Renewable Energies,
Journal Year:
2024,
Volume and Issue:
2(1)
Published: Jan. 1, 2024
This
article
describes
an
approach
applying
computational
intelligence
methods
for
the
problem
of
forecasting
solar
photovoltaic
power
generation
at
country
level.
Precise
forecast
plays
a
vital
role
in
designing
dependable
system.
The
computed
predictions
enable
implementation
efficient
planning,
management,
and
distribution
strategies
generated
power,
ultimately
enhancing
performance
efficiency
study
analyzes
compares
artificial
neural
network
approaches
specific
case
using
real
data
from
Uruguay
period
2018
to
2022.
Several
architectures
are
evaluated
forecasting.
main
results
indicate
that
combination
Encoder-Decoder
Long
Short
Term
Memory
networks
is
most
effective
method
addressed
problem.
yielded
promising
results,
with
average
mean
error
value
0.09,
improving
over
other
architectures.
Even
better
were
obtained
sunny
days.
forecasts
hold
significant
its
application
planning
scheduling
processes,
aiming
enhance
overall
quality
service
electricity
grid.
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 23504 - 23513
Published: Jan. 1, 2024
Load
forecasting
in
Smart
Grids
(SG)
is
a
major
module
of
current
energy
management
systems,
that
play
vital
role
optimizing
resource
allocation,
improving
grid
stability,
and
assisting
the
combination
renewable
sources
(RES).
It
contains
predictive
electricity
consumption
forms
over
certain
time
intervals.
Forecasting
remains
stimulating
task
as
load
data
has
exhibited
changing
patterns
because
factors
such
weather
change
shifts
usage
behaviour.
The
beginning
advanced
analytics
machine
learning
(ML)
approaches;
particularly
deep
(DL)
mostly
enhanced
accuracy.
Deep
neural
networks
(DNNs)
namely
Long
Short-Term
Memory
(LSTM)
Convolutional
Neural
Networks
(CNN)
have
achieved
popularity
for
their
capability
to
capture
difficult
temporal
dependencies
data.
This
study
designs
Short-Load
scheme
using
Hybrid
Learning
Beluga
Whale
Optimization
(LFS-HDLBWO)
approach.
intention
LFS-HDLBWO
technique
predict
SG
environment.
To
accomplish
this,
initially
uses
Z-score
normalization
approach
scaling
input
dataset.
Besides,
makes
use
convolutional
bidirectional
long
short-term
memory
with
an
autoencoder
(CBLSTM-AE)
model
prediction
purposes.
Finally,
BWO
algorithm
could
be
used
optimal
hyperparameter
selection
CBLSTM-AE
algorithm,
which
helps
enhance
overall
results.
A
wide-ranging
experimental
analysis
was
made
illustrate
better
results
method.
obtained
value
demonstrates
outstanding
performance
system
other
existing
DL
algorithms
minimum
average
error
rate
3.43
2.26
under
FE
Dayton
datasets,
respectively.
Energy Reports,
Journal Year:
2024,
Volume and Issue:
11, P. 5504 - 5531
Published: May 22, 2024
Electricity
consumption
is
increasing
rapidly,
and
the
limited
availability
of
natural
resources
necessitates
efficient
energy
usage.
Predicting
managing
electricity
costs
challenging,
leading
to
delays
in
pricing.
Smart
appliances
Internet
Things
(IoT)
networks
offer
a
solution
by
enabling
monitoring
control
from
broadcaster
side.
Green
IoT,
also
known
as
Things,
emerges
sustainable
approach
for
communication,
data
management,
device
utilization.
It
leverages
technologies
such
Wireless
Sensor
Networks
(WSN),
Cloud
Computing
(CC),
Machine-to-Machine
(M2M)
Communication,
Data
Centres
(DC),
advanced
metering
infrastructure
reduce
promote
environmentally
friendly
practices
design,
manufacturing,
IoT
optimizes
processing
through
enhanced
signal
bandwidth,
faster
more
communication.
This
comprehensive
review
explores
advancements
smart
grids,
paving
path
sustainability.
covers
energy-efficient
communication
protocols,
intelligent
renewable
integration,
demand
response,
predictive
analytics,
real-time
monitoring.
The
importance
edge
computing
fog
allowing
distributed
intelligence
emphasized.
addresses
challenges,
opportunities
presents
successful
case
studies.
Finally,
concludes
outlining
future
research
avenues
providing
policy
recommendations
foster
advancement
IoT.
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 23319 - 23337
Published: Jan. 1, 2024
Electric
vehicles
(EVs)
have
become
a
prominent
alternative
to
fossil
fuel
in
the
modern
transportation
industry
due
their
competitive
benefits
of
carbon
neutrality
and
environment
friendliness.
The
tremendous
adoption
EVs
leads
significant
increase
demand
for
charging
infrastructure.
