A low-cost two-tier fog computing testbed for streaming IoT-based applications

In this article, we propose a comprehensive multilayer (IoT-device, edge, fog, and cloud) streaming analytics platform with two-tier fog layer, which comprises streaming and analytics tiers. The approach, functionally validated on a testbed of clusters of low-cost off-the-shelf components, demonstrates that both real-time streaming processing and large-scale data analytics are feasible, with even completely avoiding the use of cloud layer. The fog layer uses advanced streaming and analytics paradigms, such as Apache Kafka, Apache Spark, and Hadoop, to support the effective development of applications that use streaming, long-term data storage and analytics. As such, the platform is suitable for and is affordable for 'private' users. Furthermore, we add to the platform intelligent edge layer that abstracts and can simulate the operation of the IoT-device layer in real time or can be directly connected to the IoT-device layer. The experiments on a real-life IoT-based smart parking application show that our two-tier approach is cost effective and scalable, and can handle simultaneously streaming processing and analytics tasks successfully.