I
n
d
on
e
s
i
a
n
Jo
u
r
n
al
of
E
l
e
c
t
r
i
c
al
E
n
g
i
n
e
e
r
i
n
g a
n
d
C
om
p
u
t
e
r
S
c
i
e
n
c
e
V
ol
.
42
, N
o.
2
,
M
a
y
20
26
, pp.
44
2
~
453
I
S
S
N
:
2
502
-
4
7
52
, D
O
I
:
10.11591/
i
j
e
e
cs
.v
42.
i
2
.pp
442
-
453
442
Jou
r
n
al
h
om
e
page
:
ht
t
p:
/
/
i
j
e
e
cs
.i
ae
s
c
or
e
.c
om
M
e
t
a
-
st
ac
k
i
n
g
m
o
d
e
l
s
f
or
e
l
e
c
t
r
i
c
i
t
y l
oa
d
f
o
r
e
c
ast
i
n
g
i
n
We
st
Java
D
e
n
an
d
a A
u
f
ad
l
an
T
s
a
q
i
f
,
B
agu
s
S
ar
t
on
o
,
H
ar
i
Wi
j
ay
an
t
o
S
c
h
o
ol
of
D
a
t
a
S
c
i
e
n
c
e
,
M
a
t
h
e
m
a
t
i
c
s
,
a
n
d
I
n
f
or
m
a
t
i
c
s
,
I
P
B
U
ni
ve
r
s
i
t
y
,
B
o
g
o
r
,
I
n
do
n
e
s
i
a
A
r
t
i
c
l
e
I
n
f
o
A
B
S
T
R
A
C
T
A
r
t
i
c
l
e
h
i
s
t
o
r
y
:
R
e
c
e
i
v
e
d
D
e
c
3, 2025
R
e
v
i
s
e
d
M
a
r
7, 2026
A
c
c
e
pt
e
d
M
a
y
26, 2026
I
n
d
o
n
e
s
i
a
’
s
e
l
e
c
tr
ici
ty
d
e
m
a
n
d
c
o
n
ti
n
u
e
s
to
i
n
c
r
e
a
s
e
d
u
e
t
o
p
o
p
u
l
a
ti
o
n
g
r
o
wth
,
u
r
b
a
n
i
z
a
ti
o
n
,
a
n
d
i
n
d
u
s
tr
i
a
l
e
x
p
a
n
s
i
o
n
,
th
e
r
e
f
o
r
e
m
a
k
i
n
g
a
c
c
u
r
a
te
l
o
a
d
f
o
r
e
c
a
s
ti
n
g
i
s
e
s
s
e
n
ti
a
l
to
m
a
i
n
tai
n
s
u
p
p
l
y
-
d
e
m
a
n
d
b
a
l
a
n
c
e
.
Ho
we
v
e
r
,
e
l
e
c
tr
ica
l
l
o
a
d
d
e
m
a
n
d
i
n
W
e
s
t
J
a
v
a
h
a
s
a
c
o
m
p
l
e
x
p
a
tt
e
r
n
(
s
e
a
s
o
n
a
l
i
ty
,
n
o
n
l
i
n
e
a
r
b
e
h
a
v
i
o
r
,
we
a
th
e
r
v
a
r
i
a
b
il
i
ty
,
a
n
d
h
o
l
i
d
a
y
e
f
f
e
c
ts
)
,
wh
i
c
h
m
o
ti
v
a
tes
th
e
u
s
e
o
f
a
m
e
ta
-
s
tac
k
i
n
g
a
p
p
r
o
a
c
h
to
e
f
f
e
c
ti
v
e
l
y
c
a
p
tu
r
e
s
u
c
h
c
o
m
p
l
e
x
i
ty
.
P
r
e
v
i
o
u
s
r
e
s
e
a
r
c
h
s
h
o
ws
th
a
t
m
e
ta
-
s
tac
k
i
n
g
o
u
tp
e
r
f
o
r
m
s
i
n
d
i
v
i
d
u
a
l
m
o
d
e
l
s
,
b
u
t
i
t
f
a
il
s
to
c
a
p
tu
r
e
s
u
d
d
e
n
c
h
a
n
g
e
s
a
n
d
i
ts
p
e
r
f
o
r
m
a
n
c
e
c
o
n
s
i
s
ten
c
y
r
e
m
a
i
n
s
u
n
c
l
e
a
r
.
T
h
e
r
e
f
o
r
e
,
th
i
s
s
tu
d
y
p
r
o
p
o
s
e
s
a
m
e
ta
-
s
tac
k
i
n
g
f
r
a
m
e
wo
r
k
f
o
r
d
a
il
y
e
l
e
c
tr
i
c
i
ty
l
o
a
d
f
o
r
e
c
a
s
ti
n
g
i
n
W
e
s
t
J
a
v
a
(
2
0
0
6
-
2
0
2
3
)
th
a
t
i
n
c
l
u
d
e
s
we
a
th
e
r
a
n
d
h
o
l
i
d
a
y
v
a
r
i
a
b
l
e
s
b
y
c
o
m
b
i
n
i
n
g
C
NN
-
B
i
L
S
T
M
,
C
NN
-
B
i
GR
U,
a
n
d
W
i
n
d
o
we
d
-
XG
B
o
o
s
t
f
o
r
e
c
a
s
ts
t
h
r
o
u
g
h
l
i
n
e
a
r
r
e
g
r
e
s
s
i
o
n
a
n
d
e
v
a
l
u
a
tes
i
ts
p
e
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
f
i
v
e
d
a
ta
-
s
p
li
tt
i
n
g
s
c
e
n
a
r
i
o
s
a
n
d
n
i
n
e
f
o
r
e
c
a
s
t
h
o
r
i
z
o
n
s
,
wh
i
c
h
r
e
p
r
e
s
e
n
t
s
t
h
e
m
a
i
n
n
o
v
e
l
ty
i
n
th
i
s
r
e
s
e
a
r
c
h
.
M
e
ta
-
s
tac
k
i
n
g
s
h
o
ws
s
tr
o
n
g
g
e
n
e
r
a
li
z
a
t
i
o
n
a
c
r
o
s
s
s
c
e
n
a
r
i
o
s
a
n
d
s
tr
o
n
g
l
o
n
g
-
te
r
m
f
o
r
e
c
a
s
ti
n
g
p
e
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
h
o
r
i
z
o
n
s
,
wh
i
l
e
c
o
n
s
i
s
ten
tl
y
p
r
o
v
i
d
i
n
g
a
b
a
l
a
n
c
e
d
tr
a
d
e
-
o
f
f
b
e
twe
e
n
M
APE
a
n
d
tr
e
n
d
a
c
c
u
r
a
c
y
,
wh
e
r
e
th
e
m
o
d
e
l
tr
a
i
n
e
d
o
n
th
e
l
o
n
g
e
s
t
h
i
s
to
r
i
c
a
l
d
a
tas
e
t
a
c
h
i
e
v
e
s
th
e
b
e
s
t
p
e
r
f
o
r
m
a
n
c
e
w
i
th
1
.
8
9
%
M
APE
a
n
d
8
6
%
tr
e
n
d
a
c
c
u
r
a
c
y
.
T
h
e
p
r
o
p
o
s
e
d
a
p
p
r
o
a
c
h
s
u
c
c
e
s
s
f
u
l
l
y
c
a
p
tu
r
e
s
s
e
a
s
o
n
a
l
a
n
d
h
o
l
i
d
a
y
-
r
e
l
a
ted
l
o
a
d
p
a
tt
e
r
n
s
,
i
n
d
i
c
a
t
i
n
g
i
ts
p
o
ten
ti
a
l
to
s
u
p
p
o
r
t
P
L
N
i
n
i
m
p
r
o
v
i
n
g
d
e
m
a
n
d
p
l
a
n
n
i
n
g
a
n
d
o
p
e
r
a
ti
o
n
a
l
d
e
c
i
s
i
o
n
-
m
a
k
i
n
g
.
K
e
y
w
or
d
s
:
C
N
N
-
B
i
G
R
U
C
N
N
-
B
i
L
S
T
M
E
l
e
c
t
r
i
c
i
t
y
l
oa
d f
or
e
c
a
s
t
i
ng
M
e
t
a
-
s
t
a
c
ki
ng
W
i
ndow
e
d
-
X
G
B
oos
t
T
h
i
s
i
s
a
n
o
p
e
n
a
c
c
e
s
s
a
r
ti
c
l
e
u
n
d
e
r
th
e
C
C
B
Y
-
SA
l
i
c
e
n
s
e
.
C
or
r
e
s
pon
di
n
g A
u
t
h
or
:
D
e
na
nda
A
uf
a
dl
a
n
T
s
a
qi
f
S
c
hool
of
D
a
t
a
S
c
i
e
nc
e
, M
a
t
he
m
a
t
i
c
s
, a
nd I
n
f
or
m
a
t
i
c
s
, I
P
B
U
ni
v
e
r
s
i
t
y
16680 B
og
or
R
e
g
e
nc
y
, W
e
s
t
J
a
v
a
,
I
ndone
s
i
a
E
m
a
i
l
:
de
na
nda
a
uf
a
dl
a
nt
s
@
gm
a
i
l
.c
o
m
1.
I
N
T
R
O
D
U
C
T
I
O
N
E
l
e
c
t
r
i
c
l
oa
d
r
e
p
r
e
s
e
nt
s
t
he
a
m
ount
of
e
l
e
c
t
r
i
c
a
l
e
ne
r
gy
c
ons
u
m
e
d
b
y
us
e
r
s
o
v
e
r
t
i
m
e
a
nd
i
s
c
a
t
e
g
or
i
z
e
d
a
s
t
i
m
e
s
e
r
i
e
s
da
t
a
,
w
hi
c
h
c
ont
a
i
n
t
e
m
por
a
l
d
e
pe
nde
nc
i
e
s
a
nd
c
o
m
pl
e
x
pa
t
t
e
r
ns
s
uc
h
a
s
t
r
e
nd,
s
e
a
s
ona
l
i
t
y
,
a
nd
r
a
ndo
m
f
l
uc
t
ua
t
i
ons
[
1]
.
I
n
I
ndone
s
i
a
,
e
l
e
c
t
r
i
c
i
t
y
de
m
a
nd
ha
s
be
e
n
i
nc
r
e
a
s
i
ng
r
a
pi
dl
y
due
t
o
popul
a
t
i
on
g
r
ow
t
h,
ur
ba
ni
z
a
t
i
on,
a
nd
i
ndus
t
r
i
a
l
e
xpa
ns
i
on,
t
hus
pos
i
ng
s
i
g
ni
f
i
c
a
nt
c
ha
l
l
e
ng
e
s
f
or
r
e
l
i
a
bl
e
s
uppl
y
pl
a
nni
ng
a
nd
i
nf
r
a
s
t
r
uc
t
ur
e
de
v
e
l
op
m
e
nt
[
2]
.
F
or
e
c
a
s
t
i
ng
pl
a
y
s
a
n
e
s
s
e
nt
i
a
l
r
ol
e
i
n
i
de
nt
i
f
y
i
ng
t
he
s
e
pa
t
t
e
r
ns
t
o
s
uppor
t
de
c
i
s
i
on
-
m
a
ki
n
g
i
n
t
he
e
ne
r
gy
s
e
c
t
or
[
3]
.
A
c
c
ur
a
t
e
e
l
e
c
t
r
i
c
i
t
y
de
m
a
nd
f
or
e
c
a
s
t
i
ng
he
l
ps
m
a
i
nt
a
i
n
t
he
ba
l
a
nc
e
be
t
w
e
e
n
s
uppl
y
a
nd
de
m
a
nd,
pr
e
v
e
nt
po
w
e
r
di
s
r
upt
i
ons
,
a
nd
i
m
pr
o
v
e
di
s
t
r
i
but
i
on
e
f
f
i
c
i
e
nc
y
[
4]
.
