Biomimetics,
Год журнала:
2025,
Номер
10(3), С. 176 - 176
Опубликована: Март 12, 2025
The
Educational
Competition
Optimizer
(ECO)
is
a
newly
proposed
human-based
metaheuristic
algorithm.
It
derives
from
the
phenomenon
of
educational
competition
in
society
with
good
performance.
However,
basic
ECO
constrained
by
its
limited
exploitation
and
exploration
abilities
when
tackling
complex
optimization
problems
exhibits
drawbacks
premature
convergence
diminished
population
diversity.
To
this
end,
paper
proposes
an
enhanced
optimizer,
named
EDECO,
incorporating
estimation
distribution
algorithm
replacing
some
best
individual(s)
using
dynamic
fitness
distance
balancing
strategy.
On
one
hand,
enhances
global
ability
improves
quality
establishing
probabilistic
model
based
on
dominant
individuals
provided
which
solves
problem
that
unable
to
search
neighborhood
optimal
solution.
other
strategy
increases
speed
balances
through
adaptive
mechanism.
Finally,
conducts
experiments
EDECO
29
CEC
2017
benchmark
functions
compares
four
algorithms
as
well
advanced
improved
algorithms.
results
show
indeed
achieves
significant
improvements
compared
algorithms,
performs
noticeably
better
than
competitors.
Next,
study
applies
10
engineering
problems,
experimental
superiority
solving
real
problems.
These
findings
further
support
effectiveness
usefulness
our
challenges.
Processes,
Год журнала:
2025,
Номер
13(3), С. 787 - 787
Опубликована: Март 8, 2025
This
study
introduces
an
Enhanced
Local
Search
(ELS)
technique
integrated
into
the
Bee
Colony
Optimization
(BCO)
algorithm
to
address
Economic
Dispatch
(ED)
problem
characterized
by
a
continuous
cost
function.
paper
combines
Lambda
Iteration
and
Golden
Section
with
more
efficient
method
called
for
(ELS-BCO).
The
proposed
methodology
seeks
enhance
search
efficiency
solution
quality.
One
of
main
challenges
standard
BCO
is
random
initialization,
which
can
lead
slow
convergence.
ELS-BCO
overcomes
this
issue
using
better
initial
estimation
refine
movement
direction
bees.
These
enhancements
significantly
improve
algorithm’s
capacity
identify
optimal
solutions.
performance
was
evaluated
on
two
benchmark
systems
three
six
power
generators,
results
were
compared
those
original
BCO,
LI-BCO,
GS-BCO,
traditional
optimization
methods
such
as
Particle
Swarm
(PSO),
Hybrid
PSO,
Simulated
Annealing,
Sine
Cosine
Algorithm,
Mountaineering
Team-Based
Optimization,
Teaching–Learning-Based
Optimization.
demonstrate
that
achieves
faster
convergence
higher-quality
solutions
than
these
existing
methods.
Biomimetics,
Год журнала:
2025,
Номер
10(3), С. 176 - 176
Опубликована: Март 12, 2025
The
Educational
Competition
Optimizer
(ECO)
is
a
newly
proposed
human-based
metaheuristic
algorithm.
It
derives
from
the
phenomenon
of
educational
competition
in
society
with
good
performance.
However,
basic
ECO
constrained
by
its
limited
exploitation
and
exploration
abilities
when
tackling
complex
optimization
problems
exhibits
drawbacks
premature
convergence
diminished
population
diversity.
To
this
end,
paper
proposes
an
enhanced
optimizer,
named
EDECO,
incorporating
estimation
distribution
algorithm
replacing
some
best
individual(s)
using
dynamic
fitness
distance
balancing
strategy.
On
one
hand,
enhances
global
ability
improves
quality
establishing
probabilistic
model
based
on
dominant
individuals
provided
which
solves
problem
that
unable
to
search
neighborhood
optimal
solution.
other
strategy
increases
speed
balances
through
adaptive
mechanism.
Finally,
conducts
experiments
EDECO
29
CEC
2017
benchmark
functions
compares
four
algorithms
as
well
advanced
improved
algorithms.
results
show
indeed
achieves
significant
improvements
compared
algorithms,
performs
noticeably
better
than
competitors.
Next,
study
applies
10
engineering
problems,
experimental
superiority
solving
real
problems.
These
findings
further
support
effectiveness
usefulness
our
challenges.
