A new system for controlled testing of sensor network applications: architecture, prototype and experimental evaluation

In this paper we first argue the case for a system which can accurately reproduce sensed input or stimuli for fair evaluation of wireless sensor network applications. It is shown, with a simple example, that consistent input is crucial in the evaluation of applications, and that the lack of such rigor may lead to wrong conclusions, and therefore a biased choice of what seems to be the best application. We present an architecture for a system that utilizes sensor nodes to provide the required stimuli and can exercise control over other sensor nodes that are executing the application under test. In our architecture, each sensor node executing the application under test is paired with a modified sensor node called the control node. We showcase a prototype implementation of the architecture using the MICAz hardware platform and TinyOS operating system software. Evaluation results for the prototype in a network setting are then presented. Our architecture, to the best of our knowledge, is the first to provide the benefits of both hardware-based and software-based approaches to enable controlled testing of sensor network applications. We also provide an optimization formulation for finding the least number of nodes through which control packets can be disseminated to every control node in the network.