Deadline-constrained energy-aware workflow scheduling in geographically distributed cloud data centers

The energy cost of cloud data centers is increasingly concerned worldwide; the minimization of energy cost is becoming an urgent problem. Considering data centers are geographically distributed, electricity prices are different in each data center. Consequently, it is also critical to assign workflow tasks to the geographically distributed data centers because data required by tasks is usually conserved in the given data center. So, as electricity prices and data transmission times change, it becomes a big challenge to minimize energy costs when scheduling workflow tasks to heterogeneous servers in cloud data centers. A DEWS (Deadline-constrained Energy-aware Workflow Scheduling) algorithm is proposed in this paper, which consists of task sequencing, VND-based data center searches, task sequence adjustment, and VM searching with Dynamic Voltage Frequency Scaling (DVFS). The DVFS method is included in the optimization procedure to cut down the additional energy cost of service providers. The experimental results show that the proposed algorithm outperforms the compared algorithms and reduces energy cost by 5%-20%. (C)& nbsp;2022 Elsevier B.V. All rights reserved.

Automated summary

The increasing concern over the energy cost of cloud data centers has led to the urgent problem of minimizing energy cost. This paper proposes a DEWS algorithm that addresses the challenge of scheduling workflow tasks in geographically distributed data centers to minimize energy costs. The algorithm includes task sequencing, data center searches, task sequence adjustment, and VM searching with DVFS, resulting in a 5%-20% reduction in energy cost.