Priority Switching by Means of Neural Networks
The result's identifiers
Result code in 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>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Priority Switching by Means of Neural Networks
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA102%2F07%2F1503" target="_blank" >GA102/07/1503: Advanced Optimizing the Design of Communication Systems via neural networks</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICSC - Seventh International Conference on Soft Computing Applied in Computer and Economic Environments
ISBN
978-80-7314-163-9
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
—
Publisher name
Neuveden
Place of publication
Neuveden
Event location
Hodonín
Event date
Jan 23, 2009
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—