Green Cloud Computing: Energy Efficiency in

Cloud Based Data Centers

Ramkumar.R (2nd-MCA)
Pope John Paul II College of Education
[Link]@[Link]
[Link]: 8870912513

communications technology (ICT) sector. In the last

Abstract
Cloud computing is the whole new
paradigm in the field of information technology
and moving towards a cloud based system
increases day by day because of this cloud based
data centers are increasing greatly which leads to
high energy consumption every day and also the
emission of CO2 by these data centers greatly
affect the environment. To overcome this problem
Green Computing came into existence. The main
goal of green computing is to recycle and reuse.
Green

Computing

computing

speed

helps
at

to

get

decreased

the

same
energy

consumption. In this paper I discussed about how

green computing can be achieved by load

compel of years, Cloud based data centers are

increasing greatly because of the demand for
computer resource. Since more data centers are came
into existence the energy consumption of these data
centers are also increased to a great extent. In
addition to high energy consumption there is an
addition impact on the environment by the form of
carbon-di-oxide emissions. According to the report of
Congress on Server and data centers [4], the data
centers are responsible for about 2% of global CO2
emission and they use nearly 80 million megawatthours of energy annually, it is about 1.5 times the
amount of electricity used by the whole New York
City.

balancing and virtualization. Which can reduce

By 2020 the total amount of Carbon-di-

the energy consumption of cloud data centers

oxide emitted by these data centers will be nearly 359

which will in turn reduce the low emission of C02.

megatons. In such a situation it is crucial importance

Keywords: Load balancing, Virtualization, Multitenancy, SaaS, IaaS, PaaS.

that the cloud data centers should have a good energy

efficiency. The Major problem in poor energy
efficiency is that most of the energy are wasted when

Introduction
The issue of energy consumption in
information technology equipment has been receiving
increasing attention in recent years and there is
growing recognition of the need to manage energy
consumption across the entire information and

servers run at low utilization.

According to the recent research from Pike Research
[5], the global market for green data centers will
grow from $17.1 billion in 2012 to $45.4 billion by
2016. In fact on-site server with no virtualization will
emit bout 46 kg of CO2 per year.

cloud. While keeping critical service and data in their

control by using private cloud.
Cloud computing also offers different types of
service to its customer and it is of three types:
a) SaaS: Software as a Service (SaaS),
sometimes referred to as "software on demand," is
software that is deployed over the internet and/or is
deployed to run behind a firewall on a local area
network or personal computer. With SaaS, a provider
licenses an application to customers either as a
service on demand, through a subscription, in a "payas-you-go" model.
b) IaaS: "Infrastructure as a Service (IaaS)",

Cloud Computing

delivers computer infrastructure - typically a platform

Cloud Computing is not a very new concept
in IT, in fact Cloud Computing is a more advanced
version of the Data Processing Service Bureaus that
we had 40 years ago. Nevertheless, the best known
companies in the IT field offer or will shortly offer
Cloud Computing services to a range of customers
from organizations of all sizes to individuals. The
cloud model is been classified into three types:

virtualization environment - as a service. Rather than

purchasing servers, software, data-center space or
network equipment, clients instead buy those
resources as a fully outsourced service.
c)

PaaS: Platform as a Service (PaaS) is the

delivery of a computing platform and solution stack

as a service. PaaS offerings facilitate deployment of
applications without the cost and complexity of

a) Public Clouds: Public cloud is the most

buying and managing the underlying hardware and

common deployment model where the service are

software and provisioning hosting capabilities,

available to anyone on the internet. The service is

providing all of the facilities required to support the

available to public in a pay-as you-go manner.

complete life cycle of building and delivering web

b) Private

Clouds:

Private

clouds

are

deployed within an organization to provide IT

services to its internal user. It offers a great control

applications and services entirely available from the

Internet.
Green Computing

over the infrastructure, improving security and

service because its access is restricted within an
organization.

Green computing is the environmentally

responsible and eco-friendly use of computer and its

Hybrid Clouds: Hybrid clouds is emerged

resources. It is also defined as the process of

due to the diffusion of both public and private cloud

designing, manufacturing, and disposing computer

advantages. By this model, organizations outsource

devices which will not affect environment. Most of

non-critical information and processing to public

the IT companies now started to realize that moving

c)

green computing not only terms of public relation but

also it will reduce the cost. Currently the IT

are widely distributed. They are: Sever and storage

industries are responsible for 3% of the worlds

virtualization

energy consumption with an increase of 20% every

year. By 2030 the power consumption will be double.

A) Server Virtualization:

virtual server

allows several machines to share the same physical

The five core green computing technologies

server to run instead of having their own server that

are: Green Data Center, Virtualization, Green Cloud

leads to less cost in terms of hardware, management

Computing,

for their infrastructure facilities and space.

Power

Optimization

and

Grid

Computing. This technology is beneficial as it:

Reduce energy consumption of computing

resources during peak operation.

