Conference paper
Sub-flow packet sampling for scalable ML classification of interactive traffic
37th Annual IEEE Conference on Local Computer Networks
2012 IEEE 37th Conference on Local Computer Networks (LCN) (Clearwater, Florida, 22/10/2012–25/10/2012)
2012
Abstract
Machine Learning (ML) classifiers have been shown to provide accurate, timely and continuous IP flow classification when evaluating sub-flows (short moving windows of packets within flows). They can be used to provide automated QoS management for interactive traffic, such as fast-paced multiplayer games or VoIP. As with other ML classification approaches, previous sub-flow techniques have assumed all packets in all flows are being observed and evaluated. This limits scalability and poses a problem for practical deployment in network core or edge routers. In this paper we propose and evaluate subflow packet sampling (SPS) to reduce an ML sub-flow classifier's resource requirements with minimal compromise of accuracy. While random packet sampling increases classification time from <;1 second to over 30 seconds and can reduce accuracy from 98% to <;90%, our tailored SPS technique retains classification times of <;1 second while providing 98% accuracy.
Details
- Title
- Sub-flow packet sampling for scalable ML classification of interactive traffic
- Authors/Creators
- S. Zander (Author/Creator)T. Nguyen (Author/Creator)G. Armitage (Author/Creator)
- Publication Details
- 37th Annual IEEE Conference on Local Computer Networks
- Conference
- 2012 IEEE 37th Conference on Local Computer Networks (LCN) (Clearwater, Florida, 22/10/2012–25/10/2012)
- Identifiers
- 991005541133807891
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
33 Record Views