Study of Dynamic Timeout Strategy based on flow rate metrics in high-speed networks

Authors:
Zhou Ming-zhong;Gong Jian;Ding Wei
Affiliations:
Southeast Univ. and Jiangsu Province Key Laboratory of Computer Networking Technology and Jiangsu Province Key Laboratory of Network and Information Security, Nanjing, Jiangsu, China;Southeast Univ. and Jiangsu Province Key Laboratory of Computer Networking Technology and Jiangsu Province Key Laboratory of Network and Information Security, Nanjing, Jiangsu, China;Southeast Univ. and Jiangsu Province Key Laboratory of Computer Networking Technology and Jiangsu Province Key Laboratory of Network and Information Security, Nanjing, Jiangsu, China
Venue:
InfoScale '06 Proceedings of the 1st international conference on Scalable information systems
Year:
2006

Citing 9
Cited 0

Internet traffic characterization

Internet traffic characterization
Load-sensitive routing of long-lived IP flows

Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Monitoring very high speed links

IMW '01 Proceedings of the 1st ACM SIGCOMM Workshop on Internet Measurement
On the characteristics and origins of internet flow rates

Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
Properties and prediction of flow statistics from sampled packet streams

Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurment
The War Between Mice and Elephants

The War Between Mice and Elephants
On Class-based Isolation of UDP, Short-lived and Long-lived TCP Flows

On Class-based Isolation of UDP, Short-lived and Long-lived TCP Flows
Inverting sampled traffic

Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement
A parameterizable methodology for Internet traffic flow profiling

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The measurements based on flow characteristics are playing more and more important roles in the analysis of Network Behavior. As one of main methods for flow recognition, the timeout strategies have a significant impact on the correctness and performance of flow measurements. This paper discusses the state-of-art of flow timeout strategies, and explains where they are applicable and their shortcomings. To deal with short flows that take a large part of the total flows in the networks, the paper proposes the Dynamic Timeout Strategy (DToS) by analyzing flows distribution and flow rate metrics in details. The studies show that this method can improve the performances of network measurement and the efficiency of the resource usage by using different timeout strategies to deal with flows that have different rate features based on integrated usage analyses of target networks. It can also apperceive network abnormal behavior efficiently, and then take emergent measures to ensure the safety of measurement system. Some experiments have been carried out to show the rationality of DToS strategy. The applicable area of this strategy is also analyzed at the end of this paper.