Delay Prediction in Mobile Ad Hoc Network using Artificial Neural Network

The end-to-end packet delay in mobile ad hoc network depends on many influential variables such as path length from source to destination, average neighbours of intermediate hops, interference from other transmissions and medium access control protocol etc. Hence, accurate prediction of end-to-end packet delay is very difficult but necessary for Quality of Service (QoS) routing in Mobile Ad Hoc Network (MANET) environment. In this article, we have tried to evaluate the applicability and capability of artificial neural network for prediction of end-to-end packet delay in mobile ad hoc network environment. We have used path length and average number of neighbors between source destination pair as input parameters to calculate the delay. In the present study, we developed two models based on Radial Basis Function (RBF) network and Generalized Regression Neural Network (GRNN). Three different data sets consisting of delay, path length and average neighbors are obtained using network simulator for three different routing protocols namely (i) Ad-hoc On-demand Distance Vector (AODV) routing, (ii) Destination Sequenced Distance Vector (DSDV) routing and (iii) Dynamic Source Routing (DSR). According to various performance evaluation criterion, we found that GRNN gives better prediction than RBF network