I
n r
e
g
i
ons
l
i
ke
B
og
or
C
i
t
y
,
W
e
s
t
J
a
v
a
t
ha
t
a
r
e
c
ha
r
a
c
t
e
r
i
z
e
d b
y
hi
g
h r
a
i
nf
a
l
l
, de
ns
e
popul
a
t
i
on,
a
nd
m
ul
t
i
pl
e
e
xt
e
r
na
l
f
a
c
t
or
s
s
uc
h
a
s
t
e
m
pe
r
a
t
ur
e
,
r
a
i
nf
a
l
l
,
a
nd
e
l
e
c
t
r
i
c
i
t
y
t
a
r
i
f
f
s
,
r
e
l
i
a
bl
e
f
or
e
c
a
s
t
i
ng
i
s
ne
e
de
d
f
or
e
f
f
e
c
t
i
v
e
e
n
e
r
gy
pl
a
nni
ng
[
5]
, [
6]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
I
S
S
N
:
2
5
0
2
-
4
7
52
M
e
t
a
-
s
t
ac
k
i
ng m
od
e
l
s
f
o
r
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
o
r
e
c
as
t
i
ng
i
n W
e
s
t
J
av
a
(
D
e
nand
a A
u
f
a
d
l
an
T
s
a
qi
f
)
443
T
r
a
di
t
i
ona
l
s
t
a
t
i
s
t
i
c
a
l
m
ode
l
s
s
uc
h
a
s
A
R
I
M
A
of
f
e
r
i
nt
e
r
pr
e
t
a
bi
l
i
t
y
but
ha
v
e
l
i
m
i
t
a
t
i
ons
w
he
n
ha
ndl
i
ng
m
ul
t
i
v
a
r
i
a
t
e
a
nd
n
onl
i
ne
a
r
r
e
l
a
t
i
ons
hi
ps
i
n
f
or
e
c
a
s
t
i
ng
[
7]
.
A
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
g
e
nc
e
m
od
e
l
s
,
i
nc
l
udi
ng
X
G
B
oos
t
,
C
N
N
,
L
S
T
M
,
a
nd
G
R
U
,
o
v
e
r
c
o
m
e
t
he
s
e
c
ha
l
l
e
n
g
e
s
b
y
c
a
pt
ur
i
ng
c
o
m
pl
e
x
a
nd
nonl
i
ne
a
r
t
e
m
por
a
l
pa
t
t
e
r
ns
[
8]
,
[
9]
.
L
S
T
M
e
f
f
e
c
t
i
v
e
l
y
l
e
a
r
ns
l
ong
-
t
e
r
m
de
pe
nd
e
nc
i
e
s
,
w
hi
l
e
G
R
U
a
c
hi
e
v
e
s
hi
g
he
r
c
o
m
put
a
t
i
ona
l
e
f
f
i
c
i
e
nc
y
f
or
s
hor
t
-
t
e
r
m
de
pe
nde
n
c
i
e
s
[
10]
.
T
o
f
ur
t
he
r
i
m
p
r
o
v
e
f
or
e
c
a
s
t
i
ng
pe
r
f
or
m
a
nc
e
,
hy
br
i
d
a
ppr
oa
c
he
s
ha
v
e
be
e
n
pr
opos
e
d.
O
ne
of
t
he
m
os
t
pr
om
i
s
i
ng
a
ppr
oa
c
he
s
i
s
m
e
t
a
-
s
t
a
c
ki
ng
,
w
hi
c
h
i
nt
e
g
r
a
t
e
s
m
ul
t
i
pl
e
ba
s
e
-
m
od
e
l
s
a
nd
us
e
s
a
m
e
t
a
-
l
e
a
r
ne
r
t
o
c
o
m
bi
ne
t
he
i
r
out
put
s
,
of
t
e
n
r
e
s
ul
t
i
n
s
upe
r
i
or
f
or
e
c
a
s
t
a
c
c
ur
a
c
y
[
11]
, [
12]
.
P
r
e
v
i
ous
s
t
udy
[
10]
us
e
d
m
e
t
a
-
s
t
a
c
ki
ng
t
o
f
or
e
c
a
s
t
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
i
n
A
us
t
r
a
l
i
a
a
nd
S
pa
i
n.
T
he
m
od
e
l
c
ons
i
s
t
s
of
L
S
T
M
,
Bi
-
L
S
T
M
,
X
G
B
oos
t
,
a
nd
s
t
a
c
ke
d
L
S
T
M
a
s
ba
s
e
-
l
e
a
r
ne
r
s
a
nd
l
a
s
s
o
r
e
g
r
e
s
s
i
on
a
s
m
e
t
a
-
l
e
a
r
ne
r
.
T
he
pr
opos
e
d
m
ode
l
w
a
s
s
how
n
t
o
out
pe
r
f
or
m
i
ndi
v
i
dua
l
m
ode
l
s
i
n
t
e
r
m
s
of
M
A
P
E
,
but
t
he
pr
opos
e
d
m
ode
l
s
f
a
i
l
t
o
f
or
e
c
a
s
t
t
he
m
i
ni
m
u
m
l
oa
d
v
a
l
ue
s
a
nd
f
a
i
l
t
o
a
nt
i
c
i
pa
t
e
s
udd
e
n
c
ha
ng
e
s
w
hi
c
h
i
nf
l
ue
nc
e
d by
c
a
l
e
nda
r
f
a
c
t
or
. M
ul
t
i
pl
e
L
S
T
M
v
a
r
i
a
nt
s
i
n t
he
ba
s
e
-
m
ode
l
s
r
e
s
ul
t
i
n s
i
m
i
l
a
r
f
or
e
c
a
s
t
i
ng r
e
s
ul
t
s
be
t
w
e
e
n
e
a
c
h
v
a
r
i
a
nt
,
t
hus
a
d
v
a
nt
a
g
e
s
c
a
pt
ur
e
d
b
y
t
he
m
e
t
a
-
l
e
a
r
n
e
r
i
s
s
ubopt
i
m
a
l
.
T
he
r
e
f
or
e
,
us
i
ng
m
or
e
v
a
r
i
e
d
ba
s
e
-
m
od
e
l
s
c
a
n
i
m
pr
o
v
e
t
he
m
e
t
a
-
l
e
a
r
ne
r
pe
r
f
or
m
a
nc
e
i
n
e
xpl
oi
t
i
ng
t
he
a
d
v
a
nt
a
ge
s
of
c
o
m
pl
e
m
e
nt
a
r
y
m
ode
l
s
.
L
i
ne
a
r
r
e
g
r
e
s
s
i
on
i
s
t
he
m
os
t
e
f
f
e
c
t
i
v
e
a
ppr
oa
c
h
t
o
e
xpl
oi
t
t
he
a
d
v
a
nt
a
g
e
s
of
c
o
m
pl
e
m
e
nt
a
r
y
i
nf
or
m
a
t
i
on
[
13]
.
A
l
s
o,
t
he
t
r
e
nd
a
c
c
ur
a
c
y
i
s
not
c
ons
i
de
r
e
d
i
n
t
he
r
e
s
e
a
r
c
h,
s
o
i
t
c
a
nnot
be
e
v
a
l
ua
t
e
d
how
t
he
pr
opos
e
d
m
ode
l
a
c
c
ur
a
t
e
l
y
f
or
e
c
a
s
t
t
he
t
r
e
nd,
e
s
pe
c
i
a
l
l
y
i
n
s
h
or
t
-
t
e
r
m
s
.
T
he
pr
opos
e
d
m
od
e
l
onl
y
t
e
s
t
e
d
us
i
ng
t
w
o
di
f
f
e
r
e
nt
l
oc
a
t
i
on
e
a
c
h
w
i
t
h
onl
y
one
s
c
e
na
r
i
o
of
t
r
a
i
ni
ng
a
nd
t
e
s
t
i
ng
da
t
a
,
s
o
i
t
s
e
v
a
l
ua
t
i
on
i
s
l
i
m
i
t
e
d
i
n
t
e
r
m
s
of
m
ode
l
c
ons
i
s
t
e
nc
y
a
nd
doe
s
not
c
ons
i
de
r
t
h
e
e
f
f
e
c
t
of
v
e
r
y
l
ong
-
t
i
m
e
i
nf
or
m
a
t
i
on.
T
hi
s
s
t
udy
pr
opos
e
s
a
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
t
ha
t
i
nt
e
g
r
a
t
e
s
W
i
ndo
w
e
d
-
X
G
B
oos
t
,
C
N
N
-
B
i
G
R
U
,
a
n
d
C
N
N
-
B
i
L
S
T
M
a
s
ba
s
e
-
m
ode
l
s
,
w
i
t
h
l
i
ne
a
r
r
e
gr
e
s
s
i
on
a
s
t
he
m
e
t
a
-
l
e
a
r
n
e
r
.
W
i
ndow
e
d
-
X
G
B
oos
t
i
s
s
e
l
e
c
t
e
d
f
or
i
t
s
s
i
m
pl
i
c
i
t
y
a
nd
e
f
f
i
c
i
e
nc
y
[
14]
,
w
hi
l
e
C
N
N
-
B
i
G
R
U
a
nd
C
N
N
-
B
i
L
S
T
M
e
f
f
e
c
t
i
v
e
l
y
c
a
pt
ur
e
s
pa
t
i
a
l
a
nd
t
e
m
por
a
l
de
pe
nde
nc
i
e
s
bi
di
r
e
c
t
i
ona
l
l
y
[
15]
,
[
16]
.
T
hi
s
s
t
udy
a
l
s
o
e
xpl
i
c
i
t
l
y
c
ons
i
de
r
e
d
c
a
l
e
nda
r
f
a
c
t
or
s
.
T
he
pr
opos
e
d
m
ode
l
a
i
m
s
t
o
a
c
hi
e
v
e
a
c
c
ur
a
t
e
a
nd
c
ons
i
s
t
e
nt
f
or
e
c
a
s
t
s
a
c
r
os
s
di
f
f
e
r
e
nt
da
t
a
-
s
pl
i
t
t
i
ng
s
c
e
na
r
i
os
i
n
t
e
r
m
s
of
M
A
P
E
a
nd
t
r
e
nd
a
c
c
ur
a
c
y
.
T
he
r
e
s
ul
t
s
a
r
e
e
xpe
c
t
e
d
t
o
pr
o
v
i
de
i
ns
i
g
ht
s
f
or
P
L
N
i
n
opt
i
m
i
z
i
n
g
e
l
e
c
t
r
i
c
i
t
y
s
uppl
y
pl
a
nni
ng
i
n
W
e
s
t
J
a
v
a
a
nd
c
ont
r
i
but
e
t
o
t
he
a
ppl
i
c
a
t
i
on
of
hy
br
i
d
m
e
t
hods
i
n
e
ne
r
gy
de
m
a
nd f
or
e
c
a
s
t
i
ng
.
T
he
obj
e
c
t
i
v
e
s
of
t
hi
s
r
e
s
e
a
r
c
h
a
r
e
t
o
m
ode
l
a
nd
e
v
a
l
ua
t
e
t
he
pr
opos
e
d
m
ode
l
f
or
f
or
e
c
a
s
t
i
n
g
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
i
n
W
e
s
t
J
a
v
a
,
t
o
t
e
s
t
i
t
s
pe
r
f
or
m
a
nc
e
a
nd
c
o
m
pa
r
e
i
t
w
i
t
h
i
ndi
v
i
d
ua
l
m
ode
l
s
a
c
r
os
s
di
f
f
e
r
e
nt
s
c
e
na
r
i
os
a
nd
f
or
e
c
a
s
t
hor
i
z
ons
,
a
nd
t
o
i
de
nt
i
f
y
t
he
b
e
s
t
-
pe
r
f
or
m
i
n
g
m
ode
l
w
hi
l
e
e
v
a
l
u
a
t
i
ng
i
t
s
a
bi
l
i
t
y
t
o
a
c
c
ur
a
t
e
l
y
f
or
e
c
a
s
t
t
he
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
da
t
a
i
n
W
e
s
t
J
a
v
a
.
T
hi
s
s
t
udy
s
e
e
ks
t
o
a
ddr
e
s
s
t
he
f
ol
l
ow
i
ng
r
e
s
e
a
r
c
h
que
s
t
i
ons
:
i
)
C
a
n
t
he
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
out
pe
r
f
or
m
i
ndi
v
i
dua
l
m
ode
l
s
a
c
r
os
s
di
f
f
e
r
e
nt
da
t
a
-
s
pl
i
t
t
i
ng
s
c
e
na
r
i
os
a
nd
f
or
e
c
a
s
t
hor
i
z
ons
?
(
ii
)
T
o
w
ha
t
e
xt
e
nt
c
a
n
t
he
pr
opos
e
d
m
ode
l
a
c
c
ur
a
t
e
l
y
f
or
e
c
a
s
t
e
l
e
c
t
r
i
c
i
t
y
l
oa
d i
n W
e
s
t
J
a
v
a
, pa
r
t
i
c
ul
a
r
l
y
t
hos
e
dr
i
v
e
n
b
y
c
a
l
e
nda
r
e
f
f
e
c
t
s
a
nd s
udde
n de
m
a
nd c
h
a
nge
s
?
