Energy Reports,
Год журнала:
2022,
Номер
8, С. 125 - 132
Опубликована: Фев. 25, 2022
Global
horizontal
irradiance
(GHI)
is
a
crucial
factor
impacting
photovoltaic
(PV)
production,
and
required
for
accurate
real-time
power
forecasting.
And
it
new
effective
solution
to
obtain
the
GHI
by
sky
images
because
mainly
affected
cloud
cover
motion.
Therefore,
research
proposes
unique
artificial
intelligence
approach
forecasting
('nowcasting')
based
on
images,
which
can
significantly
enhance
accuracy
cloudy
days.
First,
nowcasting
model
with
convolutional
block
attention
module
(CBAM)
proposed,
Visual
Geometry
Group
(VGG)
networks.
Then,
taking
local
(LCC)
as
numerical
feature,
we
coupled
feature
in
image
improve
performance
of
model.
Finally,
verify
effectiveness
advantages
proposed
method,
when
compared
state-of-the-art
methods,
such
Sun's
model,
Jiang's
others,
method
outperforms
them
demonstrated
11.67%
nRMSE,
7.97%
nMAE,
27.69%
MAPE,
0.91
CORR
results
ASI-16
dataset.
Energy and AI,
Год журнала:
2022,
Номер
9, С. 100169 - 100169
Опубликована: Май 25, 2022
Despite
widespread
adoption
and
outstanding
performance,
machine
learning
models
are
considered
as
"black
boxes",
since
it
is
very
difficult
to
understand
how
such
operate
in
practice.
Therefore,
the
power
systems
field,
which
requires
a
high
level
of
accountability,
hard
for
experts
trust
justify
decisions
recommendations
made
by
these
models.
Meanwhile,
last
couple
years,
Explainable
Artificial
Intelligence
(XAI)
techniques
have
been
developed
improve
explainability
models,
that
their
output
can
be
better
understood.
In
this
light,
purpose
paper
highlight
potential
using
XAI
system
applications.
We
first
present
common
challenges
applications
then
review
analyze
recent
works
on
topic,
on-going
trends
research
community.
hope
will
trigger
fruitful
discussions
encourage
further
important
emerging
topic.
Advances in Applied Energy,
Год журнала:
2023,
Номер
9, С. 100123 - 100123
Опубликована: Янв. 13, 2023
Machine
learning
has
been
widely
adopted
for
improving
building
energy
efficiency
and
flexibility
in
the
past
decade
owing
to
ever-increasing
availability
of
massive
operational
data.
However,
it
is
challenging
end-users
understand
trust
machine
models
because
their
black-box
nature.
To
this
end,
interpretability
attracted
increasing
attention
recent
studies
helps
users
decisions
made
by
these
models.
This
article
reviews
previous
that
interpretable
techniques
management
analyze
how
model
improved.
First,
are
categorized
according
application
stages
techniques:
ante-hoc
post-hoc
approaches.
Then,
analyzed
detail
specific
with
critical
comparisons.
Through
review,
we
find
broad
faces
following
significant
challenges:
(1)
different
terminologies
used
describe
which
could
cause
confusion,
(2)
performance
ML
tasks
difficult
compare,
(3)
current
prevalent
such
as
SHAP
LIME
can
only
provide
limited
interpretability.
Finally,
discuss
future
R&D
needs
be
accelerate
management.
Energy & Fuels,
Год журнала:
2024,
Номер
38(3), С. 1692 - 1712
Опубликована: Янв. 19, 2024
Modern
machine
learning
(ML)
techniques
are
making
inroads
in
every
aspect
of
renewable
energy
for
optimization
and
model
prediction.
The
effective
utilization
ML
the
development
scaling
up
systems
needs
a
high
degree
accountability.
However,
most
approaches
currently
use
termed
black
box
since
their
work
is
difficult
to
comprehend.
Explainable
artificial
intelligence
(XAI)
an
attractive
option
solve
issue
poor
interoperability
black-box
methods.
This
review
investigates
relationship
between
(RE)
XAI.
It
emphasizes
potential
advantages
XAI
improving
performance
efficacy
RE
systems.
realized
that
although
integration
with
has
enormous
alter
how
produced
consumed,
possible
hazards
barriers
remain
be
overcome,
particularly
concerning
transparency,
accountability,
fairness.
Thus,
extensive
research
required
address
societal
ethical
implications
using
create
standardized
data
sets
evaluation
metrics.
In
summary,
this
paper
shows
potential,
perspectives,
opportunities,
challenges
application
system
management
operation
aiming
target
efficient
energy-use
goals
more
sustainable
trustworthy
future.
International Journal of Sustainable Engineering,
Год журнала:
2021,
Номер
14(6), С. 1733 - 1755
Опубликована: Окт. 6, 2021
Accurate
PV
power
forecasting
techniques
are
a
prerequisite
for
the
optimal
management
of
grid
and
its
stability.
This
paper
presents
review
recent
developments
in
field
forecasting,
mainly
focusing
on
literature
which
uses
ML
techniques.
The
(sub-branch
artificial
intelligence)
extensively
used
due
to
their
ability
solve
nonlinear
complex
data
structures.
can
either
be
direct,
or
indirect,
involves
solar
irradiance
forecast
model,
plane
array
estimation
performance
model.
both
these
pathways
based
proposed
methodology,
horizons
considered
input
parameters.
In
case
unavailability
historical
new
plant
failure
real-time
acquisition,
indirect
viable
alternative.
Although
ranking
various
models
is
complicated
no
model
universal,
studies
suggest
that
methodologies
like
deep
neural
networks
ensemble
hybrid
outperform
conventional
methods
short-term
forecasting.
Recent
articles
also
present
intelligent
optimisation
data-preparation
improve
accuracy.
IEEE Access,
Год журнала:
2024,
Номер
12, С. 44023 - 44042
Опубликована: Янв. 1, 2024
The
Smart
Grid
is
a
modern
power
grid
that
relies
on
advanced
technologies
to
provide
reliable
and
sustainable
electricity.
However,
its
integration
with
various
communication
IoT
devices
makes
it
vulnerable
cyber-attacks.
Such
attacks
can
lead
significant
damage,
economic
losses,
public
safety
hazards.
To
ensure
the
security
of
smart
grid,
increasingly
strong
solutions
are
needed.
This
paper
provides
comprehensive
analysis
vulnerabilities
different
approaches
for
detecting
It
examines
including
system
cyber-attacks,
discusses
all
elements.
also
investigates
rule-based,
signature-based,
anomaly
detection,
ma-chine
learning-based
methods,
focus
their
effectiveness
related
research.
Finally,
prospective
cybersecurity
such
as
AI
blockchain,
discussed
along
challenges
future
prospects
cyberattacks
grid.
paper's
findings
help
policymakers
stakeholders
make
informed
decisions
about
develop
effective
strategies
protect
from
