Experience: Developing a Testbed for Ambient Sensing and in-Network Data Processing

With ubiquitous adaptation of IoT infrastructure, the smart applications these days are not confined within a single realm. Be it the boundary of a home environment or a city-scale infrastructure, multiple smart applications and associated services tend to serve the users by sharing a common sensing platform. Although the very purpose of this shared infrastructure motivates from the reduced installation and maintenance expenses, it offers a great deal in enabling faster cross-domain inference too. For instance, the same data reflecting room temperature and CO2 density can be taken into consideration by occupancy estimation service to feed the HVAC system, surveillance system as well as smart resource management system concurrently. Towards faster decision-making and automation it is imperative that the sensory data be pre-processed at the network edge. Now, the existing simulation platforms cannot account for the real-world dynamics affecting the performance of such edge-based sensing and data processing solutions for a shared IoT infrastructure. This work aims to document the practical lessons learnt while developing a testbed to evaluate the performance of such edge-based solutions to support ambient living. Along with the detailed description of system architecture, requirement analysis, design and development arrangement, we also provide a use case demonstration to unfold the inherent challenges and potential solution ideas to setup and conduct experiments on such a testbed environment.