Energy and Buildings,
Journal Year:
2022,
Volume and Issue:
277, P. 112479 - 112479
Published: Oct. 12, 2022
Detailed
parametric
analysis
and
measurements
are
required
to
reduce
building
energy
usage
while
maintaining
acceptable
thermal
conditions.
This
research
suggested
a
system
that
combines
Building
Information
Modeling
(BIM),
machine
learning,
the
non-dominated
sorting
genetic
algorithm-II
(NSGA
II)
investigate
impact
of
factors
on
find
optimal
design.
A
plugin
is
developed
receive
sensor
data
export
all
necessary
information
from
BIM
MSSQL
Excel.
The
model
was
imported
IDA
Indoor
Climate
Energy
(IDA
ICE)
execute
an
consumption
simulation
then
pairwise
test
produce
sample
set.
To
study
set
develop
prediction
between
usage,
11
learning
algorithms
used.
best
algorithm
Group
Least
Square
Support
Vector
Machine
(GLSSVM),
later
employed
in
NSGA
II
as
fitness
function
using
Dynamo
software.
An
multi-objective
optimization
designed
optimize
interior
comfort
(measured
by
predicted
percentage
dissatisfied
(PPD)).
Pareto
front
calculated,
optimum
point
approach
used
combination
envelope
characteristics,
HVAC
setpoints,
shading
parameters,
lighting,
air
infiltration.
feasibility
effectiveness
framework
demonstrated
case
upper
secondary
school
Norway;
results
show
that:
(1)
GLSSVM
has
unique
capacity
forecast
use
with
high
accuracy:
R2
0.99,
RMSE
1.2,
MSE
1.44,
MAE
0.89;
(2)
may
be
successfully
improved
GLSSVM-NSGA
hybrid
technique,
which
reduces
37.5%
increases
33.5%,
respectively.
Case Studies in Construction Materials,
Journal Year:
2022,
Volume and Issue:
16, P. e01046 - e01046
Published: April 11, 2022
This
study
aims
to
apply
machine
learning
methods
predict
the
compression
strength
of
self-compacting
recycled
aggregate
concrete.
To
obtain
this
goal,
ensemble
methods:
Random
Forest
(RF),
K-Nearest
Neighbor
(KNN),
Extremely
Randomized
Trees
(ERT),
Extreme
Gradient
Boosting
(XGB),
(GB),
Light
Machine
(LGBM),
Category
(CB)
and
generalized
additive
models:
Inverse
Gaussian
(GAM1)
Poisson
(GAM2)
were
applied.
For
development
models,
515
research
article
samples
collected
divided
into
three
subsets:
training
(360),
validation
(77),
testing
(78).
The
SCC
components:
cement,
water,
mineral
admixture,
fine
aggregates,
coarse
superplasticizers
taken
as
input
variables
output
variables.
determine
ability
models
project
compressive
strength,
following
metrics
used:
R2,
RMSE,
MAE,
MAPE.
results
indicate
that
RF
(R2
=
0.7128,
RMSE
0.0807,
MAE
0.06)
GB
0.6948,
0.0832,
0.0569)
have
a
strong
potential
with
aggregates.
sensitivity
analysis
model
indicates
cement
water
are
highest
impact
in
predicting
while
has
lowest
impact.
Energies,
Journal Year:
2023,
Volume and Issue:
16(2), P. 745 - 745
Published: Jan. 9, 2023
An
increase
in
consumption
and
inefficiency,
fluctuating
trends
demand
supply,
a
lack
of
critical
analytics
for
successful
management
are
just
some
the
problems
that
energy
business
throughout
world
is
currently
facing.
This
study
set
out
to
assess
potential
contributions
AI
ML
technologies
could
make
expansion
production
developing
countries,
where
these
issues
more
pronounced
because
prevalence
numerous
unauthorized
connections
electricity
grid,
large
amount
not
being
measured
or
paid
for.
primarily
aims
address
arise
due
frequent
power
outages
widespread
access
wide
range
countries.
Findings
suggest
have
major
fields
predictive
turbine
maintenance,
optimization,
grid
management,
price
prediction,
residential
building
efficiency
assessment.
A
discussion
what
has
be
done
so
nations
may
reap
benefits
artificial
intelligence
machine
learning
sector
concluded
paper.
Energy and Buildings,
Journal Year:
2023,
Volume and Issue:
303, P. 113768 - 113768
Published: Nov. 22, 2023
Stakeholders
such
as
urban
planners
and
energy
policymakers
use
building
performance
modeling
analysis
to
develop
strategic
sustainable
plans
with
the
aim
of
reducing
consumption
emissions
from
built
environment.
However,
inconsistent
data
lack
scalable
models
create
a
gap
between
traditional
planning
practices.
An
alternative
approach
is
conduct
large-scale
usage
survey,
which
time-consuming.
Similarly,
existing
studies
rely
on
machine
learning
or
statistical
approaches
for
calculating
performance.
This
paper
proposes
solution
that
employs
data-driven
predict
residential
buildings,
using
both
ensemble-based
end-use
demand
segregation
methods.
The
proposed
methodology
consists
five
steps:
collection,
archetype
development,
physics-based
parametric
modeling,
analysis.
devised
tested
Irish
stock
generates
synthetic
dataset
one
million
buildings
through
19
identified
vital
variables
four
archetypes.
As
part
process,
study
implemented
an
method,
including
heating,
lighting,
equipment,
photovoltaic,
hot
water,
at
scale.
Furthermore,
model's
enhanced
by
employing
approach,
achieving
91%
accuracy
compared
approach's
76%.
Accurate
prediction
enables
stakeholders,
planners,
make
informed
decisions
when
retrofit
measures.
Energy & Fuels,
Journal Year:
2024,
Volume and Issue:
38(3), P. 1692 - 1712
Published: Jan. 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.
