Advances in Meteorology,
Journal Year:
2024,
Volume and Issue:
2024(1)
Published: Jan. 1, 2024
Solar
radiation
prediction
research
is
a
key
area
of
interest
in
the
realm
solar
energy
utilization
and
has
garnered
significant
attention
recent
times.
In
order
to
realize
accurate
make
better
serve
photovoltaic
(PV)
power
generation,
this
study
proposes
method
based
on
sequence
model,
which
integrates
two
kinds
neural
networks,
namely,
temporal
convolutional
network
(TCN)
basis
expansion
analysis
(N‐BEATS).
First,
dataset
preprocessed
using
Pearson’s
correlation
coefficient,
outlier
detection,
normalized
obtain
valid
relevant
data;
second,
features
TCN
feature
extraction
N‐BEATS
flexible
extension
are
integrated
predict
radiation;
then,
model’s
hyperparameters
fine‐tuned
grid
search
algorithm
ensure
precise
predictions;
last,
correctness
verified
by
comparing
error
metrics
running
time.
Empirical
findings
indicate
that
TCN‐N‐BEATS
model
high
accuracy
short
time
overhead,
it
certain
application
value
prediction,
could
offer
valuable
insights
for
predicting
radiation.
Atmosphere,
Journal Year:
2025,
Volume and Issue:
16(4), P. 398 - 398
Published: March 30, 2025
Solar
radiation
is
one
of
the
most
abundant
energy
sources
in
world
and
a
crucial
parameter
that
must
be
researched
developed
for
sustainable
projects
future
generations.
This
study
evaluates
performance
different
machine
learning
methods
solar
prediction
Konya,
Turkey,
region
with
high
potential.
The
analysis
based
on
hydro-meteorological
data
collected
from
NASA/POWER,
covering
period
1
January
1984
to
31
December
2022.
compares
Long
Short-Term
Memory
(LSTM),
Bidirectional
LSTM
(Bi-LSTM),
Gated
Recurrent
Unit
(GRU),
GRU
(Bi-GRU),
LSBoost,
XGBoost,
Bagging,
Random
Forest
(RF),
General
Regression
Neural
Network
(GRNN),
Support
Vector
Machines
(SVM),
Artificial
Networks
(MLANN,
RBANN).
variables
used
include
temperature,
relative
humidity,
precipitation,
wind
speed,
while
target
variable
radiation.
dataset
was
divided
into
75%
training
25%
testing.
Performance
evaluations
were
conducted
using
Mean
Absolute
Error
(MAE),
Root
Square
(RMSE),
coefficient
determination
(R2).
results
indicate
Bi-LSTM
models
performed
best
test
phase,
demonstrating
superiority
deep
learning-based
approaches
prediction.
Energies,
Journal Year:
2024,
Volume and Issue:
17(14), P. 3435 - 3435
Published: July 12, 2024
Due
to
the
inherent
intermittency,
variability,
and
randomness,
photovoltaic
(PV)
power
generation
faces
significant
challenges
in
energy
grid
integration.
To
address
these
challenges,
current
research
mainly
focuses
on
developing
more
efficient
management
systems
prediction
technologies.
Through
optimizing
scheduling
integration
PV
generation,
stability
reliability
of
can
be
further
improved.
In
this
study,
a
new
model
is
introduced
that
combines
strengths
convolutional
neural
networks
(CNNs),
long
short-term
memory
(LSTM)
networks,
attention
mechanisms,
so
we
call
algorithm
CNN-LSTM-Attention
(CLA).
addition,
Crested
Porcupine
Optimizer
(CPO)
utilized
solve
problem
generation.
This
abbreviated
as
CPO-CLA.
first
time
CPO
has
been
into
LSTM
for
parameter
optimization.
effectively
capture
univariate
multivariate
series
patterns,
multiple
relevant
target
variables
patterns
(MRTPPs)
are
employed
CPO-CLA
model.
The
results
show
superior
traditional
methods
recent
popular
models
terms
accuracy
stability,
especially
13
h
timestep.
mechanisms
enables
adaptively
focus
most
historical
data
future
prediction.
optimizes
network
parameters,
which
ensures
robust
generalization
ability
great
significance
establishing
trust
market.
Ultimately,
it
will
help
integrate
renewable
reliably
efficiently.
