I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
1
97
0
~
1
9
79
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
38
.i
3
.
pp
1
97
0
-
1
9
79
1970
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Enha
nced t
im
e se
ries foreca
sting
u
sing
hybrid ARI
M
A and
ma
chine learning
mo
dels
Vig
nes
h Ar
um
ug
a
m
,
Vij
a
y
a
l
a
k
s
hm
i
Na
t
a
ra
j
a
n
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s,
S
R
M
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
R
a
ma
p
u
r
a
m C
a
m
p
u
s
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
22
,
2
0
2
4
R
ev
is
ed
Dec
17
,
2
0
2
4
Acc
ep
ted
Feb
27
,
2
0
2
5
Ac
c
u
ra
te
e
n
e
rg
y
d
e
m
a
n
d
fo
re
c
a
stin
g
is
e
ss
e
n
ti
a
l
fo
r
o
p
ti
m
izi
n
g
re
so
u
rc
e
m
a
n
a
g
e
m
e
n
t
a
n
d
p
lan
n
in
g
wit
h
i
n
th
e
e
n
e
rg
y
se
c
to
r.
Tra
d
it
i
o
n
a
l
t
ime
se
ries
m
o
d
e
ls,
su
c
h
a
s
ARIMA
a
n
d
S
ARIMA,
h
a
v
e
l
o
n
g
b
e
e
n
e
m
p
lo
y
e
d
fo
r
th
is
p
u
r
p
o
se
.
H
o
we
v
e
r,
t
h
e
se
m
e
th
o
d
s
o
f
ten
fa
c
e
li
m
it
a
ti
o
n
s
i
n
h
a
n
d
li
n
g
n
o
n
-
sta
ti
o
n
a
ry
d
a
ta,
c
o
m
p
lex
it
y
in
m
o
d
e
l
tu
n
i
n
g
,
a
n
d
su
sc
e
p
ti
b
il
i
ty
t
o
o
v
e
rfit
ti
n
g
.
To
a
d
d
re
ss
th
e
se
c
h
a
ll
e
n
g
e
s,
t
h
i
s
stu
d
y
p
ro
p
o
se
s
a
h
y
b
rid
a
p
p
r
o
a
c
h
t
h
a
t
in
teg
ra
tes
trad
it
i
o
n
a
l
sta
ti
stica
l
m
o
d
e
ls
with
a
d
v
a
n
c
e
d
c
o
m
p
u
tati
o
n
a
l
m
e
th
o
d
s.
By
c
o
m
b
i
n
in
g
th
e
str
e
n
g
th
s
o
f
b
o
t
h
a
p
p
ro
a
c
h
e
s,
th
e
p
r
o
p
o
se
d
m
o
d
e
ls
a
im
to
e
n
h
a
n
c
e
p
re
d
ictiv
e
a
c
c
u
ra
c
y
,
imp
ro
v
e
c
o
m
p
u
tati
o
n
a
l
e
fficie
n
c
y
,
a
n
d
m
a
in
tai
n
ro
b
u
stn
e
ss
a
c
ro
ss
v
a
ried
e
n
e
rg
y
d
a
tas
e
ts.
Ex
p
e
rime
n
tal
re
su
l
ts
d
e
m
o
n
stra
te
th
a
t
th
e
se
h
y
b
r
id
m
o
d
e
ls
c
o
n
siste
n
tl
y
o
u
t
p
e
rfo
rm
sta
n
d
a
lo
n
e
trad
it
i
o
n
a
l
m
e
th
o
d
s,
p
r
o
v
i
d
in
g
m
o
re
re
li
a
b
le
a
n
d
p
re
c
ise
fo
re
c
a
sts.
Th
e
se
fin
d
i
n
g
s
u
n
d
e
rsc
o
re
th
e
p
o
te
n
ti
a
l
o
f
h
y
b
r
id
m
e
th
o
d
o
lo
g
ies
in
a
d
v
a
n
c
i
n
g
e
n
e
r
g
y
d
e
m
a
n
d
fo
re
c
a
stin
g
a
n
d
su
p
p
o
rti
n
g
m
o
re
e
ffe
c
ti
v
e
d
e
c
isio
n
-
m
a
k
i
n
g
i
n
e
n
e
r
g
y
m
a
n
a
g
e
m
e
n
t.
K
ey
w
o
r
d
s
:
AR
I
MA
Gr
ad
ien
t b
o
o
s
tin
g
m
ac
h
in
es
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Ma
ch
in
e
lear
n
in
g
Me
an
s
q
u
ar
ed
e
r
r
o
r
R
o
o
t m
ea
n
s
q
u
ar
e
d
er
r
o
r
T
im
e
s
er
ies an
aly
s
is
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Vig
n
esh
Ar
u
m
u
g
am
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
Ap
p
licatio
n
s
,
SR
M
I
n
s
titu
te
o
f
s
cien
ce
an
d
T
ec
h
n
o
l
o
g
y
R
am
ap
u
r
am
C
am
p
u
s
C
h
en
n
ai,
I
n
d
ia
E
m
ail:
v
ig
n
esh
a2
@
s
r
m
is
t.e
d
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
AR
I
MA
m
o
d
el,
d
ev
el
o
p
e
d
b
y
B
o
x
a
n
d
J
en
k
in
s
in
t
h
e
1
9
7
0
s
,
b
r
o
u
g
h
t
a
s
tr
u
ctu
r
ed
f
r
a
m
ewo
r
k
to
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
T
h
is
m
o
d
el
b
r
ea
k
s
d
o
wn
a
tim
e
s
er
ies
in
to
th
r
ee
k
ey
elem
e
n
ts
:
au
to
r
eg
r
ess
io
n
(
AR
)
,
in
teg
r
atio
n
(
I
)
,
an
d
m
o
v
in
g
av
er
ag
e
(
MA
)
.
T
h
e
AR
co
m
p
o
n
en
t
ca
p
tu
r
es
th
e
d
ep
en
d
e
n
ce
b
etwe
en
a
v
alu
e
an
d
its
p
r
ev
io
u
s
v
alu
es,
wh
ile
th
e
I
co
m
p
o
n
en
t
e
n
s
u
r
es
s
tatio
n
ar
ity
b
y
ap
p
ly
in
g
d
if
f
e
r
en
cin
g
t
o
th
e
d
ata.
T
h
e
MA
p
ar
t
f
o
c
u
s
es
o
n
th
e
r
elatio
n
s
h
ip
b
etwe
en
a
v
alu
e
an
d
t
h
e
r
esid
u
al
e
r
r
o
r
s
f
r
o
m
p
r
e
v
io
u
s
o
b
s
er
v
atio
n
s
.
R
en
o
wn
ed
f
o
r
its
s
tr
aig
h
tf
o
r
war
d
ap
p
licatio
n
an
d
v
e
r
s
atility
,
au
to
r
eg
r
ess
iv
e
in
teg
r
ate
d
m
o
v
in
g
av
e
r
ag
e
(
AR
I
MA
)
h
as b
ec
o
m
e
a
wid
el
y
ad
o
p
te
d
to
o
l in
d
iv
er
s
e
f
o
r
ec
asti
n
g
co
n
tex
ts
[
1
]
-
[
8
]
.
T
im
e
s
er
ies f
o
r
ec
asti
n
g
is
a
cr
itical
to
o
l
in
u
n
d
er
s
tan
d
in
g
an
d
p
r
ed
ictin
g
tem
p
o
r
al
d
at
a
p
atter
n
s
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
r
an
g
in
g
f
r
o
m
f
in
an
ce
a
n
d
ec
o
n
o
m
ics
to
we
ath
er
f
o
r
ec
asti
n
g
an
d
r
eso
u
r
ce
m
an
ag
em
en
t
[
9
]
-
[
1
4
]
.
I
ts
s
ig
n
if
ican
ce
lies
in
its
ab
ilit
y
to
ex
tr
a
p
o
late
h
is
to
r
ical
d
ata
in
to
th
e
f
u
tu
r
e,
p
r
o
v
id
in
g
v
alu
a
b
le
in
s
ig
h
ts
f
o
r
d
ec
is
io
n
-
m
a
k
in
g
p
r
o
ce
s
s
es.
T
r
ad
itio
n
al
ap
p
r
o
a
ch
es,
s
u
ch
as
AR
I
MA
m
o
d
els,
h
av
e
lo
n
g
b
ee
n
f
o
u
n
d
atio
n
al
in
tim
e
s
er
ies
an
aly
s
is
d
u
e
to
th
ei
r
ab
ilit
y
t
o
ca
p
tu
r
e
lin
ea
r
d
ep
en
d
en
cie
s
with
in
d
ata
an
d
m
ak
e
r
eliab
le
f
o
r
ec
asts
u
n
d
er
ce
r
tain
ass
u
m
p
tio
n
s
o
f
s
tatio
n
ar
ity
an
d
lin
ea
r
ity
.
Ho
we
v
er
,
as
d
atasets
g
r
o
w
in
co
m
p
lex
ity
an
d
n
o
n
-
lin
ea
r
p
atter
n
s
b
ec
o
m
e
m
o
r
e
p
r
ev
al
en
t,
th
e
lim
itatio
n
s
o
f
p
u
r
ely
s
tatis
t
ical
m
o
d
els
lik
e
A
R
I
M
A
b
ec
o
m
e
ap
p
ar
e
n
t
[
1
5
]
-
[
1
9
]
.
T
h
is
n
ec
ess
itates
th
e
ev
o
lu
tio
n
to
war
d
s
h
y
b
r
id
f
o
r
ec
asti
n
g
m
o
d
els
th
at
in
teg
r
at
e
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es [
2
0
]
-
[
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ce
d
time
s
eries
fo
r
ec
a
s
t
in
g
u
s
in
g
h
yb
r
id
A
R
I
MA
a
n
d
ma
ch
in
e
lea
r
n
in
g
…
(
V
ig
n
esh
A
r
u
mu
g
a
m
)
1971
T
h
is
p
ap
er
ex
p
l
o
r
es
th
e
d
ev
el
o
p
m
en
t
an
d
ap
p
licatio
n
o
f
h
y
b
r
id
AR
I
MA
-
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
in
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
I
t
aim
s
to
b
r
id
g
e
th
e
g
ap
b
etwe
en
tr
ad
itio
n
al
s
tatis
tical
m
eth
o
d
s
a
n
d
m
o
d
er
n
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es,
o
f
f
er
i
n
g
in
s
ig
h
ts
in
to
h
o
w
th
ese
h
y
b
r
id
m
o
d
els
ca
n
o
v
er
c
o
m
e
th
e
lim
itatio
n
s
o
f
co
n
v
en
tio
n
al
AR
I
MA
m
o
d
els.
T
h
e
co
n
t
r
ib
u
tio
n
s
o
f
th
is
s
tu
d
y
lie
in
:
−
Dem
o
n
s
tr
atin
g
th
e
e
f
f
icac
y
o
f
h
y
b
r
id
AR
I
MA
-
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els
in
ca
p
tu
r
in
g
co
m
p
lex
tem
p
o
r
al
p
atter
n
s
.
−
Pro
v
id
in
g
e
m
p
ir
ical
ev
id
e
n
ce
o
f
im
p
r
o
v
ed
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
co
m
p
a
r
ed
to
t
r
ad
itio
n
al
A
R
I
MA
m
o
d
els.
−
Of
f
er
in
g
p
r
ac
tical
g
u
id
elin
e
s
f
o
r
s
elec
tin
g
an
d
im
p
le
m
en
tin
g
h
y
b
r
id
m
o
d
els
b
a
s
ed
o
n
d
ataset
ch
ar
ac
ter
is
tics
an
d
f
o
r
ec
asti
n
g
o
b
jectiv
es.
−
Pro
p
o
s
in
g
a
f
r
am
ewo
r
k
f
o
r
in
teg
r
atin
g
m
ac
h
in
e
lear
n
in
g
in
to
tim
e
s
er
ies
f
o
r
ec
asti
n
g
th
at
en
h
an
ce
s
p
r
ed
ictio
n
ca
p
ab
ilit
ies an
d
s
ca
lab
ilit
y
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Sev
er
al
s
tu
d
ies
h
av
e
b
ee
n
c
o
n
d
u
cte
d
to
ad
d
r
ess
th
e
c
h
allen
g
es
o
b
s
er
v
e
d
in
cu
r
r
en
t
s
y
s
tem
s
.
