Network Traffic Classification and Control Technology Based on Decision Tree

Abstract

The identification and classification of network traffic has very strong practical significance. The correct classification of network traffic is the basis of studying the upper network structure. The traditional traffic classification technology mainly relies on port information and load characteristics of data packets. However, in recent years, with the rapid growth of network bandwidth and the gradual complexity of application layer protocols, traditional traffic classification methods have been difficult to meet the needs of the current network environment, which urgently requires the introduction of new theories and technologies to achieve accurate network traffic classification. Combining with the existing network traffic identification and classification methods, this paper studies the network traffic classification method based on machine learning, gives the construction of the classification model based on decision tree, and realizes the function of traffic statistics and classification. Experiments show that the proposed algorithm has higher classification accuracy and is suitable for unbalanced traffic classification compared with many traditional algorithms.