A Fog-enabled Smart Home Analytics Platform
Theo Zschörnig, Robert Wehlitz, Bogdan Franczyk · 2019
Although the usage of smart home devices such as smart speakers, light bulbs and thermostats has increased rapidly in the past years, their added value, compared to conventional devices, is mostly limited to simple control and automation logic. In order to provide adaptive smart home environments, it is necessary to gain deeper insights into the data generated by these devices and use it in sophisticated data processing pipelines. Providing such analytics to a multitude of consumers requires specialised architectures, which are able to overcome various challenges identified by scientific literature. Currently available smart home analytics architectures are not designed to tackle all of these issues, specifically fault-tolerance, network-usage, latency and external regulations. In this paper, we propose an architectural solution to address these challenges based on the concept of Fog computing. Furthermore, we provide insight into the motivation for this research as well as an overview of the current state of the art in this field.