An Improved Anomaly Detection and Diagnosis Framework for Mobile Network Operators
13 June 2013
The ever increasing complexity of commercial mobile networks summons the need for methods capable to reduce human workload required for network troubleshooting. To address this issue the authors of this paper have developed an automatic anomaly detection and diagnosis framework for mobile network operators. In this paper we discuss the latest improvements introduced to that framework. These include more sophisticated profiling and detection capabilities. The new algorithms further eliminate the need of human intervention related to proper configuration of the profiling and anomaly detection apparatus. The main concepts of the new approach are described and clarified with an explanatory showcase using live network performance data.?