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.
10
,
No
.
2
,
May
201
8
,
p
p
.
748
~7
5
5
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
0
.
i2
.
p
p
748
-
7
5
5
748
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
H
o
ur Ah
ea
d
Electrici
ty Pri
ce
Foreca
sting
w
ith
Lea
st Square
Suppo
rt
Vect
o
r
M
a
chine and B
a
c
terial Fora
g
ing
Opti
m
i
z
a
tion
Alg
o
rith
m
I
nta
n Az
m
ira
Wa
n Ab
du
l R
a
za
k
1
,
I
zha
m
Z
a
ina
l A
bi
din
2
,
Ya
p K
ee
m
Sia
h
3
,
Aidil
Azw
in
Z
a
in
ul Abi
din
4
,
T
it
i
k
K
ha
w
a
Abdu
l R
a
h
m
a
n
5
,
Nurliy
a
na
B
a
ha
rin
6
,
M
o
h
d.
H
a
f
iz
B
in J
a
li
7
1
,
6,
7
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
sia
M
e
lak
a
,
M
a
lac
c
a
,
M
a
la
y
si
a
2
,
3,
4
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Na
ti
o
n
a
l
En
e
rg
y
Un
iv
e
rsit
y
,
S
e
lan
g
o
r,
M
a
la
y
sia
3
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
G
irl
Ca
m
p
u
s,
Kin
g
A
b
d
u
laz
iz Un
iv
e
rsity
,
Je
d
d
a
h
,
S
a
u
d
i
A
ra
b
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
N
ov
7
,
2
0
1
7
R
ev
i
s
ed
J
an
20
,
2
0
1
8
A
cc
ep
ted
F
eb
2
0
,
2
0
1
8
P
re
d
ictin
g
e
lec
tri
c
it
y
p
rice
h
a
s
n
o
w
b
e
c
o
m
e
a
n
i
m
p
o
rtan
t
tas
k
in
p
o
w
e
r
s
y
ste
m
o
p
e
ra
ti
o
n
a
n
d
p
lan
n
i
n
g
.
A
n
h
o
u
r
-
a
h
e
a
d
f
o
re
c
a
st
p
ro
v
id
e
s
m
a
rk
e
t
p
a
rti
c
ip
a
n
ts
w
it
h
th
e
p
re
-
d
isp
a
tch
p
rice
s
f
o
r
th
e
n
e
x
t
h
o
u
r
.
It
is
b
e
n
e
f
icia
l
f
o
r
a
n
a
c
ti
v
e
b
id
d
in
g
stra
teg
y
w
h
e
re
a
m
o
u
n
t
o
f
b
id
s
c
a
n
b
e
r
e
v
iew
e
d
o
r
m
o
d
if
ied
b
e
f
o
re
d
e
li
v
e
r
y
h
o
u
rs.
Ho
w
e
v
e
r,
o
n
ly
a
fe
w
stu
d
ies
h
a
v
e
b
e
e
n
c
o
n
d
u
c
te
d
in
th
e
f
ield
o
f
h
o
u
r
-
a
h
e
a
d
f
o
re
c
a
stin
g
.
T
h
is
is
d
u
e
to
m
o
st
p
o
w
e
r
m
a
r
k
e
ts
a
p
p
l
y
tw
o
-
se
tt
le
m
e
n
t
m
a
r
k
e
t
stru
c
tu
re
(d
a
y
-
a
h
e
a
d
a
n
d
re
a
l
ti
m
e
)
o
r
sta
n
d
a
rd
m
a
r
k
e
t
d
e
sig
n
r
a
th
e
r
th
a
n
sin
g
le
-
se
tt
lem
e
n
t
sy
ste
m
(r
e
a
l
ti
m
e
).
T
h
e
re
f
o
re
,
a
h
y
b
rid
m
u
lt
i
-
o
p
ti
m
iza
ti
o
n
o
f
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
V
M
)
a
n
d
Ba
c
teria
l
F
o
ra
g
in
g
Op
ti
m
iza
ti
o
n
A
l
g
o
rit
h
m
(BF
O
A
)
wa
s
d
e
si
g
n
e
d
in
th
is
stu
d
y
to
p
ro
d
u
c
e
a
c
c
u
ra
te
e
le
c
tri
c
it
y
p
rice
f
o
r
e
c
a
sts
w
it
h
o
p
ti
m
ize
d
L
S
S
V
M
p
a
ra
m
e
ters
a
n
d
in
p
u
t
f
e
a
tu
re
s.
S
o
f
a
r,
n
o
w
o
rk
s
h
a
s
b
e
e
n
e
sta
b
li
sh
e
d
o
n
m
u
lt
istag
e
f
e
a
tu
re
a
n
d
p
a
ra
m
e
t
e
r
o
p
ti
m
iza
ti
o
n
u
sin
g
L
S
S
V
M
-
BF
OA
f
o
r
h
o
u
r
-
a
h
e
a
d
p
rice
f
o
re
c
a
st.
T
h
e
m
o
d
e
l
w
a
s
e
x
a
m
in
e
d
o
n
th
e
On
t
a
rio
p
o
w
e
r
m
a
rk
e
t.
A
h
u
g
e
n
u
m
b
e
r
o
f
fe
a
tu
re
s
w
e
re
se
lec
ted
b
y
f
iv
e
sta
g
e
s
o
f
o
p
ti
m
iza
ti
o
n
t
o
a
v
o
id
f
ro
m
m
iss
in
g
a
n
y
i
m
p
o
rtan
t
f
e
a
tu
re
s.
T
h
e
d
e
v
e
lo
p
e
d
L
S
S
V
M
-
BF
OA
sh
o
w
s
h
ig
h
e
r
f
o
r
e
c
a
st
a
c
c
u
ra
c
y
w
it
h
lo
we
r
c
o
m
p
lex
it
y
th
a
n
m
o
st o
f
th
e
e
x
isti
n
g
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
Ba
c
teria
l
El
e
c
tri
c
it
y
P
rice
F
o
re
c
a
stin
g
F
o
ra
g
in
g
Op
ti
m
iza
ti
o
n
Ho
u
r
A
h
e
a
d
F
o
re
c
a
st
M
A
P
E
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
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
:
I
n
tan
A
z
m
ir
a
W
an
A
b
d
u
l
R
az
ak
,
Facu
lt
y
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Un
i
v
er
s
iti T
ek
n
ik
al
Ma
la
y
s
ia
Me
lak
a
,
Han
g
T
u
ah
J
a
y
a,
7
6
1
0
0
Du
r
ian
T
u
n
g
g
al,
Me
la
k
a,
Ma
la
y
s
ia.
E
m
ail: i
n
ta
n
.
az
m
ir
a
@
u
te
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Ho
u
r
-
a
h
ea
d
elec
tr
icit
y
p
r
ice
p
r
ed
ictio
n
is
cr
u
c
ial
to
m
ar
k
et
p
ar
ticip
an
ts
in
d
er
eg
u
la
ted
elec
tr
icit
y
m
ar
k
et
to
p
r
o
d
u
ce
an
ap
p
r
o
p
r
iate
b
id
d
in
g
p
lan
w
h
er
e
t
h
e
q
u
an
t
it
y
o
f
b
id
s
ca
n
b
e
r
ev
is
ed
o
r
ch
an
g
ed
p
r
io
r
to
th
e
d
is
p
atch
h
o
u
r
.
Ho
w
ev
er
,
o
n
l
y
a
f
e
w
s
t
u
d
ies
h
av
e
b
e
en
co
n
d
u
cted
i
n
th
e
f
ield
o
f
h
o
u
r
-
a
h
ea
d
p
r
ice
f
o
r
ec
asti
n
g
.
T
h
is
is
b
ec
au
s
e
m
o
s
t
p
o
w
er
m
ar
k
ets
r
u
n
t
w
o
-
s
ett
le
m
e
n
t
m
ar
k
et
s
tr
u
ct
u
r
e
(
d
ay
-
a
h
ea
d
an
d
r
ea
l
ti
m
e)
o
r
s
tan
d
ar
d
m
ar
k
e
t d
esig
n
r
ath
er
th
a
n
s
in
g
le
-
s
et
tle
m
e
n
t
s
y
s
te
m
(
r
ea
l ti
m
e)
.
