Network Traffic Prediction Based on Boosting Learning


Classification of network traffic is an important topic for network management,traffic routing, safe traffic discrimination, and better service delivery. Trafficexamination is the entire process of examining traffic data, from intercepting trafficdata to discovering patterns, relationships, misconfigurations, and anomalies in anetwork. Between them, traffic classification is a sub-domain of this field, thepurpose of which is to classify network traffic into predefined classes such as usualor abnormal traffic and application type. Most Internet applications encrypt dataduring traffic, and classifying encrypted data during traffic is not possible withtraditional methods. Statistical and intelligence methods can find and model trafficpatterns that can be categorized based on statistical characteristics. These methodshelp determine the type of traffic and protect user privacy at the same time. Toclassify encrypted traffic from end to end, this paper proposes using (XGboost)algorithms, finding the highest parameters using Bayesian optimization, andcomparing the proposed model with machine learning algorithms (NearestNeighbor, Logistic Regression, Decision Trees, Naive Bayes, Multilayer NeuralNetworks) to classify traffic from end to end. Network traffic has twoclassifications: whether the traffic is encrypted or not, and the target application. Theresearch results showed the possibility of classifying dual and multiple traffic withhigh accuracy. The proposed model has a higher classification accuracy than theother models, and finding the optimal parameters increases the model accuracy.