Detail publikačního výsledku

Parallel WAN Switch Based on Neural Network

ŠKORPIL, V.; POLÍVKA, M.

Originální název

Parallel WAN Switch Based on Neural Network

Anglický název

Parallel WAN Switch Based on Neural Network

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

The article deals with a WAN switch design based on a Feedforward neural network, specifically for the Feedforward Backpropagation algorithm. The designed switch is fully parallel, uses neural network for switch management and also for traffic engineering. The switch uses advanced packet dropping mechanism. The article describes the switch design (network processor design) and compares the developed switch with other "conventional" architectures. Architectures and performance are then compared.

Anglický abstrakt

The article deals with a WAN switch design based on a Feedforward neural network, specifically for the Feedforward Backpropagation algorithm. The designed switch is fully parallel, uses neural network for switch management and also for traffic engineering. The switch uses advanced packet dropping mechanism. The article describes the switch design (network processor design) and compares the developed switch with other "conventional" architectures. Architectures and performance are then compared.

Klíčová slova

MATLAB, model, network, neural network, switch, switch algorithm

Klíčová slova v angličtině

MATLAB, model, network, neural network, switch, switch algorithm

Autoři

ŠKORPIL, V.; POLÍVKA, M.

Rok RIV

2013

Vydáno

14.07.2012

Nakladatel

WSEAS Press

ISBN

978-1-61804-109-8

Kniha

Recent Researches in Communications and Computers

Strany od

68

Strany do

72

Strany počet

5

BibTex

@inproceedings{BUT93291,
  author="Vladislav {Škorpil} and Michal {Polívka}",
  title="Parallel WAN Switch Based on Neural Network",
  booktitle="Recent Researches in Communications and Computers",
  year="2012",
  number="1",
  pages="68--72",
  publisher="WSEAS Press",
  isbn="978-1-61804-109-8"
}