2.
M
E
T
H
O
D
2
.
1
.
D
at
a
T
hi
s
s
t
udy
us
e
d
e
l
e
c
t
r
i
c
i
t
y
,
w
e
a
t
he
r
, a
nd
c
a
l
e
nda
r
d
a
t
a
i
n W
e
s
t
J
a
v
a
,
c
ons
i
s
t
i
ng
of
da
i
l
y
obs
e
r
v
a
t
i
ons
f
r
o
m
J
a
nua
r
y
1,
2006
,
t
o
D
e
c
e
m
be
r
31,
2023
,
w
i
t
h
a
t
ot
a
l
of
6541
da
t
a
poi
nt
s
.
T
he
e
l
e
c
t
r
i
c
i
t
y
da
t
a
c
ons
i
s
t
of
30
-
m
i
nut
e
l
oa
d
m
e
a
s
ur
e
m
e
nt
s
i
n
m
e
g
a
w
a
t
t
s
(
M
W
)
,
w
hi
c
h
a
r
e
l
a
t
e
r
a
gg
r
e
g
a
t
e
d
i
nt
o
da
i
l
y
v
a
l
ue
s
t
hr
oug
h
s
um
m
a
t
i
on
a
nd
us
e
d
a
s
t
he
f
or
e
c
a
s
t
i
ng
t
a
r
ge
t
.
T
h
e
da
t
a
s
e
t
w
a
s
obt
a
i
ne
d
f
r
o
m
P
L
N
U
I
P
2B
J
A
M
A
L
I
.
I
n
a
ddi
t
i
on t
o
t
he
e
l
e
c
t
r
i
c
i
t
y
da
t
a
,
w
e
a
t
he
r
da
t
a
w
e
r
e
us
e
d
a
s
e
xt
e
r
na
l
f
e
a
t
ur
e
s
t
o s
uppor
t
t
he
f
or
e
c
a
s
t
i
ng
a
na
l
y
s
i
s
.
T
he
w
e
a
t
he
r
da
t
a
w
e
r
e
obt
a
i
ne
d
f
r
o
m
t
he
I
ndone
s
i
a
n
M
e
t
e
or
ol
ogy
,
C
l
i
m
a
t
ol
ogy
,
a
nd
G
e
ophy
s
i
c
s
A
ge
nc
y
(
B
M
K
G
)
w
e
bs
i
t
e
f
r
o
m
s
t
a
t
i
ons
:
B
a
ndung
G
e
ophy
s
i
c
s
S
t
a
t
i
on,
W
e
s
t
J
a
v
a
C
l
i
m
a
t
ol
ogy
S
t
a
t
i
on
(
B
og
or
C
i
t
y
)
,
C
i
t
e
ko
M
e
t
e
or
ol
og
y
S
t
a
t
i
on
(
B
og
or
R
e
g
e
n
c
y
)
,
K
e
r
t
a
j
a
t
i
M
e
t
e
or
ol
ogy
S
t
a
t
i
on,
a
nd
P
e
ng
g
un
g
M
e
t
e
or
ol
og
y
P
os
t
(
M
a
j
a
l
e
ng
ka
)
,
a
nd
t
he
m
e
a
s
ur
e
m
e
nt
s
f
r
o
m
t
he
s
e
s
t
a
t
i
ons
w
e
r
e
a
v
e
r
a
ge
d
f
or
e
a
c
h
v
a
r
i
a
bl
e
t
o
r
e
pr
e
s
e
nt
t
he
o
v
e
r
a
l
l
c
l
i
m
a
t
i
c
c
ondi
t
i
ons
of
W
e
s
t
J
a
v
a
.
T
he
w
e
a
t
he
r
v
a
r
i
a
bl
e
s
i
nc
l
ude
a
v
e
r
a
ge
t
e
m
p
e
r
a
t
ur
e
,
r
a
i
nf
a
l
l
i
nt
e
ns
i
t
y
,
dur
a
t
i
on
of
s
un
s
hi
ne
,
hum
i
di
t
y
,
a
nd
w
i
nd
s
pe
e
d.
A
not
he
r
e
xt
e
r
na
l
f
e
a
t
ur
e
us
e
d
i
n
t
h
i
s
r
e
s
e
a
r
c
h
i
s
c
a
l
e
nda
r
da
t
a
,
w
hi
c
h
i
de
nt
i
f
i
e
s
na
t
i
ona
l
a
nd
r
e
l
i
g
i
ous
ho
l
i
da
y
s
s
uc
h
a
s
I
nde
pe
nde
nc
e
D
a
y
,
E
i
d
a
l
-
A
dha
,
E
i
d
al
-
F
i
t
r
,
a
nd
N
e
w
Y
e
a
r
,
s
i
nc
e
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
i
s
s
t
r
ong
l
y
a
f
f
e
c
t
e
d
b
y
hol
i
da
y
s
[
17]
,
[
18]
.
F
or
e
xa
m
pl
e
,
i
n
t
he
da
y
s
l
e
a
d
i
ng
u
p
t
o
E
i
d a
l
-
F
i
t
r
, e
l
e
c
t
r
i
c
i
t
y
us
a
g
e
c
o
ns
i
s
t
e
n
t
l
y
dr
op
s
be
c
a
us
e
m
a
ny
f
a
c
t
or
i
e
s
a
r
e
s
hu
t
dow
n
[
1
9]
.
2.2. F
r
am
e
w
or
k
of
t
h
e
p
r
op
os
e
d
m
od
e
l
Th
e
r
e
s
e
a
r
c
h
w
or
kf
l
ow
i
l
l
us
t
r
a
t
e
d
i
n
F
i
g
ur
e
1
s
t
a
r
t
s
w
i
t
h
da
t
a
e
xpl
or
a
t
i
on,
f
ol
l
ow
e
d
by
s
c
e
na
r
i
o
-
ba
s
e
d
da
t
a
s
pl
i
t
t
i
ng
i
nt
o
t
r
a
i
ni
ng
a
nd
t
e
s
t
i
ng
s
e
t
s
.
T
he
d
a
t
a
i
s
t
he
n
s
pl
i
t
i
nt
o
f
i
v
e
s
c
e
na
r
i
os
ba
s
e
d
on
T
a
bl
e
1
.
F
or
e
a
c
h
s
c
e
n
a
r
i
o,
t
he
t
r
a
i
ni
ng
da
t
a
a
r
e
di
v
i
d
e
d
i
nt
o
t
w
o
pha
s
e
s
,
w
he
r
e
t
he
f
i
r
s
t
t
r
a
i
ni
ng
da
t
a
s
e
t
i
s
pr
e
-
pr
oc
e
s
s
e
d
a
nd
us
e
d
t
o
b
ui
l
d
i
ndi
v
i
dua
l
ba
s
e
-
m
ode
l
s
,
w
hi
l
e
t
he
s
e
c
ond
t
r
a
i
ni
ng
da
t
a
s
e
t
,
w
h
i
c
h
i
s
ob
t
a
i
ne
d
by
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
, V
ol
.
42
, N
o.
2
,
M
a
y
20
26
:
442
-
453
444
s
pl
i
t
t
i
ng
t
he
i
ni
t
i
a
l
t
r
a
i
ni
ng
da
t
a
be
f
o
r
e
pr
e
-
pr
oc
e
s
s
i
n
g
,
i
s
us
e
d
f
or
m
e
t
a
-
s
t
a
c
ki
n
g
m
o
de
l
l
i
ng
.
T
he
da
t
a
v
a
l
i
da
t
i
on
i
s
us
e
d
t
o
g
e
ne
r
a
t
e
out
-
of
-
f
ol
d
(
O
O
F
)
pr
e
di
c
t
i
ons
a
s
pa
r
t
of
t
he
m
e
t
a
-
s
t
a
c
ki
ng
m
e
c
h
a
ni
s
m
.
T
hi
s
w
hol
e
pr
oc
e
s
s
i
s
r
e
pe
a
t
e
d
unt
i
l
a
l
l
f
i
v
e
s
c
e
na
r
i
os
ha
v
e
be
e
n
c
o
m
pl
e
t
e
d.
F
i
na
l
l
y
,
t
he
o
v
e
r
a
l
l
m
ode
l
pe
r
f
or
m
a
nc
e
i
s
e
v
a
l
ua
t
e
d
t
o
obt
a
i
n
t
he
f
i
na
l
r
e
s
ul
t
s
of
t
he
f
or
e
c
a
s
t
i
ng
f
r
a
m
e
w
or
k,
a
s
s
ho
w
n
i
n
F
i
g
ur
e
1
.
T
hi
s
e
nt
i
r
e
m
ode
l
l
i
ng
f
l
o
w
i
s
r
e
p
e
a
t
e
d
f
or
a
l
l
f
i
v
e
s
c
e
n
a
r
i
os
.
I
ndi
v
i
dua
l
m
ode
l
s
a
nd
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
a
r
e
t
he
n
e
v
a
l
ua
t
e
d
us
i
ng
M
A
P
E
a
nd
t
r
e
nd
a
c
c
ur
a
c
y
us
i
ng
t
e
s
t
da
t
a
a
nd
a
r
e
e
v
a
l
ua
t
e
d
on
di
f
f
e
r
e
nt
hor
i
z
on
w
hi
c
h
c
a
n
be
s
e
e
n on
T
a
bl
e
2
.
T
he
us
e
of
m
ul
t
i
pl
e
da
t
a
s
pl
i
t
t
i
ng
s
c
e
na
r
i
os
a
i
m
s
t
o
e
xa
m
i
ne
t
he
c
ons
i
s
t
e
nc
y
a
nd
r
obus
t
ne
s
s
of
t
he
pr
opos
e
d
m
ode
l
s
unde
r
di
f
f
e
r
e
nt
t
r
a
i
ni
ng
l
e
ng
t
hs
ba
s
e
d
on
T
a
bl
e
1
.
B
y
e
xt
e
ndi
ng
t
he
s
t
a
r
t
i
ng
y
e
a
r
of
t
h
e
t
r
a
i
ni
ng
da
t
a
f
r
o
m
2018
ba
c
k
t
o
20
06,
t
hi
s
s
c
he
m
e
a
l
l
ow
s
t
he
a
na
l
y
s
i
s
of
w
he
t
he
r
a
l
ong
e
r
hi
s
t
or
i
c
a
l
da
t
a
s
e
t
l
e
a
ds
t
o
be
t
t
e
r
f
or
e
c
a
s
t
i
ng
pe
r
f
or
m
a
n
c
e
.
S
c
e
na
r
i
o
5
i
s
s
pe
c
i
f
i
c
a
l
l
y
de
s
i
g
ne
d
t
o
e
v
a
l
ua
t
e
how
t
he
m
ode
l
s
pe
r
f
or
m
w
h
e
n t
r
a
i
ne
d on a
s
hor
t
e
r
a
nd
m
or
e
l
i
m
i
t
e
d da
t
a
s
e
t
.
T
he
t
e
s
t
i
ng
hor
i
z
on
s
c
e
n
a
r
i
os
i
n
T
a
bl
e
2
a
r
e
de
s
i
g
ne
d
t
o
e
v
a
l
ua
t
e
m
ode
l
pe
r
f
or
m
a
nc
e
a
c
r
os
s
di
f
f
e
r
e
nt
f
or
e
c
a
s
t
i
ng
l
e
n
g
t
hs
,
r
a
ng
i
n
g
f
r
o
m
s
hor
t
-
t
e
r
m
t
o
l
on
g
-
t
e
r
m
pr
e
di
c
t
i
ons
.
T
hi
s
s
c
he
m
e
a
l
l
o
w
s
t
he
a
n
a
l
y
s
i
s
of
ho
w
m
ode
l
pe
r
f
or
m
e
d
w
he
n
f
or
e
c
a
s
t
i
ng
f
or
1
w
e
e
k, s
e
v
e
r
a
l
w
e
e
ks
,
m
ont
hl
y
,
a
nd qua
r
t
e
r
l
y
hor
i
z
ons
.
F
i
g
ur
e
1
.
F
r
a
m
e
w
or
k of
t
he
pr
opos
e
d
m
od
e
l
T
a
bl
e
1
.
