The document discusses the potential of green cloud computing in India, emphasizing the need for energy-efficient measures in data centers to reduce carbon emissions and operational costs. It outlines various strategies such as optimizing cooling systems, implementing virtualization, and utilizing renewable energy sources to achieve sustainability. Additionally, it highlights the limitations faced in adopting green cloud computing, including high component costs and maintenance challenges.

1. GREEN CLOUD COMPUTING
SUNNY KUMAR NIRALA (BE/1163/2011) PREM PRAKASH LEYANGI(BE/1168/2011)
AKASH LAL DAS (BE/1172/2011)
UNDER GUIDANCE OF Dr. SUBRAJEET MOHAPATRA

2. GREEN CLOUD COMPUTING
POTENTIAL OF GREEN CLOUD COMPUTING IN INDIA AND
MEASURES TO IMPROVE THE EFFICIENCY OF DATA CENTRES.

3. CLOUD COMPUTING
 Cloud computing is model for enabling convenient, on
demand network access to a shared pool of
configurable computing resources that can be rapidly
provisioned and released with minimal management
effort or service provider interaction.
 Cloud providers typically use a "pay as you go" model.
Pay As You Go (PAYG) is a utility computing billing

4. WHY? GREEN CLOUD COMPUTING
 power consumption of data centers has huge impacts on
environments.
 growing demand of Cloud infrastructure has drastically
increased the energy consumption of data centers, which
has become a critical issue.
 High energy consumption not only translates to high
operational cost, which reduces the profit margin of Cloud
providers, but also leads to high carbon emissions which is
not environmentally friendly. Hence, energy efficient
solutions are required to minimize the impact of Cloud
computing on the environment , hence the requirement for
green cloud computing.

5.  Information and Communication Technologies (ICT) industry
generates about 2% of the total global CO2 emissions, which is
equal to the aviation industry. According to a report published by
the European Union, a decrease in emission volume of 15%–30%
is required before year 2020 to keep the global temperature
increase below 2 degree C.
 Energy consumption and carbon emission by Cloud
infrastructures has become a key environmental concern.

6. COMPARISON OF DIFFERENT CLOUD
DATA CENTRES
Cloud
datacenters
Location Estimated
power usage
Effectivenes
s
% of Dirty
Energy
Generation
% of
Renewable
Electricity
Google Lenoir 1.21 50.5% Coal,
38.7%
Nuclear
3.8%
Apple Apple, NC 50.5% Coal,
38.7%
Nuclear
3.8%
Microsoft Chicago, IL 1.22 72.8% Coal,
22.3%
Nuclear
1.1%

7. GREEN CLOUD COMPUTING
MODEL
Data
centre
Power
Cooling
Design
Green computing

8. POWER USAGE EFFECTIVENESS
(PUE)
 Power usage effectiveness (PUE) is a metric used to determine
the energy efficiency of a data center.
 PUE = Total Facility Power / IT Equipment Power.
 DCiE = IT Equipment Power / Total Facility Power.
 1<= PUE <= infinity .
 Average PUE in US =1.91.
 Average PUE in INDIA =2.5 and above

9. Cooling device (Chiller, Computer
Room Air Conditioning (CRAC))
33%+9%
IT Equipment 30%
Electrical Equipments (UPS, Power
Distribution Units (PDUs), lighting)
28%
Within a datacenter is its cooling system that contributes to almost 1/3 of
total energy consumption.

10. IMPROVING COOLING EFFICIENCY IN
DATA CENTRES
 Implement Hot-Aisle/Cold-Aisle -
Arrange racks in rows so the fronts face each other in cold aisles
and the backs face each other in hot aisles. That prevents servers
from drawing in hot air from servers in the adjacent row . Hot-
aisle/cold-aisle configurations can reduce energy use up to 20%.
 Install Blanking Panels –
Blocking off unused rack spaces forces cold air through your
servers and prevents hot air from recirculating through the
enclosure.
 Organize Cables -
Tangled cables block airflow. They prevent efficient cold air
distribution under raised floors and cause heat to build up inside
enclosures.

