Frontiers in Neurorobotics,
Год журнала:
2022,
Номер
16
Опубликована: Авг. 24, 2022
Aiming
at
the
problems
of
slow
convergence
and
easy
fall
into
local
optimal
solution
classic
ant
colony
algorithm
in
path
planning,
an
improved
is
proposed.
Firstly,
Floyd
introduced
to
generate
guiding
path,
increase
pheromone
content
on
path.
Through
difference
initial
pheromone,
guided
quickly
find
target
node.
Secondly,
fallback
strategy
applied
reduce
number
ants
who
die
due
falling
trap
probability
finding
Thirdly,
gravity
concept
artificial
potential
field
method
distance
from
optional
node
are
improve
heuristic
function
make
up
for
speed
algorithm.
Fourthly,
a
multi-objective
optimization
proposed,
which
comprehensively
considers
three
indexes
length,
security,
energy
consumption
combines
dynamic
idea
optimize
update
method,
avoid
comprehensive
quality
Finally,
according
connectivity
principle
quadratic
B-spline
curve
nodes
optimized
shorten
length
effectively.
IEEE Access,
Год журнала:
2024,
Номер
12, С. 60058 - 60069
Опубликована: Янв. 1, 2024
Accurate
wind
power
prediction
helps
to
stabilize
the
operation
of
system,
improve
utilization
rate
renewable
energy,
reduce
dependence
on
traditional
and
achieve
sustainable
energy
development.
An
ultra
short-term
method
integrating
EMD-EncoderForest-TCN
is
proposed
address
difficulty
predicting
due
frequent
changes
in
speed.
Firstly,
time-series
input
data
model
decomposed
into
high-frequency
low-frequency
components
using
Empirical
Mode
Decomposition.
Then,
based
EncoderForest
TCN
model,
differential
information
extraction
performed
components.
The
regularizes
captures
trend
patterns
data.
models
time
series
capture
complex
structures
power.
Finally,
convolutional
neural
networks,
output
results
each
part
are
calculated
accurate
Based
operational
an
actual
farm,
conduct
a
case
study
analysis.
show
that
can
power,
with
accuracy
improvement
2.57%.
Frontiers in Neurorobotics,
Год журнала:
2022,
Номер
16
Опубликована: Авг. 24, 2022
Aiming
at
the
problems
of
slow
convergence
and
easy
fall
into
local
optimal
solution
classic
ant
colony
algorithm
in
path
planning,
an
improved
is
proposed.
Firstly,
Floyd
introduced
to
generate
guiding
path,
increase
pheromone
content
on
path.
Through
difference
initial
pheromone,
guided
quickly
find
target
node.
Secondly,
fallback
strategy
applied
reduce
number
ants
who
die
due
falling
trap
probability
finding
Thirdly,
gravity
concept
artificial
potential
field
method
distance
from
optional
node
are
improve
heuristic
function
make
up
for
speed
algorithm.
Fourthly,
a
multi-objective
optimization
proposed,
which
comprehensively
considers
three
indexes
length,
security,
energy
consumption
combines
dynamic
idea
optimize
update
method,
avoid
comprehensive
quality
Finally,
according
connectivity
principle
quadratic
B-spline
curve
nodes
optimized
shorten
length
effectively.
