Hybrid cloud-fog computing workflow application placement: joint consideration of reliability and time credibility

The fast evolution of the Internet of Things (IoT) marketplace demands real-time interactive services. Cloud computing systems aim to harness remote data center-based computing resources to perform these services instantly. However, these cloud systems fall short due to the distances from users to the data source, affecting response time and scheduling reliability. The newest drift is to integrate fog resources and cloud resources to perform data analytics in proximity to the edge end-users. However, the makespan and reliability are two prime concerns in such integration that requires attention. Most application placement policies in the literature do not consider makespan and reliability simultaneously. In this paper, we propose a hybrid multi-criteria decision-making (Hybrid-MCD) model to optimize the scheduling reliability and workflow makespan simultaneously. It formulates the problem as a bi-objective task scheduling problem that enhances the scheduling reliability and improves the service delivery time ratio of workflow tasks placed on computing resources. Furthermore, we formed a Deadline-aware stepwise Reliability Optimization (DARO) algorithm that maximizes the application’s execution time and reliability by adapting the reliability-recursive maximization algorithm and remapping workflow applications that are not on the critical path. The proposed algorithm’s performance is evaluated in a simulated cloud-fog environment using iFogSim. The results demonstrate that the algorithm is more efficient in optimizing makespan and system reliability jointly than other comparable algorithms.