A Dynamic Energy-Efficient Scheduling Method for Periodic Workflows Based on Collaboration of Edge-Cloud Computing Resources

Abstract

Edge-cloud computing offers an efficient method to flexibly allocate various computing resources for periodic workflow applications commonly employed in industrial production, commercial operations, and scientific research. Rationalized allocation of computational resources for scheduling in the edge-cloud environment is the key to reducing energy consumption of the periodic workflows scheduling process. To this end, this paper proposes an optimization method for dynamic energy-efficient scheduling of periodic workflows based on the collaboration of edge-cloud computational resources while satisfying the constraints of workflow deadlines. In our method, periodic workflow scheduling is defined to be performed on a three-tier integrated scheduling architecture of user terminals, edge computing platform, and cloud computing platform. Task groups are generated based on workflow critical paths, and appropriate edge-cloud computing resources are selected for workflow tasks using corresponding scheduling policies at each scheduling stage. It reduces energy consumption during task scheduling while satisfying workflow deadline constraints. Comparative experiments in a simulated edge-cloud environment show that our method reduces energy consumption of the scheduling process by 19.38%, 22.7%, and 37.34% compared to GA, PSO, and cloud computing, respectively. That is, the method effectively reduces the scheduling energy consumption during periodic workflow processing and significantly improves computational resource utilization.