Abstract-Response surface methodology (RSM) is a collection of statistical design and numerical optimization techniques traditionally used to optimize industrial processes. In this paper, we demonstrate that the methodology can be successfully applied to the domain of networking. Specifically, we obtain increased throughput with a significant decrease in delay in a ns-2 simulation model of a mobile ad hoc network (MANET) by using RSM to optimize protocol interaction found by factor screening. Whether the experimentation is with a stochastic simulation model or a physical system, such as a MANET or a wireless sensor network test-bed, RSM provides a general and practical methodology to screen factors and robustly and jointly optimize responses.

Delay sensitive applications are driving the need for the support of quality-of-service (QoS) in mobile ad hoc networks. In this paper, we use statistical design of experiments to study the impact of factors and their interaction on the service delivered. We consider the factors of QoS architecture, routing protocol, medium access control protocol, offered load, and mobility, at mixed levels. Real-time throughput, total throughput, and average delay are used as the measures of service delivery. A statistical analysis of the data collected by simulation using analysis of variance techniques is performed. This allows us to identify both main effects and interactions of factors that best explain the response variables. For average delay several factors of the experiment interact. For both forms of throughput, the impact of the routing protocol is not apparent except as it interacts with other factors, and the factor interactions are not as extensive as for delay. Thus, for all response variables the factors cannot be studied in isolation. As well, the analysis provides a means for a system architect to determine the level to set the factors to optimize a specific service delivery metric, or combination of metrics.