11.  Use Close-Coupled Cooling -
Close-coupled cooling allows you to focus cooling where it’s
needed most without lowering the temperature of the entire room.
The modular nature of close-coupled cooling also allows data
center managers to quickly reconfigure cooling to handle new
equipment or overheating racks.
 Isolate and Remove Hot Air -
Thermal duct rack enclosures route hot air through an overhead
duct .
 Replace Inefficient UPS Systems -
Removing unnecessary heat sources helps cool the room.

12. COST EFFECTIVE COOLING OF DATA
CENTRES
 Data centres should be setup in those regions having lesser
temperature throughout the year.
 World’s leading tech. companies such as Google show us the
away , that a significant decrease in Power Usage Effectiveness
(PUE) can be obtained by simply choosing an appropriate
location for the data center. Regions with cooler temperature
throughout the year are more preferable. This is because cooling
consumes a large portion of total energy consumed in data
centers in India. As per Industry experts 80 degrees Fahrenheit is a
safe temperature value , considering IT equipment specifications.

13. DATA CENTRES IN INDIA
Location Sq. area(in sq. ft) Rack-loading(in kgs)
Ahmedabad 13,729 1000-1200
Mumbai 12,000 1000-1200
Jaipur 10,111 1000-1200
Ludhiana 7870 1000-1200
Faridabad 13,450 1000-1200
Ghaziabad 6280 1000-1200

14. MERITS OF DATA CENTRES IN
INDIA
 In india BSNL has incorporated with DIMENSION DATA to
develop data centres supporting green computing .Some features
of these data centres are
 1. Green Computing adoption.
 2. Incorporation of appropriate technology in infrastructure help us
reduce operational expenses such as power consumption and
heat generation and also reduce the carbon footprint.

15. HOW GREEN COMPUTING IS
ACHIEVED IN DATA CENTRES IN INDIA
 adopting “green” friendly technologies at various aspects of the data centre
such as :
 1. Exploring utilization of renewable energy sources to power
certain functional areas of the data centre.
 2. Deploying energy efficient servers and storage.
 3. Virtualization to drive up efficiency.
 4. Employing power saver features into the critical equipments, for
example servers go into sleep mode.
 5. Reduceing unnecessary operational overheads and travel by
centralizing all the operations through our command centre. We
are striving to run these data centres at a PUE of 1.7 .


16. POWER
 Data centres get power from electricity (which is produced by
burning coal in power plants leading to enormous amount of
carbon emission in the atmosphere) and backup
generators(running on deisel having high cost and adds to
pollution of the atmosphere).
 Feasible alternative leading to green cloud computing
 Initially POWER is obtained form ELECTRICITY(from
plants)+ELECTRICITY(from backup generator) .

17. RENEWABLE ENERGY AS A SOURCE
OF POWER
 The installed capacity of Renewable energy has touched 32,269.6
Mw or 12.95% of the total potential available in the country, as on
March 31, 2014. With this, the renewable energy, including large
hydro electricity, constitutes 28.8% of the overall installed capacity
in India.
 The untapped market potential for overall renewable energy in
India is 2,16,918.39 Mw that shows huge growth potential for
renewable energy in India.
 India has the world's fifth-largest electricity generation capacity,
which currently stands at 243 Gw.

18. Equipments used in Datacentres and their Power
Consumption
Equipment Capacity Power
consumption
Storage HP 8100 EVA 604.8 Tb 4.9 kW
Content Server HP DL380 G5 800 Mb/s 225 W
Computation
Server
HP DL380 G5 335 W
LAN Cisco 6509 320 Gb/s 3.8 kW
Gateway Router Juniper MX-960 660 Gb/s 5.1 kW
Ethernet
Switch(Small)
Cisco 4503 64 Gb/s 474 W
Ethernet Switch Cisco 6509 160 Gb/s 3.8 kW
BNG Juniper E320 60 Gb/s 3.3 kW
Provider Edge Cisco 12816 160 Gb/s 4.21 kW
Core Router Cisco CRS-1 640 Gb/s 10.9 kW
WDM(800Km) Fujitsu 7700 40 Gb/s 136 W/Channel

