Deadline-Constrained Many-Objective Workflow Scheduling for IoT Environments

Advanced data-intensive services and applications in the Internet of Things (IoT) scenarios require efficient access to external resources for data processing and computation. Fog computing addresses such a need by moving part of the activity closer to the edge, alleviating network congestion, and improving responsiveness. A major problem in scheduling the workflow required by the IoT applications for their execution in fog nodes is accounting for the many quality of service (QoS) requirements that should be guaranteed, as well as possible deadlines for workflow completion imposed by the applications. In this article, we present a novel meta-heuristic approach for solving a deadline-constrained many-objective workflow scheduling problem that enhances the arithmetic optimization algorithm (AOA) with dynamic evolutionary state estimation for selecting arithmetic operators and balancing exploration and exploitation in the search space. Our approach also accounts for parallelization in task allocation and includes a repairing mechanism for infeasible solutions. The extensive experimental evaluation on benchmarks of real-world workflows, comparing against alternative algorithms, demonstrates the effectiveness of our approach.