Research on similarity mapping algorithm for high-speed Ethernet.

This paper proposed an adaptive similarity mapping algorithm for high-speed Ethernet based on the special nature of user behavior and characteristics of the flow quintuple. It fully considered the random distribution of the quintuple in this algorithm and designed an improved XOR-SHIFT algorithm for flows classification. This paper raised concepts of similar database and heterogeneous database and designed similarity comparison functions for this two databases. With this method, similar eigenvalues can be mapped to data files precisely and matching efficiency is improved. It carried out some simulation tests in the campus network and proved that this mapping algorithm has higher precision and applicability than other methods. It is appropriate to search similarity flows in large data networks. [ABSTRACT FROM AUTHOR]