A Network Traffic Classification Method Based on Constrained Fuzzy Clustering and Granular Computing

Abstract

The invention belongs to the technical field of network traffic classification, and discloses a network traffic classification method based on constrained fuzzy clustering and granular computing. In the training phase, traffic information is used to merge labeled data sets and unlabeled data sets; Operate the merged data set through CCFCM, and output a set of clustering centers in numerical format; build network traffic particles around numerical clustering centers, and will continue to optimize under the guidance of reasonable granularity criteria; the most obtained With the help of tagged flows, each traffic granule will be mapped to the corresponding traffic category; the packet-level and flow-level features are extracted from NTG to build a classification rule base; in the testing phase, the granular classifier uses classification rules to identify New network flow or network anomaly. Because network traffic granules can describe the potential structure of traffic data in detail, the classification accuracy of traffic will be greatly improved.

Description

technical field [0001] The invention belongs to the technical field of network traffic classification, in particular to a network traffic classification method based on constrained fuzzy clustering and granular computing. Background technique [0002] Currently, network traffic classification aims to identify the category of traffic generated by different applications and protocols, which can provide network administrators with a fine-grained or coarse-grained view of network conditions, such as quality of service measurement, resource allocation, and intrusion detection, and then Help it manage the network conveniently. With the emergence of more and more new types of network services and network access devices, network traffic classification has attracted increasing attention to manage networks in an intelligent manner. [0003] The current traffic classification methods are mainly divided into five types: the first is correlation-based classification, which first aggrega...

AI Technical Summary

Problems solved by technology

This will greatly affect the classification accuracy

The second problem is that some methods are not always reliable. For example, the load-based classification method will become ineffective when dealing with encrypted data; the port-based classification method will also become ineffective in the face of dynamic port mechanisms.

A third problem is that they cannot be used in conjunction with packet-level and flow-level features to perform traffic classification

This will greatly affect the accuracy of classification;

[0008] (2) Some methods are not always reliable

When the network fluctuates or the network environment changes, the accuracy of most methods will become lower;

[0009] (3) They cannot be used in conjunction with packet-level and flow-level features to perform traffic classification

[0010] The difficulty in solving the above problems and defects is as follows: Although there are many methods that are constantly trying to improve the accuracy and reliability of classification, reliable and stable traffic classification still faces many difficulties

First of all, due to the continuous development of the network, more and more applications bring massive data traffic, and many unknown traffic and even malicious traffic are mixed in, which brings great difficulties to classification

Secondly, the collection of data sets and labels is also a difficult problem for traffic classification

Images