Automatic fault detection and diagnosis in cellular networks using operations support systems data

Self-Healing is one of the key important functionalities in self-organizing mobile communication networks. Despite its importance, self-healing has yet to receive a deserving research attention in the literature. This paper considers important quality indicators in a live mobile communications network and presents an automatic unified detection and diagnosis framework to identify root causes of faults occurred in the network. The proposed solution relies on unsupervised clustering of both traffic and signaling (continuous) key performance indicators for diagnosis. Hence, it is immune to the human error in the modeling phase. It also allows to effectively encapsulate experts knowledge as they relate clusters to root causes in the design phase. Detailed analysis of fault detection, the clustering schemes and the diagnosis are provided using operations support systems data of a real cellular network.