Ar
u
m
u
g
am
a
n
d
Nata
r
ajan
[
1
]
p
r
o
v
id
e
a
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
o
f
AR
I
MA
an
d
s
ea
s
o
n
al
AR
I
MA
(
SAR
I
MA
)
m
o
d
els,
wh
ich
ex
ten
d
AR
I
MA
b
y
in
c
o
r
p
o
r
atin
g
s
ea
s
o
n
al
ef
f
ec
ts
.
SAR
I
MA
m
o
d
els
ar
e
p
ar
ticu
lar
ly
e
f
f
ec
tiv
e
f
o
r
d
ata
with
s
tr
o
n
g
s
ea
s
o
n
al
p
atter
n
s
b
y
in
cl
u
d
in
g
s
ea
s
o
n
al
d
if
f
er
e
n
cin
g
a
n
d
s
ea
s
o
n
al
AR
an
d
MA
ter
m
s
.
T
h
eir
s
tu
d
y
h
ig
h
lig
h
ts
th
e
r
o
b
u
s
tn
ess
o
f
AR
I
MA
an
d
SAR
I
MA
m
o
d
el
s
in
ca
p
tu
r
in
g
lin
ea
r
p
atter
n
s
an
d
m
a
k
in
g
ac
cu
r
at
e
f
o
r
ec
asts
in
v
a
r
io
u
s
a
p
p
li
ca
tio
n
s
.
Ho
wev
er
,
th
e
y
also
n
o
te
th
e
m
o
d
els
’
lim
itatio
n
s
,
esp
ec
ially
th
eir
ass
u
m
p
tio
n
o
f
lin
ea
r
ity
a
n
d
r
eq
u
ir
em
en
t
f
o
r
s
tatio
n
a
r
ity
.
L
i
et
a
l.
[
2
]
d
em
o
n
s
tr
ated
t
h
e
ef
f
ec
tiv
en
ess
o
f
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
in
u
ltra
-
s
h
o
r
t
-
ter
m
p
o
wer
lo
ad
f
o
r
ec
asti
n
g
,
h
ig
h
lig
h
tin
g
its
a
b
ilit
y
to
h
an
d
le
h
ig
h
-
d
im
e
n
s
io
n
al
d
ata
an
d
in
co
r
p
o
r
ate
ex
o
g
en
o
u
s
v
ar
ia
b
les
f
o
r
im
p
r
o
v
e
d
ac
c
u
r
ac
y
.
Similar
ly
,
th
e
s
tu
d
y
b
y
Xu
e
et
a
l.
[
3
]
ex
p
lo
r
ed
a
co
m
b
i
n
ed
L
STM
-
AR
I
MA
m
o
d
el
f
o
r
an
o
m
aly
d
etec
tio
n
in
co
m
m
u
n
icatio
n
n
etwo
r
k
s
.
T
h
is
h
y
b
r
id
ap
p
r
o
ac
h
lev
er
ag
es th
e
s
tr
en
g
t
h
s
o
f
b
o
th
AR
I
MA
an
d
L
STM
,
with
AR
I
MA
ca
p
tu
r
in
g
th
e
lin
ea
r
co
m
p
o
n
e
n
t
o
f
th
e
d
ata
an
d
L
STM
m
o
d
elin
g
th
e
n
o
n
-
lin
ea
r
r
esid
u
als.
T
h
eir
f
in
d
in
g
s
s
u
g
g
est
th
at
s
u
ch
h
y
b
r
id
m
o
d
els
c
an
s
ig
n
if
ican
tly
e
n
h
an
ce
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
b
y
ad
d
r
ess
in
g
th
e
lim
itatio
n
s
o
f
ea
ch
in
d
i
v
id
u
al
ap
p
r
o
ac
h
.
Dee
p
lear
n
in
g
m
o
d
els
lik
e
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
an
d
h
y
b
r
id
C
NN
-
L
STM
ar
ch
itectu
r
es
h
av
e
also
b
ee
n
ex
p
lo
r
ed
f
o
r
tim
e
s
er
ies
f
o
r
e
ca
s
tin
g
.
Me
h
tab
an
d
Sen
[
4
]
u
tili
ze
d
C
NN
an
d
L
STM
-
b
ased
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
s
to
ck
p
r
ice
p
r
ed
i
ctio
n
,
d
em
o
n
s
tr
atin
g
th
at
th
e
co
m
b
in
e
d
a
p
p
r
o
ac
h
co
u
ld
ca
p
tu
r
e
b
o
th
s
p
atial
an
d
tem
p
o
r
al
d
ep
en
d
en
cies
in
th
e
d
ata,
lead
in
g
to
s
u
p
er
io
r
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
co
m
p
ar
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
.
Xu
et
a
l.
[
5
]
p
r
o
p
o
s
ed
a
d
ee
p
b
elief
n
etwo
r
k
(
DB
N)
-
b
ased
AR
m
o
d
el
f
o
r
non
-
lin
ea
r
tim
e
s
er
ies
f
o
r
ec
as
tin
g
.
T
h
eir
m
o
d
el
in
teg
r
ates
d
ee
p
lear
n
in
g
with
tr
ad
itio
n
al
s
tatis
t
ical
m
eth
o
d
s
,
ca
p
tu
r
in
g
in
t
r
icate
p
atter
n
s
in
th
e
d
ata
th
at
ar
e
o
f
ten
m
is
s
ed
b
y
s
tan
d
alo
n
e
AR
I
MA
m
o
d
els.
T
h
is
I
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es
h
as o
p
en
e
d
n
ew
av
en
u
es
f
o
r
m
o
r
e
ac
cu
r
ate
an
d
r
eliab
le
tim
e
s
er
ies
f
o
r
ec
asts
.
I
n
th
e
r
ea
lm
o
f
en
er
g
y
s
y
s
tem
s
,
Z
h
ao
et
a
l.
[
6
]
r
ev
iewe
d
th
e
ap
p
licatio
n
o
f
e
m
er
g
in
g
in
f
o
r
m
atio
n
a
n
d
co
m
m
u
n
icatio
n
tech
n
o
lo
g
ies
f
o
r
s
m
ar
t
en
er
g
y
s
y
s
tem
s
an
d
r
e
n
ewa
b
le
tr
a
n
s
itio
n
s
.
T
h
eir
wo
r
k
u
n
d
er
s
c
o
r
es
th
e
p
o
ten
tial
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els
in
o
p
tim
izin
g
en
er
g
y
c
o
n
s
u
m
p
tio
n
f
o
r
ec
asts
,
en
h
an
ci
n
g
t
h
e
ef
f
icien
c
y
an
d
s
u
s
tain
ab
ilit
y
o
f
en
er
g
y
s
y
s
tem
s
.
Hy
b
r
id
m
o
d
els
th
at
co
m
b
in
e
AR
I
MA
with
m
ac
h
in
e
l
ea
r
n
in
g
alg
o
r
ith
m
s
h
av
e
also
b
ee
n
p
r
o
p
o
s
ed
to
ad
d
r
ess
s
p
ec
if
ic
f
o
r
ec
asti
n
g
ch
allen
g
es.
Saleti
et
a
l.
[
7
]
i
n
tr
o
d
u
ce
d
a
h
y
b
r
i
d
AR
I
MA
-
L
STM
m
o
d
el
th
at
in
t
eg
r
ates
MA
tech
n
iq
u
es
to
en
h
an
ce
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
.
T
h
eir
s
tu
d
y
h
ig
h
lig
h
ts
th
e
p
r
ac
tical
b
e
n
ef
its
o
f
co
m
b
in
in
g
t
r
ad
itio
n
al
s
tatis
tical
m
o
d
els
with
d
ee
p
lear
n
in
g
,
p
r
o
v
i
d
in
g
a
r
o
b
u
s
t
f
r
am
ewo
r
k
f
o
r
tim
e
s
er
ies
an
aly
s
is
.
Po
m
o
r
s
k
i
an
d
Go
r
s
e
[
8
]
ex
p
lo
r
ed
th
e
u
s
e
o
f
ad
a
p
tiv
e
MA
in
Ma
r
k
o
v
-
s
witch
in
g
r
eg
r
ess
io
n
m
o
d
els,
d
em
o
n
s
tr
atin
g
im
p
r
o
v
em
en
ts
i
n
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
.
T
h
is
ap
p
r
o
ac
h
e
m
p
h
asizes
th
e
im
p
o
r
ta
n
ce
o
f
ad
a
p
tiv
ity
in
h
an
d
lin
g
e
v
o
lv
in
g
tim
e
s
er
i
es
d
ata,
a
f
ea
tu
r
e
th
at
is
well
-
ca
p
tu
r
ed
b
y
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
Peleg
et
a
l.
[
9
]
lev
er
ag
e
d
th
e
tr
ip
le
ex
p
o
n
e
n
tial
MA
f
o
r
f
ast
-
ad
ap
tiv
e
m
o
m
en
t e
s
tim
atio
n
,
f
u
r
th
e
r
en
h
an
ci
n
g
th
e
ad
ap
tab
ilit
y
o
f
f
o
r
ec
asti
n
g
m
o
d
els.
T
h
is
tech
n
iq
u
e
allo
ws
f
o
r
m
o
r
e
r
esp
o
n
s
iv
e
a
d
ju
s
tm
en
ts
to
ch
an
g
es
in
d
at
a
p
atter
n
s
,
im
p
r
o
v
in
g
t
h
e
o
v
er
all
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
f
o
r
ec
asts
.
I
n
ad
d
itio
n
to
d
ee
p
lear
n
in
g
,
o
th
e
r
m
ac
h
in
e
lea
r
n
in
g
tech
n
iq
u
e
s
s
u
ch
as
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
es
(
GB
M)
h
av
e
s
h
o
wn
p
r
o
m
is
e
in
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
He
et
a
l.
[
1
0
]
r
e
v
iewe
d
th
e
tech
n
o
lo
g
ies
an
d
ec
o
n
o
m
ics
o
f
elec
tr
ic
en
er
g
y
s
to
r
a
g
e
s
y
s
tem
s
,
h
ig
h
lig
h
tin
g
th
e
r
o
le
o
f
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
in
o
p
tim
izin
g
s
to
r
ag
e
an
d
d
is
tr
ib
u
tio
n
s
tr
ateg
ies.
T
h
e
I
o
f
m
ac
h
in
e
lear
n
i
n
g
with
tr
ad
itio
n
al
m
eth
o
d
s
o
f
f
e
r
s
a
co
m
p
r
eh
en
s
iv
e
ap
p
r
o
ac
h
to
f
o
r
ec
asti
n
g
,
ad
d
r
ess
in
g
b
o
th
lin
ea
r
an
d
n
o
n
-
lin
ea
r
asp
ec
ts
o
f
tim
e
s
er
ies
d
ata.
Dey
et
a
l.
[
1
1
]
d
ev
el
o
p
ed
a
h
y
b
r
id
C
NN
-
L
STM
an
d
in
ter
n
et
o
f
th
i
n
g
s
(
I
o
T
)
-
b
ased
s
y
s
tem
f
o
r
m
o
n
ito
r
in
g
a
n
d
p
r
ed
ictin
g
co
al
m
in
e
h
az
ar
d
s
.
T
h
eir
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
ap
p
licab
ili
ty
o
f
h
y
b
r
id
m
o
d
els
in
s
af
ety
-
cr
itical
en
v
i
r
o
n
m
e
n
ts
,
wh
er
e
ac
c
u
r
ate
an
d
tim
ely
f
o
r
ec
asts
ar
e
ess
en
tial
f
o
r
p
r
e
v
e
n
tin
g
ac
cid
e
n
ts
an
d
en
s
u
r
in
g
o
p
er
atio
n
al
ef
f
icien
c
y
.
T
h
e
liter
atu
r
e
in
d
icate
s
a
cl
ea
r
tr
en
d
to
war
d
s
th
e
I
o
f
m
a
ch
in
e
lear
n
i
n
g
with
tr
ad
itio
n
al
s
tatis
tical
m
o
d
els
in
tim
e
s
er
ies
f
o
r
ec
asti
n
g
.
T
h
ese
h
y
b
r
id
ap
p
r
o
ac
h
es
lev
e
r
a
g
e
th
e
s
tr
en
g
th
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
97
0
-
1
9
79
1972
b
o
th
m
eth
o
d
o
lo
g
ies,
o
f
f
e
r
in
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
ac
cu
r
ate
f
o
r
ec
asti
n
g
f
r
am
ewo
r
k
.
