E3S Web of Conferences,
Год журнала:
2024,
Номер
591, С. 05002 - 05002
Опубликована: Янв. 1, 2024
The
rapid
expansion
of
hybrid
renewable
energy
microgrid
systems
presents
new
challenges
in
maintaining
system
reliability
and
performance.
This
paper
explores
the
application
machine
learning
algorithms
for
predictive
maintenance
such
systems,
focusing
on
early
detection
potential
failures
to
optimize
operational
efficiency
reduce
downtime.
By
integrating
real-time
data
from
solar,
wind,
storage
components,
proposed
models
predict
remaining
useful
life
(RUL)
critical
components.
results
demonstrate
significant
improvements
accuracy,
offering
a
robust
solution
enhancing
longevity
microgrids.
Results in Engineering,
Год журнала:
2024,
Номер
23, С. 102445 - 102445
Опубликована: Июнь 18, 2024
In
the
electronic
era,
demand
for
efficient
storage
systems
has
rapidly
increased,
making
health
and
durability
of
batteries
crucial.
This
research
investigates
performance
distinct
Machine
Learning
(ML)
techniques—namely,
Logistic
Regression
(LR),
Convolutional
Neural
Network
(CNN),
CNN
tuning
using
Particle
Swarm
Optimization
(PSO)—for
Battery
Health
Analysis
(BHA).
The
dataset
comprises
various
parameters
related
to
battery
health,
with
Remaining
Useful
Time
(RUL)
as
target
variable.
proposed
work
is
evaluated
Root
Mean
Squared
Error
(RMSE),
Absolute
(MAE),
R-squared
(R2)
scores.
Initially,
basic
LR
Model
employed
BHA,
followed
by
capture
complex
data
patterns.
Subsequently,
Model's
optimized
PSO
algorithm,
aiming
improved
performance.
Experimental
results
demonstrate
that
significantly
outperforms
approach
in
terms
accuracy,
lower
RMSE
MAE,
higher
R2
conventional
model
outperformed
approach,
resulting
a
20.11,
MAE
15.26,
score
0.996;
whereas,
PSO-Optimized-CNN
further
enhanced
metrics
14.97,
8.03
0.998.
Henceforth,
PSO-optimized
exhibits
compared
standalone
Model.
findings
offer
valuable
insights
into
ML
approaches
BHA
suggest
methods
optimizing
management
applications,
including
renewable
energy
systems,
electric
vehicles,
portable
electronics.
Results in Engineering,
Год журнала:
2024,
Номер
23, С. 102661 - 102661
Опубликована: Авг. 5, 2024
The
occurrence
of
cascading
failures
poses
significant
risks
to
the
stability
and
reliability
modern
smart
grids.
This
article
presents
a
novel
hybrid
algorithm
designed
assess
mitigate
these
failures.
technique
combines
advanced
clustering
algorithms,
specifically
Affinity
Propagation
Graph
(APG)
Self-Propagating
(SPG),
detect
critical
nodes,
Unified
Power
Flow
Controllers
(UPFCs)
provide
compensation
grid
networks.
first
uses
APG
divide
network
into
clusters
considers
center
bus
as
node.
If
is
not
critical,
SPG
applied
identify
approach
identifies
node
in
just
0.02
s
(for
both
SPG)
with
improved
accuracy
compared
existing
methods.
After
identifying
UPFCs
are
strategically
installed
regulate
power
flow
reduce
probability
failures,
taking
approximately
0.14
s.
Simulation
results
demonstrate
effectiveness
proposed
method
enhancing
resilience
reducing
likelihood
By
deploying
at
this
ensures
resilient
operation
various
scenarios.
research
significantly
contributes
development
technologies
by
providing
comprehensive
framework
address
distribution
shows
potential
for
improving
grids
amid
changing
system
dynamics
uncertainties.
E3S Web of Conferences,
Год журнала:
2024,
Номер
591, С. 05002 - 05002
Опубликована: Янв. 1, 2024
The
rapid
expansion
of
hybrid
renewable
energy
microgrid
systems
presents
new
challenges
in
maintaining
system
reliability
and
performance.
This
paper
explores
the
application
machine
learning
algorithms
for
predictive
maintenance
such
systems,
focusing
on
early
detection
potential
failures
to
optimize
operational
efficiency
reduce
downtime.
By
integrating
real-time
data
from
solar,
wind,
storage
components,
proposed
models
predict
remaining
useful
life
(RUL)
critical
components.
results
demonstrate
significant
improvements
accuracy,
offering
a
robust
solution
enhancing
longevity
microgrids.
