Detection and Correlation of Digital Anomalies

Client 23 companies
Scope Of Work 2 years
Architect Lucas Wilson

Project Detail

Anomaly detection is essential, because it allows a rapid reaction to the problems and helps assuring performance and security in computer networks. Our company presents an anomaly detection system based on the traffic characterization performed by the BLGBA model, which is responsible for the DSNS generation and an alarm system that compares the DSNS and the real movement obtained in SNMP objects, sending the alarms to a correlation system when a behavior deviation is detected.

It’s a full correlation system based on a directed graph which represents the possible paths of anomaly propagation through the SNMP objects in a network element. Three years of data collected from the our business partner’s networks were used to evaluate this anomaly detection system. The results were encouraging and confirmed that our system is able to detect anomalies on the monitored network elements, avoiding the high false alarms rate.

Now we are ready and proud to move our system to the new high level industry productivity. Using our solution your business will be flexibility and fully covered from the critical financial risks in case of full analytics and detection the wrong and danger anomalies in-house business processes.