Energy Informatics,
Journal Year:
2024,
Volume and Issue:
7(1)
Published: Nov. 15, 2024
With
the
rapid
development
of
renewable
energy,
microgrid
cluster
systems
are
gradually
being
applied.
To
promote
scheduling
technology,
maximize
economic
benefits
while
reducing
operating
cost
required
for
scheduling,
an
optimized
scheme
is
proposed
by
constructing
a
function
to
minimize
microgrids.
Then,
chaos
mutation
and
Gaussian
applied
improve
moth-flame
algorithm
that
easily
falling
into
local
optima.
A
optimization
model
on
basis
improved
constructed.
The
experimental
results
showed
in
islanding
mode
was
4286.21
yuan
after
160
iterations.
After
optimizing
3912.3
yuan,
with
decrease
8.7%.
had
stable
average
loss
value
20%
efficiency
97.19%
10–50
iterations,
which
significantly
higher
than
other
intelligent
algorithms.
This
indicates
has
high
reliability
effectiveness
scheduling.
Therefore,
effectively
optimizes
cluster,
providing
new
solutions
efficient
utilization
smart
grids
energy
future.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: March 23, 2025
This
paper
investigates
the
economic
energy
management
of
a
wireless
electric
vehicle
charging
stations
(EVCS)
connected
to
hybrid
renewable
system
comprising
photovoltaic
(PV),
wind,
battery
storage,
and
main
grid.
The
study
adopts
an
Improved
Harris
Hawk
Optimization
(IHHO)
algorithm
optimize
minimize
operational
costs
under
varying
scenarios.
Three
distinct
EV
load
profiles
are
considered
evaluate
performance
proposed
optimization
technique.
Simulation
results
demonstrate
that
IHHO
achieves
significant
cost
reductions
improves
utilization
efficiency
compared
other
state-of-the-art
algorithms
such
as
Quantum
Particle
Swarm
(IQPSO),
Honeybee
Mating
(HBMO),
Enhanced
Exploratory
Whale
Algorithm
(EEWOA).
For
scenarios
with
energies,
reduced
electricity
by
up
36.41%,
achieving
per-unit
low
3.17
INR
for
most
demanding
profile.
Under
generation
disconnection,
maintained
its
superiority,
reducing
37.89%
unoptimized
dispatch
strategies.
integration
storage
further
enhanced
system's
resilience
cost-effectiveness,
particularly
during
periods
unavailability.
algorithm's
robust
performance,
reflected
in
ability
handle
dynamic
challenging
conditions,
demonstrates
potential
practical
deployment
real-world
EVCS
powered
systems.
findings
highlight
reliable
efficient
tool
optimizing
dispatch,
promoting
energy,
supporting
sustainable
infrastructure
development.
outperforms
all
benchmark
algorithms,
35.82%
Profile
3,
minimum
3.11
INR/kWh
across
Specifically,
achieved
lowest
6479.72
INR/day
1,
10,893.23
2,
20,821.63
consistently
outperforming
IQPSO,
HBMO,
EEWOA.
Chemical Product and Process Modeling,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 15, 2025
Abstract
Energy
is
vital
for
life
and
human
development,
with
global
warming
due
to
activities
such
as
the
combustion
of
fossil
fuels
deforestation
emitting
dangerous
greenhouse
gases,
changing
climate
Earth.
Global
energy
demand
increasing,
developed
nations
viewing
buildings
major
consumers.
Due
long
lifespan
buildings,
it
important
evaluate
their
suitability
future
change
possible
changes
in
consumption.
Appraisal
cooling
loads
each
building
now
required
rising
costs
need
reduce
impacts
caused
by
consumption
from
buildings.
This
paper
aims
apply
Random
Forest
Regression
(RF)
Support
Vector
(SVR),
well-known
machine
learning
algorithms
predict
loads.
It
utilizes
Jellyfish
Search
Optimizer
(JSO)
Transit
Optimization
Algorithm
(TSOA)
enhance
accuracy
minimize
overall
error
Cooling
Load
(CL)
estimation.
The
investigation
suggests
two
high-performance
schemes,
applies
optimizers
hybrid
an
ensemble
approach
accurate
appraisal
.
Moreover,
SHAP
method
utilized
compare
effectiveness
parameters.
research
proves
be
insightful
constructing
CL
projection
that
a
RFJS-based
model
most
effective
way
optimize
attained
R
2
0.994
at
its
best
RMSE
0.744.
Other
than
this,
following
was
RSJS,
whose
were
0.989
0.985,
accordingly.
third
best-performing
SVJS
values
0.972
1.583,
