The available end-to-end bandwidth is an important specification in network
measurement. Most tools need to spend much time in measuring and analyzing before
calculating the available bandwidth. This paper proposes a low overhead mechanism for
accurate and fast measurement of the available bandwidth by analyzing the cross traffic
effect in the Internet. A model is established to reflect the relationship between utilization
and the sending rate of probe packets, which is combined with an extended Kalman filter to
obtain the new available bandwidth. This mechanism does not require any prior knowledge
of the bottleneck link capacity and can reduce the effect of accuracy. Besides, the sending
rate of probing packets can be much lower than the available bandwidth. Performance
of the mechanism is verified numerically, showing fast response to burst cross traffic, low
estimation error, and short convergence time.
ZHOU Yi-qiu1, CHEN Bing1, QIAN Hong-yan1, Lü Zong-lei2
. Accurate and Low Overhead Mechanism for Measuring Available Bandwidth[J]. Journal of Applied Sciences, 2015
, 33(2)
: 155
-166
.
DOI: 10.3969/j.issn.0255-8297.2015.02.005
[1] Kim J C, Lee Y. An end-to-end measurement and monitoring technique for the bottleneck link capacity and its available bandwidth [J].Computer Networks, 2014,vol. 58, no. 14:158–179.
[2] H´aga P, Diriczi K, Vattay G, Csabai I. Understanding packet pair separation beyond the fluid model: The key role of traffic granularity. in INFOCOM, 2006.
[3] Guerrero C D, Labrador M A. Traceband: A fast, low overhead and accurate tool for available bandwidth estimation and monitoring [J]. Computer Networks, 2010, vol. 54, no. 6: 977-990.
[4] Guerrero C D, Labrador M A. A hidden markov model approach to available bandwidth estimation and monitoring [C]. Orlando: in Proceedings of the Internet Network Management Workshop, 2008.
[5] Guerrero C D, Morillo D S. On the Reduction of the Available Bandwidth Estimation Error Through Clustering with K-means [C], Italy: in INFOCOM Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies, 2013.
[6] Hu Z, Zhang D, Zhu A, Chen Z, Zhou H. SLDRT: A measurement technique for available bandwidth on multi-hop path with bursty cross traffic [J]. Computer Networks, 2012, Vol. 56, no. 14: 3247-3260.
[7] 赵卫虎, 孟相如, 麻海圆, 庄绪春．一种自适应的高精度可用带宽测量算法[J]. 计算机测量与控制. 2011. 19( 6):1297-1300.
[8] Hu N, Li L E, Mao Z M, Steenkiste P, Wang J, Locating internet bottlenecks: Algorithms, measurements, and implications [C]. New York: in Proc. ACM SIGCOMM, 2004.
[9] Bergfeldt E, Ekelin S, Karlsson JM. Real-time available-bandwidth estimation using filtering and change detection [J]. Computer Networks, 2009, vol. 34, no. 4: 41–54.
[10] Lao L, Dovrolis C, Sanadidi M Y. The probe gap model can underestimate the available bandwidth of multihop paths [C]. Italy: SIGCOMM Comput. Commun, 2006.
[11] Li M, Wu Y L, Chang C R. Available bandwidth estimation for the network paths with multiple tight links and bursty traffic [J]. Journal of Network and Computer Applications, 2013, vol. 36, no. 1: 353–367. .
[12] Jain M, Dovrolis C. Ten fallacies and pitfalls on end-to-end available bandwidth estimation [C]. New York: In Proceedings of the 4th ACM SIGCOMM conference on Internet measurement, 2004.
[13] 刘敏，李忠诚，过晓冰．端到端的可用带宽测量方法[J]. 软件学报. 2006, 17(1): 108－116.
[14] Nilsson M. Measuring available path capacity using short probe trains [C]. New York: in INFOCOM Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies, 2010.
[15] Nilsson M. Measuring available path capacity using short probe trains[C]. New york: Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies, 2010:905–914.
