QoS-Aware Placement of Tasks on a Fog Cluster in an Edge Computing Environment

The advances made in the sensing and communications technologies over the last few years have made the deployment of IoT solutions possible on a massive scale. The wide deployment of IoT sensors and devices has resulted in the development of smart services that were not possible before. These services typically rely on cloud services for processing IoT data streams, given that edge devices have limited computing and storage capabilities. However, time-sensitive IoT applications and services do not tolerate the high latency they can encounter when sending IoT data streams to the cloud. Fog computing-based solutions for these services are increasingly becoming attractive because of the low latency they can guarantee. With increasing deployments of fog nodes and fog clusters, we propose an architecture for the placement of IoT applications tasks on a cluster of fog nodes in the vicinity of the application’s data sources. The Fog Broker component can implement various scheduling policies to help IoT applications meet their quality-of-service (QoS) requirements. Our simulations show that it is possible to maintain low application latency and distribute the load between the fog nodes of the cluster by using simple scheduling strategies.