T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
,
p
p
.
1
5
5
5
~1
565
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
:
1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
23
i
6
.
27219
1555
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
A
hy
brid
ARIM
A
and
DN
N
a
ppro
a
ch w
ith
residua
l l
ea
rning
f
o
r
elect
ric
vehicle
ch
a
rg
ing
de
m
a
nd
fo
recas
ting
Wa
hy
u Ce
s
a
r,
Dw
idh
a
r
m
a
P
riy
a
s
t
a
,
P
r
a
s
et
y
o
Aj
i,
M
ely
a
na
,
Ag
us
Su
pria
nto
,
O
s
en
F
ili Na
m
i,
Riza
N
a
t
i
o
n
a
l
R
e
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
(
B
R
I
N
)
,
Jak
a
r
t
a
P
u
sa
t
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
17
,
2025
R
ev
i
s
ed
Sep
19
,
2
0
2
5
A
cc
ep
ted
Oct
19
,
2
0
2
5
T
h
e
ra
p
id
g
ro
w
th
o
f
e
lec
tri
c
v
e
h
icle
(EV
)
a
d
o
p
ti
o
n
h
a
s
c
re
a
ted
sig
n
if
ica
n
t
c
h
a
ll
e
n
g
e
s
f
o
r
p
o
w
e
r
g
rid
m
a
n
a
g
e
m
e
n
t
a
n
d
c
h
a
rg
in
g
i
n
f
r
a
stru
c
tu
re
p
lan
n
in
g
.
A
c
c
u
ra
te
f
o
re
c
a
stin
g
o
f
EV
c
h
a
rg
in
g
d
e
m
a
n
d
is
th
e
re
f
o
re
e
ss
e
n
ti
a
l
to
e
n
su
re
re
li
a
b
le
e
lec
tri
c
it
y
su
p
p
ly
a
n
d
e
ffe
c
ti
v
e
st
a
ti
o
n
d
e
p
lo
y
m
e
n
t.
Th
is
stu
d
y
p
ro
p
o
se
s
a
n
o
v
e
l
h
y
b
rid
f
o
re
c
a
sti
n
g
f
ra
m
e
w
o
rk
th
a
t
c
o
m
b
in
e
s
a
u
to
re
g
re
ss
i
v
e
in
teg
ra
ted
m
o
v
in
g
a
v
e
ra
g
e
(
A
R
IM
A
)
w
it
h
d
e
e
p
n
e
u
ra
l
n
e
tw
o
r
k
s
(DN
N
)
th
ro
u
g
h
a
re
sid
u
a
l
lea
rn
i
n
g
stra
teg
y
.
In
th
is
a
p
p
ro
a
c
h
,
A
RIM
A
m
o
d
e
ls
th
e
li
n
e
a
r
tem
p
o
ra
l
p
a
tt
e
rn
s,
w
h
il
e
DN
N
c
a
p
tu
re
s
th
e
n
o
n
li
n
e
a
r
re
sid
u
a
ls,
re
su
lt
in
g
i
n
im
p
ro
v
e
d
e
ff
icie
n
c
y
a
n
d
p
re
d
ictiv
e
a
c
c
u
ra
c
y
.
T
h
e
p
r
o
p
o
se
d
h
y
b
rid
m
o
d
e
l
is
o
n
e
o
f
th
e
f
irst
a
p
p
l
ica
ti
o
n
s
o
f
th
e
re
sid
u
a
l
lea
rn
in
g
a
p
p
ro
a
c
h
f
o
r
EV
d
e
m
a
n
d
f
o
re
c
a
s
ti
n
g
in
In
d
o
n
e
sia
.
Ex
p
e
rim
e
n
tal
e
v
a
lu
a
ti
o
n
u
sin
g
re
a
l
-
w
o
rld
d
a
il
y
c
o
n
su
m
p
ti
o
n
d
a
ta
sh
o
w
s
th
a
t
th
e
h
y
b
rid
m
e
th
o
d
a
c
h
iev
e
d
th
e
h
ig
h
e
st
p
re
d
icti
o
n
a
c
c
u
ra
c
y
o
f
9
8
.
2
2
%
,
c
o
n
siste
n
tl
y
o
u
t
p
e
rf
o
rm
in
g
sin
g
le
-
m
o
d
e
l
b
a
s
e
li
n
e
s.
Be
y
o
n
d
tec
h
n
ica
l
p
e
rf
o
rm
a
n
c
e
,
th
e
m
o
d
e
l
c
a
n
su
p
p
o
rt
st
a
k
e
h
o
ld
e
rs
i
n
p
lan
n
in
g
c
h
a
rg
in
g
in
f
ra
stru
c
tu
re
a
n
d
h
e
lp
m
a
in
tain
g
rid
sta
b
il
it
y
in
ra
p
i
d
ly
g
ro
w
in
g
EV
e
c
o
sy
st
e
m
s.
K
ey
w
o
r
d
s
:
Au
to
r
eg
r
es
s
i
v
e
in
te
g
r
ated
m
o
v
i
n
g
av
er
a
g
e
C
h
ar
g
in
g
d
e
m
a
n
d
f
o
r
ec
ast
in
g
Dee
p
n
eu
r
al
n
e
t
w
o
r
k
E
lectr
ic
v
eh
ic
le
H
y
b
r
id
m
o
d
el
R
esid
u
al
lear
n
i
n
g
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
lic
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
ah
y
u
C
e
s
ar
Natio
n
al
R
e
s
ea
r
ch
a
n
d
I
n
n
o
v
a
tio
n
A
g
e
n
c
y
(
B
R
I
N)
St
.
M.
H
.
T
h
am
r
i
n
No
.
8
J
ak
ar
ta
P
u
s
at,
I
n
d
o
n
esia
E
m
ail:
w
a
h
y
0
4
7
@
b
r
i
n
.
g
o
.
id
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ic
v
eh
icle
s
(
E
Vs)
h
a
v
e
g
ain
ed
i
n
cr
ea
s
i
n
g
atte
n
tio
n
wo
r
ld
w
id
e
d
u
e
to
t
h
eir
ad
v
an
t
ag
es
o
v
er
f
o
s
s
i
l
-
f
u
eled
v
e
h
icle
s
,
in
cl
u
d
in
g
e
n
er
g
y
e
f
f
icie
n
c
y
a
n
d
r
ed
u
ce
d
ca
r
b
o
n
em
is
s
io
n
s
[
1
]
.
E
V
ad
o
p
tio
n
in
I
n
d
o
n
esia,
en
co
u
r
ag
i
n
g
t
h
e
ex
p
an
s
io
n
o
f
c
h
ar
g
in
g
s
ta
tio
n
s
,
is
cr
u
cial
to
s
u
p
p
o
r
t
th
e
g
o
v
er
n
m
e
n
t
’
s
elec
tr
if
icatio
n
g
o
als
[
2
]
.
Ho
wev
er
,
th
e
u
n
e
v
en
d
is
tr
ib
u
t
io
n
o
f
el
ec
tr
icit
y
s
u
p
p
l
y
ac
r
o
s
s
r
e
g
io
n
s
co
m
p
lica
tes
in
f
r
astru
ct
u
r
e
p
lan
n
i
n
g
an
d
h
ig
h
lig
h
t
s
th
e
n
ee
d
f
o
r
ac
cu
r
ate
d
em
a
n
d
f
o
r
ec
asti
n
g
.
A
cc
u
r
ate
E
V
ch
ar
g
i
n
g
d
em
a
n
d
f
o
r
ec
asti
n
g
is
cr
u
cial
f
o
r
m
a
n
y
s
tak
e
h
o
ld
er
s
.
Fo
r
c
h
ar
g
i
n
g
s
ta
tio
n
d
e
v
elo
p
er
s
,
it
s
u
p
p
o
r
ts
d
ec
is
io
n
-
m
ak
in
g
r
e
g
ar
d
in
g
s
ite
s
elec
ti
o
n
an
d
ca
p
ac
it
y
p
lan
n
i
n
g
.
Fo
r
elec
tr
ic
u
til
ities
,
i
t
en
s
u
r
es
alig
n
m
e
n
t
b
et
w
ee
n
ch
ar
g
i
n
g
d
e
m
an
d
an
d
elec
tr
icit
y
s
u
p
p
l
y
,
esp
ec
iall
y
i
n
r
eg
io
n
s
s
u
c
h
as
r
e
m
o
te
is
lan
d
s
w
h
er
e
g
en
er
ati
n
g
ca
p
ac
it
y
is
li
m
ited
.
Fu
r
t
h
er
m
o
r
e,
r
eliab
le
d
em
a
n
d
f
o
r
ec
asti
n
g
ca
n
in
f
o
r
m
n
atio
n
al
e
n
er
g
y
p
o
lic
y
,
in
cl
u
d
in
g
th
e
p
o
t
en
tial
n
ee
d
f
o
r
ad
d
itio
n
al
p
o
w
er
g
e
n
er
atio
n
to
s
u
s
tai
n
a
g
r
o
w
in
g
E
V
ec
o
s
y
s
te
m
.
Gi
v
en
t
h
at
elec
tr
icit
y
s
u
p
p
l
y
i
n
I
n
d
o
n
e
s
ia
r
e
m
ai
n
s
u
n
ev
e
n
ac
r
o
s
s
r
eg
io
n
s
,
t
h
is
s
t
u
d
y
f
o
cu
s
es
o
n
elec
tr
ici
t
y
co
n
s
u
m
p
tio
n
p
r
ed
ictio
n
u
s
i
n
g
h
is
to
r
ical
co
n
s
u
m
p
tio
n
d
ata
r
ec
o
r
d
ed
in
th
e
ch
ar
g
i
n
g
s
tatio
n
m
an
a
g
e
m
en
t
s
y
s
te
m
(
C
SMS)
[
3
]
.
T
h
e
r
esu
lt
s
o
f
t
h
i
s
elec
tr
icit
y
co
n
s
u
m
p
t
io
n
p
r
ed
ictio
n
ar
e
v
er
y
i
m
p
o
r
ta
n
t
f
o
r
en
titi
e
s
p
lan
n
in
g
to
b
u
ild
n
e
w
ch
ar
g
i
n
g
s
tatio
n
s
,
a
s
it
h
elp
s
e
s
ti
m
ate
elec
tr
icit
y
d
e
m
a
n
d
t
h
a
t
m
u
s
t b
e
ali
g
n
ed
w
ith
th
e
a
v
a
ilab
le
p
o
w
er
s
u
p
p
l
y
in
ea
c
h
r
eg
io
n
.
Qu
a
n
tita
tiv
e
f
o
r
ec
asti
n
g
tec
h
n
iq
u
e
s
u
s
e
h
i
s
to
r
ical
d
ata
an
d
v
ar
io
u
s
m
a
th
e
m
atica
l
m
o
d
els
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
5
5
-
1
565
1556
co
n
tain
i
n
g
ca
u
s
al
v
ar
iab
les
t
o
p
r
ed
ict
d
em
a
n
d
[
4
]
.
T
im
e
s
er
ies
f
o
r
ec
asti
n
g
tak
e
s
t
h
i
s
ap
p
r
o
ac
h
f
u
r
t
h
er
b
y
p
r
ed
ictin
g
f
u
t
u
r
e
ev
e
n
ts
b
ased
o
n
h
is
to
r
ical
in
s
ig
h
ts
.
P
r
ev
io
u
s
r
esear
ch
o
n
d
aily
el
ec
tr
icit
y
co
n
s
u
m
p
t
io
n
f
o
r
ec
as
tin
g
h
as
ex
p
lo
r
ed
an
d
co
m
p
ar
ed
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
(
M
L
)
alg
o
r
it
h
m
s
.
Sev
er
al
s
tu
d
ie
s
h
a
v
e
an
a
l
y
ze
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
m
o
d
els
s
u
c
h
as
r
an
d
o
m
f
o
r
est
(
R
F),
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
,
ex
tr
e
m
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGB
)
,
an
d
ar
tif
icia
l
n
e
u
r
al
n
et
w
o
r
k
s
(
A
NN)
u
til
izin
g
a
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
s
tr
u
ct
u
r
e.
T
h
e
r
es
u
lt
s
s
h
o
w
ed
th
at
th
e
A
NN
w
it
h
ML
P
ar
ch
itect
u
r
e
ac
h
ie
v
ed
th
e
b
est
p
er
f
o
r
m
a
n
ce
,
o
b
tain
i
n
g
an
R
²
s
co
r
e
o
f
0
.
8
5
an
d
a
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
o
f
1
1
5
.
1
7
[
5
]
,
ev
en
w
it
h
o
u
t
i
n
co
r
p
o
r
atin
g
w
ea
t
h
er
-
r
elate
d
v
ar
iab
les.
I
n
a
r
elate
d
s
tu
d
y
,
Z
h
o
u
et
a
l
.
[
6
]
f
o
u
n
d
th
at
th
e
ANN
/
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
ST
M
)
m
o
d
el
o
u
tp
er
f
o
r
m
ed
SVR
in
ter
m
s
o
f
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
T
h
eir
r
esear
ch
u
s
e
d
a
B
ay
esia
n
Dee
p
L
ea
r
n
i
n
g
f
r
a
m
e
w
o
r
k
co
m
b
in
ed
w
i
th
L
ST
M
n
et
w
o
r
k
s
to
ac
co
u
n
t
f
o
r
u
n
ce
r
tai
n
t
y
in
f
o
r
ec
asts
.
T
h
is
m
o
d
el,
tr
ai
n
ed
o
n
ac
tu
al
d
ata
f
r
o
m
a
n
E
V
ch
ar
g
i
n
g
s
tat
io
n
at
C
altec
h
,
p
r
o
d
u
ce
d
an
R
MSE
o
f
ar
o
u
n
d
3
9
.
3
%,
a
n
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
M
AE
)
o
f
4
2
.
4
%,
an
d
s
h
o
w
ed
a
1
7
.
9
%
in
cr
ea
s
e
in
ac
c
u
r
ac
y
co
m
p
ar
ed
to
SVR
.
Sim
ilar
l
y
,
r
esear
c
h
b
y
Kr
iek
i
n
g
e
et
a
l
.
[
7
]
f
o
c
u
s
ed
o
n
p
r
ed
ictin
g
n
ex
t
-
d
a
y
elec
tr
icit
y
d
e
m
an
d
at
a
h
o
s
p
ital E
V
ch
ar
g
i
n
g
s
tatio
n
u
s
i
n
g
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
s
(
DNN)
,
ac
h
ie
v
in
g
a
MA
E
o
f
2
8
.
8
%,
m
ar
k
i
n
g
th
eir
h
ig
h
est
ac
cu
r
ac
y
.
A
d
d
itio
n
all
y
,
R
o
y
et
a
l
.
[
8
]
in
v
esti
g
ated
en
er
g
y
co
n
s
u
m
p
tio
n
f
o
r
ec
asti
n
g
f
o
r
E
Vs
u
s
i
n
g
m
u
ltip
le
ML
tec
h
n
iq
u
es,
in
cl
u
d
in
g
ti
m
e
s
er
ie
s
r
eg
r
ess
io
n
,
r
eg
r
e
s
s
io
n
-
au
to
r
eg
r
es
s
iv
e
i
n
te
g
r
ated
m
o
v
in
g
a
v
er
ag
e
(
AR
I
M
A
)
,
XG
B
,
an
d
A
NN
w
i
th
L
ST
M
ar
ch
itect
u
r
e.
T
h
eir
f
i
n
d
in
g
s
s
h
o
w
ed
th
a
t
th
e
AN
N
-
L
ST
M
m
o
d
el
p
er
f
o
r
m
ed
b
est,
w
it
h
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
P
E
)
v
alu
e
s
o
f
1
3
.
1
4
,
1
5
.
4
1
,
an
d
3
1
.
3
5
f
o
r
clu
s
ter
s
1
,
2
,
an
d
3
,
r
esp
ec
tiv
el
y
.
B
ased
o
n
a
r
ev
ie
w
o
f
s
e
v
er
al
p
r
ev
io
u
s
s
cie
n
ti
f
ic
j
o
u
r
n
als,
f
e
w
s
t
u
d
ies
h
a
v
e
in
v
es
tig
a
t
ed
h
y
b
r
id
f
o
r
ec
asti
n
g
m
o
d
el
s
th
at
ex
p
lic
itl
y
i
n
teg
r
ate
AR
I
M
A
w
ith
D
NN
th
r
o
u
g
h
r
esid
u
a
l
lea
r
n
i
n
g
,
p
ar
ticu
lar
l
y
in
th
e
I
n
d
o
n
esia
n
co
n
te
x
t.
