Title :
A connectionist approach to SDH bandwidth management
Author_Institution :
Telecom Australia Res. Lab., Clayton, Vic., Australia
Abstract :
In the present paper the application of neural networks to bandwidth management is discussed. Two neural architectures were examined; the radial basis function network, and a Hopfield network. The radial basis function network has been applied to the task of traffic prediction and the Hopfield network used as a linear programming solver. The two networks can be used to assist with the management of bandwidth in a synchronous transmission network, namely a SONET or SDH network
Keywords :
Hopfield neural nets; SONET; feedforward neural nets; linear programming; synchronous digital hierarchy; telecommunication network management; telecommunications computing; Hopfield network; SDH bandwidth management; SONET; bandwidth management; connectionist approach; linear programming solver; neural networks; radial basis function network; synchronous transmission network; traffic prediction;
Conference_Titel :
Artificial Neural Networks, 1993., Third International Conference on
Conference_Location :
Brighton
Print_ISBN :
0-85296-573-7
