I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
12
,
No
.
1
,
Octo
b
er
201
8
,
p
p
.
1
6
1
~
1
6
7
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
1
2
.i
1
.
p
p
161
-
1
6
7
161
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
An Acc
ura
te
M
e
d
iu
m
-
Ter
m
Lo
a
d
Foreca
sting
bas
e
d on Hybri
d
Techniqu
e
Z
.
M
.
Ya
s
in
1
,
N.
F
.
A.
Aziz
2
,
N.
A.
Sa
li
m
3
,
N.
A.
Wa
ha
b
4
,
N.
A.
Ra
h
m
a
t
5
1
,
3,
4
F
a
c
u
l
ty
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
S
h
a
h
A
lam
,
M
a
la
y
sia
2
,5
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
P
o
w
e
r
En
g
in
e
e
rin
g
,
U
n
iv
e
rsiti
T
e
n
a
g
a
Na
sio
n
a
l,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
1
,
2
0
1
8
R
ev
i
s
ed
Ju
n
1
2
,
2
0
1
8
A
cc
ep
ted
Ju
l 2
5
,
2
0
1
8
A
n
a
c
c
u
ra
te
m
e
d
iu
m
ter
m
lo
a
d
f
o
re
c
a
stin
g
is
sig
n
i
f
ica
n
t
fo
r
p
o
w
e
r
g
e
n
e
ra
ti
o
n
sc
h
e
d
u
li
n
g
,
e
c
o
n
o
m
ic
a
n
d
re
li
a
b
le
o
p
e
ra
ti
o
n
i
n
p
o
w
e
r
s
y
st
e
m
.
M
o
st
o
f
c
las
sic
a
l
a
p
p
ro
a
c
h
f
o
r
m
e
d
iu
m
ter
m
lo
a
d
f
o
re
c
a
stin
g
o
n
ly
c
o
n
sid
e
r
to
tal
d
a
il
y
lo
a
d
d
e
m
a
n
d
.
T
h
is
a
p
p
r
o
a
c
h
m
a
y
n
o
t
p
r
o
v
id
e
a
c
c
u
r
a
te
re
su
lt
s
sin
c
e
th
e
lo
a
d
d
e
m
a
n
d
is
f
lu
c
tu
a
ted
in
a
d
a
y
.
In
th
is
p
a
p
e
r,
a
h
y
b
rid
A
n
t
-
L
io
n
Op
ti
m
ize
r
Lea
st
-
sq
u
a
re
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(A
LO
-
L
S
S
V
M
)
is
p
ro
p
o
se
d
to
f
o
re
c
a
st
2
4
-
h
o
u
r
l
o
a
d
d
e
m
a
n
d
f
o
r
th
e
n
e
x
t
y
e
a
r.
A
n
t
-
L
io
n
Op
ti
m
i
z
e
r
(AL
O)
is
u
ti
li
z
e
d
to
o
p
ti
m
ize
th
e
RBF
Ke
rn
e
l
p
a
ra
m
e
ter
s
in
L
e
a
st
-
S
q
u
a
re
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(L
S
-
S
VM).
T
h
e
o
b
jec
ti
v
e
o
f
th
e
o
p
ti
m
iz
a
ti
o
n
is
t
o
m
in
i
m
ize
th
e
M
e
a
n
A
b
so
lu
te
P
e
r
c
e
n
tag
e
Err
o
r
(M
A
P
E).
T
h
e
p
e
rfo
rm
a
n
c
e
o
f
AL
O
-
L
S
S
V
M
tec
h
n
i
q
u
e
w
a
s
c
o
m
p
a
re
d
w
it
h
th
o
se
o
b
tain
e
d
f
ro
m
L
S
-
S
V
M
tec
h
n
iq
u
e
th
ro
u
g
h
a
1
0
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
p
r
o
c
e
d
u
re
.
T
h
e
h
isto
ri
c
a
l
h
o
u
rly
lo
a
d
d
a
ta
a
re
a
n
a
ly
z
e
d
a
n
d
a
p
p
r
o
p
riate
f
e
a
tu
re
s
a
re
se
lec
ted
f
o
r
th
e
m
o
d
e
l.
T
h
e
re
a
r
e
2
4
in
p
u
ts
a
n
d
2
4
o
u
t
p
u
ts
v
e
c
to
rs
f
o
r
th
is
m
o
d
e
l
w
h
ich
re
p
re
se
n
t
s
24
-
h
o
u
r
lo
a
d
d
e
m
a
n
d
f
o
r
w
h
o
le
y
e
a
r.
T
h
e
re
su
lt
s
re
v
e
a
led
th
a
t
th
e
h
ig
h
a
c
c
u
ra
c
y
o
f
p
re
d
ictio
n
c
o
u
ld
b
e
a
c
h
iev
e
d
u
sin
g
A
L
O
-
L
S
S
V
M
.
K
ey
w
o
r
d
s
:
An
t
L
io
n
Op
ti
m
izer
L
ea
s
t
-
Sq
u
ar
e
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
i
n
e
Me
an
A
b
s
o
lu
te
P
er
ce
n
tag
e
E
r
r
o
r
Me
d
iu
m
-
T
er
m
L
o
ad
Fo
r
ec
asti
n
g
.
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Z
.
M.
Yasi
n
Fac
u
lt
y
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
Sh
a
h
A
la
m
,
Ma
la
y
s
ia
E
-
m
a
il:
zu
h
aila
m
y
7
4
@
g
m
a
il.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ic
lo
ad
f
o
r
ec
asti
n
g
is
i
m
p
o
r
tan
t in
p
lan
n
i
n
g
,
o
p
er
atio
n
an
d
r
eg
u
latio
n
o
f
elec
tr
ic
p
o
w
er
s
y
s
te
m
s
An
ac
cu
r
ate
lo
ad
f
o
r
ec
asti
n
g
w
il
l
lead
to
s
u
b
s
tan
t
ial
s
a
v
i
n
g
s
in
o
p
er
atin
g
a
n
d
m
ai
n
te
n
an
ce
co
s
ts
,
in
cr
ea
s
e
d
th
e
s
tab
il
it
y
,
r
eliab
il
it
y
a
n
d
s
ec
u
r
it
y
o
f
th
e
s
y
s
te
m
[
1
]
.
Un
d
er
esti
m
ate
t
h
e
lo
ad
d
e
m
an
d
m
a
y
ca
u
s
e
t
h
e
in
s
u
f
f
icien
t
o
f
p
o
w
er
s
u
p
p
l
y
t
o
th
e
co
n
s
u
m
er
s
.
Fu
r
t
h
er
m
o
r
e
,
it
m
a
y
r
es
u
lt
t
h
e
r
ed
u
ctio
n
o
f
p
o
w
er
q
u
alit
y
i
n
th
e
s
y
s
te
m
.
O
n
t
h
e
o
th
er
h
an
d
,
o
v
er
esti
m
atio
n
m
a
y
lead
t
h
e
p
r
o
v
id
er
to
m
ak
e
u
n
n
ec
e
s
s
ar
y
i
n
v
e
s
t
m
en
t
an
d
d
o
es
n
o
t
m
ee
t
th
e
o
p
ti
m
u
m
ec
o
n
o
m
ic
p
o
w
er
d
is
p
atc
h
.
E
lect
r
ic
lo
ad
f
o
r
ec
ast
ca
n
b
e
d
iv
id
e
d
in
to
3
t
y
p
es.
T
h
e
f
ir
s
t
t
y
p
e
is
lo
n
g
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
.
T
h
e
f
o
r
ec
ast
w
h
it
in
5
to
2
0
y
ea
r
s
is
cla
s
s
i
f
ied
as
lo
n
g
ter
m
lo
ad
f
o
r
ec
asti
n
g
[
2
]
.