A
d
d
r
ess
i
n
g
th
i
s
g
ap
,
th
i
s
s
t
u
d
y
p
r
o
p
o
s
es
a
h
y
b
r
id
AR
I
M
A
-
DNN
m
o
d
el
w
it
h
r
esid
u
a
l
lear
n
in
g
f
o
r
p
r
ed
ictin
g
d
ail
y
E
V
ch
ar
g
in
g
d
e
m
an
d
.
T
h
is
s
t
u
d
y
d
i
f
f
er
s
f
r
o
m
ea
r
lier
r
e
s
ea
r
ch
b
y
e
m
p
lo
y
i
n
g
a
h
y
b
r
id
A
R
I
M
A
m
o
d
el
co
m
b
i
n
ed
w
ith
D
NN,
lev
er
a
g
i
n
g
a
r
esid
u
al
lear
n
i
n
g
ap
p
r
o
ac
h
to
f
u
r
t
h
er
i
m
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Hi
s
to
r
ical
co
n
s
u
m
p
tio
n
d
ata
f
r
o
m
a
C
SMS
ar
e
u
til
ized
to
d
esig
n
th
e
m
o
d
el,
w
h
ic
h
lev
er
ag
e
s
AR
I
M
A
f
o
r
ca
p
tu
r
in
g
li
n
ea
r
te
m
p
o
r
al
p
atter
n
s
an
d
DNN
w
it
h
r
esid
u
a
l
lear
n
in
g
f
o
r
m
o
d
eli
n
g
n
o
n
li
n
ea
r
co
m
p
o
n
e
n
ts
.
T
h
e
o
b
j
ec
tiv
e
is
to
d
ev
elo
p
a
h
y
b
r
i
d
A
R
I
M
A
-
D
NN
m
o
d
el
w
it
h
r
esid
u
al
lear
n
i
n
g
to
p
r
ed
ict
E
V
ch
ar
g
in
g
lo
ad
u
s
i
n
g
r
ea
l
ex
p
er
im
e
n
tal
d
ata
f
r
o
m
J
ak
ar
ta,
th
er
eb
y
s
u
p
p
o
r
tin
g
ef
f
ec
t
iv
e
in
f
r
astru
ct
u
r
e
p
lan
n
i
n
g
a
n
d
ele
ctr
icit
y
m
an
a
g
e
m
en
t in
I
n
d
o
n
e
s
ia.
2.
M
E
T
H
O
D
2
.
1
.
Appro
a
ch
a
nd
t
ec
hn
iqu
e
T
h
is
s
t
u
d
y
e
m
p
lo
y
s
a
h
y
b
r
id
m
o
d
el
co
m
b
i
n
in
g
AR
I
M
A
a
n
d
DNN
to
p
er
f
o
r
m
ti
m
e
s
er
ie
s
f
o
r
ec
asti
n
g
u
s
i
n
g
a
d
ata
w
in
d
o
w
i
n
g
o
r
l
o
o
p
b
ac
k
ap
p
r
o
ac
h
.
T
im
e
s
er
i
es
f
o
r
ec
asti
n
g
is
a
q
u
an
t
itati
v
e
m
e
th
o
d
u
s
ed
t
o
an
t
icip
ate
f
u
t
u
r
e
v
alu
e
s
b
ased
o
n
p
atter
n
s
f
o
u
n
d
in
s
eq
u
en
ti
al
h
is
to
r
ical
d
ata
[
9
]
.
B
y
ex
a
m
i
n
in
g
an
d
lear
n
i
n
g
f
r
o
m
p
ast
tr
e
n
d
s
,
th
i
s
ap
p
r
o
ac
h
f
ac
i
litates
f
u
t
u
r
e
p
r
ed
ictio
n
s
a
n
d
h
elp
s
m
iti
g
ate
p
o
ten
t
i
al
r
is
k
s
,
[
1
0
]
.
A
s
a
s
p
ec
ialized
ar
ea
w
ith
in
ML
,
ti
m
e
s
er
ie
s
f
o
r
ec
asti
n
g
f
o
cu
s
es
o
n
te
m
p
o
r
al
d
ata,
e
m
p
h
asiz
in
g
t
h
e
p
r
ed
i
ctio
n
o
f
f
u
tu
r
e
v
al
u
es
f
r
o
m
p
ast
s
eq
u
e
n
ce
s
.
E
f
f
ec
ti
v
e
f
o
r
ec
asti
n
g
r
eq
u
ir
es
a
n
u
n
d
er
s
ta
n
d
in
g
o
f
s
e
v
er
al
co
r
e
ele
m
en
t
s
o
f
ti
m
e
s
er
ies
d
ata,
in
cl
u
d
i
n
g
l
o
n
g
-
ter
m
tr
en
d
s
(
g
e
n
er
al
u
p
war
d
o
r
d
o
w
n
w
ar
d
m
o
v
e
m
e
n
ts
)
,
s
ea
s
o
n
al
o
r
c
y
cli
c
p
atter
n
s
(
r
ec
u
r
r
in
g
b
eh
a
v
io
r
o
v
e
r
r
eg
u
lar
i
n
ter
v
al
s
)
,
ir
r
eg
u
lar
f
l
u
ct
u
atio
n
s
(
o
f
te
n
in
f
l
u
en
ce
d
b
y
e
x
ter
n
al
ev
en
t
s
)
,
an
d
r
an
d
o
m
n
o
is
e
(
u
n
p
r
ed
ictab
le
v
ar
iatio
n
s
)
[
1
1
]
.
AR
I
M
A
,
also
r
ef
er
r
ed
to
as
th
e
B
o
x
-
J
en
k
i
n
s
m
o
d
el,
is
w
i
d
ely
r
ec
o
g
n
ized
f
o
r
its
e
f
f
ec
t
iv
en
e
s
s
i
n
m
o
d
eli
n
g
n
o
n
-
s
ta
tio
n
ar
y
ti
m
e
s
er
ies
d
ata
[
1
2
]
.
I
t
s
er
v
es
b
o
th
to
e
n
h
a
n
ce
u
n
d
er
s
tan
d
i
n
g
o
f
t
h
e
d
ata
a
n
d
to
en
ab
le
ac
cu
r
ate
f
u
t
u
r
e
tr
en
d
p
r
ed
ictio
n
s
.
A
R
I
M
A
e
x
te
n
d
s
t
h
e
au
to
r
eg
r
ess
iv
e
m
o
v
i
n
g
av
er
a
g
e
(
AR
M
A
)
m
o
d
el
b
y
i
n
te
g
r
atin
g
d
if
f
er
en
c
in
g
to
h
an
d
le
n
o
n
-
s
tatio
n
ar
it
y
,
an
d
it
co
m
b
i
n
es
t
h
e
au
t
o
r
eg
r
e
s
s
i
v
e
(
A
R
)
an
d
m
o
v
i
n
g
av
er
ag
e
(
M
A
)
co
m
p
o
n
en
ts
in
to
a
s
in
g
le
f
r
a
m
e
w
o
r
k
.
T
h
is
m
o
d
el
i
s
s
p
ec
if
ica
ll
y
s
u
ited
f
o
r
d
atasets
th
at
ar
e
eith
er
s
ta
tio
n
ar
y
o
r
c
an
b
e
m
ad
e
s
tatio
n
ar
y
t
h
r
o
u
g
h
tr
a
n
s
f
o
r
m
atio
n
[
1
3
]
.
T
h
e
co
m
p
lete
m
at
h
e
m
atica
l
f
o
r
m
u
latio
n
o
f
th
e
AR
M
A
(
,
)
m
o
d
el
i
s
d
etailed
in
[
1
4
]
.
=
+
1
−
1
+
⋯
+
−
+
1
−
1
+
⋯
+
−
+
(
1
)
w
h
er
e
o
p
er
ato
r
lag
(
B
=
−
1
)
-
d
i
f
f
er
e
n
c
in
g
,
w
r
it
ten
as
:
=
(
1
−
)
)
.
T
h
er
ef
o
r
e,
th
e
co
m
p
lete
AR
I
MA
(
,
,
)
f
o
r
m
u
la
i
s
(
2
)
(
)
(
1
−
)
=
+
(
)
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
h
yb
r
id
A
R
I
MA
a
n
d
DN
N
a
p
p
r
o
a
ch
w
ith
r
esid
u
a
l le
a
r
n
in
g
fo
r
elec
tr
ic
ve
h
icle
ch
a
r
g
in
g
…
(
W
a
h
yu
C
esa
r
)
1557
T
h
en
,
to
m
a
k
e
it
A
R
I
M
A
(
,
,
)
,
w
e
d
if
f
er
e
n
ciate
it
ti
m
es
(
s
i
n
ce
A
R
I
M
A
i
s
ess
e
n
tia
ll
y
AR
MA
af
ter
d
if
f
er
en
ci
n
g
tim
e
s
)
.
T
h
is
d
if
f
er
en
ci
n
g
r
esu
l
t
is
w
r
itt
en
in
y
o
u
r
g
r
ap
h
a
s
′
=
(
1
−
)
.
I
n
th
is
co
n
tex
t,
′
d
en
o
tes
th
e
d
if
f
er
e
n
ce
d
ti
m
e
s
er
ies,
w
h
ic
h
m
a
y
h
av
e
u
n
d
er
g
o
n
e
o
n
e
o
r
m
o
r
e
d
if
f
er
en
c
in
g
ope
r
atio
n
s
.
T
h
e
p
r
e
d
icto
r
s
o
n
th
e
r
ig
h
t
-
h
a
n
d
s
id
e
o
f
t
h
e
A
R
I
MA
eq
u
atio
n
in
c
lu
d
e
b
o
th
la
g
g
ed
v
a
lu
e
s
o
f
t
h
e
o
r
ig
in
al
s
er
ies
of
an
d
p
r
ev
io
u
s
er
r
o
r
ter
m
s
.
T
h
is
f
o
r
m
u
lati
o
n
is
k
n
o
w
n
a
s
th
e
A
R
I
M
A
(
,
,
)
m
o
d
el
in
(
2
)
,
w
h
er
e
r
ef
er
s
to
th
e
o
r
d
e
r
o
f
th
e
A
R
co
m
p
o
n
e
n
t,
d
r
ep
r
esen
t
s
th
e
n
u
m
b
er
o
f
d
if
f
er
en
cin
g
s
tep
s
ap
p
lied
to
ac
h
iev
e
s
tat
io
n
ar
it
y
,
an
d
in
d
icate
s
t
h
e
o
r
d
er
o
f
th
e
MA
co
m
p
o
n
e
n
t.
AR
I
M
A
m
o
d
els
ca
n
b
e
co
n
s
tr
u
cted
u
s
i
n
g
eith
er
a
s
ea
s
o
n
al
o
r
n
o
n
-
s
ea
s
o
n
al
ap
p
r
o
ac
h
,
d
ep
en
d
in
g
o
n
th
e
n
atu
r
e
o
f
t
h
e
ti
m
e
s
e
r
ies,
w
it
h
t
h
e
,
,
an
d
p
ar
am
eter
s
d
ef
i
n
in
g
it
s
s
t
r
u
ctu
r
e.
Af
ter
g
e
n
er
atin
g
th
e
A
R
I
M
A
f
o
r
ec
ast
′
,
th
e
r
esid
u
als
ar
e
ca
l
cu
lated
as
th
e
d
if
f
e
r
e
n
ce
b
et
w
ee
n
th
e
ac
tu
al
o
b
s
er
v
atio
n
an
d
th
e
f
o
r
ec
ast,
ex
p
r
ess
ed
as
=
−
′
.
T
h
ese
r
esid
u
als
r
ep
r
esen
t
th
e
n
o
n
li
n
ea
r
co
m
p
o
n
e
n
t
s
n
o
t
ca
p
tu
r
ed
b
y
t
h
e
A
R
I
M
A
m
o
d
el.
I
n
t
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
f
r
a
m
e
w
o
r
k
,
t
h
e
r
esid
u
al
s
s
er
v
e
as
t
h
e
p
r
im
ar
y
i
n
p
u
t
f
o
r
th
e
DNN,
allo
w
i
n
g
th
e
n
et
w
o
r
k
to
f
o
cu
s
s
p
ec
i
f
icall
y
o
n
m
o
d
elin
g
co
m
p
le
x
n
o
n
li
n
ea
r
d
ep
en
d
en
cies
w
h
ile
AR
I
M
A
h
a
n
d
les
t
h
e
li
n
ea
r
s
tr
u
ctu
r
e.
B
e
f
o
r
e
b
ein
g
u
s
ed
a
s
in
p
u
t
to
t
h
e
DNN,
th
e
r
es
id
u
al
s
eq
u
en
ce
u
n
d
er
g
o
es
t
w
o
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
.
First,
a
s
l
id
in
g
w
i
n
d
o
w
tec
h
n
iq
u
e
is
ap
p
lied
to
r
estru
ctu
r
e
th
e
r
esid
u
al
ti
m
e
s
er
ies
i
n
to
s
u
p
e
r
v
is
ed
lear
n
in
g
s
a
m
p
les,
w
h
er
e
ea
ch
w
i
n
d
o
w
o
f
p
ast
r
e
s
id
u
als
is
m
ap
p
ed
to
a
f
u
tu
r
e
r
esid
u
al
v
alu
e.
Seco
n
d
,
th
e
d
ata
ar
e
n
o
r
m
a
lized
u
s
in
g
m
i
n
-
m
a
x
s
ca
lin
g
to
e
n
s
u
r
e
all
f
ea
t
u
r
es
ar
e
w
i
t
h
i
n
a
u
n
i
f
o
r
m
r
a
n
g
e,
i
m
p
r
o
v
i
n
g
c
o
n
v
er
g
e
n
ce
d
u
r
i
n
g
DNN
tr
ai
n
in
g
.
DNN
ar
e
a
b
r
an
c
h
o
f
ML
b
ased
o
n
A
NN
co
m
p
o
s
ed
o
f
m
u
l
tip
le
la
y
er
s
h
en
ce
th
e
ter
m
“
d
ee
p
lear
n
i
n
g
.
”
T
h
ese
n
et
w
o
r
k
s
ar
e
ca
p
ab
le
o
f
lear
n
in
g
f
r
o
m
an
d
in
ter
p
r
etin
g
co
m
p
le
x
d
ata
p
atter
n
s
[
1
5
]
.
DNNs
ar
e
p
ar
ticu
lar
l
y
p
o
w
er
f
u
l
i
n
m
o
d
e
lin
g
h
o
w
s
y
s
te
m
s
r
esp
o
n
d
to
ch
an
g
in
g
en
v
ir
o
n
m
en
tal
v
ar
iab
le
s
.
T
h
ey
ar
e
b
io
lo
g
icall
y
i
n
s
p
ir
ed
b
y
th
e
s
tr
u
c
tu
r
e
an
d
f
u
n
ctio
n
in
g
o
f
th
e
h
u
m
a
n
b
r
ain
,
w
h
er
e
i
n
t
er
co
n
n
ec
ted
n
e
u
r
o
n
s
p
r
o
ce
s
s
a
n
d
tr
an
s
m
i
t in
f
o
r
m
a
tio
n
[
1
3
]
.
T
h
is
s
tu
d
y
ap
p
lies
a
s
u
p
er
v
i
s
ed
lear
n
in
g
al
g
o
r
ith
m
w
it
h
i
n
th
e
DNN
f
r
a
m
e
w
o
r
k
.
A
DNN
i
s
ar
ch
itect
u
r
all
y
d
esi
g
n
ed
to
m
i
m
ic
t
h
e
h
u
m
a
n
b
r
ain
,
co
n
s
is
t
in
g
o
f
la
y
er
s
o
f
in
ter
co
n
n
ec
ted
p
r
o
ce
s
s
in
g
u
n
its
k
n
o
w
n
a
s
n
e
u
r
o
n
s
.
