An Integrated Modeling Approach to Evaluate and Optimize Data Center Sustainability, Dependability and Cost

Gustavo Callou,Rafael Souza,Dietmar Tutsch,João Ferreira,Paulo Maciel

doi:10.3390/en7010238

Abstract

Data centers have evolved dramatically in recent years, due to the advent of social networking services, e-commerce and cloud computing. The conflicting requirements are the high availability levels demanded against the low sustainability impact and cost values. The approaches that evaluate and optimize these requirements are essential to support designers of data center architectures. Our work aims to propose an integrated approach to estimate and optimize these issues with the support of the developed environment, Mercury. Mercury is a tool for dependability, performance and energy flow evaluation. The tool supports reliability block diagrams (RBD), stochastic Petri nets (SPNs), continuous-time Markov chains (CTMC) and energy flow (EFM) models. The EFM verifies the energy flow on data center architectures, taking into account the energy efficiency and power capacity that each device can provide (assuming power systems) or extract (considering cooling components). The EFM also estimates the sustainability impact and cost issues of data center architectures. Additionally, a methodology is also considered to support the modeling, evaluation and optimization processes. Two case studies are presented to illustrate the adopted methodology on data center power systems.

Highlights

Pollution, environmental degradation and climate change are examples of environmental impact concerns of the scientific community and industry
Avail is the column with the availability results, 9 s is the availability level (A) in number of nines (−log[1−A/100]), Down. is the downtime, which is represented in hours, as well as the associated cost, Acq is the acquisition cost, Op is the operational cost, Tot is the total cost, Ex corresponds to the results for the exergy consumption, Sys Eff is the system efficiency, Obj Func is the objective function, which is represented by the mean of m executions, as well as by the smaller result obtained, and Diff. is the difference, which is represented by the fraction of the results obtained through the evaluation of all scenarios by the results obtained from the optimization process
It is important to stress that in case the list of candidate components increases, the difference between the runtime spent by the optimization algorithm in comparison to the execution of all possible scenarios tends to grow in such way that it may become impossible to perform the analysis of all possible scenarios

Summary

Introduction

Environmental degradation and climate change are examples of environmental impact concerns of the scientific community and industry. In information technology (IT), the emergence of social networking services, e-commerce and cloud computing has led to a rapid increase in computing and communication capabilities provided by data centers [2] This has changed the global economy, where a decade ago, less than 300 million people accessed the Internet, in comparison to : this number has risen to over two billion people [1]. This remarkable growth comes with an increase in power consumption, which accounts for about 2% of today’s U.S power generation [3]. These aspects of IT have significantly contributed to global carbon emissions

Objectives

Methods

Results

Conclusion