Journal of Solar Energy Research Updates,
Journal Year:
2024,
Volume and Issue:
11, P. 103 - 113
Published: Dec. 31, 2024
This
study
presents
the
recent
trends
in
transition
from
fossil
fuels
towards
renewable
energy
for
combating
climate
change
and
achieving
a
net-zero
target
by
2030
as
per
United
Nations
Sustainable
Development
Goal-7
(Energy
All).
However,
Net
Zero
is
difficult
to
achieve
unless
effective
conservation
efficiency
policies,
regulations,
financial
investment,
are
not
initiated
along
with
major
energy.
Therefore,
study's
objective
present
current
status
of
initiatives
different
countries
including
India
address
this
problem
recommendations
various
Conference
Parties
COP-29.
The
case
shows
that
enhanced
efficiency,
conservation,
solar
regulations
high
energy-consuming
sectors
like
industry,
agriculture,
buildings,
domestic
awareness
among
society
important
realistic
targets.
Chhattisgarh
State
identifies
sectors,
leading
2.7
million
kWh
reduction
consumption
past
two
decades
through
initiatives.
These
measures
an
efficient
Net-Zero
way.
results
importance
follow-up
action
developing
least-developed
worldwide.
Advanced Theory and Simulations,
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 8, 2025
Abstract
Photovoltaic
(PV)
power
generation
is
vital
for
sustainable
energy
development,
yet
its
inherent
randomness
and
volatility
challenge
grid
stability.
Accurate
short‐term
PV
prediction
essential
reliable
operation.
This
paper
proposes
an
integrated
method
combining
dynamic
similar
selection
(DSS),
variational
mode
decomposition
(VMD),
bidirectional
gated
recurrent
unit
(BiGRU),
improved
sparrow
search
algorithm
(ISSA).
First,
DSS
selects
training
data
based
on
local
meteorological
similarity,
reducing
interference.
VMD
then
decomposes
into
smooth
components,
mitigating
volatility.
The
Pearson
correlation
coefficient
used
to
filter
highly
relevant
variables,
enhancing
input
quality.
BiGRU
captures
temporal
evolution
patterns,
with
ISSA
optimizing
key
parameters
robust
forecasting.
Validated
historical
Australian
under
diverse
weather
conditions,
the
proposed
effectively
reduces
volatility,
significantly
improving
accuracy
reliability.
These
advancements
support
stable
supply
efficient
Energies,
Journal Year:
2024,
Volume and Issue:
17(13), P. 3078 - 3078
Published: June 21, 2024
This
work
identifies
the
most
effective
machine
learning
techniques
and
supervised
models
to
estimate
power
output
from
photovoltaic
(PV)
plants
precisely.
The
performance
of
various
regression
is
analyzed
by
harnessing
experimental
data,
including
Random
Forest
regressor,
Support
Vector
(SVR),
Multi-layer
Perceptron
regressor
(MLP),
Linear
(LR),
Gradient
Boosting,
k-Nearest
Neighbors
(KNN),
Ridge
(Rr),
Lasso
(Lsr),
Polynomial
(Plr)
XGBoost
(XGB).
methodology
applied
starts
with
meticulous
data
preprocessing
steps
ensure
dataset
integrity.
Following
phase,
which
entails
eliminating
missing
values
outliers
using
Isolation
Feature
selection
based
on
a
correlation
threshold
performed
identify
relevant
parameters
for
accurate
prediction
in
PV
systems.
Subsequently,
employed
outlier
detection,
followed
model
training
evaluation
key
metrics
such
as
Root-Mean-Squared
Error
(RMSE),
Normalized
(NRMSE),
Mean
Absolute
(MAE),
R-squared
(R2),
Integral
(IAE),
Standard
Deviation
Difference
(SDD).
Among
evaluated,
emerges
top
performer,
highlighting
promising
results
an
RMSE
19.413,
NRMSE
0.048%,
R2
score
0.968.
Furthermore,
(the
best-performing
model)
integrated
into
MATLAB
application
real-time
predictions,
enhancing
its
usability
accessibility
wide
range
applications
renewable
energy.
