A Cost-Effective and QoS-Aware Approach to Scheduling Real-Time Workflow Applications in PaaS and SaaS Clouds

The ever increasing popularity of cloud computing has relieved many consumers and businesses from the burden of acquiring, maintaining and monitoring expensive hardware and software infrastructure. In this paper, we focus on Platform as a Service (PaaS) and Software as a Service (SaaS) clouds, where users submit their workflow applications in order to be executed within strict timing constraints. It is assumed that the target cloud platform is based on a multi-tenant approach, where applications of different users may share the same virtual machines. We propose a list scheduling heuristic for the scheduling of real-time workflow applications in a heterogeneous PaaS (or SaaS) cloud that incorporates imprecise computations and bin packing techniques. Our scheduling approach has two objectives: (a) to guarantee that all applications will meet their deadline, providing high quality results and (b) to minimize the execution time of each workflow application and thus the cost charged to the user. The proposed approach is compared to a baseline list scheduling algorithm via simulation, for workflow applications with various communication to computation ratios. The simulation results show that the proposed scheduling strategy outperforms the baseline policy, providing promising results.