Green Technology, Cloud Computing and Data Centers: the Need for Integrated Energy Efficiency Framework and Effective Metric

Abstract

Energy efficiency (EE), energy consumption cost and environmental impact are vibrant challenges to cloud computing and data centers. Reducing energy consumption and emissions of carbon dioxide (CO2) in data centers represent open areas and driving force for future research work on green data centers. Our Literature review reveals that there are currently several energy efficiency frameworks for data centers which combine a green IT architecture with specific activities and procedures that led to decrease the impact on environment and less CO2 emissions. The current available frameworks have some pros and cons that is the reason why there is an urgent need for an integrated criterion for selecting and adopting energy efficiency framework for data centers. The required energy efficiency framework criteria should also consider the social network applications as a vital related factor in elevating energy consumption, as well as high potential for better energy efficiency in data centers. Additionally, in this paper, we highlighted the importance of the identification of efficient and effective energy efficiency metric that can be used for the measurement and determination of the value of data centers efficiency and their performance combined with sound and empirically validated integrated EE framework.

Full text

(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 5, No. 5, 2014
89 | P a g e
www.ijacsa.thesai.org
Green Technology, Cloud Computing and Data
Centers: the Need for Integrated Energy Efficiency
Framework and Effective Metric
Nader Nada
Fatih University
Istanbul, Turkey
Abusfian Elgelany
Sudan University
Khartoum, Sudan
Abstract—Energy efficiency (EE), energy consumption cost
and environmental impact are vibrant challenges to cloud
computing and data centers. Reducing energy consumption and
emissions of carbon dioxide (CO2) in data centers represent open
areas and driving force for future research work on green data
centers. Our Literature review reveals that there are currently
several energy efficiency frameworks for data centers which
combine a green IT architecture with specific activities and
procedures that led to decrease the impact on environment and
less CO2 emissions. The current available frameworks have some
pros and cons that is the reason why there is an urgent need
for an integrated criterion for selecting and adopting energy
efficiency framework for data centers. The required energy
efficiency framework criteria should also consider the social
network applications as a vital related factor in elevating energy
consumption, as well as high potential for better energy efficiency
in data centers. Additionally, in this paper, we highlighted the
importance of the identification of efficient and effective energy
efficiency metric that can be used for the measurement and
determination of the value of data centers efficiency and their
performance combined with sound and empirically validated
integrated EE framework.
Keywords—Cloud Computing; green Cloud; Datacenter;
Energy efficiency
I. INTRODUCTION TO GREEN TECHNOLOGY IN CLOUD
COMPUTING
Cloud computing is a promising area in distributed
computing. Data centers are the main component of cloud
computing. Data centers energy consumption cost and
environmental effect are dynamic challenge to cloud
computing. Additionally, the growing usage of social
applications and the expansion of e-business require an
increase in the number of data centers. However, the
combination of global warming and inconsistent climate make
the cost of energy a major challenge for the sustainability of e-
business [1]. It is a corner stone of the infrastructure of cloud
computing approach by which a variety of information
technology (IT) services were built. They extended the ability
of centralized repository for computing, hosting, storage,
management, monitoring, networking and deployment of data.
With the rapid increase in the capacity and size of data
centers, there is a continuous increase in the demand of energy
consumption [2]. Data centers, beside their ongoing high
energy consumption, also produce carbon dioxide that riddled
with IT inefficiencies. International Data Corporation (IDC)
annual report found that cloud computing reached $42bn in
2012 and the revenue of cloud in 2013 was $150bn [3].
Environmental impact of Information Technology (IT)
under the banner of “Green IT” was been discussed by
academia, media and government Since (2007), when the
Environmental Protection Agency (EPA) submitted a report to
the US Congress [5] about the expected energy consumption of
data centers. Since then Green IT has been receiving growing
attention. The overall objective of Green IT is to increase
energy efficiency and reduce CO2 emissions [6], figure 1
represents the effect of good practice of green data centers to
gas emission. There are two ways to make data center greener:
First, improve energy efficiency of data center, second, use
clean energy supply. Cloud computing has different techniques
to solve energy-efficient problem by minimizing the impact of
cloud computing on the environment. These techniques deal
with energy efficiency consumption like virtualization,
hardware base, operating systems base and data centers. Some
new features arise like energy performance, and time wise.
