Short-Term Prediction of Rural Photovoltaic Power Generation Based on Improved Dung Beetle Optimization Algorithm
Jie Meng,
No information about this author
Qing Yuan,
No information about this author
Weiqi Zhang
No information about this author
et al.
Sustainability,
Journal Year:
2024,
Volume and Issue:
16(13), P. 5467 - 5467
Published: June 27, 2024
Addressing
the
challenges
of
randomness,
volatility,
and
low
prediction
accuracy
in
rural
low-carbon
photovoltaic
(PV)
power
generation,
along
with
its
unique
characteristics,
is
crucial
for
sustainable
development
energy.
This
paper
presents
a
forecasting
model
that
combines
variational
mode
decomposition
(VMD)
an
improved
dung
beetle
optimization
algorithm
(IDBO)
kernel
extreme
learning
machine
(KELM).
Initially,
Gaussian
mixture
(GMM)
used
to
categorize
PV
data,
separating
analogous
samples
during
different
weather
conditions.
Afterwards,
VMD
applied
stabilize
initial
sequence
extract
numerous
consistent
subsequences.
These
subsequences
are
then
employed
develop
individual
KELM
models,
their
nuclear
regularization
parameters
optimized
by
IDBO.
Finally,
predictions
from
various
aggregated
produce
overall
forecast.
Empirical
evidence
via
case
study
indicates
proposed
VMD-IDBO-KELM
achieves
commendable
across
diverse
conditions,
surpassing
existing
models
affirming
efficacy
superiority.
Compared
traditional
VMD-DBO-KELM
algorithms,
mean
absolute
percentage
error
on
sunny
days,
cloudy
days
rainy
reduced
2.66%,
1.98%
6.46%,
respectively.
Language: Английский
Short-Term Power Load Forecasting Based on CEEMDAN-WT-VMD Joint Denoising and BiTCN-BiGRU-Attention
Electronics,
Journal Year:
2025,
Volume and Issue:
14(9), P. 1871 - 1871
Published: May 4, 2025
Short-term
power
load
forecasting
is
crucial
for
safe
grid
operation.
To
address
the
insufficiency
of
traditional
decomposition
methods
in
suppressing
high-frequency
noise
within
multi-source
noisy
time
series,
this
study
proposes
a
hybrid
model
integrating
CEEMDAN-WT-VMD
joint
denoising
with
BiTCN-BiGRU-Attention
architecture.
The
methodology
comprises
three
stages:
(1)
CEEMDAN
raw
data
to
mitigate
mode
mixing
and
extract
stationary
IMF
components;
(2)
wavelet
threshold
filter
interference
while
preserving
reconstructing
low-frequency
signals;
(3)
secondary
feature
using
Variational
Mode
Decomposition
(VMD)
enhance
stability.
A
architecture
combines
Bidirectional
Temporal
Convolutional
Network
(BiTCN)
long-term
dependency
capture,
Gated
Recurrent
Unit
(BiGRU)
dynamic
extraction,
an
attention
mechanism
key
pattern
emphasis.
final
value
generated
by
progressively
accumulating
predictions
decomposed
components.
Empirical
analysis
based
on
from
region
Australia
demonstrates
that,
through
horizontal
vertical
comparative
experiments,
proposed
method
significant
improvements
both
accuracy
stability
compared
other
frontier
models.
Language: Английский
Enhancing Short-Term Load Forecasting Accuracy in High-Volatility Regions Using LSTM-SCN Hybrid Models
Applied Sciences,
Journal Year:
2024,
Volume and Issue:
14(24), P. 11606 - 11606
Published: Dec. 12, 2024
Short-Term
Load
Forecasting
(STLF)
is
essential
for
the
efficient
management
of
power
systems,
as
it
improves
forecasting
accuracy
while
optimizing
scheduling
efficiency.
Despite
significant
recent
advancements
in
STLF
models,
high-volatility
regions
remains
a
key
challenge.
To
address
this
issue,
paper
introduces
hybrid
load
model
that
integrates
Long
Memory
Network
(LSTM)
with
Stochastic
Configuration
(SCN).
We
first
verify
Universal
Approximation
Property
SCN
through
experiments
on
two
regression
datasets.
Subsequently,
we
reconstruct
features
and
input
them
into
LSTM
feature
extraction.
These
extracted
vectors
are
then
used
inputs
SCN-based
STLF.
Finally,
evaluate
performance
LSTM-SCN
against
other
baseline
models
using
Australian
Electricity
dataset.
also
select
five
test
set
to
validate
model’s
advantages
such
scenarios.
The
results
show
achieved
an
RMSE
56.970,
MAE
43.033,
MAPE
0.492%
set.
Compared
next
best
model,
reduced
errors
by
6.016,
8.846,
0.053%
RMSE,
MAE,
MAPE,
respectively.
Additionally,
consistently
outperformed
across
all
analyzed.
findings
highlight
its
contribution
improved
system
management,
particularly
challenging
Language: Английский