T
h
is
t
y
p
e
o
f
f
o
r
ec
asti
n
g
a
ls
o
h
a
s
n
o
n
-
l
in
ea
r
co
r
r
elatio
n
w
it
h
o
th
er
f
ac
to
r
s
.
T
h
e
s
ec
o
n
d
t
y
p
e
is
m
ed
iu
m
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
.
Me
d
iu
m
-
ter
m
lo
ad
f
o
r
ec
as
tin
g
(
MT
L
F)
ca
n
b
e
co
n
s
id
e
r
ed
as
f
o
r
ec
ast
f
o
r
m
o
n
t
h
l
y
u
p
to
s
e
v
er
al
y
ea
r
[
3
]
.
Op
er
ato
r
s
ca
n
r
el
y
o
n
M
T
L
F
in
m
a
k
i
n
g
d
ec
is
io
n
s
f
o
r
u
n
it
co
m
m
it
m
en
t,
s
y
s
te
m
s
ec
u
r
it
y
a
n
al
y
s
i
s
,
d
is
p
atch
i
n
g
s
c
h
ed
u
le
an
d
lo
ad
f
lo
w
an
al
y
s
is
.
T
h
er
ef
o
r
e,
i
m
p
r
o
v
in
g
MT
L
F
ac
cu
r
ac
y
is
cr
u
cial
f
o
r
in
cr
ea
s
i
n
g
t
h
e
e
f
f
icien
c
y
o
f
s
y
s
te
m
s
a
n
d
r
ed
u
ci
n
g
t
h
e
co
s
t
s
[
4
]
.
T
h
e
th
ir
d
ty
p
e
is
s
h
o
r
t
-
ter
m
l
o
ad
f
o
r
ec
asti
n
g
(
ST
L
F).
ST
L
F
m
ai
n
l
y
co
v
er
s
th
e
p
er
io
d
o
f
o
n
e
w
ee
k
,
an
d
r
ef
er
s
to
th
e
as
s
ess
m
e
n
t
o
f
lo
ad
p
er
h
o
u
r
d
u
r
in
g
t
h
e
d
ay
[
5
]
.
T
h
is
t
y
p
e
o
f
p
r
ed
ictio
n
is
m
o
r
e
s
p
ec
if
ic
in
ti
m
e
as
it
co
n
s
id
er
s
h
o
u
r
l
y
p
r
ed
ictio
n
.
T
h
e
m
o
r
e
s
p
ec
if
ic
th
e
m
o
r
e
ac
cu
r
ate
th
e
p
r
ed
ictio
n
ca
n
b
e.
T
h
e
s
h
o
r
t
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
is
n
ee
d
ed
f
o
r
co
n
tr
o
l
an
d
s
c
h
ed
u
li
n
g
o
f
p
o
w
er
s
y
s
te
m
,
p
o
w
er
s
y
s
te
m
m
ai
n
te
n
an
ce
,
p
o
w
er
s
y
s
te
m
o
p
er
atio
n
a
n
d
co
n
tin
g
e
n
c
y
a
n
al
y
s
i
s
[6
-
7]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
1
,
Octo
b
er
2
0
1
8
:
1
6
1
–
167
162
C
o
n
v
en
t
io
n
al
m
eth
o
d
s
s
u
c
h
a
s
lin
ea
r
r
eg
r
es
s
io
n
m
et
h
o
d
s
[
8
]
,
tim
e
-
s
er
ies
m
o
d
elli
n
g
[
9
]
a
n
d
g
en
er
al
ex
p
o
n
en
t
ial
m
e
th
o
d
[
1
0
]
h
av
e
b
ee
n
u
tili
ze
d
f
o
r
lo
ad
f
o
r
e
ca
s
tin
g
.
T
h
ese
m
e
th
o
d
s
w
er
e
ab
le
to
p
r
e
d
ict
th
e
lin
ea
r
lo
ad
s
er
ies
an
d
u
n
ab
le
to
p
r
e
d
ict
n
o
n
-
li
n
ea
r
ch
ar
ac
ter
o
f
lo
ad
[
1
1
]
.
I
n
lin
e
w
it
h
th
e
r
ap
id
d
ev
elo
p
m
en
t
o
f
ar
tific
ial
i
n
tell
ig
e
n
ce
al
g
o
r
ith
m
s
,
esp
ec
iall
y
al
g
o
r
ith
m
s
w
it
h
s
tr
o
n
g
s
el
f
-
lear
n
i
n
g
s
u
c
h
a
s
s
i
m
u
lated
an
n
ea
l
in
g
al
g
o
r
ith
m
,
ar
ti
f
ic
ial
n
e
u
r
al
n
e
t
w
o
r
k
,
B
P
n
e
u
r
al
n
et
w
o
r
k
an
d
p
ar
ticle
s
w
ar
m
f
u
zz
y
i
n
f
er
en
ce
h
a
v
e
b
ee
n
w
id
el
y
u
s
ed
i
n
lo
ad
p
r
ed
ictio
n
s
.
Ho
w
e
v
er
,
all
th
ese
m
eth
o
d
s
h
a
v
e
t
h
eir
o
wn
ad
v
a
n
t
a
g
es
an
d
d
is
ad
v
an
ta
g
es.
R
ec
e
n
tl
y
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
w
h
ic
h
i
s
s
u
itab
le
f
o
r
s
o
lv
i
n
g
p
r
ac
tical
p
r
o
b
lem
s
s
u
c
h
a
s
lo
ad
f
o
r
ec
asti
n
g
[
1
2
]
.
An
i
m
p
r
o
v
ed
v
er
s
io
n
o
f
S
VM
,
L
ea
s
t
-
Sq
u
ar
e
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
L
S
-
SVM)
ap
p
lies
eq
u
alit
y
co
n
s
tr
ain
ts
i
n
s
tead
o
f
in
eq
u
alit
y
co
n
s
tr
ai
n
ts
to
s
i
m
p
lify
th
e
co
m
p
lex
ca
lcu
latio
n
an
d
i
m
p
r
o
v
e
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
I
n
th
is
p
ap
er
,
th
e
h
y
b
r
id
ized
o
f
L
S
-
SVM
an
d
A
n
t
-
L
io
n
Op
ti
m
izer
(
AL
O)
is
p
r
esen
ted
f
o
r
m
ed
iu
m
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
d
ata
is
o
b
tain
ed
f
r
o
m
P
J
M
w
eb
s
ite.
P
J
M
is
a
r
eg
io
n
al
tr
an
s
m
is
s
io
n
o
r
g
a
n
izatio
n
(
R
T
O)
th
at
co
o
r
d
in
ates
elec
tr
ical
tr
an
s
m
is
s
io
n
s
y
s
te
m
s
i
n
all
o
r
p
ar
ts
o
f
I
llin
o
is
,
Dela
w
ar
e,
I
n
d
ian
a,
K
en
tu
c
k
y
,
Ma
r
y
la
n
d
,
Mic
h
i
g
an
,
Ne
w
J
er
s
e
y
,
No
r
th
C
ar
o
li
n
a,
Oh
io
,
P
en
n
s
y
lv
a
n
ia,
T
en
n
es
s
ee
,
Vir
g
i
n
ia,
W
est
Vir
g
i
n
ia
a
n
d
th
e
Dis
tr
ict
o
f
C
o
l
u
m
b
ia.
I
n
o
r
d
er
to
v
er
i
f
y
th
e
e
f
f
ec
ti
v
e
n
ess
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
h
is
to
r
ical
lo
ad
d
ata
f
r
o
m
Du
k
e
is
s
elec
ted
.
