An Algorithm to Construct FP-Tree on VODCA

To construct FP-Tree in mining frequent pattern, we propose a parallel algorithm CFPV (Construct FP-Tree on VODCA) for construct FP-Tree. This method is based on a new parallel computing environment on the distributed shared memory, called View-Oriented, Distributed, Cluster-based Approach to parallel computing (VODCA). It discusses the fact of views division and the results when generate FP-Tree on VODCA, and discusses the dynamic task allocation strategy of the algorithm. The experimental results prove the correctness and effectiveness of CFPV algorithm.