T
h
ese
n
eu
r
o
n
s
f
o
r
m
a
n
o
n
li
n
ea
r
n
et
w
o
r
k
th
at
p
r
o
ce
s
s
es i
n
p
u
t d
ata
an
d
p
r
o
d
u
ce
s
o
u
tp
u
ts
t
h
r
o
u
g
h
a
s
eq
u
en
ce
o
f
tr
an
s
f
o
r
m
atio
n
s
[
1
6
]
.
A
t
y
p
ical
DN
N
co
n
s
is
t
s
o
f
t
h
r
ee
m
ai
n
co
m
p
o
n
e
n
ts
: a
n
in
p
u
t
la
y
er
,
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
e
r
s
,
an
d
an
o
u
tp
u
t
la
y
er
.
T
h
e
h
id
d
en
la
y
er
s
tr
an
s
f
o
r
m
in
p
u
t
d
ata
in
to
in
t
er
m
ed
iate
r
ep
r
esen
tatio
n
s
,
w
h
i
ch
ar
e
th
en
u
t
ilized
b
y
t
h
e
o
u
tp
u
t
l
a
y
er
to
g
e
n
er
at
e
p
r
ed
ictio
n
s
.
T
h
e
o
u
tp
u
ts
f
r
o
m
th
e
h
id
d
en
la
y
er
s
ar
e
co
m
m
o
n
l
y
r
ef
er
r
ed
to
as
ac
tiv
atio
n
s
o
r
n
o
d
es.
A
n
ex
a
m
p
le
o
f
an
A
NN
w
it
h
a
M
L
P
ar
ch
itect
u
r
e
is
d
is
c
u
s
s
ed
in
[
1
7
]
.
E
ac
h
n
eu
r
o
n
i
n
th
e
n
e
t
w
o
r
k
r
ec
ei
v
e
s
in
p
u
t
s
i
g
n
als
w
ei
g
h
ted
b
y
s
p
ec
i
f
ic
v
a
l
u
es.
T
h
ese
w
ei
g
h
ted
in
p
u
t
s
ar
e
s
u
m
m
ed
an
d
th
e
n
p
ass
ed
th
r
o
u
g
h
an
ac
ti
v
atio
n
f
u
n
ctio
n
,
w
h
ich
co
m
p
ar
es
t
h
e
s
u
m
to
a
th
r
esh
o
ld
.
I
f
th
e
s
u
m
e
x
ce
ed
s
th
e
th
r
es
h
o
ld
,
th
e
n
eu
r
o
n
is
ac
tiv
ated
an
d
p
ass
es
its
o
u
tp
u
t
to
o
th
er
co
n
n
ec
ted
n
eu
r
o
n
s
;
o
th
er
w
is
e,
it
r
e
m
ain
s
in
ac
ti
v
e.
T
h
is
m
ec
h
an
i
s
m
e
n
ab
les
th
e
n
et
w
o
r
k
to
lear
n
an
d
m
a
k
e
p
r
ed
ictio
n
s
b
ased
o
n
co
m
p
le
x
i
n
p
u
t
p
atter
n
s
.
2
.
2
.
I
nte
g
ra
t
io
n o
f
ARI
M
A
a
nd
DNN
w
it
h r
esid
ua
l le
a
r
nin
g
f
o
r
predict
iv
e
m
o
del
s
T
h
e
in
teg
r
atio
n
o
f
tr
ad
it
io
n
a
l
s
tatis
tical
m
eth
o
d
s
w
it
h
d
ee
p
lear
n
in
g
m
o
d
els
h
a
s
e
m
e
r
g
ed
as
a
p
r
o
m
i
s
in
g
d
ir
ec
tio
n
i
n
ti
m
e
s
er
ies
f
o
r
ec
asti
n
g
.
Sp
ec
if
ica
ll
y
,
th
e
co
m
b
i
n
atio
n
o
f
th
e
AR
I
M
A
m
o
d
el
w
it
h
DNN,
en
h
a
n
ce
d
b
y
r
esid
u
a
l
lear
n
in
g
[
1
8
]
,
lev
er
ag
es
th
e
s
tr
en
g
t
h
s
o
f
b
o
th
ap
p
r
o
ac
h
es
AR
I
M
A
’
s
ab
i
lit
y
to
m
o
d
el
l
in
ea
r
d
ep
en
d
en
c
ies
a
n
d
DNN
’
s
ca
p
ac
it
y
to
ca
p
tu
r
e
c
o
m
p
le
x
n
o
n
li
n
ea
r
p
atter
n
s
.
T
h
is
h
y
b
r
id
m
o
d
elin
g
s
tr
ateg
y
i
m
p
r
o
v
es
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
a
n
d
g
en
er
aliza
t
io
n
,
e
s
p
ec
iall
y
f
o
r
co
m
p
le
x
r
ea
l
-
w
o
r
ld
ti
m
e
s
er
ies
d
ata
s
u
c
h
as
elec
tr
icit
y
co
n
s
u
m
p
tio
n
o
f
EV
d
e
m
a
n
d
[
1
9
]
.
A
R
I
M
A
m
o
d
els
h
a
v
e
lo
n
g
b
ee
n
t
h
e
co
r
n
er
s
to
n
e
o
f
ti
m
e
s
er
ies
an
al
y
s
i
s
d
u
e
to
th
eir
ef
f
ec
tiv
e
n
e
s
s
in
m
o
d
eli
n
g
li
n
ea
r
tr
en
d
s
an
d
s
ea
s
o
n
alit
y
[
2
0
]
.
Ho
w
ev
er
,
th
e
y
s
tr
u
g
g
le
w
i
th
n
o
n
li
n
ea
r
an
d
n
o
n
s
tatio
n
ar
y
d
ata
co
m
p
o
n
e
n
t
s
.
I
n
co
n
tr
ast,
DNN,
esp
ec
ially
ar
c
h
itect
u
r
es
lik
e
ML
P
,
ex
ce
l
at
id
en
ti
f
y
in
g
n
o
n
lin
ea
r
d
ep
en
d
e
n
c
ies
i
n
lar
g
e
an
d
n
o
is
y
d
ataset
s
.
B
y
i
n
teg
r
ati
n
g
t
h
e
s
e
t
w
o
m
o
d
el
s
th
r
o
u
g
h
r
esid
u
al
lear
n
in
g
,
t
h
e
li
n
ea
r
co
m
p
o
n
e
n
t
s
ar
e
f
ir
s
t
ca
p
tu
r
ed
b
y
A
R
I
M
A,
an
d
th
e
r
e
m
ai
n
i
n
g
r
esid
u
al
er
r
o
r
s
,
w
h
ic
h
m
a
y
co
n
tai
n
n
o
n
li
n
ea
r
s
tr
u
ct
u
r
es
ar
e
lear
n
ed
b
y
th
e
DNN
[
2
1
]
.
T
h
e
h
y
b
r
id
A
R
I
M
A
-
DNN
m
et
h
o
d
f
o
llo
w
s
a
t
w
o
-
s
tag
e
ap
p
r
o
ac
h
th
at
b
eg
in
s
w
it
h
li
n
ea
r
m
o
d
elin
g
u
s
i
n
g
A
R
I
MA
to
ca
p
t
u
r
e
th
e
lin
ea
r
co
m
p
o
n
e
n
ts
o
f
th
e
ti
m
e
s
er
ies
d
ata.
On
ce
th
e
AR
I
MA
m
o
d
el
is
f
itted
an
d
g
e
n
e
r
ates
p
r
ed
ictio
n
s
,
th
e
r
esid
u
als
ca
lcu
la
ted
as
t
h
e
d
i
f
f
e
r
en
ce
b
et
w
ee
n
t
h
e
ac
t
u
al
d
ata
an
d
t
h
e
AR
I
M
A
f
o
r
ec
asts
ar
e
ex
tr
ac
ted
.
T
h
ese
r
esid
u
als,
w
h
ich
ar
e
ass
u
m
ed
to
c
o
n
tain
th
e
n
o
n
li
n
ea
r
p
atter
n
s
n
o
t
ca
p
tu
r
ed
b
y
A
R
I
M
A,
ar
e
th
en
u
s
ed
as
in
p
u
t
to
a
DNN,
s
u
c
h
as
a
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
m
o
d
els,
w
h
ich
is
t
r
ain
ed
to
le
ar
n
an
d
p
r
ed
ict
th
ese
n
o
n
li
n
ea
r
co
m
p
o
n
e
n
t
s
.
T
h
e
f
o
llo
w
i
n
g
is
a
f
lo
w
o
f
th
is
r
esear
c
h
m
et
h
o
d
u
s
e
th
e
h
y
b
r
id
AR
I
M
A
m
o
d
els
in
te
g
r
ated
w
it
h
DNN
w
it
h
r
esid
u
al
tec
h
n
iq
u
es
.
T
h
e
A
R
I
M
A
m
o
d
el
p
ar
am
ete
r
v
alu
es
ca
n
b
e
d
eter
m
i
n
ed
m
an
u
all
y
o
r
tu
n
ed
u
s
i
n
g
th
e
au
to
_
ar
i
m
a
f
u
n
ctio
n
f
r
o
m
t
h
e
P
y
t
h
o
n
p
r
o
g
r
a
m
m
i
n
g
A
P
I
lib
r
ar
y
[
2
2
]
.
B
y
p
er
f
o
r
m
i
n
g
t
h
i
s
tu
n
i
n
g
p
r
o
ce
s
s
w
i
t
h
th
e
d
atas
e
t,
th
e
g
o
al
is
to
o
b
tain
an
o
p
ti
m
al
A
R
I
M
A
m
o
d
el
tailo
r
ed
to
t
h
e
d
ataset.
Her
e,
p
r
e
p
r
esen
ts
th
e
o
r
d
er
o
f
th
e
AR
co
m
p
o
n
e
n
t,
d
is
th
e
o
r
d
er
o
f
d
if
f
er
e
n
ci
n
g
,
a
n
d
q
is
th
e
o
r
d
er
o
f
th
e
MA
co
m
p
o
n
en
t.
T
h
e
f
ac
t
t
h
at
t
h
e
t
u
n
ed
d
if
f
er
e
n
ci
n
g
(
)
p
ar
am
e
ter
is
n
o
n
ze
r
o
in
d
icate
s
th
a
t
th
e
d
ata
s
et
is
n
o
n
-
s
tatio
n
ar
y
.
Ho
w
e
v
e
r
,
th
is
s
t
u
d
y
al
s
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
5
5
-
1
565
1558
in
v
o
l
v
es
m
an
u
all
y
s
ea
r
ch
i
n
g
f
o
r
th
e
o
p
tim
al
AR
I
M
A
m
o
d
el
p
ar
a
m
eter
s
to
ac
h
iev
e
th
e
b
est
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
A
R
I
M
A
m
o
d
eli
n
g
i
s
ap
p
lied
to
th
e
tim
e
s
er
ies
d
ata
to
ca
p
tu
r
e
its
lin
ea
r
co
m
p
o
n
en
t
s
,
s
u
c
h
as
tr
en
d
s
an
d
s
ea
s
o
n
alit
y
.
Af
ter
t
h
e
A
R
I
M
A
m
o
d
el
g
e
n
er
ates
f
o
r
ec
asts
,
th
e
r
esid
u
als
ca
lc
u
lat
ed
as
th
e
d
if
f
er
en
ce
b
et
w
ee
n
th
e
ac
tu
al
v
al
u
es
an
d
th
e
A
R
I
M
A
p
r
ed
ictio
n
s
ar
e
ex
tr
ac
ted
.
T
h
ese
r
esid
u
als
r
ep
r
esen
t
th
e
n
o
n
li
n
ea
r
p
atter
n
s
th
at
AR
I
M
A
co
u
ld
n
o
t
ca
p
tu
r
e.
I
n
th
e
n
ex
t
s
ta
g
e,
th
ese
r
esid
u
al
s
ar
e
u
s
ed
as
in
p
u
t
f
o
r
a
DNN,
w
h
ich
is
tr
ain
ed
to
m
o
d
el
an
d
p
r
ed
ict
th
e
r
e
m
a
in
i
n
g
n
o
n
li
n
ea
r
co
m
p
o
n
en
t
s
in
th
e
d
ata.
T
o
e
n
h
a
n
ce
t
h
e
DNN
’
s
ab
ilit
y
to
r
ec
o
g
n
ize
te
m
p
o
r
al
p
atter
n
s
,
ad
d
itio
n
al
i
n
p
u
t
f
ea
t
u
r
es
s
u
c
h
as
th
e
d
a
y
o
f
th
e
w
ee
k
(
co
n
v
er
ted
to
n
u
m
er
ic
f
o
r
m
)
m
a
y
b
e
in
cl
u
d
e
d
.
Fig
u
r
e
1
illu
s
tr
ate
s
a
h
y
b
r
id
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
co
m
b
in
i
n
g
A
R
I
M
A
a
n
d
DNN
m
et
h
o
d
s
to
p
r
e
d
ict
d
ail
y
E
V
en
er
g
y
d
e
m
a
n
d
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
w
it
h
d
ata
co
ll
ec
tio
n
,
w
h
er
e
h
is
to
r
ica
l
d
ail
y
E
V
e
n
er
g
y
d
e
m
a
n
d
d
ata
is
g
at
h
er
ed
.
T
h
is
is
f
o
llo
w
ed
b
y
d
ata
p
r
ep
r
o
ce
s
s
in
g
an
d
w
i
n
d
o
w
i
n
g
,
w
h
er
e
i
n
p
u
t
s
eq
u
en
ce
s
ar
e
cr
ea
ted
u
s
i
n
g
a
w
in
d
o
w
s
ize
o
f
7
d
a
y
s
to
p
r
ep
a
r
e
th
e
d
ata
f
o
r
m
o
d
eli
n
g
.
Fig
u
r
e
1
.
Diag
r
a
m
i
n
te
g
r
atio
n
AR
I
M
A
an
d
DNN
m
o
d
els
w
it
h
r
esid
u
al
tec
h
n
iq
u
e
s
AR
I
M
A
m
o
d
elin
g
in
Fi
g
u
r
e
1
is
ap
p
lied
to
ca
p
tu
r
e
lin
ea
r
tr
en
d
s
an
d
s
ea
s
o
n
alit
y
,
an
d
th
e
r
esid
u
als
ca
lcu
lated
as
t
h
e
d
if
f
er
en
ce
b
et
w
ee
n
ac
t
u
al
v
al
u
es
a
n
d
A
R
I
MA
p
r
ed
ictio
n
s
ar
e
ex
tr
ac
te
d
.
T
h
ese
r
esid
u
als,
alo
n
g
w
it
h
ad
d
itio
n
al
f
ea
t
u
r
es
s
u
ch
as
t
h
e
d
a
y
co
n
v
er
ted
to
n
u
m
er
ical
f
o
r
m
at,
ar
e
u
s
ed
as
in
p
u
t
f
o
r
th
e
DNN
to
m
o
d
el
th
e
n
o
n
l
in
ea
r
co
m
p
o
n
en
t
s
.
T
h
e
f
i
n
al
f
o
r
ec
ast
i
s
g
e
n
er
ated
b
y
co
m
b
i
n
i
n
g
th
e
AR
I
MA
f
o
r
ec
ast
w
i
th
th
e
DNN
’
s
p
r
ed
ictio
n
o
f
th
e
r
esid
u
als.
Fi
n
all
y
,
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
i
s
e
v
alu
a
ted
u
s
i
n
g
m
etr
ic
s
s
u
c
h
as
MA
P
E
an
d
R
MSE
,
an
d
is
co
m
p
ar
ed
ag
ai
n
s
t
b
aseli
n
e
m
o
d
e
ls
lik
e
A
R
I
M
A
-
o
n
l
y
an
d
DN
N
-
o
n
l
y
to
ass
es
s
th
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
h
y
b
r
id
ap
p
r
o
ac
h
.
T
h
is
s
tu
d
y
e
m
p
lo
y
s
a
DNN
w
ith
a
m
u
l
tila
y
er
ar
ch
itectu
r
e
co
n
s
is
tin
g
o
f
an
in
p
u
t
la
y
er
,
o
n
e
o
r
m
o
r
e
hi
d
d
en
la
y
er
s
,
an
d
a
n
o
u
tp
u
t
l
a
y
er
.
