CADMANT: Context Anomaly Detection for MAintenance and Network Troubleshooting

In telecommunications network troubleshooting, analytical applications are widely used. Such applications typically use CEP (Complex Event Processing) and SQL queries for data processing and network analysis. Performance engineers need in-depth knowledge of both the telecommunications domain and telecommunications data structures in order to create the required queries. Moreover valuable information contained in free form text data fields such as “additional_info”, “user_text” or “problem_text” can also be ignored. This work proposes CADMANT: Context Anomaly Detection for MAintenance and Network Troubleshooting. Traditional approaches focus on a specific record type and create specific cause and effect rules. With the CADMANT approach all free form text fields of alarms, logs, etc. are treated as text documents similar to Twitter feeds. CADMANT uses distance based outlier detection within sliding windows to detect abnormal terms at configurable time intervals. The CADMANT approach provides automated analysis without the requirement for SQL/CEP queries and provides distinct network insights in comparison to traditional approaches.