B
y
ad
d
r
ess
in
g
th
e
lim
itatio
n
s
o
f
s
tan
d
alo
n
e
AR
I
MA
m
o
d
els,
s
u
ch
as
th
eir
in
ab
ilit
y
to
ca
p
tu
r
e
n
o
n
-
lin
ea
r
p
atter
n
s
an
d
th
eir
s
en
s
itiv
ity
to
p
ar
am
eter
s
elec
tio
n
,
h
y
b
r
id
m
o
d
els p
r
o
v
id
e
a
r
o
b
u
s
t so
lu
tio
n
f
o
r
m
o
d
er
n
tim
e
s
er
ies an
aly
s
is
.
3.
M
E
T
H
O
D
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
h
y
b
r
id
AR
I
MA
-
m
ac
h
in
e
lear
n
in
g
m
o
d
el
to
e
n
h
an
ce
th
e
ac
c
u
r
ac
y
an
d
r
o
b
u
s
tn
ess
o
f
tim
e
s
er
ies
f
o
r
e
ca
s
tin
g
.
Sp
ec
if
ically
,
we
ex
p
l
o
r
e
th
e
I
o
f
AR
I
MA
with
L
STM
n
etwo
r
k
s
a
n
d
GB
M.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
els,
AR
I
MA
-
L
STM
an
d
AR
I
MA
-
G
B
M,
lev
er
ag
e
th
e
s
tr
en
g
th
s
o
f
b
o
th
tr
ad
itio
n
al
s
tatis
tical
m
eth
o
d
s
an
d
m
o
d
er
n
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
to
ca
p
tu
r
e
b
o
th
li
n
ea
r
an
d
n
o
n
-
lin
ea
r
p
atter
n
s
in
tim
e
s
er
ies
d
ata.
W
e
em
p
lo
y
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
s
u
ch
as
XGBo
o
s
t
r
e
g
r
ess
o
r
,
L
ass
o
,
an
d
R
id
g
e
f
o
r
in
itial p
r
e
d
ictio
n
s
,
f
o
llo
wed
b
y
tim
e
s
er
ies m
o
d
els lik
e
AR
I
MA
an
d
VAR f
o
r
r
ef
in
ed
f
o
r
ec
asti
n
g
.
3
.
1
.
ARIM
A
-
L
S
T
M
m
o
del
T
h
e
AR
I
MA
-
L
STM
m
o
d
el
co
m
b
in
es th
e
lin
ea
r
m
o
d
elin
g
ca
p
ab
ilit
ies o
f
AR
I
MA
with
th
e
n
o
n
-
lin
ea
r
p
atter
n
r
ec
o
g
n
itio
n
s
tr
en
g
th
s
o
f
L
STM
n
etwo
r
k
s
.
T
h
e
p
r
o
c
ess
in
v
o
lv
es
two
m
ain
s
tag
es:
m
o
d
elin
g
th
e
lin
ea
r
co
m
p
o
n
en
t u
s
in
g
AR
I
MA
an
d
ca
p
tu
r
in
g
th
e
n
o
n
-
lin
ea
r
r
esid
u
als with
L
STM
.
1.
Mo
d
elin
g
th
e
lin
ea
r
co
m
p
o
n
e
n
t
with
AR
I
MA
:
−
I
d
en
tific
atio
n
:
th
e
f
ir
s
t
s
tep
in
v
o
lv
es
id
en
tify
in
g
th
e
a
p
p
r
o
p
r
iate
p
ar
am
eter
s
(
p
,
d
,
q
)
(
p
,
d
,
q
)
(
p
,
d
,
q
)
f
o
r
th
e
AR
I
MA
m
o
d
el.
T
h
is
is
ac
h
iev
ed
b
y
an
aly
zin
g
th
e
a
u
to
co
r
r
elatio
n
f
u
n
ctio
n
(
AC
F)
an
d
p
ar
tial
au
to
co
r
r
elatio
n
f
u
n
ctio
n
(
PAC
F)
p
lo
ts
.
T
h
e
AC
F
an
d
PAC
F
h
elp
in
d
eter
m
in
in
g
t
h
e
o
r
d
er
o
f
th
e
AR
an
d
MA
co
m
p
o
n
e
n
ts
,
wh
ile
th
e
d
if
f
er
en
cin
g
p
ar
am
eter
d
d
d
is
ch
o
s
en
to
m
ak
e
t
h
e
s
er
ies s
tatio
n
ar
y
.
−
E
s
tim
atio
n
:
on
ce
th
e
p
ar
am
et
er
s
ar
e
id
en
tifie
d
,
th
e
AR
I
M
A
m
o
d
el
is
f
itted
to
th
e
tim
e
s
er
ies
d
ata.
T
h
e
m
o
d
el
is
f
o
r
m
u
lated
as f
o
llo
w
s
:
=
1
−
1
+
2
−
2
…
…
+
−
+
ϵ
−
θ
1
ϵ
−
1
−
θ
2
ϵ
−
2
…
…
…
θ
ϵ
−
wh
er
e
is
th
e
ac
tu
al
v
alu
e
at
tim
e
t,
ar
e
th
e
co
ef
f
icien
ts
o
f
th
e
AR
ter
m
s
,
θ
ar
e
th
e
co
ef
f
icien
ts
o
f
th
e
MA
ter
m
s
,
an
d
ϵ
is
th
e
er
r
o
r
ter
m
.
−
Diag
n
o
s
tic
ch
ec
k
in
g
:
a
f
ter
f
i
ttin
g
th
e
AR
I
MA
m
o
d
el,
d
iag
n
o
s
tic
ch
ec
k
s
ar
e
p
er
f
o
r
m
e
d
to
en
s
u
r
e
th
e
r
esid
u
als
ar
e
wh
ite
n
o
is
e.
T
h
is
in
v
o
lv
es
ex
am
in
in
g
th
e
r
e
s
id
u
als
f
o
r
an
y
a
u
to
co
r
r
elatio
n
an
d
c
h
ec
k
in
g
th
eir
n
o
r
m
ality
u
s
in
g
th
e
L
ju
n
g
-
B
o
x
test
.
2.
Mo
d
elin
g
th
e
non
-
lin
ea
r
r
esid
u
als
with
L
STM
:
−
R
esid
u
al
ex
tr
ac
tio
n
:
th
e
r
esid
u
als
ϵ
t
\
ep
s
ilo
n
_
tϵ
t
f
r
o
m
t
h
e
AR
I
MA
m
o
d
el,
wh
ich
r
ep
r
esen
t
th
e
p
o
r
tio
n
o
f
th
e
d
ata
n
o
t
ex
p
lai
n
ed
b
y
th
e
lin
ea
r
m
o
d
el,
ar
e
e
x
tr
ac
ted
.
T
h
ese
r
esid
u
als
ar
e
th
en
u
s
ed
as
t
h
e
in
p
u
t f
o
r
th
e
L
STM
n
etwo
r
k
.
−
L
STM
n
etwo
r
k
co
n
f
ig
u
r
atio
n
:
th
e
L
STM
n
etwo
r
k
is
co
n
f
i
g
u
r
ed
with
an
ap
p
r
o
p
r
iate
n
u
m
b
er
o
f
lay
e
r
s
an
d
u
n
its
to
ca
p
tu
r
e
t
h
e
tem
p
o
r
al
d
ep
en
d
en
cies in
th
e
r
esid
u
als.
T
h
e
L
STM
m
o
d
el
is
d
e
f
in
ed
a
s
(
1
)
:
=
(
⋅
[
ℎ
−
1
,
]
+
)
=
(
⋅
[
ℎ
−
1
,
]
+
)
=
(
⋅
[
ℎ
−
1
,
]
+
)
=
(
⋅
[
ℎ
−
1
,
]
+
)
=
∗
+
∗
̈
ℎ
=
∗
ta
n
h
(
}
(
1
)
wh
er
e
,
,
,
ar
e
th
e
in
p
u
t,
f
o
r
g
et,
an
d
o
u
tp
u
t
g
ates,
r
esp
ec
tiv
ely
,
is
th
e
ce
ll
s
tate,
an
d
ℎ
is
th
e
h
id
d
e
n
s
tate.
−
T
r
ain
in
g
t
h
e
L
STM
:
t
h
e
L
ST
M
n
etwo
r
k
is
tr
ain
e
d
o
n
th
e
r
esid
u
als
u
s
in
g
a
s
u
itab
le
lo
s
s
f
u
n
ctio
n
(
e.
g
.
,
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
)
a
n
d
an
o
p
tim
izer
(
e.
g
.
,
Ad
am
)
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
in
v
o
l
v
es b
ac
k
p
r
o
p
ag
atio
n
th
r
o
u
g
h
tim
e
(
B
PTT
)
to
u
p
d
at
e
th
e
n
etwo
r
k
weig
h
ts
.
3
.
2
.
ARIM
A
-
G
B
M
m
o
del
T
h
e
AR
I
MA
-
GB
M
m
o
d
el
i
n
teg
r
ates
th
e
lin
ea
r
AR
I
MA
m
o
d
el
with
th
e
p
o
wer
f
u
l
en
s
em
b
le
lear
n
in
g
ca
p
ab
ilit
ies
o
f
GB
M.
T
h
e
GB
M
alg
o
r
ith
m
en
h
an
ce
s
th
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
y
c
o
m
b
i
n
in
g
m
u
ltip
le
wea
k
lear
n
er
s
to
f
o
r
m
a
s
tr
o
n
g
p
r
ed
i
ctiv
e
m
o
d
el.
Mo
d
elin
g
th
e
lin
ea
r
co
m
p
o
n
e
n
t
with
AR
I
MA
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ce
d
time
s
eries
fo
r
ec
a
s
t
in
g
u
s
in
g
h
yb
r
id
A
R
I
MA
a
n
d
ma
ch
in
e
lea
r
n
in
g
…
(
V
ig
n
esh
A
r
u
mu
g
a
m
)
1973
T
h
e
AR
I
MA
m
o
d
elin
g
p
r
o
c
ess
i
s
id
en
tical
to
th
at
d
esc
r
ib
ed
f
o
r
th
e
AR
I
MA
-
L
STM
m
o
d
el,
in
v
o
lv
in
g
id
en
tific
atio
n
,
esti
m
atio
n
,
an
d
d
iag
n
o
s
tic
ch
ec
k
in
g
.
Mo
d
elin
g
th
e
n
o
n
-
lin
ea
r
r
esid
u
als
with
GB
M:
−
R
esid
u
al
ex
tr
ac
tio
n
:
th
e
r
esid
u
als
ϵt
\
ep
s
ilo
n
_
tϵ
t
f
r
o
m
t
h
e
AR
I
MA
m
o
d
el
ar
e
u
s
ed
as
th
e
in
p
u
t
f
o
r
th
e
GB
M.
−
GB
M
co
n
f
ig
u
r
atio
n
:
th
e
GB
M
is
co
n
f
ig
u
r
ed
with
a
s
u
itab
l
e
n
u
m
b
er
o
f
tr
ee
s
,
lear
n
in
g
r
ate,
an
d
m
ax
im
u
m
d
ep
th
.
T
h
ese
h
y
p
er
p
ar
am
eter
s
ar
e
tu
n
ed
u
s
in
g
cr
o
s
s
-
v
alid
at
io
n
to
p
r
e
v
en
t
o
v
er
f
itti
n
g
a
n
d
en
s
u
r
e
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
.
T
h
e
GB
M
m
o
d
e
l is f
o
r
m
u
lated
as
(
2
)
:
(
)
=
−
1
(
)
+
γ
ℎ
(
)
(
)
(
2
)
wh
er
e
(
)
is
th
e
m
o
d
el
p
r
ed
ictio
n
at
iter
atio
n
m
m
m
,
ℎ
(
)
is
th
e
wea
k
lear
n
er
(
d
ec
is
io
n
tr
ee
)
ad
d
ed
at
iter
atio
n
m
,
an
d
γ
is
th
e
lear
n
in
g
r
ate.
Data
p
r
ep
r
o
ce
s
s
in
g
in
v
o
lv
es
c
lean
in
g
a
n
d
tr
an
s
f
o
r
m
in
g
th
e
r
aw
d
ata
to
m
ak
e
it
s
u
itab
le
f
o
r
an
aly
s
is
.