T
h
e
in
p
u
t
la
y
er
r
ec
ei
v
es
elec
tr
icit
y
co
n
s
u
m
p
t
io
n
d
ata
f
r
o
m
t
h
e
p
ast
s
ev
e
n
d
ay
s
,
w
h
ic
h
is
th
e
n
p
r
o
ce
s
s
ed
b
y
t
h
e
h
id
d
en
la
y
er
s
to
g
en
er
ate
p
r
e
d
ictio
n
s
in
th
e
o
u
tp
u
t
la
y
er
.
H
y
p
er
p
ar
am
e
ter
tu
n
i
n
g
is
p
er
f
o
r
m
ed
u
s
i
n
g
th
e
Gr
id
Se
ar
ch
m
eth
o
d
to
o
p
ti
m
ize
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
r
an
g
es
f
r
o
m
o
n
e
to
th
r
ee
,
w
it
h
1
to
1
5
0
n
eu
r
o
n
s
p
er
la
y
er
,
an
d
R
eL
U
is
u
s
ed
as
th
e
ac
tiv
atio
n
f
u
n
c
tio
n
.
T
h
e
m
o
d
el
is
o
p
ti
m
ized
u
s
in
g
t
h
e
A
d
a
m
o
p
ti
m
izer
,
w
h
ich
ad
ap
tiv
el
y
ad
j
u
s
ts
lear
n
in
g
r
ates
b
ased
o
n
th
e
tr
ain
in
g
d
ata.
T
h
e
tu
n
i
n
g
p
r
o
ce
s
s
in
clu
d
es
f
i
v
e
ep
o
ch
s
p
er
tr
ial,
r
e
p
ea
ted
3
0
tim
e
s
,
w
it
h
lear
n
in
g
r
ates te
s
ted
at
0
.
0
1
,
0
.
0
0
1
,
an
d
0
.
0
0
0
5
.
T
h
e
o
p
tim
al
n
u
m
b
er
o
f
ep
o
ch
s
i
s
s
elec
ted
b
ased
o
n
th
e
lo
w
est
MA
P
E
f
r
o
m
t
h
e
v
alid
ati
o
n
d
at
a.
T
o
p
r
ev
en
t
o
v
er
f
itti
n
g
d
u
r
i
n
g
th
e
tr
ai
n
i
n
g
o
f
t
h
e
h
y
b
r
id
AR
I
M
A
–
DNN
r
es
id
u
al
lear
n
in
g
m
o
d
el,
s
ev
er
al
r
e
g
u
lar
izat
io
n
s
tr
ateg
i
es
w
er
e
ap
p
lied
.
Sin
ce
th
e
AR
I
M
A
co
m
p
o
n
en
t
alr
ea
d
y
ca
p
tu
r
es
t
h
e
li
n
ea
r
te
m
p
o
r
al
d
ep
en
d
en
cies,
th
e
DNN
is
tr
ain
ed
o
n
l
y
o
n
r
es
id
u
als,
r
ed
u
ci
n
g
t
h
e
r
is
k
o
f
lear
n
in
g
r
ed
u
n
d
an
t
p
atter
n
s
.
F
u
r
th
er
m
o
r
e,
ea
r
l
y
s
to
p
p
in
g
w
a
s
i
m
p
le
m
e
n
ted
with
a
p
atie
n
ce
o
f
1
0
ep
o
ch
s
b
y
m
o
n
ito
r
in
g
t
h
e
v
alid
atio
n
lo
s
s
an
d
h
alt
in
g
tr
a
in
i
n
g
o
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
ce
ased
to
im
p
r
o
v
e,
th
er
eb
y
a
v
o
id
in
g
u
n
n
ec
es
s
ar
y
i
ter
atio
n
s
t
h
at
m
a
y
lead
to
m
e
m
o
r
izat
io
n
o
f
n
o
i
s
e.
I
n
a
d
d
itio
n
,
d
r
o
p
o
u
t
lay
er
s
w
it
h
a
r
ate
o
f
0
.
2
w
er
e
in
tr
o
d
u
ce
d
in
t
h
e
h
id
d
en
la
y
e
r
s
o
f
th
e
DNN
to
r
an
d
o
m
l
y
d
ea
ctiv
ate
a
f
r
ac
tio
n
o
f
n
e
u
r
o
n
s
d
u
r
i
n
g
tr
ain
in
g
,
w
h
ic
h
h
elp
s
p
r
ev
e
n
t
co
-
ad
ap
tatio
n
a
m
o
n
g
u
n
it
s
.
L
2
w
ei
g
h
t
r
eg
u
lar
iza
tio
n
w
it
h
a
co
ef
f
ic
ien
t
o
f
0
.
0
0
1
w
a
s
also
e
m
p
lo
y
ed
to
p
en
alize
o
v
er
l
y
co
m
p
le
x
m
o
d
els,
e
n
s
u
r
in
g
s
m
o
o
t
h
er
g
e
n
er
aliza
tio
n
.
T
h
e
r
esid
u
al
i
n
p
u
t
s
w
er
e
n
o
r
m
alize
d
u
s
i
n
g
m
i
n
–
m
a
x
s
ca
lin
g
,
w
h
ich
n
o
t
o
n
l
y
ac
ce
l
er
ates
co
n
v
er
g
e
n
ce
b
u
t
also
s
tab
ilizes
tr
ain
i
n
g
,
re
d
u
cin
g
v
ar
ia
n
ce
ac
r
o
s
s
ep
o
ch
s
.
F
in
al
l
y
,
t
h
e
d
ata
s
et
w
a
s
d
i
v
id
ed
in
to
tr
ai
n
i
n
g
,
v
alid
atio
n
,
an
d
test
in
g
s
u
b
s
et
s
to
g
u
ar
an
tee
u
n
b
iased
ev
al
u
at
io
n
.
T
o
g
eth
er
,
th
ese
m
ea
s
u
r
e
s
s
tr
en
g
th
e
n
t
h
e
r
o
b
u
s
tn
e
s
s
o
f
th
e
h
y
b
r
id
m
o
d
el,
en
s
u
r
in
g
t
h
at
th
e
i
m
p
r
o
v
e
m
e
n
t
s
in
ac
c
u
r
ac
y
ar
e
g
e
n
er
aliza
b
le
r
ath
er
th
an
ar
ti
f
ac
t
s
o
f
o
v
er
f
it
tin
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
h
yb
r
id
A
R
I
MA
a
n
d
DN
N
a
p
p
r
o
a
ch
w
ith
r
esid
u
a
l le
a
r
n
in
g
fo
r
elec
tr
ic
ve
h
icle
ch
a
r
g
in
g
…
(
W
a
h
yu
C
esa
r
)
1559
2
.
3
.
Da
t
a
prepro
ce
s
s
ing
I
n
th
e
d
ata
p
r
e
p
ar
atio
n
s
tag
e,
a
p
r
e
p
r
o
ce
s
s
in
g
p
r
o
ce
d
u
r
e
is
c
o
n
d
u
cted
o
n
ex
p
er
i
m
en
tal
d
ata
co
llected
f
r
o
m
d
ail
y
elec
tr
icit
y
co
n
s
u
m
p
tio
n
o
f
tr
an
s
ac
tio
n
a
t
th
r
e
e
d
if
f
er
e
n
t
c
h
ar
g
i
n
g
s
tatio
n
s
i
n
J
ak
ar
ta,
I
n
d
o
n
esia
d
u
r
in
g
2
0
2
1
–
2
0
2
2
.
T
h
is
p
r
o
ce
s
s
i
n
v
o
lv
e
s
d
ata
clea
n
i
n
g
a
n
d
tr
an
s
f
o
r
m
atio
n
,
as
ill
u
s
tr
ate
d
in
F
ig
u
r
e
1
.
T
h
e
d
esig
n
ed
p
r
ed
ictiv
e
m
o
d
el
is
i
m
p
le
m
e
n
ted
w
it
h
i
n
th
e
c
h
ar
g
i
n
g
s
tatio
n
ec
o
s
y
s
te
m
a
n
d
w
ill
b
e
in
teg
r
a
te
d
w
it
h
th
e
C
SM
S
ap
p
licatio
n
.
C
SMS
s
er
v
es
as
th
e
ce
n
tr
al
s
y
s
te
m
f
o
r
ea
ch
ch
ar
g
in
g
s
tatio
n
a
n
d
ca
n
b
e
ac
ce
s
s
ed
b
y
u
s
er
s
ac
r
o
s
s
v
ar
io
u
s
r
eg
io
n
s
.
T
h
e
d
iag
r
am
i
llu
s
tr
ates
i
n
Fi
g
u
r
e
2
th
e
w
o
r
k
f
lo
w
o
f
a
n
E
V
ch
ar
g
i
n
g
s
tatio
n
ec
o
s
y
s
te
m
in
teg
r
ated
w
it
h
a
f
o
r
ec
asti
n
g
m
o
d
el
f
o
r
elec
tr
icit
y
co
n
s
u
m
p
tio
n
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
w
ith
t
h
e
co
llectio
n
o
f
d
ata
f
r
o
m
m
u
ltip
le
E
V
ch
ar
g
i
n
g
s
tatio
n
s
,
w
h
ich
co
m
m
u
n
icate
u
s
i
n
g
th
e
o
p
en
ch
ar
g
e
p
o
in
t
p
r
o
t
o
co
l
(
OC
P
P
)
.
T
h
ese
d
ata
ar
e
s
to
r
ed
in
a
ce
n
tr
al
d
atab
as
e
an
d
u
n
d
er
g
o
p
r
ep
r
o
ce
s
s
in
g
,
w
h
ic
h
i
n
clu
d
es
d
ata
clea
n
i
n
g
,
tr
an
s
f
o
r
m
atio
n
,
an
d
s
p
litt
i
n
g
i
n
to
tr
ain
in
g
an
d
test
in
g
s
et
s
.
T
h
e
d
ata
ar
e
ca
te
g
o
r
ized
in
to
t
w
o
g
r
o
u
p
s
:
d
atasets
w
i
t
h
w
ea
t
h
e
r
v
ar
iab
les
an
d
d
ataset
s
w
it
h
o
u
t
w
ea
t
h
er
v
ar
iab
les.
O
n
ce
p
r
ep
r
o
ce
s
s
in
g
i
s
co
m
p
lete,
t
h
e
m
o
d
el
tr
ai
n
i
n
g
a
n
d
test
i
n
g
p
h
ase
ta
k
es
p
lace
.
T
h
is
s
tep
in
v
o
lv
e
s
h
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
,
m
o
d
el
tr
ain
in
g
f
o
r
f
o
r
ec
asti
n
g
elec
tr
icit
y
co
n
s
u
m
p
tio
n
,
an
d
p
er
f
o
r
m
an
c
e
ev
al
u
atio
n
u
s
i
n
g
m
e
tr
ics
s
u
ch
as
M
A
P
E
o
r
R
MSE
.
T
h
e
tr
ain
ed
f
o
r
ec
ast
in
g
m
o
d
el
is
t
h
en
in
teg
r
ated
i
n
to
th
e
s
y
s
te
m
u
s
in
g
t
h
e
d
atab
ase
ce
n
tr
al
s
y
s
te
m
,
allo
w
i
n
g
i
t
to
p
r
ed
ict
f
u
t
u
r
e
elec
tr
icit
y
co
n
s
u
m
p
t
io
n
.
T
h
e
ce
n
tr
al
s
y
s
te
m
co
n
ti
n
u
o
u
s
l
y
u
p
d
ates
an
d
d
is
p
la
y
s
n
e
w
d
ata
w
h
ile
also
in
te
g
r
atin
g
f
o
r
ec
ast
r
es
u
lt
s
.
T
h
ese
f
o
r
ec
asts
ar
e
u
s
ed
to
en
h
a
n
ce
t
h
e
e
f
f
icie
n
c
y
o
f
c
h
ar
g
in
g
s
tatio
n
s
b
y
o
p
tim
izin
g
elec
tr
icit
y
s
u
p
p
l
y
an
d
d
e
m
a
n
d
m
a
n
a
g
e
m
en
t.
T
h
e
o
v
er
all
s
y
s
te
m
i
m
p
r
o
v
e
s
t
h
e
r
eliab
ilit
y
o
f
E
V
ch
ar
g
i
n
g
in
f
r
astr
u
ct
u
r
e,
en
s
u
r
i
n
g
a
s
tab
le
an
d
ef
f
icie
n
t e
n
er
g
y
d
is
tr
ib
u
tio
n
n
et
w
o
r
k
.
Fig
u
r
e
2
.
T
h
e
f
r
am
e
w
o
r
k
o
f
c
h
ar
g
i
n
g
s
tatio
n
co
n
s
u
m
p
tio
n
f
o
r
ec
ast
[
5
]
T
h
e
d
ata
clea
n
in
g
p
r
o
ce
s
s
i
s
ca
r
r
ied
o
u
t
b
y
s
elec
ti
n
g
o
n
e
d
ataset
f
r
o
m
th
r
ee
c
h
ar
g
in
g
s
tatio
n
s
i
n
J
ak
ar
ta
to
b
e
u
s
ed
as
th
e
p
r
im
ar
y
d
ataset.
Mis
s
in
g
d
ata
is
th
en
f
illed
u
s
in
g
th
e
alg
eb
r
aic
av
er
ag
i
n
g
m
et
h
o
d
,
as
d
escr
ib
ed
in
(
3
)
,
u
n
d
e
r
th
e
ass
u
m
p
tio
n
th
a
t
th
e
m
i
s
s
i
n
g
d
ata
r
ep
r
esen
ts
th
e
av
er
ag
e
co
n
s
u
m
p
tio
n
o
f
th
e
t
w
o
n
ea
r
est
c
h
ar
g
i
n
g
s
tatio
n
s
.
T
h
e
alg
eb
r
aic
av
er
ag
in
g
m
et
h
o
d
e
s
ti
m
ates
m
i
s
s
i
n
g
d
ata
b
ased
o
n
th
e
a
v
er
ag
e
d
ata
f
r
o
m
s
e
v
er
al
n
ea
r
b
y
c
h
ar
g
i
n
g
s
tatio
n
s
.
T
h
is
ap
p
r
o
ac
h
is
f
o
r
m
u
lat
ed
u
s
in
g
(
3
)
[
2
3
]
.
=
+
+
n
(
3
)
th
is
s
t
u
d
y
,
m
is
s
in
g
d
ata
at
c
h
ar
g
i
n
g
s
tatio
n
(
d
en
o
ted
as
)
is
esti
m
ated
u
s
i
n
g
d
ata
f
r
o
m
t
h
e
n
ea
r
es
t
ch
ar
g
i
n
g
s
tatio
n
s
,
,
an
d
(
,
,
)
,
w
it
h
r
ep
r
esen
tin
g
t
h
e
n
u
m
b
e
r
o
f
s
tatio
n
s
co
n
s
i
d
er
ed
.
T
h
e
d
ata
tr
an
s
f
o
r
m
atio
n
p
r
o
ce
s
s
s
tar
ts
b
y
s
elec
ti
n
g
r
elev
a
n
t
a
ttrib
u
te
s
,
w
h
ic
h
i
n
cl
u
d
e
elec
tr
icit
y
co
n
s
u
m
p
t
io
n
f
r
o
m
t
h
e
p
r
ev
io
u
s
s
e
v
en
d
a
y
s
(
a
w
i
n
d
o
w
s
ize
o
f
7
)
.
A
d
d
itio
n
all
y
,
th
e
d
ay
o
f
th
e
w
ee
k
is
en
co
d
ed
n
u
m
er
icall
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
5
5
-
1
565
1560
(
=
1
th
r
o
u
g
h
=
7
)
.
T
h
ese
tr
an
s
f
o
r
m
ed
attr
ib
u
tes
f
o
r
m
th
e
in
p
u
t
f
ea
tu
r
es,
to
tali
n
g
ei
g
h
t,
w
h
ile
t
h
e
elec
tr
icit
y
co
n
s
u
m
p
t
io
n
f
o
r
th
e
n
ex
t d
a
y
s
er
v
e
s
as t
h
e
o
u
tp
u
t la
b
el.
2
.
4
.
E
v
a
lua
t
i
o
n
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
m
o
d
el
w
i
ll
b
e
as
s
ess
ed
u
s
in
g
th
e
M
A
P
E
,
w
h
ic
h
s
er
v
es
to
v
al
id
ate
its
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
.
