Power Management in Green Computing

1. POWER MANAGEMENT IN
GREEN COMPUTING
By: Mukund Mudakavi
SDM College of Engineering and Technology

2. ABSTRACT:
Green computing or green IT, refers to
environmentally sustainable computing
or IT. It is "the study and practice of
designing, manufacturing, using, and
disposing of computers, servers, and
associated subsystems—such as
monitors, printers, storage devices, and
networking and communications
systems—efficiently and effectively with
minimal or no impact on the
environment.

3. 1. Introduction to Power
management :
The Advanced Configuration
and Power Interface (ACPI), an
open industry standard, allows
an operating system to directly
control the power saving
aspects of its underlying
hardware. This allows a system
to automatically turn off
components such
as monitors and hard
drives after set periods of
inactivity

4. 2. Power supply :
 Desktop computer power supplies (PSUs)
are generally 70–75%
efficient, dissipating the remaining
energy as heat. An industry initiative
called 80 PLUS certifies PSUs that are at
least 80% efficient; typically these
models are drop-in replacements for
older, less efficient PSUs of the same
form factor . As of July 20,
 2007, all new Energy Star 4.0-certified
desktop PSUs must be at least 80%
efficient.

5. Power Savings Opportunities :
Following areas where the authors felt that
there is scope of optimising the usage of
power
 I/O devices
 Storage units
 Processors
 Operating Systems
 Due to their frequency of operation in
any computing devices.

6.  As illustrated below, today’s average
desktop computer with a cathode ray
tube (CRT) monitor uses more than
five times as much energy as a laptop
(570 kWh/yr vs. 100 kWh/yr).
Therefore, replacing a desktop system
with a laptop system could save about
470 kWh/yr - nearly $40 annually.
Monitor choice greatly impacts the
overall system energy usage. For
example, simply switching from a CRT
to the increasingly common LCD
(liquid crystal display), yields the
desktop computer user savings of
more than 100 kWh/yr. Likewise,
much of the energy savings potential
from a laptop is negated if it is
connected to an external CRT
monitor.

8. 2.1 Display :
Brightnes White Grey Black CRT
s CRT CRT
100 85 74 63
50 84 67.5 60.5
0 77.7 65 60.0
Brightness Power Consumption
(watts)
0 15
50 23
100 28

9. Power Consumption CRT Monitor LCD Monitor
Parameter
Avg. consumption 76 W 20 W
Screen color sensitivity Extremely sensitive. Completely insensitive.
Consumes lot more power Consumes same power for all
(43% more) when displaying colors on screen.
white on screen.
Brightness setting sensitivity Moderately sensitive. Sensitive. Consumes higher
Consumes more power at power for higher brightness
higher brightness.
Less sensitive. (Almost Completely insensitive.
Contrast setting sensitivity insensitive when brightness Consumes same power for all
setting is low.) contrast
Consumption when turned 2W 0W
off from computer power
settings

10. 3. Processors Processor Power
Consumption :
 Testing power consumption of CPUs is a trickier
task than graphics cards. The differences in power
consumption between a CPU at idle and a CPU at
full load wasn't as large as with graphics cards. So
it is reported that the difference in idle and peak
scores.
 The systems all had the following common
components . . . .

11. COMPONENT MODEL
Power supply PC power and cooling Turbocool 850 SSI
Motherboard, Intel Testing Intel D975XBX
Motherboard, AMD testing ASUS A8N32-SLI
Memory, AMD testing 1GB Corsair XMS 3200XL, CAS 2-2-2-5
Memory, Intel testing Corsair XMS5300 Pro at 4-4-4-8
Graphics card Nvidia GeForce 7800 GTX (256MB)
Hard drive 1 Seagate 7200.8 160GB SATA
Hard drive 2 Western Digital 400GB SATA
Optical drive Sony multiformat DVD burner

12. Operating system issues
Linux vs. Windows Power Usage
In our "desktop usage" power tests,
both Fedora 8 Test 3 and Ubuntu
7.10 had consumed more power
than both versions of Microsoft
Windows tested. Fedora and Ubuntu
were consuming 65 Watts while
Windows XP had only consumed 58
Watts and Windows Vista was in the
middle with 62 Watts. Granted, this
test isn't very controlled and was
just intended to give a rough
overview.

14. 3. Conclusion :
 It has been observed that the power
management can be achieved by
controlling the use of the processor
through the optimized usage of processer
and the display devices through the
operating system. A little optimization in
the discussed areas will produce the
better power control for domestic and
commercial computing devices. The
power management has a large scope in
the portable devices also as it is the
technology of the future.

15. 4. REFERENCES :

San Murugesan, ―Harnessing Green IT: Principles and
Practices,‖ IEEE IT Professional, January-February
2008, pp 24-33
http://technet.microsoft.com/en-
us/windows/dd361745.aspx).
www.Internetworldstats.com for 2005 computer usage
statistics
www.Industcards.com for 2005 coal fired plants data
US EPA Energy information administration EGRID
2000 database as referred by
www.greenmountain.com
US EPA National Vehicle and Fuel Emissions
Laboratory EPA420-F-97-037 standards as referred by
www.greenmountain.com
http://www.energystar.gov/index.cfm?c=pm_mmd.pr_p
m_mmd AMD’s New Phenom Chips to Consume 45W –
Sources by Anton Shilov

16. THANK YOU 