Fuels,
Год журнала:
2024,
Номер
5(4), С. 715 - 726
Опубликована: Окт. 24, 2024
In
recent
years,
due
to
the
spike
in
natural
gas
spot
prices,
gas-fired
power
corporations’
operating
costs
have
skyrocketed.
Traditional
generation
corporations
gradually
been
withdrawing
from
investment,
replaced
by
oil
and
enterprises
with
upstream
resources.
The
development
of
plants
helps
maintain
stability
grid
has
a
positive
effect
on
realization
carbon
neutrality
goals.
At
present,
most
financial
evaluation
methods
for
projects
tend
focus
static
tariffs
project
itself
lack
consideration
overall
contribution
industry
chain
latest
“gas–electricity
price
linkage”
mechanisms
China,
leading
reducing
investment
yield
constraints.
this
paper,
methodology
based
industrial
mechanism
was
proposed.
return
characteristics
specific
under
different
provinces
were
revealed
through
methodology.
Considering
trends
major
operation
strategies
These
studies
provide
references
suggestions
future
decisions
new
projects.
Heliyon,
Год журнала:
2023,
Номер
9(11), С. e21439 - e21439
Опубликована: Ноя. 1, 2023
This
article
investigates
the
performance
of
three
models
-
Autoregressive
Integrated
Moving
Average
(ARIMA),
Threshold
(TARMA)
and
Evidential
Neural
Network
for
Regression
(ENNReg)
in
forecasting
Brent
crude
oil
price,
a
crucial
economic
variable
with
significant
impact
on
global
economy.
With
increasing
complexity
price
dynamics
due
to
geopolitical
factors
such
as
Russo-Ukrainian
war,
we
examine
incorporating
information
war
accuracy
these
models.
Our
analysis
shows
that
can
significantly
improve
models,
ENNReg
model
inclusion
dummy
outperforms
other
during
period.
Including
has
enhanced
by
0.11%.
These
results
carry
implications
regarding
policymakers,
investors,
researchers
interested
developing
accurate
presence
events
war.
The
be
used
governments
oil-exporting
countries
budget
policies.
Energy Strategy Reviews,
Год журнала:
2024,
Номер
51, С. 101318 - 101318
Опубликована: Янв. 1, 2024
Evaluating
the
economic
benefits
of
tight
oil
resources
is
necessary
for
China
to
increase
its
production
and
reserves.
This
study
systematically
analyzes
uncertainties
in
development
China,
factors
affecting
economy,
coevolution
from
technology
market
perspectives.
The
results
indicate
that
a
positive
environment
technological
progress
are
important
realizing
oil.
Four
potential
scenarios
also
identified
(i.e.,
current
scenario,
limited
efficient
inefficient
scenario),
each
associated
with
different
internal
rates
return
(8
%,
14
20
6
respectively).
Jurnal Samudra Ekonomi dan Bisnis,
Год журнала:
2025,
Номер
16(01), С. 29 - 45
Опубликована: Янв. 29, 2025
This
study
focuses
on
coal
companies
in
Indonesia,
a
key
sector
the
mining
industry.
It
explores
how
ARIMA
and
ARCH/GARCH
models
can
predict
share
prices
of
these
companies.
The
results
indicate
that
are
effective,
with
Mean
Absolute
Percentage
Error
(MAPE)
values
ranging
from
6
to
20
percent.
movement
stock
is
directly
proportional
changes
benchmark
price.
Additionally,
it
emphasizes
significant
impact
geopolitical
events,
like
Russia-Ukraine
conflict,
post-pandemic
economic
conditions
These
factors
have
influenced
company
prices,
highlighting
value
forecasting
adapting
market
fluctuations.
research
provides
important
insights
for
investors,
suggesting
advanced
econometric
help
make
informed
investment
decisions
enhance
strategies
volatile
by
accounting
external
events
model
accuracy.
Neural Computing and Applications,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 29, 2025
Abstract
Given
the
volatile
nature
of
oil
prices
in
wake
COVID-19
and
Russia-Ukraine
war,
need
for
advanced
prediction
models
is
evident.
The
Autoregressive
Integrated
Moving
Average
model
estimated
through
maximum
likelihood
method
with
Marquardt-BFGS
optimisation
(ARIMA-BFGS)
was
used
to
select
relevant
predictors
three
different
models:
Extreme
Learning
Machine
(ELM),
newly
introduced
Evidential
Neural
Network
Regression
Gaussian
Random
Fuzzy
numbers
(EVNN-FUZZY)
an
Artificial
fine-tuned
Particle
Swarm
Optimisation
(ANN-PSO).
Formal
unit
root
tests,
Augmented
Dickey
Fuller
(ADF)
Phillips-Perron
(PP)
are
test
stationarity
Brent
price
before
estimating
ARIMA-BFGS.
Evaluation
measures
such
as
root-mean-squared
error
(RMSE),
mean
absolute
(MAE),
percentage
(MAPE)
coefficient
determination
(
$$R^2$$
R2
)
assess
performance
models.
study
utilises
a
combination
traditional
methods
neural
networks
improve
accuracy
prediction.
ANN-PSO
improves
predictive
precision
ARIMA-BFGS
by
65.30%
training
dataset
88.72%
testing
sample.
incorporation
war
has
improved
EVNN-FUZZY.
Governments,
investors
producers
can
all
benefit
from
these
outcomes
while
making
financial
decisions.
findings
this
be
oil-exporting
economies
guide
their
budgets,
oil-importing
countries
use
them
manage
inflation.