T
h
e
h
o
u
r
l
y
d
ata
f
o
r
w
h
o
le
d
a
y
s
i
n
2
0
1
0
an
d
2
0
1
1
a
r
e
u
s
ed
as
an
in
p
u
t
a
n
d
o
u
tp
u
t
f
o
r
tr
ain
i
n
g
d
ata
an
d
test
in
g
d
ata
r
esp
ec
tiv
el
y
.
T
h
e
h
o
u
r
l
y
d
ata
in
th
e
f
ir
s
t
d
a
y
o
f
J
an
u
ar
y
is
s
et
to
b
e
in
p
u
t
w
h
il
e
th
e
s
ec
o
n
d
d
a
y
o
f
J
an
u
ar
y
w
i
l
l
b
e
th
e
o
u
tp
u
t.
T
h
e
h
o
u
r
l
y
d
ata
in
th
e
1
s
t
d
a
y
u
n
til
3
6
4
th
d
a
y
w
ill
ass
ig
n
ed
as
in
p
u
t
w
h
ile
t
h
e
h
o
u
r
l
y
d
ata
in
th
e
2
n
d
d
a
y
u
n
ti
l
3
6
5
th
d
a
y
w
il
l
b
e
th
e
o
u
tp
u
t.
T
h
e
d
ata
ca
n
b
e
d
o
w
n
lo
ad
ed
f
r
o
m
[
1
3
]
.
2
.
1
.
L
ea
s
t
-
Sq
ua
re
Su
pp
o
rt
Vec
t
o
r
M
a
chine (
L
S
-
SVM
)
T
h
e
ap
p
r
o
ac
h
o
f
L
S
-
SVM
i
s
a
r
ef
o
r
m
u
latio
n
o
f
t
h
e
p
r
in
cip
les
o
f
SVM,
w
h
ic
h
ap
p
lie
s
eq
u
ali
t
y
in
s
tead
o
f
i
n
eq
u
al
it
y
co
n
s
tr
ai
n
ts
[
1
4
]
.
T
h
e
o
p
tim
izatio
n
p
r
o
b
le
m
i
n
L
S
-
SVM
i
s
f
o
r
m
u
lated
as:
(
1
)
W
h
er
e
is
a
n
u
n
k
n
o
w
n
co
ef
f
i
cien
t
v
ec
to
r
,
is
a
r
eg
u
lar
izati
o
n
co
n
s
ta
n
t
a
n
d
e
i
s
as
s
u
m
ed
to
b
e
a
w
h
ite
n
o
is
e
p
r
o
ce
s
s
.
E
q
u
atio
n
(
1
)
is
s
u
b
j
ec
t to
:
(
2
)
W
h
er
e
x
i
is
m
ap
p
ed
in
to
a
h
ig
h
d
i
m
en
s
io
n
a
l
f
ea
t
u
r
e
s
p
ac
e
w
it
h
m
ap
p
in
g
φ.
T
h
e
p
r
o
b
le
m
ca
n
b
e
s
o
lv
ed
u
s
in
g
L
ag
r
a
n
g
e
m
u
ltip
l
ier
s
an
d
th
e
s
o
l
u
tio
n
is
p
r
esen
t
ed
in
f
o
r
m
:
(
3
)
W
h
er
e
K(
x
,
x
i)
r
ep
r
esen
ts
k
er
n
el,
d
ef
i
n
ed
as
t
h
e
d
o
t
p
r
o
d
u
c
t
b
et
w
ee
n
t
h
e
φ(
x
)
T
an
d
φ(
x
)
.
I
n
t
h
i
s
p
ap
er
,
R
ad
ial
B
asis
f
u
n
ctio
n
(
R
B
F)
is
u
s
ed
.
(
4
)
I
n
L
S
-
S
VM
w
it
h
R
B
F
k
er
n
el
f
u
n
ctio
n
,
t
h
e
s
elec
tio
n
o
f
p
ar
a
m
eter
s
b
et
w
ee
n
g
a
m
m
a
a
n
d
s
ig
m
a
i
s
ess
e
n
tial.
T
h
ese
p
ar
am
eter
s
n
ee
d
to
b
e
tu
n
i
n
g
to
m
i
n
i
m
ize
tr
ain
in
g
er
r
o
r
an
d
im
p
r
o
v
ed
th
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
T
h
is
p
ap
er
p
r
o
p
o
s
ed
1
0
-
f
o
ld
s
cr
o
s
s
v
alid
ati
o
n
tech
n
iq
u
e
f
o
r
th
e
p
ar
a
m
et
er
s
s
elec
tio
n
.
Me
a
n
ab
s
o
lu
te
p
er
ce
n
ta
g
e
er
r
o
r
(
MA
P
E
)
is
u
s
ed
to
q
u
a
n
ti
f
y
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
ed
ictio
n
.
T
h
e
lo
w
er
v
al
u
e
o
f
MA
P
E
in
d
icate
t
h
at
t
h
e
p
r
ed
ictio
n
is
g
o
o
d
.
T
h
e
f
o
r
m
u
la
o
f
MA
P
E
is
s
h
o
w
n
i
n
E
q
u
atio
n
5
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
cc
u
r
a
te
Med
iu
m
-
Ter
m
Lo
a
d
F
o
r
ec
a
s
tin
g
b
a
s
ed
o
n
Hyb
r
id
Tech
n
iq
u
e
(
Z.M.
Ya
s
in
)
163
∑
|
|
(
5
)
W
h
er
e
is
th
e
ac
t
u
al
v
al
u
e
a
n
d
is
th
e
f
o
r
ec
ast
v
al
u
e.
B
esid
es
M
A
P
E
,
th
e
e
v
alu
a
tio
n
o
f
th
e
e
s
ti
m
atio
n
is
d
eter
m
i
n
ed
b
y
t
h
e
co
r
r
elatio
n
o
f
d
ete
r
m
in
a
tio
n
,
R
2
as sh
o
w
n
i
n
E
q
.
(
6
)
.
∑
(
)
∑
(
)
(
6
)
W
h
er
e
is
th
e
av
er
a
g
e
v
a
lu
e
o
f
ac
tu
al
L
S
-
SVM.
2
.
2
.
Ant
L
io
n O
pti
m
izer
T
h
e
A
L
O
alg
o
r
it
h
m
i
m
itated
f
r
o
m
t
h
e
in
ter
ac
tio
n
b
et
w
ee
n
an
t
-
lio
n
s
an
d
an
t
s
in
t
h
e
tr
ap
[
1
5
]
.
T
h
is
alg
o
r
ith
m
asp
ir
ed
f
r
o
m
5
i
m
p
o
r
tan
t
s
tep
in
t
h
e
tr
u
e
n
at
u
r
e
o
f
th
e
a
n
t
-
lio
n
s
h
u
n
ti
n
g
b
eh
av
io
r
.
T
h
e
an
t
-
lio
n
b
u
ild
t
h
e
tr
ap
b
y
d
ig
g
i
n
g
t
h
e
s
an
d
.
Af
ter
t
h
at
t
h
e
a
n
t
i
s
r
a
n
d
o
m
l
y
w
alk
u
n
t
il
tr
ap
p
in
g
i
n
th
e
a
n
t
-
lio
n
's
p
it
s
.
T
h
is
w
i
ll
g
i
v
e
t
h
e
an
t
-
lio
n
t
h
e
ch
an
ce
to
ca
tc
h
th
e
a
n
t
b
u
t
u
s
u
all
y
th
e
p
r
e
y
w
ill
r
u
n
a
w
a
y
.
T
h
is
w
ill
lead
to
f
o
u
r
t
h
s
tep
w
h
ic
h
th
e
an
t
-
lio
n
w
ill
t
h
r
o
w
t
h
e
s
an
d
m
a
k
i
n
g
t
h
e
an
t
s
lid
i
n
g
to
w
ar
d
an
t
-
lio
n
.