However, the concerns should be to swap problem between
energy consumption and performance.
II. LITERATURE REVIEW ON ENERGY EFFICIENCY
FRAMEWORKS FOR CLOUD COMPUTING
In our literature review below is based on previous studies
of investigated energy efficiency on cloud computing and
focused on data center technology.
Asghar Sabbaghiet al.[9], investigated previous researches
and introduced energy efficiency framework on information
technology that enabled Green supply chain management. They
proposed a unique conceptual taxonomy of information
technology for sustainability. They also identified the
relationship between Green supply chain management
information flow, IT governance and Green infrastructure
components.

(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 5, No. 5, 2014
90 | P a g e
www.ijacsa.thesai.org
Fig. 1. Green Data Center Market Value [7]
Zhiming Wang et al.[10], proposed mechanism to support
maximizing resource utilization by using active and idle energy
consumption by finish time minimization. This mechanism
reduces the power consumption by allowing spare servers to be
in idle state. This mechanism put into account QoS of cloud
datacenter.
RajkumarBuyya et al.[11], proposed a novel mechanism in
three ways: (a) architectural principles for energy-efficient
management of Clouds; (b) energy-efficient resource allocation
policies and scheduling algorithms considering QoS, and
devices power usage characteristics; and (c) a novel software
technology for energy-efficient management of Clouds.
Anton Beloglazov et al.[12], developed a unique
mechanism which supports dynamic consolidation of VMs
based on adaptive utilization thresholds, which put into account
Service Level Agreements (SLA).
Nguyen Quang Hung et al.[13], proposed unique server
selection policy, and four algorithms solving the lease
scheduling problem. This approach reduces 7.24% and 7.42%
energy consumption than the existing greedy mapping
algorithm.
Uddin et al.[14]and his team introduced a unique
framework to improve the performance and energy efficiency
of data centers. They developed a classification mechanism for
data center components depending on different resource pools
and different parameters like energy consumption, resource
utilization, workload, etc. The framework highlights the
importance of implementing green metrics like Power Usage
Effectiveness (PUE) to measure the efficiency of data center in
terms of energy utilization and carbon dioxide (CO2)
emissions. The framework is based on virtualization and cloud
computing to increase the resource utilization of already
installed servers from 10% to more than 50%.
Meenakshi Sharma et al.[15],developed a new mechanism
with two steps: firstly they developed an analysis of different
Virtual Machine(VM) load balancing algorithms, second
introduced a new VM load balancing algorithm that has been
developed and implemented in Virtual Machine environment of
cloud computing in order to achieve better response time and
cost.
In S. Kontogiannis et al.[16], the research team developed a
unique mechanism called Adaptive Workload Balancing
algorithm (AWLB) for cloud datacenter based web systems
which deals with agents into two dimensions the web
datacenter and web servers. AWLB algorithm also supports
protocol specification for signaling purposes among web
switch and datacenter nodes and also utilizes other protocols
such as SNMP and ICMP for its balancing process.
Performance gains are shown from tests of AWLB against
known balancing Least Connections (LC) and Least Loaded
(LL) algorithms. Table 1 represents the summary of our
literature review on cloud computing energy efficiency
frameworks and techniques.
III. URGENT NEED FOR ENERGY EFFICIENCY INTEGRATED
FRAMEWORK FOR CLOUD COMPUTING AND DATA CENTERS
Reducing energy consumption and emissions of carbon
dioxide (CO2) in data centers represent open challenges and
driving the future research work for green data centers. Our
Literature review reveals that there is an urgent need
for integrated energy efficiency framework for data centers
which combines a green IT architecture with specific activities
and procedures that led to minimal impact on environment and
less CO2 emissions. The required energy efficiency framework
should also consider the social network applications as a vital
related factor in elevating energy consumption, as well as high
potential for energy efficiency.