19. VIRTUALIZATION
 Virtualization software makes it possible to run multiple operating
systems and multiple applications on the same server at the same
time,“
 Virtualization converts discrete servers to virtualized images that
run as independent machines on a centralized server or server
pool.
 The technology behind virtualization is known as a virtual machine
monitor (VMM) or virtual manager
 Hardware Virtualization uses software that is called a hypervisor
(commonly VMware ESXi, Microsoft Hyper-V, or Citrix XenServer)
to abstract the physical characteristics of a server. This permits
multiple guest operating systems to run virtually on a single
physical server.
 "It enables businesses to reduce IT costs while increasing the
efficiency, utilization and flexibility of their existing computer
hardware.“

20. ADVANTAGES
 Maximize resources — Virtualization can reduce the number of
physical systems you need to acquire, and you can get more
value out of the servers. Most traditionally built systems are
underutilized.
 Multiple systems —run different operating systems and
applications
 IT budget integration — When you use virtualization,
management, administration and all the attendant requirements of
managing your own infrastructure remain a direct cost of your IT
operation. Reduce it staffing to manage different servers
individually.
 Large corporations with little downtime tolerance and airtight
security requirements may find that virtualization fits them best.
Traditionally suited with private clouds.

21. GREEN ADVANTAGES
 Desktop Virtualization facilitates a number of carbon-footprint reducing
initiatives:
 Freeing up of server or storage devices, which can then be re-deployed in
those areas where additional capacity is sought, thus preventing the need for
additional hardware purchase. Excess devices can be decommissioned,
thereby reducing the volume of IT hardware that needs to be powered,
maintained and cooled.
 Enables the deployment of greener, energy-efficient thin-client devices or
helps extend the lifespan of older, conventional, PC devices by deploying
them as lower-function access devices.
 By separating the user experience from a fixed device, users can access
their virtual desktops from a variety of locations. For business, this facilitates
environmentally friendly work-from-home or tele-commuting initiatives and
provides the business with the option of scaling back office-space
provisioning.

22. EXAMPLE OF
VIRTUALIZED/UNVIRTUALIZED DATA
CENTERS
 Before virtualization:
 Annual energy utilization = 100kW x 8760 hrs/yr = 876000 kWh
Annual electricity cost = 876000kWh x Rs. 3.10/kWh* = Rs. 27,
15,600
*Base Tariff for HT I – Industries – Mahadiscom
 After Virtualization:
 Assumption that the PUE goes up to 2.1 due to reduced capacity
utilization.
Annual energy utilization = (25+25*1.1=52.5) kW x 8760 hrs/yr =
459900 kWh
Annual electricity cost = 459900 kWh x Rs. 3.10/kWh* = Rs.
14,25,690
*Base Tariff for HT I – Industries – Mahadiscom, for example at
commercial consumer level prices are at more than 2x of these
levels.

23.  Tulip Telecom free up many racks, amounting to about Rs 30 lakh
per year. Power consumption by the datacenter has reduced to 8
KW, lowering power and cooling expenses by Rs 17 lakh per
year.
 Over all, the server virtualization project has helped Tulip Telecom
save almost Rs 55 lakh per year, while furthering its commitment
to greener datacenters.
 Considering that both data centers (both before and after
virtualization) are able to perform the same amount of work, we
can see from the above calculation that the virtualized data center
is noticeably more energy efficient.

24. EXAMPLE
 Capgemini can, on average, cut the number of servers needed by 55%-75%,
which would move the average utilization of a typical organization's IT estate from
between 5%-30% to as high as 65%-85%.

The most sustainable data center in the world
 Capgemini's newest data center, the Merlin facility in Swindon, UK, boasts
astounding energy-efficiency credentials, including:
 A PUE of 1.09 (factory tested)
 Capgemini's global infrastructure outsourcing services supports over 26,000
physical servers, of which 8,000 are virtualized.
 The fresh air-cooling system delivers 80% savings in run costs and produces up to
50% less carbon output.
 Uses 91% less power than a conventional data center with a PUE of 2.5
 Has a power plant that utilizes a state-of-the-art flywheel – not battery – UPS with
fast generators for improved resilience.

