Energy Reports,
Journal Year:
2022,
Volume and Issue:
8, P. 2656 - 2671
Published: Feb. 10, 2022
The
difficulty
in
balancing
energy
supply
and
demand
is
increasing
due
to
the
growth
of
diversified
flexible
building
resources,
particularly
rapid
development
intermittent
renewable
being
added
into
power
grid.
accuracy
consumption
prediction
top
priority
for
electricity
market
management
ensure
grid
safety
reduce
financial
risks.
speed
load
are
fundamental
prerequisites
different
objectives
such
as
long-term
planning
short-term
optimization
systems
buildings
past
few
decades
have
seen
impressive
time
series
forecasting
models
focusing
on
domains
objectives.
This
paper
presents
an
in-depth
review
discussion
models.
Three
widely
used
approaches,
namely,
physical
(i.e.,
white
box),
data-driven
black
hybrid
grey
were
classified
introduced.
principles,
advantages,
limitations,
practical
applications
each
model
investigated.
Based
this
review,
research
priorities
future
directions
domain
highlighted.
conclusions
drawn
could
guide
prediction,
therefore
facilitate
efficiency
buildings.
Applied Sciences,
Journal Year:
2019,
Volume and Issue:
9(13), P. 2630 - 2630
Published: June 28, 2019
Energy-efficiency
is
one
of
the
critical
issues
in
smart
cities.
It
an
essential
basis
for
optimizing
cities
planning.
This
study
proposed
four
new
artificial
intelligence
(AI)
techniques
forecasting
heating
load
buildings’
energy
efficiency
based
on
potential
neural
network
(ANN)
and
meta-heuristics
algorithms,
including
bee
colony
(ABC)
optimization,
particle
swarm
optimization
(PSO),
imperialist
competitive
algorithm
(ICA),
genetic
(GA).
They
were
abbreviated
as
ABC-ANN,
PSO-ANN,
ICA-ANN,
GA-ANN
models;
837
buildings
considered
analyzed
influential
parameters,
such
glazing
area
distribution
(GLAD),
(GLA),
orientation
(O),
overall
height
(OH),
roof
(RA),
wall
(WA),
surface
(SA),
relative
compactness
(RC),
estimating
(HL).
Three
statistical
criteria,
root-mean-squared
error
(RMSE),
coefficient
determination
(R2),
mean
absolute
(MAE),
used
to
assess
aforementioned
models.
The
results
indicated
that
model
provided
highest
performance
efficiency,
with
RMSE
1.625,
R2
0.980,
MAE
0.798.
remaining
models
(i.e.,
ABC-ANN)
yielded
lower
1.932,
1.982,
1.878;
0.972,
0.970,
0.973;
1.027,
0.957,
respectively.
Frontiers in Energy Research,
Journal Year:
2021,
Volume and Issue:
9
Published: March 29, 2021
The
rapid
development
in
data
science
and
the
increasing
availability
of
building
operational
have
provided
great
opportunities
for
developing
data-driven
solutions
intelligent
energy
management.
Data
preprocessing
serves
as
foundation
valid
analyses.
It
is
an
indispensable
step
analysis
considering
intrinsic
complexity
operations
deficiencies
quality.
refers
to
a
set
techniques
enhancing
quality
raw
data,
such
outlier
removal
missing
value
imputation.
This
article
comprehensive
review
analysing
massive
data.
A
wide
variety
are
summarised
terms
their
applications
imputation,
detection,
reduction,
scaling,
transformation,
partitioning.
In
addition,
three
state-of-the-art
proposed
tackle
practical
challenges
field,
i.e.,
augmentation,
transfer
learning,
semi-supervised
learning.
In-depth
discussions
been
presented
describe
pros
cons
existing
methods,
possible
directions
future
research
potential
smart
outcomes
helpful
field.
Energy and Built Environment,
Journal Year:
2019,
Volume and Issue:
1(2), P. 149 - 164
Published: Nov. 16, 2019
With
the
advent
of
era
big
data,
buildings
have
become
not
only
energy-intensive
but
also
data-intensive.
Data
mining
technologies
been
widely
utilized
to
release
values
massive
amounts
building
operation
data
with
an
aim
improving
performance
energy
systems.
This
paper
aims
at
making
a
comprehensive
literature
review
applications
in
this
domain.
In
general,
can
be
classified
into
two
categories,
i.e.,
supervised
and
unsupervised
technologies.
field,
are
usually
for
load
prediction
fault
detection/diagnosis.
And
pattern
identification
Comprehensive
discussions
made
about
strengths
shortcomings
mining-based
methods.
Based
on
review,
suggestions
future
researches
proposed
towards
effective
efficient
solutions