S
pl
i
t
t
i
ng
da
t
a
s
c
e
na
r
i
os
on W
e
s
t
J
a
v
a
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
S
c
e
n
a
r
i
o
T
r
a
i
n
i
ng
da
t
a
T
e
s
t
i
ng
da
t
a
1
01/
01/
2006
–
31/
12/
20
22
01/
01/
2023
–
31/
12/
20
23
2
01/
01/
2009
–
31/
12/
20
22
01/
01/
2023
–
31/
12/
20
23
3
01/
01/
2012
–
31/
12/
20
22
01/
01/
2023
–
31/
12/
20
23
4
01/
01/
2015
–
31/
12/
20
22
01/
01/
2023
–
31/
12/
20
23
5
01/
01/
2018
–
31/
12/
20
22
01/
01/
2023
–
31/
12/
20
23
T
a
bl
e
2
.
T
e
s
t
i
ng
da
t
a
hor
i
z
on s
c
e
na
r
i
os
S
c
e
n
a
r
i
o
H
o
r
i
z
o
n
T
e
s
t
i
ng
da
t
a
1
1
W
e
e
k
01/
01/
2023
–
08/
01/
20
23
2
2
W
e
e
k
01/
01/
2023
–
15/
01/
20
23
3
3
W
e
e
k
01/
01/
2023
–
22/
01/
20
23
4
4
W
e
e
k
01/
01/
2023
–
29/
01/
20
23
5
1
M
o
n
t
h
01/
01/
2023
–
31/
01/
20
23
6
2
M
o
n
t
h
01/
01/
2023
–
28/
02/
20
23
7
1
Q
ua
r
t
e
r
01/
01/
2023
–
31/
03/
20
23
8
2
Q
ua
r
t
e
r
01/
01/
2023
–
30/
06/
20
23
9
3
Q
ua
r
t
e
r
01/
01/
2023
–
30/
09/
20
23
2
.3
.
D
at
a
p
r
e
p
r
oc
e
s
s
i
n
g
B
ot
h
t
r
a
i
ni
ng
da
t
a
s
e
t
s
unde
r
g
o
a
pr
e
p
r
oc
e
s
s
i
ng
pr
o
c
e
s
s
,
a
s
i
l
l
us
t
r
a
t
e
d
i
n
F
i
g
ur
e
2
,
w
hi
c
h
i
s
di
f
f
e
r
e
nt
i
a
t
e
d
ba
s
e
d
on
t
he
m
ode
l
t
y
pe
:
de
e
p
l
e
a
r
ni
ng
(
C
N
N
-
B
i
L
S
T
M
a
nd
C
N
N
-
B
i
G
R
U
)
a
nd
W
i
ndow
e
d
-
X
G
B
oos
t
.
F
or
t
he
de
e
p
l
e
a
r
ni
ng
m
ode
l
s
,
one
-
hot
e
nc
odi
ng
i
s
a
ppl
i
e
d
be
f
or
e
da
t
a
s
pl
i
t
t
i
n
g
,
f
ol
l
ow
e
d
b
y
M
i
n
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
I
S
S
N
:
2
5
0
2
-
4
7
52
M
e
t
a
-
s
t
ac
k
i
ng m
od
e
l
s
f
o
r
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
o
r
e
c
as
t
i
ng
i
n W
e
s
t
J
av
a
(
D
e
nand
a A
u
f
a
d
l
an
T
s
a
qi
f
)
445
M
a
x
nor
m
a
l
i
z
a
t
i
on
a
nd
w
i
ndo
w
bui
l
di
ng
a
f
t
e
r
s
pl
i
t
t
i
ng
.
W
i
ndow
bui
l
di
ng
t
r
a
ns
f
or
m
s
t
he
t
i
m
e
s
e
r
i
e
s
i
nt
o
s
e
que
nt
i
a
l
i
nput
-
out
p
ut
pa
i
r
s
.
T
hi
s
r
e
s
e
a
r
c
h
us
i
ng
a
w
i
ndo
w
s
i
z
e
of
31
da
y
s
t
o
c
a
pt
ur
e
f
ul
l
m
ont
hl
y
s
e
a
s
ona
l
pa
t
t
e
r
ns
.
F
or
W
i
ndow
e
d
-
XG
B
oos
t
,
pr
e
pr
oc
e
s
s
i
ng
c
ons
i
s
t
s
of
da
t
a
s
pl
i
t
t
i
ng
a
nd
s
i
g
ni
f
i
c
a
nt
l
a
g
e
xt
r
a
c
t
i
on
f
or
t
he
l
oa
d
v
a
r
i
a
bl
e
us
i
ng
t
he
pa
r
t
i
a
l
a
ut
oc
or
r
e
l
a
t
i
on
f
unc
t
i
on
(
P
A
C
F
)
pl
ot
.
T
he
us
e
of
t
he
P
A
C
F
pl
ot
pr
ov
i
de
s
s
t
a
t
i
s
t
i
c
a
l
j
us
t
i
f
i
c
a
t
i
on
f
or
s
e
l
e
c
t
i
ng
r
e
l
e
v
a
nt
l
a
g
t
e
r
m
s
by
i
de
nt
i
f
y
i
ng
s
i
g
ni
f
i
c
a
nt
pa
r
t
i
a
l
a
ut
oc
or
r
e
l
a
t
i
ons
,
e
ns
ur
i
ng
t
ha
t
onl
y
i
nf
or
m
a
t
i
v
e
t
e
m
por
a
l
de
pe
nde
nc
i
e
s
a
r
e
i
nc
l
ude
d i
n t
he
m
ode
l
[
20]
.
F
i
g
ur
e
2
. P
r
e
pr
oc
e
s
s
i
ng
s
c
he
m
e
f
o
r
de
e
p l
e
a
r
ni
ng
a
nd W
i
ndo
w
e
d
-
X
G
B
oos
t
2
.4
.
M
od
e
l
i
n
g
s
c
h
e
me
T
he
w
hol
e
m
ode
l
i
ng
m
e
c
ha
ni
s
m
i
s
i
l
l
us
t
r
a
t
e
d
i
n
F
i
g
ur
e
3
.
E
a
c
h
s
c
e
na
r
i
o
ha
s
a
di
f
f
e
r
e
n
t
s
t
a
r
t
i
ng
poi
nt
f
or
t
he
t
r
a
i
ni
ng
da
t
a
,
w
he
r
e
t
he
d
a
t
a
s
e
t
i
s
di
v
i
de
d i
nt
o t
w
o di
f
f
e
r
e
nt
t
r
a
i
ni
ng
s
e
t
s
.
T
he
f
i
r
s
t
t
r
a
i
ni
ng
s
e
t
i
s
us
e
d
f
or
i
ndi
v
i
dua
l
m
ode
l
s
m
od
e
l
i
ng
,
i
nc
l
udi
ng
pr
e
pr
oc
e
s
s
i
ng
,
h
y
pe
r
pa
r
a
m
e
t
e
r
t
uni
ng
,
a
nd
ge
ne
r
a
t
i
n
g
f
or
e
c
a
s
t
s
.
I
n
t
hi
s
s
t
udy
,
t
he
i
ndi
v
i
dua
l
m
ode
l
s
,
w
hi
c
h
l
a
t
e
r
a
c
t
a
s
b
a
s
e
-
m
ode
l
s
i
n
t
he
m
e
t
a
-
s
t
a
c
ki
n
g
f
r
a
m
e
w
or
k,
c
ons
i
s
t
of
C
N
N
-
B
i
L
S
T
M
,
C
N
N
-
B
i
G
R
U
,
a
nd
W
i
ndow
e
d
-
X
G
B
oos
t
.
T
he
opt
i
m
a
l
hy
pe
r
pa
r
a
m
e
t
e
r
c
onf
i
g
ur
a
t
i
on
obt
a
i
ne
d
f
r
o
m
t
hi
s
s
t
a
g
e
i
s
t
he
n
r
e
us
e
d
i
n
t
he
s
e
c
ond
s
t
a
g
e
,
w
he
r
e
t
he
s
e
c
ond
t
r
a
i
ni
ng
s
e
t
i
s
us
e
d
f
or
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
i
n
g
by
r
e
-
t
r
a
i
ni
ng
t
he
s
e
b
a
s
e
-
m
od
e
l
s
w
i
t
hout
f
ur
t
h
e
r
t
uni
ng
,
a
nd
t
he
i
r
pr
e
di
c
t
i
ons
a
r
e
c
o
m
bi
ne
d us
i
ng
a
l
i
ne
a
r
r
e
g
r
e
s
s
i
on
m
ode
l
a
s
t
he
m
e
t
a
-
l
e
a
r
n
e
r
.
F
i
g
ur
e
3
. M
ode
l
i
ng
s
c
he
m
e
H
y
pe
r
p
a
r
a
m
e
t
e
r
opt
i
m
i
z
a
t
i
on
i
s
c
onduc
t
e
d
us
i
ng
B
a
ye
s
i
a
n
opt
i
m
i
z
a
t
i
on
t
o
e
f
f
i
c
i
e
nt
l
y
e
x
pl
or
e
t
he
de
f
i
ne
d
s
e
a
r
c
h
s
pa
c
e
.
T
he
C
N
N
c
o
m
pone
nt
a
ppl
i
e
s
one
or
t
w
o
c
on
v
ol
ut
i
ona
l
l
a
y
e
r
s
w
i
t
h
f
i
l
t
e
r
s
r
a
ng
i
ng
f
r
o
m
16
t
o
128
a
nd
ke
r
ne
l
s
i
z
e
s
of
2,
3,
or
5,
a
nd
a
c
t
i
v
a
t
i
on
f
unc
t
i
ons
i
nc
l
udi
ng
R
e
L
U
,
t
a
nh,
or
l
i
ne
a
r
.
T
h
e
r
e
c
ur
r
e
nt
c
o
m
pone
nt
c
ons
i
s
t
s
of
one
or
t
w
o
bi
d
i
r
e
c
t
i
ona
l
l
a
ye
r
s
(
B
i
G
R
U
or
B
i
L
S
T
M
)
w
i
t
h
16 t
o 128 ne
ur
ons
pe
r
l
a
y
e
r
a
nd
a
c
t
i
v
a
t
i
on
f
unc
t
i
ons
of
t
a
nh,
R
e
L
U
,
or
l
i
ne
a
r
.
M
ode
l
opt
i
m
i
z
a
t
i
on
i
s
pe
r
f
o
r
m
e
d
us
i
ng
A
da
m
o
r
R
M
S
pr
op
w
i
t
h
a
l
e
a
r
ni
ng
r
a
t
e
s
a
m
pl
e
d
w
i
t
hi
n
10
−
4
to
10
−
2
,
a
nd
t
r
a
i
ni
ng
i
s
c
onduc
t
e
d
us
i
ng
ba
t
c
h
s
i
z
e
s
of
16,
32,
or
64
.
F
or
t
he
W
i
ndow
e
d
-
X
G
B
oos
t
m
ode
l
,
t
he
a
r
c
hi
t
e
c
t
ur
e
i
s
ba
s
e
d
on
gr
a
di
e
nt
boos
t
i
ng
de
c
i
s
i
on
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
, V
ol
.
42
, N
o.
2
,
M
a
y
20
26
:
442
-
453
446
t
r
e
e
s
w
i
t
h
l
a
g
-
ba
s
e
d
i
nput
f
e
a
t
ur
e
s
.
T
he
nu
m
be
r
of
t
r
e
e
s
(
n_e
s
t
i
m
a
t
or
s
)
r
a
n
g
e
s
f
r
o
m
50
t
o
1000,
w
i
t
h
m
a
xi
m
u
m
t
r
e
e
de
pt
h
be
t
w
e
e
n
3
a
nd
15.
T
he
boos
t
i
ng
l
e
a
r
ni
ng
r
a
t
e
i
s
s
e
a
r
c
he
d
w
i
t
hi
n
0.
001
to
0.3,
w
hi
l
e
s
a
m
pl
i
ng
pa
r
a
m
e
t
e
r
s
i
nc
l
ude
s
ubs
a
m
pl
e
w
i
t
hi
n
0.6
t
o
1.0
a
nd
c
o
l
s
a
m
pl
e
_b
y
t
r
e
e
w
i
t
hi
n
0.
5
t
o
1.0.