P
r
ev
io
u
s
r
esear
ce
r
s
p
r
o
p
o
s
ed
v
ar
io
u
s
m
et
h
o
d
s
s
u
c
h
as
ti
m
e
s
er
ies
m
o
d
el
o
f
Mu
lti
v
ar
iate
A
d
ap
ti
v
e
R
eg
r
es
s
io
n
Sp
lin
e
s
(
M
A
R
S)
[
1
]
,
L
ev
en
b
er
g
-
m
ar
q
u
ar
d
t
(
L
M
)
b
ac
k
p
r
o
p
ag
atio
n
[
2
]
,
an
d
I
n
p
u
t
–
Ou
tp
u
t
Hid
d
en
Ma
r
k
o
v
Mo
d
el
(
I
OHM
M)
[
3
]
.
Me
an
w
h
ile,
a
h
y
b
r
id
m
et
h
o
d
ar
e
also
d
ev
elo
p
ed
s
u
ch
as
r
ec
u
r
r
en
t
n
e
u
r
al
n
et
w
o
r
k
s
(
R
NN)
an
d
e
x
cita
b
le
d
y
n
a
m
ics
[
4
]
an
d
a
h
y
b
r
id
m
o
d
el
o
f
Au
to
r
eg
r
ess
iv
e
Mo
v
in
g
Av
er
ag
e
E
x
o
g
e
n
o
u
s
(
AR
M
A
X
)
,
ad
ap
tiv
e
w
av
elet
n
e
u
r
al
n
et
w
o
r
k
(
A
W
NN)
,
an
d
Gen
er
aliz
ed
A
u
to
r
eg
r
e
s
s
i
v
e
C
o
n
d
itio
n
a
l
Hete
r
o
s
k
ed
asti
cit
y
(
G
AR
C
H
)
to
tr
ea
t
li
n
ea
r
a
n
d
n
o
n
li
n
ea
r
s
tr
u
ctu
r
es
o
f
p
r
i
ce
s
er
ies
[
5
]
.
Oth
er
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
Ho
u
r
A
h
e
a
d
E
lectricity P
r
ice
F
o
r
ec
a
s
tin
g
w
it
h…
(
I
n
ta
n
A
z
mir
a
W
a
n
A
b
d
u
l R
a
z
a
k
)
749
Neu
r
al
Net
w
o
r
k
(
NN)
tec
h
n
iq
u
es
w
er
e
also
m
o
d
elled
s
u
ch
as
E
x
p
ec
tatio
n
Ma
x
i
m
izatio
n
(
E
M)
tech
n
iq
u
e
f
o
r
m
ax
i
m
u
m
lik
el
ih
o
o
d
esti
m
at
i
o
n
o
f
R
N
N
(
R
N
N
-
E
M)
[
6
]
,
Mu
lti
-
la
y
er
P
er
ce
p
tr
o
n
NN
tr
ain
ed
b
y
E
x
te
n
d
ed
Kal
m
a
n
Fil
ter
(
M
L
P
-
E
KF)
an
d
EM
(
ML
P
-
E
M)
[
7
]
an
d
E
x
t
en
d
ed
Kal
m
an
Fil
ter
f
o
r
R
NN
(
R
NN
-
E
KF)
[
8
]
.
A
Gen
er
alize
d
R
eg
r
es
s
io
n
Ne
u
r
al
Net
w
o
r
k
(
GR
NN)
w
as
d
ev
elo
p
ed
b
y
[
9
]
an
d
D
is
cr
ete
C
o
s
i
n
e
T
r
an
s
f
o
r
m
s
I
n
p
u
t
Fea
tu
r
ed
Feed
-
Fo
r
w
ar
d
Neu
r
al
Net
w
o
r
k
(
D
C
T
-
FF
NN)
m
o
d
el
w
as
p
r
o
p
o
s
ed
b
y
[
1
0
]
.
T
h
e
s
a
m
e
r
esear
ch
er
s
f
u
r
t
h
er
i
m
p
r
o
v
ed
th
e
f
o
r
ec
ast
b
y
cr
ea
ti
n
g
cl
ass
i
f
icatio
n
m
o
d
els
u
s
in
g
t
h
r
ee
la
y
er
ed
FF
NN,
C
ascad
e
-
Fo
r
w
ar
d
Neu
r
al
Ne
t
w
o
r
k
(
C
FNN)
tr
ain
ed
b
y
t
h
e
L
M
alg
o
r
ith
m
,
an
d
G
R
NN
m
o
d
els
[
1
1
]
.
Mo
s
t
ex
i
s
ti
n
g
tech
n
iq
u
e
s
h
a
v
e
g
o
o
d
p
r
ed
ictio
n
s
d
u
r
in
g
n
o
r
m
al
cir
cu
m
s
tan
ce
s
o
r
w
it
h
o
u
t
a
s
u
r
g
e
ev
en
t
;
b
u
t
w
h
en
s
p
ik
e
s
ar
e
p
r
esen
t,
f
o
r
ec
ast
p
r
ed
ictio
n
s
b
ec
o
m
e
lar
g
e
.
H
en
ce
,
t
h
is
s
tu
d
y
in
tr
o
d
u
ce
s
a
n
e
w
tech
n
iq
u
e
i
n
elec
tr
icit
y
p
r
ice
f
o
r
ec
ast b
y
d
ev
elo
p
in
g
h
o
u
r
-
a
h
ea
d
elec
tr
icit
y
p
r
ice
f
o
r
ec
ast
in
g
m
o
d
el
w
i
th
L
ea
s
t
Sq
u
ar
e
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
L
SS
VM
)
a
n
d
B
ac
ter
ial
Fo
r
ag
in
g
Op
ti
m
izatio
n
A
l
g
o
r
it
h
m
(
B
FO
A
)
.
B
FO
A
h
as
a
f
a
s
t
co
n
v
er
g
e
n
ce
[
1
2
]
a
nd
h
as
b
ee
n
e
x
p
lo
r
ed
in
m
an
y
f
ield
s
s
u
c
h
as
f
ac
e
r
ec
o
g
n
i
tio
n
[
1
3
]
,
[
1
4
]
,
b
io
m
etr
ic
a
u
t
h
en
t
icatio
n
[
1
5
]
,
m
u
l
ti
m
o
d
al
f
u
n
ctio
n
[
1
6
]
,
[
1
7
]
,
an
d
f
lex
ib
le
m
a
n
u
f
ac
t
u
r
i
n
g
s
y
s
te
m
s
(
FMS)
[
1
8
]
.
Fu
r
th
er
m
o
r
e,
r
esear
ch
er
s
in
co
n
tr
o
l
an
d
p
o
w
er
s
y
s
te
m
d
ev
elo
p
ed
B
FOA
m
o
d
els
f
o
r
Static
S
y
n
ch
r
o
n
o
u
s
Ser
ies
C
o
m
p
e
n
s
a
to
r
(
SS
SC
)
Da
m
p
in
g
C
o
n
tr
o
ller
Desi
g
n
[
1
9
]
,
r
o
b
o
tic
m
an
ip
u
lato
r
w
o
r
k
s
p
ac
e
o
p
ti
m
izat
io
n
[
20]
,
th
r
ee
p
h
ase
in
d
u
ctio
n
m
o
to
r
an
d
elec
tr
icit
y
lo
ad
f
o
r
ec
asti
n
g
[
2
8
]
,
[
3
4
]
.
T
o
th
e
b
est
o
f
th
e
au
t
h
o
r
s
’
r
ev
ie
w
,
n
o
li
ter
atu
r
e
h
as
b
ee
n
f
o
u
n
d
o
n
t
h
e
co
m
b
i
n
atio
n
o
f
L
SS
VM
an
d
B
FO
A
in
t
h
e
elec
tr
icit
y
p
r
ice
f
o
r
ec
ast.
F
u
r
th
er
m
o
r
e,
th
e
ap
p
r
o
ac
h
o
f
m
u
lti
s
tag
e
f
ea
t
u
r
e
an
d
p
ar
a
m
eter
s
elec
tio
n
s
u
s
in
g
a
s
in
g
l
e
o
p
tim
izatio
n
m
et
h
o
d
h
as
n
o
t
b
ee
n
in
v
esti
g
ated
y
et.
W
ith
a
s
in
g
le
o
p
ti
m
izatio
n
m
et
h
o
d
o
f
B
FOA
,
t
h
e
in
p
u
t
f
ea
t
u
r
es
an
d
L
S
SVM
p
ar
a
m
e
ter
s
ar
e
s
i
m
u
lta
n
eo
u
s
l
y
o
p
tim
ized
th
r
o
u
g
h
f
iv
e
-
s
tag
e
o
p
t
i
m
izatio
n
ap
p
r
o
ac
h
.