25. CARBON EMISSIONS EXAMPLE
USA
 Compared with natural gas, which emits between 0.6 and 2
pounds of carbon dioxide equivalent per kilowatt-hour
(CO2E/kWh), and coal, which emits between 1.4 and 3.6 pounds
of CO2E/kWh, wind emits only 0.02 to 0.04 pounds of
CO2E/kWh, solar 0.07 to 0.2,geothermal 0.1 to 0.2,
and hydroelectric between 0.1 and 0.5. Renewable electricity
generation from biomass can have a wide range of global warming
emissions depending on the resource and how it is harvested.
Sustainably sourced biomass has a low emissions footprint, while
unsustainable sources of biomass can generate significant global
warming emissions.

26. CHART APPROXIMATION
OF CARBON EMISSIONS

27. STABLE ENERGY PRICES
 Renewable energy is providing affordable electricity across the
country right now, and can help stabilize energy prices in the
future.
 The costs of renewable energy technologies have declined
steadily, and are projected to drop even more. For example, the
average price of a solar panel has dropped almost 60 percent
since 2011 . The cost of generating electricity from wind dropped
more than 20 percent between 2010 and 2012 and more than 80
percent since 1980 .
 While renewable facilities require upfront investments to build,
once built they operate at very low cost and, for most
technologies, the fuel is free. As a result, renewable energy prices
are relatively stable over time.

28. MEASURES TO IMPROVE EFFICIENCY
OF DATA CENTRE
 1. Processor Efficiency -processor manufacturers provide lower voltage versions
of their processors that consume on average 30 Watts less than standard
processors.
 2. Power Supplies -Best-in-class power supplies are available today that deliver
efficiency of 90 percent. Use of these power supplies reduces power draw within
the data center by 124 kW or 11 percent of the 1,127 kW total.
 3. Power management software -Data centers are sized for peak conditions that
may rarely exist. In a typical business data center, daily demand progressively
increases from about 5 a.m. to 11 a.m. and then begins to drop again at 5 p.m.
Server processors have power management features built-in that can reduce
power when the processor is idle.
 4. Blade Servers -Many organizations have implemented blade servers to meet
processing requirements and improve server management
 5. Server Virtualization-As server technologies are optimized, virtu- alization is
increasingly being deployed to increase server utilization and reduce the number
of servers required.

29.  6. Higher Voltage AC Power Distribution -Most data centers use a
type of UPS called a double-conversion system. These systems
convert incoming power to DC and then back to AC within the UPS.
This enables the UPS to generate a clean, consistent waveform for
IT equipment and effectively isolates IT equipment from the power
source.
 7. Cooling Best Practices -Most data centers have implemented
some best practices, such as the hot-aisle/cold- aisle rack
arrangement. Potential exists in sealing gaps in floors, using blanking
panels in open spaces in racks, and avoiding mixing of hot and cold
air.
 8. Variable-Capacity Cooling.
 9. High-Density Supplemental Cooling .
 10. Monitoring and Optimization -Room cooling units on one side of a
facility may be humidifying the environment based on local conditions
while units on the opposite side of the facility are dehumidifying.

30. Energy
saving
actions
Saving independent of
other action
Saving(kw) Saving(%)
Saving with cascade effect
Saving(Kw) Saving(%)
cumulative
s saving
Low power
processors
111 10 111 10 111
High-
efficiency
power
supplies
141 12 124 11 235
Power
management
features
125 11 88 8 321
Blade servers 8 1 7 1 328
Server
virtualization
156 14 86 8 414

31. Energy-Saving
Action
Saving independent
of other action
Saving(kw)
Saving(%)
Saving with cascade effect
Saving(Kw) Saving(%) Cumulative
s Saving
Higher Voltage
AC Power
Distribution
34 3 20 2 434
Cooling Best
Practices
24 2 15 1 449
Variable
Capacity
Cooling
79 7 49 4 498
Supplemental
Cooling
200 18 72 6 570
Monitoring and
Optimization
25 2 15 1 585

32. LIMITATION OF GREEN CLOUD
COMPUTING
 The principle limitation is the high cost of purchase of components
that are required to make the cloud computing more efficient and
more environment friendly(like cooling eqipments,carbon
emission rating meter etc.)
 The maintenance of devices in data centres is also a prime
limitation.
 The provision of power from renewable sources in developing
countries is limited and expensive .