R
e
g
ul
a
r
i
z
a
t
i
on
pa
r
a
m
e
t
e
r
s
i
nc
l
ude
g
a
m
m
a
w
i
t
hi
n
0
t
o
5,
m
i
n_c
hi
l
d_w
e
i
g
ht
w
i
t
hi
n
1
t
o
15,
L
2
r
e
g
ul
a
r
i
z
a
t
i
on
(
)
w
i
t
hi
n
1e
-
3
t
o
100,
a
nd
L
1 r
e
g
ul
a
r
i
z
a
t
i
on (
)
w
i
t
hi
n
1e
-
3
to
100 t
o c
ont
r
ol
m
od
e
l
c
o
m
pl
e
xi
t
y
a
nd pr
e
v
e
n
t
o
v
e
r
f
i
t
t
i
ng
.
W
ol
pe
r
t
[
21]
i
nt
r
oduc
e
d
m
e
t
a
-
s
t
a
c
ki
ng
,
a
hy
b
r
i
d
m
od
e
l
a
ppr
oa
c
h
t
ha
t
c
o
m
bi
ne
s
m
ul
t
i
pl
e
m
ode
l
s
,
know
n
a
s
ba
s
e
-
l
e
a
r
ne
r
s
,
t
hr
oug
h
a
not
he
r
m
ode
l
c
a
l
l
e
d
a
s
m
e
t
a
-
l
e
a
r
ne
r
.
M
e
t
a
-
s
t
a
c
ki
ng
c
on
s
i
s
t
s
of
t
w
o
l
e
v
e
l
s
l
e
v
e
l
0,
w
he
r
e
ba
s
e
-
m
ode
l
s
a
r
e
t
r
a
i
ne
d
i
n
pa
r
a
l
l
e
l
us
i
ng
t
he
s
e
c
ond
t
r
a
i
ni
ng
da
t
a
,
a
nd
l
e
v
e
l
1,
w
he
r
e
l
e
v
e
l
0
f
or
e
c
a
s
t
s
a
r
e
us
e
d
a
s
i
nput
f
or
t
he
m
e
t
a
-
l
e
a
r
ne
r
.
T
o
e
ns
ur
e
unbi
a
s
e
d
m
e
t
a
-
l
e
a
r
n
e
r
i
nput
,
OOF
pr
e
di
c
t
i
ons
a
r
e
g
e
ne
r
a
t
e
d t
hr
ou
g
h a
n i
t
e
r
a
t
i
v
e
m
e
c
ha
ni
s
m
,
a
s
i
l
l
us
t
r
a
t
e
d i
n
F
i
g
ur
e
4
.
T
he
s
e
c
ond
t
r
a
i
ni
ng da
t
a
a
r
e
di
v
i
de
d i
nt
o
s
e
v
e
r
a
l
i
t
e
r
a
t
i
ons
,
w
he
r
e
e
a
c
h
i
t
e
r
a
t
i
on
us
e
s
one
s
ubs
e
t
a
s
t
r
a
i
ni
ng
da
t
a
w
hi
l
e
t
he
r
e
m
a
i
ni
ng
da
t
a
a
r
e
us
e
d
f
o
r
v
a
l
i
da
t
i
on
da
t
a
.
T
he
v
a
l
i
da
t
i
on
r
e
s
ul
t
s
f
r
om
I
t
e
r
a
t
i
on
1
t
o
I
t
e
r
a
t
i
on
5
a
r
e
c
o
m
bi
ne
d
t
o
f
or
m
O
O
F
pr
e
di
c
t
i
ons
a
c
r
os
s
t
he
e
nt
i
r
e
s
e
c
ond
t
r
a
i
ni
ng
da
t
a
.
T
he
s
e
O
O
F
pr
e
di
c
t
i
ons
a
r
e
t
he
n
u
s
e
d
a
s
i
np
ut
s
t
o
t
r
a
i
n
t
he
m
e
t
a
-
l
e
a
r
ne
r
,
e
ns
ur
i
ng
t
ha
t
e
a
c
h
pr
e
di
c
t
i
on
i
s
g
e
ne
r
a
t
e
d
f
r
o
m
a
m
ode
l
t
ha
t
doe
s
not
di
r
e
c
t
l
y
t
r
a
i
n
on
t
he
s
a
m
e
v
a
l
i
da
t
i
on
obs
e
r
v
a
t
i
ons
[
20]
.
M
e
t
a
-
s
t
a
c
ki
n
g
a
ppr
oa
c
h
a
l
l
ow
s
t
he
ba
s
e
-
m
ode
l
s
t
o
c
o
m
p
e
ns
a
t
e
f
or
e
a
c
h
ot
he
r
’
s
l
i
m
i
t
a
t
i
ons
w
hi
l
e
l
e
v
e
r
a
g
i
n
g
t
he
i
r
i
ndi
v
i
dua
l
s
t
r
e
n
g
t
hs
[
22]
, [
23]
.
F
i
g
ur
e
4
. O
ut
-
of
-
f
ol
d pr
e
di
c
t
i
ons
s
c
he
m
e
2
.5
.
M
od
e
l
e
val
u
at
i
on
s
c
h
e
m
e
M
ode
l
e
v
a
l
ua
t
i
on
i
s
c
onduc
t
e
d
t
o
a
s
s
e
s
s
t
he
pe
r
f
or
m
a
nc
e
of
m
e
t
a
-
s
t
a
c
ki
ng
c
o
m
pa
r
e
d
t
o
i
ndi
v
i
dua
l
m
od
e
l
s
,
a
s
i
l
l
us
t
r
a
t
e
d
i
n
F
i
g
ur
e
5
.
F
or
e
c
a
s
t
s
a
r
e
g
e
ne
r
a
t
e
d
f
or
a
l
l
s
c
e
na
r
i
os
us
i
ng
da
t
a
up
t
o
2022
f
or
m
od
e
l
i
ng
,
w
hi
l
e
t
he
y
e
a
r
2023
i
s
us
e
d
a
s
t
he
t
e
s
t
da
t
a
s
e
t
t
o
e
v
a
l
ua
t
e
pe
r
f
or
m
a
nc
e
on
uns
e
e
n
da
t
a
.
T
he
t
e
s
t
da
t
a
a
r
e
f
ur
t
he
r
di
v
i
de
d i
nt
o
m
ul
t
i
pl
e
f
or
e
c
a
s
t
hor
i
z
ons
ba
s
e
d on
T
a
bl
e
2
.
T
he
e
v
a
l
ua
t
i
on
i
nc
l
ude
s
g
e
ne
r
a
l
i
z
a
t
i
on
a
na
l
y
s
i
s
b
y
c
o
m
pa
r
i
n
g
t
r
a
i
n
a
nd
t
e
s
t
a
c
c
ur
a
c
y
,
a
s
w
e
l
l
a
s
p
e
r
f
or
m
a
nc
e
a
s
s
e
s
s
m
e
nt
on
t
he
t
e
s
t
da
t
a
us
i
ng
M
A
P
E
a
nd
t
r
e
nd
a
c
c
u
r
a
c
y
a
c
r
os
s
di
f
f
e
r
e
nt
hor
i
z
ons
.
F
i
na
l
l
y
,
t
he
be
s
t
m
ode
l
i
s
de
t
e
r
m
i
ne
d
ba
s
e
d
on
i
t
s
ov
e
r
a
l
l
f
or
e
c
a
s
t
i
ng
pe
r
f
or
m
a
nc
e
unde
r
t
he
s
e
e
v
a
l
ua
t
i
on
c
r
i
t
e
r
i
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
I
S
S
N
:
2
5
0
2
-
4
7
52
M
e
t
a
-
s
t
ac
k
i
ng m
od
e
l
s
f
o
r
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
o
r
e
c
as
t
i
ng
i
n W
e
s
t
J
av
a
(
D
e
nand
a A
u
f
a
d
l
an
T
s
a
qi
f
)
44
7
F
i
g
ur
e
5
. M
ode
l
e
v
a
l
ua
t
i
on s
c
he
m
e
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
I
n
t
hi
s
s
e
c
t
i
on,
w
e
pr
e
s
e
nt
a
n
e
v
a
l
ua
t
i
on
of
t
he
pr
opos
e
d
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
f
or
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
or
e
c
a
s
t
i
ng
i
n
W
e
s
t
J
a
v
a
P
r
o
v
i
nc
e
.
T
he
m
ode
l
'
s
pe
r
f
or
m
a
nc
e
i
s
c
o
m
pa
r
e
d
a
g
a
i
ns
t
t
hr
e
e
i
ndi
v
i
dua
l
ba
s
e
-
l
e
a
r
ne
r
s
,
w
hi
c
h
a
r
e
W
i
ndow
e
d
-
X
G
B
oos
t
,
C
N
N
-
B
i
G
R
U
,
a
nd
C
N
N
-
B
i
L
S
T
M
.
T
he
m
ode
l
’
s
a
l
s
o
e
v
a
l
ua
t
e
d
on
f
i
v
e
di
f
f
e
r
e
nt
s
c
e
na
r
i
os
.
3.1.
P
e
r
f
or
m
an
c
e
e
val
u
at
i
on
m
e
t
r
i
c
s
T
he
m
e
t
r
i
c
s
us
e
d
i
n
t
hi
s
s
t
u
dy
a
r
e
M
e
a
n
A
bs
ol
ut
e
P
e
r
c
e
nt
a
g
e
E
r
r
or
(
M
A
P
E
)
a
nd
t
r
e
nd
a
c
c
ur
a
c
y
.
T
he
s
e
m
e
t
r
i
c
s
c
l
e
a
r
l
y
s
how
t
he
di
f
f
e
r
e
nc
e
s
be
t
w
e
e
n
t
he
pr
e
di
c
t
e
d
v
a
l
ue
s
a
nd
t
he
a
c
t
ua
l
v
a
l
ue
s
.
M
A
P
E
i
s
f
or
m
ul
a
t
e
d a
s
f
ol
l
ow
s
[
24]
:
=
1
Σ
=
1
|
(
(
)
−
(
)
)
(
)
|
(
1
)
w
he
r
e
(
)
i
s
t
he
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
i
n
pe
r
i
od
,
(
)
i
s
t
he
f
or
e
c
a
s
t
e
d
e
l
e
c
t
r
i
c
i
t
y
i
n
pe
r
i
od
.
T
h
e
c
onf
us
i
on m
a
t
r
i
x i
s
us
e
d t
o m
e
a
s
ur
e
c
l
a
s
s
i
f
i
c
a
t
i
on a
c
c
ur
a
c
y
,
c
a
l
c
ul
a
t
e
d a
s
[
25]
:
A
c
c
ur
a
c
y
=
+
+
+
+
×
100
(
2
)
wh
e
r
e
t
r
e
nds
a
r
e
c
ons
i
de
r
e
d
up
w
a
r
d
(
P
os
i
t
i
v
e
)
i
f
+
1
>
a
nd
dow
n
w
a
r
d
(
N
e
g
a
t
i
v
e
)
i
f
+
1
<
.
T
he
c
ount
s
of
t
r
ue
pos
i
t
i
v
e
(
T
P
)
,
t
r
ue
ne
g
a
t
i
v
e
(
T
N
)
,
f
a
l
s
e
pos
i
t
i
v
e
(
F
P
)
,
a
nd
f
a
l
s
e
ne
g
a
t
i
v
e
(
F
N
)
a
r
e
obt
a
i
ne
d
b
y
c
o
m
pa
r
i
n
g
t
he
di
r
e
c
t
i
on of
t
he
a
c
t
ua
l
a
nd pr
e
di
c
t
e
d t
r
e
nds
.
3.2.
R
e
s
u
l
t
B
e
f
or
e
m
ode
l
l
i
ng
t
he
W
e
s
t
J
a
v
a
e
l
e
c
t
r
i
c
a
l
l
oa
d
da
t
a
,
a
n
e
xpl
or
a
t
or
y
a
na
l
y
s
i
s
i
s
c
onduc
t
e
d
t
o
g
e
t
a
c
l
e
a
r
unde
r
s
t
a
ndi
ng
of
t
he
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
a
nd pa
t
t
e
r
ns
w
i
t
hi
n t
he
da
t
a
. B
a
s
e
d on
F
i
g
ur
e
6
,
i
n
t
he
l
on
g
e
r
-
t
e
r
m
,
t
he
w
e
s
t
j
a
v
a
e
l
e
c
t
r
i
c
a
l
l
oa
d
da
t
a
f
r
o
m
2006
unt
i
l
2023
ha
s
pos
i
t
i
v
e
t
r
e
nds
,
w
hi
c
h
i
s
c
a
us
e
d
b
y
t
he
m
o
r
e
a
d
v
a
nc
e
d
t
e
c
hnol
ogy
r
e
qui
r
e
s
m
or
e
e
l
e
c
t
r
i
c
a
nd
hum
a
n
popul
a
t
i
on
i
nc
r
e
a
s
e
[
26]
.