Save energy during idle operation.

Use eco-friendly sources of energy.

Reduce harmful effects of computing

resources.

Reduce computing wastes.

B) Storage Virtualization: Many applications

produces lots of data that cannot be stored in a single
server due to storage capacity. Another problem is
that multiple user can access the same data at the
same time which could cause traffic over the
network. For this reason data should be virtualized to
avoid access problem and improve the data
management along with reducing cost.
Load Balancing in Cloud
Load balancing in clouds is a mechanism
that distributes the excess load evenly across many
servers. This technique is used to achieve high user
satisfaction and resource utilization this helps in high
performance improvement. Proper load balancing can
help in utilizing the available resources optimally,
thereby minimizing the resource consumption.
Load balancing also required to achieve
green computing in clouds. Which can be done two
types:
1.

Reducing Energy Consumption: Load

balancing helps in avoiding overheating by balancing

the workload across many servers. By which we can
Virtualization
Virtualization is the main key factor for

reduce the amount of energy consumed.

2.

Reducing

Carbon

Emission:

Energy

Cloud Computing to attain sustainability from the

consumption and carbon emission are hand in hand.

cost and energy efficient point of view. Even though

The more the energy is consumed, higher the carbon

there are different types of virtualization, two types

emission. As the energy consumption is reduced by

load balancing. So we can reduce the carbon

Conclusion

emission by which we can achieve green computing.

energy consumption analysis of cloud computing and

Cloud Enabling Green Computing

The

important

technology

for

energy

efficient in clouds is the Virtualization Which helps

in significant improvement in energy efficient by
sharing

the

same

infrastructure.

By

In this paper, I presented a comprehensive

using

virtualization companies can gain high savings in the

how it can be reduced. By using techniques like load

balancing and virtualization we can reduce the power
consumption of cloud data centers which will in turn
reduce the emission of carbon-di-oxide. I also
discussed the types of virtualization used in cloud
data centers and the features of green enabled cloud

form of space, management, and energy.

computing.
Dynamic Provision: In traditional computing,
datacenters and private infrastructure used to be
maintained to fulfill worst case demand. Thus most
of the IT companies deploy more infrastructure than
needed. The reasons for this situation are: a) it is very
difficult to predict the demand before itself. b) To

Whatever the technique is been used we have to

make some arrangements to reduce the power
consumption in cloud data centers and also the
emission of CO2 should be reduced. So that the
environment can be saved.

guarantee availability of services and to maintain

certain level of service quality to end users.

Reference
[1] Baliga, J.; Ayre, R.W.A.; Hinton, K.; Tucker,

Multi-tenancy: Using this approach, we can reduce

RodneyS., "Green Cloud Computing: Balancing

the energy usage and associated carbon emissions.

Energy in Processing, Storage, and Transport,"

Proceedings of the IEEE , vol.99, no.1, Jan.

The SaaS providers serve on the same infrastructure

2011,pp.149-167.

and software. This method is more useful than having

multiple copies of software installed on different

[2] Aikema, D.; Mirtchovski, A.; Kiddle, C.; Simmonds, R.

"Green

servers.

cloud

VM

migration:

Power

use

analysis", Green Computing Conference (IGCC), 2012

Server

Utilization:

Sometimes

on-premise

International, pp. 1 6.

infrastructure runs with very low utilization. Using

virtualization same application can be hosted and

[3] Yamini, R., "Power management in cloud computing

using green algorithm," Advances in Engineering,

used on the same server thus lead to utilization up to

Science and Management (ICAESM), International

70%.

Conference on , 30-31 March 2012, pp.128,133.

Datacenter Efficiency: By using the most energy

[4] R. Brown et al., Report to congress on server and data

efficient technologies, cloud providers can improve

center energy efficiency: Public law 109-431,

the PUE of their datacenters. Today most of the

Lawrence Berkeley National Laboratory, 2008.

datacenters can achieve PUE levels low as 1.1 to 1.2,

[5]

Pike

Research

Article

on

green

date

center

which is nearly about 40% more energy efficient

([Link]

than traditional datacenters.

market-pike-research/).

[6] Siddharth Ghansela, Green Strategy for Reducing EWaste, International Journal of Advanced Research
in Computer Science and Software Engineering, vol 6,
issue 3, june 2013.
[7] Jaya Prakash.S.; Subramanyam.K.; Prasad.U.D.S.V.
Toward energy efficiency of green computing based
on virtualization, International Journal of emerging
trends in engineering and development, vol 7, issue 2,
nov 2012,pp.1-5.
[8] Gaurav Jindal.; Manisha Gupta, Green Computing
Future of Computers, International Journal of
Emerging Research in Management &Technology,
December 2012.
[9] Nidhi Jain Kansal.; Inderveer Chana., Cloud Load
Balancing Techniques : A Step Towards Green
Computing , IJCSI International Journal of Computer
Science Issues, Vol. 9, Issue 1, No 1, January 2012.