But,
scarcity
stations
(CSs)
concerns
efficient
reliable
EV
charging.
Existing
studies
discussed
energy
consumption
prediction
schemes
at
CS
without
analyzing
affecting
parameters
such
as
demand,
weather,
day,
etc.
In
this
regard,
we
proposed
an
distribution
framework
smart
grid
after
location,
weekday,
weekend,
user.
Moreover,
considered
dataset
perform
detailed
deep
analysis
patterns
based
on
aforementioned
(Station
ID)
within
location
(Location
ID),
user
(UserID).
main
aim
is
understand
grid-based
electricity
by
We
done
different
present
graphical
representations.
This
article
presents
the
research
results
on
creating
prediction
models
using
historical
data
projected
power
usage
in
an
area
with
many
sectors.
Given
constantly
high
energy
intensity
of
any
critical
sector,
it
is
imperative
to
prioritize
optimization
use.
A
method
enhance
precision
managing
expenses
planning
phase
involves
anticipating
electrical
loads.
Although
there
a
wealth
scientific
study
consumption
prediction,
continues
be
significant
problem
because
evolving
demands
wholesale
electricity
and
market,
which
require
precise
forecasts
for
resilience.
aims
improve
managerial
decision-making
through
strategic
planning.
The
approach
constructing
prognostic
based
data,
including
consumption,
system
performance
metrics,
meteorological
data.
achieves
highly
accurate
short-term
predictions
ensemble
techniques
like
random
forest,
gradient
boosting
(XGBoost,
CatBoost),
intelligent
models.
Incorporating
neural
network
minimal
error
rates,
demonstrating
models'
suitability
predicting
integrated
consumption.
Sustainability,
Journal Year:
2025,
Volume and Issue:
17(2), P. 458 - 458
Published: Jan. 9, 2025
The
relationship
between
the
urbanization
process
and
ecological
environment
is
key
to
regional
development.
As
a
typical
Chinese
city
undergoing
rapid
urban
development,
Zhengzhou
an
important
representative
of
changes
in
environment.
In
this
study,
we
explored
response
development
Zhengzhou,
using
night
light
data,
Landsat
satellite
imagery,
population
data
from
city.
analysis
NTL
showed
that
there
were
three
stages
2000
2021:
slow
expansion
stage
2003,
steady
2004
2011,
2012
2021.
multi-year
average
RSEI
value
was
less
than
0.4,
it
trend
first
increasing
then
decreasing,
indicating
quality
city’s
poor
indirectly
degree
region
significant.
indicate
has
significantly
reduced
environment,
particularly
after
entered
expansion.
coupling
(C)
coordination
(D)
decreasing
trend,
lower
0.3.
This
indicates
been
seriously
affected
by
urbanization,
natural
ecology
strongly
impacted
human
activity.
C
D
also
2015
but
increased
2016
2021,
gradually
improved.
had
strong
negative
correlation
with
size
growth
rate
positive
Moran
value,
increase
increases
burden
on
However,
reasonable
spatial
distribution
conducive
improving
urban–ecological
coordination.
Electronics,
Journal Year:
2025,
Volume and Issue:
14(2), P. 249 - 249
Published: Jan. 9, 2025
To
enhance
the
utilization
efficiency
of
wind
and
solar
renewable
energy
in
industrial
parks,
reduce
operational
costs,
optimize
charging
experience
for
electric
vehicle
(EV)
users,
this
paper
proposes
a
real-time
scheduling
strategy
based
on
“Dual
Electricity
Price
Reservation—Surplus
Refund
Without
Additional
Charges
Mechanism”
(DPRSRWAC).
The
employs
Gaussian
Mixture
Model
(GMM)
to
analyze
EV
users’
discharging
behaviors
within
park,
constructing
behavior
prediction
model.
It
introduces
reservation,
penalty,
ticket-grabbing
mechanisms,
combined
with
Interval
Optimization
Method
(IOM)
Particle
Swarm
(PSO),
dynamically
solve
optimal
reservation
electricity
price
at
each
time
step,
thereby
guiding
user
effectively.
Furthermore,
linear
programming
(LP)
is
used
schedules
EVs,
incorporating
data
into
generation-side
behavior,
along
prices,
determined
using
Dynamic
Programming
(DP).
In
addition,
study
explicitly
considers
battery
aging
cost
associated
V2G
operations
benefit
model
owners
mode,
incentivizing
participation
enhancing
acceptance.
A
simulation
analysis
demonstrates
that
proposed
effectively
reduces
park
operation
costs
by
8.0%
33.1%,
respectively,
while
increasing
19.3%.
Key
performance
indicators
are
significantly
improved,
indicating
strategy’s
economic
viability
feasibility.
This
work
provides
an
effective
solution
management
smart
parks.