$31.81
$10.68
$9.26
$6.39
$4.94
$3.82
2015
2014
2013
2012
2011
2010
$16.00
$14.00
$12.00
$10.00
$8.00
$6.00
$4.00
$2.00
$0.00

(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 5, No. 5, 2014
91 | P a g e
www.ijacsa.thesai.org
TABLE I. DATA CENTERS ENERGY EFFICIENCY TECHNIQUES
IV. GREEN METRICS TO MEASURE AND ASSESS ENERGY
EFFICIENCY OF DATA CENTER
Globally, the energy consumption of data centers is
continuously on the increase [17]. The energy operations cost
will continue to double every five years between 2005 and
2025 [18]. This increase led to higher emission of CO2that
reflects negatively on global warming and environmental
health.
Measuring energy consumption of data centers has become
a significant concern of all datacenters stakeholders to meet
end-user agreement [19].Energy efficiency metric is a tool used
to measure energy efficiency in data centers [20]. The most
important challenge in the data centers industry is the limitation
of effective standard energy efficiency metrics, which supports
improving energy efficiency [21,22].
For an effective energy efficiency assessment on data
centers and its components, we need to assess the effectiveness
of the used metrics and to measure the energy efficiency of
data centers. To determine whether these metrics are effective
or not we need to assess these metrics against its intended goals
and under a range of common used cases to determine the
values of its effectiveness in terms of reporting, targets,
education, analysis and decision support [23].
Our literature review on common energy efficiency metrics
that are currently in use by data centers reveals that none of
these metrics are meeting the prior mentioned criteria.
Therefore, our research is not only introducing a comparative
review of the most common used metrics and their features
(criteria) but also attempting to recommend better metric to be
used in the assessment of data centers energy efficiency.
In last few years operators have adopted PUE metrics as the
measure of energy efficiency for the mechanical and electrical
infrastructure of the data center. The process of assessment has
submitted a focus and comparable measure of performance,
which has enabled data centers operators to make substantial
improvements. However, until now no consensus about IT or
software energy efficiency and most energy efficiency
measurements stopped at the IT power cord. In this paper we
are proposing the Fixed to Variable Energy Ratio (FVER)
metric which could be used to measure the data centers energy
efficiency instead of PUE. The reason behind our choice in
favor of the FVER metric is that it combines and meets all the
needed criteria for better energy efficiency assessment in data
centers, listed in table 2, including the usage of IT and software
applications in data centers [24]. Figure 1 depicts the difference
between FVER and PUR and Table 2 represents the different
Goals of energy efficiency metrics including PUE, DCiE,
FVER, and DCeP where:
Power Usage Effectiveness (PUE) =
Total Facility Power/ IT Equipment Power (1)
Data Center Infrastructure Effectiveness (DCiE) = 1 / PUE (2)
Fixed to Variable Energy Ratio (FVER) =1+Fixed
Energy/Variable Energy (3)
Data Center Energy Productivity (DCeP) = Useful Work
Produced / Total Data Center Energy Consumed over time (4)
V. CONCLUSION AND CONTRIBUTION
The first contribution of this paper is our literature review
on current energy efficiency frameworks. The study reveals
that there are currently several energy efficiency frameworks
for data centers which combine a green IT architecture with
specific activities and procedures that will lead to decrease
the impact on environment and the diminution of CO2
emissions. The current available frameworks have some pros
and cons (see Table 1) that is why there is an urgent need for an
integrated energy efficiency framework for data centers and
cloud computing. The framework should consider a common
and integrated set of criteria. The selection and adoption of
such framework should be in accordance with the data center
area of application and its surrounding environment.
