Priority Switching by Means of Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F09%3APU86294" target="_blank" >RIV/00216305:26210/09:PU86294 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Priority Switching by Means of Neural Networks

Popis výsledku v původním jazyce

The paper trades off two neural networks used for choose optimal way in the priority packet switching. Packet switching is one of the most important points in the IT networks. Packet has to be delivered from a sender to a receiver through packet switch with minimum time delay. Each packet can have a self priority which says how important speed of transfer is. For a fast choose preferential packets in the packet switch and theirs sending can be used neural network. Neural network decide for one state ofexemplar states with minimal energetic function it mean there is optimal choose of the most preferred packets. Neural networks are based on a simple calculation with manifold parallelisms. There don't have to be fast processor for complicated evaluationbut be sufficient slower processors in the packet switch. It is cheaper and faster solution. There are many types of neural networks. Every neural network has specific characteristics and different chances of usage for different problems.

Název v anglickém jazyce

Priority Switching by Means of Neural Networks

Popis výsledku anglicky

The paper trades off two neural networks used for choose optimal way in the priority packet switching. Packet switching is one of the most important points in the IT networks. Packet has to be delivered from a sender to a receiver through packet switch with minimum time delay. Each packet can have a self priority which says how important speed of transfer is. For a fast choose preferential packets in the packet switch and theirs sending can be used neural network. Neural network decide for one state ofexemplar states with minimal energetic function it mean there is optimal choose of the most preferred packets. Neural networks are based on a simple calculation with manifold parallelisms. There don't have to be fast processor for complicated evaluationbut be sufficient slower processors in the packet switch. It is cheaper and faster solution. There are many types of neural networks. Every neural network has specific characteristics and different chances of usage for different problems.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA102%2F07%2F1503" target="_blank" >GA102/07/1503: Pokročilá optimalizace návrhu komunikačních systémů pomocí neuronových sítí</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2009

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICSC - Seventh International Conference on Soft Computing Applied in Computer and Economic Environments

ISBN

978-80-7314-163-9

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

Neuveden

Místo vydání

Neuveden

Místo konání akce

Hodonín

Datum konání akce

23. 1. 2009

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—