Fog-based architecture for scheduling multiple workflows with high availability requirement

Given the significant development of the Internet of Things (IoT) in recent years as well as the growing need for data around the world, cloud computing alone is not able to manage this volume of data. Accordingly, fog computing has just now become a popular paradigm for further data analysis in close proximity to devices generating and processing data instantly, in order to solve various problems of existing cloud-only based systems. With regard to the complexity and the wide variety of types of computational resources such as cloud servers and fog nodes, workflow scheduling is thus one of the most important challenges in fog computing environments. To address such a problem, this paper presents software architecture for scheduling multiple workflows in cloud-fog environments simultaneously. Within this scheduling, workflow clustering and priority of workflows are also taken into account. As well, architecture layers, components, as well as their major interactions are represented using 4 + 1 architectural view models. The architecture components are ultimately proposed to meet quality attributes such as availability, reliability, recoverability, interoperability, and performance. The proposed architecture evaluation is based on the Architecture Tradeoff Analysis Method (ATAM) is a scenario-based technique. Compared with previous works, various scenarios and more quality attributes are discussed within this evaluation in addition to clustering and prioritizing workflows.