A neural-network-based approach for routing in a packet switching network

Author

Cavalieri, S. ; Di Stefano, Alessandro ; Mirabella, O.

Author_Institution

Istituto di Inf. e Telecomunicazioni, Catania Univ., Italy

Volume

2

fYear

1992

fDate

7-11 Jun 1992

Firstpage

913

Abstract

The authors report on routing in the packet switching network through a neural approach. The results obtained from a comparison between the latter and a minimum path algorithm are on average very similar. Each communication node learns the optimal results of a centralized routing algorithm (the Dijkstra one). This global information allows the node to operate a distributed routing in the production phase, identifying the adjacent node to which a packet is to be passed. The behavior of the neural approach is discussed and compared with the classical one

Keywords

network routing; neural nets; packet switching; switching networks; telecommunications computer control; Dijkstra algorithm; adjacent node identification; centralized routing algorithm; communication node; counter propagation network; learning phase; neural nets; packet switching network; routing; Communication system traffic control; Costs; Degradation; Delay estimation; Intelligent networks; Neural networks; Packet switching; Production; Routing; Telecommunication traffic;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.226871

Filename

226871