Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Сен. 2, 2024
Due
to
changes
in
urban
residents'
consumption
habits
and
lifestyles,
accurately
predicting
natural
gas
has
become
increasingly
important.
To
address
this
issue,
paper
proposes
a
forecasting
model
that
combines
Ensemble
Learning
(EL),
Variational
Mode
Decomposition
(VMD),
Transformer,
LSTM.
First,
XGBoost,
CatBoost,
LightGBM
are
used
as
base
learners
the
ensemble
learning
framework,
with
predictions
generated
by
integrated
into
original
dataset.
Next,
VMD
method
is
employed
decompose
load
sequence
several
intrinsic
mode
functions
(IMFs),
effectively
extracting
inherent
features
of
sequence.
Finally,
data
input
Transformer-ResLSTM
network
for
prediction.
This
replaces
Transformer
decoder
structure
an
LSTM
fully
connected
layers,
creating
new
structure.
Additionally,
residual
connection
mechanism
introduced
both
encoder
Experimental
results
show
that,
compared
traditional
models
such
ARIMA,
GRU,
LSTM,
proposed
hybrid
significantly
improves
prediction
accuracy,
reducing
MSE
92–98%
MAE
74–83%.
In
summary,
demonstrates
significant
potential
practical
value
enhancing
accuracy
forecasting.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Окт. 9, 2024
Accurate
runoff
forecasting
is
of
great
significance
for
water
resource
allocation
flood
control
and
disaster
reduction.
However,
due
to
the
inherent
strong
randomness
sequences,
this
task
faces
significant
challenges.
To
address
challenge,
study
proposes
a
new
SMGformer
forecast
model.
The
model
integrates
Seasonal
Trend
decomposition
using
Loess
(STL),
Informer's
Encoder
layer,
Bidirectional
Gated
Recurrent
Unit
(BiGRU),
Multi-head
self-attention
(MHSA).
Firstly,
in
response
nonlinear
non-stationary
characteristics
sequence,
STL
used
extract
sequence's
trend,
period,
residual
terms,
multi-feature
set
based
on
'sequence-sequence'
constructed
as
input
model,
providing
foundation
subsequent
models
capture
evolution
runoff.
key
features
are
then
captured
layer.
Next,
BiGRU
layer
learn
temporal
information
these
features.
further
optimize
output
MHSA
mechanism
introduced
emphasize
impact
important
information.
Finally,
accurate
achieved
by
transforming
through
Fully
connected
verify
effectiveness
proposed
monthly
data
from
two
hydrological
stations
China
selected,
eight
compare
performance
results
show
that
compared
with
Informer
1th
step
MAE
decreases
42.2%
36.6%,
respectively;
RMSE
37.9%
43.6%
NSE
increases
0.936
0.975
0.487
0.837,
respectively.
In
addition,
KGE
at
3th
0.960
0.805,
both
which
can
maintain
above
0.8.
Therefore,
accurately
sequence
extend
effective
period
Sustainability,
Год журнала:
2024,
Номер
16(6), С. 2522 - 2522
Опубликована: Март 19, 2024
Accurately
predicting
the
cold
load
of
industrial
buildings
is
a
crucial
step
in
establishing
an
energy
consumption
management
system
for
constructions,
which
plays
significant
role
advancing
sustainable
development.
However,
due
to
diverse
influencing
factors
and
complex
nonlinear
patterns
exhibited
by
data
buildings,
these
loads
poses
challenges.
This
study
proposes
hybrid
prediction
approach
combining
Improved
Snake
Optimization
Algorithm
(ISOA),
Variational
Mode
Decomposition
(VMD),
random
forest
(RF),
BiLSTM-attention.
Initially,
ISOA
optimizes
parameters
VMD
method,
obtaining
best
decomposition
results
data.
Subsequently,
RF
employed
predict
components
with
higher
frequencies,
while
BiLSTM-attention
utilized
lower
frequencies.
The
final
are
obtained
predictions.
proposed
method
validated
using
actual
from
building,
experimental
demonstrate
its
excellent
predictive
performance,
making
it
more
suitable
constructions
compared
traditional
methods.
By
enhancing
accuracy
not
only
improves
efficiency
but
also
promotes
reduction
carbon
emissions,
thus
contributing
development
sector.