A
t
th
e
f
in
al
s
tep
,
an
t
-
lio
n
ca
tc
h
t
h
e
p
r
ey
a
n
d
r
eb
u
ild
th
e
p
it.
R
a
n
d
o
m
w
al
k
s
o
f
an
ts
ar
e
r
ep
r
esen
ted
as E
q
u
ati
o
n
(
7
)
.
(
)
(
)
(
)
(
7
)
W
h
er
e
is
th
e
m
i
n
i
m
u
m
o
f
r
an
d
o
m
w
al
k
o
f
i
-
th
v
ar
iab
le,
is
th
e
m
a
x
i
m
u
m
o
f
r
an
d
o
m
w
al
k
in
i
-
t
h
v
ar
iab
le,
is
th
e
m
i
n
i
m
u
m
o
f
i
-
t
h
v
ar
iab
le
at
t
-
t
h
iter
atio
n
,
a
n
d
in
d
icate
s
t
h
e
m
a
x
i
m
u
m
o
f
i
-
t
h
v
ar
iab
le
a
t
t
-
t
h
iter
atio
n
.
T
h
e
n
e
w
eq
u
a
ti
o
n
s
ar
e
f
o
r
m
u
lated
b
ased
o
n
t
h
e
r
an
d
o
m
w
alk
s
o
f
p
r
e
y
th
at
ar
e
af
f
ec
ted
b
y
an
t
-
lio
n
'
s
tr
ap
s
.
(
8
)
(
9
)
W
h
er
e
is
th
e
m
in
i
m
u
m
o
f
all
v
ar
iab
les
at
t
-
t
h
iter
atio
n
,
in
d
icate
s
th
e
v
ec
to
r
in
cl
u
d
i
n
g
th
e
m
ax
i
m
u
m
o
f
all
v
ar
iab
les
at
t
-
t
h
iter
atio
n
,
is
th
e
m
i
n
i
m
u
m
o
f
all
v
ar
iab
les
f
o
r
i
-
t
h
a
n
t
,
is
th
e
m
a
x
i
m
u
m
o
f
all
v
ar
iab
les
f
o
r
i
-
t
h
an
t,
a
n
d
s
h
o
w
s
th
e
p
o
s
itio
n
o
f
t
h
e
s
e
lecte
d
j
-
th
an
tlio
n
at
t
-
th
i
ter
ati
o
n
.
T
h
e
m
at
h
e
m
a
ticall
y
m
o
d
elin
g
f
o
r
t
h
e
b
e
h
av
io
r
o
f
s
lid
in
g
a
n
ts
to
w
ar
d
a
n
t
-
lio
n
ar
e
f
o
r
m
u
la
ted
as
E
q
.
(
1
0
)
an
d
E
q
.
(
1
1
)
.
T
h
e
f
o
r
m
u
latio
n
s
ar
e
b
ased
o
n
t
h
e
r
ad
iu
s
o
f
a
n
ts
’
r
a
n
d
o
m
w
alk
s
t
h
at
i
s
d
ec
r
ea
s
ed
ev
en
t
u
all
y
.
(
1
0
)
(
1
1
)
A
t t
h
e
f
in
a
l step
,
an
t
-
lio
n
ca
tch
th
e
p
r
e
y
a
n
d
r
eb
u
ild
th
e
p
it.
T
h
e
s
tep
is
f
o
r
m
u
lated
as:
(
)
(
)
(
1
2
)
E
liti
s
m
i
s
a
cr
u
c
ial
c
h
ar
ac
ter
is
tic
o
f
ev
o
l
u
tio
n
ar
y
al
g
o
r
ith
m
s
th
a
t
allo
w
s
th
e
m
to
m
ai
n
tai
n
t
h
e
b
es
t
s
o
lu
tio
n
(
s
)
o
b
tain
ed
at
an
y
l
ev
el
o
f
o
p
ti
m
izatio
n
p
r
o
ce
s
s
.
T
h
e
b
est
an
t
-
l
io
n
o
b
tain
ed
is
s
av
ed
in
e
v
er
y
iter
atio
n
an
d
co
n
s
id
er
ed
as
el
ite.
T
h
e
elite
ar
e
th
e
f
ittes
t
an
t
-
lio
n
a
n
d
s
h
o
u
ld
b
e
ab
le
to
af
f
ec
t
t
h
e
r
an
d
o
m
w
al
k
s
o
f
all
th
e
an
ts
in
iter
atio
n
p
r
o
ce
s
s
.
T
h
u
s
,
i
t
i
s
a
s
s
u
m
ed
th
at
e
v
er
y
a
n
t
r
an
d
o
m
l
y
w
al
k
s
ar
o
u
n
d
a
s
elec
ted
an
t
-
lio
n
b
y
t
h
e
r
o
u
lette
w
h
ee
l
an
d
th
e
elite
s
i
m
u
lta
n
eo
u
s
l
y
as
f
o
llo
w
s
:
(
1
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
1
,
Octo
b
er
2
0
1
8
:
1
6
1
–
167
164
W
h
er
e
is
th
e
r
a
n
d
o
m
w
al
k
ar
o
u
n
d
th
e
a
n
tl
io
n
s
elec
ted
b
y
t
h
e
r
o
u
lette
w
h
ee
l
at
t
-
t
h
iter
at
io
n
,
is
th
e
r
an
d
o
m
w
alk
ar
o
u
n
d
th
e
elite
at
t
-
t
h
iter
atio
n
,
a
n
d
is
t
h
e
p
o
s
itio
n
o
f
i
-
t
h
t
-
th
i
ter
atio
n
.
R
ef
er
e
n
ce
[
1
5
]
p
r
o
v
ed
th
at
th
e
p
r
o
p
o
s
ed
A
L
O
alg
o
r
it
h
m
s
h
o
w
s
h
ig
h
ex
p
lo
r
atio
n
an
d
ex
p
l
o
itatio
n
i
n
s
o
lv
i
n
g
m
at
h
e
m
atica
l
f
u
n
ctio
n
s
.
T
h
e
p
r
o
p
o
s
ed
r
an
d
o
m
w
a
lk
m
ec
h
a
n
i
s
m
an
d
r
an
d
o
m
s
e
lectio
n
o
f
a
n
t
-
lio
n
s
s
ti
m
u
la
te
ex
p
lo
r
atio
n
w
h
ic
h
f
ac
ilit
ate
t
h
e
AL
O
al
g
o
r
ith
m
t
o
ac
h
iev
e
g
lo
b
al
o
p
ti
m
a
a
n
d
s
o
lv
e
lo
ca
l
o
p
ti
m
a
s
tag
n
atio
n
w
h
e
n
s
o
l
v
i
n
g
co
m
p
lex
it
y
p
r
o
b
le
m
s
.
Mo
r
eo
v
er
,
ad
ap
tiv
e
s
h
r
in
k
i
n
g
b
o
u
n
d
ar
ies
o
f
a
n
t
-
lio
n
s
’
tr
ap
s
an
d
eliti
s
m
e
m
p
h
as
ize
e
x
p
lo
itatio
n
a
s
iter
atio
n
i
n
cr
ea
s
es,
w
h
ic
h
lead
s
to
an
ac
cu
r
ate
a
p
p
r
o
x
im
a
tio
n
o
f
t
h
e
g
lo
b
al
o
p
ti
m
u
m
.
