2021 IEEE Sustainable Power and Energy Conference (iSPEC),
Journal Year:
2023,
Volume and Issue:
25, P. 1 - 6
Published: Nov. 28, 2023
Load
forecasting
plays
a
critical
role
in
decision-making
for
power
systems,
including
aspects
such
as
unit
commitment
and
economic
dispatch.
Over
the
past
few
decades,
numerous
methods
have
been
extensively
researched.
Various
metrics
proposed
to
assess
performance
of
different
load
techniques,
Mean
Absolute
Percentage
Error
(MAPE)
Root
Squared
(RMSE),
aid
selecting
most
suitable
accurate
models.
However,
these
can
only
compare
forecasts
within
same
dataset,
rather
than
across
multiple
datasets.
To
effectively
rank
datasets,
we
propose
normalizing
traditional
into
skill
scores.
facilitate
this
normalization,
first
define
calculate
so-called
reference
perfect
performance.
On
basis,
scores
datasets
be
computed
ranked
accordingly.
We
carry
out
case
studies
using
GEFCom
dataset
Guangdong
Power
Company
showcase
efficacy
method
delivering
more
rational
assessment
ranking
predictions.
Solar Energy,
Journal Year:
2024,
Volume and Issue:
271, P. 112413 - 112413
Published: March 1, 2024
Accurate
global
horizontal
irradiance
(GHI)
forecasting
is
critical
for
integrating
solar
energy
into
the
power
grid
and
operating
plants.
The
Weather
Research
Forecasting
model
with
its
radiation
extension
(WRF-Solar)
has
been
used
to
forecast
in
different
regions
around
world.
However,
application
of
WRF-Solar
prediction
GHI
West
Africa,
particularly
Ghana,
not
yet
investigated.
aim
this
study
evaluate
performance
predicting
focusing
on
three
automatic
weather
stations
(Akwatia,
Kumasi
Kologo)
year
2021.
We
two
one-way
nested
domains
(D1
=
15
km
D2
3
km)
investigate
ability
fully
coupled
up
72-hour
ahead
under
atmospheric
conditions.
initial
lateral
boundary
conditions
were
taken
from
ECMWF
high-resolution
operational
forecasts.
Our
findings
reveal
that
performs
better
clear
skies
than
cloudy
skies.
Under
skies,
Kologo
performed
best
GHI,
a
first
day
nRMSE
9.62
%.
at
all
sites
had
significant
uncertainties.
Additionally,
able
reproduce
observed
diurnal
cycle
high
AOD
most
selected
days.
This
enhances
understanding
model's
capabilities
limitations
Ghana.
provide
valuable
information
stakeholders
involved
generation
integration
towards
optimized
management
region.
Energies,
Journal Year:
2024,
Volume and Issue:
17(14), P. 3480 - 3480
Published: July 15, 2024
Socioeconomic
growth
and
population
increase
are
driving
a
constant
global
demand
for
energy.
Renewable
energy
is
emerging
as
leading
solution
to
minimise
the
use
of
fossil
fuels.
However,
renewable
resources
characterised
by
significant
intermittency
unpredictability,
which
impact
their
production
integration
into
power
grid.
Forecasting
models
increasingly
being
developed
address
these
challenges
have
become
crucial
sources
integrated
in
systems.
In
this
paper,
comparative
analysis
forecasting
methods
developed,
focusing
on
photovoltaic
wind
power.
A
review
state-of-the-art
techniques
conducted
synthesise
categorise
different
models,
taking
account
climatic
variables,
optimisation
algorithms,
pre-processing
techniques,
various
horizons.
By
integrating
diverse
such
algorithms
carefully
selecting
forecast
horizon,
it
possible
highlight
accuracy
stability
forecasts.
Overall,
ongoing
development
refinement
achieve
sustainable
reliable
future.
Journal of Renewable and Sustainable Energy,
Journal Year:
2023,
Volume and Issue:
15(5)
Published: Sept. 1, 2023
The
current
grid
code
in
China
regard
to
solar
forecasting
is,
my
opinion,
underdeveloped,
especially
contrast
the
rate
at
which
photovoltaics
are
being
installed.
As
such,
explaining
limitations
of
and
resetting
pathways
improve
it
thought
utilitarian
for
those
scientists
policymakers
who
responsible
or
aware
but
have
not
themselves
worked
on
problem
forecasting.
In
this
perspective
article,
I
should
first
explain
with
respect
China's
perceived
deficiencies
research
practices,
then
outline
a
five-stage
workflow
that
could
completely
mitigate
situation.
Among
other
things,
over-reliance
accuracy
as
basis
gauging
goodness
forecasts
is
identified
root
cause
status
quo,
thus,
advocate
holistic
forecast
verification
procedure
encompasses
consistency,
quality,
value.
With
mind,
proposed
better
integration
purposes
relies
effective
information
flow
among
weather
department,
operators,
individual
plant
owners,
inline
code.
What
goes
beyond
proposal
further
introduces
couple
concepts
called
“hierarchical
reconciliation”
“firm
forecasting,”
new
able
eliminate
errors
wholly,
thus
making
power
dispatchable
system
level.
slight
premium
incurred,
now
possible
manage
plants,
variable
renewables
general,
same
style
managing
conventional
fire-powered
generators.
Energy,
Journal Year:
2024,
Volume and Issue:
291, P. 130284 - 130284
Published: Jan. 11, 2024
Forecasting
techniques
for
solar
and
wind
energy
are
essential
controlling
their
variability
being
heavily
researched.
However,
regional
differences
in
predictability
these
forecast
models
have
rarely
been
studied.
Regional
refer
to
performance
based
on
location.
In
this
study,
time-series
often
used
short-term
forecasts
were
quantitatively
analyzed.
A
three-step
methodology
was
devised
extract
significant
features
forecasting
develop
a
model
estimate
performance.
(1)
Multiple
models,
including
machine
learning,
applied
100
random
sites
calculate
(2)
The
of
each
site
statistically
extracted
compared
with
(3)
formula-based
modefl
developed
highly
correlated
metrics.
standard
deviations
the
rolling
mean
those
metrics
among
statistics
useful
interpreting
data
showed
correlation
>0.8
both
wind.
These
findings
can
reduce
uncertainty
applications
minimize
risk
power
system
operations.
Solar Energy,
Journal Year:
2024,
Volume and Issue:
279, P. 112801 - 112801
Published: Aug. 5, 2024
We
conduct
a
comparative
study
of
deterministic-to-probabilistic
(D2P)
and
probabilistic-to-probabilistic
(P2P)
forecasting
methods
for
photovoltaic
(PV)
power
generation.
In
this
analysis,
we
go
beyond
traditional
statistical
metrics
to
introduce
novel
metric
in
the
field
PV
forecasting.
This
evaluates
economic
value
production
across
all
possible
cost–loss
ratios,
offering
comprehensive
view
forecast's
utility
at
different
probability
thresholds.
The
study,
based
on
real-world
data
from
plant
production,
includes
assessment
techniques
using
ECMWF's
ensemble
system
(EPS)
P2P
approach,
contrasts
with
deterministic
weather
forecasts
D2P
approach.
While
advantages
EPS
might
not
be
immediately
apparent
through
conventional
metrics,
detailed
examination
significance
results,
without
EPS,
demonstrates
distinct
significant
former,
especially
terms
value.
innovative
approach
estimating
forecast
could
used
by
energy
resource
managers
perform
an
effective
priori
cost–benefit
analysis
assess
whether
additional
investment
required
implement
EPS-based
is
cost-effective
compared
alone.