M
A
P
E
q
u
a
n
ti
f
ie
s
r
elati
v
e
er
r
o
r
b
y
ca
lcu
la
tin
g
th
e
p
er
ce
n
ta
g
e
d
i
f
f
er
e
n
ce
b
et
w
ee
n
p
r
ed
icted
an
d
ac
tu
al
v
al
u
es.
T
h
is
m
e
tr
ic
is
e
s
p
ec
iall
y
b
e
n
e
f
icial
w
h
e
n
t
h
e
s
ca
le
o
f
th
e
p
r
ed
icted
v
a
r
iab
le
p
la
y
s
a
cr
itical
r
o
le
in
ev
a
lu
ati
n
g
f
o
r
ec
ast
p
r
ec
is
io
n
.
A
s
a
w
id
el
y
u
s
ed
lo
s
s
f
u
n
ct
io
n
in
r
e
g
r
ess
io
n
tas
k
s
,
M
A
P
E
o
f
f
er
s
a
n
in
tu
i
tiv
e
u
n
d
er
s
ta
n
d
in
g
o
f
p
r
ed
ictio
n
e
r
r
o
r
s
in
r
elativ
e
ter
m
s
[
2
4
]
.
E
x
p
r
ess
ed
as
a
p
er
ce
n
tag
e,
it
r
ef
lects
t
h
e
av
er
a
g
e
d
ev
iatio
n
b
et
w
ee
n
ac
tu
al
a
n
d
p
r
ed
icted
v
alu
es.
M
A
P
E
i
s
co
m
m
o
n
l
y
ap
p
lied
in
ti
m
e
s
er
ies
an
al
y
s
is
to
ev
a
lu
a
te
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
.
T
h
e
f
o
r
m
u
la
f
o
r
MA
P
E
is
p
r
esen
ted
(
4
)
[
2
5
]
.
=
1
∑
_
−
ŷ
_
_
=
1
100%
(
4
)
w
h
er
e
th
e
v
ar
iab
le
s
in
(
4
)
ar
e
d
ef
in
ed
is
th
e
n
u
m
b
er
o
f
s
a
m
p
les
in
th
e
d
ataset,
ᵢ
is
th
e
ac
tu
al
v
alu
e,
an
d
ŷᵢ
is
th
e
p
r
ed
icted
v
alu
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
ARI
M
A
m
o
delin
g
I
n
th
is
s
t
u
d
y
,
th
e
d
ataset
o
f
E
V
ch
ar
g
in
g
d
e
m
a
n
d
is
p
r
ed
i
cted
u
s
in
g
th
e
A
R
I
M
A
m
o
d
e
l,
w
h
ic
h
is
ef
f
ec
tiv
e
w
h
e
n
th
e
h
is
to
r
ical
d
ata
ex
h
ib
its
a
li
n
ea
r
an
d
/o
r
co
n
s
is
ten
t
s
ea
s
o
n
al
p
atter
n
.
AR
I
MA
p
er
f
o
r
m
s
w
e
ll
o
n
s
tab
le
t
i
m
e
s
er
ies
d
ata
th
a
t
is
n
o
t
h
ea
v
i
l
y
in
f
l
u
e
n
ce
d
b
y
co
m
p
lex
e
x
ter
n
al
f
ac
to
r
s
.
D
ail
y
o
r
w
ee
k
l
y
E
V
d
em
a
n
d
o
f
ten
s
h
o
w
s
r
ec
u
r
r
in
g
p
atter
n
s
,
m
a
k
in
g
A
R
I
M
A
q
u
ite
ef
f
ec
ti
v
e
f
o
r
s
h
o
r
t
-
ter
m
d
em
a
n
d
f
o
r
ec
asti
n
g
w
h
e
n
th
e
E
V
ch
ar
g
in
g
d
ata
h
a
s
s
u
f
f
icie
n
tl
y
s
tab
le
h
i
s
to
r
ical
p
atter
n
s
.
I
n
s
u
ch
ca
s
e
s
,
AR
I
M
A
ca
n
b
e
u
s
ed
as
a
b
aselin
e
p
r
ed
ictio
n
m
o
d
el.
Ho
w
e
v
er
,
th
er
e
ar
e
li
m
itatio
n
s
.
AR
I
M
A
is
les
s
o
p
ti
m
al
w
h
en
th
e
d
e
m
a
n
d
p
atter
n
is
h
i
g
h
l
y
n
o
n
-
li
n
ea
r
an
d
in
f
l
u
en
ce
d
b
y
m
a
n
y
ex
ter
n
al
v
ar
iab
les
s
u
ch
as
w
ea
t
h
er
,
elec
tr
icit
y
p
r
ices,
p
r
o
m
o
tio
n
s
,
o
r
s
p
ec
if
ic
e
v
en
t
s
.
I
n
s
u
ch
ca
s
es,
h
y
b
r
id
m
o
d
els
ar
e
u
s
ed
to
h
an
d
le
m
o
r
e
co
m
p
le
x
n
o
n
-
li
n
ea
r
d
ata,
s
u
ch
as
DN
N
,
w
h
ich
ar
e
m
o
r
e
ad
ap
tiv
e
to
ex
ter
n
al
(
ex
o
g
e
n
o
u
s
)
f
ac
to
r
s
a
n
d
t
y
p
ic
all
y
p
r
o
d
u
ce
m
o
r
e
ac
cu
r
ate
r
esu
lt
s
.
I
n
t
h
is
s
t
u
d
y
,
to
ad
d
r
ess
th
e
co
m
p
lex
it
y
o
f
d
eter
m
in
i
n
g
th
e
o
p
ti
m
a
l
p
ar
am
eter
s
(
,
,
)
,
th
e
_
f
u
n
c
tio
n
f
r
o
m
th
e
lib
r
ar
y
is
u
s
ed
,
a
s
it
a
u
to
m
atica
ll
y
e
v
a
lu
ates
v
ar
io
u
s
p
ar
a
m
eter
co
m
b
i
n
atio
n
s
u
s
in
g
in
f
o
r
m
at
i
o
n
cr
iter
ia
(
s
u
ch
as
A
k
ai
k
e
in
f
o
r
m
at
io
n
cr
iter
io
n
(
A
I
C
)
or
B
a
y
esia
n
in
f
o
r
m
ati
o
n
cr
iter
io
n
(
B
I
C
)
)
to
s
elec
t
th
e
b
est
m
o
d
el
[
2
6
]
.
T
h
e
d
iv
is
i
o
n
o
f
th
e
d
ataset
i
n
to
tr
ain
i
n
g
an
d
test
i
n
g
s
ets
s
ig
n
i
f
ica
n
tl
y
a
f
f
ec
ts
t
h
e
ac
c
u
r
ac
y
o
f
th
e
A
R
I
M
A
m
o
d
el,
a
s
i
t
r
elies
h
ea
v
il
y
o
n
t
h
e
c
h
r
o
n
o
l
o
g
ical
o
r
d
er
o
f
d
ata
in
a
ti
m
e
s
er
ies.
AR
I
M
A
lear
n
s
f
r
o
m
p
ast
p
atter
n
s
(
s
u
ch
a
s
tr
en
d
s
a
n
d
s
ea
s
o
n
al
it
y
)
to
f
o
r
ec
ast
th
e
f
u
t
u
r
e.
T
h
er
ef
o
r
e,
if
th
e
d
ata
is
s
p
l
it
r
an
d
o
m
l
y
(
n
o
n
-
c
h
r
o
n
o
lo
g
i
ca
ll
y
)
,
th
e
p
r
ed
ictio
n
s
b
ec
o
m
e
in
v
alid
an
d
th
e
ac
cu
r
ac
y
d
ec
r
ea
s
es.
I
n
t
h
e
AR
I
M
A
m
o
d
el
ev
al
u
atio
n
,
v
ar
i
o
u
s
co
m
b
i
n
atio
n
s
o
f
p
ar
a
m
ete
r
s
,
,
an
d
w
er
e
test
ed
to
f
in
d
t
h
e
o
p
ti
m
a
l
co
n
f
ig
u
r
atio
n
.
T
h
e
d
ataset
w
a
s
s
p
lit
in
to
d
if
f
er
en
t
tr
ain
-
tes
t
r
atio
s
(
6
0
:4
0
,
7
0
:
3
0
,
8
0
:2
0
,
an
d
9
0
:1
0
)
to
ass
ess
m
o
d
el
p
er
f
o
r
m
an
ce
.
Us
in
g
M
A
P
E
as
th
e
e
v
al
u
atio
n
m
etr
ic
,
th
e
b
est
r
esu
l
t
w
a
s
ac
h
iev
ed
w
i
th
a
9
0
:1
0
s
p
lit,
w
h
er
e
th
e
A
R
I
M
A
(
6
,
3
,
2
)
m
o
d
el
p
r
o
d
u
ce
d
th
e
lo
w
e
s
t
er
r
o
r
,
w
i
th
a
M
A
P
E
o
f
1
6
.
4
9
%.
T
h
is
in
d
icate
s
th
a
t
AR
I
M
A
(
6
,
3,
2
)
is
th
e
o
p
ti
m
al
co
n
f
i
g
u
r
atio
n
f
o
r
th
is
d
ataset.
I
n
th
i
s
s
tag
e,
a
n
A
R
I
M
A
m
o
d
el
is
ap
p
lied
to
th
e
tim
e
s
er
ie
s
d
ata
en
er
g
y
d
e
m
an
d
E
V
to
ca
p
tu
r
e
its
lin
ea
r
co
m
p
o
n
en
t
s
,
s
u
c
h
as
tr
e
n
d
s
an
d
s
ea
s
o
n
alit
y
.
On
ce
th
e
A
R
I
M
A
m
o
d
el
is
tr
ain
ed
an
d
m
ak
e
s
f
o
r
ec
asts
,
r
esid
u
als
ar
e
ca
lc
u
lated
.
T
h
ese
r
esid
u
als
r
ep
r
esen
t
t
h
e
u
n
e
x
p
lain
ed
p
ar
t
o
f
th
e
d
ata
s
p
ec
if
icall
y
,
t
h
e
n
o
n
li
n
ea
r
p
atter
n
s
t
h
at
AR
I
M
A
co
u
l
d
n
o
t
ca
p
tu
r
e.
T
h
e
r
esid
u
al
is
t
h
e
d
if
f
er
e
n
ce
b
et
w
ee
n
th
e
ac
tu
al
o
b
s
er
v
ed
v
alu
e
a
n
d
th
e
p
r
ed
ictio
n
m
ad
e
b
y
t
h
e
AR
I
M
A
m
o
d
el.
T
h
ese
r
esid
u
als
as
i
n
p
u
t
f
o
r
a
DNN
to
m
o
d
el
t
h
e
n
o
n
li
n
ea
r
r
elatio
n
s
h
ip
s
i
n
th
e
d
ata.
Si
n
c
e
AR
I
M
A
h
a
s
alr
ea
d
y
m
o
d
ele
d
th
e
lin
ea
r
p
ar
t
,
th
e
DNN
f
o
cu
s
e
s
o
n
lear
n
i
n
g
th
e
co
m
p
le
x
,
n
o
n
li
n
ea
r
s
tr
u
ct
u
r
es
th
at
r
e
m
ai
n
i
n
t
h
e
r
esid
u
als.
T
o
g
eth
er
,
t
h
is
t
w
o
-
s
tep
m
o
d
eli
n
g
p
r
o
ce
s
s
e
n
h
a
n
ce
s
f
o
r
ec
ast
ac
cu
r
ac
y
b
y
h
y
b
r
id
AR
I
M
A
-
DNN
m
eth
o
d
g
et
s
co
m
b
in
i
n
g
th
e
s
tr
en
g
t
h
s
o
f
A
R
I
MA
f
o
r
lin
ea
r
tr
en
d
s
an
d
DNN
f
o
r
n
o
n
li
n
ea
r
d
y
n
a
m
ics.
3
.
2
.
Resid
ua
l
m
o
del
ing
w
it
h dee
p neura
l net
w
o
rk
s
T
h
e
r
esid
u
al
m
o
d
el
w
it
h
DN
N
is
d
ev
elo
p
ed
th
r
o
u
g
h
a
s
y
s
t
e
m
atic
h
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
p
r
o
ce
s
s
to
o
b
tain
o
p
ti
m
al
p
ar
a
m
eter
s
f
o
r
th
e
M
L
P
ar
ch
itectu
r
e.
Af
ter
f
i
ttin
g
t
h
e
A
R
I
M
A
m
o
d
el,
th
e
r
esid
u
als
d
e
f
i
n
ed
as
th
e
d
if
f
er
en
ce
b
et
w
ee
n
th
e
o
b
s
er
v
ed
v
al
u
es
an
d
AR
I
M
A
p
r
ed
ictio
n
s
ar
e
ex
tr
ac
ted
.
T
h
ese
r
esid
u
als
ar
e
f
ir
s
t
n
o
r
m
alize
d
to
a
s
tan
d
ar
d
s
ca
le
an
d
p
r
o
ce
s
s
ed
u
s
in
g
a
s
lid
in
g
w
in
d
o
w
ap
p
r
o
ac
h
to
g
en
er
ate
s
eq
u
en
t
ial
in
p
u
t
-
o
u
tp
u
t
p
air
s
s
u
itab
le
f
o
r
DNN
lear
n
i
n
g
.
T
h
is
e
n
s
u
r
es
th
at
te
m
p
o
r
al
d
e
p
en
d
e
n
cies
i
n
t
h
e
r
e
s
id
u
al
p
atter
n
s
ar
e
p
r
eser
v
ed
.
T
o
f
u
r
th
er
en
r
ic
h
th
e
i
n
p
u
t
r
ep
r
esen
tatio
n
,
ca
teg
o
r
ical
f
ea
tu
r
es
s
u
ch
as
t
h
e
d
a
y
o
f
t
h
e
w
ee
k
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
h
yb
r
id
A
R
I
MA
a
n
d
DN
N
a
p
p
r
o
a
ch
w
ith
r
esid
u
a
l le
a
r
n
in
g
fo
r
elec
tr
ic
ve
h
icle
ch
a
r
g
in
g
…
(
W
a
h
yu
C
esa
r
)
1561
(
en
co
d
ed
as
n
u
m
er
ic
1
-
7
)
ar
e
in
te
g
r
ated
,
allo
w
i
n
g
th
e
n
et
w
o
r
k
to
ca
p
tu
r
e
p
er
io
d
ic
n
o
n
lin
e
ar
v
ar
iatio
n
s
in
t
h
e
ch
ar
g
i
n
g
d
e
m
a
n
d
.
T
h
e
u
s
e
o
f
th
e
DN
N
is
m
o
t
i
v
ated
b
y
its
s
tr
o
n
g
ca
p
ab
ilit
y
to
m
o
d
el
n
o
n
li
n
ea
r
an
d
n
o
n
-
s
tat
io
n
ar
y
co
m
p
o
n
e
n
t
s
t
h
at
ca
n
n
o
t
b
e
ef
f
ec
tiv
e
l
y
ca
p
t
u
r
ed
b
y
A
R
I
MA
alo
n
e.
A
g
r
id
-
b
ased
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
s
tr
ateg
y
w
as
co
n
d
u
cted
to
o
p
ti
m
ize
t
h
e
n
u
m
b
er
o
f
h
id
d
en
l
a
y
er
s
,
n
e
u
r
o
n
co
u
n
t
s
,
lear
n
i
n
g
r
ate,
an
d
tr
ain
in
g
ep
o
ch
s
.
Sp
ec
if
ica
ll
y
,
m
o
d
els
w
it
h
o
n
e
to
t
h
r
ee
h
id
d
en
la
y
e
r
s
w
er
e
ev
al
u
ated
ac
r
o
s
s
d
i
f
f
e
r
en
t
tr
ain
–
te
s
t
s
p
li
t
r
atio
s
(
9
0
:1
0
,
8
0
:
2
0
,
7
0
:3
0
,
a
n
d
6
0
:4
0
)
.
T
h
e
tu
n
i
n
g
p
r
o
ce
s
s
in
co
r
p
o
r
ated
o
v
er
f
itti
n
g
m
i
t
ig
atio
n
tec
h
n
iq
u
e
s
s
u
c
h
as
ea
r
l
y
s
to
p
p
in
g
,
d
r
o
p
o
u
t
r
eg
u
lar
izatio
n
(
0
.
