Abstract
Due to the popularity of Dynamic Adaptive Streaming Over HTTP (DASH), broadband and Internet service providers’ links transmit mainly multimedia content. As the most popular providers encrypt their video services, the attempts to identify their traffic through Deep Packet Inspection (DPI) encounter difficulties. Therefore, encrypted DASH traffic requires new classification methods. In this work, we propose to identify DASH traffic taking into account statistical dependencies among video flows. For this purpose, we employ cluster analysis which can identify groups of traffic flows that show similarity using only the application level information. In our work, we applied three unsupervised clustering algorithms, namely MinMax K-Means, OPTICS and AutoClass, to classify video traces obtained from an emulated environment. The experimental results show that the employed algorithms are able to effectively distinguish video flows generated by different play-out strategies. The classification performance depends on the network conditions and parameters of the learning process.
Highlights
The growing popularity of Dynamic Adaptive Streaming Over HTTP (DASH) service floods broadband and Internet service providers’ links with multimedia content
Contrary to conventional classification methods, which treat the traffic flows as the individual and independent instances, we demonstrate that the correlation information can significantly improve the classification performance, especially when the network conditions are variable
In this work, using the cluster analysis and information about traffic flows gathered at the application level, we were able to identify groups of traffic flows that were generated by four exemplary play-out strategies
Summary
The growing popularity of DASH service floods broadband and Internet service providers’ links with multimedia content. A network operator may want to identify and throttle DASH services to manage its bandwidth budget and to ensure good performance of business-critical applications. The classical approach to traffic classification relies on mapping applications to wellknown port numbers and has been very successful in the past. DASH uses popular 80 and 443 TCP ports and its data is multiplexed with other HTTP based traffic, portbased identification for these services are not appropriate. Another popular approach relies on DPI, its effectiveness for encrypted traffic is limited [13, 45]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
