Neural Network Based Available Bandwidth Estimation in the ETOMIC Infrastructure

Author

Hága, Peter ; Laki, Sándor ; Tóth, Ferenc ; Csabai, István ; Stéger, József ; Vattay, Gábor

Author_Institution

Eotvos Univ. & Collegium Budapest -Inst. for Adv. Study Budapest, Budapest

fYear

2007

fDate

21-23 May 2007

Firstpage

1

Lastpage

10

Abstract

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.

Keywords

bandwidth allocation; neural nets; telecommunication computing; European Traffic Observatory Measurement Infrastructure; bandwidth estimation; multihop networks; neural network; Artificial neural networks; Bandwidth; Delay estimation; Global Positioning System; Machine learning; Mathematical model; Neural networks; Performance evaluation; Physics; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Testbeds and Research Infrastructure for the Development of Networks and Communities, 2007. TridentCom 2007. 3rd International Conference on

Conference_Location

Lake Buena Vista, FL

Print_ISBN

978-1-4244-0739-2

Electronic_ISBN

978-1-4244-0739-2

Type

conf

DOI

10.1109/TRIDENTCOM.2007.4444688

Filename

4444688