AI Mobility Measurement Parameter Selection for Robust Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current solutions for mobility measurement parameter settings in wireless communication systems, such as 5G NR, lack robustness in accommodating radio-related situations, leading to potential radio link failures and handover failures, especially for latency-sensitive services like XR applications.
Innovation Solution
Implementing AI/ML models for selecting and dynamically updating mobility measurement parameters at the UE level, allowing for timely and accurate reporting of mobility measurements to prevent radio link failures and handover failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional mobility measurement parameter settings are used, then the system operation is simple, but the robustness against radio link failures and handover failures deteriorates
Solution Approach 1:
The UE autonomously selects mobility measurement parameters based on its own AI/ML model predictions without requiring network configuration or control. The UE self-determines the optimal parameters (e.g., timeToTrigger, hysteresis) based on predicted channel conditions, removing the need for complex network-side parameter management while improving reliability through adaptive, context-aware selection.
Solution Approach 2:
The system dynamically changes mobility measurement parameters based on AI/ML model predictions of future channel conditions. Instead of using fixed or network-configured parameters, the UE adjusts parameters like timeToTrigger and hysteresis in real-time according to predicted radio conditions, enabling adaptive optimization that improves handover reliability without requiring complex network intervention.
2Measurement precision
If AI/ML models are implemented for dynamic parameter selection, then the robustness and accuracy of mobility measurements improve, but the device complexity and computational requirements increase
Solution Approach 1:
The AI/ML model performs preliminary predictions of future channel conditions before handover decisions are needed. By predicting radio conditions in advance and pre-determining optimal parameters, the system avoids the need for complex real-time calculations during critical handover moments, reducing computational burden while maintaining high measurement accuracy.
Solution Approach 2:
The patent extracts the complex AI/ML processing functionality from the network side and places it in the UE. This allows the network to remain simple while the UE handles the computational complexity locally, enabling accurate measurements without increasing network device complexity. The UE's AI/ML model operates independently using local measurements and predictions.
3Adaptability or versatility
If traditional parameter settings are used, then the system operation is simple and fast, but the adaptability to different radio situations deteriorates
Solution Approach 1:
The system transitions from static, network-configured parameters to dynamic, UE-selected parameters that adapt in real-time to changing radio conditions. The UE continuously monitors channel conditions and adjusts mobility measurement parameters dynamically based on AI/ML predictions, enabling the system to adapt to diverse and varying radio situations without requiring complex network reconfiguration.
Data Source
AI summary
AI native mobility measurement parameters selection is described. An apparatus is configured to obtain a set of mobility measurements associated with a set of network nodes. The set of network nodes includes a serving cell and at least one neighboring cell. The apparatus is configured to select a set of mobility measurement parameters, associated with a set of mobility parameter ranges, in accordance with an AI/ML model and based on at least one of the set of mobility measurements or a set of measurement configurations indicative of at least one of a set of mobility measurement parameter candidates or the set of mobility parameter ranges. The apparatus is configured to transmit, to the serving cell and at a time in accordance with the AI/ML model, a selected value report indicative of a set of mobility measurement values associated with the set of mobility measurement parameters.