Estimation and Improvement of Routing Protocol Mobile Ad-Hoc Network Using Fuzzy Neural Network

Abstract

Ad-Hoc Networks are a generation of networks that are truly wireless, and can be easily constructed without any operator. There are protocols for management of these networks, in which the effectiveness and the important elements in these networks are the Quality of Service (QoS). In this work the evaluation of QoS performance of MANETs is done by comparing the results of using AODV, DSR, OLSR and TORA routing protocols using the Op-Net Modeler, then conduct an extensive set of performance experiments for these protocols with a wide variety of settings. The results show that the best protocol depends on QoS using two types of applications (+ve and –ve QoS in the FIS evaluation). QoS of the protocol varies from one protocol to another depending on the applications used in the network. The network design is done using the program (Op-Net V14.5 modular) with core i7 computer for multiple nodes deployed randomly in several area (100 * 100, 200 * 200, 400 * 400, 800 * 800, 1000 * 1000)m2 accomplished by changing the number of nodes in the network (10, 20, 40 and 80). There are three programs designed using (MATLAB 2012A programming language). The first one evaluates the (QoS) using the organizational structure of the mysterious system (HFS), which relied on the standard applications that should be provided by the protocols to make the applications accepted by the nodes requirements. After the evaluation the QoS for all cases, we design Neural Network to assist in estimation of the best protocol for any network through QoS for all protocols (AODV, DSR, OLSR and TORA). Neural network has four entrances (area, number of nodes, real time application ratio and non-real time application ratio). The results show that the QoS estimated is (0.5401) of (OLSR) which has been improved to (0.6421) by reducing to mobility speed and making some nodes fixed and using more than one protocol in the network to provide the best QoS .