AI/ML RNA Optimization for RRC-Inactive UE Paging Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G RAN-based Notification Areas (RNA) may include anomaly cells with poor performance, leading to poor communication experiences for UEs in RRC_INACTIVE state due to issues like RACH failures and paging issues, as gNodeB is unaware of cell details during UE mobility.
Innovation Solution
Utilizing a Radio Intelligent Controller (RIC) with AI/ML techniques to detect anomaly cells based on KPIs, PMs, CMs, and FM data, recommending actions such as excluding or disabling RRC connections to improve RNA optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If anomaly cells are included in RNA configuration, then RNA coverage area is improved, but UE communication reliability deteriorates due to paging issues and RACH failures
Solution Approach 1:
The patent extracts and removes anomaly cells from the RNA configuration based on AI/ML detection of abnormal patterns in KPIs, performance measurements, and fault management data. This selective removal maintains RNA coverage for healthy cells while excluding problematic cells that cause paging failures and RACH issues, thereby resolving the contradiction between coverage area and communication reliability.
Solution Approach 2:
The patent implements a feedback mechanism where the RIC continuously monitors cell performance metrics and dynamically adjusts RNA configuration based on detected anomaly patterns. The system uses KPI trends, performance measurements, and fault data to provide feedback on cell health status, enabling adaptive RNA optimization that balances coverage area with communication reliability through continuous monitoring and reconfiguration.
2Reliability
If gNodeB monitors all cell details for UE mobility, then UE communication reliability is improved, but device complexity increases
Solution Approach 1:
The patent introduces an intermediary RIC (Radio Intelligent Controller) that handles the complex task of monitoring and analyzing cell performance data using AI/ML techniques. The RIC acts as a mediator between the gNodeB and the anomaly detection function, processing KPIs, performance measurements, and fault management data to identify anomaly cells. This intermediary approach enables reliable UE communication monitoring without increasing gNodeB complexity, as the RIC performs the sophisticated analysis externally.
3Measurement precision
If AI/ML techniques are deployed for anomaly detection, then measurement precision is improved, but device complexity increases due to RIC implementation
Solution Approach 1:
The patent enables the RIC to perform self-service anomaly detection by autonomously analyzing performance measurements, KPIs, and fault management data using embedded AI/ML models. The system automatically identifies anomaly cells, determines their status, and triggers appropriate actions without requiring manual configuration or intervention. This self-service capability achieves high measurement precision for anomaly detection while managing system complexity through automated decision-making and adaptive learning algorithms.
Data Source
Figure 1
Figure 2
AI summary
A method of optimizing Radio Access Network-based Notification Area (RNA) in the case a user equipment (UE) transitions to radio resource control inactive (RRC_INACTIVE) state includes: detecting, by a radio intelligent controller (RIC) using artificial intelligence (AI) and/or machine learning (ML) technique (e.g., State Vector Machine or Isolation Forest), an anomaly cell based on at least one of the following factors: key performance indicators (KPIs), performance measurements (PMs), configuration parameters (CMs), fault management (FM) data, and trace data; determining, by the RIC, based on the at least one of the factors, a cause for the detected anomaly cell; and recommending, by the RIC to a gNodeB associated with the RNA having the anomaly cell, at least one of the following actions: a) exclude the anomaly cell from the RNA, and b) disable new radio resource control (RRC) connections from the UE.