A
ll
t
h
ese
c
h
ar
ac
ter
is
tic
s
r
eq
u
ir
e
th
e
AL
O
alg
o
r
it
h
m
to
s
o
lv
e
r
ea
l
o
p
ti
m
izat
io
n
p
r
o
b
le
m
s
p
o
ten
tiall
y
a
n
d
av
o
id
lo
ca
l
o
p
ti
m
a.
T
h
er
ef
o
r
e,
th
is
p
ap
er
p
r
esen
ts
t
h
e
ap
p
licatio
n
o
f
AL
O
f
o
r
s
o
lv
in
g
lo
ad
f
o
r
ec
asti
n
g
p
r
o
b
le
m
s
.
2
.
3
.
Dev
elo
p
m
e
nt
o
f
H
y
br
id L
S
-
SVM
I
n
t
h
is
p
ap
er
,
a
h
y
b
r
id
An
t
-
L
i
o
n
Op
ti
m
izer
L
ea
s
t
-
s
q
u
ar
e
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
AL
O
-
L
S
SVM)
i
s
p
r
o
p
o
s
ed
to
f
o
r
ec
ast
2
4
-
h
o
u
r
lo
ad
d
em
a
n
d
.
A
s
m
en
t
io
n
ed
ea
r
lier
,
in
L
S
-
SVM
(
w
it
h
th
e
R
B
F
k
er
n
el)
,
t
w
o
p
ar
am
eter
s
n
ee
d
to
b
e
tu
n
i
n
g
w
h
ic
h
ar
e
g
a
m
m
a
(
γ
)
an
d
s
ig
m
a
(
σ
2
)
.
Sig
m
a
is
th
e
k
er
n
el
f
u
n
ctio
n
p
ar
am
e
ter
(
s
q
u
ar
ed
b
an
d
w
id
t
h
)
w
h
ile
g
a
m
m
a
is
th
e
r
e
g
u
lar
izatio
n
p
ar
a
m
eter
f
o
r
d
eter
m
in
i
n
g
t
h
e
tr
a
d
e
-
o
f
f
b
et
w
ee
n
th
e
tr
ain
i
n
g
er
r
o
r
m
i
n
i
m
izat
io
n
an
d
s
m
o
o
th
n
e
s
s
o
f
t
h
e
esti
m
ated
f
u
n
ctio
n
.
I
f
t
h
e
v
al
u
e
o
f
s
i
g
m
a
is
to
o
b
ig
,
it
w
i
ll
lead
to
u
n
d
er
f
itti
n
g
p
h
en
o
m
e
n
o
n
to
s
a
m
p
le
d
ata.
On
th
e
co
n
tr
ar
y
,
if
th
e
v
a
lu
e
o
f
s
i
g
m
a
is
to
o
s
m
a
ll,
it
w
il
l
lead
to
o
v
er
f
itt
in
g
p
h
e
n
o
m
en
o
n
to
s
a
m
p
le
d
ata
[
1
6
]
.
I
n
AL
O
-
L
SS
VM
,
AL
O
i
s
u
s
ed
to
en
h
a
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
L
S
-
SVM
b
y
o
p
ti
m
izi
n
g
t
h
e
v
al
u
es
o
f
g
a
m
m
a
an
d
s
i
g
m
a.
T
h
e
o
b
j
ec
tiv
e
o
f
th
e
o
p
ti
m
iza
tio
n
i
s
to
m
in
i
m
ize
th
e
v
al
u
e
o
f
Me
a
n
A
b
s
o
lu
te
P
er
ce
n
tag
e
E
r
r
o
r
(
MA
P
E
)
.
T
h
e
o
v
er
all
f
lo
w
c
h
ar
t
o
f
AL
O
-
L
SS
V
M
is
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Firstl
y
,
t
h
e
a
n
t
-
lio
n
a
n
d
an
t
m
atr
ices
ar
e
i
n
itia
lized
r
an
d
o
m
l
y
.
I
n
e
v
er
y
iter
atio
n
,
th
e
p
o
s
iti
o
n
o
f
ea
ch
an
t
w
i
th
r
esp
ec
t
to
a
n
an
t
-
l
io
n
ar
e
u
p
d
ated
.
T
h
en
,
th
e
b
est
f
i
tn
es
s
ar
e
s
e
lecte
d
b
y
t
h
e
r
o
u
lette
w
h
ee
l
o
p
er
ato
r
an
d
th
e
elite.
T
h
e
b
o
u
n
d
ar
y
o
f
p
o
s
itio
n
u
p
d
atin
g
i
s
d
ef
i
n
ed
as
p
r
o
p
o
r
tio
n
al
to
th
e
cu
r
r
en
t
n
u
m
b
er
o
f
iter
at
io
n
.
T
h
e
u
p
d
atin
g
p
o
s
i
tio
n
i
s
t
h
e
n
ac
co
m
p
li
s
h
ed
b
y
t
w
o
r
an
d
o
m
w
al
k
s
ar
o
u
n
d
t
h
e
s
elec
te
d
an
t
-
lio
n
a
n
d
elite.
W
h
en
all
t
h
e
an
ts
r
an
d
o
m
l
y
walk
,
th
e
y
ar
e
ev
al
u
ated
b
y
t
h
e
f
it
n
es
s
f
u
n
ctio
n
.
I
f
a
n
y
o
f
t
h
e
an
ts
b
ec
o
m
e
f
itter
th
an
a
n
y
o
th
er
a
n
t
-
lio
n
s
,
th
ei
r
p
o
s
i
tio
n
s
ar
e
co
n
s
id
er
ed
as
th
e
n
e
w
p
o
s
itio
n
s
f
o
r
t
h
e
a
n
t
-
lio
n
s
i
n
th
e
n
e
x
t
iter
atio
n
.
T
h
e
b
est
an
t
-
lio
n
is
co
m
p
ar
ed
to
th
e
b
est
a
n
t
-
lio
n
f
o
u
n
d
d
u
r
i
n
g
o
p
ti
m
izatio
n
(
eli
te)
an
d
s
u
b
s
tit
u
ted
if
it
i
s
n
ec
e
s
s
ar
y
.
T
h
ese
s
tep
s
ar
e
r
ep
ea
ted
u
n
til
th
e
ter
m
i
n
at
io
n
cr
ite
r
io
n
is
m
et.
T
h
e
ter
m
in
atio
n
cr
iter
io
n
is
s
et
b
ased
o
n
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
f
i
tn
e
s
s
w
h
ich
i
s
less
t
h
an
1
0
-
7
.
T
h
e
m
ax
i
m
u
m
iter
atio
n
is
s
e
t to
3
0
0
an
d
th
e
n
u
m
b
er
o
f
th
e
s
ea
r
ch
a
g
en
t i
s
s
et
to
2
0
.
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
AL
O
-
L
SS
VM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
cc
u
r
a
te
Med
iu
m
-
Ter
m
Lo
a
d
F
o
r
ec
a
s
tin
g
b
a
s
ed
o
n
Hyb
r
id
Tech
n
iq
u
e
(
Z.M.
Ya
s
in
)
165
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
LS
-
S
VM
w
it
h
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
tec
h
n
iq
u
e
is
u
s
ed
to
f
i
n
d
th
e
v
al
u
e
o
f
g
a
m
m
a
(
γ
)
an
d
s
i
g
m
a
(
2
)
in
th
is
p
ap
er
.
T
h
e
ac
cu
r
ac
y
o
f
p
r
ed
ictio
n
is
d
eter
m
i
n
ed
b
y
ca
lc
u
lati
n
g
Me
a
n
A
b
s
o
l
u
te
P
er
ce
n
tag
e
E
r
r
o
r
(
MA
P
E
)
an
d
co
r
r
elatio
n
o
f
d
eter
m
in
at
io
n
(
R
2
)
.