T
h
is
m
et
h
o
d
is
s
h
o
w
n
to
p
r
o
v
id
e
b
etter
p
r
ed
ictio
n
ac
cu
r
ac
y
co
m
p
ar
ed
to
m
o
s
t
ex
i
s
ti
n
g
m
o
d
el
s
,
w
h
ic
h
ca
n
co
n
tr
ib
u
te
f
o
r
d
ec
is
io
n
-
m
a
k
i
n
g
an
d
h
o
u
r
l
y
m
ar
k
et
o
p
er
atio
n
.
2.
T
O
P
O
L
O
G
Y
OF
SVM
,
L
SS
VM
AND
B
F
O
A
T
h
is
s
ec
tio
n
p
r
o
v
id
es to
p
o
lo
g
i
es o
f
SVM,
L
SS
VM
an
d
B
FO
A
w
h
ic
h
w
er
e
ap
p
lied
in
th
is
s
tu
d
y
.
2
.
1
.
SV
M
a
nd
L
SS
VM
SVM
ca
n
r
ed
u
ce
o
v
er
-
f
itti
n
g
,
lo
ca
l
m
in
i
m
a
p
r
o
b
le
m
s
[
2
6
]
,
an
d
ab
le
to
d
ea
l
w
i
th
h
i
g
h
d
i
m
en
s
io
n
a
l
in
p
u
t
s
p
ac
es
s
p
len
d
id
l
y
.
Ho
wev
er
,
th
e
m
a
in
d
r
a
w
b
ac
k
o
f
S
VM
is
th
e
h
i
g
h
co
m
p
u
tatio
n
al
co
m
p
lex
i
t
y
d
u
e
to
co
n
s
tr
ain
ed
o
p
ti
m
izatio
n
p
r
o
g
r
a
m
m
in
g
.
He
n
ce
,
L
ea
s
t
Sq
u
ar
es
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
L
S
SVM)
h
a
s
b
ee
n
p
r
o
p
o
s
ed
to
r
ed
u
ce
th
e
SVM
co
m
p
u
tatio
n
al
b
u
r
d
en
,
w
h
ic
h
ap
p
lies
w
it
h
eq
u
ali
t
y
r
ath
er
th
an
t
h
e
i
n
eq
u
al
it
y
co
n
s
tr
ain
ts
.
L
SS
VM
s
o
l
v
es
a
s
y
s
te
m
o
f
li
n
ea
r
eq
u
atio
n
s
t
o
ca
ter
Qu
ad
r
atic
P
r
o
g
r
am
m
i
n
g
(
QP
)
is
s
u
e
s
t
h
at
in
cr
ea
s
e
co
m
p
u
tatio
n
al
s
p
ee
d
[
2
7
]
,
[
2
8
]
.
T
h
e
lin
ea
r
s
y
s
te
m
,
n
a
m
el
y
a
s
Kar
u
s
h
-
Ku
h
n
-
T
u
ck
er
(
KKT
)
,
is
s
i
m
p
ler
t
h
an
QP
s
y
s
te
m
.
L
S
S
VM
also
k
ee
p
s
t
h
e
SV
M
p
r
in
cip
le,
w
h
ich
h
as
g
o
o
d
g
en
er
a
lizatio
n
ca
p
ab
ilit
y
.
L
S
SVM
r
ed
u
ce
s
th
e
S
u
m
Sq
u
ar
e
E
r
r
o
r
s
(
SS
E
s
)
o
f
tr
ai
n
i
n
g
d
ata
s
et
s
an
d
co
n
cu
r
r
en
tl
y
d
i
m
in
is
h
i
n
g
m
ar
g
i
n
er
r
o
r
.
T
h
e
L
SS
VM
m
o
d
el
f
o
r
r
eg
r
ess
io
n
is
r
ep
r
esen
ted
as i
n
(
1
):
(
1)
2
.2
.
B
F
O
A
T
h
e
E
.
co
li
b
ac
ter
ia,
w
h
ich
is
p
r
esen
t
i
n
h
u
m
a
n
's
i
n
test
in
e
s
h
a
s
u
n
iq
u
e
f
o
r
ag
i
n
g
ac
ti
v
it
ies
d
u
r
i
n
g
lo
ca
tin
g
a
n
d
in
g
es
tin
g
n
u
tr
ie
n
t
o
r
f
o
o
d
.
B
FOA
i
m
itate
s
t
h
is
m
ec
h
an
i
s
m
th
r
o
u
g
h
f
o
u
r
m
ai
n
s
tep
s
d
u
r
i
n
g
f
o
r
ag
i
n
g
;
n
a
m
el
y
,
c
h
e
m
o
tax
i
s
,
s
w
ar
m
i
n
g
,
r
ep
r
o
d
u
ctio
n
,
an
d
eli
m
i
n
atio
n
-
d
i
s
p
er
s
al.
T
h
e
f
lo
w
o
f
B
FO
A
ap
p
lied
in
th
is
w
o
r
k
i
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
I
n
t
h
e
ch
e
m
o
ta
x
is
s
tep
,
b
ac
ter
ia
lo
o
k
f
o
r
n
u
tr
ien
t
s
to
m
a
x
i
m
ize
th
e
e
n
er
g
y
in
ta
k
e
w
h
i
le
f
o
r
ag
in
g
b
y
tak
i
n
g
s
m
all
s
tep
s
(
ch
e
m
o
tax
is
)
an
d
i
n
ter
ac
t
i
n
g
w
i
th
o
t
h
e
r
b
ac
ter
ia
b
y
s
e
n
d
i
n
g
at
tr
ac
t
an
t
s
i
g
n
al
to
f
o
r
m
f
lo
ck
s
;
o
r
r
ep
ellen
t
s
ig
n
al
to
m
o
v
e
i
n
d
i
v
id
u
all
y
.
T
h
e
y
tu
m
b
le
o
r
s
w
i
m
to
s
ea
r
ch
n
u
tr
ien
t
b
u
t
k
ee
p
a
w
a
y
f
r
o
m
u
n
s
a
f
e
p
lace
s
.
T
h
er
ef
o
r
e
,
s
u
p
p
o
s
e
th
at
is
th
e
i
-
t
h
b
ac
ter
i
u
m
p
o
s
itio
n
at
j
-
t
h
c
h
e
m
o
tac
tic,
k
-
t
h
r
ep
r
o
d
u
ctio
n
,
an
d
l
-
th
eli
m
i
n
atio
n
-
d
i
s
p
er
s
al
s
tep
,
th
e
p
o
s
itio
n
o
f
ea
ch
b
ac
ter
iu
m
a
f
ter
s
w
i
m
m
in
g
o
r
tu
m
b
li
n
g
ca
n
b
e
d
ef
in
ed
as (
2
):
(
2)
b
x
x
K
x
f
k
N
k
k
)
,
(
)
(
1
)
,
,
(
l
k
j
i
)
(
)
(
)
(
)
(
)
,
,
(
)
,
,
1
(
i
i
i
i
C
l
k
j
l
k
j
T
i
i
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.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
4
8
–
7
5
5
750
Star
t
Select
tr
ain
i
n
g
p
er
io
d
C
o
r
r
elatio
n
an
al
y
s
i
s
No
Yes
Yes
No
No
Yes
P
er
f
o
r
m
eli
m
i
n
atio
n
an
d
d
is
p
er
s
al
I
n
itializatio
n
o
f
v
ar
iab
les
R
an
d
o
m
i
n
it
ial
p
o
s
itio
n
o
f
i
E
li
m
i
n
atio
n
&
d
is
p
er
s
al
lo
o
p
co
u
n
ter
l
<
?
R
ep
r
o
d
u
ctio
n
lo
o
p
co
u
n
ter
k
<
?
C
h
e
m
o
ta
x
is
lo
o
p
co
u
n
ter
j
<
?
C
o
m
p
u
te
an
d
s
o
r
t
R
ep
r
o
d
u
ctio
n
E
n
d
B
C
No
Yes
C
B
ac
ter
iu
m
’
s
i
n
d
ex
lo
o
p
co
u
n
ter
i
<
S?
B
C
o
m
p
u
te
=
T
u
m
b
le
a
n
d
m
o
v
e
C
o
m
p
u
te
n
e
w
Set s
w
i
m
co
u
n
ter
m
= 0
m
<
?
m
=
m
+ 1
No
Yes
Set
=
S
w
i
m
C
o
m
p
u
te
n
e
w
?
