Multi-objective optimization of a hybrid model for network traffic classification by combining machine learning techniques

Considerable effort has been made by researchers in the area of network traffic classification, since the Internet is constantly changing. This characteristic makes the task of traffic identification not a straightforward process. Besides that, encrypted data is being widely used by applications and protocols. There are several methods for classifying network traffic such as known ports and Deep Packet Inspection (DPI), but they are not effective since many applications constantly randomize their ports and the payload could be encrypted. This paper proposes a hybrid model that makes use of a classifier based on computational intelligence, the Extreme Learning Machine (ELM), along with Feature Selection (FS) and Multi-objective Genetic Algorithms (MOGA) to classify computer network traffic without making use of the payload or port information. The proposed model presented good results when evaluated against the UNIBS data set, using four performance metrics: Recall, Precision, Flow Accuracy and Byte Accuracy, with most rates exceeding 90%. Besides that, presented the best features and feature selection algorithm for the given problem along with the best ELM parameters.