Performance comparison of multicast protocol for physically hierarchical ad hoc networks using neural concepts

An ad hoc network is a dynamically reconfigurable wireless network with no fixed infrastructure or central administration. Each host is mobile and must act as a router. Routing and multicasting protocols in ad hoc networks are faced with the challenge of delivering data to destinations through multihop routes in the presence of node movements and topology changes. Most of the proposed algorithms assume physically flat network architecture with mobile hosts having homogenous capability in terms of network resources and computing power. In practice however, this assumption often may not hold true since there exists various types of mobile hosts with different role and mobility pattern. Here we consider mobile ad hoc network that have physically hierarchical architecture where different types of mobile hosts form an ad hoc network hierarchy. A way for automatically organizing the hierarchical architecture is provided by the self-organizing map (SOM). The self-organizing map is one of the most prominent artificial neural network models adhering to the unsupervised learning paradigm. The simulation of the hierarchical ad hoc networks using neural concepts yields better performance.