International Journal of Computer Networks And Applications,
Год журнала:
2024,
Номер
11(1), С. 1 - 1
Опубликована: Фев. 26, 2024
In
a
cloud
computing
environment,
good
resource
management
remains
major
challenge
for
its
operation.Implementing
virtual
machine
placement
(VMP)
on
physical
machines
helps
to
achieve
various
objectives,
such
as
allocation,
load
balancing,
energy
consumption,
and
quality
of
service.VMP
(virtual
placement)
in
the
is
critical,
so
it's
important
audit
implementation.It
must
take
into
account
resources
server,
including
CPU,
RAM,
storage.In
this
paper,
metaheuristic
algorithm
based
Grey
Wolf
Optimization
(GWO)
method
used
optimize
effectively
minimizing
number
active
host
servers.Experimental
results
demonstrate
effectiveness
proposed
method,
called
Virtual
Machine
Placement
(GWOVMP).The
reduces
power
consumption
by
20.99
wastage
1.80
compared
with
existing
algorithms.
Journal of King Saud University - Computer and Information Sciences,
Год журнала:
2021,
Номер
34(8), С. 6481 - 6490
Опубликована: Май 28, 2021
The
rapid
growth
in
the
cloud
data
center
needs
a
dynamic
resource
provision
to
maintain
Quality
of
Services
parameters.
To
guarantee
it,
Virtual
Machine
Migration
as
part
VM
Consolidation
has
significant
role.
Efficient
migration
requires
knowledge
host's
future
utilization
advance.
Because
high
variation
usage
and
workloads,
predicting
host
using
history
is
challenging.
This
paper
proposes
Support
Vector
Regression-based
methodology
predict
multiple
resource's
history.
A
Hybrid
Kernel
function
that
includes
radial
basis
polynomial
kernel
been
proposed
then
trains
multiple-resource
Compared
existing
approaches:
linear
regression-based
prediction,
Euclidean
distance,
Absolute
Summation
based
regression,
method
performs
better
terms
root
mean
square
error,
absolute
percentage
R2.
result
section
concludes
on
evaluating
error
percent,
prediction
16%
for
approach
predicts
with
7%,
64%,
67%
more
accuracy
than
MRHOD,
MDRHU-ED,
MDRHU-AS
approaches,
respectively.
Dynamic
consolidation
of
Virtual
Machines
(VMs)
can
effectively
enhance
the
resource
utilization
and
energy-efficiency
Cloud
Data
Centers
(CDC).
Existing
research
on
reservation
scheduling
signify
that
Service
Users
(CSUs)
play
a
crucial
role
in
improving
by
providing
valuable
information
to
service
providers.
However,
CSUs'
provided
minimization
energy
consumption
CDC
is
novel
direction.
The
challenges
herein
are
twofold.
First,
finding
right
benign
be
received
from
CSU
which
complement
CDC.
Second,
smart
application
such
significantly
reduce
To
address
those
challenges,
we
have
proposed
heuristic
VM
Consolidation
algorithm,
RTDVMC,
minimizes
through
exploiting
information.
Our
exemplifies
fact
if
VMs
dynamically
consolidated
based
time
when
removed
—
useful
respective
CSU,
then
more
physical
machines
turned
into
sleep
state,
yielding
lower
consumption.
We
simulated
performance
RTDVMC
with
real
workload
traces
originated
than
800
PlanetLab
VMs.
empirical
figures
affirm
superiority
over
existing
prominent
Static
Adaptive
Threshold
DVMC
algorithms.
Sustainable
resource
management
within
a
cloud
computing
environment
is
highly
critical
and
prominently
studied
research
topic.
In
this
context,
paper
presented
comprehensive
survey
of
potential
sustainable
(Sus-RM)
strategies
that
have
addressed
the
energy
optimization
challenges
during
workload
scheduling
management.
The
perspective
followed
by
discussion
intended
motivation,
challenges,
objectives,
approaches
manifested.
designed
methodology
with
proposed
method-centric
classification
taxonomy
Sus-RM
conferred.
Based
on
common
features
managing
sustainability
dealing
operations
including
task
scheduling,
virtual
machine
(VM)
placement,
VM
rescheduling
or
migration,
are
further
grouped
into
class
category.
concept
behind
each
methodbased
approach
respective
state-of-the-art
belonging
to
category
concisely
discussed
their
pandect
comparative
summary.
Besides,
conceptual
theoretical
analysis,
takeaways
lessons
learned
outlining
method
presented.
Further,
trade-off
among
leading
capsuled
respectively
put
forward
imperative
concluding
remarks
about
holistic
study
Sus-RM.
Finally,
scientific
concluded
insightful
concrete
future
directions.
ACM Computing Surveys,
Год журнала:
2019,
Номер
52(4), С. 1 - 37
Опубликована: Авг. 30, 2019
The
dynamic
nature
of
the
cloud
environment
has
made
distributed
resource
management
process
a
challenge
for
service
providers.
importance
maintaining
quality
in
accordance
with
customer
expectations
and
highly
cloud-hosted
applications
add
new
levels
complexity
to
process.
Advances
big-data
learning
approaches
have
shifted
conventional
static
capacity
planning
solutions
complex
performance-aware
methods.
It
is
shown
that
decision-making
adjustment
closely
related
behavior
system,
including
utilization
resources
application
components.
Therefore,
continuous
monitoring
system
attributes
performance
metrics
provides
raw
data
analysis
problems
affecting
application.
Data
analytic
methods,
such
as
statistical
machine-learning
approaches,
offer
required
concepts,
models,
tools
dig
into
find
general
rules,
patterns,
characteristics
define
functionality
system.
Obtained
knowledge
from
helps
determine
changes
workloads,
faulty
components,
or
can
cause
degrade.
A
timely
reaction
degradation
avoid
violations
level
agreements,
performing
proper
corrective
actions
auto-scaling
other
solutions.
In
this
article,
we
investigate
main
requirements
limitations
management,
study
workload
anomaly
context
cloud.
taxonomy
works
on
problem
presented
identifies
existing
research
side
techniques.
Finally,
considering
observed
gaps
direction
reviewed
works,
list
these
proposed
future
researchers
pursue.