No
Set
m
=
Yes
D
D
D
B
FOA
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
Ho
u
r
A
h
e
a
d
E
lectricity P
r
ice
F
o
r
ec
a
s
tin
g
w
it
h…
(
I
n
ta
n
A
z
mir
a
W
a
n
A
b
d
u
l R
a
z
a
k
)
751
Fig
u
r
e
1
:
Flo
w
c
h
ar
t o
f
L
S
SV
M
-
B
FO
A
Mo
d
el
Dev
elo
p
m
en
t
W
h
er
e
C
(
i)
is
th
e
m
ea
s
u
r
e
o
f
th
e
s
tep
tak
e
n
d
u
r
in
g
tu
m
b
li
n
g
o
r
s
w
i
m
m
i
n
g
,
an
d
∆
is
t
h
e
v
ec
to
r
in
a
r
an
d
o
m
d
ir
ec
tio
n
w
h
er
e
t
h
e
e
le
m
e
n
ts
lie
in
p
o
s
itio
n
[
-
1
,
1
]
.
T
h
e
o
b
j
ec
tiv
e
f
u
n
c
tio
n
o
r
ac
tu
al
co
s
t
f
o
r
ev
er
y
lo
ca
tio
n
o
f
b
ac
ter
iu
m
i
is
ca
lcu
lated
an
d
r
ep
r
esen
ted
as
J(
i,j,
k,
l)
.
Du
r
in
g
s
w
ar
m
i
n
g
s
tep
,
a
b
ac
ter
iu
m
th
at
ha
s
f
o
u
n
d
a
g
o
o
d
n
u
tr
ien
t
s
o
u
r
ce
d
u
r
in
g
its
s
ea
r
ch
m
a
y
at
tr
ac
t
o
th
er
b
ac
ter
ia
to
f
o
r
m
f
lo
ck
s
.
I
n
s
tead
,
th
e
r
ep
ellen
t
s
ig
n
al
m
a
y
b
e
r
elea
s
ed
to
e
n
s
u
r
e
t
h
at
t
h
e
b
ac
ter
ia
ar
e
n
o
t
t
o
o
clo
s
e
to
ea
ch
o
th
er
.
T
h
e
c
ell
-
to
-
ce
ll
a
ttr
ac
tio
n
an
d
r
ep
ellen
t
o
f
E
.
C
o
li
s
w
ar
m
ca
n
b
e
r
ep
r
esen
ted
as
J
cc
,
th
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
v
al
u
e
to
b
e
ad
d
ed
to
th
e
cu
r
r
en
t
o
b
j
ec
tiv
e
f
u
n
ctio
n
w
h
ich
w
ill
d
ec
r
ea
s
e
t
h
e
f
i
n
al
o
b
jectiv
e
f
u
n
ctio
n
.
W
h
en
f
o
o
d
is
s
u
f
f
icie
n
t
an
d
t
h
e
te
m
p
er
atu
r
e
i
s
ap
p
r
o
p
r
iate
,
th
e
h
ea
lt
h
ies
t o
r
g
o
o
d
b
ac
ter
ia
w
i
ll g
r
o
w
i
n
le
n
g
t
h
an
d
b
r
ea
k
i
n
th
e
m
id
d
le
to
f
o
r
m
th
e
s
el
f
-
r
ep
licati
n
g
w
h
ic
h
co
n
t
r
ib
u
tes
to
th
e
n
e
x
t
g
e
n
er
atio
n
w
h
ile
th
e
least
h
ea
lth
y
b
ac
ter
i
a
d
ie
.
T
h
is
ac
ti
v
it
y
is
k
n
o
w
n
as
r
ep
r
o
d
u
ctio
n
.
T
h
u
s
,
B
FO
A
u
s
es
t
h
is
p
h
e
n
o
m
e
n
o
n
b
y
s
tr
u
ct
u
r
in
g
th
e
b
est
o
b
j
ec
tiv
e
f
u
n
ctio
n
i
n
th
e
asce
n
d
in
g
o
r
d
er
an
d
m
a
in
tai
n
i
n
g
h
al
f
o
f
th
e
p
o
p
u
lat
io
n
s
ize
to
r
ep
r
o
d
u
ce
w
h
ile
th
e
o
th
er
h
al
f
i
s
eli
m
i
n
ated
.
T
h
e
last
s
tep
i
s
th
e
eli
m
i
n
atio
n
-
d
i
s
p
er
s
al
w
h
er
e
th
e
ch
e
m
o
tactic
p
r
o
ce
s
s
ca
n
b
e
d
is
s
o
lv
ed
an
d
t
h
e
b
ac
ter
ia
s
p
r
ea
d
to
n
ew
p
o
s
itio
n
s
w
h
en
a
s
u
d
d
en
c
h
an
g
e
i
n
th
e
en
v
ir
o
n
m
e
n
t e
x
is
t
s
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
On
tar
io
,
th
e
elec
tr
ic
it
y
m
ar
k
et
is
o
p
er
ated
b
y
t
h
e
I
n
d
ep
en
d
en
t
E
lectr
i
cit
y
S
y
s
te
m
s
Op
er
ato
r
(
I
E
SO)
,
w
h
ich
co
n
tr
o
ls
t
h
e
o
p
er
atio
n
o
f
p
o
w
er
s
y
s
te
m
s
,
p
r
ed
icts
s
h
o
r
t
-
ter
m
d
e
m
a
n
d
an
d
elec
tr
icit
y
s
u
p
p
l
y
,
an
d
m
a
n
ag
e
s
r
ea
l
ti
m
e
m
ar
k
et
elec
tr
icit
y
p
r
ices.
D
u
e
to
th
e
s
in
g
le
s
ett
le
m
e
n
t
r
ea
l
-
ti
m
e
p
o
w
er
m
ar
k
et,
O
n
tar
io
is
r
ep
o
r
ted
to
b
e
o
n
e
o
f
t
h
e
m
o
s
t v
o
lati
le
m
ar
k
et
s
i
n
t
h
e
w
o
r
ld
an
d
h
e
n
ce
it i
s
a
b
i
g
c
h
alle
n
g
e
f
o
r
elec
tr
ic
p
r
ice
f
o
r
ec
aster
s
.
[
2
9
]
.
A
p
p
r
o
p
r
iate
s
elec
tio
n
o
f
f
ea
tu
r
es
a
f
f
ec
ts
th
e
ef
f
icie
n
c
y
a
n
d
ac
cu
r
ac
y
o
f
p
r
ed
ictio
n
s
.
T
h
e
in
p
u
t
f
ea
tu
r
es
u
s
ed
i
n
t
h
is
s
t
u
d
y
ar
e
a
s
i
n
[
3
0
]
,
w
h
er
e
c
o
r
r
elatio
n
an
al
y
s
i
s
i
s
p
er
f
o
r
m
ed
to
o
b
s
er
v
e
th
e
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
es
f
o
r
f
o
r
ec
asti
n
g
.
T
h
e
to
tal
f
ea
t
u
r
es
ar
e
[
(
1
5
d
ay
s
x
2
4
h
o
u
r
s
p
r
ice)
+
(
1
5
d
ay
s
x
2
4
h
o
u
r
s
d
em
a
n
d
)
+
1
-
h
o
u
r
p
r
e
-
d
is
p
atc
h
p
r
ice
=
7
2
1
]
.
No
ted
th
at
t
h
i
s
m
et
h
o
d
is
a
n
in
it
ial
p
r
o
ce
s
s
to
f
il
ter
o
r
r
ed
u
ce
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
to
b
e
o
p
tim
ized
b
y
B
FO
A
.
H
y
b
r
id
m
o
d
el
o
f
L
SS
VM
-
B
FO
A
w
as
d
ev
elo
p
ed
w
it
h
f
i
v
e
-
s
tag
e
o
p
ti
m
izatio
n
o
f
f
ea
t
u
r
e
a
n
d
p
ar
am
e
ter
.
T
h
e
f
lo
w
o
f
B
F
OA
ap
p
lied
in
t
h
is
w
o
r
k
is
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Du
r
in
g
t
h
e
f
ir
s
t
s
ta
g
e,
all
7
2
1
f
ea
tu
r
es
ar
e
ap
p
lied
an
d
th
e
B
FO
A
s
elec
t
s
ce
r
tain
n
u
m
b
er
o
f
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
es
to
b
e
f
ed
in
to
th
e
L
SS
VM
.
A
t
t
h
e
s
a
m
e
ti
m
e,
B
FO
A
o
p
ti
m
ize
s
th
e
L
S
SVM
p
ar
a
m
eter
s
;
g
a
m
m
a
(
γ
)
an
d
s
i
g
m
a
(
σ
)
.