2
-
0
.
5
a
cr
o
s
s
h
id
d
en
la
y
er
s
)
,
an
d
L
2
w
e
ig
h
t
p
en
altie
s
,
en
s
u
r
in
g
t
h
e
m
o
d
el
g
e
n
er
alize
s
w
e
ll to
u
n
s
ee
n
d
ata.
T
h
e
b
est
-
p
er
f
o
r
m
in
g
co
n
f
i
g
u
r
atio
n
w
a
s
o
b
tain
ed
w
it
h
t
w
o
h
id
d
en
la
y
er
s
co
n
s
i
s
ti
n
g
o
f
6
4
an
d
3
2
n
eu
r
o
n
s
r
esp
ec
tiv
e
l
y
,
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
1
,
R
eL
U
ac
tiv
atio
n
f
u
n
c
tio
n
s
,
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
3
,
an
d
1
,
5
0
0
tr
ain
i
n
g
ep
o
ch
s
u
n
d
er
a
9
0
:1
0
s
p
lit
r
atio
.
T
h
is
co
n
f
ig
u
r
ati
o
n
ac
h
ie
v
ed
a
MA
P
E
o
f
0
.
3
9
%
o
n
th
e
r
esid
u
al
f
o
r
ec
asti
n
g
tas
k
,
co
n
f
ir
m
i
n
g
t
h
at
th
e
r
esid
u
al
-
b
ased
DNN
n
o
t
o
n
ly
ef
f
ec
t
iv
el
y
co
m
p
le
m
e
n
ts
A
R
I
M
A
b
u
t
also
s
ig
n
i
f
ica
n
tl
y
e
n
h
an
ce
s
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
y
ca
p
tu
r
i
n
g
co
m
p
lex
n
o
n
l
in
ea
r
d
y
n
a
m
ics.
3
.
3
.
F
ina
l f
o
re
ca
s
t
g
ener
a
t
io
n
h
y
brid AR
I
M
A
-
DNN
T
h
e
f
in
al
f
o
r
ec
ast
g
en
er
atio
n
in
t
h
e
h
y
b
r
id
A
R
I
M
A
-
DN
N
r
esid
u
al
lear
n
i
n
g
ap
p
r
o
ac
h
in
v
o
lv
e
s
co
m
b
i
n
i
n
g
t
h
e
s
tr
e
n
g
th
s
o
f
b
o
th
li
n
ea
r
an
d
n
o
n
l
in
ea
r
m
o
d
elin
g
to
p
r
o
d
u
ce
a
m
o
r
e
ac
c
u
r
ate
p
r
ed
ictio
n
.
T
h
e
AR
I
M
A
m
o
d
el
i
s
u
s
ed
to
f
o
r
ec
ast
th
e
li
n
ea
r
co
m
p
o
n
en
ts
o
f
t
h
e
ti
m
e
s
er
ies
d
ata,
s
u
ch
a
s
tr
en
d
s
a
n
d
s
ea
s
o
n
ali
t
y
.
T
h
e
r
esid
u
a
ls
ca
lc
u
lated
as
t
h
e
d
i
f
f
er
e
n
ce
b
et
w
e
en
t
h
e
ac
tu
a
l
v
al
u
es
an
d
t
h
e
AR
I
M
A
p
r
ed
ictio
n
s
ar
e
o
b
tain
ed
.
T
h
ese
r
esid
u
als,
w
h
ic
h
r
ep
r
esen
t
t
h
e
n
o
n
lin
ea
r
p
atter
n
s
n
o
t
ca
p
tu
r
ed
b
y
AR
I
MA
,
ar
e
th
e
n
u
s
ed
to
tr
ai
n
a
DNN.
AR
I
M
A
m
o
d
els
ca
p
tu
r
e
li
n
ea
r
tr
en
d
s
,
w
h
ile
DNNs
h
a
n
d
le
co
m
p
le
x
n
o
n
li
n
ea
r
p
atter
n
s
.
I
n
th
is
h
y
b
r
id
ap
p
r
o
ac
h
,
th
e
DN
N
lear
n
s
to
p
r
e
d
ict
th
e
r
esid
u
als
f
r
o
m
th
e
A
R
I
M
A
m
o
d
el.
T
h
is
d
iv
i
s
io
n
o
f
tas
k
s
r
ed
u
ce
s
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
in
th
e
D
NN.
T
h
e
f
in
al
f
o
r
ec
ast
is
o
b
tain
ed
b
y
co
m
b
i
n
i
n
g
b
o
t
h
m
o
d
els
u
s
i
n
g
th
e
f
o
r
m
u
la
is
th
e
f
in
a
l
p
r
ed
ictio
n
is
o
b
tain
ed
b
y
ad
d
in
g
th
e
f
o
r
ec
ast
f
r
o
m
th
e
AR
I
M
A
m
o
d
el
w
it
h
th
e
r
esid
u
a
l
p
r
ed
ictio
n
g
en
er
ated
b
y
th
e
DNN
m
o
d
el.
T
h
is
co
m
b
in
at
io
n
lev
er
a
g
es
t
h
e
co
m
p
le
m
en
ta
r
y
s
tr
en
g
t
h
s
o
f
b
o
t
h
m
o
d
el
s
to
i
m
p
r
o
v
e
o
v
er
all
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
3
(
a)
s
h
o
w
s
t
h
at
t
h
e
AR
I
M
A
(
6
,
3,
2
)
m
o
d
el
ca
n
f
o
llo
w
t
h
e
g
e
n
er
al
tr
en
d
o
f
E
V
ch
ar
g
i
n
g
d
em
a
n
d
,
b
u
t
f
ail
s
to
ca
p
tu
r
e
s
h
o
r
t
-
ter
m
f
lu
ct
u
atio
n
s
a
n
d
s
u
d
d
en
p
ea
k
s
,
r
es
u
lti
n
g
in
a
r
ela
ti
v
el
y
h
i
g
h
M
A
P
E
o
f
1
6
.
4
9
%.
I
n
co
n
tr
ast,
Fig
u
r
e
3
(
b
)
s
h
o
w
s
t
h
e
h
y
b
r
id
A
R
I
M
A
-
DNN
m
o
d
el,
w
h
o
s
e
p
r
ed
icted
v
alu
e
s
ar
e
m
u
c
h
m
o
r
e
clo
s
el
y
ali
g
n
ed
w
it
h
ac
tu
al
d
e
m
a
n
d
,
an
d
s
u
cc
es
s
f
u
ll
y
tr
ac
k
b
o
th
lo
n
g
-
ter
m
tr
e
n
d
s
an
d
n
o
n
lin
ea
r
v
ar
iatio
n
s
.
B
y
co
m
b
i
n
i
n
g
AR
I
MA
’
s
ad
v
a
n
ta
g
e
in
m
o
d
eli
n
g
lin
ea
r
p
atter
n
s
w
ith
DN
N
’
s
ab
ilit
y
to
ca
p
tu
r
e
n
o
n
li
n
ea
r
r
esid
u
al
s
,
th
e
h
y
b
r
i
d
m
o
d
el
ac
h
iev
e
s
s
i
g
n
if
ica
n
tl
y
b
etter
ac
cu
r
ac
y
,
as
r
e
f
lecte
d
b
y
it
s
lo
w
er
M
A
P
E
o
f
1
.
7
8
%.
T
ab
le
1
co
m
p
ar
es t
h
is
w
i
th
o
t
h
er
co
m
p
ar
ab
le
d
ee
p
lear
n
in
g
m
et
h
o
d
s
.
(
a)
(
b
)
Fig
u
r
e
3
.
E
v
alu
atio
n
:
(
a)
AR
I
MA
p
r
ed
ictio
n
v
s
ac
t
u
al
an
d
(
b
)
h
y
b
r
id
A
R
I
M
A
-
D
NN
p
r
ed
ictio
n
v
s
ac
tu
al
T
ab
le
1
.
Fo
r
ec
asti
n
g
b
est ac
cu
r
ac
y
co
m
p
ar
i
s
o
n
M
o
d
e
l
M
A
P
E
(
%)
R
M
S
E
(
k
W
h
)
M
A
E
(
k
W
h
)
A
N
N
-
M
L
P
L
S
T
M
1
3
.
8
9
1
3
.
0
3
1
1
1
.
4
7
8
8
.
6
6
9
4
.
7
3
7
5
.
3
7
A
R
I
M
A
-
D
N
N
(
r
e
si
d
u
a
l
-
b
a
se
d
)
1
.
7
8
1
2
.
0
7
1
0
.
2
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
5
5
-
1
565
1562
T
ab
le
1
co
m
p
ar
es
th
e
f
o
r
ec
ast
in
g
ac
c
u
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
A
N
N
-
M
L
P
,
L
ST
M,
an
d
h
y
b
r
id
A
R
I
M
A
-
DNN
(
r
esid
u
al
-
b
ased
)
m
o
d
els
.
As
s
h
o
w
n
in
Fi
g
u
r
e
3
(
a)
,
tr
ad
itio
n
al
AR
I
M
A
is
ef
f
ec
ti
v
e
f
o
r
lo
n
g
-
ter
m
tr
en
d
s
b
u
t
s
tr
u
g
g
le
s
w
it
h
n
o
n
li
n
ea
r
f
lu
ct
u
atio
n
s
,
w
h
ile
A
N
N
-
M
L
P
an
d
L
ST
M
p
r
o
v
id
e
b
etter
ac
cu
r
ac
y
b
u
t
r
e
m
a
in
less
co
n
s
i
s
ten
t.
I
n
co
n
tr
ast,
th
e
h
y
b
r
id
r
esid
u
al
lear
n
in
g
ap
p
r
o
ac
h
ef
f
ec
t
iv
el
y
ca
p
t
u
r
es
b
o
th
li
n
ea
r
a
n
d
n
o
n
li
n
ea
r
d
y
n
a
m
ics,
ac
h
iev
in
g
th
e
b
e
s
t
o
v
er
all
p
er
f
o
r
m
a
n
ce
w
it
h
a
M
A
P
E
o
f
1
.
7
8
%,
an
R
M
SE
o
f
1
2
.
0
7
k
W
h
,
an
d
a
MA
E
o
f
1
0
.
2
6
k
W
h
,
m
a
k
i
n
g
it
th
e
b
est
-
p
er
f
o
r
m
i
n
g
m
o
d
el
co
m
p
ar
ed
to
s
in
g
le
-
m
o
d
el
ap
p
r
o
ac
h
es
an
d
ac
h
ie
v
i
n
g
b
etter
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
co
m
p
ar
ed
to
u
s
i
n
g
o
n
l
y
AR
I
M
A
,
A
NN
-
M
L
P
,
o
r
L
ST
M.
No
tab
ly
,
th
e
h
y
b
r
id
AR
I
M
A
-
D
NN
co
n
s
i
s
te
n
tl
y
o
u
tp
er
f
o
r
m
s
t
h
e
s
e
q
u
en
ce
-
b
ased
L
ST
M
b
en
ch
m
ar
k
,
h
ig
h
li
g
h
ti
n
g
it
s
r
o
b
u
s
tn
es
s
a
n
d
s
u
itab
ilit
y
f
o
r
EV
ch
ar
g
in
g
d
e
m
an
d
f
o
r
ec
ast
in
g
.
T
h
e
d
if
f
er
en
ce
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
an
d
th
e
AR
I
M
A
-
ANN
h
y
b
r
id
(
d
is
cr
ete
w
av
e
let
tr
an
s
f
o
r
m
(
DW
T
)
-
b
ased
)
[
1
0
]
in
p
r
ev
io
u
s
r
esear
ch
lies
i
n
it
s
in
te
g
r
atio
n
s
tr
ate
g
y
.
T
h
e
D
W
T
-
b
ased
m
eth
o
d
d
ec
o
m
p
o
s
es
th
e
s
er
ies
i
n
to
f
r
eq
u
e
n
c
y
c
o
m
p
o
n
e
n
ts
,
w
h
ile
AR
I
M
A
-
DNN
u
s
es
r
esid
u
a
l
lear
n
in
g
,
w
h
ic
h
allo
w
s
A
NN
to
d
ir
ec
tly
m
o
d
el
th
e
n
o
n
l
i
n
ea
r
er
r
o
r
s
lef
t
b
y
AR
I
M
A
.
T
h
is
d
es
ig
n
i
m
p
r
o
v
e
s
ef
f
icie
n
c
y
a
n
d
ac
cu
r
ac
y
,
w
it
h
e
m
p
ir
ical
r
es
u
lts
co
n
f
ir
m
in
g
th
at
A
R
I
M
A
-
DN
N
p
r
o
v
id
es
s
u
p
er
io
r
p
e
r
f
o
r
m
a
n
c
e
(
MA
P
E
1
.
7
8
%)
c
o
m
p
ar
ed
to
th
e
DW
T
-
b
ased
A
R
I
M
A
-
ANN
h
y
b
r
id
(
MA
P
E
1
.
9
4
%),
d
em
o
n
s
tr
ati
n
g
its
p
o
w
er
i
n
ca
p
tu
r
i
n
g
co
m
p
lex
n
o
n
lin
ea
r
d
e
m
a
n
d
p
atter
n
s
i
n
r
ea
l
-
w
o
r
ld
EV
ch
ar
g
i
n
g
d
ata.
Fro
m
a
co
m
p
u
ta
tio
n
al
p
er
s
p
ec
tiv
e,
th
e
h
y
b
r
id
A
R
I
M
A
–
DNN
m
o
d
el
r
em
ai
n
s
ef
f
icie
n
t
b
ec
au
s
e
AR
I
M
A
p
r
o
v
id
es
f
ast
li
n
ea
r
co
m
p
o
n
e
n
t
e
s
ti
m
atio
n
,
t
h
er
eb
y
r
ed
u
ci
n
g
t
h
e
r
esid
u
al
co
m
p
lex
it
y
f
ed
in
to
t
h
e
DNN.
T
h
is
d
ec
o
m
p
o
s
itio
n
h
el
p
s
s
h
o
r
ten
tr
ain
i
n
g
ti
m
e
co
m
p
ar
ed
to
tr
ain
in
g
a
s
tan
d
alo
n
e
d
ee
p
m
o
d
el
o
n
th
e
f
u
ll
r
a
w
d
ata.
W
h
ile
DNNs
t
y
p
ica
ll
y
r
e
q
u
ir
e
h
i
g
h
er
co
m
p
u
tatio
n
a
l
r
eso
u
r
ce
s
,
th
e
r
esid
u
al
lear
n
i
n
g
d
esi
g
n
allo
w
s
th
e
n
e
t
w
o
r
k
to
f
o
cu
s
o
n
n
o
n
lin
ea
r
p
atter
n
s
w
ith
f
e
wer
p
ar
am
eter
s
,
i
m
p
r
o
v
i
n
g
b
o
th
co
n
v
er
g
e
n
ce
s
p
ee
d
an
d
in
f
er
en
ce
ef
f
ic
ien
c
y
.
I
n
ter
m
s
o
f
r
ea
l
-
ti
m
e
ap
p
licab
ilit
y
,
th
e
AR
I
M
A
co
m
p
o
n
e
n
t
ca
n
b
e
u
p
d
ated
in
cr
e
m
e
n
tall
y
w
it
h
m
i
n
i
m
al
o
v
er
h
ea
d
,
an
d
th
e
tr
ain
ed
DNN
ca
n
g
en
er
ate
p
r
ed
ictio
n
s
in
n
ea
r
r
ea
l
ti
m
e
o
n
ce
d
ep
lo
y
ed
.
T
h
is
m
a
k
es
t
h
e
h
y
b
r
id
f
r
am
e
w
o
r
k
s
u
i
tab
le
f
o
r
in
t
eg
r
atio
n
in
to
E
V
C
SMS
,
w
h
er
e
ac
cu
r
ate
d
em
a
n
d
f
o
r
ec
asti
n
g
m
u
s
t
b
e
p
er
f
o
r
m
e
d
co
n
tin
u
o
u
s
l
y
to
s
u
p
p
o
r
t
d
y
n
a
m
ic
s
ch
ed
u
li
n
g
,
en
er
g
y
d
is
tr
ib
u
tio
n
,
an
d
g
r
id
s
tab
ilit
y
.