T
h
e
s
tep
s
in
clu
d
e
h
a
n
d
lin
g
m
is
s
in
g
v
alu
es,
n
o
r
m
alizin
g
th
e
d
ata,
an
d
c
r
ea
tin
g
n
ew
f
ea
tu
r
e
s
.
1.
Han
d
lin
g
m
is
s
in
g
v
alu
es:
m
is
s
in
g
v
alu
es
in
th
e
tem
p
er
atu
r
e
an
d
en
er
g
y
c
o
n
s
u
m
p
tio
n
d
a
ta
ar
e
im
p
u
ted
u
s
in
g
lin
ea
r
in
ter
p
o
latio
n
.
2.
No
r
m
aliza
tio
n
:
t
h
e
d
ata
is
n
o
r
m
alize
d
to
a
co
m
m
o
n
s
ca
le
to
en
s
u
r
e
u
n
if
o
r
m
ity
an
d
f
ac
ilit
ate
m
o
d
el
tr
ain
in
g
.
T
h
is
is
d
o
n
e
u
s
in
g
m
in
-
m
ax
s
ca
lin
g
:
′
=
−
−
(
3
)
wh
er
e
x
is
th
e
o
r
ig
in
al
v
alu
e,
an
d
ar
e
th
e
m
in
im
u
m
an
d
m
ax
im
u
m
v
alu
es
in
th
e
d
ataset,
an
d
x
′
is
th
e
n
o
r
m
alize
d
v
alu
e.
3.
Featu
r
e
en
g
in
ee
r
in
g
:
f
ea
tu
r
e
en
g
in
ee
r
in
g
in
v
o
lv
es
cr
ea
tin
g
n
ew
f
ea
tu
r
es
to
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
.
Fo
r
in
s
tan
ce
,
we
d
er
iv
e
av
er
a
g
e
tem
p
er
atu
r
e
f
r
o
m
m
in
im
u
m
an
d
m
ax
im
u
m
tem
p
e
r
atu
r
es:
_
=
_
+
_
2
2
(
4
)
Ma
ch
in
e
lear
n
in
g
m
o
d
els
:
1.
XGBo
o
s
t
r
eg
r
ess
o
r
:
XGBo
o
s
t
is
an
en
s
em
b
le
lear
n
i
n
g
m
eth
o
d
k
n
o
wn
f
o
r
its
ef
f
icien
c
y
an
d
ef
f
ec
tiv
en
ess
in
r
eg
r
ess
io
n
task
s
.
T
h
e
m
o
d
el
is
tr
ain
ed
to
p
r
e
d
ict
en
e
r
g
y
co
n
s
u
m
p
tio
n
b
ased
o
n
tem
p
er
atu
r
e
d
ata
a
n
d
o
th
er
f
ea
tu
r
es e
x
tr
ac
ted
d
u
r
in
g
p
r
ep
r
o
ce
s
s
in
g
.
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
f
o
r
XGBo
o
s
t c
an
b
e
wr
itten
as:
(
)
=
∑
(
=
1
−
̈
)
+
∑
Ω
(
f
(
k
)
=
1
(
5
)
wh
er
e
l is th
e
lo
s
s
f
u
n
ctio
n
(
e.
g
.
,
MSE
)
,
an
d
Ω
is
th
e
r
e
g
u
lar
izatio
n
ter
m
to
c
o
n
tr
o
l m
o
d
el
co
m
p
lex
ity
.
2.
L
ass
o
r
eg
r
ess
io
n
:
lass
o
r
eg
r
ess
io
n
p
er
f
o
r
m
s
b
o
th
v
ar
iab
le
s
elec
tio
n
an
d
r
eg
u
lar
izati
o
n
to
en
h
a
n
ce
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
T
h
e
L
ass
o
o
b
jectiv
e
f
u
n
ctio
n
is
:
min
β
(
1
2
∑
(
−
β
)
2
=
1
)
+
λ
∑
β
=
1
(
6
)
wh
er
e
λ
is
th
e
r
eg
u
lar
izatio
n
p
ar
am
eter
.
3.
R
id
g
e
r
eg
r
ess
io
n
:
r
id
g
e
r
eg
r
e
s
s
io
n
also
ad
d
s
a
r
eg
u
lar
izatio
n
ter
m
b
u
t
u
s
es
th
e
L
2
n
o
r
m
.
I
ts
o
b
jectiv
e
f
u
n
ctio
n
is
:
min
β
(
1
2
∑
(
−
β
)
2
=
1
)
+
λ
∑
β
2
=
1
(
7
)
T
im
e
s
er
ies m
o
d
els
:
Af
ter
in
itial
p
r
ed
ictio
n
s
u
s
in
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
we
em
p
lo
y
tim
e
s
er
ies
m
o
d
els
to
ca
p
tu
r
e
tem
p
o
r
al
d
ep
en
d
e
n
cies a
n
d
r
e
f
in
e
th
e
f
o
r
ec
asts
.
1.
AR
I
MA
:
A
R
I
MA
is
a
p
o
p
u
la
r
tim
e
s
er
ies
f
o
r
ec
asti
n
g
tech
n
iq
u
e
th
at
co
m
b
in
es
AR
an
d
MA
co
m
p
o
n
en
ts
with
d
if
f
er
en
cin
g
to
ac
h
iev
e
s
tatio
n
ar
ity
.
T
h
e
AR
I
MA
m
o
d
el
is
d
ef
in
ed
as:
=
+
1
−
1
+
2
−
2
+
⋯
+
−
+
+
1
−
1
+
2
−
2
+
⋯
+
−
(
8
)
wh
er
e
is
th
e
v
alu
e
at
tim
e
t,
ϕ
an
d
θ
a
r
e
th
e
co
e
f
f
icien
ts
,
an
d
ϵ
t
is
th
e
er
r
o
r
ter
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
97
0
-
1
9
79
1974
2.
VAR
(
v
ec
to
r
au
to
r
eg
r
ess
iv
e
m
o
d
el
)
:
VAR
is
a
m
u
ltiv
ar
iate
tim
e
s
er
ie
s
m
o
d
el
th
at
ca
p
tu
r
es
th
e
lin
ea
r
in
ter
d
ep
en
d
en
cies a
m
o
n
g
m
u
lt
ip
le
tim
e
s
er
ies.
T
h
e
VAR m
o
d
el
f
o
r
a
two
-
v
ar
ia
b
le
ca
s
e
is
:
1
,
=
1
+
11
,
1
1
,
−
1
+
12
,
1
2
,
−
1
+
1
,
(
9
)
2
,
=
2
+
21
,
1
1
,
−
1
+
22
,
1
2
,
−
1
+
2
,
(
1
0
)
wh
er
e
1
,
an
d
2
,
t
ar
e
th
e
tim
e
s
er
ies
v
ar
iab
les,
c
ar
e
th
e
co
n
s
ta
n
ts
,
ϕ
ar
e
th
e
co
ef
f
icien
ts
,
an
d
ϵ
is
th
e
er
r
o
r
ter
m
.
Mo
d
el
e
v
alu
atio
n
:
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
ea
c
h
m
o
d
el
is
ev
alu
ated
u
s
in
g
s
tan
d
ar
d
m
etr
ics:
−
MSE
:
=
1
∑
(
=
1
−
̂
̈
)
2
(
1
1
)
MSE
ca
lcu
lates
th
e
av
er
a
g
e
s
q
u
ar
ed
d
if
f
e
r
en
ce
b
etwe
en
p
r
e
d
icted
v
alu
es
an
d
ac
tu
al
v
alu
es
(
̂
)
.
I
t
p
en
alize
s
lar
g
er
er
r
o
r
s
m
o
r
e
h
ea
v
ily
d
u
e
to
s
q
u
ar
in
g
ea
ch
d
if
f
e
r
en
ce
.
L
o
wer
MSE
v
alu
es
in
d
i
ca
te
b
etter
m
o
d
el
p
er
f
o
r
m
an
ce
.
MSE
q
u
an
tifie
s
th
e
ac
cu
r
ac
y
o
f
p
r
e
d
ictio
n
s
m
ad
e
b
y
ea
ch
m
o
d
el
(
XGBo
o
s
t
r
eg
r
ess
o
r
,
L
ass
o
,
R
id
g
e,
AR
I
MA
-
L
STM
,
AR
I
MA
-
GB
M)
f
o
r
p
ea
k
e
n
er
g
y
d
em
an
d
.
M
o
d
els
with
lo
wer
MSE
ar
e
co
n
s
id
er
ed
m
o
r
e
ac
cu
r
ate
in
f
o
r
ec
asti
n
g
e
n
er
g
y
c
o
n
s
u
m
p
ti
o
n
p
atter
n
s
.
−
R
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
M
SE)
:
R
M
SE
=
√
1
∑
(
=
1
−
̈
)
2
(
1
2
)
R
MSE
is
th
e
s
q
u
ar
e
r
o
o
t
o
f
MSE
,
p
r
o
v
id
in
g
a
m
ea
s
u
r
e
o
f
th
e
av
er
ag
e
m
a
g
n
itu
d
e
o
f
er
r
o
r
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
v
al
u
es
in
th
e
s
am
e
u
n
its
as
th
e
o
r
ig
in
al
d
ata.
I
t
g
i
v
es
a
m
o
r
e
in
t
u
itiv
e
u
n
d
er
s
tan
d
in
g
o
f
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
er
r
o
r
s
.
R
MSE
ass
ess
es
th
e
o
v
er
all
d
ev
iatio
n
o
f
p
r
ed
icted
en
e
r
g
y
d
e
m
an
d
v
alu
es
f
r
o
m
ac
tu
al
o
b
s
er
v
atio
n
s
.
Mo
d
els
with
lo
wer
R
MSE
ar
e
p
r
ef
er
r
ed
as
th
ey
in
d
icate
clo
s
er
alig
n
m
en
t
b
etwe
en
p
r
e
d
icted
an
d
ac
tu
al
v
al
u
es.
−
Me
an
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
:
=
1
∑
|
−
̈
|
×
100
=
1
(
1
3
)
I
n
ev
alu
atin
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
ea
ch
m
o
d
el,
s
tan
d
a
r
d
m
etr
ics
s
u
ch
as
MSE
,
R
MS
E
,
an
d
MA
PE
ar
e
em
p
lo
y
ed
.
MSE
q
u
an
tifie
s
th
e
av
er
ag
e
s
q
u
a
r
ed
d
if
f
er
en
ce
b
etwe
en
p
r
ed
icte
d
(
y
^i
\
h
at{
y
}_
iy
^i)
an
d
ac
tu
al
(
y
iy
_
iy
i)
v
alu
es,
p
r
o
v
id
in
g
a
m
ea
s
u
r
e
o
f
o
v
e
r
all
m
o
d
el
ac
c
u
r
ac
y
.
R
MSE
,
d
er
iv
ed
f
r
o
m
MSE
,
r
ep
r
esen
ts
th
e
s
q
u
ar
e
r
o
o
t
o
f
t
h
e
av
er
a
g
e
s
q
u
ar
ed
d
if
f
e
r
en
ce
s
,
o
f
f
er
in
g
a
m
o
r
e
in
ter
p
r
etab
le
m
ea
s
u
r
e
i
n
t
h
e
o
r
ig
in
al
u
n
its
o
f
th
e
p
r
ed
icted
v
ar
ia
b
le.
MA
PE
ca
lcu
lates
th
e
av
er
ag
e
p
er
ce
n
tag
e
d
if
f
er
e
n
ce
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
v
alu
es
r
elativ
e
to
th
e
ac
tu
al
v
alu
es,
m
ak
in
g
it
p
ar
ticu
lar
ly
u
s
ef
u
l
f
o
r
ass
ess
in
g
p
r
ed
ictio
n
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
en
t
s
ca
les
an
d
m
ag
n
itu
d
es
o
f
d
ata.
T
h
ese
m
etr
ics
ar
e
cr
u
cial
in
co
m
p
ar
in
g
a
n
d
s
e
lectin
g
th
e
b
est
-
f
it
m
o
d
el
f
o
r
p
r
ed
ictin
g
p
ea
k
e
n
er
g
y
d
em
an
d
b
ased
o
n
h
is
to
r
ical
d
ata
an
d
tem
p
er
atu
r
e
v
ar
iab
les
f
r
o
m
T
am
il
Nad
u
.
