FECk: A New Efficient Clustering Algorithm for the Events Correlation Problem in Telecommunication Networks

In this paper we introduce an efficient clustering algorithm embedded in a novel approach for solving the problem of faults identification in large telecommunication networks. Our algorithm is especially designed for the event correlation problem taking into account comprehensive information about the system behaviour. Although alarms are usually useful for identifying faults in such systems, their large number overloads the current management systems, making it extremely difficult to provide an answer within a reasonable response time. The alarm flow presents some interesting characteristics like alarm storm and alarm cascade. For instance, a single fault may result in a large number of alarms, and it is often very difficult to isolate the true cause of the fault. One way of overcoming this problem is to analyze, interpret and reduce the number of these alarms before trying to localize the faults. In this paper, we present FEC_k, and we compare it with some available clustering algorithms by experimenting them with some samples from both simulated and real data from Ericsson´s network.