A
lt
h
o
u
g
h
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
A
R
I
M
A
–
DNN
r
esid
u
al
lear
n
in
g
m
o
d
el
d
e
m
o
n
s
tr
a
tes
s
tr
o
n
g
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
,
its
g
e
n
er
aliza
tio
n
is
co
n
s
tr
ai
n
ed
b
y
th
e
d
ataset,
w
h
ic
h
is
li
m
ited
to
d
aily
co
n
s
u
m
p
tio
n
d
ata
co
llected
f
r
o
m
o
n
l
y
th
r
ee
ch
ar
g
i
n
g
s
tatio
n
s
w
it
h
in
a
s
in
g
le
r
eg
io
n
.
T
h
is
r
estrict
io
n
m
a
y
a
f
f
ec
t
t
h
e
m
o
d
el
’
s
ab
ilit
y
to
r
ep
r
esen
t
b
r
o
ad
er
ch
ar
g
in
g
b
eh
a
v
io
r
s
ac
r
o
s
s
d
i
f
f
er
e
n
t
ar
ea
s
w
it
h
v
ar
y
i
n
g
in
f
r
astr
u
ctu
r
e
a
n
d
u
s
er
d
e
m
a
n
d
.
T
o
im
p
r
o
v
e
r
o
b
u
s
t
n
ess
,
f
u
tu
r
e
s
t
u
d
ies
s
h
o
u
ld
v
alid
ate
th
e
f
r
a
m
e
w
o
r
k
o
n
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
d
atasets
co
v
er
in
g
m
u
l
tip
le
ch
ar
g
i
n
g
s
tat
io
n
s
a
n
d
g
eo
g
r
ap
h
ical
co
n
tex
ts
.
Fu
r
t
h
er
m
o
r
e,
ex
ten
d
in
g
t
h
e
m
o
d
el
to
a
m
u
lti
v
ar
iate
f
o
r
ec
asti
n
g
f
r
a
m
e
w
o
r
k
w
o
u
ld
en
h
a
n
ce
its
ap
p
l
icab
ilit
y
.
B
y
i
n
co
r
p
o
r
atin
g
ex
o
g
en
o
u
s
v
ar
iab
les
s
u
c
h
as
w
ea
t
h
er
co
n
d
itio
n
s
,
tr
af
f
ic
d
en
s
it
y
,
o
r
d
y
n
a
m
ic
elec
tr
icit
y
p
r
icin
g
,
th
e
m
o
d
el
co
u
ld
ca
p
tu
r
e
ex
ter
n
al
in
f
l
u
en
ce
s
o
n
E
V
c
h
a
r
g
in
g
d
e
m
a
n
d
m
o
r
e
e
f
f
ec
tiv
e
l
y
.
S
u
ch
i
m
p
r
o
v
e
m
en
ts
w
o
u
ld
n
o
t
o
n
l
y
s
tr
e
n
g
th
e
n
p
r
e
d
ictiv
e
ac
cu
r
ac
y
b
u
t
als
o
s
u
p
p
o
r
t
r
ea
l
-
w
o
r
ld
d
ec
is
i
o
n
-
m
a
k
in
g
i
n
co
m
p
le
x
an
d
ev
o
lv
i
n
g
en
er
g
y
ec
o
s
y
s
te
m
s
.
4.
CO
NCLU
SI
O
N
A
cc
o
r
d
in
g
to
th
e
f
i
n
d
in
g
s
o
f
t
h
is
r
esear
c
h
an
d
t
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
v
i
s
u
a
l
r
esu
l
ts
o
f
th
e
g
r
ap
h
s
a
n
d
p
er
f
o
r
m
a
n
ce
m
etr
ic
s
s
h
o
w
n
,
th
e
h
y
b
r
id
AR
I
M
A
-
DNN
m
o
d
e
l
s
h
o
w
s
a
m
u
ch
b
etter
f
o
r
e
ca
s
t
ac
c
u
r
ac
y
t
h
a
n
s
in
g
le
m
o
d
els.
T
h
is
s
tu
d
y
co
n
f
ir
m
s
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
A
R
I
M
A
-
DNN
m
o
d
el
w
i
t
h
r
esid
u
al
lear
n
i
n
g
o
u
tp
er
f
o
r
m
s
s
in
g
le
-
m
o
d
el
ap
p
r
o
ac
h
es
b
y
e
f
f
ec
ti
v
el
y
ca
p
t
u
r
in
g
b
o
th
li
n
ea
r
an
d
n
o
n
lin
ea
r
p
atter
n
s
i
n
E
V
ch
ar
g
i
n
g
d
e
m
a
n
d
.
T
h
e
h
y
b
r
i
d
m
eth
o
d
d
e
m
o
n
s
tr
ate
s
it
s
s
tr
en
g
t
h
i
n
p
r
o
d
u
ci
n
g
m
o
r
e
a
cc
u
r
ate
an
d
s
tab
le
f
o
r
ec
asts
,
m
a
k
i
n
g
it
a
r
eliab
le
to
o
l
f
o
r
en
er
g
y
d
e
m
a
n
d
p
r
ed
ictio
n
.
B
ey
o
n
d
tech
n
ical
i
m
p
r
o
v
e
m
e
n
t
s
,
th
e
f
i
n
d
in
g
s
p
r
o
v
id
e
p
r
ac
tical
v
al
u
e
f
o
r
s
ta
k
e
h
o
ld
er
s
.
A
cc
u
r
ate
d
em
a
n
d
f
o
r
ec
asti
n
g
ca
n
as
s
i
s
t
s
ta
k
eh
o
ld
er
s
i
n
b
alan
cin
g
elec
tr
icit
y
lo
ad
,
s
u
p
p
o
r
t
ch
ar
g
in
g
s
ta
tio
n
d
ev
elo
p
er
s
in
p
lan
n
i
n
g
in
f
r
astr
u
ctu
r
e
ca
p
ac
it
y
,
an
d
g
u
id
e
p
o
licy
m
a
k
er
s
i
n
f
o
r
m
u
lati
n
g
s
tr
ateg
ies
f
o
r
n
atio
n
al
E
V
d
ep
lo
y
m
en
t,
p
ar
ticu
lar
l
y
i
n
r
eg
io
n
s
w
it
h
li
m
i
ted
p
o
w
er
s
u
p
p
l
y
.
Fo
r
f
u
t
u
r
e
r
esear
ch
,
th
e
m
o
d
el
ca
n
b
e
en
h
an
ce
d
b
y
in
co
r
p
o
r
atin
g
ex
o
g
e
n
o
u
s
v
ar
iab
les
s
u
c
h
as
w
ea
t
h
er
,
tr
af
f
ic
f
lo
w
,
o
r
s
o
c
io
-
ec
o
n
o
m
ic
d
ata
to
i
m
p
r
o
v
e
p
r
ed
ictio
n
r
o
b
u
s
tn
es
s
.
F
u
r
t
h
er
ex
p
lo
r
atio
n
o
f
d
is
tr
ib
u
ted
lear
n
i
n
g
f
r
a
m
e
w
o
r
k
s
m
a
y
also
b
r
o
ad
e
n
ap
p
licab
ilit
y
ac
r
o
s
s
m
u
l
ti
-
o
p
er
ato
r
E
V
ch
ar
g
in
g
i
n
I
n
d
o
n
esia.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
is
s
tu
d
y
w
as
m
ad
e
p
o
s
s
ib
l
e
th
r
o
u
g
h
t
h
e
s
u
p
p
o
r
t
o
f
Natio
n
al
R
e
s
ea
r
ch
a
n
d
I
n
n
o
v
atio
n
A
g
e
n
c
y
(
B
R
I
N)
w
it
h
th
e
p
r
o
v
is
io
n
o
f
f
ac
ilit
ies a
n
d
eq
u
ip
m
e
n
t
f
o
r
d
ata
ac
q
u
is
itio
n
in
t
h
e
ex
p
er
i
m
en
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
h
yb
r
id
A
R
I
MA
a
n
d
DN
N
a
p
p
r
o
a
ch
w
ith
r
esid
u
a
l le
a
r
n
in
g
fo
r
elec
tr
ic
ve
h
icle
ch
a
r
g
in
g
…
(
W
a
h
yu
C
esa
r
)
1563
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
e
ex
p
er
i
m
en
t a
n
d
d
ata
co
lle
ctio
n
ac
ti
v
itie
s
i
n
th
is
s
tu
d
y
wer
e
f
u
n
d
ed
b
y
t
h
e
Natio
n
al
R
e
s
ea
r
ch
a
n
d
I
n
n
o
v
a
tio
n
A
g
e
n
c
y
(
B
R
I
N)
o
f
I
n
d
o
n
esia.
T
h
e
au
th
o
r
s
g
r
atef
u
ll
y
ac
k
n
o
w
led
g
e
th
e
f
in
a
n
cia
l
s
u
p
p
o
r
t
p
r
o
v
id
ed
b
y
B
R
I
N
f
o
r
f
ac
ilit
a
tin
g
d
ata
a
cq
u
is
itio
n
an
d
ex
p
er
i
m
en
tal
i
m
p
le
m
e
n
tat
io
n
t
h
r
o
u
g
h
o
u
t th
i
s
r
esear
ch
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
a
c
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
W
ah
y
u
C
e
s
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
D
w
id
h
ar
m
a
P
r
i
y
a
s
ta
✓
✓
✓
✓
✓
✓
P
r
asety
o
A
j
i
✓
✓
✓
✓
✓
✓
✓
Me
l
y
a
n
a
✓
✓
✓
✓
✓
Ag
u
s
S
u
p
r
ian
to
✓
✓
✓
✓
✓
✓
Ose
n
F
ili Na
m
i
✓
✓
✓
R
iza
✓
✓
✓
✓
✓
✓
✓
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
si
s
I
:
I
n
v
e
st
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
si
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
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
i
s
s
t
u
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
d
u
e
to
p
r
iv
ac
y
a
n
d
co
n
f
id
en
t
ialit
y
r
e
s
tr
ictio
n
s
.
T
h
e
d
ataset
is
r
estricte
d
f
o
r
r
esear
ch
p
u
r
p
o
s
es
u
n
d
er
th
e
Nat
io
n
al
R
e
s
ea
r
ch
a
n
d
I
n
n
o
v
a
tio
n
A
g
e
n
c
y
(
B
R
I
N)
a
n
d
ca
n
n
o
t b
e
s
h
ar
ed
p
u
b
licl
y
w
it
h
o
u
t
p
r
io
r
au
th
o
r
izatio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
D
.
R
o
me
r
o
-
O
c
a
ñ
o
,
M
.
A
.
C
o
sí
o
-
L
e
ó
n
,
V
.
M
.
V
a
l
e
n
z
u
e
l
a
-
A
l
c
a
r
a
z
,
a
n
d
C
.
A
.
B
r
i
z
u
e
l
a
,
“
T
h
e
i
m
p
a
c
t
o
f
g
r
a
d
u
a
l
l
y
r
e
p
l
a
c
i
n
g
f
o
ssi
l
f
u
e
l
-
p
o
w
e
r
e
d
v
e
h
i
c
l
e
s
w
i
t
h
e
l
e
c
t
r
i
c
o
n
e
s:
A
b
i
-
o
b
j
e
c
t
i
v
e
o
p
t
i
mi
sa
t
i
o
n
a
p
p
r
o
a
c
h
,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
4
,
p
.
1
1
6
5
4
6
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
6
5
4
6
.
[
2
]
G
.
F
.
S
a
v
a
r
i
e
t
a
l
.
,
“
A
sse
ssm
e
n
t
o
f
c
h
a
r
g
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s,
i
n
f
r
a
st
r
u
c
t
u
r
e
a
n
d
c
h
a
r
g
i
n
g
s
t
a
t
i
o
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
sc
h
e
me
s
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s:
A
r
e
v
i
e
w
,
”
Ai
n
S
h
a
m
s E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
1
4
,
n
o
.
4
,
p
.
1
0
1
9
3
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
se
j
.
2
0
2
2
.
1
0
1
9
3
8
.
[
3
]
P
.
A
j
i
,
D
.
A
.
R
e
n
a
t
a
,
A
.
L
a
r
a
sat
i
,
a
n
d
R
i
z
a
,
“
D
e
v
e
l
o
p
me
n
t
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
st
a
t
i
o
n
ma
n
a
g
e
me
n
t
sy
st
e
m
i
n
u
r
b
a
n
a
r
e
a
s,”
i
n
Pr
o
c
e
e
d
i
n
g
-
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
Po
l
i
c
y
i
n
El
e
c
t
ri
c
P
o
w
e
r
a
n
d
En
e
rg
y
,
I
C
T
-
PE
P
2
0
2
0
,
I
EEE,
S
e
p
.
2
0
2
0
,
p
p
.
1
9
9
–
2
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
T
-
P
EP5
0
9
1
6
.
2
0
2
0
.
9
2
4
9
8
3
8
.
[
4
]
M
.
S
e
y
e
d
a
n
a
n
d
F
.
M
a
f
a
k
h
e
r
i
,
“
P
r
e
d
i
c
t
i
v
e
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s
f
o
r
su
p
p
l
y
c
h
a
i
n
d
e
ma
n
d
f
o
r
e
c
a
st
i
n
g
:
me
t
h
o
d
s,
a
p
p
l
i
c
a
t
i
o
n
s,
a
n
d
r
e
se
a
r
c
h
o
p
p
o
r
t
u
n
i
t
i
e
s,”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
7
,
n
o
.
1
,
p
.
5
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
0
-
0
0
3
2
9
-
2.
[
5
]
D
.
A
.
R
e
n
a
t
a
e
t
a
l
.
,
“
M
o
d
e
l
i
n
g
o
f
El
e
c
t
r
i
c
V
e
h
i
c
l
e
C
h
a
r
g
i
n
g
E
n
e
r
g
y
C
o
n
su
m
p
t
i
o
n
u
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
I
C
AC
S
I
S
2
0
2
1
,
I
EEE,
O
c
t
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
S
I
S
5
3
2
3
7
.
2
0
2
1
.
9
6
3
1
3
2
4
.
[
6
]
D
.
Z
h
o
u
e
t
a
l
.
,
“
U
si
n
g
b
a
y
e
si
a
n
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
st
a
t
i
o
n
l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
5
,
n
o
.
1
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
1
7
6
1
9
5
.
[
7
]
G
.
V
a
n
K
r
i
e
k
i
n
g
e
,
C
.
D
e
C
a
u
w
e
r
,
N
.
S
a
p
o
u
n
t
z
o
g
l
o
u
,
T
.
C
o
o
se
man
s,
a
n
d
M
.
M
e
ssag
i
e
,
“
D
a
y
-
a
h
e
a
d
f
o
r
e
c
a
st
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
d
e
ma
n
d
w
i
t
h
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Wo
r
l
d
El
e
c
t
ri
c
Ve
h
i
c
l
e
J
o
u
rn
a
l
,
v
o
l
.
1
2
,
n
o
.
4
,
p
.
1
7
8
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
w
e
v
j
1
2
0
4
0
1
7
8
.
[
8
]
R
.
R
o
y
,
T
.
D
o
k
k
a
,
D
.
A
.
El
l
i
s,
E.
D
u
d
e
k
,
a
n
d
P
.
B
a
r
n
f
a
t
h
e
r
,
“
U
n
d
e
r
st
a
n
d
i
n
g
c
o
n
t
r
o
l
l
e
d
EV
c
h
a
r
g
i
n
g
i
mp
a
c
t
s u
s
i
n
g
sce
n
a
r
i
o
-
b
a
se
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s:
P
o
st
e
r
,”
e
-
E
n
e
r
g
y
2
0
2
1
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
1
1
2
t
h
AC
M
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Fu
t
u
r
e
En
e
r
g
y
S
y
s
t
e
m
s
,
p
p
.
2
8
8
–
2
8
9
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
4
7
5
5
5
.
3
4
6
6
5
7
3
.
[
9
]
L.
-
H
.
L
e
,
“
T
i
me
se
r
i
e
s
a
n
a
l
y
si
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
i
n
d
a
t
a
a
n
a
l
y
si
s,
f
o
r
e
c
a
st
i
n
g
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
H
PU
2
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
:
N
a
t
u
ra
l
S
c
i
e
n
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
2
0
–
2
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
6
7
6
4
/
h
p
u
2
.
j
o
s.2
0
2
4
.
