An Early Resource Characterisation of Wi-Fi Sensing on Residential Gateways

Wi-Fi signals have emerged as a new powerful modality for sensing human and space dynamics in a built environment. Indeed, recent research has successfully shown brand new models with Wi-Fi signals explaining space dynamics, assessing the social environment and even tracking people's posture, gesture and emotion. However, these models are seldom used in a realistic execution environment, i.e., on residential gateways, and in a realistic operating environment, i.e., when these gateways are equipped with networking tasks. In this paper, we present the first, albeit preliminary, measurement study of common Wi-Fi sensing models (e.g., for human occupancy and physical activity detection) on a representative residential gateways platform. This investigation aims to understand the performance characteristics, resource requirements and the execution bottlenecks for Wi-Fi sensing models when being used in parallel with communication tasks. Based on our findings we propose two optimisation techniques - i) dynamic sampling, and ii) dynamic planning of inference execution - to achieve optimum Wi-Fi sensing performance without compromising the quality of communication service. The results and insights of this study, lay an empirical foundation for the development of optimisation methods and execution environments that enable sensing models to be more readily integrated into next-generation residential gateways.