B
y
s
y
s
tem
atica
lly
ev
alu
atin
g
th
ese
m
etr
ics,
th
e
s
tu
d
y
en
s
u
r
es
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
in
f
o
r
ec
asti
n
g
en
er
g
y
c
o
n
s
u
m
p
ti
o
n
p
atter
n
s
,
co
n
tr
ib
u
tin
g
to
ef
f
ec
tiv
e
en
er
g
y
m
an
ag
e
m
en
t stra
teg
ies in
th
e
r
eg
io
n
.
−
T
h
eil
’
s
U
-
s
tatis
tic
s
U
=
√
1
∑
(
̅
̅
̅
̅
=
1
−
̈
)
2
̈
2
1
∑
(
=
1
2
2
)
(
1
4
)
wh
er
e:
−
n
is
th
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
.
−
r
ep
r
esen
t th
e
o
b
s
er
v
ed
v
alu
e
f
o
r
th
e
i
-
th
d
ata
p
o
in
t.
−
̈
co
r
r
esp
o
n
d
s
to
th
e
p
r
ed
icted
v
alu
e.
−
y
ˉ
in
d
icate
s
m
ea
n
f
o
r
o
b
s
er
v
e
d
v
alu
es {
̈
}
I
n
th
e
s
tu
d
y
,
T
h
eil
’
s
U
-
s
tatis
tics
is
em
p
lo
y
ed
alo
n
g
s
id
e
o
th
er
m
etr
ics
lik
e
MSE
,
R
MSE
,
an
d
MA
PE
t
o
co
m
p
r
eh
e
n
s
iv
ely
ev
alu
ate
t
h
e
f
o
r
ec
ast ac
cu
r
ac
y
o
f
m
o
d
els s
u
ch
as ARIM
A
-
L
STM
an
d
A
R
I
MA
-
GB
M.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ce
d
time
s
eries
fo
r
ec
a
s
t
in
g
u
s
in
g
h
yb
r
id
A
R
I
MA
a
n
d
ma
ch
in
e
lea
r
n
in
g
…
(
V
ig
n
esh
A
r
u
mu
g
a
m
)
1975
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
m
eth
o
d
o
lo
g
y
o
f
th
is
r
es
ea
r
ch
in
v
o
lv
ed
d
e
v
elo
p
in
g
a
n
d
e
v
alu
atin
g
h
y
b
r
id
AR
I
M
A
-
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
p
r
ed
ictin
g
p
ea
k
en
er
g
y
d
em
an
d
.
T
h
e
h
y
b
r
id
m
o
d
els
co
m
b
in
e
th
e
s
tr
en
g
th
s
o
f
AR
I
MA
f
o
r
lin
ea
r
tim
e
s
er
ies
m
o
d
elin
g
an
d
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
(
L
STM
an
d
GB
M)
f
o
r
ca
p
tu
r
in
g
n
o
n
-
lin
ea
r
p
atter
n
s
in
th
e
d
ata.
T
h
e
p
r
o
ce
s
s
b
eg
an
with
d
ata
p
r
ep
r
o
c
ess
in
g
,
wh
ich
in
clu
d
ed
h
an
d
l
in
g
m
is
s
in
g
v
alu
es,
n
o
r
m
alizin
g
th
e
d
ata,
an
d
cr
ea
tin
g
ad
d
itio
n
al
f
ea
tu
r
es
s
u
ch
as
tem
p
er
atu
r
e
tr
en
d
s
.
T
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
(
XGBo
o
s
t
r
eg
r
ess
o
r
,
l
ass
o
,
an
d
r
id
g
e
)
wer
e
tr
ain
ed
u
s
in
g
a
tr
ain
i
n
g
s
et,
with
h
y
p
er
p
ar
am
eter
s
tu
n
ed
v
ia
cr
o
s
s
-
v
alid
atio
n
to
m
in
im
ize
th
e
v
alid
atio
n
er
r
o
r
.
R
esid
u
als
f
r
o
m
th
ese
m
o
d
els
wer
e
an
aly
ze
d
to
en
s
u
r
e
th
ey
f
o
llo
wed
a
wh
ite
n
o
is
e
p
atter
n
,
in
d
icatin
g
th
at
th
e
s
y
s
tem
atic
p
atter
n
s
in
th
e
d
a
ta
wer
e
ef
f
ec
tiv
ely
ca
p
tu
r
ed
.
T
h
e
r
esid
u
als
wer
e
th
e
n
u
s
ed
as
in
p
u
ts
f
o
r
th
e
AR
I
MA
an
d
VAR
m
o
d
els
to
ca
p
tu
r
e
an
y
r
em
ain
in
g
tem
p
o
r
al
d
e
p
en
d
e
n
cies.
T
h
e
m
o
d
els
wer
e
ev
alu
ated
u
s
in
g
MSE
,
R
MSE
,
MA
PE,
an
d
T
h
eil
’
s
U
-
s
tati
s
tics
to
co
m
p
ar
e
th
eir
p
e
r
f
o
r
m
an
ce
.
Vis
u
aliza
tio
n
s
,
in
clu
d
in
g
f
o
r
e
ca
s
t
s
u
m
m
ar
ies
an
d
alig
n
m
en
t
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
o
b
s
er
v
atio
n
s
,
wer
e
cr
ea
ted
to
illu
s
tr
ate
th
e
m
o
d
e
ls
’
p
r
ed
ictiv
e
ca
p
a
b
ilit
ies.
T
h
e
s
ev
en
s
ets
o
f
d
ata
u
s
ed
in
th
is
s
tu
d
y
co
r
r
esp
o
n
d
to
ea
ch
d
ay
o
f
th
e
wee
k
:
M
o
n
d
ay
,
T
u
esd
ay
,
W
ed
n
esd
a
y
,
T
h
u
r
s
d
ay
,
Fri
d
ay
,
Satu
r
d
ay
,
a
n
d
Su
n
d
ay
.
T
h
ese
d
ata
s
ets
wer
e
co
llected
f
r
o
m
a
m
ajo
r
m
etr
o
p
o
litan
en
e
r
g
y
p
r
o
v
id
er
’
s
h
is
to
r
ical
r
ec
o
r
d
,
s
p
an
n
in
g
o
v
er
a
p
er
i
o
d
o
f
f
iv
e
y
ea
r
s
.
T
h
e
d
ata
in
cl
u
d
e
d
etailed
h
o
u
r
ly
r
ec
o
r
d
s
o
f
en
er
g
y
c
o
n
s
u
m
p
tio
n
,
tem
p
er
atu
r
e,
h
u
m
id
ity
,
an
d
o
t
h
er
r
elev
a
n
t e
n
v
ir
o
n
m
en
tal
f
ac
to
r
s
.
I
m
p
o
r
ta
n
ce
o
f
d
ay
-
s
p
ec
if
ic
d
a
ta
:
t
h
e
d
ec
is
io
n
to
co
llect
an
d
an
aly
ze
d
ay
-
s
p
ec
if
ic
d
ata
is
d
r
iv
en
b
y
th
e
in
h
er
en
t
v
ar
iab
ilit
y
in
e
n
er
g
y
co
n
s
u
m
p
tio
n
p
atter
n
s
ac
r
o
s
s
d
if
f
er
en
t d
a
y
s
o
f
th
e
wee
k
.
F
o
r
ex
am
p
le:
−
W
ee
k
d
ay
s
(
Mo
n
d
ay
to
Frid
a
y
)
:
e
n
er
g
y
co
n
s
u
m
p
tio
n
p
att
er
n
s
ar
e
in
f
lu
en
ce
d
b
y
in
d
u
s
tr
ial
ac
tiv
itie
s
,
b
u
s
in
ess
o
p
er
atio
n
s
,
an
d
r
eg
u
lar
wo
r
k
s
ch
e
d
u
les.
−
W
ee
k
en
d
s
(
Satu
r
d
ay
an
d
Su
n
d
ay
)
:
c
o
n
s
u
m
p
tio
n
p
atter
n
s
d
if
f
er
d
u
e
to
r
ed
u
ce
d
in
d
u
s
tr
ial
ac
tiv
ity
an
d
ch
an
g
es in
r
esid
en
tial e
n
e
r
g
y
u
s
e,
o
f
ten
h
i
g
h
er
d
u
e
to
m
o
r
e
tim
e
s
p
en
t a
t h
o
m
e
T
ab
le
1
p
r
esen
ts
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
h
y
b
r
id
AR
I
MA
-
m
ac
h
in
e
lear
n
in
g
m
o
d
els
co
m
p
ar
ed
t
o
b
aselin
e
m
o
d
els
f
o
r
p
r
ed
icti
n
g
p
ea
k
e
n
er
g
y
d
e
m
an
d
f
o
r
ea
ch
d
ay
o
f
th
e
wee
k
.
Fi
g
u
r
e
1
p
r
o
v
i
d
es
a
co
m
p
r
eh
e
n
s
iv
e
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
am
o
n
g
d
if
f
er
e
n
t
m
o
d
els
em
p
lo
y
ed
in
th
is
r
esear
ch
f
o
r
p
r
ed
ictin
g
p
ea
k
en
er
g
y
d
em
a
n
d
.
E
ac
h
s
u
b
p
l
o
t
in
th
e
f
ig
u
r
e
co
r
r
esp
o
n
d
s
to
a
s
p
ec
if
ic
m
etr
ic:
MSE
,
R
M
SE,
MA
PE,
an
d
T
h
eil
’
s
U
-
s
tatis
ti
cs.
T
h
ese
m
etr
ics
ar
e
cr
u
cial
f
o
r
ass
ess
in
g
th
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
th
e
f
o
r
ec
asti
n
g
m
o
d
els u
s
ed
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
AR
I
MA
m
o
d
el
M
o
d
e
l
M
e
t
r
i
c
M
o
n
d
a
y
Tu
e
s
d
a
y
W
e
d
n
e
s
d
a
y
Th
u
r
sd
a
y
F
r
i
d
a
y
S
a
t
u
r
d
a
y
S
u
n
d
a
y
X
G
B
o
o
st
r
e
g
r
e
sso
r
M
S
E
0
.
0
2
0
0
.
0
2
3
0
.
0
2
4
0
.
0
2
5
0
.
0
2
6
0
.
0
2
2
0
.
0
2
1
R
M
S
E
0
.
1
4
1
0
.
1
5
2
0
.
1
5
5
0
.
1
5
8
0
.
1
6
1
0
.
1
4
8
0
.
1
4
5
M
A
P
E
2
.
9
0
%
3
.
1
0
%
3
.
1
2
%
3
.
2
0
%
3
.
2
5
%
3
.
0
5
%
3
.
0
0
%
Th
e
i
l
’
s U
-
s
t
a
t
i
s
t
i
c
s
0
.
1
4
0
.
1
5
0
.
1
5
0
.
1
6
0
.
1
6
0
.
1
4
0
.
1
4
La
sso
r
e
g
r
e
ssi
o
n
M
S
E
0
.
0
2
9
0
.
0
3
0
0
.
0
3
1
0
.
0
3
2
0
.
0
3
3
0
.
0
3
0
0
.
0
2
9
R
M
S
E
0
.
1
7
0
0
.
1
7
3
0
.
1
7
6
0
.
1
7
9
0
.
1
8
2
0
.
1
7
3
0
.
1
7
0
M
A
P
E
4
.
1
0
%
4
.
5
0
%
4
.
5
8
%
4
.
6
0
%
4
.
6
5
%
4
.
5
5
%
4
.
5
0
%
Th
e
i
l
’
s U
-
s
t
a
t
i
s
t
i
c
s
0
.
1
8
0
.
1
9
0
.
1
9
0
.
1
9
0
.
2
0
0
.
1
9
0
.
1
8
R
i
d
g
e
r
e
g
r
e
ss
i
o
n
M
S
E
0
.
0
2
7
0
.
0
2
8
0
.
0
2
9
0
.
0
3
0
0
.
0
3
1
0
.
0
2
8
0
.
0
2
7
R
M
S
E
0
.
1
6
4
0
.
1
6
7
0
.
1
7
0
0
.
1
7
3
0
.
1
7
6
0
.
1
6
7
0
.
1
6
4
M
A
P
E
4
.
0
0
%
4
.
1
0
%
4
.
2
0
%
4
.
3
0
%
4
.
3
5
%
4
.
2
5
%
4
.
2
0
%
Th
e
i
l
’
s U
-
s
t
a
t
i
s
t
i
c
s
0
.
1
7
0
.
1
7
0
.
1
8
0
.
1
8
0
.
1
9
0
.
