an identification method combining data streaming counting with probabilistic fading for heavy-hitter flows

ISCAS OpenIR

	an identification method combining data streaming counting with probabilistic fading for heavy-hitter flows
	Li Zhen; Yang Yahui; Xie Gaogang; Qin Guangcheng
	2011
发表期刊	Jisuanji Yanjiu yu Fazhan/Computer Research and Development
ISSN	1000-1239
卷号	48 期号:6 页码:1010-1017
摘要	Identifying heavy-hitter flows in the network is of tremendous importance for many network management activities. Heavy-hitter flows identification is essential for network monitoring, management, and charging, etc. Network administrators usually pay special attention to these Heavy-hitter flows. How to find these flows has been the concern of many studies in the past few years. Lossy counting and probabilistic lossy counting are among the most well-known algorithms for finding Heavy-hitters. But they have some limitations. The challenge is finding a way to reduce the memory consumption effectively while achieving better accuracy. In this work, a probabilistic fading method combining data streaming counting is proposed, which is called PFC(probabilistic fading counting). This method leverages the advantages of data streaming counting, and it manages to find the heavy-hitter by analyzing the power-low characteristic in the network flow. By using network's power-law and continuity, PFC accelerates the removal of non-active and aging flows in table records. So PFC reduces memory consumption, and decreases false positive ratio too. Comparisons with lossy counting and probabilistic lossy counting based on real Internet traces suggest that PFC is remarkably efficient and more accurate. Particularly, experiment results show that PFC has 60% lower memory consumption without increasing the false positive ratio.; Identifying heavy-hitter flows in the network is of tremendous importance for many network management activities. Heavy-hitter flows identification is essential for network monitoring, management, and charging, etc. Network administrators usually pay special attention to these Heavy-hitter flows. How to find these flows has been the concern of many studies in the past few years. Lossy counting and probabilistic lossy counting are among the most well-known algorithms for finding Heavy-hitters. But they have some limitations. The challenge is finding a way to reduce the memory consumption effectively while achieving better accuracy. In this work, a probabilistic fading method combining data streaming counting is proposed, which is called PFC(probabilistic fading counting). This method leverages the advantages of data streaming counting, and it manages to find the heavy-hitter by analyzing the power-low characteristic in the network flow. By using network's power-law and continuity, PFC accelerates the removal of non-active and aging flows in table records. So PFC reduces memory consumption, and decreases false positive ratio too. Comparisons with lossy counting and probabilistic lossy counting based on real Internet traces suggest that PFC is remarkably efficient and more accurate. Particularly, experiment results show that PFC has 60% lower memory consumption without increasing the false positive ratio.
收录类别	EI
关键词	Data Reduction Network Management
部门归属	(1) School of Software and Microelectronics Peking University Beijing 102600 China; (2) Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China; (3) Institute of Communication Engineering PLA University of Science and Technology Nanjing 210007 China
语种	中文
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16182
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Li Zhen,Yang Yahui,Xie Gaogang,et al. an identification method combining data streaming counting with probabilistic fading for heavy-hitter flows[J]. Jisuanji Yanjiu yu Fazhan/Computer Research and Development,2011,48(6):1010-1017.
APA	Li Zhen,Yang Yahui,Xie Gaogang,&Qin Guangcheng.(2011).an identification method combining data streaming counting with probabilistic fading for heavy-hitter flows.Jisuanji Yanjiu yu Fazhan/Computer Research and Development,48(6),1010-1017.
MLA	Li Zhen,et al."an identification method combining data streaming counting with probabilistic fading for heavy-hitter flows".Jisuanji Yanjiu yu Fazhan/Computer Research and Development 48.6(2011):1010-1017.