The second contribution was the literature review on
energy efficiency metrics that are currently used for the
assessment of energy efficiency in data centers (depicted in
Table 2 and Figure 2). This part of our study developed a
comparative study of the most commonly used metrics and
their features (criteria), additionally we recommended the use
of FVER instead of PUE as a better metric for the assessment
of data centers energy efficiency which was based on certain
required criteria including the usage of IT and software
N
o
Author
Approach
Strengths
Limitation
1
Asghar
Sabbag
hi
Conceptual
taxonomy of
information
technology
Supply
Management
Focus on
infrastructure
only
2
Zhimin
g Wang
Maximizing
resource
utilization
Put into
account QoS
Much job
performance
take amount of
time
Sleep-in-
Waking up-
ready.
3
Rajku
marBu
yya
Resource
allocation
and
scheduling
Quality-of-
service
No parameter to
indicate CO2
emission
4
Anton
Belogla
zov
Adaptive
utilization
Meeting the
Service
Level
Agreements
(SLA)
No parameter to
show the
energy
efficiency level
5
Meena
kshi
Sharma
Load
balancing
algorithms
Good in
reduce
energy,
pricing and
time
Much
calculation need
more time to
take decision
6
Mueen
Uddin
Virtualizatio
n
Increase the
utilization
ratio
High utilization
leads to
introduce CO2
7
S.
Kontog
iannis
workload
balancing
algorithm
can balance
the workload
in
multidimensi
onal
resources
Increase the
Web traffic

(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 5, No. 5, 2014
92 | P a g e
www.ijacsa.thesai.org
applications in data centers. Our future work will focus on the
development and empirical validation of an integrated energy
efficiency framework for cloud computing and data centers.
Fig. 2. FVER Vs PUE [25]
REFERENCES
[1] Mell, P. and T. Grance. The NIST Definition of Cloud Computing,
2009.
[2] Mueen Uddin, framework for energy efficient data centers using
virtualization, 2012.
[3] IDC - Press Release, 2013.
[4] Ian Foster, Cloud Computing and Grid Computing 360-Degree
Compared, 2008.
[5] James W. Smith, Green Cloud A literature review of Energy-Aware
Computing, 2011.
[6] Asghar Sabbaghi, Green Information Technology and Sustainability,
2012.
[7] Ariel Schwartz, Green Data Center Marketto More than TripleOver Next
Five Years, 2010.
[8] Eric Woods, Data Center Electricity Consumption 2005-2010: The Good
and Bad News, 2011.
[9] Asghar Sabbaghi, Green information technology and sustainability: A
Conceptual taxonomy, volume 13, Issue 2, pp. 26-32, 2012.
[10] Zhiming Wang, Energy-aware and revenue-enhancing Combinatorial
Scheduling in Virtualized of Cloud Datacenter, Volume7, Number1,
January 2012.
[11] Rajkumar Buyya, Energy-Efficient Management of Data Center
Resources for Cloud Computing: A Vision, Architectural Elements, and
Open Challenges, 2010.
[12] Anton Beloglazov, aSurvey on Power Management Solutions for
Individual Systems and Cloud, 2010.
[13] Nguyen Quang Hung, Performance constraint and power-aware
allocation for user requests in virtual computing, 2011.
TABLE II. GOALS OF ENERGY EFFICIENCY METRICS [24]
[14] Mueen Uddin, Green Information Technology (IT) framework for
energy efficient data centers using virtualization, 2012.
[15] Meenakshi Sharma, Performance Evaluation of Adaptive Virtual
Machine Load Balancing Algorithm, 2012.
[16] S. Kontogiannis, A probing algorithm with Adaptive workload load
balancing capabilities for heterogeneous clusters, journal of computing,
volume 3, issue 7, July2011.
[17] Lacity, Mary C and Khan, Shaji A and Willcocks, Leslie P, A review of
the IT outsourcing literature: Insights for practice, The Journal of
Strategic Information Systems, Elsevier, 18, 130-146 (2009).
