Neural Network Based Available Bandwidth Estimation in the ETOMIC Infrastructure

Efficient and reliable available bandwidth measurement remains an important goal for many applications. In this paper we introduce an empirical bandwidth estimation tool based on neural networks. Training the neural network on simulation data, it provides reliable estimation of physical and available bandwidth for simulated single and multi-hop networks, in laboratory environment and among the real world conditions of the ETOMIC testbed.

[1]  István Csabai,et al.  Understanding Packet Pair Separation Beyond the Fluid Model: The Key Role of Traffic Granularity , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[2]  Attila Pasztor,et al.  Accurate Active Measurement in the Internet and its Applications , 2003 .

[3]  Mary Baker,et al.  Measuring bandwidth , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[4]  Mats Björkman,et al.  A new end-to-end probing and analysis method for estimating bandwidth bottlenecks , 2000, Globecom '00 - IEEE. Global Telecommunications Conference. Conference Record (Cat. No.00CH37137).

[5]  Qiang Wang,et al.  ISE01-3: FEAT: Improving Accuracy in End-to-end Available Bandwidth Measurement , 2006, IEEE Globecom 2006.

[6]  Dmitri Loguinov,et al.  Single-hop probing asymptotics in available bandwidth estimation: sample-path analysis , 2004, IMC '04.

[7]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[8]  M. Frans Kaashoek,et al.  A measurement study of available bandwidth estimation tools , 2003, IMC '03.

[9]  Zhao Wen-tao,et al.  Efficient available bandwidth estimation for network paths , 2008 .

[10]  Scott E. Fahlman,et al.  An empirical study of learning speed in back-propagation networks , 1988 .

[11]  Richard G. Baraniuk,et al.  pathChirp: Efficient available bandwidth estimation for network paths , 2003 .

[12]  Mikel Izal,et al.  The European Traffic Observatory Measurement Infrastructure (ETOMIC): a testbed for universal active and passive measurements , 2005, First International Conference on Testbeds and Research Infrastructures for the DEvelopment of NeTworks and COMmunities.

[13]  Péter Mátray,et al.  Results of Large-Scale Queueing Delay Tomography Performed in the ETOMIC Infrastructure , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[14]  Martin A. Riedmiller,et al.  RPROP - A Fast Adaptive Learning Algorithm , 1992 .

[15]  Yves Chauvin,et al.  Backpropagation: the basic theory , 1995 .

[16]  Parameswaran Ramanathan,et al.  What do packet dispersion techniques measure? , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[17]  Peter Steenkiste,et al.  Evaluation and characterization of available bandwidth probing techniques , 2003, IEEE J. Sel. Areas Commun..

[18]  J. Aracil,et al.  The European traffic observatory measurement infrastructure (ETOMIC) , 2004, 2004 IEEE International Workshop on IP Operations and Management.

[19]  Manish Jain,et al.  Pathload: A Measurement Tool for End-to-End Available Bandwidth , 2002 .

[20]  HágaPéter,et al.  Granular model of packet pair separation in Poissonian traffic , 2007 .

[21]  Manish Jain,et al.  End-to-end available bandwidth: measurement methodology, dynamics, and relation with TCP throughput , 2003, IEEE/ACM Trans. Netw..

[22]  István Csabai,et al.  Granular model of packet pair separation in Poissonian traffic , 2007, Comput. Networks.

[23]  Martin Nilsson,et al.  Real-Time Measurement of End-to-End Available Bandwidth using Kalman Filtering , 2006, 2006 IEEE/IFIP Network Operations and Management Symposium NOMS 2006.

[24]  Lutz Prechelt,et al.  Investigation of the CasCor Family of Learning Algorithms , 1997, Neural Networks.

[25]  Antonio Pescapè,et al.  Analysis and experimentation of Internet Traffic Generator , 2003 .

[26]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[27]  Christian Igel,et al.  Improving the Rprop Learning Algorithm , 2000 .