Classifying packets with hierarchical intelligent cuttings

摘要: Increasing demands on Internet router performance and functionality create a need for algorithms that classify packets quickly with minimal storage requirements allow frequent updates. Unlike previous algorithms, the algorithm proposed here meets this well by using heuristics exploit structure present in classifiers. Our approach, which we call HiCuts (hierarchical intelligent cuttings), attempts to partition search space each dimension, guided simple classifier's structure. We discover preprocessing classifier. can tune algorithm's parameters trade off query time against requirements. In classifying based four header fields, performs requires relatively little compared previously described algorithms.