High Speed Network First-stage Alarm Correlator

At the heart of fault management is alarm correlation. The approach that is used in commercial telecom systems, as specified by international standards, is correlation through monitoring, filtering and masking event alarms. This is vital since it reduces the amount of event instances presented, the symptoms of the fault. The next objective is to automatically present the actual fault. Artificial Intelligence (AI) offers the potential of determining the fault or multiple faults, yet AI has its own problems including dealing with the vast amounts of potential variations in the data. Not least of these problems is the mistrust, by engineers, in the ’non-deterministic’ AI results produced. This paper presents a simple first-stage alarm correlator to reduce the data for both induction and deduction.