KPI Anomaly Detection in Radio Access Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The analysis of vast amounts of key performance indicators (KPIs) in cellular networks is tedious and time-consuming, requiring efficient anomaly detection and analysis techniques to identify and rank common anomalous KPI types across multiple sites and clusters.
Innovation Solution
A KPI analyzer program running on a computing device at a network node continuously collects and analyzes KPI measurements from the Radio Access Network, identifying common anomalous KPI types that satisfy a ubiquity criterion by ranking them based on an anomaly metric, and outputs lists and summaries for further exploration and monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of KPI data is performed using dashboards or spreadsheets, then analysis depth and customization are improved, but analysis time and labor effort increase significantly
Solution Approach 1:
An automated anomaly detection system acts as an intermediary between raw KPI data and human analysts. The system automatically collects KPI measurements from multiple sites, detects anomalies using statistical methods, identifies common anomalous KPI types, and generates structured reports. This intermediary processing reduces the time and effort required for manual analysis while maintaining or improving analysis quality through systematic anomaly detection across vast datasets.
2Loss of information
If comprehensive monitoring of vast arrays of provider equipment and user equipment is implemented, then network performance visibility is improved, but data processing complexity and resource requirements increase
Solution Approach 1:
The system extracts only the most relevant information from vast amounts of KPI data by automatically detecting anomalies and identifying common anomalous KPI types across multiple sites. Instead of processing and presenting all raw data, the system extracts and highlights only the anomalous patterns that require attention, significantly reducing data processing complexity while maintaining comprehensive network performance visibility.
3Measurement precision
If detailed analysis of individual KPI measurements across multiple sites is performed, then anomaly detection accuracy is improved, but identification time and computational resources increase
Solution Approach 1:
The system performs preliminary automated analysis by continuously collecting KPI measurements, detecting anomalies, and identifying common anomalous KPI types across multiple sites before human intervention is needed. This preliminary action prepares structured anomaly reports in advance, enabling rapid identification and response to network issues without requiring manual analysis of individual measurements, thus improving both accuracy and identification speed.
Data Source
AI summary
An analyzer configured to monitor a radio access network (RAN) of a cellular network is provided. The RAN includes multiple clusters that each includes multiple sites and multiple cells. The analyzer receives a multiple key performance indicator (KPI) measurements from the multiple clusters. Each KPI measurements generated for one of several KPI types. The analyzer receives information identifying anomalous KPI measurements in the received KPI measurements. For a cluster of the RAN, the analyzer identifies one or more common anomalous KPI types that satisfy a ubiquity criterion. The analyzer ranks the identified common anomalous KPI types for the cluster based on an anomaly metric that is derived from the anomalous KPI measurements generated for each identified common anomalous KPI type. The analyzer outputs a list of common anomalous KPI types for the cluster based on the ranking.