A case-based reasoning method for alarm filtering and correlation in telecommunication networks

Alarm correlation plays an important role in improving the service and reliability in modern telecommunication networks. As the network grows in size and complexity, the supervisors of network are finding it increasingly difficult to cope with the volume of alarm messages produced even from a single network fault. In this paper, a new using case-based reasoning (CBR) method for alarm correlation in telecommunication networks has been developed. The proposed method has been simulated by developing three main modules: a module for generating faults and alarms, defining network configuration, and alarm filtering and correlation by using case-based reasoning. One of the most important aspects of the obtained results was the speed of the system. Because of its simplicity, the case-based reasoning model is fast, requiring only a few floating-point calculations to produce the result. The accuracy of alarm correlation achieved in the simulation was higher than 90% in the case of unavailability of the required cases