Science and Technology for Energy Transition,
Journal Year:
2024,
Volume and Issue:
79, P. 77 - 77
Published: Jan. 1, 2024
Demand
Response
(DR)
is
recognized
as
an
efficient
method
for
reducing
operational
uncertainties
and
promoting
the
incorporation
of
renewable
energy
sources.
However,
since
effectiveness
DR
greatly
influenced
by
consumer
behavior,
it
crucial
to
determine
degree
which
programs
can
offer
adaptable
capability
facilitate
use
resources.
To
address
this
challenge,
present
paper
proposes
a
methodological
framework
that
characterizes
in
modeling.
First,
demand-side
activities
within
are
segmented
into
distinct
modules,
encompassing
load
utilization,
contract
selection,
actual
performance,
enable
multifaceted
analysis
impacts
physical
human
variables
across
various
time
scales.
On
basis,
variety
data-driven
methods
such
regret
matching
mechanism
introduced
establish
model
evaluate
impact
factors
on
applicability.
Finally,
multi-attribute
evaluation
proposed,
effects
implementing
economic
viability
environmental
sustainability
distribution
systems
examined.
The
proposed
demonstrated
authentic
regional
system.
simulation
results
show
compared
scenarios
without
considering
uncertainty,
fully
consider
thereby
enabling
more
realistic
assessment
benefits
associated
with
enhancing
accommodation
smart
grids.
From
comparative
new
installation
scenarios,
integration
photovoltaic
wind
power
system,
presence
increase
consumption
rate
6.39%
37.44%,
respectively,
reduce
system
operating
cost
1.37%
3.32%.
Through
different
types,
when
shiftable
two-way
interactive
load,
increases
20.57%
26.35%,
decreases
2.12%
4.68%.
In
regard,
methodology,
hopefully,
could
provide
reliable
tool
utility
companies
or
government
regulatory
agencies
improve
sector
efficiency
based
refined
potential
flexibility
future
grids
incorporating
energies.
Energy and Built Environment,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 1, 2024
Black-box
models
have
demonstrated
remarkable
accuracy
in
forecasting
building
energy
loads.
However,
they
usually
lack
interpretability
and
do
not
incorporate
domain
knowledge,
making
it
difficult
for
users
to
trust
their
predictions
practical
applications.
One
important
interesting
question
remains
unanswered:
is
possible
use
intrinsically
interpretable
achieve
comparable
that
of
black-box
models?
With
an
aim
answering
this
question,
study
proposes
machine
learning-based
method
forecast
It
creatively
combines
two
learning
algorithms:
clustering
decision
trees
adaptive
multiple
linear
regression.
Clustering
automatically
identify
various
operation
conditions,
allowing
the
training
tailored
each
condition.
can
reduce
complexity
model
data,
leading
higher
accuracy.
Adaptive
regression
improved
algorithm
load
prediction.
adaptively
modify
coefficients
according
operations,
enhancing
non-linear
fitting
capability
The
proposed
evaluated
utilizing
operational
data
from
office
building.
results
indicate
exhibits
both
random
forests
extreme
gradient
boosting.
Furthermore,
shows
significantly
superior
accuracy,
with
average
improvement
10.2
%,
compared
some
popular
algorithms
such
as
artificial
neural
networks,
support
vector
regression,
classification
trees.
As
interpretability,
reveals
historical
cooling
loads
are
most
crucial
predicting
under
conditions.
Additionally,
outdoor
air
temperature
has
a
significant
contribution
prediction
during
daytime
on
weekdays
summer
transition
seasons.
In
future,
will
be
valuable
explore
integrating
laws
physics
into
further
enhance
its
interpretability.
Journal of Physics Conference Series,
Journal Year:
2025,
Volume and Issue:
3001(1), P. 012002 - 012002
Published: April 1, 2025
Abstract
Distributed
multi-energy
systems
(DMESs)
hold
significant
potentials
for
achieving
energy
sustainability
by
incorporating
renewable
resources
and
maximizing
synergies.
Proper
optimal
design
is
highly
essential
fully
leveraging
these
the
desired
performances
of
DMESs.
However,
there
lack
consideration
operation
strategies
to
manage
distributed
flexible
during
stage,
which
may
result
in
inefficient
utilization,
increased
costs,
reduced
grid
friendliness.
Therefore,
this
paper
proposed
a
comprehensive
energetic-economic-environmental
optimization
framework
DMESs
considering
impact
operational
flexibility.
The
flexibility
battery
storage
indoor
temperature
regulation
was
incorporated
through
system
control
mechanism
fed
back
into
layer,
iteratively
solved
using
non-dominated
sorting
genetic
algorithm
ideal
method.
effectiveness
validated
typical
DMES
serving
three-story
office
building
xxxm2.
Optimal
devices
capacity
corresponding
leverage
were
obtained.
This
study
provides
valuable
insight
guidance
more
grid-friendly
practical
engineering
identifying
opportunities.
Energies,
Journal Year:
2024,
Volume and Issue:
17(19), P. 4794 - 4794
Published: Sept. 25, 2024
Energy
management
models
for
buildings
have
been
designed
primarily
to
reduce
energy
costs
and
improve
efficiency.
However,
the
focus
has
recently
shifted
GEBs
with
a
view
toward
balancing
supply
demand
while
enhancing
system
flexibility
responsiveness.
This
paper
provides
comprehensive
comparative
analysis
of
other
building
models,
categorizing
their
features
into
internal
external
dimensions.
review
highlights
evolution
including
intelligent
buildings,
smart
green
zero-energy
introduces
eight
distinct
related
efficient,
connected,
smart,
flexible
aspects.
The
is
based
on
an
extensive
literature
detailed
comparison
across
aforementioned
features.
prioritize
interaction
power
grid,
which
distinguishes
them
from
traditional
focusing
efficiency
occupant
comfort.
also
discusses
technological
components
research
trends
associated
GEBs,
providing
insights
development
potential
in
context
sustainable
efficient
design.