Du
r
in
g
t
h
e
s
ec
o
n
d
s
tag
e
o
f
o
p
tim
izatio
n
,
B
FO
A
o
p
ti
m
iz
es
th
e
f
ea
t
u
r
es
an
d
p
ar
am
eter
s
t
h
at
h
a
v
e
b
ee
n
s
e
l
ec
ted
f
r
o
m
t
h
e
f
ir
s
t
s
ta
g
e
o
f
o
p
ti
m
izatio
n
.
T
h
ese
s
tep
s
ar
e
r
ep
ea
ted
f
o
r
th
e
n
e
x
t
s
tag
e
o
f
o
p
ti
m
i
za
tio
n
u
n
til
n
o
im
p
r
o
v
e
m
e
n
t
h
a
s
b
ee
n
o
b
s
er
v
ed
in
t
h
e
f
it
n
es
s
v
al
u
e
o
r
Me
an
A
b
s
o
lu
te
P
er
ce
n
tag
e
E
r
r
o
r
(
MA
P
E
)
.
MA
P
E
a
n
d
Me
an
A
b
s
o
l
u
te
E
r
r
o
r
(
MA
E
)
ar
e
ex
p
r
ess
ed
as
i
n
(
3
)
an
d
(
4
)
;
r
esp
ec
tiv
el
y
,
w
h
er
e
P
actual
an
d
P
forecast
ar
e
th
e
ac
tu
al
an
d
f
o
r
ec
asted
HOE
P
at
h
o
u
r
t
,
r
esp
ec
tiv
el
y
,
w
h
ile
N
is
th
e
n
u
m
b
er
o
f
h
o
u
r
s
.
(
3)
(
4)
N
t
t
a
c
t
u
a
l
f
o
r
e
c
a
s
t
t
a
c
t
u
a
l
P
P
P
N
t
1
100
M
A
P
E
N
t
fo
r
e
c
a
s
t
t
a
c
tu
a
l
t
P
P
N
1
1
M
A
E
D
Featu
r
e
an
d
p
ar
a
m
eter
s
elec
tio
n
L
S
SVM
tr
ain
in
g
C
o
m
p
u
te
J
(
MA
P
E
)
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.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
4
8
–
7
5
5
752
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
co
m
p
ar
is
o
n
w
i
th
p
r
ev
io
u
s
r
esear
ch
er
s
,
s
i
x
p
r
ed
ictiv
e
m
o
d
els
w
er
e
d
ev
elo
p
ed
to
r
ep
r
esen
t
th
r
o
u
g
h
o
u
t
2
0
0
4
.
E
ac
h
m
o
d
el
is
tr
ai
n
ed
w
it
h
ten
w
ee
k
s
o
f
t
r
ain
in
g
s
a
m
p
le
s
p
r
io
r
to
th
e
f
o
r
ec
asti
n
g
w
ee
k
as
p
r
esen
ted
in
[
3
0
]
.
T
a
b
le
1
p
r
e
s
en
t
s
t
h
e
r
es
u
lt
f
o
r
al
l
tes
t
w
e
ek
s
a
n
d
o
p
ti
m
izatio
n
s
ta
g
es.
I
t
ca
n
b
e
n
o
ted
t
h
a
t
th
e
av
er
ag
e
M
A
P
E
d
ec
r
ea
s
es
af
ter
ea
ch
lev
el
o
f
o
p
ti
m
izat
io
n
.
T
h
e
b
est
MA
P
E
s
ar
e
o
b
tain
ed
d
u
r
in
g
th
e
f
i
f
t
h
s
tag
e
o
f
o
p
ti
m
izatio
n
.
T
ab
le
2
r
ev
ea
ls
th
e
n
e
t
w
o
r
k
co
n
f
i
g
u
r
atio
n
s
f
o
r
all
test
w
ee
k
s
d
u
r
in
g
t
h
e
f
i
f
t
h
s
tag
e
o
f
o
p
tim
izatio
n
.
T
h
e
B
FO
A
p
ar
am
eter
s
m
u
s
t b
e
ch
o
s
e
n
p
r
o
p
er
l
y
b
y
t
r
ial
an
d
er
r
o
r
m
e
th
o
d
[
3
1
]
,
[
3
2
]
,
[
3
3
]
.
T
h
e
m
ain
o
p
ti
m
izatio
n
p
r
o
ce
s
s
o
cc
u
r
s
d
u
r
i
n
g
c
h
e
m
o
tax
is
ac
tiv
it
y
w
h
er
e
t
h
e
o
b
j
ec
tiv
e
f
u
n
ct
io
n
i
s
ca
lcu
lated
f
o
r
ea
ch
b
ac
ter
iu
m
.
T
o
o
s
m
all
v
alu
e
o
f
N
c
m
a
y
tr
ap
th
e
b
ac
ter
ia
in
to
lo
ca
l
m
i
n
i
m
a.
N
s
v
al
u
e
m
u
s
t
b
e
s
m
aller
t
h
a
n
N
c
v
al
u
e.
A
lt
h
o
u
g
h
t
h
e
s
w
i
m
m
i
n
g
ac
tiv
it
y
o
cc
u
r
s
i
n
ch
e
m
o
ta
x
is
lo
o
p
,
th
e
s
w
i
m
m
i
n
g
co
u
n
ter
w
il
l
b
e
ter
m
in
a
ted
if
t
h
e
M
A
P
E
p
r
o
d
u
ce
d
is
g
r
ea
ter
th
an
t
h
e
p
r
ev
io
u
s
M
A
P
E
.
T
h
e
v
alu
e
o
f
p
ed
is
s
et
as
0
.
2
5
s
in
ce
to
o
lar
g
e
v
alu
e
ca
n
in
c
r
ea
s
e
co
m
p
u
tatio
n
al
b
u
r
d
en
d
u
e
to
an
ex
ten
s
i
v
e
s
ea
r
ch
.
Me
an
w
h
ile,
th
e
N
re
s
h
o
u
ld
n
o
t
b
e
to
o
s
m
all
a
s
it
m
a
y
ca
u
s
e
p
r
e
m
a
tu
r
e
co
n
v
er
g
en
ce
.
As
i
n
g
e
n
er
al,
in
cr
ea
s
in
g
t
h
e
s
ize
o
f
S
,
N
ed
,
N
re
,
an
d
N
c
m
a
y
in
cr
ea
s
e
th
e
co
m
p
u
tatio
n
al
b
u
r
d
en
,
b
u
t
h
o
p
ef
u
ll
y
it
m
a
y
i
m
p
r
o
v
e
th
e
o
p
ti
m
izatio
n
p
r
o
ce
s
s
s
in
ce
b
ac
ter
ia
h
a
v
e
a
w
id
er
s
ea
r
ch
s
p
ac
e.
F
u
r
th
er
m
o
r
e,
th
e
d
ev
elo
p
ed
m
o
d
els
o
f
L
S
SVM
-
B
FO
A
ar
e
co
m
p
ar
ed
w
it
h
o
t
h
er
ex
is
ti
n
g
m
o
d
els
a
s
tab
u
lated
in
T
ab
l
e
3
.
B
ased
o
n
th
e
o
b
s
er
v
atio
n
o
f
T
ab
le
3
,
th
e
L
S
SVM
-
B
FO
A
m
o
d
el
s
h
o
w
s
b
etter
r
esu
lt
th
a
n
o
t
h
er
av
ai
lab
le
m
o
d
els
ex
ce
p
t
f
o
r
L
S
S
VM
+G
A
[
3
0
]
an
d
R
NN
w
it
h
ex
citab
le
d
y
n
a
m
ics
[
4
]
m
o
d
el
s
.
Ho
w
ev
er
,
th
e
L
S
SVM
-
B
F
O
A
m
o
d
el
is
co
n
s
id
e
r
ed
as
co
m
p
ar
ab
le
s
in
ce
t
h
e
d
i
f
f
er
e
n
ce
s
o
f
M
A
P
E
ar
e
o
n
l
y
0
.
5
5
%
[
4
]
an
d
3
.
6
%
[
3
0
]
.
I
n
co
m
p
ar
is
o
n
,
t
h
e
R
NN
m
o
d
el
h
a
s
a
m
o
r
e
co
m
p
le
x
s
tr
u
ct
u
r
e,
w
h
ic
h
is
d
e
s
ig
n
ed
to
h
an
d
le
s
p
i
k
y
a
n
d
n
o
n
-
s
p
ik
y
p
r
ice
r
eg
io
n
s
.
T
ab
le
1
.
