Where do all my smart home data go? Context-aware data generation and forwarding for edge-based microservices over shared IoT infrastructure

With the explosion of the Internet of Things (IoT) devices, the advent of the edge computing paradigm, and the rise of intelligent applications for smart infrastructure surveillance, in-network data management is gaining a lot of research attention these days. The challenge lies in accommodating multiple application microservices with varying Quality of Service (QoS) requirements to share the sensing infrastructure for better resource utilization. In this work, we propose a novel data collection framework, CaDGen (Context-aware Data Generation) for such a shared IoT infrastructure that enables integrated data filtration and forwarding towards minimizing the resource consumption footprint for the IoT infrastructure. The proposed filtration mechanism utilizes the contextual information associated with the running application for determining the relevance of the data. Whereas the proposed forwarding policy aims to satisfy the diverse QoS requirements for the running applications by selecting the suitable next-hop forwarder based on the microservices distribution across different edge devices. A thorough performance evaluation of CaDGen through a testbed implementation as well as a simulation study for diverse setups reveals promising results concerning network resource utilization, scalability, energy conservation, and distribution of computation for optimal service provisioning. It is observed that the CaDGen can achieve nearly 35% reduction in the generated data for a moderately dynamic scenario without compromising on the data quality.