The
air
conditioning
system
consumes
more
than
half
of
the
total
energy
demand
in
hub
airport
buildings.
To
enhance
efficiency
and
to
enable
intelligent
management,
it
is
vital
build
an
accurate
cold
load
prediction
model.
However,
current
models
face
challenges
dealing
with
dispersed
patterns
lack
interpretability
when
black
box
are
adopted.
tackle
these
challenges,
we
propose
a
novel
k-means-Temporal
Fusion
Transformer
(TFT)
based
hybrid
Specifically,
daily
grouped
using
improved
k-means
clustering
method
that
considers
both
input
feature
weights
dynamic
time
warping
(DTW)
distances.
Additionally,
statistical
features
output
inputted
into
TFT.
By
further
incorporating
context
information,
integration
data
between
different
schema
categories
achieved,
thus
reducing
errors
may
occur
during
transition
process.
As
result,
performance
significantly
improved.
Chongqing
Jiangbei
Airport
T3A
terminal
used
as
case
study,
experiments
conducted
cooling
from
No.1
station,
well
traffic
meteorological
station
data.
Results
compared
other
mainstream
models,
confirming
proposed
day-ahead
forecasting
model
achieves
improvements
several
indicators,
including
MAE,
MAPE,
CV-RMSE,
R2,
which
384
kW,
3%,
5%,
0.058
respectively.
Thermo,
Journal Year:
2024,
Volume and Issue:
4(1), P. 100 - 139
Published: March 6, 2024
Given
the
climate
change
in
recent
decades
and
ever-increasing
energy
consumption
building
sector,
research
is
widely
focused
on
green
revolution
ecological
transition
of
buildings.
In
this
regard,
artificial
intelligence
can
be
a
precious
tool
to
simulate
optimize
performance,
as
shown
by
plethora
studies.
Accordingly,
paper
provides
review
more
than
70
articles
from
years,
i.e.,
mostly
2018
2023,
about
applications
machine/deep
learning
(ML/DL)
forecasting
performance
buildings
their
simulation/control/optimization.
This
was
conducted
using
SCOPUS
database
with
keywords
“buildings”,
“energy”,
“machine
learning”
“deep
selecting
papers
addressing
following
applications:
design/retrofit
optimization,
prediction,
control/management
heating/cooling
systems
renewable
source
systems,
and/or
fault
detection.
Notably,
discusses
main
differences
between
ML
DL
techniques,
showing
examples
use
The
aim
group
most
frequent
ML/DL
techniques
used
field
highlighting
potentiality
limitations
each
one,
both
fundamental
aspects
for
future
approaches
considered
are
decision
trees/random
forest,
naive
Bayes,
support
vector
machines,
Kriging
method
neural
networks.
investigated
convolutional
recursive
networks,
long
short-term
memory
gated
recurrent
units.
Firstly,
various
explained
divided
based
methodology.
Secondly,
grouping
aforementioned
occurs.
It
emerges
that
efficiency
issues
while
management
systems.