T
he
r
e
’
s
a
l
s
o
a
r
e
pe
a
t
e
d
s
i
g
ni
f
i
c
a
nt
dr
op
i
n
t
he
da
t
a
,
w
he
r
e
t
he
m
os
t
s
i
g
ni
f
i
c
a
nt
dr
op
i
s
c
a
us
e
d
by
E
i
d
a
l
-
F
i
t
r
a
nd
E
i
d
a
l
-
A
dha
.
A
l
s
o
,
ot
he
r
s
hol
i
da
y
s
uc
h
a
s
N
e
w
Y
e
a
r
l
e
d
t
o
a
s
i
g
ni
f
i
c
a
nt
dr
op.
T
hi
s
i
s
c
a
us
e
d
b
y
m
a
ny
f
a
c
t
or
i
e
s
c
l
os
e
d
due
t
o
m
a
j
or
hol
i
da
y
s
[
19]
.
C
o
v
i
d
-
19
i
nc
i
de
nt
a
l
s
o
l
e
d
t
o
a
s
i
g
ni
f
i
c
a
nt
dr
o
p
i
n
t
he
da
t
a
w
hi
c
h
c
a
n
be
s
e
e
n
on
t
he
pe
r
i
od
of
2021.
B
a
s
e
d
on
t
he
s
e
f
i
ndi
ng
s
i
ndi
c
a
t
e
t
ha
t
t
he
e
l
e
c
t
r
i
c
a
l
l
oa
d
da
t
a
i
s
dr
i
v
e
n by
g
l
oba
l
a
nd l
oc
a
l
e
v
e
nt
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
, V
ol
.
42
, N
o.
2
,
M
a
y
20
26
:
442
-
453
448
F
i
g
ur
e
6
.
W
e
s
t
J
a
v
a
e
l
e
c
t
r
i
c
a
l
l
oa
d
d
a
t
a
p
a
t
t
e
r
n f
r
o
m
J
a
nua
r
y
1,
2006 unt
i
l
D
e
c
e
m
be
r
31,
202
3
P
r
i
or
to
a
na
l
y
s
i
s
of
t
he
f
or
e
c
a
s
t
i
ng
m
ode
l
s
,
a
n
i
ni
t
i
a
l
a
na
l
y
s
i
s
w
a
s
pe
r
f
or
m
e
d
t
o
i
de
nt
i
f
y
s
e
a
s
ona
l
pa
t
t
e
r
n
i
n
t
he
e
l
e
c
t
r
i
c
a
l
da
t
a
l
oa
d.
T
he
r
e
s
ul
t
s
i
ndi
c
a
t
e
t
he
da
t
a
ha
s
7
-
da
y
s
s
e
a
s
ona
l
i
t
y
a
ut
o
c
or
r
e
l
a
t
i
on
pa
t
t
e
r
n,
a
s
s
how
n
i
n
F
i
g
ur
e
7
.
W
e
a
n
a
l
yz
e
d
t
he
f
or
e
c
a
s
t
e
d
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
i
n
W
e
s
t
J
a
v
a
P
r
o
v
i
n
c
e
a
c
r
os
s
di
f
f
e
r
e
nt
s
c
e
na
r
i
os
t
o e
v
a
l
ua
t
e
w
h
e
t
he
r
t
he
pr
opos
e
d
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
out
pe
r
f
or
m
s
t
he
i
ndi
v
i
dua
l
m
ode
l
s
.
F
i
g
ur
e
8
pr
e
s
e
nt
s
t
he
di
s
t
r
i
b
ut
i
on
of
m
ode
l
pe
r
f
or
m
a
nc
e
a
c
r
os
s
f
i
v
e
s
c
e
na
r
i
os
us
i
ng
t
r
a
i
ni
ng
a
nd
t
e
s
t
i
ng
da
t
a
, a
l
l
ow
i
ng
e
v
a
l
ua
t
i
on on g
e
ne
r
a
l
i
z
a
t
i
on
c
a
pa
bi
l
i
t
y
.
F
i
g
ur
e
8
(
a
)
i
l
l
us
t
r
a
t
e
s
t
he
di
s
t
r
i
but
i
on
of
M
A
P
E
f
or
e
a
c
h
m
od
e
l
.
T
h
e
m
e
t
a
-
s
t
a
c
ki
n
g
m
ode
l
s
how
s
a
m
o
r
e
s
t
a
bl
e
di
s
t
r
i
but
i
on a
nd a
s
m
a
l
l
e
r
g
a
p be
t
w
e
e
n t
r
a
i
ni
ng
a
nd t
e
s
t
i
ng
e
r
r
o
r
s
, i
ndi
c
a
t
i
ng
be
t
t
e
r
g
e
ne
r
a
l
i
z
a
t
i
on.
F
i
g
ur
e
8
(
b)
pr
e
s
e
nt
s
t
he
di
s
t
r
i
but
i
on
of
t
r
e
nd
a
c
c
ur
a
c
y
.
T
he
m
e
t
a
-
s
t
a
c
ki
ng
m
od
e
l
m
a
i
nt
a
i
ns
c
ons
i
s
t
e
nt
t
r
e
nd
pe
r
f
or
m
a
n
c
e
a
c
r
os
s
s
c
e
n
a
r
i
os
,
de
m
ons
t
r
a
t
i
ng
i
t
s
r
obus
t
ne
s
s
c
om
p
a
r
e
d
t
o
t
he
i
ndi
v
i
dua
l
m
od
e
l
s
.
T
h
e
g
a
p
be
t
w
e
e
n
t
r
a
i
ni
ng
a
nd
t
e
s
t
i
ng
pe
r
f
or
m
a
nc
e
i
s
r
e
l
a
t
i
v
e
l
y
s
m
a
l
l
,
i
ndi
c
a
t
i
ng
good
g
e
ne
r
a
l
i
z
a
t
i
on
a
bi
l
i
t
y
c
o
m
pa
r
e
d
t
o
i
ndi
v
i
dua
l
m
od
e
l
s
,
w
hi
c
h
t
e
nd
t
o
e
xhi
bi
t
l
a
r
ge
r
di
s
c
r
e
p
a
nc
i
e
s
be
t
w
e
e
n
t
r
a
i
n
a
nd
t
e
s
t
r
e
s
ul
t
s
.
E
r
r
or
!
R
e
f
e
r
e
n
c
e
s
ou
r
c
e
n
ot
f
ou
n
d
.
pr
e
s
e
nt
s
t
he
c
om
pa
r
i
s
on
of
t
e
s
t
i
ng
pe
r
f
or
m
a
n
c
e
a
c
r
os
s
s
c
e
na
r
i
os
,
hi
g
hl
i
g
ht
i
ng
bot
h
e
r
r
or
m
a
g
ni
t
ude
a
nd
t
r
e
nd
a
c
c
ur
a
c
y
f
or
e
a
c
h
m
od
e
l
.
T
hi
s
f
i
g
ur
e
a
i
m
s
t
o
s
ho
w
how
t
he
m
ode
l
s
pe
r
f
or
m
a
nd
t
he
i
r
c
ons
i
s
t
e
nc
y
a
c
r
os
s
s
c
e
na
r
i
os
.
E
r
r
or
!
R
e
f
e
r
e
n
c
e
s
ou
r
c
e
n
ot
f
ou
n
d
.
(
a
)
di
s
pl
a
y
s
t
he
t
e
s
t
i
ng
M
A
P
E
,
w
hi
l
e
E
r
r
or
!
R
e
f
e
r
e
n
c
e
s
ou
r
c
e
n
ot
f
ou
n
d
.
(
b)
di
s
p
l
a
y
s
t
he
t
e
s
t
i
ng
t
r
e
nd
a
c
c
ur
a
c
y
. B
a
s
e
d on
E
r
r
or
!
R
e
f
e
r
e
n
c
e
s
ou
r
c
e
n
ot
f
ou
n
d
.
(
a
)
,
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
a
c
hi
e
v
e
s
t
he
l
ow
e
s
t
M
A
P
E
i
n
s
c
e
na
r
i
os
2006
,
2015
,
a
nd
2
018
.
C
N
N
-
B
i
L
S
T
M
pe
r
f
or
m
s
s
l
i
g
ht
l
y
be
t
t
e
r
i
n
200
9
a
nd
2012
,
but
s
how
s
r
e
l
a
t
i
v
e
l
y
l
o
w
t
r
e
nd
a
c
c
ur
a
cy
.
B
a
s
e
d
on
E
r
r
or
!
R
e
f
e
r
e
n
c
e
s
ou
r
c
e
n
ot
f
ou
n
d
.
(
b)
m
e
t
a
-
s
t
a
c
ki
ng
h
a
s
t
he
hi
g
he
s
t
t
r
e
nd
a
c
c
u
r
a
c
y
i
n
m
os
t
s
c
e
n
a
r
i
os
(
2006,
2009,
2012,
a
nd
2015)
,
w
he
r
e
a
s
W
i
ndow
e
d
-
X
G
B
oos
t
s
how
s
th
e
hi
g
he
s
t
t
r
e
nd
a
c
c
ur
a
c
y
i
n
2018
but
w
i
t
h
r
e
l
a
t
i
v
e
l
y
hi
g
h
M
A
P
E
.
O
v
e
r
a
l
l
,
m
e
t
a
-
s
t
a
c
ki
ng
pr
o
v
i
de
s
a
b
e
t
t
e
r
ba
l
a
nc
e
be
t
w
e
e
n l
o
w
f
or
e
c
a
s
t
i
ng
e
r
r
or
a
nd c
ons
i
s
t
e
nt
t
r
e
nd a
c
c
ur
a
c
y
a
c
r
os
s
s
c
e
na
r
i
os
.
F
i
g
ur
e
7
. W
e
s
t
J
a
v
a
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
a
ut
oc
or
r
e
l
a
t
i
on
p
a
t
t
e
r
n
L
a
g
le
c
tric
a
l o
a
d
w
A
u
t
o
c
o
r
r
e
l
a
t
i
o
n
(
%
)
E
l
e
c
t
r
i
c
a
l
L
oa
d
(
M
w
)
Y
e
a
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
I
S
S
N
:
2
5
0
2
-
4
7
52
M
e
t
a
-
s
t
ac
k
i
ng m
od
e
l
s
f
o
r
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
o
r
e
c
as
t
i
ng
i
n W
e
s
t
J
av
a
(
D
e
nand
a A
u
f
a
d
l
an
T
s
a
qi
f
)
449
(
a
)
(
b)
F
i
g
ur
e
8
.
D
i
s
t
r
i
but
i
o
n of
(
a
)
M
A
P
E
a
nd (
b)
t
r
e
nd a
c
c
ur
a
c
y
of
t
r
a
i
ni
ng
a
nd t
e
s
t
i
ng
da
t
a
f
or
e
a
c
h
m
ode
l
(
a
)
(
b)
F
i
g
ur
e
9
.
C
om
pa
r
i
s
on of
(
a
)
M
A
P
E
a
nd (
b)
t
r
e
nd a
c
c
ur
a
c
y
of
t
e
s
t
i
ng
da
t
a
f
o
r
e
a
c
h s
c
e
na
r
i
o
a
nd
m
ode
l
F
i
g
ur
e
10
pr
e
s
e
nt
s
t
he
c
o
m
pa
r
i
s
on
of
a
v
e
r
a
g
e
t
e
s
t
i
ng
pe
r
f
or
m
a
nc
e
a
c
r
os
s
di
f
f
e
r
e
nt
f
or
e
c
a
s
t
hor
i
z
ons
,
r
a
ng
i
n
g
f
r
o
m
s
hor
t
-
t
e
r
m
(
1
-
4
w
e
e
ks
)
t
o
l
ong
e
r
-
t
e
r
m
hor
i
z
ons
(
up
t
o
3
qua
r
t
e
r
s
)
.
T
hi
s
f
i
g
ur
e
a
i
m
s
t
o
e
v
a
l
u
a
t
e
how
e
a
c
h
m
ode
l
p
e
r
f
or
m
e
d
a
s
t
he
f
or
e
c
a
s
t
i
ng
l
e
n
g
t
h
i
nc
r
e
a
s
e
s
a
nd
t
o
a
s
s
e
s
s
pe
r
f
or
m
a
nc
e
s
t
a
bi
l
i
t
y
.
