Energy-Aware Scheduling Based on Marginal Cost and Task Classification in Heterogeneous Data Centers

Kaixuan Ji,Antonio Fernández Anta,Youshi Wang,Penglei Song,Avinab Marahatta,Zhiyong Liu,Ce Chi,Fa Zhang

doi:10.3390/en14092382

Abstract

The energy consumption problem has become a bottleneck hindering further development of data centers. However, the heterogeneity of servers, hybrid cooling modes, and extra energy caused by system state transitions increases the complexity of the energy optimization problem. To deal with such challenges, in this paper, an Energy Aware Task Scheduling strategy (EATS) utilizing marginal cost and task classification method is proposed that cooperatively improves the energy efficiency of servers and cooling systems. An energy consumption model for servers, cooling systems, and state transition is developed, and the energy optimization problem in data centers is formulated. The concept of marginal cost is introduced to guide the task scheduling process. The task classification method is incorporated with the idea of marginal cost to further improve resource utilization and reduce the total energy consumption of data centers. Experiments are conducted using real-world traces, and energy reduction results are compared. Results show that EATS achieves more energy-savings of servers, cooling systems, state transition in comparison to the other two techniques under a various number of servers, cooling modules and task arrival intensities. It is validated that EATS is effective at reducing total energy consumption and improving the resource utilization of data centers.

Highlights

Experiments were conducted utilizing two datasets (Google cluster data [8] and Alibaba cluster data [9]), and the results indicate the validity of Energy Aware Task Scheduling strategy (EATS) for improving the energy efficiency of data centers in comparison with other algorithms
Data centers are rapidly multiplying and becoming widespread, which is resulting in high energy consumption and inefficient resource utilization
An energy-aware task scheduling strategy based on the marginal cost and task classification method was proposed to reduce the energy consumption of servers and cooling systems cooperatively so that the total energy consumption of data centers is minimized see Supplementary

Summary

Introduction

Data centers have been exponentially developing with the rapid innovations in cloud computing technology [1]. The data center provides immense computing and storage resources for cloud users to meet their increasing demands. Power-hungry and environmental footprint issues are impeding the further development of data centers [2]. Recent statistics indicate that the data center’s power demands will increase more than 66% over the period 2011–2035 [1].

Methods

Results

Conclusion