Abstract: The mining of association rules is one of the primary methods used in telecommunication alarm correlation analysis, in which the alarm databases are very large. The efficiency of the algorithms plays an important role in tackling large datasets. The classical FP-growth algorithm can produce a large number of conditional pattern trees which makes it difficult to mine association rules in telecommunication environment. In this paper, an algorithm LFPTDP based on the Layered Frequent Pattern Tree is proposed for mining frequent patterns and deleting infrequent items with dynamic pruning which can avoid producing conditional pattern trees. Analysis and simulation show that it is a valid method with better time and space efficiency, which is adapted to mining association rules in telecommunication alarm correlation analysis.

Key words: association rules, alarm correlation analysis, conditional pattern tree, Layered Frequent Pattern Tree