Alocação Dinamica de Taxa de Transmissao em Redes de Pacote Utilizando Redes Neurais Recorrentes Treinadas com Algoritmos em Tempo Real (Dynamic Transmission Rate Allocation in Packet Networks Using Recorrent Neural Networks Trained with Real Time Algorithm)

F. H. T. Vieira (flavio@decom.fee.unicamp.br)1, R. P. Lemos (lemos@eee.ufg.br)2, L. L. Lee (lee@decom.fee.unicamp.br)1


1Departamento de Comunicações da Faculdade de Engenharia Eletrica e Computacao da Universidade Estadual de Campinas (FEEC-UNICAMP)
2Escola de Engenharia Eletrica da Universidade Federal de Goias (UFG)

This paper appears in: Revista IEEE América Latina

Publication Date: Oct. 2003
Volume: 1,   Issue: 1 
ISSN: 1548-0992


Abstract:
In this paper recurrent neural networks are considered to realize traffic prediction in computer network. The transmission rate that must be allocated in order to prevent byte losses and to get an efficient network use is estimated in real time. For such, recurrent neural networks were trained with real time learning algorithms: RTRL (Real Time Recurrent Learning) and extended Kalman filter. The algorithms are applied in the dynamic transmission rate allocation in a network link, verifying its efficiencies in the traffic prediction and control.

Index Terms:
Predictive control, Neural Networks, Traffic, Transmission Rate   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (395)]