원문정보
초록
영어
Traffic classification is critical to effective network control and management. Recent researches on Internet traffic classifications have developed several methods for identifying types of application, which have advantages in certain types of network traffic. However, these methods are powerless to measure the network traffic with dynamic port, encrypted payloads, mixing traffic, and real-time traffic. In response to the growing requirements of traffic classification for increasingly complex network environment, this paper introduces network traffic classification architecture (NTCA) with high performance. By combining port-based, signature string matching, regular expression matching, and machine learning methods, NTCA achieves high speed and accuracy traffic classification. The experimental results show that our proposed method is able to achieve over 95.0% in average accuracy for all testing traces.
목차
1. Introduction
2. The Framework of NTCA
3. Traffic Classification Engine
3.1. Port-Based Matching
3.2. Signature String Matching
3.3. Regular Expression Matching
3.4. Machine Learning Method
3.5. The Hybrid Method
4. Experiments on Traffic Classification
4.1. Data Sets
4.2. Performance Metrics
4.3. Experimental Methodology
5. Conclusions and Future Work
Acknowledgments
References