1
7
0
.
1
7
A
R
I
M
A
-
LSTM
M
S
E
0
.
0
1
5
0
.
0
1
7
0
.
0
1
8
0
.
0
1
9
0
.
0
2
0
0
.
0
1
7
0
.
0
1
6
R
M
S
E
0
.
1
2
2
0
.
1
3
0
0
.
1
3
4
0
.
1
3
8
0
.
1
4
1
0
.
1
3
0
0
.
1
2
6
M
A
P
E
2
.
7
0
%
2
.
8
0
%
2
.
8
5
%
2
.
9
0
%
3
.
0
0
%
2
.
8
0
%
2
.
7
5
%
Th
e
i
l
’
s U
-
s
t
a
t
i
s
t
i
c
s
0
.
1
1
0
.
1
2
0
.
1
2
0
.
1
2
0
.
1
3
0
.
1
2
0
.
1
1
A
R
I
M
A
-
G
B
M
M
S
E
0
.
0
1
8
0
.
0
2
0
0
.
0
2
1
0
.
0
2
2
0
.
0
2
3
0
.
0
2
0
0
.
0
1
9
R
M
S
E
0
.
1
3
4
0
.
1
4
1
0
.
1
4
5
0
.
1
4
8
0
.
1
5
2
0
.
1
4
1
0
.
1
3
8
M
A
P
E
2
.
9
0
%
2
.
9
5
%
3
.
0
1
%
3
.
1
0
%
3
.
1
5
%
2
.
9
5
%
2
.
9
0
%
Th
e
i
l
’
s U
-
s
t
a
t
i
s
t
i
c
s
0
.
1
3
0
.
1
3
0
.
1
4
0
.
1
4
0
.
1
4
0
.
1
3
0
.
1
3
Fig
u
r
e
1
illu
s
tr
ates
th
e
co
m
p
a
r
ativ
e
p
er
f
o
r
m
a
n
ce
o
f
v
a
r
io
u
s
r
eg
r
ess
io
n
m
o
d
els
(
XGBo
o
s
t
r
eg
r
ess
o
r
,
lass
o
r
eg
r
ess
io
n
,
r
id
g
e
r
eg
r
ess
io
n
,
AR
I
MA
-
L
STM
,
an
d
AR
I
MA
-
GB
M)
ac
r
o
s
s
s
ev
en
d
ay
s
,
u
s
in
g
m
etr
ics s
u
ch
as
MSE
,
R
MSE
,
MA
PE,
an
d
T
h
eil’
s
U
-
s
tatis
tics
.
T
h
e
AR
I
MA
-
L
STM
m
o
d
el
co
n
s
is
ten
tly
s
h
o
ws
th
e
lo
west
MSE
an
d
MA
PE
v
alu
es,
h
i
g
h
lig
h
tin
g
its
s
u
p
er
io
r
ac
cu
r
ac
y
an
d
f
o
r
ec
asti
n
g
e
f
f
icien
cy
co
m
p
ar
ed
to
o
th
er
m
o
d
els
o
v
er
t
h
e
o
b
s
er
v
e
d
p
e
r
io
d
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
co
m
p
ar
is
o
n
b
etwe
en
t
h
e
ac
tu
al
en
er
g
y
d
em
an
d
an
d
th
e
p
r
ed
icted
v
alu
es
g
en
e
r
ated
b
y
th
e
AR
I
MA
-
L
STM
m
o
d
el
o
v
er
a
s
p
ec
if
ied
p
e
r
io
d
.
T
h
e
g
r
ee
n
lin
e
r
ep
r
esen
ts
th
e
ac
tu
al
o
b
s
er
v
ed
en
er
g
y
d
em
an
d
,
w
h
ile
th
e
b
lu
e
d
ash
ed
lin
e
d
en
o
tes
th
e
f
o
r
e
ca
s
ted
v
alu
es
f
r
o
m
th
e
AR
I
MA
-
L
STM
m
o
d
el.
T
h
e
clo
s
e
alig
n
m
en
t
b
etwe
en
th
e
two
lin
es
s
u
g
g
ests
th
at
t
h
e
AR
I
MA
-
L
STM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
97
0
-
1
9
79
1976
m
o
d
el
is
h
ig
h
ly
e
f
f
ec
tiv
e
in
c
ap
tu
r
in
g
b
o
t
h
lin
ea
r
an
d
n
o
n
-
l
in
ea
r
p
atter
n
s
i
n
th
e
d
ata.
T
h
i
s
in
d
icate
s
th
at
th
e
m
o
d
el
h
as
s
u
cc
ess
f
u
lly
lev
er
ag
ed
th
e
s
tr
en
g
th
s
o
f
b
o
th
AR
I
MA
an
d
L
STM
co
m
p
o
n
en
ts
,
with
AR
I
MA
ca
p
tu
r
in
g
s
h
o
r
t
-
ter
m
tr
en
d
s
an
d
L
STM
lear
n
in
g
lo
n
g
-
ter
m
d
ep
en
d
en
cies.
T
h
e
m
in
im
al
d
e
v
iatio
n
b
etwe
en
th
e
ac
tu
al
an
d
p
r
ed
icted
v
alu
es
u
n
d
er
s
co
r
es
th
e
m
o
d
el’
s
r
o
b
u
s
tn
ess
an
d
ac
cu
r
ac
y
in
f
o
r
e
ca
s
tin
g
p
ea
k
e
n
er
g
y
d
em
an
d
.
Fig
u
r
e
1
.
C
o
m
p
a
r
is
o
n
with
b
a
s
elin
e
m
o
d
els
T
h
ese
m
etr
ics
co
llectiv
ely
h
ig
h
lig
h
t
th
e
AR
I
MA
-
L
STM
m
o
d
el
’
s
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
in
p
r
o
v
id
i
n
g
p
r
ec
is
e
an
d
r
eliab
le
f
o
r
ec
asts
.
Fig
u
r
e
2
p
r
esen
ts
th
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
ac
tu
al
en
er
g
y
d
em
an
d
an
d
th
e
p
r
ed
icted
v
alu
es g
en
er
ated
b
y
th
e
AR
I
MA
-
GB
M
m
o
d
el.
T
h
e
g
r
ee
n
lin
e
r
ep
r
esen
ts
th
e
ac
t
u
al
o
b
s
er
v
e
d
e
n
er
g
y
d
em
an
d
,
w
h
ile
th
e
p
u
r
p
le
d
as
h
ed
lin
e
in
d
icate
s
th
e
f
o
r
ec
ast
ed
v
alu
es
f
r
o
m
th
e
AR
I
MA
-
GB
M
m
o
d
el.
Similar
to
Fig
u
r
e
1
,
th
e
AR
I
MA
-
GB
M
m
o
d
el
s
h
o
ws
a
s
tr
o
n
g
ca
p
ab
ilit
y
in
p
r
ed
ictin
g
e
n
er
g
y
d
em
an
d
with
a
clo
s
e
alig
n
m
en
t
b
etwe
en
th
e
ac
tu
al
an
d
f
o
r
ec
asted
v
alu
es.
Ho
wev
er
,
s
lig
h
t
d
ev
iatio
n
s
ca
n
b
e
o
b
s
er
v
ed
co
m
p
ar
e
d
to
th
e
AR
I
MA
-
L
STM
m
o
d
el,
s
u
g
g
esti
n
g
th
at
wh
ile
th
e
AR
I
M
A
-
GB
M
m
o
d
el
is
ef
f
ec
tiv
e,
it
m
ay
n
o
t c
ap
tu
r
e
th
e
d
ata
p
atter
n
s
as c
o
m
p
r
eh
en
s
iv
ely
as th
e
AR
I
MA
-
L
STM
m
o
d
el.
Fig
u
r
e
2
.
AR
I
MA
-
L
STM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ce
d
time
s
eries
fo
r
ec
a
s
t
in
g
u
s
in
g
h
yb
r
id
A
R
I
MA
a
n
d
ma
ch
in
e
lea
r
n
in
g
…
(
V
ig
n
esh
A
r
u
mu
g
a
m
)
1977
T
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
f
o
r
th
e
AR
I
MA
-
GB
M
m
o
d
el
is
s
h
o
wn
in
F
ig
u
r
e
3
.
T
h
ese
m
et
r
ics,
wh
ile
in
d
icatin
g
a
h
ig
h
lev
el
o
f
ac
c
u
r
ac
y
,
ar
e
s
lig
h
tly
less
o
p
tim
al
th
an
th
o
s
e
o
f
th
e
AR
I
MA
-
L
STM
m
o
d
el.
T
h
is
s
u
g
g
ests
th
at
th
e
AR
I
MA
-
G
B
M
m
o
d
el,
th
o
u
g
h
r
o
b
u
s
t,
m
ay
b
e
b
etter
s
u
ited
f
o
r
d
at
asets
wh
er
e
g
r
ad
ien
t
b
o
o
s
tin
g
tech
n
iq
u
es
ex
ce
l,
b
u
t
m
ig
h
t
n
o
t
ca
p
tu
r
e
th
e
s
am
e
d
ep
th
o
f
tem
p
o
r
al
d
ep
e
n
d
en
cies
as
th
e
L
STM
-
b
ased
ap
p
r
o
ac
h
.
Fig
u
r
e
3
.
AR
I
MA
-
GB
M
5.
CO
NCLU
SI
O
N
T
h
e
r
esear
ch
aim
ed
to
en
h
an
ce
tr
ad
itio
n
al
f
o
r
ec
asti
n
g
m
eth
o
d
s
b
y
in
teg
r
atin
g
AR
I
MA
with
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
s
u
ch
as
L
STM
an
d
GB
M.
T
h
r
o
u
g
h
r
i
g
o
r
o
u
s
ex
p
er
im
en
tatio
n
a
n
d
ev
alu
atio
n
u
s
in
g
co
m
p
r
eh
en
s
iv
e
m
etr
ics
lik
e
MSE
,
R
MSE
,
MA
PE,
an
d
T
h
eil
’
s
U
-
s
tatis
tics
,
th
e
s
tu
d
y
co
n
d
u
cte
d
a
th
o
r
o
u
g
h
c
o
m
p
ar
is
o
n
o
f
m
o
d
el
p
er
f
o
r
m
an
c
e.
T
h
e
co
m
p
ar
ativ
e
an
aly
s
is
am
o
n
g
XGBo
o
s
t
r
eg
r
ess
o
r
,
lass
o
r
eg
r
ess
io
n
,
r
i
d
g
e
r
eg
r
ess
io
n
,
AR
I
MA
-
L
STM
,
an
d
AR
I
MA
-
GB
M
h
ig
h
lig
h
ted
th
e
n
o
tab
le
s
u
p
er
io
r
ity
o
f
th
e
h
y
b
r
i
d
AR
I
MA
-
L
STM
m
o
d
el.
AR
I
MA
-
L
STM
co
n
s
is
ten
tly
ex
h
ib
ited
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
m
etr
ics,
d
em
o
n
s
tr
at
in
g
its
ab
ilit
y
to
ef
f
ec
tiv
ely
ca
p
tu
r
e
b
o
th
lin
ea
r
a
n
d
n
o
n
-
li
n
ea
r
p
atter
n
s
in
th
e
d
ata,
th
er
eb
y
e
n
h
an
ci
n
g
ac
cu
r
ac
y
in
p
r
ed
ictin
g
p
ea
k
en
e
r
g
y
d
em
an
d
.
T
h
e
I
o
f
L
STM
with
AR
I
MA
p
r
o
v
e
d
p
ar
ticu
lar
ly
ad
v
a
n
tag
eo
u
s
b
y
lev
er
a
g
in
g
L
STM
’
s
ca
p
a
b
ilit
y
to
lea
r
n
tem
p
o
r
al
d
e
p
en
d
en
cies
i
n
d
ata
s
eq
u
en
ce
s
.
T
h
is
r
esear
c
h
co
n
t
r
ib
u
tes
s
ig
n
if
ican
tly
to
a
d
v
an
cin
g
tim
e
s
er
ies
f
o
r
ec
asti
n
g
te
ch
n
iq
u
es
in
s
ev
er
al
cr
itical
asp
ec
ts
.
Firstl
y
,
it
ac
h
iev
es
im
p
r
o
v
ed
ac
cu
r
ac
y
i
n
p
ea
k
en
e
r
g
y
d
em
a
n
d
p
r
ed
ic
tio
n
co
m
p
ar
ed
to
s
tan
d
alo
n
e
AR
I
MA
m
o
d
els
an
d
o
th
er
b
aselin
e
ap
p
r
o
ac
h
es.
