QoS-Classifier for VPN and Non-VPN traffic based on time-related features

Abstract

The Quality of Service (QoS) is a continuous challenge issue in the telecommunication industry, mainly for having an impact on telco services provision. Traffic Classification, Traffic Marking, and Policing are general stages of QoS managing. Different approaches have focused on Traffic Classification and Traffic Marking, which machine learning algorithms arise as promising techniques ones. However, Traffic Marking overtime-related features is not widely explored, especially for Virtual Private Network (VPN) traffic. Hence, a specific QoS classifier for VPN traffic based on per-hop behavior (PHB) for a specific domain was proposed. To this end, a baseline QoS-Marked dataset was generated from a characterized VPN traffic; to which some machine learning algorithms were compared and a T-Tester was performed. As a result, Bagging-based learning model has the best behavior for all scenarios in which the higher value achieved was a 94,42% accuracy. Consequently, a QoS classifier is an effective approach for traffic treatment on Differentiated Services (DiffServ) networks.