L
S
-
SV
M
is
s
i
m
u
lated
ten
ti
m
e
s
to
d
eter
m
i
n
e
t
h
e
b
est
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
b
est,
av
er
a
g
e
an
d
w
o
r
s
t
r
es
u
lt
s
in
ter
m
o
f
M
A
P
E
v
a
lu
e
ar
e
ta
b
u
lated
in
T
ab
le
1
.
T
h
e
r
esu
lt
s
r
e
v
ea
led
t
h
at
t
h
e
b
est
v
al
u
e
f
o
r
g
a
m
m
a
an
d
s
ig
m
a
ar
e
1
3
2
.
3
3
4
4
an
d
4
4
.
3
0
2
0
w
h
ic
h
p
r
o
d
u
ce
MA
P
E
o
f
4
.
3
7
9
6
%.
T
h
e
lo
w
er
th
e
M
A
P
E
is
b
etter
,
w
h
ile
th
e
R
2
s
h
o
u
ld
ap
p
r
o
ac
h
to
1
w
h
ic
h
in
d
icate
s
t
h
e
g
o
o
d
r
eg
r
ess
io
n
li
n
e.
T
ab
le
1
.
MA
P
E
an
d
R
2
o
b
tain
ed
f
r
o
m
L
S
-
SVM
C
r
o
ss v
a
l
i
d
a
t
i
o
n
t
e
c
h
n
i
q
u
e
B
e
st
A
v
e
r
a
g
e
w
o
r
st
M
A
P
E
(
%)
4
.
3
7
9
6
4
.
5
4
5
3
4
.
7
0
9
6
R2
0
.
8
8
7
3
0
.
8
7
5
6
0
.
8
7
0
3
I
n
o
r
d
er
to
o
p
tim
ize
th
e
v
al
u
e
o
f
R
B
F
p
ar
a
m
eter
s
,
a
n
e
w
al
g
o
r
ith
m
n
a
m
el
y
AL
O
-
L
SS
VM
i
s
p
r
o
p
o
s
ed
as
d
escr
ib
ed
in
s
ec
ti
o
n
4
.
I
n
A
L
O
-
L
SS
VM
,
t
h
e
K
er
n
el
p
ar
a
m
eter
s
w
er
e
o
p
ti
m
iz
ed
u
s
i
n
g
AL
O.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
tr
ai
n
i
n
g
d
ata
u
s
in
g
AL
O
-
L
SS
VM
is
ill
u
s
t
r
ated
in
F
ig
u
r
e
2
.
Fro
m
t
h
e
r
esu
lt
s
o
b
tain
ed
i
n
Fig
u
r
e
2
,
th
e
o
p
tim
u
m
v
al
u
e
f
o
r
g
a
m
m
a
(
γ
)
is
3
4
0
.
2
4
4
2
w
h
ile
f
o
r
s
ig
m
a
(
σ
2
)
is
3
2
1
.
1
0
7
6
.
T
h
ese
v
alu
e
s
p
r
o
d
u
ce
4
.
3
5
6
% o
f
MA
P
E
.
Fig
u
r
e
2
.
T
r
ain
in
g
d
ata
p
r
o
d
u
ce
d
b
y
AL
O
-
L
SS
V
M
T
ab
le
2
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
o
f
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
b
et
w
ee
n
L
S
-
SVM
w
it
h
cr
o
s
s
v
alid
atio
n
tech
n
iq
u
e
a
n
d
AL
O
-
L
SS
V
M
i
n
ter
m
s
o
f
M
A
P
E
an
d
R
2
.
Fro
m
t
h
e
r
es
u
lt
s
tab
u
la
ted
in
T
ab
le
2
,
it
ca
n
b
e
s
ee
n
th
at
AL
O
-
L
SS
VM
p
r
o
d
u
ce
d
b
etter
p
er
f
o
r
m
a
n
ce
i
n
ter
m
s
o
f
MA
P
E
v
al
u
e
an
d
R
2
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
M
A
P
E
an
d
R
2
T
e
c
h
n
i
q
u
e
G
a
mm
a
(
γ
)
S
i
g
ma
(
σ2
)
M
A
P
E
(
%)
R2
LS
-
S
V
M
1
3
2
.
3
3
4
4
4
4
.
3
0
2
0
3
4
.
3
80
6
0
.
8
8
7
3
A
L
O
-
L
S
S
V
M
3
4
0
.
2
4
4
2
3
2
1
.
1
0
7
6
4
.
3
5
6
0
0
.
8
9
0
8
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
AL
O
-
L
S
SVM
f
o
r
m
ed
iu
m
ter
m
lo
ad
f
o
r
ec
asti
n
g
i
s
m
ea
s
u
r
ed
th
r
o
u
g
h
te
s
ti
n
g
p
r
o
ce
s
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
T
h
e
f
ig
u
r
e
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
p
r
ed
icted
an
d
ac
tu
al
d
ata
f
o
r
o
n
e
y
ea
r
test
i
n
g
d
ata.
Fro
m
th
e
r
e
s
u
lts
p
r
ese
n
ted
in
Fi
g
u
r
e
3
,
it
c
an
b
e
o
b
s
er
v
ed
th
at
t
h
e
p
r
ed
icted
an
d
ac
tu
al
d
ata
ar
e
q
u
ite
s
i
m
ilar
.
Fo
r
clea
r
o
b
s
er
v
atio
n
o
n
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
AL
O
-
L
SS
VM
,
g
r
ap
h
o
f
test
i
n
g
d
ata
f
o
r
a
m
o
n
t
h
(
J
an
u
ar
y
2
0
1
1
)
an
d
w
ee
k
(
f
ir
s
t
w
ee
k
o
f
J
an
u
ar
y
2
0
1
1
)
ar
e
p
lo
tted
in
Fig
u
r
e
4
an
d
Fig
u
r
e
5
r
esp
ec
tiv
el
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
12
,
No
.
1
,
Octo
b
er
2
0
1
8
:
1
6
1
–
167
166
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
p
r
ed
icted
an
d
ac
tu
al
d
ata
in
a
y
ea
r
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
p
r
ed
icted
an
d
ac
tu
al
d
ata
in
J
an
u
ar
y
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
p
r
ed
icted
an
d
ac
tu
al
d
ata
in
t
h
e
f
ir
s
t
w
ee
k
o
f
J
an
u
ar
y
I
t
ca
n
b
e
s
ee
n
f
r
o
m
Fi
g
u
r
e
3
t
h
at
t
h
e
elec
tr
ical
u
s
a
g
e
i
s
h
i
g
h
est
i
n
s
u
m
m
er
s
ea
s
o
n
w
h
ile
th
e
lo
w
es
t
u
s
a
g
e
i
n
Feb
r
u
ar
y
to
Ma
r
c
h
w
h
ic
h
ar
e
s
p
r
in
g
s
ea
s
o
n
.
T
h
e
h
ig
h
e
s
t
elec
tr
ical
u
s
a
g
e
in
s
u
m
m
er
is
d
u
e
t
o
in
cr
ea
s
i
n
g
th
e
u
s
a
g
e
o
f
air
-
c
o
n
d
itio
n
er
an
d
also
i
n
cr
ea
s
i
n
g
th
e
h
u
m
a
n
ac
ti
v
itie
s
s
i
n
ce
it
is
a
h
o
lid
a
y
.
T
h
e
m
aj
o
r
m
ai
n
te
n
an
ce
w
o
r
k
i
s
b
est to
b
e
d
o
n
e
in
Feb
r
u
ar
y
to
M
ar
ch
.
B
y
r
e
f
er
r
in
g
to
Fig
u
r
e
5
,
th
e
f
ir
s
t
d
a
y
is
Sa
tu
r
d
a
y
a
n
d
co
n
ti
n
u
e
s
u
n
til
Frid
a
y
.
