Optimizing the Performance of Routing Protocol of MANET Using Taguchi Method

A mobile ad hoc network (MANET) is a collection of mobile nodes dynamically forming temporary network without the use of any existing network infrastructure or centralized administration. To provide and maintain better connectivity for this type of network a number of routing protocols have been proposed. Software Simulators are used for the performance evaluation of the routing protocol before implementing it in real life. CBR traffic is the commonly used as traffic type to evaluate MANET routing protocols performance. But TCP traffic is connection oriented and more reliable than CBR traffic. Therefore it is necessary to analyze the impact of TCP traffic types on MANET routing protocols before selecting a particular protocol for the network. The improvement of one performance metric may be a degradation of another performance metric. A single setup of experiment may be best for packet delivery fraction but the same setting may not yield best results for normalized routing load. In this paper, we optimize the performance of Dynamic Source Routing (DSR) using TCP traffic with multiple performances metric. The Taguchi‟s quality loss function concept has been employed to deal with multi performance metrics. Taguchi experimental design comprising of L8 orthogonal array of two levels for each parameter is used to organize the parameters and their range. A statistical analysis of means (ANOM) and analysis of variance (ANOVA) on quality loss function is performed to find the optimal values of factors which are statistically significant in order to achieve the best performance metrics of DSR routing protocol. The ANOVA results shows that number of nodes and number of connections are the most influential factors on all performance metrics. Taguchi approach suggests that optimal values for number of nodes and number of connections must be kept at low level and value of pause time must be kept at high level.