An algorithm of multi-level fuzzy association rules mining with multiple minimum supports in network faults diagnosis

The alarm correlation analysis based on multi-level fuzzy association rules mining is the cutting-edge field of the network fault diagnosis research. In the application environment of alarms in communication networks, multi-level fuzzy association rules mining algorithms are proposed, and two strategies are adopted to set minimum support, which are multiple minimum supports and one minimum support. Simulations are carried out to the comparison of algorithms under the two strategies. Multi-level fuzzy association rules mining of alarms is effectively realized. The advantages and efficiency of algorithms are demonstrated by the experiments.