Conference PaperPDF Available

Abstract

Green cloud computing aims at a processing infrastructure that combines flexibility, quality of services, and reduced energy utilisation. In order to achieve this objective, the management solution must regulate the internal settings to address the pressing issue of data centre over- provisioning related to the need to match the peak demand. In this context, we propose an integrated solution for environment, services and network management based on organisation model of autonomous agent components. This work introduces the system management model, analyses the system’s behaviour, describes the operation principles, and presents a case study scenario and some results. We extended CloudSim to simulate the organisation model approach and implemented the migration and reallocation policies using this improved version to validate our management solution.
Environments
, Services
and
Network
Management for Green
Clouds
Carlos Becker Westphall
Networks and Management Laborato ry
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
1
Summary
1
-
Introduction
2
-
Motivation
3
-
Proposals
and
Solutions
3
-
Proposals
and
Solutions
4
-
Case
Studies
5
-
Results
6
-
Conclusions
7
-
Future Works
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
2
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
3
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
1 Introdu ctio n
W
e
propose
an
integrated
solution
for
environment,
services
and
netwo rk
management
based
on
organization
theory
model
.
This
work
introduces
the
system
management
model,
analyses
the
system’s
behavior
,
describes
the
operation
principles,
and
presents
case
studies
and
some
results
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
4
1 Introdu ctio n
We
extended
CloudSim
to
simulate
the
organization
model
approach
and
implemented
the
migration
and
reallocation
policies
using
this
improved
versio n
to
validate
our
management
solution
.
Organization
:
2
introduces
a
motivating
scenario
.
3
outlines
the
system
design
.
4
presents
case
studies
.
5
presents
some
results
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
5
2 Motivation
Our
research
was
motivated
by
a
practical
scenario
at
our
universitys
data
center
.
Organization
theory
model
for
integrated
management
of
the
green
clouds
focusing
management
of
the
green
clouds
focusing
on
:
(i)
optimizing
resource
allocation
through
predictive
models
;
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
6
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
7
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
2 Motivation
(ii)
coordinating
control
over
the
multiple
elements,
reducing
the
infrastructure
utilization
;
(iii)
promoting
the
“balance”
between
local
(iii)
promoting
the
“balance”
between
local
and
remote
resources
;
and
(iv)
aggregating
energy
management
of
network
devices
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
8
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
9
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
2 Motivation (
Concepts & Analysis)
Cloud computing
T
his
structure
describes
the
most
common
implementation
of
cloud
;
and
It
is
based
on
server
virtualization
It
is
based
on
server
virtualization
functionalities,
where
there
is
a
layer
that
abstracts
the
physical
resources
of
the
servers
and
presents
them
as
a
set
of
resources
to
be
shared
by
VMs
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
10
The NIST Cloud Definition Framework
CommunityCommunity
CloudCloud
PrivatePrivate
CloudCloud
Public CloudPublic Cloud
Hybrid Clouds
Deployment
Models
Service
Models
Software as a
Service (
SaaS
)
Platform as a
Service (
Paa S
)
Infrastructure as a
Service (
IaaS
)
11
Essential
Characteristics
Common
Characteristics
Re source Pooling
Broad Network Access
Rapid Elasticity
Measured Service
On Demand Self
-
Service
Low Cost Software
Virtualization
Service Orientation
Advanced Security
Homogeneity
Massive Scale
Re silient Computing
Geographic Distribution
Based upon original chart created by Alex Dowbor
2 Motivation (
Concepts & Analysis)
Green
cloud
T
he
green
cloud
is
not
very
different
from
cloud
computing,
but
it
infers
a
concern
over
the
structure
and
the
social
over
the
structure
and
the
social
responsibility
of
energy
consumption
;
and
H
ence
aiming
to
ensure
the
infrastructure
sustainability
without
breaking
contracts
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
12
2 Motivation (
Concepts & Analysis)
Analysis
Table
I
relates
(
1
)
the
3
possible
combinations
between
VMs
and
PMs
,
with
(
2
)
the
average
activation
delay,
and
(
3
)
the
(
2
)
the
average
activation
delay,
and
(
3
)
the
chances
of
the
services
not
being
processed
(risk
)
;
and
I
t
also
presents
the
energy
consumed
according
to
each
scenario
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
13
2 Motivation (
Concepts & Analysis)
PM State
VM
State
Time
Risks
Watts
Consumption
Down
Down
30s
High
0Ws
None
Up
Down
10s
Medium
200Ws
Medium
Up
Down
10s
Medium
200Ws
Medium
Up
Up
0s
None
215Ws
High
R
ELAT ION
BETWEEN
SITUATIONS
&R
ISKS
&A
CTIVATION
DELAY
&C
ONSUMPTION
(ASSUNÇÃO, M. D.
ET
AL
. ENERGY 2010)
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
14
2
Motivation
(
Related Works)
E
.
Pinheiro
,
et
al
.
Load
balancing
and
unbalancing
for
power
and
performance
in
cluster
-
based
systems
in
Proceedings
of
the
Workshop
on
Compilers
and
Operating
Systems
for
Low
Power
.