Seco
n
d
ly
,
th
e
h
y
b
r
i
d
m
o
d
els
d
em
o
n
s
tr
ated
r
o
b
u
s
tn
ess
in
h
a
n
d
lin
g
c
o
m
p
lex
d
ata
p
atter
n
s
an
d
v
ar
iatio
n
s
,
u
n
d
e
r
s
co
r
in
g
th
eir
s
u
itab
i
lity
f
o
r
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
wh
er
e
p
r
ec
is
e
an
d
r
eliab
le
f
o
r
ec
asts
ar
e
ess
en
ti
al.
L
astl
y
,
th
e
p
r
ac
tical
im
p
lic
atio
n
s
o
f
t
h
is
s
tu
d
y
p
r
o
v
id
e
v
alu
a
b
le
in
s
ig
h
ts
f
o
r
en
er
g
y
m
an
a
g
em
en
t
a
n
d
p
lan
n
in
g
,
en
ab
lin
g
s
tak
eh
o
ld
e
r
s
to
m
ak
e
in
f
o
r
m
e
d
d
ec
is
io
n
s
b
ased
o
n
d
ep
en
d
ab
l
e
f
o
r
ec
asts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
r
ec
eiv
ed
n
o
s
p
e
cif
ic
g
r
an
t
f
r
o
m
a
n
y
f
u
n
d
in
g
ag
en
cy
in
t
h
e
p
u
b
lic,
co
m
m
er
cial,
o
r
n
o
t
f
o
r
-
p
r
o
f
it secto
r
s
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Vig
n
esh
Ar
u
m
u
g
am
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Vijay
alak
s
h
m
i
Nata
r
ajan
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
97
0
-
1
9
79
1978
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
licts
o
f
in
ter
est r
e
g
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
u
s
ed
an
d
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
o
n
r
ea
s
o
n
a
b
le
r
eq
u
est
.
RE
F
E
R
E
NC
E
S
[
1
]
V
.
A
r
u
m
u
g
a
m
a
n
d
V
.
N
a
t
a
r
a
j
a
n
,
“
T
i
me
seri
e
s
mo
d
e
l
i
n
g
a
n
d
f
o
r
e
c
a
s
t
i
n
g
u
s
i
n
g
a
u
t
o
r
e
g
r
e
ss
i
v
e
i
n
t
e
g
r
a
t
e
d
m
o
v
i
n
g
a
v
e
r
a
g
e
a
n
d
sea
s
o
n
a
l
a
u
t
o
r
e
g
r
e
ss
i
v
e
i
n
t
e
g
r
a
t
e
d
m
o
v
i
n
g
a
v
e
r
a
g
e
mo
d
e
l
s,
”
I
n
s
t
ru
m
e
n
t
a
t
i
o
n
M
e
su
r
e
Me
t
r
o
l
o
g
i
e
,
v
o
l
.
2
2
,
n
o
.
4
,
p
p
.
1
6
1
–
1
6
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
8
2
8
0
/
i
2
m.
2
2
0
4
0
4
.
[
2
]
K
.
Li
,
W
.
H
u
a
n
g
,
G
.
H
u
,
a
n
d
J.
Li
,
“
U
l
t
r
a
-
s
h
o
r
t
t
e
r
m
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
b
a
se
d
o
n
C
EE
M
D
A
N
-
S
E
a
n
d
LS
TM
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
E
n
e
r
g
y
a
n
d
B
u
i
l
d
i
n
g
s
,
v
o
l
.
2
7
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
2
.
1
1
2
6
6
6
.
[
3
]
S
.
X
u
e
,
H
.
C
h
e
n
,
a
n
d
X
.
Zh
e
n
g
,
“
D
e
t
e
c
t
i
o
n
a
n
d
q
u
a
n
t
i
f
i
c
a
t
i
o
n
o
f
a
n
o
m
a
l
i
e
s
i
n
c
o
mm
u
n
i
c
a
t
i
o
n
n
e
t
w
o
r
k
s b
a
se
d
o
n
LS
TM
-
A
R
I
M
A
c
o
m
b
i
n
e
d
m
o
d
e
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
C
y
b
e
rn
e
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
0
,
p
p
.
3
1
5
9
–
3
1
7
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
0
4
2
-
022
-
0
1
5
8
6
-
8.
[
4
]
S
.
M
e
h
t
a
b
a
n
d
J
.
S
e
n
,
“
S
t
o
c
k
p
r
i
c
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
C
N
N
a
n
d
LST
M
-
b
a
s
e
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
c
i
si
o
n
A
i
d
S
c
i
e
n
c
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
(
D
A
S
A)
,
N
o
v
.
2
0
2
0
,
p
p
.
4
4
7
–
4
5
3
,
d
o
i
:
1
0
.
1
1
0
9
/
D
A
S
A
5
1
4
0
3
.
2
0
2
0
.
9
3
1
7
2
0
7
.
[
5
]
W
.
X
u
,
H
.
P
e
n
g
,
X
.
Z
e
n
g
,
F
.
Z
h
o
u
,
X
.
Ti
a
n
,
a
n
d
X
.
P
e
n
g
,
“
D
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
-
b
a
se
d
A
R
m
o
d
e
l
f
o
r
n
o
n
l
i
n
e
a
r
t
i
me
seri
e
s
f
o
r
e
c
a
st
i
n
g
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
7
,
p
p
.
6
0
5
–
6
2
1
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
1
9
.
0
2
.
0
0
6
.
[
6
]
N
.
Z
h
a
o
,
H
.
Z
h
a
n
g
,
X
.
Y
a
n
g
,
J.
Y
a
n
,
a
n
d
F
.
Y
o
u
,
“
Emer
g
i
n
g
i
n
f
o
r
ma
t
i
o
n
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
sm
a
r
t
e
n
e
r
g
y
sy
st
e
ms
a
n
d
r
e
n
e
w
a
b
l
e
t
r
a
n
s
i
t
i
o
n
,
”
A
d
v
a
n
c
e
s
i
n
A
p
p
l
i
e
d
En
e
r
g
y
,
v
o
l
.
9
,
p
.
1
0
0
1
2
5
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
a
p
e
n
.
2
0
2
3
.
1
0
0
1
2
5
.
[
7
]
S
.
S
a
l
e
t
i
,
L.
Y
.
P
a
n
c
h
u
mart
h
i
,
Y
.
R
.
K
a
l
l
a
m,
L.
P
a
r
c
h
u
r
i
,
a
n
d
S
.
Ji
t
t
e
,
“
E
n
h
a
n
c
i
n
g
f
o
r
e
c
a
s
t
i
n
g
a
c
c
u
r
a
c
y
w
i
t
h
a
mo
v
i
n
g
a
v
e
r
a
g
e
-
i
n
t
e
g
r
a
t
e
d
h
y
b
r
i
d
A
R
I
M
A
-
LST
M
M
o
d
e
l
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
6
,
p
.
7
0
4
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
024
-
0
3
0
6
0
-
4.
[
8
]
P
.
P
o
m
o
r
sk
i
a
n
d
D
.
G
o
r
se
,
“
I
mp
r
o
v
i
n
g
o
n
t
h
e
m
a
r
k
o
v
-
sw
i
t
c
h
i
n
g
r
e
g
r
e
ss
i
o
n
m
o
d
e
l
b
y
t
h
e
u
s
e
o
f
a
n
a
d
a
p
t
i
v
e
mo
v
i
n
g
a
v
e
r
a
g
e
,
”
i
n
S
p
ri
n
g
e
r
Pro
c
e
e
d
i
n
g
s
i
n
B
u
si
n
e
ss
a
n
d
Ec
o
n
o
m
i
c
s
,
2
0
2
3
,
p
p
.
1
7
–
3
0
.
[
9
]
R
.
P
e
l
e
g
,
R
.
W
e
i
ss
,
A
.
H
o
o
g
i
,
“
L
e
v
e
r
a
g
i
n
g
t
h
e
t
r
i
p
l
e
e
x
p
o
n
e
n
t
i
a
l
m
o
v
i
n
g
a
v
e
r
a
g
e
f
o
r
f
a
s
t
-
a
d
a
p
t
i
v
e
mo
men
t
e
st
i
ma
t
i
o
n
,
”
a
rXi
v
p
re
p
r
i
n
t
a
rXi
v
:
2
3
0
6
.
0
1
4
2
3
,
2
0
2
3
.
”
[
1
0
]
W
.
H
e
,
M
.
K
i
n
g
,
X
.
Lu
o
,
M
.
D
o
o
n
e
r
,
D
.
Li
,
a
n
d
J.
W
a
n
g
,
“
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
e
c
o
n
o
m
i
c
s
o
f
e
l
e
c
t
r
i
c
e
n
e
r
g
y
s
t
o
r
a
g
e
s
i
n
p
o
w
e
r
sy
st
e
ms:
R
e
v
i
e
w
a
n
d
p
e
r
sp
e
c
t
i
v
e
,
”
A
d
v
a
n
c
e
s
i
n
A
p
p
l
i
e
d
En
e
rg
y
,
v
o
l
.
4
,
p
.
1
0
0
0
6
0
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
a
p
e
n
.
2
0
2
1
.
1
0
0
0
6
0
.
[
1
1
]
P
.
D
e
y
,
S
.
K
.
C
h
a
u
l
y
a
,
a
n
d
S
.
K
u
m
a
r
,
“
H
y
b
r
i
d
C
N
N
-
LST
M
a
n
d
I
o
T
-
b
a
se
d
c
o
a
l
mi
n
e
h
a
z
a
r
d
s
m
o
n
i
t
o
r
i
n
g
a
n
d
p
r
e
d
i
c
t
i
o
n
sy
st
e
m,
”
Pro
c
e
ss
S
a
f
e
t
y
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
Pr
o
t
e
c
t
i
o
n
,
v
o
l
.
1
5
2
,
p
p
.
2
4
9
–
2
6
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
s
e
p
.
2
0
2
1
.
0
6
.
0
0
5
.
[
1
2
]
J.
-
S
.
C
h
o
u
a
n
d
D
.
-
S
.
Tr
a
n
,
“
F
o
r
e
c
a
st
i
n
g
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
t
i
m
e
seri
e
s
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
b
a
s
e
d
o
n
u
sa
g
e
p
a
t
t
e
r
n
s
o
f
r
e
s
i
d
e
n
t
i
a
l
h
o
u
se
h
o
l
d
e
r
s,
”
En
e
r
g
y
,
v
o
l
.
1
6
5
,
p
p
.
7
0
9
–
7
2
6
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
1
8
.
0
9
.
1
4
4
.
[
1
3
]
B
.
T
h
a
n
g
a
r
a
j
a
n
,
M
.
S
.
N
a
g
a
r
a
j
a
,
a
n
d
B
.
V
.
D
h
a
n
d
r
a
,
“
A
n
o
v
e
l
h
y
b
r
i
d
m
o
d
e
l
f
o
r
t
i
me
seri
e
s
f
o
r
e
c
a
st
i
n
g
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
a
u
t
o
r
e
g
r
e
ss
i
v
e
i
n
t
e
g
r
a
t
e
d
mo
v
i
n
g
a
v
e
r
a
g
e
m
o
d
e
l
s
,
”
i
n
T
re
n
d
s
i
n
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
P
a
r
t
F
2
3
5
7
,
2
0
2
4
,
p
p
.
7
4
7
–
7
5
4
.
[
1
4
]
J.
L
o
p
e
z
B
e
r
n
a
l
,
S
.
S
o
u
m
e
r
a
i
,
a
n
d
A
.
G
a
s
p
a
r
r
i
n
i
,
“
A
m
e
t
h
o
d
o
l
o
g
i
c
a
l
f
r
a
mew
o
r
k
f
o
r
m
o
d
e
l
se
l
e
c
t
i
o
n
i
n
i
n
t
e
r
r
u
p
t
e
d
t
i
me
seri
e
s
st
u
d
i
e
s,
”
J
o
u
rn
a
l
o
f
C
l
i
n
i
c
a
l
E
p
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
1
0
3
,
p
p
.
8
2
–
9
1
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
i
n
e
p
i
.
2
0
1
8
.
0
5
.
0
2
6
.
[
1
5
]
E.
B
e
a
r
d
e
t
a
l
.
