LUCAS - an expert system for intelligent fault management and alarm correlation

The amount of control data flowing across modem communication networks is rapidly increasing. Huge streams of data are flooding the operation and maintenance center (OMC). Thus the operator needs a management system that converts these massive data storms to manageable magnitudes. To achieve this an intelligent alarm filtering system is required to interpret the data stream, thereby simplifying the decision-making process and shortening the operator's reaction time. Such an intelligent tool is the first step on the way to achieving knowledge-based network management. An event correlation tool, called Lucent Correlated Alarm Simulator (LUCAS) has been designed as a prototype for GSM networks. This paper gives an insight into the conception of the tool's architecture and in particular describes the algorithm used for the correlation engine.