MA
P
E
of
L
SS
VM
-
B
FO
A
f
o
r
Ho
u
r
-
A
h
ea
d
Fo
r
ec
as
t
O
p
t
i
mi
z
a
t
i
o
n
S
t
a
g
e
M
A
P
E
(
%)
W
e
e
k
1
W
e
e
k
2
W
e
e
k
3
W
e
e
k
4
W
e
e
k
5
W
e
e
k
6
A
v
e
r
a
g
e
S
t
a
g
e
1
1
6
.
5
8
1
5
.
3
0
1
2
.
5
1
2
6
.
8
9
1
7
.
3
6
2
1
.
6
7
1
8
.
3
9
S
t
a
g
e
2
1
3
.
5
3
1
3
.
0
1
1
0
.
6
9
1
9
.
9
2
1
5
.
8
3
1
4
.
4
8
1
4
.
5
8
S
t
a
g
e
3
1
1
.
2
1
1
0
.
8
2
7
.
9
9
1
3
.
9
4
1
4
.
9
1
1
1
.
9
0
1
1
.
8
0
S
t
a
g
e
4
1
3
.
5
3
1
0
.
1
5
7
.
1
0
1
1
.
6
3
1
3
.
4
3
1
0
.
7
6
1
1
.
1
1
S
t
a
g
e
5
1
1
.
8
7
1
0
.
3
1
8
.
5
5
1
1
.
2
1
1
3
.
3
0
1
0
.
7
8
1
1
.
0
0
S
t
a
g
e
6
1
1
.
7
9
1
0
.
3
4
8
.
4
0
1
1
.
6
8
1
3
.
2
5
1
1
.
2
0
1
1
.
1
1
T
ab
le
2
.
Selecte
d
co
n
f
ig
u
r
atio
n
o
f
L
SS
VM
-
B
F
O
A
f
o
r
Ho
u
r
-
Ah
ea
d
Fo
r
ec
ast
T
e
st
d
a
t
a
W
e
e
k
1
W
e
e
k
2
W
e
e
k
3
W
e
e
k
4
W
e
e
k
5
W
e
e
k
6
S
20
20
20
20
16
20
N
c
50
1
0
0
50
50
50
50
N
s
5
N
re
4
N
ed
2
p
ed
0
.
2
5
G
a
mm
a
5
.
2
1
1
5
.
7
2
1
6
.
2
2
1
8
.
5
3
0
.
8
5
1
.
5
4
S
i
g
ma
0
.
9
9
2
.
2
4
7
.
6
2
1
0
.
3
0
1
.
0
7
2
.
9
8
S
e
l
e
c
t
e
d
F
e
a
t
u
r
e
s
17
22
22
16
22
22
R
e
g
r
e
ssi
o
n
(
R
)
0
.
8
1
0
.
8
9
0
.
8
8
0
.
9
3
0
.
8
0
0
.
8
5
M
A
E
5
.
5
4
5
.
0
1
4
.
4
8
5
.
0
0
9
.
3
7
7
.
1
8
T
ab
le
3
.
MA
P
E
f
o
r
Ho
u
r
-
Ah
e
ad
Fo
r
ec
ast
in
th
e
O
n
tar
io
E
lectr
icit
y
Ma
r
k
e
t
R
e
f
.
Y
e
a
r
M
e
t
h
o
d
T
e
st
w
e
e
k
A
v
e
r
a
g
e
M
A
P
E
1
2
3
4
5
6
L
S
S
V
M
-
B
F
O
A
1
1
.
8
7
1
0
.
3
1
8
.
5
5
1
1
.
2
1
1
3
.
3
0
1
0
.
7
8
1
1
.
0
0
[
3
0
]
2
0
1
6
L
S
S
V
M
-
GA
7
.
5
5
7
.
4
5
5
.
5
5
7
.
8
8
7
.
2
1
8
.
7
7
7
.
4
0
[
4
]
2
0
1
3
R
N
N
+
e
x
c
i
t
a
b
l
e
d
y
n
a
mi
c
s
1
0
.
7
6
9
.
1
2
1
1
.
6
1
1
0
.
4
5
[
6
]
2
0
1
1
R
N
N
-
Ex
p
e
c
t
a
t
i
o
n
M
a
x
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m (RN
N
-
E
M
)
1
5
.
0
9
1
5
.
1
6
1
0
.
5
2
1
0
.
2
1
1
5
.
7
8
1
5
.
7
1
1
3
.
7
2
R
N
N
-
Ex
t
e
n
d
e
d
K
a
l
man
F
i
l
t
e
r
(
R
N
N
-
EK
F
)
1
6
.
0
1
1
6
.
5
4
1
1
.
8
9
1
1
.
9
6
1
6
.
5
9
1
6
.
4
5
1
4
.
9
1
M
L
P
-
E
K
F
1
6
.
8
3
1
6
.
7
4
1
2
.
6
4
1
5
.
2
5
1
6
.
7
7
1
6
.
9
6
1
5
.
8
7
M
L
P
-
EM
1
5
.
4
8
1
5
.
3
9
1
1
.
8
7
1
2
.
0
7
1
6
.
7
8
1
6
.
7
3
1
4
.
7
2
[
1
]
2
0
0
6
M
A
R
S
(
c
a
se
1
)
1
3
.
3
1
2
.
9
9
.
4
1
4
.
4
1
2
.
9
1
5
.
5
1
3
.
0
7
M
A
R
S
(
c
a
se
2
)
1
2
.
5
1
2
.
3
8
.
6
1
1
.
7
1
1
.
8
1
3
.
9
1
1
.
8
0
I
ESO
2
3
.
7
8
2
5
.
2
6
1
0
.
4
1
1
6
.
2
2
2
2
.
0
6
2
3
.
5
1
2
0
.
2
1
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
Ho
u
r
A
h
e
a
d
E
lectricity P
r
ice
F
o
r
ec
a
s
tin
g
w
it
h…
(
I
n
ta
n
A
z
mir
a
W
a
n
A
b
d
u
l R
a
z
a
k
)
753
5.
CO
NCLU
SI
O
N
I
n
t
h
e
f
ield
o
f
elec
tr
icit
y
p
r
ice
f
o
r
ec
asti
n
g
,
ac
c
u
r
ac
y
o
f
t
h
e
p
r
ed
ictio
n
i
s
t
h
e
m
ain
i
s
s
u
e.
Nev
er
th
e
less
,
p
r
ed
icti
v
e
m
o
d
els
w
it
h
h
i
g
h
p
r
ec
is
io
n
u
s
u
al
l
y
n
ee
d
a
m
o
r
e
co
m
p
le
x
m
o
d
el
s
tr
u
ct
u
r
e
.
A
p
ar
t
f
r
o
m
t
h
at,
s
elec
tio
n
o
f
f
ea
t
u
r
es
an
d
p
ar
a
m
eter
ar
e
als
o
im
p
o
r
tan
t
tas
k
s
d
u
r
i
n
g
t
h
e
f
o
r
ec
ast
m
o
d
el
d
ev
elo
p
m
en
t.
He
n
ce
,
a
h
y
b
r
id
m
o
d
el
o
f
L
SS
VM
-
B
FO
A
f
o
r
ho
ur
-
ah
ea
d
elec
tr
icit
y
p
r
ice
f
o
r
ec
ast
w
a
s
d
ev
elo
p
ed
in
th
is
s
t
u
d
y
.
B
FOA
co
m
p
lete
s
b
o
th
f
ea
tu
r
e
an
d
L
S
SVM
p
ar
a
m
eter
o
p
ti
m
izati
o
n
s
s
i
m
u
ltan
eo
u
s
l
y
.
T
h
r
o
u
g
h
s
ev
er
al
lev
e
ls
o
f
o
p
ti
m
izatio
n
,
t
h
e
a
m
o
u
n
t
o
f
i
n
p
u
ts
to
b
e
f
ed
i
n
to
t
h
e
L
SS
V
M
s
tr
u
c
tu
r
e
w
i
ll
b
e
r
ed
u
ce
d
a
n
d
at
th
e
s
a
m
e
ti
m
e
th
e
v
al
u
e
o
f
t
h
e
L
SS
VM
p
ar
a
m
eter
is
r
ef
i
n
ed
.
A
lt
h
o
u
g
h
t
h
e
ac
cu
r
ac
y
o
f
th
e
L
S
SVM
-
B
FO
A
i
s
s
li
g
h
tl
y
lo
w
er
t
h
an
th
e
p
r
ev
io
u
s
b
est
m
o
d
el
s
,
th
e
d
ev
elo
p
ed
m
o
d
el
s
h
o
w
s
s
i
m
p
ler
s
tr
u
ctu
r
e
an
d
p
r
o
v
id
es
b
etter
MA
P
E
th
an
m
o
s
t
o
f
th
e
ex
is
ti
n
g
m
o
d
el
s
in
th
e
O
n
tar
io
p
o
w
er
m
ar
k
e
t.