Star
ti
n
g
f
r
o
m
Frid
a
y
's
n
ig
h
t,
t
h
e
elec
tr
icit
y
co
n
s
u
m
ed
is
in
cr
ea
s
e
u
n
til
Sa
tu
r
d
a
y
.
T
h
is
is
d
u
e
to
m
o
r
e
ac
tiv
iti
es
in
w
ee
k
en
d
an
d
p
eo
p
les
s
tar
t
to
h
av
e
a
g
r
ea
t
ti
m
e
a
f
ter
w
o
r
k
i
n
g
.
B
ased
o
n
t
h
e
g
r
ap
h
,
t
h
e
p
o
w
er
p
r
o
v
id
er
s
h
o
u
ld
in
cr
ea
s
e
t
h
e
g
en
er
atio
n
in
w
ee
k
en
d
co
m
p
a
r
ed
to
w
ee
k
d
a
y
s
.
T
h
is
an
al
y
s
i
s
w
i
ll
h
elp
th
e
elec
tr
ici
t
y
p
r
o
v
id
er
to
d
eter
m
i
n
e
o
p
tim
a
l
u
n
it
co
m
m
it
m
e
n
t
an
d
p
lan
th
e
s
c
h
ed
u
le.
Fro
m
all
th
e
s
ce
n
ar
io
s
h
a
v
e
b
ee
n
d
is
cu
s
s
ed
ab
o
v
e,
Me
d
iu
m
-
ter
m
L
o
ad
Fo
r
ec
asti
n
g
i
s
ess
en
tial
to
p
o
w
er
S
u
p
p
l
y
C
o
m
p
an
y
to
d
eter
m
i
n
e
th
e
elec
tr
i
cit
y
co
n
s
u
m
p
tio
n
i
n
s
p
ec
if
ic
t
i
m
e.
Fro
m
t
h
e
f
o
r
ec
asti
n
g
,
t
h
e
co
m
p
a
n
y
m
ig
h
t
n
o
t
o
v
er
g
e
n
er
ate
th
u
s
w
ill
cu
t
-
o
f
f
th
e
o
p
er
atin
g
co
s
t
.
B
esid
es,
th
e
elec
tr
icit
y
co
llap
s
e
o
r
tr
ip
ca
n
b
e
av
o
id
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
cc
u
r
a
te
Med
iu
m
-
Ter
m
Lo
a
d
F
o
r
ec
a
s
tin
g
b
a
s
ed
o
n
Hyb
r
id
Tech
n
iq
u
e
(
Z.M.
Ya
s
in
)
167
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
h
ad
p
r
esen
ted
a
m
e
d
iu
m
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
b
y
u
s
i
n
g
AL
O
-
L
SS
VM
to
p
r
ed
ic
t
th
e
lo
ad
d
em
a
n
d
f
o
r
ev
er
y
h
o
u
r
in
a
y
e
ar
.
I
t
is
b
ec
o
m
e
a
r
esp
o
n
s
ib
ilit
y
to
p
o
w
er
in
d
u
s
tr
y
i
n
m
a
k
i
n
g
p
r
ec
is
e
p
r
ed
ictio
n
in
o
r
d
er
to
k
ee
p
a
h
ea
lth
y
p
o
w
er
s
u
p
p
l
y
a
n
d
co
m
p
etit
io
n
b
et
w
ee
n
t
h
e
co
m
p
a
n
ie
s
i
n
ter
m
s
o
f
ec
o
n
o
m
y
.
I
n
p
o
w
er
p
lan
n
i
n
g
,
it
is
i
m
p
o
r
tan
t
n
o
t
to
m
ak
e
o
v
er
esti
m
atio
n
i
n
o
r
d
er
to
av
o
id
o
v
er
s
p
en
t.
T
h
e
d
eter
m
i
n
atio
n
o
f
tar
if
f
also
ta
k
es
t
h
e
lo
ad
f
o
r
ec
asti
n
g
a
s
th
e
in
p
u
t
to
an
al
y
ze
.
T
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
t
h
in
g
to
t
ak
e
i
n
to
ac
co
u
n
t
is
th
e
s
tab
ilizatio
n
o
f
t
h
e
elec
tr
ical
d
is
tr
ib
u
tio
n
esp
ec
iall
y
at
th
e
r
ec
ei
v
i
n
g
e
n
d
s
.
I
n
o
r
d
er
to
av
o
id
elec
tr
ical
co
llap
s
e
at
a
p
ar
ticu
lar
ar
ea
,
m
ed
iu
m
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
is
n
ee
d
ed
to
g
i
v
e
t
h
e
p
r
ec
is
e
p
r
ed
ictio
n
s
in
ce
lo
ad
d
em
a
n
d
v
ar
ie
s
f
r
o
m
ac
co
r
d
in
g
to
ti
m
e.
T
h
e
r
esu
lt
s
s
h
o
w
ed
th
at
th
e
ac
c
u
r
ate
p
r
ed
ictio
n
b
ased
o
n
h
o
u
r
l
y
lo
ad
de
m
a
n
d
co
u
ld
b
e
ac
h
iev
ed
u
s
i
n
g
AL
O
-
L
S
SVM
alg
o
r
it
h
m
.
I
n
f
u
t
u
r
e,
it
is
s
u
g
g
e
s
ted
th
at
AL
O
-
L
SS
VM
is
also
u
tili
ze
d
f
o
r
lo
n
g
-
ter
m
lo
ad
f
o
r
ec
asti
n
g
to
v
er
i
f
y
th
e
r
o
b
u
s
t
n
e
s
s
an
d
t
h
e
n
o
n
li
n
ea
r
it
y
o
f
t
h
i
s
h
y
b
r
id
tech
n
iq
u
e.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
lik
e
to
t
h
an
k
t
h
e
U
n
i
v
er
s
iti
T
en
a
g
a
Nasio
n
al
a
n
d
t
h
e
Mi
n
is
tr
y
o
f
Hi
g
h
er
E
d
u
ca
tio
n
(
MO
HE
)
,
Ma
la
y
s
i
a
th
r
o
u
g
h
r
esear
c
h
g
r
an
t
2
0
1
6
0
1
0
4
FR
GS
f
o
r
th
e
f
in
a
n
ci
al
s
u
p
p
o
r
t
to
th
i
s
r
esear
ch
.
RE
F
E
R
E
NC
E
S
[1
]
A
l
m
e
sh
a
iei
E,
S
o
l
tan
H.
“
A
m
e
t
h
o
d
o
l
o
g
y
f
o
r
El
e
c
tri
c
P
o
w
e
r
L
o
a
d
F
o
re
c
a
stin
g
”
.
Al
e
x
a
n
d
ri
a
E
n
g
i
n
e
e
rin
g
J
o
u
rn
a
l
.
2
0
1
1
:
5
0
(
2
);
1
3
7
–
1
4
4
.
[2
]
Ho
n
g
T
,
F
a
n
S
.
“
P
ro
b
a
b
il
ist
ic
e
lec
tri
c
lo
a
d
f
o
re
c
a
stin
g
:
A
tu
to
rial
re
v
ie
w
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Fo
re
c
a
stin
g
.
2
0
1
6
:
3
2
(
3
);
9
1
4
–
9
3
8
.
[3
]
X
ia
C,
W
a
n
g
J,
M
c
M
e
n
e
m
y
K.
”
S
h
o
rt,
m
e
d
iu
m
a
n
d
lo
n
g
ter
m
lo
a
d
f
o
re
c
a
stin
g
m
o
d
e
l
a
n
d
v
irt
u
a
l
lo
a
d
f
o
re
c
a
ste
r
b
a
se
d
o
n
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
s
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
Po
we
r
a
n
d
En
e
rg
y
S
y
ste
ms
.
