International Journal of Communication Systems,
Journal Year:
2020,
Volume and Issue:
33(14)
Published: July 15, 2020
Summary
Internet
of
Things
(IoT)
is
an
ecosystem
that
can
improve
the
life
quality
humans
through
smart
services,
thereby
facilitating
everyday
tasks.
Connecting
to
cloud
and
utilizing
its
services
are
now
public
common,
experts
seek
find
some
ways
complete
computing
use
it
in
IoT,
which
next
decades
will
make
everything
online.
Fog
computing,
where
expands
edge
network,
one
way
achieve
objectives
delay
reduction,
immediate
processing,
network
congestion.
Since
IoT
devices
produce
variations
workloads
over
time,
application
experience
traffic
trace
fluctuations.
So
knowing
about
distribution
future
required
handle
workload
while
meeting
QoS
constraint.
As
a
result,
context
fog
main
objective
resource
management
dynamic
provisioning
such
avoids
excess
or
dearth
provisioning.
In
present
work,
we
first
propose
distributed
framework
for
autonomic
computing.
Then,
provide
customized
version
system
based
on
control
MAPE‐k
loop.
The
makes
reinforcement
learning
technique
as
decision
maker
planning
phase
support
vector
regression
analysis
phase.
At
end,
conduct
family
simulation‐based
experiments
assess
performance
our
introduced
system.
average
delay,
cost,
violation
decreased
by
1.95%,
11%,
5.1%,
respectively,
compared
with
existing
solutions.
Soft Computing,
Journal Year:
2020,
Volume and Issue:
25(19), P. 12569 - 12588
Published: Dec. 12, 2020
Abstract
The
ubiquitous
diffusion
of
cloud
computing
requires
suitable
management
policies
to
face
the
workload
while
guaranteeing
quality
constraints
and
mitigating
costs.
typical
trade-off
is
between
used
power
adherence
a
service-level
metric
subscribed
by
customers.
To
this
aim,
possible
idea
use
an
optimization-based
placement
mechanism
select
servers
where
deploy
virtual
machines.
Unfortunately,
high
packing
factors
could
lead
performance
security
issues,
e.g.,
machines
can
compete
for
hardware
resources
or
collude
leak
data.
Therefore,
we
introduce
multi-objective
approach
compute
optimal
strategies
considering
different
goals,
such
as
impact
outages,
required
datacenter,
perceived
users.
Placement
are
found
using
deep
reinforcement
learning
framework
best
heuristic
each
machine
composing
workload.
Results
indicate
that
our
method
outperforms
bin
heuristics
widely
in
literature
when
either
synthetic
real
workloads.
Scientific Reports,
Journal Year:
2023,
Volume and Issue:
13(1)
Published: Jan. 10, 2023
The
massive
upsurge
in
cloud
resource
demand
and
inefficient
load
management
stave
off
the
sustainability
of
Cloud
Data
Centres
(CDCs)
resulting
high
energy
consumption,
contention,
excessive
carbon
emission,
security
threats.
In
this
context,
a
novel
Sustainable
Secure
Load
Management
(SaS-LM)
Model
is
proposed
to
enhance
for
users
with
CDCs.
model
estimates
reserves
required
resources
viz.,
compute,
network,
storage
dynamically
adjust
subject
maximum
sustainability.
An
evolutionary
optimization
algorithm
named
Dual-Phase
Black
Hole
Optimization
(DPBHO)
optimizing
multi-layered
feed-forward
neural
network
allowing
estimate
usage
detect
probable
congestion.
Further,
DPBHO
extended
Multi-objective
secure
sustainable
VM
allocation
minimize
number
active
server
machines,
wastage
greener
SaS-LM
implemented
evaluated
using
benchmark
real-world
Google
Cluster
traces.
compared
state-of-the-arts
which
reveals
its
efficacy
terms
reduced
emission
consumption
up
46.9%
43.9%,
respectively
improved
utilization
16.5%.
PeerJ Computer Science,
Journal Year:
2022,
Volume and Issue:
8, P. e834 - e834
Published: Jan. 12, 2022
The
demand
for
virtual
machine
requests
has
increased
recently
due
to
the
growing
number
of
users
and
applications.
Therefore,
placement
(VMP)
is
now
critical
provision
efficient
resource
management
in
cloud
data
centers.
VMP
process
considers
a
set
machines
onto
physical
machines,
accordance
with
criteria.
optimal
solution
multi-objective
can
be
determined
by
using
fitness
function
that
combines
objectives.
This
paper
proposes
novel
model
enhance
performance
decision-making
process.
Placement
decisions
are
made
based
on
three
criteria:
time,
power
consumption,
wastage.
proposed
aims
satisfy
minimum
values
objectives
all
available
machines.
To
optimize
solution,
was
implemented
optimization
algorithms:
particle
swarm
Lévy
flight
(PSOLF),
flower
pollination
(FPO),
hybrid
algorithm
(HPSOLF-FPO).
Each
tested
experimentally.
results
comparative
study
between
algorithms
show
strongest
performance.
Moreover,
against
bin
packing
best
fit
strategy.
outperforms
strategy
total
server
utilization.
Electronics,
Journal Year:
2023,
Volume and Issue:
12(11), P. 2452 - 2452
Published: May 29, 2023
With
the
proliferation
of
Internet
Things
(IoT)
and
development
wireless
communication
technologies
such
as
5G,
new
types
services
are
emerging
mobile
data
traffic
is
growing
exponentially.
The
computing
model
has
shifted
from
traditional
cloud
to
edge
(MEC)
ensure
QoS.
main
feature
MEC
“sink”
network
resources
meet
needs
delay-sensitive
computation-intensive
services,
provide
users
with
better
services.
Computation
offloading
one
major
research
issues
in
MEC.
In
this
paper,
we
summarize
state
art
task
First,
introduce
basic
concepts
typical
application
scenarios
MEC,
then
formulate
problem.
analyze
industry
terms
key
technologies,
schemes,
scenarios,
objectives.
Finally,
an
outlook
on
challenges
future
directions
computational
techniques
indicate
suggested
direction
follow-up
work.
