Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Дек. 30, 2024
The
best
layout
design
related
to
the
sensor
node
distribution
represents
one
among
major
research
questions
in
Wireless
Sensor
Networks
(WSNs).
It
has
a
direct
impact
on
WSNs'
cost,
detection
capabilities,
and
monitoring
quality.
optimization
of
several
conflicting
objectives,
including
as
load
balancing,
coverage,
lifetime,
connection,
energy
consumption
nodes,
is
necessary
for
optimization.
Layout
an
NP-hard
combinatorial
issue.
A
number
meta-heuristic
strategies
have
been
put
out
address
this
issue
past
ten
years.
Nevertheless,
these
methods
only
addressed
subset
objectives-combinations
consumption,
count
area
lifetime-or
they
offered
computationally
costly
solutions.
Therefore,
paper
presents
problem
using
novel
intelligent
deep
learning-based
methodology.
Here,
objective
cover
numerous
objectives
associated
with
optimal
layouts
homogeneous
WSNs
that
involves
connectivity,
nodes.
handled
by
Advanced
Generative
Adversarial
Network
(AGAN),
where
parameter
tuning
performed
nature
inspired
algorithm
called
Piranha
Foraging
Optimization
Algorithm
(PFOA),
consideration
deriving
function.
Simulation
findings
revealed
proposed
AGAN-PFOA
generated
Pareto
front
non-dominated
solutions
having
better
hyper-volumes
well
spread
than
state-of-the-art
WSN
terms
PDR,
alive
count,
delay,
routing
overhead
61.46%,
15.12%,
12.67%,
65.91%,
70.59%,
44.88%,
68.86%
existing
respectively.
Case Studies in Thermal Engineering,
Год журнала:
2024,
Номер
61, С. 104917 - 104917
Опубликована: Авг. 3, 2024
Accurate
estimation
of
unknown
parameters
complex
photovoltaic
models
is
crucial
to
whether
generators
can
efficiently
convert
energy.
When
a
model
has
multiple
diode
branches,
its
complexity
increases
geometrically.
To
address
the
problems
high
and
difficulty
in
estimation,
this
paper
proposes
an
effective
improved
algorithm
based
on
success-history
adaptation
differential
evolution
with
linear
population
size
reduction
(L-SHADE)—Bi-parameter
coordinated
updating
L-SHADE
parameter
decomposition
method
(CSpL-SHADED).
First
CSpL-SHADED,
dynamic
crossover
rate
ranking
technology
developed
bridge
relationship
between
individuals
rates,
thereby
improving
mutation
capabilities.
In
addition,
sub-population
mechanism
also
proposed
divide
entire
into
sub-populations
so
that
they
are
evenly
distributed
search
space,
ability
local
areas
improved.
Secondly,
solar
different
effectively
decomposed
nonlinear
by
method.
The
accurately
estimated
calculated
constructed
matrix
equation.
Through
experiments
four
complexity,
CSpL-SHADED
showed
strong
competitiveness
varying
degrees
compared
comparative
algorithms.
Algorithms,
Год журнала:
2024,
Номер
17(12), С. 589 - 589
Опубликована: Дек. 20, 2024
This
study
presents
an
innovative
hybrid
evolutionary
algorithm
that
combines
the
Arctic
Puffin
Optimization
(APO)
with
JADE
dynamic
differential
evolution
framework.
The
APO
algorithm,
inspired
by
foraging
patterns
of
puffins,
demonstrates
certain
challenges,
including
a
tendency
to
converge
prematurely
at
local
minima,
slow
rate
convergence,
and
insufficient
equilibrium
between
exploration
exploitation
processes.
To
mitigate
these
drawbacks,
proposed
approach
incorporates
features
JADE,
which
enhances
exploration–exploitation
trade-off
through
adaptive
parameter
control
use
external
archive.
By
synergizing
effective
search
mechanisms
modeled
after
behavior
puffins
JADE’s
advanced
strategies,
this
integration
significantly
improves
global
efficiency
accelerates
convergence
process.
effectiveness
APO-JADE
is
demonstrated
benchmark
tests
against
well-known
IEEE
CEC
2022
unimodal
multimodal
functions,
showing
superior
performance
over
32
compared
optimization
algorithms.
Additionally,
applied
complex
engineering
design
problems,
structures
mechanisms,
revealing
its
practical
utility
in
navigating
challenging,
multi-dimensional
spaces
typically
encountered
real-world
problems.
results
confirm
outperformed
all
optimizers,
effectively
addressing
challenges
unknown
areas
optimization.