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
a
n
d
u
si
n
g
t
i
me
ser
i
e
s
a
n
a
l
y
ses
i
n
a
d
d
i
c
t
i
o
n
r
e
sea
r
c
h
,
”
Ad
d
i
c
t
i
o
n
,
v
o
l
.
1
1
4
,
n
o
.
1
0
,
p
p
.
1
8
6
6
–
1
8
8
4
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
1
1
/
a
d
d
.
1
4
6
4
3
.
[
1
6
]
T.
Li
b
o
sc
h
i
k
,
K
.
F
o
k
i
a
n
o
s,
a
n
d
R
.
F
r
i
e
d
,
“
t
sc
o
u
n
t
:
a
n
R
p
a
c
k
a
g
e
f
o
r
a
n
a
l
y
si
s
o
f
c
o
u
n
t
t
i
m
e
ser
i
e
s
f
o
l
l
o
w
i
n
g
g
e
n
e
r
a
l
i
z
e
d
l
i
n
e
a
r
mo
d
e
l
s
,
”
J
o
u
r
n
a
l
o
f
S
t
a
t
i
st
i
c
a
l
S
o
f
t
w
a
re
,
v
o
l
.
8
2
,
n
o
.
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
8
6
3
7
/
j
ss.
v
0
8
2
.
i
0
5
.
[
1
7
]
P
.
L
o
m
b
a
r
d
,
L.
Jo
s
é
O
r
t
i
z
,
a
n
d
P
.
C
h
r
i
st
i
n
e
,
“
A
r
e
v
i
e
w
o
n
b
u
i
l
d
i
n
g
s
e
n
e
r
g
y
c
o
n
su
m
p
t
i
o
n
i
n
f
o
r
mat
i
o
n
,
”
En
e
r
g
y
a
n
d
b
u
i
l
d
i
n
g
s
,
p
p
.
3
9
4
–
3
9
8
,
2
0
0
8
.
[
1
8
]
C
.
A
g
h
e
m
o
,
L
.
B
l
a
so
,
a
n
d
A
.
P
e
l
l
e
g
r
i
n
o
,
“
B
u
i
l
d
i
n
g
a
u
t
o
ma
t
i
o
n
a
n
d
c
o
n
t
r
o
l
sy
s
t
e
ms
:
a
c
a
se
st
u
d
y
t
o
e
v
a
l
u
a
t
e
t
h
e
e
n
e
r
g
y
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
p
e
r
f
o
r
ma
n
c
e
s
o
f
a
l
i
g
h
t
i
n
g
c
o
n
t
r
o
l
s
y
s
t
e
m
i
n
o
f
f
i
c
e
s,
”
A
u
t
o
m
a
t
i
o
n
i
n
C
o
n
st
r
u
c
t
i
o
n
,
v
o
l
.
4
3
,
p
p
.
1
0
–
2
2
,
J
u
l
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
u
t
c
o
n
.
2
0
1
4
.
0
2
.
0
1
5
.
[
1
9
]
E.
C
o
r
r
y
,
P
.
P
a
u
w
e
l
s
,
S
.
H
u
,
M
.
K
e
a
n
e
,
a
n
d
J.
O
’
D
o
n
n
e
l
l
,
“
A
p
e
r
f
o
r
ma
n
c
e
a
ssessm
e
n
t
o
n
t
o
l
o
g
y
f
o
r
t
h
e
e
n
v
i
r
o
n
m
e
n
t
a
l
a
n
d
e
n
e
r
g
y
man
a
g
e
me
n
t
o
f
b
u
i
l
d
i
n
g
s
,
”
Au
t
o
m
a
t
i
o
n
i
n
C
o
n
s
t
r
u
c
t
i
o
n
,
v
o
l
.
5
7
,
p
p
.
2
4
9
–
2
5
9
,
S
e
p
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
u
t
c
o
n
.
2
0
1
5
.
0
5
.
0
0
2
.
[
2
0
]
S
.
Z
h
o
u
,
Z.
W
u
,
J
.
L
i
,
a
n
d
X
.
Zh
a
n
g
,
“
R
e
a
l
-
t
i
me
e
n
e
r
g
y
c
o
n
t
r
o
l
a
p
p
r
o
a
c
h
f
o
r
smar
t
h
o
m
e
e
n
e
r
g
y
m
a
n
a
g
e
m
e
n
t
sy
st
e
m,
”
E
l
e
c
t
r
i
c
Po
w
e
r
C
o
m
p
o
n
e
n
t
s
a
n
d
S
y
st
e
m
s
,
v
o
l
.
4
2
,
n
o
.
3
–
4
,
p
p
.
3
1
5
–
3
2
6
,
M
a
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
3
2
5
0
0
8
.
2
0
1
3
.
8
6
2
3
2
2
.
[
2
1
]
Y.
-
S
.
Le
e
a
n
d
L.
-
I
.
To
n
g
,
“
F
o
r
e
c
a
st
i
n
g
e
n
e
r
g
y
c
o
n
su
m
p
t
i
o
n
u
s
i
n
g
a
g
r
e
y
m
o
d
e
l
i
m
p
r
o
v
e
d
b
y
i
n
c
o
r
p
o
r
a
t
i
n
g
g
e
n
e
t
i
c
p
r
o
g
r
a
mm
i
n
g
,
”
En
e
r
g
y
C
o
n
v
e
r
si
o
n
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
5
2
,
n
o
.
1
,
p
p
.
1
4
7
–
1
5
2
,
Ja
n
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
c
o
n
m
a
n
.
2
0
1
0
.
0
6
.
0
5
3
.
[
2
2
]
J.
M
.
Y
o
u
n
g
,
I
.
S
t
a
c
e
y
,
T
.
A
.
D
o
b
b
i
n
s,
S
.
D
u
n
l
o
p
,
A
.
L
.
D
e
ssa
i
x
,
a
n
d
D
.
C
.
C
u
r
r
o
w
,
“
A
sso
c
i
a
t
i
o
n
b
e
t
w
e
e
n
t
o
b
a
c
c
o
p
l
a
i
n
p
a
c
k
a
g
i
n
g
a
n
d
Q
u
i
t
l
i
n
e
c
a
l
l
s
:
a
p
o
p
u
l
a
t
i
o
n
‐
b
a
se
d
,
i
n
t
e
r
r
u
p
t
e
d
t
i
me‐s
e
r
i
e
s
a
n
a
l
y
s
i
s,
”
Me
d
i
c
a
l
J
o
u
r
n
a
l
o
f
A
u
st
r
a
l
i
a
,
v
o
l
.
2
0
0
,
n
o
.
1
,
p
p
.
2
9
–
3
2
,
Ja
n
.
2
0
1
4
,
d
o
i
:
1
0
.
5
6
9
4
/
mj
a
1
3
.
1
1
0
7
0
.
[
2
3
]
Y
.
H
u
,
L.
P
e
n
g
,
X
.
Li
,
X
.
Y
a
o
,
H
.
Li
n
,
a
n
d
T.
C
h
i
,
“
A
n
o
v
e
l
e
v
o
l
u
t
i
o
n
t
r
e
e
f
o
r
a
n
a
l
y
z
i
n
g
t
h
e
g
l
o
b
a
l
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
st
r
u
c
t
u
r
e
,
”
E
n
e
r
g
y
,
v
o
l
.
1
4
7
,
p
p
.
1
1
7
7
–
1
1
8
7
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
1
8
.
0
1
.
0
9
3
.
[
2
4
]
S.
-
C
.
Y
i
p
,
K
.
W
o
n
g
,
W
.
-
P
.
H
e
w
,
M
.
-
T.
G
a
n
,
R
.
C
.
W
.
P
h
a
n
,
a
n
d
S
.
-
W
.
Ta
n
,
“
D
e
t
e
c
t
i
o
n
o
f
e
n
e
r
g
y
t
h
e
f
t
a
n
d
d
e
f
e
c
t
i
v
e
smar
t
met
e
r
s
i
n
sm
a
r
t
g
r
i
d
s u
si
n
g
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
P
o
w
e
r
&
E
n
e
r
g
y
S
y
st
e
m
s
,
v
o
l
.
9
1
,
p
p
.
2
3
0
–
2
4
0
,
O
c
t
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s
.
2
0
1
7
.
0
4
.
0
0
5
.
[
2
5
]
P
.
C
h
u
j
a
i
,
N
.
K
e
r
d
p
r
a
so
p
,
a
n
d
K
.
K
e
r
d
p
r
a
so
p
,
“
Ti
m
e
s
e
r
i
e
s
a
n
a
l
y
si
s
o
f
h
o
u
seh
o
l
d
e
l
e
c
t
r
i
c
c
o
n
s
u
mp
t
i
o
n
w
i
t
h
A
R
I
M
A
a
n
d
A
R
M
A
mo
d
e
l
s
,
”
L
e
c
t
u
r
e
N
o
t
e
s
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
0
2
,
p
p
.
2
9
5
–
3
0
0
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
n
h
a
n
ce
d
time
s
eries
fo
r
ec
a
s
t
in
g
u
s
in
g
h
yb
r
id
A
R
I
MA
a
n
d
ma
ch
in
e
lea
r
n
in
g
…
(
V
ig
n
esh
A
r
u
mu
g
a
m
)
1979
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vig
n
e
sh
Ar
u
m
u
g
a
m
is
a
re
se
a
rc
h
sc
h
o
lar
fr
o
m
S
R
M
U
n
iv
e
rsity
.
He
is
a
ls
o
wo
rk
i
n
g
a
s
a
ss
istan
t
p
r
o
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Ra
m
a
p
u
ra
m
Ca
m
p
u
s.
His
re
se
a
rc
h
i
n
ter
e
sts
li
e
i
n
c
l
o
u
d
c
o
m
p
u
t
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
p
ro
g
ra
m
m
in
g
.
He
h
o
ld
s
a
M
a
ste
r
o
f
C
o
m
p
u
t
e
r
Ap
p
li
c
a
ti
o
n
s
(M
CA)
,
a
n
M
.
P
h
i
l
.
in
c
o
m
p
u
ter
sc
ien
c
e
,
a
n
d
a
Ba
c
h
e
lo
r
o
f
Ed
u
c
a
ti
o
n
(B.
E
d
.
)
.
Wi
th
a
str
o
n
g
f
o
u
n
d
a
ti
o
n
i
n
th
e
se
a
re
a
s,
he
h
a
s
c
o
n
tri
b
u
ted
si
g
n
ifi
c
a
n
t
ly
to
a
c
a
d
e
m
ic
re
se
a
rc
h
a
n
d
h
a
s
se
v
e
ra
l
p
u
b
li
c
a
ti
o
n
s
in
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
i
g
n
e
sh
a
2
@
srm
ist.
e
d
u
.
in
.
Dr
.
Vija
y
a
l
a
k
sh
m
i
N
a
ta
r
a
ja
n
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s
a
t
S
RM
I
n
stit
u
te
o
f
S
c
ie
n
c
e
a
n
d
Tec
h
n
o
l
o
g
y
.
S
h
e
e
a
rn
e
d
h
e
r
P
h
.
D
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
fr
o
m
An
n
a
Un
iv
e
rsity
i
n
2
0
1
8
.
S
h
e
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
v
a
ri
o
u
s
p
ro
fe
ss
io
n
a
l
b
o
d
ies
,
in
c
l
u
d
i
n
g
t
h
e
Co
m
p
u
ter
S
o
c
iety
o
f
In
d
ia
(
CS
I)
a
n
d
t
h
e
In
ter
n
a
ti
o
n
a
l
As
so
c
iatio
n
o
f
E
n
g
i
n
e
e
rs
(IAENG
).
Ad
d
it
io
n
a
ll
y
,
sh
e
se
rv
e
s
o
n
th
e
Bo
a
r
d
o
f
S
t
u
d
ies
a
t
P
o
n
d
ich
e
rry
U
n
iv
e
rsit
y
a
s
a
n
o
m
i
n
e
e
.
S
h
e
h
a
s
n
u
m
e
ro
u
s
p
u
b
li
c
a
ti
o
n
s
in
i
n
tern
a
ti
o
n
a
l
jo
u
rn
a
ls,
re
flec
ti
n
g
h
e
r
d
e
d
ica
ti
o
n
to
re
se
a
rc
h
a
n
d
a
c
a
d
e
m
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
v
ij
a
y
a
ln
@s
rm
ist.
e
d
u
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.