XDense is a novel wired 2D-mesh grid sensor network system for application scenarios that beneit from densely deployed sensing (e.g. thousands of sensors per square meter). It was conceived for cyber-physical systems (CPS) that require real-time sensing and actuation, like active low control (AFC) on aircraft wing surfaces. XDense communication and distributed processing capabilities are designed to enable complex feature extraction within bounded time and in a responsive manner. In this paper we tackle the issue of deterministic behavior of XDense. We present a methodology that uses traic shaping heuristics to guarantee bounded communication delays and the fulillment of memory requirements. We evaluate the model for varied network conigurations and workload, and present a comparative performance analysis in terms of on link utilization, queue size and execution time. With the proposed traic shaping heuristics, we endow XDense with the capabilities required for real-time applications.

No abstract