2001
.
Systems
for
Low
Power
.
2001
.
Pinheiro
et
al
.
have
proposed
a
technique
for
managing
a
cluster
of
physical
machines
that
minimizes
power
consumption
while
maintaining
the
QoS
level
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
15
2
Motivation
(
Related Works)
The
main
technique
to
minimize
power
consumption
is
to
adjust
the
load
balancing
system
to
consolidate
the
workload
in
some
resources
of
the
cluster
to
shut
down
the
idle
resources
.
resources
.
At
the
end,
besides
having
an
economy
of
20
%
compared
to
fulltime
online
clusters,
it
saves
less
than
6
%
of
the
whole
consumption
of
the
data
center
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
16
2
Motivation
(
Related Works)
R
.
N
.
Calheiros,
et
al
.
Cloudsim
:
A
toolkit
for
modeling
and
simulation
of
cloud
computing
environments
and
evaluation
of
resource
provisioning
algorithms
Software
:
Practice
provisioning
algorithms
Software
:
Practice
and
Experience
.
2011
.
Calheiros
et
al
.
have
developed
a
framework
for
cloud
computing
simulation
.
It
has
four
main
features
:
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
17
2
Motivation
(
Related Works)
(i)
it
allows
for
modeling
and
instantiation
of
major
cloud
computing
infrastructures
,
(ii)
it
offers
a
platform
providing
flex ibility
of
service
brokers
,
scheduling
and
allocati o ns
service
brokers
,
scheduling
and
allocati o ns
policies,
(iii)
its
virtualization
engine
can
be
customized
,
thus
providing
the
capability
to
simulate
hetero geneous
clouds,
and
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
18
2
Motivation
(
Related Works)
(iv)
it
is
capable
of
choosing
the
scheduling
strategies
for
the
resources
.
R
.
Buyya,
et
al
.
Intercloud
:
Utility
-
oriented
federation
of
cloud
computing
environments
federation
of
cloud
computing
environments
for
scaling
of
application
services
Proceedings
of
the
10
th
International
Conference
on
Algorithms
and
Archi tectures
for
Parallel
Processing
.
2010
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
19
2
Motivation
(
Related Works)
Buyya
et
al
.
suggested
creatin g
federated
clouds,
called
Interclouds
,
which
form
a
cloud
computing
environment
to
support
dynamic
expansion
or
contraction
.
expansion
or
contraction
.
The
simulation
results
revealed
that
the
availability
of
these
federated
clouds
reduces
the
average
turn
-
around
time
by
more
than
50
%
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
20
2
Motivation
(
Related Works)
It
is
shown
that
a
significant
benefit
for
the
application’s
performance
is
obtained
by
using
simple
load
migration
policies
.
R
.
Buyya
,
et
al
.
Energy
-
Efficient
Management
of
Data
Center
Resources
for
Cloud
Computing
:
A
Data
Center
Resources
for
Cloud
Computing
:
A
Vision,
Architectural
Elements,
and
Open
Challenges
in
Proceedings
of
the
2010
International
Conference
on
Parallel
and
Distribute d
Processing
Techniques
and
Applications
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
21
2
Motivation
(
Related Works)
Buyya
et
al
.
aimed
to
create
architecture
of
green
cloud
.
In
the
proposals
some
simulations
are
executed
comparing
the
outcomes
of
propo sed
policies,
with
simulations
of
DVFS
(Dynamic
Voltage
and
Frequency
Scaling)
.
Voltage
and
Frequency
Scaling)
.
T
hey
leave
other
possible
research
directions
open,
such
as
optimization
problems
due
to
the
virtual
network
topology
,
increasing
response
time
for
the
migration
of
VMs
because
of
the
delay
between
servers
or
virtual
machines
when
they
are
not
located
in
the
same
data
centers
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
22
2
Motivation
(
Related Works)
L
.
Liu,
et
al
.
Greencloud
:
a
new
architecture
for
green
data
center
in
Proceedings
of
the
6
th
international
conference
industry
session
on
auto nomic
computing
.
2009
.
on
auto nomic
computing
.
2009
.
Liu
et
al
.
presented
the
GreenCloud
architecture
to
reduce
data
center
power
consumption
while
guaranteeing
the
performance
from
user
perspective
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
23
2
Motivation
(
Related Works)
P
.
Mahavadevan
,
et
al
.
On
Energy
Efficiency
for
Enterprise
and
Data
Center
Networks
in
IEEE
Communications
Magazine
.
2011
.
Mahadevan
et
al
.
described
the
challenges
Mahadevan
et
al
.
described
the
challenges
relating
to
life
cycle
energy
management
of
netwo rk
devices,
present
a
sustainabi lity
analysis
of
these
devices,
and
develop
techniques
to
significantly
reduce
network
operation
power
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
24
2
Motivation
(
Problem Sc ena ri o)
To
understand
the
prob lem
scenario,
we
introduc e
the
elements,
interactions,
and
operation
principles
in
green
clouds
.
The
target
in
green
clouds
is
:
how
to
keep
The
target
in
green
clouds
is
:
how
to
keep
resources
turned
off
as
long
as
possible?
