Classification and Root-Cause Analyzing Tool
Analysis of the RAN for 2G to 5G
CARAT is focusing on mobile communication networks starting from 2G up until 5G. The analysis is performed for speech and data transactions, so that a thorough result of recorded issues is reported. The analysis includes incomplete transactions (failed or dropped) as well as successful ones. It covers correctness, completeness, and quality for the events.
Based on our expertise in wireless communication networks we identified patterns in traces that identify problems or failures of measurement equipment or measured network. This offers an in-depth analysis of the recorded behavior in the traces and allows the user to work on efficiently on solving identified issues.
Classification
With CARAT’s analysis, many different patterns are detected and assigned to the following classes.
AI / ML in CARAT
The integration of more advanced machine learning methods (AI/ML) in CARAT serves to improve the ability to classify unknown patterns and increase classification accuracy. This is achieved through a combination of supervised and unsupervised ML algorithms, giving us the best of both worlds. While we want to uncover the hidden patterns in the complex data sets with the unsupervised ML algorithms, the supervised part ensures the validity of our results.
Data sources for the analysis
- Drive/Walk test data from Swissqual, Infovista, Focus Infocom …
- Crowd data (UE-based measurements)
- Protocol traces (PCAP) from the core and RAN
- Application test data (voice, interactivity, performance, capacity, …)
