Design and Evaluation of Routing Concepts for QoS in Mobile Ad hoc Networks by using Hopfield neural network

Abstract

Ad hoc networking is a concept in computer communications, which means that users wanting to communicate with each other forming a temporary network, without any form of centralized administration. Each node participating in the network acts both as host and as a router and must therefore is willing to forward packets for other nodes. For this purpose, a routing algorithm is needed. The most important characteristic in ad hoc network is the dynamic topology, which is a consequence of node mobility. Since direct communication is allowed only between adjacent nodes, distant nodes communicate over multihops.Quality of Service (QoS) routing in an ad hoc network is difficult because the network topology may change constantly and the available state information for routing is inherently imprecise. An algorithm LARHNN (Lagrange relaxation method based on Hop field neural network) is proposed to solve QoS routing in ad hoc networks, the algorithm depends on Lagrange relaxation method to solve the QoS routing problem Delay Constrained Least Cost (DCLC) which is considered as NP-complete, the proposed algorithm selects a network path with sufficient re¬sources to satisfy Delay Constrained Least Cost path in unicast routing and constrained minimal tree in multicast routing. The proposed algorithm uses the Hopfield neural network model of artificial neural networks to find the needed shortest path in execution of the proposed algorithm. And Hopfield neural network is selected from the other shortest path algorithms since it has good facilities to work in real time and adapt topology changes, Symmetrical connection, distributed asynchronous control, content addressable memory, in addition to its computation time, which depend on the speed of used hardware.