Resource Allocation for Multiple Workflows in Cloud-Fog Computing Systems

Constant innovations in the Internet of Things (IoT) in latest years have generated large amounts of data, putting pressure on the infrastructure of cloud computing. Fog computing has recently become a popular computing paradigm that can provide computing resources close to the end users and solve multiple issues with the current cloud-only systems. Fog computing helps to reduce transmission latency and monetary cost for cloud resources, while cloud computing helps to fulfill the increasing demands of large-scale compute-intensive offloading applications. Since its introduction, there has been a great number of studies on fog computing, in which devices that are free-of-charge and closer to the user can provide low-latency services to end devices. However, how to schedule workflow applications in the cloud-fog environment to seek the tradeoff between makespan and price is facing enormous challenges. To address such a problem, we present an adaptation of the Path-Clustering Heuristic to the cloud-fog environment for multiple workflows. Firstly, we define the models for workflow execution time and resource cost in fog computing. Afterwards, we describe the algorithms implemented. We validate our proposal by extensive simulation. Experimental results show that our scheduling adaptation achieves better performance while keeping similar costs compared to others