Title :
Team theory and backpropagation for dynamic routing in communication networks
Author :
Frisiani, G. ; Parisini, T. ; Siccardi, L. ; Zoppoli, R.
Author_Institution :
Dept. of Commun., Comput. & Syst. Sci., Genova Univ., Italy
Abstract :
The dynamic routing problem in communication networks is considered. Traffic routing nodes are required to generate routing decisions on the basis of local information, and to compute or adapt their routing strategies online. The first requirement leads to regarding routing nodes as the cooperating decision makers of a team organization. The second requirement calls for a computationally distributed algorithm. This fact and the impossibility of solving, under general conditions, team functional optimization problems suggest that each routing node be assigned a set of multilayer feedforward neural networks able to generate routing decisions. The weights of such neural networks are then adjusted by means of an algorithm based on backpropagation
Keywords :
data communication systems; neural nets; optimisation; telecommunication networks; telecommunications computing; backpropagation; communication networks; distributed algorithm; dynamic routing; local information; multilayer feedforward neural networks; routing decisions; routing strategies; team functional optimization; team theory; traffic routing nodes; weights; Backpropagation; Communication networks; Computer networks; Distributed algorithms; Distributed computing; Feedforward systems; Intelligent networks; Multi-layer neural network; Neural networks; Routing;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155198