F
i
g
ur
e
10
(
a
)
s
how
s
t
he
a
v
e
r
a
g
e
M
A
P
E
a
c
r
os
s
hor
i
z
ons
,
i
nd
i
c
a
t
i
ng
t
ha
t
m
e
t
a
-
s
t
a
c
ki
ng
c
ons
i
s
t
e
nt
l
y
a
c
hi
e
v
e
s
t
he
l
ow
e
s
t
e
r
r
or
f
or
l
ong
e
r
hor
i
z
ons
(
1 t
o 3 qua
r
t
e
r
s
)
, a
l
t
houg
h i
t
doe
s
not
a
l
w
a
y
s
do
m
i
na
t
e
a
t
ve
r
y s
hor
t
hor
i
z
ons
(1
-
2
w
e
e
ks
)
.
F
i
g
ur
e
10
(
b)
i
l
l
us
t
r
a
t
e
s
t
he
a
v
e
r
a
ge
t
r
e
nd
a
c
c
u
r
a
c
y
,
w
he
r
e
m
e
t
a
-
s
t
a
c
ki
n
g
ge
ne
r
a
l
l
y
pe
r
f
or
m
s
be
t
t
e
r
a
t
l
ong
e
r
hor
i
z
ons
,
w
hi
l
e
W
i
ndow
e
d
-
X
G
B
oos
t
a
nd
C
N
N
-
B
i
G
R
U
oc
c
a
s
i
ona
l
l
y
obt
a
i
n
t
he
h
i
g
he
s
t
s
c
or
e
s
a
t
c
e
r
t
a
i
n
s
hor
t
e
r
hor
i
z
ons
.
O
v
e
r
a
l
l
,
t
he
s
e
r
e
s
ul
t
s
s
ugg
e
s
t
t
ha
t
m
e
t
a
-
s
t
a
c
ki
n
g
i
s
m
o
r
e
r
e
l
i
a
bl
e
f
or
l
ong
-
t
e
r
m
f
or
e
c
a
s
t
i
ng
,
w
hi
l
e
W
i
ndow
e
d
-
X
G
B
oos
t
m
a
y
be
a
be
t
t
e
r
c
hoi
c
e
f
or
s
hor
t
-
t
e
r
m
pr
e
di
c
t
i
on,
f
ur
t
he
r
a
na
l
y
s
i
s
i
s
ne
e
de
d t
o c
he
c
k
w
he
t
he
r
t
he
m
od
e
l
ge
ne
r
a
l
i
z
e
w
e
l
l
on t
he
ne
w
da
t
a
or
not
.
F
i
g
ur
e
11
pr
o
v
i
de
s
ba
s
e
l
i
ne
c
o
m
pa
r
i
s
on
b
y
a
v
e
r
a
g
i
ng
t
e
s
t
i
ng
p
e
r
f
or
m
a
nc
e
of
a
l
l
m
ode
l
s
a
c
r
os
s
t
he
f
i
v
e
s
c
e
na
r
i
os
.
B
a
s
e
d
on
F
i
g
ur
e
11
(
a
)
,
m
e
t
a
-
s
t
a
c
ki
ng
a
c
hi
e
v
e
s
t
he
l
o
w
e
s
t
a
v
e
r
a
g
e
t
e
s
t
M
A
P
E
(
2.27%
)
,
w
hi
l
e
F
i
g
ur
e
11
(
b)
i
ndi
c
a
t
e
s
t
ha
t
m
e
t
a
-
s
t
a
c
ki
ng
a
c
hi
e
v
e
s
t
he
hi
g
he
s
t
a
v
e
r
a
ge
t
e
s
t
t
r
e
nd
a
c
c
ur
a
c
y
(
85.27%
)
,
out
pe
r
f
or
m
i
ng
t
he
i
ndi
v
i
dua
l
m
ode
l
s
i
n
bot
h
m
e
t
r
i
c
s
.
W
hi
l
e
W
i
ndow
e
d
-
X
G
B
oos
t
s
how
s
r
e
l
a
t
i
v
e
l
y
hi
g
h
a
v
e
r
a
g
e
t
e
s
t
t
r
e
nd
a
c
c
ur
a
c
y
,
i
t
a
l
s
o
a
c
hi
e
v
e
s
hi
g
he
r
a
v
e
r
a
ge
t
e
s
t
M
A
P
E
.
O
n
t
he
c
ont
r
a
r
y
,
C
N
N
-
B
i
G
R
U
a
nd
C
N
N
-
B
i
L
S
T
M
a
c
hi
e
v
e
s
l
o
w
a
v
e
r
a
g
e
t
e
s
t
M
A
P
E
,
but
a
c
hi
e
v
e
s
l
o
w
a
v
e
r
a
ge
t
e
s
t
t
r
e
nd
a
c
c
u
r
a
c
y
.
O
v
e
r
a
l
l
,
t
hi
s
r
e
s
ul
t
c
onf
i
r
m
s
t
ha
t
m
e
t
a
-
s
t
a
c
ki
n
g
pr
o
v
i
de
s
t
he
ba
l
a
n
c
e
d
t
r
a
d
e
of
f
b
e
t
w
e
e
n
M
A
P
E
a
nd
t
r
e
nd
a
c
c
u
r
a
c
y
,
a
nd
s
upe
r
i
or
pe
r
f
or
m
a
nc
e
a
m
on
g
t
he
i
ndi
v
i
dua
l
m
ode
l
s
. S
um
m
a
r
y
of
t
he
r
e
s
e
a
r
c
h r
e
s
ul
t
s
i
s
pr
e
s
e
nt
e
d on t
he
T
a
bl
e
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
, V
ol
.
42
, N
o.
2
,
M
a
y
20
26
:
442
-
453
450
(
a
)
(
b)
F
i
g
ur
e
10
.
A
v
e
r
a
g
e
(
a
)
M
A
P
E
a
nd (
b)
t
r
e
nd a
c
c
ur
a
c
y
of
5 s
c
e
n
a
r
i
os
f
or
e
a
c
h
f
or
e
c
a
s
t
hor
i
z
on a
nd m
ode
l
(
a
)
(
b)
F
i
g
ur
e
11
. A
v
e
r
a
g
e
of
(
a
)
t
e
s
t
M
A
P
E
a
nd (
b)
t
e
s
t
t
r
e
nd a
c
c
u
r
a
c
y
b
y
m
ode
l
T
a
bl
e
3
. S
u
m
m
a
r
y
of
t
he
r
e
s
e
a
r
c
h
r
e
s
ul
t
s
M
ode
l
A
ve
r
a
g
e
t
e
s
t
M
A
P
E
A
ve
r
a
g
e
t
e
s
t
t
r
e
n
d
a
c
c
ur
a
c
y
S
t
r
e
ng
t
h
s
W
e
a
k
n
e
s
s
e
s
C
N
N
-
B
i
L
S
T
M
2.
43%
80.
60%
L
o
w
M
A
P
E
,
s
l
i
ght
l
y
c
o
m
pe
t
i
t
i
ve
w
i
t
h
m
e
t
a
-
s
t
a
c
ki
ng
i
n
M
A
P
E
L
o
w
e
s
t
t
r
e
n
d
a
c
c
ur
a
c
y
C
N
N
-
B
i
G
R
U
2.
64%
81.
13%
L
o
w
M
A
P
E
L
e
s
s
c
o
m
pe
t
i
t
i
ve
i
n
M
A
P
E
W
i
n
do
w
e
d
-
X
G
B
oos
t
3.
59%
84.
53%
H
i
gh
t
r
e
n
d
a
c
c
ur
a
c
y,
s
l
i
ght
l
y
c
o
m
pe
t
i
t
i
ve
w
i
t
h
m
e
t
a
-
s
t
a
c
ki
ng
i
n
t
r
e
n
d
a
c
c
ur
a
c
y
H
i
gh
M
A
P
E
,
w
e
a
ke
r
g
e
n
e
r
a
l
i
z
a
t
i
o
n
M
e
t
a
-
st
a
c
ki
ng
2.
27%
85.
27%
L
o
w
e
s
t
M
A
P
E
a
n
d
T
r
e
n
d
A
c
c
ur
a
c
y,
r
obus
t
g
e
n
e
r
a
l
i
z
a
t
i
o
n
H
i
gh
c
o
m
pu
t
a
t
i
o
n
a
l
B
a
s
e
d
on
t
he
r
e
s
e
a
r
c
h
r
e
s
ul
t
s
,
m
e
t
a
-
s
t
a
c
ki
ng
c
a
n
l
e
v
e
r
a
g
e
W
i
ndow
e
d
-
X
G
B
oos
t
s
t
r
e
ng
t
h
on
hi
g
h
t
r
e
nd
a
c
c
u
r
a
c
y
a
nd
de
e
p
l
e
a
r
ni
n
g
m
ode
l
s
s
t
r
e
n
g
t
h
on
l
ow
M
A
P
E
,
t
hus
i
ndi
c
a
t
i
ng
m
e
t
a
-
s
t
a
c
ki
ng
s
uc
c
e
s
s
f
ul
l
y
l
e
v
e
r
a
g
e
b
a
s
e
-
m
ode
l
s
s
t
r
e
n
g
t
h,
w
hi
l
e
o
v
e
r
c
o
m
i
n
g
bot
h
w
e
a
kne
s
s
e
s
.
M
e
t
a
-
s
t
a
c
ki
ng
i
s
a
be
t
t
e
r
m
ode
l
b
e
c
a
us
e
of
i
t
s
a
bi
l
i
t
y
i
n
e
f
f
e
c
t
i
v
e
l
y
g
e
n
e
r
a
l
i
z
e
on
t
he
ne
w
da
t
a
,
i
t
s
s
upe
r
i
or
i
t
y
a
g
a
i
ns
t
i
ndi
v
i
dua
l
m
ode
l
s
i
n
m
os
t
s
c
e
na
r
i
os
w
hi
l
e
m
a
i
nt
a
i
ni
ng
ba
l
a
nc
e
t
r
a
d
e
of
f
be
t
w
e
e
n
M
A
P
E
a
nd
t
r
e
nd
a
c
c
ur
a
c
y
,
a
nd
i
t
s
s
upe
r
i
or
i
t
y
i
n
l
ong
-
te
r
m
f
or
e
c
a
s
t
i
ng
.
B
a
s
e
d
on
T
a
bl
e
4
,
m
e
t
a
-
s
t
a
c
ki
n
g
i
n
s
c
e
na
r
i
o
of
2006
ha
s
t
he
l
ow
e
s
t
M
A
P
E
a
nd
t
he
3
rd
hi
g
he
s
t
t
r
e
nd
a
c
c
ur
a
c
y
,
w
hi
c
h
i
s
t
he
be
s
t
m
ode
l
i
n
t
hi
s
s
t
udy
.
F
i
g
ur
e
12
i
l
l
us
t
r
a
t
e
s
t
he
t
r
a
i
n
-
t
e
s
t
pe
r
f
or
m
a
nc
e
of
t
he
m
e
t
a
-
s
t
a
c
ki
n
g
m
od
e
l
a
c
r
os
s
s
c
e
n
a
r
i
os
,
w
hi
l
e
F
i
g
ur
e
12
(
a
)
ba
s
e
d
on
M
A
P
E
a
nd
F
i
g
u
r
e
12
(
b)
b
a
s
e
d
on
t
r
e
nd
a
c
c
ur
a
c
y)
.
F
i
g
ur
e
12
(
a
)
s
ho
w
s
t
ha
t
t
he
l
ong
e
r
t
he
da
t
a
s
e
t
,
t
he
be
t
t
e
r
m
e
t
a
-
s
t
a
c
ki
n
g
pe
r
f
or
m
s
i
n
t
e
r
m
s
of
M
A
P
E
.
O
n
t
he
c
ont
r
a
r
y
,
F
i
g
ur
e
12
(
b
)
s
how
s
a
di
f
f
e
r
e
nt
be
ha
v
i
o
r
f
or
t
r
e
nd
a
c
c
ur
a
c
y
,
w
hi
c
h
f
l
uc
t
ua
t
e
s
a
c
r
os
s
s
c
e
na
r
i
os
a
nd
doe
s
not
c
on
s
i
s
t
e
nt
l
y
i
nc
r
e
a
s
e
w
i
t
h
m
or
e
da
t
a
.
T
h
e
c
ons
i
s
t
e
nt
i
m
pr
o
v
e
m
e
nt
of
M
A
P
E
be
c
o
m
e
s
t
he
ba
s
i
s
f
or
de
t
e
r
m
i
ni
ng
t
he
be
s
t
-
pe
r
f
or
m
i
ng
m
ode
l
i
n
t
hi
s
s
t
udy
.