I
n
ad
d
itio
n
,
u
n
til
r
ec
en
tl
y
,
n
o
s
t
u
d
y
h
a
s
i
n
v
e
s
ti
g
ated
th
e
ap
p
licatio
n
o
f
B
FO
A
in
elec
tr
icit
y
p
r
ice
f
o
r
ec
asti
n
g
.
T
h
is
co
n
tr
ib
u
tio
n
ca
n
h
elp
m
ar
k
et
m
e
m
b
er
s
to
b
id
ef
f
ec
ti
v
el
y
,
m
ai
n
tai
n
e
f
f
ic
ien
t
d
ail
y
o
p
er
atio
n
s
,
a
n
d
u
lti
m
atel
y
i
n
cr
ea
s
e
t
h
e
co
m
p
a
n
y
's
p
r
o
f
its
.
T
h
er
ef
o
r
e,
s
o
m
e
r
ef
i
n
e
m
en
t
a
n
d
m
o
d
if
icatio
n
o
n
th
e
L
S
SVM
-
B
FO
A
m
o
d
el
co
u
ld
b
e
p
er
f
o
r
m
ed
in
f
u
tu
r
e
to
r
ed
u
ce
th
e
f
o
r
ec
ast
er
r
o
r
.
T
h
e
f
o
r
ec
ast
ac
cu
r
ac
y
m
a
y
b
e
en
h
a
n
ce
d
b
y
p
r
o
p
er
s
elec
tio
n
o
f
th
eir
p
ar
a
m
e
ter
s
s
u
c
h
as
t
h
e
n
u
m
b
er
o
f
b
ac
ter
ia
(
S
)
,
n
u
m
b
er
o
f
ch
e
m
o
tactic
s
tep
s
(
N
c
)
,
n
u
m
b
er
o
f
s
tep
s
tak
en
d
u
r
i
n
g
s
w
i
m
m
i
n
g
(
N
s
)
,
n
u
m
b
er
o
f
r
ep
r
o
d
u
ctio
n
s
tep
s
(
N
re
)
,
n
u
m
b
er
o
f
eli
m
i
n
atio
n
-
d
is
p
er
s
al
s
tep
s
(
N
ed
)
,
p
r
o
b
a
b
ilit
y
o
f
eli
m
i
n
atio
n
-
d
is
p
er
s
al
(
p
ed
)
,
attr
ac
tan
t d
ep
th
(
d
at
tract
)
,
an
d
attr
ac
tan
t
w
id
th
(
w
attr
act
)
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
s
t
u
d
y
i
s
s
u
p
p
o
r
ted
in
p
ar
t
b
y
t
h
e
S
h
o
r
t
T
er
m
Gr
an
t
(
P
J
P
)
p
r
o
v
id
ed
b
y
U
n
i
v
er
s
it
i
T
ek
n
ik
a
l
Ma
la
y
s
ia,
Me
la
k
a
(
P
J
P
/
2
0
1
5
/
FKE(
2
A
)
/S0
1
4
0
0
)
.
W
e
w
o
u
l
d
lik
e
to
d
ed
icate
o
u
r
ap
p
r
ec
iatio
n
to
U
n
i
v
er
s
it
i
T
ek
n
ik
al
Ma
la
y
s
ia,
Me
lak
a
(
UT
eM
)
f
o
r
p
r
o
v
id
in
g
f
in
a
n
ci
al
an
d
m
o
r
al
s
u
p
p
o
r
t
t
h
r
o
u
g
h
o
u
t
co
n
d
u
cti
n
g
t
h
is
s
tu
d
y
RE
F
E
R
E
NC
E
S
[1
]
H.
Zare
ip
o
u
r,
K
.
Bh
a
tt
a
c
h
a
ry
a
,
a
n
d
C
.
a
.
Ca
n
iza
re
s,
“
Fo
re
c
a
sti
n
g
th
e
h
o
u
rly
On
t
a
rio
e
n
e
rg
y
p
ric
e
b
y
mu
lt
iv
a
ria
te
a
d
a
p
ti
v
e
re
g
re
ss
io
n
sp
li
n
e
s,”
i
n
2
0
0
6
IEE
E
P
o
w
e
r
En
g
in
e
e
rin
g
S
o
c
iety
Ge
n
e
ra
l
M
e
e
ti
n
g
,
2
0
0
6
,
p
p
.
1
–
7.
[2
]
K.
B.
S
a
h
a
y
,
“
On
e
h
o
u
r
a
h
e
a
d
p
ric
e
fo
re
c
a
st
o
f
On
t
a
rio
e
lec
tricity
ma
rk
e
t
b
y
u
si
n
g
ANN
,
”
i
n
2
0
1
5
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
E
n
e
rg
y
Eco
n
o
m
ic
s a
n
d
E
n
v
iro
n
m
e
n
t
(ICEE
E
)
,
2
0
1
5
,
p
p
.
1
–
6.
[3
]
A
.
M
a
teo
,
A
.
M
u
ñ
o
z
,
a
n
d
J.
G
a
rc
ía
-
G
o
n
z
á
lez
,
“
M
o
d
e
li
n
g
a
n
d
F
o
re
c
a
stin
g
El
e
c
tri
c
it
y
P
rice
s
w
it
h
In
p
u
t/
Ou
t
p
u
t
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
ls,”
IEE
E
T
ra
n
s.
P
o
we
r S
y
st.
,
v
o
l.
2
0
,
n
o
.
1
,
p
p
.
1
3
–
2
4
,
2
0
0
5
.
[4
]
V
.
S
h
a
rm
a
a
n
d
D.
S
rin
iv
a
sa
n
,
“
A
h
y
b
rid
in
telli
g
e
n
t
m
o
d
e
l
b
a
se
d
o
n
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
s
a
n
d
e
x
c
it
a
b
le
d
y
n
a
m
ics
f
o
r
p
rice
p
re
d
icti
o
n
in
d
e
re
g
u
late
d
e
lec
tri
c
it
y
m
a
r
k
e
t,
”
En
g
.
A
p
p
l.
Art
if
.
I
n
tell.
,
v
o
l.
2
6
,
n
o
.
5
–
6
,
p
p
.
1
5
6
2
–
1
5
7
4
,
2
0
1
3
.
[5
]
L
.
W
u
a
n
d
M
.
S
h
a
h
i
d
e
h
p
o
u
r,
“
A
H
y
b
rid
M
o
d
e
l
f
o
r
Da
y
-
A
h
e
a
d
P
rice
F
o
re
c
a
stin
g
,
”
IEE
E
T
ra
n
s.
Po
we
r
S
y
st
,
v
o
l.
2
5
,
n
o
.
3
,
p
p
.
1
5
1
9
–
1
5
3
0
,
2
0
1
0
.
[6
]
D.
M
iri
k
it
a
n
i
a
n
d
N.
Nik
o
lae
v
,
“
No
n
li
n
e
a
r
m
a
x
i
m
u
m
li
k
e
li
h
o
o
d
e
stim
a
ti
o
n
o
f
e
lec
tri
c
it
y
sp
o
t
p
rice
s
u
sin
g
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
s,”
Ne
u
ra
l
C
o
m
p
u
t
.
Ap
p
l.
,
v
o
l.
2
0
,
n
o
.
1
,
p
p
.
7
9
–
8
9
,
F
e
b
.
2
0
1
1
.
[7
]
J.
F
.
G
.
d
e
F
re
it
a
s,
M
.
Nira
n
jan
,
a
n
d
A
.
H.
Ge
e
,
“
D
y
n
a
m
i
c
lea
rn
in
g
w
it
h
th
e
EM
a
lg
o
rit
h
m
f
o
r
n
e
u
ra
l
n
e
tw
o
rk
s,”
J
.
VL
S
I
S
ig
n
a
l
Pro
c
e
ss
.
,
v
o
l.
2
6
,
n
o
.
1
/2
,
p
p
.
1
1
9
–
1
3
1
,
2
0
0
0
.
[8
]
C.
M
a
n
d
B.
L
,
“
S
im
p
le
re
c
u
rre
n
t
n
e
tw
o
rk
train
e
d
b
y
RT
RL
a
n
d
e
x
ten
d
e
d
Ka
lm
a
n
f
il
ter
a
lg
o
rit
h
m
s,
”
Ne
u
ra
l
Ne
tw.
W
o
rld
,
v
o
l.
1
3
,
n
o
.
