Topographical proximity: exploiting domain knowledge for sequential data mining

Abstract

In today?s mobile telecommunications networks, increasingly powerful fault management systems are required to ensure robustness and quality of service of the network. In this context, fault alarm correlation is of prime importance to extract meaningful information from the vast quantities of alarms generated by the network. Existing sequential data mining techniques address the task of identifying possible correlations in frequent sequences of telecoms alarms. These frequent sequence sets, however, may contain sequences which are not plausible from the point of view of network topology constraints. This paper presents the Topographical Proximity (TP) approach which exploits the topographical information encoded in telecommunication alarms in order to address this lack of plausibility in mined alarm sequences. An evaluation of the quality of mined sequences is presented and discussed. Results show an improvement in overall system performance for imposing proximity constraints.