Unbalanced-like network traffic classification method and device and computer equipment

Abstract

The invention relates to the technical field of network traffic classification, and relates to an unbalanced-like network traffic classification method and device and computer equipment. The method comprises the steps of obtaining to-be-classified network traffic data, and extracting features of network traffic; deleting irrelevant features and redundant features by adopting a feature selection algorithm, and performing dimension reduction on the remaining features so as to select an optimal feature subset; and inputting the optimal feature subset into a weight-based multi-classifier, performing network traffic classification training in an incremental learning mode, optimizing classifier performance, and classifying the network traffic. Aiming at the problem of unbalanced distribution ofnetwork traffic samples, irrelevant features and redundant features are deleted, and the recognition rate of small categories is effectively improved on the premise of ensuring the overall classification accuracy; an incremental learning thought is introduced, the flexibility of model updating training is improved, and the model updating period is shortened; and by utilizing multiple classifiers based on weight, the influence caused by concept drift is reduced.

Description

technical field [0001] The present invention relates to the technical field of network traffic classification, and more specifically, relates to a method, device and computer equipment for classifying unbalanced network traffic. Background technique [0002] Classifying traffic according to the applications that generate network traffic is of great significance for ensuring network QoS (Quality of Service) values ​​and maintaining network security. With the help of network traffic classification, network managers can divide and analyze all traffic in the network according to different application types in real time, provide a basis for deploying quality of service (QoS) mechanisms, and provide different service quality levels for different types of applications, thereby Reduce network congestion, ensure the quality of service for key businesses, and maintain efficient and smooth network operation. At the same time, relying on traffic classification, network service provider...

AI Technical Summary

Problems solved by technology

[0006] However, most of the classification models in the above technologies are difficult to achieve frequent and timely updates, and ignore the phenomenon of concept drift, and do not fully consider the distribution of network traffic data samples Due to the general pursuit of the learning effect of large categories, it is easy to ignore the learning performance of small categories; because the importance of small category features is ignored, it is easy to misclassify small categories into large categories, resulting in uneven network traffic classification effects and low efficiency; Even cause the collapse of the network system

Images