Computers, materials & continua/Computers, materials & continua (Print),
Journal Year:
2024,
Volume and Issue:
80(2), P. 2557 - 2578
Published: Jan. 1, 2024
In
recent
decades,
fog
computing
has
played
a
vital
role
in
executing
parallel
computational
tasks,
specifically,
scientific
workflow
tasks.
cloud
data
centers,
takes
more
time
to
run
applications.
Therefore,
it
is
essential
develop
effective
models
for
Virtual
Machine
(VM)
allocation
and
task
scheduling
environments.
Effective
scheduling,
VM
migration,
allocation,
altogether
optimize
the
use
of
resources
across
different
nodes.
This
process
ensures
that
tasks
are
executed
with
minimal
energy
consumption,
which
reduces
chances
resource
bottlenecks.
this
manuscript,
proposed
framework
comprises
two
phases:
(i)
using
fractional
selectivity
approach
(ii)
by
proposing
an
algorithm
name
Fitness
Sharing
Chaotic
Particle
Swarm
Optimization
(FSCPSO).
The
FSCPSO
integrates
concepts
chaos
theory
fitness
sharing
effectively
balance
both
global
exploration
local
exploitation.
enables
wide
range
solutions
leads
total
cost
makespan,
comparison
other
traditional
optimization
algorithms.
algorithm's
performance
analyzed
six
evaluation
measures
namely,
Load
Balancing
Level
(LBL),
Average
Resource
Utilization
(ARU),
cost,
response
time.
relation
conventional
algorithms,
achieves
higher
LBL
39.12%,
ARU
58.15%,
1175,
makespan
85.87
ms,
particularly
when
evaluated
50
Neural Computing and Applications,
Journal Year:
2024,
Volume and Issue:
36(27), P. 16873 - 16897
Published: June 2, 2024
Abstract
The
artificial
hummingbird
algorithm
(AHA)
has
been
applied
in
various
fields
of
science
and
provided
promising
solutions.
Although
the
demonstrated
merits
optimization
area,
it
suffers
from
local
optimum
stagnation
poor
exploration
search
space.
To
overcome
these
drawbacks,
this
study
redesigns
update
mechanism
original
AHA
with
natural
survivor
method
(NSM)
proposes
a
novel
metaheuristic
called
NSM-AHA.
strength
developed
is
that
performs
population
management
not
only
according
to
fitness
function
value
but
also
NSM
score
value.
adopted
strategy
contributes
NSM-AHA
exhibiting
powerful
avoidance
unique
ability.
ability
proposed
was
compared
21
state-of-the-art
algorithms
over
CEC
2017
2020
benchmark
functions
dimensions
30,
50,
100,
respectively.
Based
on
Friedman
test
results,
observed
ranked
1st
out
22
competitive
algorithms,
while
8th.
This
result
highlights
provides
remarkable
evolution
convergence
performance
algorithm.
Furthermore,
two
constrained
engineering
problems
including
single-diode
solar
cell
model
(SDSCM)
parameters
design
power
system
stabilizer
(PSS)
are
solved
better
results
other
9.86E
−
04
root
mean
square
error
for
SDSCM
1.43E
03
integral
time
PSS.
experimental
showed
optimizer
solving
global
problems.
IEEE Transactions on Consumer Electronics,
Journal Year:
2024,
Volume and Issue:
70(1), P. 3802 - 3809
Published: Feb. 1, 2024
The
growth
of
the
Internet
Things
(IoT)
has
intensely
enlarged
number
related
devices
creating
and
consuming
data.
To
handle
this
ever-growing
data
flow,
Next-Generation
networks
are
developing
near
a
hybrid
architecture,
weaving
organized
edge
computing
power
(Fog)
with
cloud's
vast
resources.
However,
orchestrating
scheduling
jobs
across
dissimilar
landscape
presents
difficult
task.
Scheduling
in
IoT-Fog-Cloud
Networks
is
dangerous
facet
attaching
full
potential
IoT,
fog
computing,
cloud
infrastructure.
By
authorizing
effectual
scheduling,
metaheuristic
algorithms
donate
to
improved
survivability
systems.
They
guarantee
on-time
task
implementation,
diminish
resource
bottlenecks,
allocate
computational
loads
efficiently,
decreasing
effect
failures.
With
strong
these
can
adjust
unpredictable
states,
ensuring
seamless
flow
constant
service
for
both
real-time
non-real-time
uses.
This
manuscript
offers
design
Metaheuristic
Mountain
Gazelle
Optimization
Algorithm
based
approach
(MMGOA-TSA)
IoT
Fog-Cloud
Networks.
foremost
intention
MMGOA-TSA
technique
optimally
plan
demands
fog-cloud
network.
follows
concept
MGOA,
which
stimulated
by
social
life
wild
mountain
gazelles
(MG)
hierarchy.
Meanwhile,
determines
optimal
candidate
solutions
from
or
nodes
offloading
any
be
executed
such
method
that
effective
trade-off
among
response
time
energy
utilization
accomplished.
experimental
validation
verified
employing
set
simulations.
comparative
result
analysis
stated
gains
better
performance
over
other
techniques
terms
distinct
actions.
International Journal of Information Technology and Computer Science,
Journal Year:
2024,
Volume and Issue:
16(1), P. 1 - 12
Published: Jan. 30, 2024
Cloud
fog
computing
is
a
new
paradigm
that
combines
cloud
and
to
boost
resource
efficiency
distributed
system
performance.
Task
scheduling
crucial
in
because
it
decides
the
way
computer
resources
are
divided
up
across
tasks.
Our
study
suggests
Shark
Search
Krill
Herd
Optimization
(SSKHOA)
method
be
incorporated
into
computing's
task
scheduling.
To
enhance
both
global
local
search
capabilities
of
optimization
process,
SSKHOA
algorithm
shark
krill
herd
algorithm.
It
quickly
explores
solution
space
finds
near-optimal
work
schedules
by
modelling
swarm
intelligence
herds
predator-prey
behavior
sharks.
In
order
test
efficacy
algorithm,
we
created
synthetic
environment
performed
some
tests.
Traditional
techniques
like
LTRA,
DRL,
DAPSO
were
used
evaluate
findings.
The
experimental
results
demonstrate
outperformed
baseline
algorithms
terms
success
rate
increased
34%,
reduced
execution
time
36%,
makespan
54%
respectively.
