The
evaluation
of
solar
energy
utilization
potential
urban
building
surfaces
currently
faces
the
dilemma
high
complexity
large-scale-high-precision-multidimensional
coupled
computation.
This
study
introduces
a
more
comprehensive
method
for
clusters
splitting
and
type
identification,
uses
geometric
morphology
to
extract
multi-dimensional
feature
indicators
clusters.
A
sky
module
technology
coupling
temporal
dimension
radiation
type,
dynamic
identification
surface
orientation,
high-performance
computational
framework
metrics
parsing
have
been
developed.
Further,
variety
machine
learning
algorithms
were
examined,
finally
XGB
model,
which
balances
predictive
performance
(R2>0.95
MSE<0.10)
prevents
overfitting,
was
selected
predict
multidimensional
existing
buildings
in
non-enriched
areas.
found
that:
(a)
geographic
location
clusters,
types
can
better
characterize
variability
be
used
build
high-precision
prediction
models.
(b)
shading
typical
varies
across
orientations,
with
roofs
distributed
between
3.45%
6.98%,
façades
34.70
50.71%.
(c)The
is
significant
both
different
directions
time
dimensions,
e.g.,
winter
accounts
about
38%
summer
Chengdu
only
30%
Chongqing.
In
this
study,
we
further
captured
nonlinear
relationship
thresholds
effective
potentials
under
orientations
constructed
models
bi-directional
gains
explaining
science
advancing
applications.
Energy Sources Part B Economics Planning and Policy,
Journal Year:
2025,
Volume and Issue:
20(1)
Published: Jan. 11, 2025
In
this
paper,
we
use
GIS
analysis
to
estimate
potential
distributed
solar
PV
capacity
and
electricity
generation
in
a
suburban
neighborhood
Virginia,
United
States.
Using
combination
of
LiDAR
insolation
data,
find
that
37%
rooftop
space
the
study
area
would
receive
sufficient
support
(DPV)
system.
Applying
conservative
assumptions,
nearly
19
MW
(AC)
could
realistically
be
installed,
providing
28%
area's
estimated
annual
demand.
These
findings
provide
evidence
significant
untapped
DPV,
need
for
streamlined
permitting
processes
other
incentives
reduce
soft
costs
facilitate
DPV
installation.
We
also
discuss
opportunities
merging
planning
engineering
research
targeted
utilization
locations
where
it
can
best
distribution
grid
operations,
such
as
on
commercial
sector
buildings
particular.
Energy 360.,
Journal Year:
2024,
Volume and Issue:
1, P. 100006 - 100006
Published: Aug. 5, 2024
As
urban
solar
photovoltaic
(PV)
construction
emerges
as
a
leading
renewable
energy
technology,
there
is
growing
focus
on
its
implementation.
However,
the
challenges
of
scarce,
low-resolution,
and
inaccurate
PV-related
data
sources
hinder
accurate
assessments
PV
potentials
are
not
conducive
to
efficient
rational
smart
city
planning.
This
study
tackles
these
by
introducing
mature,
detailed,
assessment
process,
taking
Stonehaven
an
example,
aimed
at
leveraging
limited
mine
more
geographic
information
useful
for
guiding
Initially,
utilise
existing
Digital
Surface
Model
(DSM)
optical
image
data,
combined
with
deep
learning
techniques
potential
model,
comprehensively
assess
power
generation
area.
Our
results
demonstrate
that
integrating
DSM
significantly
enhances
accuracy
roof
segmentation.
Furthermore,
compared
DeeplabV3,
U-Net
performs
better
in
Additionally,
radiation
(SRP)
map
generated
highlights
superior
receiving
capacity
south-facing
flat
roofs.
We
provide
detailed
(PPGP)
individual
building
roofs,
revealing
substantial
this
area
generating
up
1.12
×
10^7
kWh
electricity
per
year.
Detailed
fine-grained
PPGP
can
also
help
optimise
siting
resource
allocation.
our
return-on-investment
period
(ROIP)
analysis
indicates
most
roofs
have
ROIPs
between
8.1
11.3
years.
The
ROIP
distribution
people
make
informed
investment
decisions.
Future
research
directions
include
enhancing
quality,
refining
segmentation
algorithms,
exploring
assisted
planning
smarter
