2021 IEEE Sustainable Power and Energy Conference (iSPEC),
Год журнала:
2023,
Номер
25, С. 1 - 6
Опубликована: Ноя. 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,
Год журнала:
2024,
Номер
279, С. 112801 - 112801
Опубликована: Авг. 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.
The
development
of
renewable
energy
is
a
crucial
strategy
for
addressing
global
shortages
and
environmental
pollution.
Solar
energy,
noted
its
cleanliness
renewability,
has
become
significant
source
energy.
Studying
the
distribution
solar
resources
essential
due
to
cyclical,
fluctuating,
seasonal
nature
irradiance.
This
paper
examines
primary
factors
influencing
irradiation,
utilizing
data
on
irradiance
photovoltaic
output
from
Wuhan
Zhangbei,
China,
in
2022.
findings
indicate
that
China
reaches
minimum
during
winter
peaks
summer.
On
sunny
days,
typically
exhibits
single-peak
trend,
while
cloudy
rainy
it
shows
greater
volatility.
primarily
consists
direct
normal
partially
diffuse
horizontal
overcast
days.
study
could
provide
theoretical
foundation
positioning
power
installations
further
predicting
future
research.
Journal of Renewable and Sustainable Energy,
Год журнала:
2024,
Номер
16(6)
Опубликована: Ноя. 1, 2024
As
power
networks
around
the
world
undergo
profound
transformation
driven
by
decarbonization
of
electricity,
integration
renewable
energy
resources
and
low
carbon
technologies,
more
active
network
participation
at
grid
edge,
distribution
operators
have
encountered
continue
to
face
various
challenges.
Both
industry
academia
are
actively
involved
in
addressing
these
challenges,
with
a
common
focus
on
ensuring
operational
efficiency
reliability
electricity
network.
This
Perspective
article
analyzes
academia–industry
relationship
sector
first-hand
experience
set
insights
from
newly
established
Distribution
System
Operators
United
Kingdom.
perspective
identifies
explores
barriers
collaboration
forms
willingness,
communication,
objectivity,
understanding,
resources,
outcomes.
We
offer
practical
recommendations
both
parties,
supported
real
actionable
strategies
overcome
2021 IEEE Sustainable Power and Energy Conference (iSPEC),
Год журнала:
2023,
Номер
25, С. 1 - 6
Опубликована: Ноя. 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.