3
.
1
.
2
0
-
2
9
.
[
1
0
]
I
.
K
h
a
n
d
e
l
w
a
l
,
R
.
A
d
h
i
k
a
r
i
,
a
n
d
G
.
V
e
r
ma,
“
T
i
me
se
r
i
e
s
f
o
r
e
c
a
st
i
n
g
u
si
n
g
h
y
b
r
i
d
a
r
i
m
a
a
n
d
a
n
n
mo
d
e
l
s
b
a
se
d
o
n
D
W
T
De
c
o
mp
o
si
t
i
o
n
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
8
,
n
o
.
C
,
p
p
.
1
7
3
–
1
7
9
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
5
.
0
4
.
1
6
7
.
[
1
1
]
G
.
E
.
P
.
B
o
x
,
G
.
M
.
J
e
n
k
i
n
s
,
G
.
C
.
R
e
i
n
s
e
l
,
a
n
d
G
.
M
.
L
j
u
n
g
,
T
i
m
e
s
e
r
i
e
s
a
n
a
l
y
s
i
s
:
f
o
r
e
c
a
s
t
i
n
g
a
n
d
c
o
n
t
r
o
l
.
J
o
h
n
W
i
l
e
y
&
S
o
n
s
,
2
0
1
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
w
i
l
e
y
.
c
o
m
/
e
n
-
u
s
/
T
i
m
e
+
S
e
r
i
e
s
+
A
n
a
l
y
s
i
s
%
3
A
+
F
o
r
e
c
a
s
t
i
n
g
+
a
n
d
+
C
o
n
t
r
o
l
%
2
C
+
5
t
h
+
E
d
i
t
i
o
n
-
p
-
9
7
8
1
1
1
8
6
7
4
9
1
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
5
5
-
1
565
1564
[
1
2
]
R
.
J.
H
y
n
d
m
a
n
a
n
d
G
.
A
t
h
a
n
a
so
p
o
u
l
o
s,
“
N
o
n
-
se
a
so
n
a
l
A
R
I
M
A
m
o
d
e
l
s,”
2
0
1
8
,
(
a
c
c
e
sse
d
F
e
b
.
2
5
,
2
0
2
5
).
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
o
t
e
x
t
s.c
o
m
/
f
p
p
2
/
n
o
n
-
se
a
so
n
a
l
-
a
r
i
ma
.
h
t
ml
[
1
3
]
C
.
A
g
g
a
r
w
a
l
,
“
A
n
i
n
t
r
o
d
u
c
t
i
o
n
t
o
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
a
n
d
D
e
e
p
L
e
a
rn
i
n
g
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
3
,
p
p
.
1
–
27
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
9
6
4
2
-
0_
1.
[
1
4
]
J.
T
u
m
b
a
a
n
d
A
.
P
e
t
e
r
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
a
u
t
o
r
e
g
r
e
ssi
v
e
i
n
t
e
g
r
a
t
e
d
mo
v
i
n
g
a
v
e
r
a
g
e
(
A
R
I
M
A
)
mo
d
e
l
t
o
f
o
r
e
c
a
st
e
l
e
c
t
r
i
c
i
t
y
c
o
n
su
mp
t
i
o
n
f
o
r
N
i
g
e
r
i
a
,
”
J
o
u
r
n
a
l
o
f
E
n
v
i
r
o
n
m
e
n
t
a
l
a
n
d
E
n
e
r
g
y
E
c
o
n
o
m
i
c
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
3
–
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
5
6
9
4
6
/
j
e
e
e
.
v
2
i
1
.
3
11
[
1
5
]
A
.
A
n
a
n
d
a
n
d
K
.
J
h
a
j
h
a
r
i
a
,
“
A
d
v
a
n
c
e
d
c
r
o
p
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
:
a
c
o
mp
r
e
h
e
n
si
v
e
r
e
v
i
e
w
,
”
T
ELKO
MN
I
K
A
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
2
3
,
n
o
.
2
,
p
.
4
0
2
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
e
l
k
o
mn
i
k
a
.
v
2
3
i
2
.
2
6
6
2
1
.
[
1
6
]
P
.
M
a
r
i
u
s
-
C
o
n
st
a
n
t
i
n
,
V
.
E.
B
a
l
a
s,
L
.
P
e
r
e
scu
-
P
o
p
e
scu
,
a
n
d
N
.
M
a
st
o
r
a
k
i
s
,
“
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
WS
E
AS
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
i
r
c
u
i
t
s
a
n
d
S
y
s
t
e
m
s
,
W
i
l
e
y
,
2
0
0
9
,
p
p
.
5
7
9
–
5
8
8
,
d
o
i
:
1
0
.
1
0
0
2
/
9
7
8
1
3
9
4
2
6
8
9
9
3
.
c
h
3
.
[
1
7
]
M
.
A
.
T
o
r
r
e
s
-
H
e
r
n
á
n
d
e
z
,
M
.
H
.
Esc
o
b
e
d
o
-
B
a
r
a
j
a
s,
H
.
A
.
G
u
e
r
r
e
r
o
-
O
su
n
a
,
T
.
I
b
a
r
r
a
-
P
é
r
e
z
,
L
.
O
.
S
o
l
í
s
-
S
á
n
c
h
e
z
,
a
n
d
M
.
d
e
l
R
.
M
a
r
t
í
n
e
z
-
B
l
a
n
c
o
,
“
P
e
r
f
o
r
man
c
e
a
n
a
l
y
si
s
o
f
e
mb
e
d
d
e
d
m
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
o
n
smar
t
c
y
b
e
r
-
p
h
y
si
c
a
l
sy
st
e
ms f
o
r
I
o
T
e
n
v
i
r
o
n
me
n
t
s
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
5
,
p
.
6
9
3
5
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
5
6
9
3
5
.
[
1
8
]
B
.
M
.
F
a
h
i
m
,
M
.
K
.
A
k
b
a
r
,
a
n
d
M
.
A
m
a
y
r
i
,
“
R
e
s
i
D
u
a
l
N
e
t
:
A
n
o
v
e
l
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
d
a
t
a
i
m
p
u
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
t
o
e
n
h
a
n
c
e
l
o
a
d
f
o
r
e
c
a
s
t
i
n
g
a
c
c
u
r
a
c
y
,
”
B
u
i
l
d
i
n
g
S
i
m
u
l
a
t
i
o
n
,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
8
9
7
–
9
2
2
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
2
7
3
-
0
2
5
-
1
2
3
6
-
8.
[
1
9
]
F
.
M
a
r
z
b
n
a
i
,
A
.
H
.
O
sma
n
,
a
n
d
M
.
S
.
H
a
ssa
n
,
“
El
e
c
t
r
i
c
v
e
h
i
c
l
e
e
n
e
r
g
y
d
e
man
d
p
r
e
d
i
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s:
A
n
in
-
d
e
p
t
h
a
n
d
c
r
i
t
i
c
a
l
sy
st
e
mat
i
c
r
e
v
i
e
w
,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
6
2
4
2
–
9
6
2
5
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ES
S
.
2
0
2
3
.
3
3
0
8
9
2
8
.
[
2
0
]
N
.
F
.
A
u
r
n
a
e
t
a
l
.
,
“
T
i
me
se
r
i
e
s
a
n
a
l
y
si
s
o
f
e
l
e
c
t
r
i
c
e
n
e
r
g
y
c
o
n
su
m
p
t
i
o
n
u
si
n
g
a
u
t
o
r
e
g
r
e
ssi
v
e
i
n
t
e
g
r
a
t
e
d
mo
v
i
n
g
a
v
e
r
a
g
e
mo
d
e
l
a
n
d
H
o
l
t
W
i
n
t
e
r
s
mo
d
e
l
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
1
9
,
n
o
.
3
,
p
p
.
9
9
1
–
1
0
0
0
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/
T
EL
K
O
M
N
I
K
A
.
v
1
9
i
3
.
1
5
3
0
3
.
[
2
1
]
P
.
M
.
R
.
B
e
n
t
o
,
J.
A
.
N
.
P
o
mb
o
,
M
.
R
.
A
.
C
a
l
a
d
o
,
a
n
d
S
.
J.
P
.
S
.
M
a
r
i
a
n
o
,
“
S
t
a
c
k
i
n
g
e
n
se
mb
l
e
me
t
h
o
d
o
l
o
g
y
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
A
R
I
M
A
mo
d
e
l
s f
o
r
s
h
o
r
t
-
t
e
r
m l
o
a
d
f
o
r
e
c
a
st
i
n
g
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
4
,
n
o
.
2
1
,
p
.
7
3
7
8
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
4
2
1
7
3
7
8
.
[
2
2
]
R
.
C
.
P
e
l
w
a
n
a
n
d
C
.
V
a
n
A
l
t
e
n
,
“
C
o
mp
a
r
i
n
g
t
h
e
Ef
f
e
c
t
i
v
e
n
e
ss
o
f
L
S
T
M
,
A
R
I
M
A
,
a
n
d
G
R
U
a
l
g
o
r
i
t
h
ms
f
o
r
f
o
r
e
c
a
st
i
n
g
c
u
s
t
o
me
r
c
h
a
r
g
i
n
g
b
e
h
a
v
i
o
r
i
n
t
h
e
e
l
e
c
t
r
i
c
mo
b
i
l
i
t
y
i
n
d
u
s
t
r
y
i
n
E
u
r
o
p
e
,
”
U
n
i
v
e
r
si
t
y
o
f
t
h
e
W
i
t
w
a
t
e
r
sr
a
n
d
,
Jo
h
a
n
n
e
sb
u
r
g
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
i
r
e
d
sp
a
c
e
.
w
i
t
s.a
c
.
z
a
/
se
r
v
e
r
/
a
p
i
/
c
o
r
e
/
b
i
t
s
t
r
e
a
ms/
3
f
7
c
c
6
1
d
-
a
5
4
7
-
4
4
f
a
-
8
0
d
9
-
2
4
7
b
0
b
a
5
e
4
6
9
/
c
o
n
t
e
n
t
[
2
3
]
M
.
A
.
A
.
A
b
d
u
l
l
a
h
,
L
.
Je
ssi
n
t
h
a
,
G
.
P
.
K
h
u
n
e
sw
a
r
i
,
S
.
A
.
M
.
J
a
mi
l
,
a
n
d
O
.
R
.
O
l
a
n
i
r
a
n
,
“
C
o
m
p
a
r
i
so
n
o
f
m
u
l
t
i
p
l
e
r
e
g
r
e
ssi
o
n
a
n
d
mo
d
e
l
a
v
e
r
a
g
i
n
g
mo
d
e
l
-
b
u
i
l
d
i
n
g
a
p
p
r
o
a
c
h
f
o
r
mi
ss
i
n
g
d
a
t
a
w
i
t
h
mu
l
t
i
p
l
e
i
m
p
u
t
a
t
i
o
n
,
”
En
g
i
n
e
e
r
i
n
g
,
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
Re
se
a
rc
h
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
1
8
5
0
2
–
1
8
5
0
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
4
8
0
8
4
/
e
t
a
sr
.
8
9
0
9
.
[
2
4
]
A
.
d
e
M
y
t
t
e
n
a
e
r
e
,
B
.
G
o
l
d
e
n
,
B
.
L
e
G
r
a
n
d
,
a
n
d
F
.
R
o
ssi
,
“
M
e
a
n
a
b
so
l
u
t
e
p
e
r
c
e
n
t
a
g
e
e
r
r
o
r
f
o
r
r
e
g
r
e
ssi
o
n
mo
d
e
l
s,”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
1
9
2
,
p
p
.
3
8
–
4
8
,
Ju
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
5
.
1
2
.
1
1
4
.
[
2
5
]
W
.
A
.
W
o
o
d
w
a
r
d
,
H
.
L
.
G
r
a
y
,
a
n
d
A
.
C
.
El
l
i
o
t
t
,
A
p
p
l
i
e
d
t
i
m
e
ser
i
e
s
a
n
a
l
y
si
s
w
i
t
h
R,
se
c
o
n
d
e
d
i
t
i
o
n
.
C
R
C
p
r
e
ss,
2
0
1
7
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
3
1
5
1
6
1
1
4
3
.
[
2
6
]
M
.
N
.
V
i
v
e
k
a
n
a
n
d
a
,
P
.
A
.
S
h
i
d
l
y
a
l
i
,
a
n
d
V
.
V
.
M
a
l
g
i
,
“
En
h
a
n
c
i
n
g
EV
mar
k
e
t
f
o
r
e
c
a
st
i
n
g
a
c
c
u
r
a
c
y
:
I
n
t
e
g
r
a
t
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
A
R
I
M
A
mo
d
e
l
s
,
”
i
n
C
O
M
N
ET
S
AT 2
0
2
4
-
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
,
N
e
t
w
o
r
k
s a
n
d
S
a
t
e
l
l
i
t
e
,
I
EEE,
N
o
v
.
2
0
2
4
,
p
p
.
4
4
5
–
450
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
N
ET
S
A
T
6
3
2
8
6
.
2
0
2
4
.
1
0
8
6
1
9
7
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Wa
h
y
u
C
e
sa
r
ea
rn
e
d
h
is
B
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
E
lec
tro
n
ics
I
n
stru
m
e
n
tatio
n
P
h
y
sic
s
f
ro
m
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
,
De
p
o
k
,
In
d
o
n
e
sia
,
in
2
0
0
9
a
n
d
h
is
M
a
ste
r
’
s
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Bu
d
i
L
u
h
u
r
Un
iv
e
rsity
,
Ja
k
a
rta,
In
d
o
n
e
si
a
,
in
2
0
2
4
.
He
w
o
rk
e
d
a
s
a
n
e
n
g
in
e
e
rin
g
sta
ff
m
e
m
b
e
r
o
n
a
n
a
v
io
n
ics
sy
st
e
m
f
o
r
u
n
m
a
n
n
e
d
a
e
rial
v
e
h
icle
s
(U
A
V
s) an
d
a
s a
re
se
a
rc
h
e
r
o
f
f
li
g
h
t
c
o
n
tro
l
sy
ste
m
s
in
th
e
De
fe
n
se
a
n
d
S
e
c
u
rit
y
In
d
u
stry
T
e
c
h
n
o
l
o
g
y
Ce
n
ter
(2
0
1
0
-
2
0
2
1
).
S
in
c
e
2
0
2
2
,
h
e
h
a
s
b
e
e
n
w
o
rk
in
g
a
s
a
n
e
n
g
in
e
e
rin
g
sta
ff
m
e
m
b
e
r
a
t
th
e
sm
a
rt
c
a
rd
a
p
p
li
c
a
ti
o
n
a
n
d
e
lec
tri
c
v
e
h
i
c
le
(EV
)
c
h
a
rg
in
g
sta
ti
o
n
m
a
n
a
g
e
m
e
n
t
sy
ste
m
re
s
e
a
rc
h
g
ro
u
p
in
t
h
e
Re
se
a
rc
h
Ce
n
tre
o
f
El
e
c
tro
n
ics
in
th
e
Na
ti
o
n
a
l
Re
se
a
rc
h
a
n
d
I
n
n
o
v
a
ti
o
n
A
g
e
n
c
y
(BR
IN).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
w
a
h
y
0
4
7
@b
rin
.
g
o
.
id
.
D
w
id
h
a
r
m
a
Priy
a
st
a
e
a
rn
e
d
h
is
B
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
f
ro
m
S
a
g
a
Un
iv
e
rsit
y
,
Ja
p
a
n
,
in
1
9
9
4
.
He
o
b
tai
n
e
d
h
is
M
a
ste
r
’
s
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Un
iv
e
rsity
o
f
Ne
w
S
o
u
th
W
a
les
,
A
u
stra
li
a
,
in
2
0
0
0
.
He
c
o
m
p
lete
d
h
is
Do
c
t
o
ra
l
p
ro
g
ra
m
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
t
th
e
G
ra
d
u
a
te
S
c
h
o
o
l
o
f
Dip
o
n
e
g
o
ro
U
n
iv
e
rsity
in
2
0
2
4
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
t
t
h
e
Na
ti
o
n
a
l
Re
se
a
rc
h
a
n
d
In
n
o
v
a
ti
o
n
Ag
e
n
c
y
(BRIN).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
w
id
0
0
2
@
b
ri
n
.
g
o
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.