T
he
a
c
c
ur
a
c
y
of
a
l
l
m
ode
l
s
a
c
r
os
s
5
s
c
e
na
r
i
os
i
s
e
xpl
a
i
ne
d i
n
T
a
bl
e
4
.
F
i
g
ur
e
13
3
pr
e
s
e
nt
s
t
he
f
or
e
c
a
s
t
i
ng
pe
r
f
or
m
a
nc
e
of
t
he
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
on
t
he
2023
t
e
s
t
i
ng
da
t
a
,
i
nc
l
udi
ng
t
he
a
c
t
ua
l
v
e
r
s
us
pr
e
di
c
t
e
d
v
a
l
ue
s
i
n
F
i
g
ur
e
13
3
(
a
)
a
nd
t
he
r
e
s
i
dua
l
a
na
l
y
s
i
s
i
n
F
i
g
ur
e
13
3
(
b)
.
A
s
s
ho
w
n i
n
F
i
g
ur
e
13
3
(
a
)
, t
he
pr
e
di
c
t
e
d s
e
r
i
e
s
c
l
os
e
l
y
f
ol
l
ow
s
t
he
a
c
t
ua
l
l
oa
d a
c
r
os
s
m
os
t
pe
r
i
ods
, c
a
pt
ur
i
ng
bot
h
upw
a
r
d
a
nd
do
w
n
w
a
r
d
m
o
v
e
m
e
nt
s
w
i
t
h
g
ood
c
ons
i
s
t
e
nc
y
.
T
he
m
ode
l
r
e
m
a
i
ns
s
t
a
b
l
e
dur
i
ng
p
e
r
i
ods
of
s
udde
n
s
pi
ke
s
or
dr
ops
,
i
nd
i
c
a
t
i
ng
s
t
r
ong
ge
ne
r
a
l
i
z
a
t
i
on
on
uns
e
e
n
da
t
a
a
nd
r
e
l
i
a
bl
e
pe
r
f
or
m
a
nc
e
f
or
ope
r
a
t
i
ona
l
f
or
e
c
a
s
t
i
ng
.
D
e
s
pi
t
e
t
he
s
t
r
ong
o
v
e
r
a
l
l
pr
e
di
c
t
i
v
e
pe
r
f
o
r
m
a
nc
e
obs
e
r
v
e
d
i
n
F
i
g
ur
e
13
3
(
a
)
,
r
e
s
i
dua
l
g
a
p
s
a
r
e
s
t
i
l
l
obs
e
r
v
e
d,
a
s
i
l
l
us
t
r
a
t
e
d
i
n
F
i
g
ur
e
13
3
(
b)
.
T
h
e
l
a
r
g
e
s
t
e
r
r
o
r
s
t
e
nd
t
o
oc
c
ur
dur
i
ng
na
t
i
ona
l
hol
i
da
y
s
a
nd
j
oi
nt
l
e
a
v
e
pe
r
i
ods
.
A
l
t
houg
h
hol
i
da
y
i
ndi
c
a
t
or
s
w
e
r
e
i
nc
l
ude
d
a
s
m
ode
l
f
e
a
t
ur
e
s
,
unc
o
m
m
on
hol
i
da
y
s
or
m
a
j
o
r
hol
i
da
y
s
s
t
i
l
l
g
e
ne
r
a
t
e
hi
g
he
r
r
e
s
i
dua
l
s
due
t
o s
udde
n s
hi
f
t
s
i
n e
l
e
c
t
r
i
c
i
t
y
de
m
a
nd.
O
v
e
r
a
l
l
, t
he
r
e
s
ul
t
s
i
ndi
c
a
t
e
t
ha
t
t
he
pr
opos
e
d
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
a
c
hi
e
v
e
s
a
m
or
e
ba
l
a
nc
e
d
pe
r
f
or
m
a
nc
e
be
t
w
e
e
n
M
A
P
E
a
nd
t
r
e
n
d
a
c
c
ur
a
c
y
a
c
r
os
s
m
ul
t
i
pl
e
da
t
a
-
s
pl
i
t
t
i
ng
s
c
e
na
r
i
os
c
o
m
pa
r
e
d t
o t
he
i
ndi
v
i
dua
l
m
od
e
l
s
. T
he
m
ode
l
t
r
a
i
ne
d unde
r
t
he
2006
s
c
e
na
r
i
o
de
m
ons
t
r
a
t
e
s
t
he
s
t
r
on
g
e
s
t
o
v
e
r
a
l
l
pe
r
f
or
m
a
nc
e
i
n
t
e
r
m
s
o
f
f
or
e
c
a
s
t
i
ng
a
c
c
ur
a
c
y
a
nd
g
e
ne
r
a
l
i
z
a
t
i
on on uns
e
e
n da
t
a
.
M
a
ki
ng
i
t
r
e
l
i
a
bl
e
t
o s
uppor
t
P
L
N
ope
r
a
t
i
ona
l
ne
e
ds
.
T
he
pr
opos
e
d
f
r
a
m
e
w
or
k
pr
e
s
e
nt
s
pot
e
nt
i
a
l
s
c
a
l
a
bi
l
i
t
y
f
or
r
e
a
l
-
t
i
m
e
f
or
e
c
a
s
t
i
ng
i
n
P
L
N
ope
r
a
t
i
ona
l
.
T
he
b
a
s
e
-
m
od
e
l
s
a
r
e
t
r
a
i
ne
d
us
i
ng
hi
s
t
or
i
c
a
l
da
t
a
,
a
nd
t
he
m
e
t
a
-
l
e
a
r
ne
r
c
o
m
bi
ne
s
t
he
i
r
f
or
e
c
a
s
t
s
t
hr
oug
h
a
s
i
m
pl
e
r
e
gr
e
s
s
i
on
a
ppr
oa
c
h.
A
s
a
r
e
s
ul
t
,
t
he
pr
e
di
c
t
i
on
pr
oc
e
s
s
r
e
m
a
i
ns
c
o
m
put
a
t
i
ona
l
l
y
e
f
f
i
c
i
e
nt
a
nd
c
a
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
I
S
S
N
:
2
5
0
2
-
4
7
52
M
e
t
a
-
s
t
ac
k
i
ng m
od
e
l
s
f
o
r
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
f
o
r
e
c
as
t
i
ng
i
n W
e
s
t
J
av
a
(
D
e
nand
a A
u
f
a
d
l
an
T
s
a
qi
f
)
451
g
e
ne
r
a
t
e
da
i
l
y
l
oa
d
f
or
e
c
a
s
t
s
w
i
t
h
m
i
ni
m
a
l
pr
oc
e
s
s
i
ng
t
i
m
e
.
T
hi
s
m
a
ke
s
t
he
pr
opos
e
d
f
r
a
m
e
w
o
r
k
s
ui
t
a
bl
e
f
or
i
nt
e
g
r
a
t
i
on i
nt
o P
N
’
s
ope
r
a
t
i
ona
l
pl
a
nni
ng
.
T
a
bl
e
4
. M
A
P
E
a
nd t
r
e
nd a
c
c
ur
a
c
y
of
a
l
l
m
ode
l
s
a
c
r
os
s
f
i
v
e
s
c
e
na
r
i
os
(
t
r
a
i
n a
nd t
e
s
t
pe
r
f
or
m
a
nc
e
)
(
a
)
(
b)
F
i
g
ur
e
12
.
T
r
a
i
n
-
t
e
s
t
(
a
)
M
A
P
E
a
nd (
b)
t
r
e
nd a
c
c
ur
a
c
y
ba
s
e
d on t
r
a
i
n
-
t
e
s
t
da
t
a
s
e
t
of
t
he
m
e
t
a
-
s
t
a
c
ki
ng
m
ode
l
a
c
r
os
s
a
l
l
s
c
e
na
r
i
os
H
o
w
e
v
e
r
r
e
s
i
dua
l
e
r
r
or
s
s
t
i
l
l
oc
c
ur
dur
i
ng
unc
om
m
on
a
nd
m
a
j
or
hol
i
da
y
pe
r
i
ods
,
s
uc
h
a
s
C
hi
ne
s
e
N
e
w
Y
e
a
r
a
nd
E
i
d
a
l
-
F
i
t
r
.
N
e
v
e
r
t
he
l
e
s
s
,
t
he
m
ode
l
e
f
f
e
c
t
i
v
e
l
y
c
a
pt
ur
e
s
bot
h
s
hor
t
-
t
e
r
m
a
nd
l
ong
-
t
e
r
m
v
a
r
i
a
t
i
ons
i
n
e
l
e
c
t
r
i
c
i
t
y
l
oa
d
.
I
t
i
s
i
m
po
r
t
a
nt
t
o
not
e
t
ha
t
t
he
c
u
r
r
e
nt
m
e
t
a
-
l
e
a
r
ne
r
i
s
t
r
a
i
ne
d
onl
y
on
t
h
e
f
or
e
c
a
s
t
s
g
e
ne
r
a
t
e
d
b
y
t
he
ba
s
e
-
m
ode
l
s
,
w
i
t
hout
e
xpl
i
c
i
t
l
y
i
nc
or
por
a
t
i
ng
c
a
l
e
nda
r
-
r
e
l
a
t
e
d
f
e
a
t
ur
e
s
.
F
ut
ur
e
i
m
pr
o
v
e
m
e
nt
s
m
a
y
c
ons
i
de
r
i
nt
e
g
r
a
t
i
n
g
c
a
l
e
nda
r
f
a
c
t
or
s
i
nt
o
t
he
m
e
t
a
-
l
e
a
r
ne
r
t
o
be
t
t
e
r
c
a
pt
ur
e
de
m
a
nd
s
hi
f
t
s
dr
i
v
e
n b
y
hol
i
da
y
e
f
f
e
c
t
s
.
(
a
)
(
b)
F
i
g
ur
e
13
.
C
om
pa
r
i
s
on of
(
a
)
a
c
t
ua
l
v
s
.
f
or
e
c
a
s
t
e
d l
oa
d a
nd (
b)
r
e
s
i
dua
l
s
w
i
t
h hol
i
da
y
m
a
r
k
e
r
s
on t
he
2023
t
e
s
t
i
ng
da
t
a
4.
C
O
N
C
L
U
S
I
O
N
S
c
e
n
a
r
i
o
T
ype
C
N
N
-
B
i
L
S
T
M
C
N
N
-
B
i
G
R
U
W
i
n
do
w
e
d
-
X
G
B
oos
t
M
e
t
a
-
s
t
a
c
ki
ng
M
A
P
E
T
r
e
n
d
a
c
c
ur
a
c
y
M
A
P
E
T
r
e
n
d
a
c
c
ur
a
c
y
M
A
P
E
T
r
e
n
d
a
c
c
ur
a
c
y
M
A
P
E
T
r
e
n
d
a
c
c
ur
a
c
y
2006
T
r
a
i
n
1.
63%
84.
16
%
1.
81%
83.
18%
1.
26%
86.
74%
2.
01%
84.
55%
T
e
s
t
2.
10%
84.
33%
2.
23%
82.
33%
3.
45%
85.
33%
1.
89%
86.
00%
2009
T
r
a
i
n
1.
66%
83.
18%
1.
77%
85.
32%
1.
28%
86.
41%
2.
14%
84.
60%
T
e
s
t
2.
07%
81.
67%
2.
31%
83.
33%
3.
67%
85.
33%
2.
09%
86.
33%
2012
T
r
a
i
n
1.
52%
85.
10%
1.
67%
83.
89%
1.
17%
87.
73%
2.
28%
84.
00%
T
e
s
t
2.
15%
82.
00%
2.
42%
81.
00%
3.
91%
85.
00%
2.
31%
87.
00%
2015
T
r
a
i
n
1.
46%
85.
70%
2.
00%
83.
07%
1.
07%
88.
38%
2.
33%
84.
44%
T
e
s
t
2.
63%
75.
33%
2.
91%
79.
00%
3.
41%
81.
33%
2.
33%
82.
67%
2018
T
r
a
i
n
2.
80%
83.
36%
2.
09%
84.
11%
0.
86%
89.
18%
2.
64%
84.
52%
T
e
s
t
3.
21%
79.
67%
3.
33%
80.
00%
3.
51%
85.
67%
2.
72%
84.
33%
Evaluation Warning : The document was created with Spire.PDF for Python.