Download now Free registration required
This paper presents an efficient clustering algorithm for faults identification in large telecommunication networks. The alarms and faults in telecommunication networks present some interesting characteristics like storm and cascade of events. 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 a fault. The authors' algorithm is especially designed for the event correlation problem taking into account comprehensive information about the system behaviour. Their technique is tested and compared with some available clustering algorithms on some samples from both simulated and real data from Ericsson's network.
- Format: PDF
- Size: 476.26 KB