关键词: 分组流分类, 决策树, 时空性能, 参数评估

Abstract:

Heuristic packet classification algorithms based on decision tree aim to classify packets with minimal time and space requirements. In this paper ,an adjustable algorithm based on parameter evaluation is presented. It follows the idea of popular packet classification algorithms,introduces the conception of performance parameters, and adjusts weights of these parameters to aquire data structure with the best performance . Simulations show that , compared with other algorithms of the same kind ,a good improvement can be obtained when using our new algorithm.

Key words: packet classification, decision tree, time and space performance, parameter evaluation