A neural network model to configure maps for a satellite communication network

A self-configurable satellite communication network that can be dynamically configured to different maps, to best meet the network requirements, by means of a modified Kohonen self-organization procedure is described. The model consists of three stages. The first stage is the pattern recognition task, in which an exemplar map that best meets the current network requirements is selected. The second stage is an analysis of the discrepancy between the chosen exemplar map and the state of the network, and adaptively modifies the chosen exemplar map to conform closely to the network requirement (input data pattern) by Kohonen's self-organization procedure. On the basis of certain performance criteria, it is decided in the third stage whether a new map is generated to replace the original map. Experimental results are presented to demonstrate that the self-organization model can dynamically configure maps for a satellite communication network.<
>