Frontiers in Energy Research,
Journal Year:
2024,
Volume and Issue:
12
Published: Oct. 18, 2024
The
widespread
adoption
of
nonlinear
power
electronic
devices
in
residential
settings
has
significantly
increased
the
stochasticity
and
uncertainty
systems.
original
load
data,
characterized
by
numerous
irregular,
random,
probabilistic
components,
adversely
impacts
predictive
performance
deep
learning
techniques,
particularly
neural
networks.
To
address
this
challenge,
paper
proposes
a
time-series
prediction
technique
based
on
mature
network
point
technique,
i.e.,
decomposing
data
into
deterministic
stochastic
components.
component
is
predicted
using
technology,
fitted
with
Gaussian
mixture
distribution
model
parameters
are
great
expectation
algorithm,
after
which
obtained
generation
method.
Using
study
evaluates
six
different
methods
to
forecast
power.
By
comparing
errors
these
methods,
optimal
identified,
leading
substantial
improvement
accuracy.
Protection and Control of Modern Power Systems,
Journal Year:
2024,
Volume and Issue:
9(6), P. 1 - 18
Published: Nov. 1, 2024
Supercapacitors
(SCs)
are
widely
recognized
as
excellent
clean
energy
storage
devices.
Accurate
state
of
health
(SOH)
estimation
and
remaining
useful
life
(RUL)
prediction
essential
for
ensuring
their
safe
reliable
operation.
This
paper
introduces
a
novel
method
SOH
RUL
prediction,
based
on
hybrid
neural
network
optimized
by
an
improved
honey
badger
algorithm
(HBA).
The
combines
the
advantages
convolutional
(CNN)
bidirectional
long-short-term
memory
(BiLSTM)
network.
HBA
optimizes
hyperparameters
CNN
automatically
extracts
deep
features
from
time
series
data
reduces
dimensionality,
which
then
used
input
BiLSTM.
Additionally,
recurrent
dropout
is
introduced
in
layer
to
reduce
overfitting
facilitate
learning
process.
approach
not
only
improves
accuracy
estimates
forecasts
but
also
significantly
processing
time.
SCs
under
different
working
conditions
validate
proposed
method.
results
show
that
model
effectively
features,
enriches
local
details,
enhances
global
perception
capabilities.
outperforms
single
models,
reducing
root
mean
square
error
below
1%,
offers
higher
robustness
compared
other
methods.
Frontiers in Energy Research,
Journal Year:
2024,
Volume and Issue:
12
Published: Sept. 23, 2024
The
increasing
penetration
of
distributed
photovoltaic
(PV)
brings
challenges
to
the
safe
and
reliable
operation
distribution
networks,
PV
access
grid
changes
characteristics
traditional
grid.
Therefore,
assessment
carrying
capacity
is
great
significance
for
network
planning.
To
this
end,
a
differentiated
scenario-based
method
based
on
combination
Convolutional
Neural
Networks
(CNN)
Gated
Recurrent
Unit
(GRU)
proposed.
Firstly,
meteorological
affecting
power
are
quantitatively
analyzed
using
Pearson’s
correlation
coefficient,
influence
external
factors
assessed
by
integrating
measured
data.
Then,
problem
high
blindness
clustering
parameters
initial
centers
in
K-means
algorithm,
optimal
number
clusters
determined
combining
cluster
Density
Based
Index
(DBI)
hierarchical
clustering.
improved
reduces
complexity
massive
scenarios
obtain
under
scenarios.
On
basis,
prediction
CNN-GRU
model
proposed,
which
employs
CNN
feature
extraction
high-dimensional
data,
then
temporal
data
optimally
trained
GRU
model.
results,
solution
efficiency
effectively
accurate
realized.
Finally,
taking
into
account
demand
network,
combined
with
flow
calculation
bearing
considering
node
voltage
evaluated.
In
addition,
verified
source-grid-load
IEEE
33-bus
system.
simulation
results
show
that
proposed
fusion
deep
learning
can
accurately
efficiently
assess
provide
theoretical
guidance
realizing
large
scale.
Frontiers in Energy Research,
Journal Year:
2024,
Volume and Issue:
12
Published: Nov. 18, 2024
In
the
current
distribution
network’s
energy
structure,
photovoltaic
(PV)
occupies
a
high
proportion.
However,
access
of
proportion
PV
will
lead
to
phenomenon
reverse
power
flow
in
network,
and
then
problem
line
overvoltage.
When
increases,
overvoltage
also
worsens,
which
endangers
normal
operation
system.
To
solve
this
problem,
paper
starts
with
voltage
rise
theory
network
lines.
Firstly,
through
strict
mathematical
derivation,
it
compares
influence
main
parameters
on
rise,
summarizes
simple
calculation
equation
for
PV.
Then,
according
mechanism
principle
inverter
control,
considering
economy
practicability
suppression
strategy,
strategy
system
is
proposed.
Finally,
model
simulating
small
village
used
verify
effectiveness
proposed
strategy.
Frontiers in Energy Research,
Journal Year:
2024,
Volume and Issue:
12
Published: Nov. 27, 2024
As
the
proportion
of
renewable
energy
generation
continues
to
rise,
study
voltage
source
converter
(VSC)
control
has
become
a
focal
point
research.
The
concepts
emulating
characteristics
synchronous
machines
have
led
proposals
droop
and
virtual
(VSG).
However,
deeper
comparison
these
two
methods
is
still
needed,
particularly
in
terms
their
ability
support
system
when
partial
power
sources
experience
fault
conditions.
This
paper
analyzes
compares
principles
small-signal
modeling,
finally,
based
on
nine-bus
with
100%
generation,
scenarios
are
designed:
sudden
load
increase
disconnection.
differences
between
compared
analyzed.
results
indicate
that
VSG
exhibits
greater
damping
capable
providing
inertial
system,
making
its
frequency
less
susceptible
change.
