Nowadays, cloud computing with pay-per-use infrastructures provides an ideal environment for processing large-scale scientific workflows. Workflows that are interrelated and have specific tasks in scientific applications are referred to as workflows ensemble. Mapping scientific workflow tasks based on their priorities onto computing resources while adhering to deadline and budget constraints is one of the most challenging problems in cloud computing. In this paper, we present an intelligent and adaptive algorithm for scheduling workflow ensemble with optimized resource provision under given deadline and budget constraints. The proposed method makes decisions based on workflow priorities and attempts to execute the many high-priority workflows as possible. To observe budget, deadline, and resource utilization as Quality of Service (QoS) parameters, we introduce three approaches: Fastest Scheduling, Scheduling With MinCost, and GapRate analysis. By using different strategies for the main problem, an optimal scheduling map is created. To evaluate the proposed algorithm, we conduct simulations with a set of scientific workflows ensemble and present the related results. The experimental outcomes demonstrate that resource utilization is increased by using gap analysis in the public cloud while executing the best possible number of workflows with high priority under deadline and budget constraints, in comparison to the state-of-the-art approach

Keywords