises indicating a second AI/ML Model identifier and/or a second AI/ML Model configuration identifier.