A Mobile Ad Hoc Network (MANET) is a wireless multi-hop network formed by a set of mobile nodes in a self-organizing way
without relying on a predefined infrastructure such as base station, which results in all networking functions must be performed by the nodes themselves. In this paper, the application of the Taguchi method on understanding the functional relationship between the performance of dynamic source routing (DSR)
protocol and the influence of process parameters in MANET is presented. The effect of various network parameters including terrain, network size, pause time, node velocity, transmission range, traffic load, and packet rate was investigated on the following performance metrics: number of routing packets (NRP) and number of packets dropped (NPD). Results showed that packet rate had the strongest influence on the NPD, and network size had the biggest effect on the NRP. Within the seven parameters investigated, the effect of network size, pause time, node velocity, and traffic load was considered significant on the NRP and the effect of pocket rate, transmission range, and terrain was considered significant on the NPD. The results of this study would be helpful for routing designers in designing the future reactive protocols or improving the DSR algorithms since by knowing the order of predominance established, when conducting simulation, the designers can know what parameter should be given high priority compared to others, which can act directly to improve and enhance the protocol performance. The experimental results obtained also confirm the adequacy and effectiveness of the used approach.