2
0
1
0
:
3
2
(
7
);
7
4
3
–
7
5
0
.
[4
]
L
a
o
u
a
f
i
A
,
M
o
rd
jao
u
i
M
,
L
a
o
u
a
f
i
F
.
“
A
n
e
v
a
lu
a
ti
o
n
o
f
c
o
n
v
e
n
ti
o
n
a
l
a
n
d
c
o
m
p
u
tatio
n
a
l
i
n
telli
g
e
n
c
e
m
e
th
o
d
s
f
o
r
m
e
d
iu
m
a
n
d
lo
n
g
-
term
lo
a
d
f
o
re
c
a
stin
g
in
A
lg
e
ria
”
.
3
rd
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
n
tro
l,
En
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
.
Al
g
e
ria
.
2
0
1
5
.
1
-
6
.
[5
]
S
a
n
ti
k
a
G
.
D,
M
a
h
m
u
d
y
W
.
F
,
Na
b
a
A
.
“
Ru
le o
p
ti
m
iza
ti
o
n
o
f
f
u
z
z
y
in
f
e
re
n
c
e
s
y
ste
m
su
g
e
n
o
u
sin
g
e
v
o
lu
ti
o
n
stra
teg
y
f
o
r
e
lec
tri
c
it
y
c
o
n
su
m
p
ti
o
n
f
o
re
c
a
stin
g
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
.
2
0
1
7
:
7
(4
)
;
2
2
4
1
–
2
2
5
2
.
[6
]
Zi
z
i
Zh
a
n
g
,
Ho
n
g
L
i,
Ya
n
g
Z
h
a
o
,
Xia
o
b
o
H
u
.
“
S
h
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
b
a
se
d
o
n
th
e
g
ri
d
m
e
th
o
d
a
n
d
th
e
t
im
e
se
ries
f
u
z
z
y
lo
a
d
f
o
re
c
a
stin
g
m
e
t
h
o
d
”
.
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ren
e
wa
b
le
Po
we
r
Ge
n
e
ra
ti
o
n
.
Be
ij
in
g
.
2
0
1
5
.
1
-
6
.
[7
]
Bu
n
n
o
o
n
P
.
“
El
e
c
tri
c
it
y
P
e
a
k
L
o
a
d
De
m
a
n
d
u
sin
g
De
-
n
o
isin
g
W
a
v
e
let
T
ra
n
s
f
o
r
m
in
teg
ra
ted
w
it
h
Ne
u
ra
l
Ne
t
w
o
rk
M
e
th
o
d
s
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
:
2
0
1
6
:
6
(
1
);
1
2
-
2
0
.
[8
]
Qiu
X
,
Z
h
a
n
g
L
,
Re
n
Y,
S
u
g
a
n
th
a
n
P
,
Am
a
ra
tu
n
g
a
G
.
“
En
se
m
b
le
d
e
e
p
lea
rn
in
g
f
o
r
re
g
re
ss
io
n
a
n
d
ti
m
e
se
ries
f
o
re
c
a
stin
g
”
.
IEE
E
S
y
mp
o
siu
m
S
e
rie
s o
n
Co
m
p
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
(
CIEL
2
0
1
4
)
.
2
0
1
4
.
F
l
o
rid
a
.
1
-
6.
[9
]
Ch
a
o
u
c
h
M
.
“
Clu
ste
rin
g
-
b
a
se
d
i
m
p
ro
v
e
m
e
n
t
o
f
n
o
n
p
a
ra
m
e
tri
c
fu
n
c
ti
o
n
a
l
t
im
e
se
ries
f
o
re
c
a
stin
g
:
A
p
p
li
c
a
ti
o
n
to
in
tra
-
d
a
y
h
o
u
se
h
o
ld
-
lev
e
l
lo
a
d
c
u
rv
e
s
”
.
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
m
a
rt Grid
.
2
0
1
4
:
5
(1
)
;
4
1
1
–
4
1
9
.
[1
0
]
T
a
y
lo
r
J.
W
.
“
S
h
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
w
it
h
e
x
p
o
n
e
n
ti
a
ll
y
w
e
i
g
h
ted
m
e
th
o
d
s
”
.
IEE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
P
o
we
r
S
y
ste
ms
.
2
0
1
2
:
2
7
(
1
);
4
5
8
–
4
6
4
.
[1
1
]
Zen
g
M
,
X
u
e
S
,
W
a
n
g
Z,
Z
h
u
X
,
Zh
a
n
g
G
.
“
S
h
o
rt
-
term
lo
a
d
f
o
re
c
a
stin
g
o
f
s
m
a
rt
g
rid
s
y
ste
m
s
b
y
c
o
m
b
in
a
ti
o
n
o
f
g
e
n
e
ra
l
re
g
re
ss
io
n
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
lea
st
sq
u
a
re
s
-
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
a
lg
o
rit
h
m
o
p
ti
m
iz
e
d
b
y
h
a
rm
o
n
y
se
a
rc
h
a
lg
o
rit
h
m
m
e
th
o
d
”
.
A
p
p
li
e
d
M
a
th
e
ma
ti
c
s a
n
d
In
fo
rm
a
t
io
n
S
c
ien
c
e
s
.
2
0
1
3
:
7
(
1
);
2
9
1
–
2
9
8
.
[1
2
]
Zh
e
n
g
Y,
Zh
u
L
,
Zo
u
X
.
“
S
h
o
rt
-
T
e
r
m
L
o
a
d
F
o
re
c
a
stin
g
Ba
se
d
o
n
G
a
u
ss
ian
W
a
v
e
let
S
V
M
”
.
E
n
e
rg
y
Pro
c
e
d
ia
.
2
0
1
1
:
1
2
(
1
);
3
8
7
–
3
9
3
.
[1
3
]
Histo
rica
l
lo
a
d
d
a
ta retriev
e
d
f
ro
m
:
h
tt
p
:/
//
w
ww
.
jp
m
.
c
o
m
.
[1
4
]
Ng
u
y
e
n
K,
L
e
T
,
L
a
i
V
,
Ng
u
y
e
n
D,
T
ra
n
D,
M
a
W
.
“
L
e
a
st
sq
u
a
re
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
f
o
r
larg
e
-
sc
a
le
d
a
tas
e
t
”
.
Pro
c
e
e
d
in
g
s
o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
J
o
in
t
C
o
n
fer
e
n
c
e
o
n
Ne
u
r
a
l
Ne
tw
o
rk
s
.
Ire
lan
d
.
2
0
1
5
.
1
-
8.
[1
5
]
M
irj
a
li
li
S
.
“
T
h
e
a
n
t
li
o
n
o
p
ti
m
iz
e
r
”
.
Ad
v
a
n
c
e
s in
En
g
i
n
e
e
rin
g
S
o
ft
wa
re
.
2
0
1
5
:
8
3
(1
)
;
8
0
–
9
8
.
[1
6
]
De
-
y
u
e
M
,
W
e
n
-
y
in
g
L
,
“
Ap
p
li
c
a
ti
o
n
o
f
L
e
a
st
S
q
u
a
re
s
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
(L
S
S
V
M
)
b
a
se
d
o
n
T
im
e
S
e
ries
i
n
P
o
w
e
r
S
y
ste
m
M
o
n
th
ly
L
o
a
d
F
o
r
e
c
a
stin
g
”
,
Asia
-
Pa
c
if
ic P
o
we
r a
n
d
En
e
rg
y
C
o
n
fer
e
n
c
e
,
2
0
1
1
.
1
-
4,
Evaluation Warning : The document was created with Spire.PDF for Python.