This
research
paper
introduces
an
innovative
methodology
for
predicting
mutual
fund
prices
in
the
Indian
financial
market
by
utilizing
a
hybrid
ensemble
learning
technique
based
on
Stacking
Regressor
algorithm.
Conventional
forecasting
techniques
frequently
face
difficulties
capturing
intricate
non-linear
connections
and
interdependencies
found
within
data.
To
tackle
this
problem,
suggested
solution
is
introduction
of
framework
that
harnesses
collective
capabilities
multiple
base
learners
to
enhance
prediction
accuracy.
The
approach
consists
two
main
components:
meta-learner.
Experimental
evaluations
are
conducted
using
comprehensive
dataset
market.
proposed
compares
well
with
traditional
single-model
other
methods.
Ridge
used
as
meta-regressor
stacking-regressor
model.
results
demonstrate
stacking
regression-based
achieves
superior
predictive
performance
relation
precision,
resilience,
consistency.
successfully
varied
viewpoints
learners,
enhancing
overall
precision
predictions
compared
standalone
models.
outcomes
study
make
valuable
contribution
domain
price
forecasting,
emphasizing
potential
advantages
employing
methods
presents
promising
opportunity
investors
institutions
improve
their
decision-making
processes,
optimize
portfolio
management
strategies,
mitigate
risks
associated
investments.This
IET Generation Transmission & Distribution,
Год журнала:
2025,
Номер
19(1)
Опубликована: Янв. 1, 2025
ABSTRACT
VES
is
a
method
of
balancing
the
energy
power
system
with
other
equipment
or
scheduling
strategies,
particularly
respect
to
controllable
loads,
owing
end‐user
electrification.
This
paper
summarises
connotations,
classifications,
and
typical
modelling
applications
for
users.
Thereafter,
methods,
characteristics,
specific
operation
cases
five
types
VESs
are
introduced,
including
electric
vehicles,
buildings,
cold
storage,
industrial
production
hydrogen
storage.
Furthermore,
storage
capacity
planning,
strategy,
control
strategy
VESS
realised
through
optimal
strategies.
Finally,
in
conjunction
demand
response,
development
prospects
strategies
discussed
improve
economic
environmental
benefits
microgrids.
Energies,
Год журнала:
2024,
Номер
17(16), С. 4099 - 4099
Опубликована: Авг. 18, 2024
The
increasing
use
of
renewable
energy
sources
introduces
significant
fluctuations
in
power
generation,
demanding
enhanced
regulatory
capabilities
to
maintain
the
balance
between
supply
and
demand.
To
promote
multi-energy
coupling
local
consumption
energy,
integrated
systems
have
become
a
focal
point
multidisciplinary
research.
This
study
models
adjustable
sources,
networks,
loads
within
electric–thermal
as
storage
entities,
forming
virtual
participate
optimization
scheduling
systems.
paper
investigates
modeling
control
strategies
Initially,
it
definition,
logical
architecture,
technical
connotations
storage.
Next,
temperature-controlled
compares
them
with
traditional
systems,
analyzing
their
characteristic
differences
summarizing
system
methods
indicators.
then
focuses
on
specific
applications
four
typical
scenarios.
Finally,
explores
future
development
directions
Buildings,
Год журнала:
2024,
Номер
14(10), С. 3040 - 3040
Опубликована: Сен. 24, 2024
Building
envelopes
and
indoor
environments
exhibit
thermal
inertia,
forming
a
virtual
energy
storage
system
in
conjunction
with
the
building
air
conditioner
(AC)
system.
This
represents
current
demand
response
resource
for
electricity
use.
Thus,
this
study
centers
on
CatBoost
algorithm
within
machine
learning
(ML)
technology,
utilizing
LASSO
regression
model
feature
selection
applying
Optuna
framework
hyperparameter
optimization
(HPO)
to
develop
cost-optimal
control
method
minimizing
AC
loads.
addresses
challenges
associated
traditional
load
forecasting
methods,
which
are
often
impacted
by
environmental
temperature,
parameters,
user
behavior
uncertainties.
These
methods
struggle
accurately
capture
complex
dynamics
nonlinear
relationships
of
operations,
making
it
difficult
devise
operation
scheduling
strategies
effectively.
The
proposed
was
applied
validated
using
case
an
office
Nanjing,
China.
prediction
results
showed
coefficient
variation
root
mean
square
error
(CV-RMSE)
values
6.4%
2.2%.
Compared
original
operating
conditions,
temperature
remained
comfortable
range,
reduced
5.25%,
costs
were
24.94%.
demonstrate
that
offers
improved
computational
efficiency,
enhanced
performance,
economic
benefits.