No
Goal
PUE
DCi
E
FVER
DCeP
1
Provide a clear,
preferably intuitive
understanding of the
measure
Y
Y
Y
2
Provide a clear,
preferably intuitive
direction of
improvement
Y
Y
Y
3
Describe a clearly
defined part of the
energy to useful work
function of the IT
services
Y
Y
Y
4
Be persistent, i.e. the
metrics should be
designed to be stable
and extensible as the
scope of efficiency
measurement increases,
rather than confusing the
market with rapid
replacement
Y
Y
Y
5
Demonstrate the
improvements available
in a modern design of
facility
Y
Y
6
Demonstrate the
improvements available
through upgrade of
existing facilities using
more efficient M&E
systems
Y
Y
7
Provide a clear,
preferably intuitive
understanding of the
impacts of changes
Y
Y
8
Be reversible, i.e. it
should be possible to
determine the energy
use at the electrical input
to the data center for any
specified device or
group of devices within
the data center
Y
Y
Y
9
Be capable of
supporting ‘what if’
analysis for IT and data
center operators in
determining the energy
improvement and ROI
for improvements and
changes to either the
facility or the IT
equipment it houses
Y
Y

(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 5, No. 5, 2014
93 | P a g e
www.ijacsa.thesai.org
[18] Laura Sisó, Ramon B. Fornós, Assunta Napolitano &Jaume, Energy-
and Heat-aware metrics for computing modules, 2012.
[19] Tung, Teresa, Data Center Energy Forecast, Silicon Valley Leadership
Group, San Jose, CA, (2008).
[20] Wang, Lizhe and Khan, Samee U, Review of performance metrics for
green data centers: a taxonomy study, The Journal of Supercomputing,
Springer, 1-18 (2013).
[21] Belady, Christian L and Malone, Christopher G, Metrics and an
infrastructure model to evaluate data center efficiency, Proceedings of
the Pacific Rim/ASME InternationalElectronic Packaging
Technical Conference and Exhibition(IPACK), ASME, (2007).
[22] Rivoire, Suzanne and Shah, Mehul A and Ranganathan, Parthasarathy
and Kozyrakis, Christos, JouleSort: a balancedenergy-efficiency
benchmark, Proceedings of the 2007 ACMSIGMOD international
conference on Management of data,ACM, 365-376 (2007).
[23] Liam Newcombe, Data center energy efficiency metrics existing and
proposed metrics to provide effective understanding and reporting of
data center energy, 2013.
[24] Liam Newcombe, Data center Fixed to VariableEnergy Ratio metricDC-
FVER, 2012
[25] Peter Hopton, Move Over PUE, 2012.
[26] G. Eason, B. Noble, and I. N. Sneddon, “On certain integrals of
Lipschitz-Hankel type involving products of Bessel functions,” Phil.
Trans. Roy. Soc. London, vol. A247, pp. 529–551, April 1955.
(references)
[27] J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol.
2. Oxford: Clarendon, 1892, pp.68–73.
[28] I. S. Jacobs and C. P. Bean, “Fine particles, thin films and exchange
anisotropy,” in Magnetism, vol. III, G. T. Rado and H. Suhl, Eds. N ew
York: Academic, 1963, pp. 271–350.
[29] K. Elissa, “Title of paper if known,” unpublished.
[30] R. Nicole, “Title of paper with only first word capitalized,” J. Name
Stand. Abbrev., in press.
[31] Y. Y orozu, M. Hirano, K. Oka, a nd Y. Tagawa, “Electron spectroscopy
studies on magneto-optical media and plastic substrate interface,” IEEE
Transl. J. Magn. Japan, vol. 2, pp. 740–741, August 1987 [Digests 9th
Annual Conf. Magnetics Japan, p. 301, 1982].
[32] M. Young, The Technical Writer’s Handbook. Mill Valley, CA:
University Science, 1989.