The
interactions
and
operation
principles
of
the
scenario
are
:
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
25
2
Motivation
(
Problem Sc ena ri o)
(i)
there
are
multiple
applications
generating
different
load
requirements
over
the
day
;
(ii)
a
load
“bala nce”
system
distributes
the
load
to
active
servers
in
the
processing
pool
;
load
to
active
servers
in
the
processing
pool
;
(iii)
the
resources
are
grouped
in
clusters
that
include
servers
and
local
environmental
control
units
;
and
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
26
2
Motivation
(
Problem Sc ena ri o)
(iv)
the
management
system
can
turn
on/off
machines
overtime,
but
the
question
is
when
to
activate
resources
on
-
demand?
In
other
words,
taking
too
much
delay
to
In
other
words,
taking
too
much
delay
to
activate
resources
in
response
to
a
surge
of
demand
(too
reactive)
may
result
in
the
shortage
of
processing
power
for
a
while
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
27
3
Propos al s
and
Solutions
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
28
3
Propos al s
and
Solutions
The four ro les that operations system may be
classified as are
: VM management; Servers
management; Netwo rk management; and
Environment management.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
29
Environment management.
The three roles that service system may be
classified as are
: Monitor element; Service
scheduler; and Service analyser.
4 Case
Studies
We
modeled
the
system
using
Norms
(NM),
Beliefs
(BL)
and
Plan
Rules
(PR),
inferring
that
we
would
need
(NM)
to
reduce
energy
consumption
.
consumption
.
Based
on
inferences
from
NM,
BL
and
PR
agents
would
monitor
the
system
and
determine
actions
dynamically
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
30
5
Results
The
main
components
implemented
in
the
improved
version
at
CloudSim
are
as
follows
:
HostMonitor
:
controls
the
input
and
output
of
physical
machines
;
VmMonitor
:
controls
the
input
and
output
of
virtual
machines
;
NewBroker
:
controls
the
size
of
requests
;
SensorGlobal
:
controls
the
sensors
;
requests
;
SensorGlobal
:
controls
the
sensors
;
CloudletSchedulerSpaceShareByTimeout
:
controls
the
size
and
simulation
time
;
VmAllocationPol icyExtended
:
allocati o n
policy
;
VmSchedulerExtended
:
allocates
the
virtual
machines
;
UtilizationModelFunction
:
checks
the
format
of
requests
;
CloudletWaiting
:
controls
the
time
of
the
request
;
and
DatacenterExtended
:
controls
the
datacenter
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
31
5
Results
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
32
(J. Werner, G. A. Geronimo, C. B. Westphall et al. LANOMS 2011)
5
Results
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
33
5
Results
Parameter
Value
VM
Image
size
1GB
VM
-
RAM
256MB
PM
-
Engine
Xen
PM
-
RAM
8GB
PROPOSED SCENARIO
CHARACTERISTCS
(
J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
PM
-
RAM
8GB
PM
-
Frequency
3.0GHZ
PM
-
Cores
2
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
34
5
Results
(
consumption
)
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
35
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
5
Results
(SLA
violations
)
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
36
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
5
Results
(
Hybrid
strategy
)
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
37
5
Results
(
Hybrid
strategy
)
Strate gy
Cost
Consumption
On
-
demand
-
3.2 %
-
23.5 %
REDUCTION
OF COST AND POWER
CONSUMPTION
(J. Werner, G. A. Geronimo, C. B. Westphall et al. CLEI EJ 2012)
Idle resources
-
49.0 %
-
59.0 %
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
38
6
Conclusio ns
Tests
were
realized
to
prove
the
validity
of
the
system
by
utilizing
the
CloudSim
simulator
from
the
University
of
Melbourne
in
Australia
.
We
have
implemented
improvements
related
We
have
implemented
improvements
related
to
service
-
based
interaction
.
We
implemented
migration
policies
and
relocation
of
virtual
machines
by
monitoring
and
controlling
the
system
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
39
6
Conclusio ns
We
achieved
the
fol lowing
results
in
the
test
environment
:
-
Dynamic
physical
orchestration
and
service
orchestration
led
to
87
,
18
%
energy
savings,
orchestration
led
to
87
,
18
%
energy
savings,
when
compared
to
static
approaches
;
and
-
Improvement
in
load
“bala ncing
and
high
availability
schemas
provide
up
to
8
,
03
%
SLA
error
decrease
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
40
7 Future Wo rks
As
future
work
we
intend
to
simulate
other
strategies
to
get
a
more
accurate
feedback
of
the
model,
using
other
simulation
environment
and
testing
different
approaches
of
beliefs
and
plan
rules
.
rules
.
Furthermore
,
we
would
like
to
exploit
the
integration
of
other
approaches
from
the
field
of
artificial
intelligence,
viz
.
bayesian
networks,
advanced
strategies
of
intention
reconsideration,
and
improved
coordination
in
multi
-
agen t
systems
.
MARCH 3RD, REUNION ISLAND
IARIA GLOBENET 2012
-
KEYNOTE SPEECH
41
ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.