3
,
p
p
.
2
2
3
–
2
3
4
,
2
0
0
3
.
[9
]
S
.
A
n
b
a
z
h
a
g
a
n
,
“
Da
y
-
Ah
e
a
d
Price
Fo
re
c
a
stin
g
i
n
Asi
a
â
€
TM
S
F
irst
L
i
b
e
ra
li
ze
d
El
e
c
tricity
M
a
rk
e
t
Us
in
g
Art
if
icia
l
Ne
u
ra
l
Ne
two
rk
s
,
”
in
S
e
c
o
n
d
In
t
e
rn
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
u
sta
in
a
b
le
En
e
rg
y
a
n
d
In
telli
g
e
n
t
S
y
st
e
m
(S
EIS
CON
2
0
1
1
)
,
2
0
1
1
,
v
o
l.
4
,
n
o
.
4
,
p
p
.
4
7
6
–
4
8
5
.
[1
0
]
S
.
A
n
b
a
z
h
a
g
a
n
a
n
d
N.
Ku
m
a
r
a
p
p
a
n
,
“
Da
y
-
a
h
e
a
d
d
e
re
g
u
la
ted
e
l
e
c
tricity
ma
rk
e
t
p
ric
e
fo
re
c
a
sti
n
g
u
sin
g
n
e
u
ra
l
n
e
two
rk
in
p
u
t
fea
t
u
re
d
b
y
DC
T
,
”
En
e
rg
y
Co
n
v
e
rs.
M
a
n
a
g
.
,
v
o
l.
7
8
,
p
p
.
7
1
1
–
7
1
9
,
2
0
1
4
.
[1
1
]
S
.
A
n
b
a
z
h
a
g
a
n
a
n
d
N.
K
u
m
a
ra
p
p
a
n
,
“
A
n
e
u
ra
l
n
e
tw
o
rk
a
p
p
ro
a
c
h
to
d
a
y
-
a
h
e
a
d
d
e
re
g
u
late
d
e
lec
tri
c
it
y
m
a
r
k
e
t
p
rice
s c
las
sif
i
c
a
ti
o
n
,
”
El
e
c
tr.
P
o
w
e
r S
y
st.
Res
.
,
v
o
l.
8
6
,
p
p
.
1
4
0
–
1
5
0
,
2
0
1
2
.
[1
2
]
V
.
P
.
S
a
k
th
iv
e
l,
R.
Bh
u
v
a
n
e
sw
a
ri,
a
n
d
S
.
S
u
b
ra
m
a
n
ian
,
“
De
si
g
n
o
p
ti
m
iza
ti
o
n
o
f
th
re
e
-
p
h
a
se
e
n
e
rg
y
e
ff
icie
n
t
in
d
u
c
ti
o
n
m
o
to
r
u
sin
g
a
d
a
p
ti
v
e
b
a
c
teria
l
f
o
ra
g
in
g
a
lg
o
rit
h
m
,
”
C
OM
PE
L
In
t.
J
.
Co
mp
u
t.
M
a
th
.
El
e
c
tr.
El
e
c
tro
n
.
En
g
.
,
v
o
l.
2
9
,
n
o
.
3
,
p
p
.
6
9
9
–
7
2
6
,
2
0
1
0
.
[1
3
]
R.
Ja
k
h
a
r,
N.
Ka
u
r,
a
n
d
R.
S
in
g
h
,
“
F
a
c
e
Re
c
o
g
n
it
io
n
Us
in
g
Ba
c
teria
F
o
ra
g
in
g
Op
ti
m
iz
a
ti
o
n
-
Ba
se
d
S
e
lec
ted
F
e
a
tu
re
s,”
In
t.
J
.
Ad
v
.
C
o
mp
u
t.
S
c
i.
Ap
p
l.
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
1
0
6
–
1
1
1
,
2
0
1
1
.
[1
4
]
S
.
A
riv
a
la
g
a
n
a
n
d
K.
V
e
n
k
a
t
a
c
h
a
lap
a
th
y
,
“
F
a
c
e
Re
c
o
g
n
it
io
n
b
a
se
d
o
n
a
Hy
b
rid
M
e
ta
-
h
e
u
risti
c
F
e
a
tu
re
S
e
lec
ti
o
n
A
l
g
o
rit
h
m
,
”
In
t.
J
.
C
o
mp
u
t.
A
p
p
l
.
,
v
o
l.
5
5
,
n
o
.
1
7
,
p
p
.
1
8
–
2
2
,
2
0
1
2
.
[1
5
]
M
.
Ka
rn
a
n
a
n
d
N
.
Krish
n
a
ra
j,
“
A
M
o
d
e
l
to
S
e
c
u
re
M
o
b
il
e
De
v
ice
s
Us
in
g
Ke
y
stro
k
e
D
y
n
a
m
i
c
s
th
ro
u
g
h
S
o
f
t
Co
m
p
u
ti
n
g
T
e
c
h
n
iq
u
e
s,”
I
n
t.
J
.
S
o
ft
C
o
mp
u
t.
E
n
g
.
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
7
1
–
7
5
,
2
0
1
2
.
[1
6
]
K.
M
.
Ba
k
w
a
d
,
S
.
S
.
P
a
tt
n
a
ik
,
B.
S
.
S
o
h
i
,
S
.
De
v
i,
B.
K.
P
a
n
i
g
ra
h
i,
a
n
d
S
.
V
.
R.
S
.
G
o
ll
a
p
u
d
i,
“
M
u
lt
im
o
d
a
l
F
u
n
c
ti
o
n
O
p
ti
m
iza
ti
o
n
Us
in
g
S
y
n
c
h
ro
n
o
u
s
Ba
c
teria
l
F
o
ra
g
in
g
Op
ti
m
iza
ti
o
n
T
e
c
h
n
iq
u
e
,
”
IET
E
J
.
R
e
s.
,
v
o
l.
5
6
,
p
p
.
80
–
8
7
,
2
0
1
0
.
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.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
4
8
–
7
5
5
754
[1
7
]
A
.
Ka
sa
i
e
z
a
d
e
h
,
A
.
Kh
a
jep
o
u
r,
a
n
d
S
.
L
.
W
a
sla
n
d
e
r,
“
S
p
ira
l
Ba
c
ter
ia
l
Fo
r
a
g
i
n
g
Op
ti
miz
a
ti
o
n
me
t
h
o
d
,
”
i
n
P
r
o
c
e
e
d
in
g
s o
f
th
e
2
0
1
0
A
m
e
rica
n
Co
n
tro
l
Co
n
f
e
re
n
c
e
,
2
0
1
0
,
p
p
.
4
8
4
5
–
4
8
5
0
.
[1
8
]
B.
D.
a
n
d
B.
D.
S
.
A
.
V
.
S
.
S
re
e
d
h
a
r
Ku
m
a
r,
V
.
V
e
e
ra
n
n
a
,
“
A
M
AT
LAB
G
UI
T
o
o
l
f
o
r
Op
ti
m
iza
ti
o
n
o
f
F
M
S
S
c
h
e
d
u
l
in
g
u
sin
g
Co
n
v
e
n
ti
o
n
a
l
a
n
d
Ev
o
lu
t
io
n
a
ry
A
p
p
ro
a
c
h
e
s,”
In
t.
J
.
Cu
rr
.
En
g
.
T
e
c
h
n
o
l
.
,
v
o
l.
3
,
n
o
.
5
,
p
p
.
1
7
3
9
–
1
7
4
4
,
2
0
1
3
.
[1
9
]
E.
S
.
A
li
a
n
d
S
.
M
.
A
b
d
-
E
laz
im
,
“
H
y
b
rid
BF
OA
-
PS
O
a
p
p
ro
a
c
h
fo
r
S
S
S
C
d
a
m
p
in
g
c
o
n
tro
ll
e
r
d
e
sig
n
,
”
2
0
1
3
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
tro
l,
De
c
isio
n
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(Co
DIT
)
.
Ie
e
e
,
p
p
.
4
6
4
–
4
6
9
,
M
a
y
-
2
0
1
3
.
[2
0
]
S
.
P
a
n
d
a
,
D
.
M
ish
ra
,
B.
B.
Bis
w
a
l,
a
n
d
M
.
T
rip
a
th
y
,
“
Re
v
o
lu
te
m
a
n
ip
u
lato
r
w
o
rk
sp
a
c
e
o
p
ti
m
iza
ti
o
n
u
sin
g
a
m
o
d
if
ied
b
a
c
teria
f
o
ra
g
in
g
a
lg
o
rit
h
m
:
A
c
o
m
p
a
r
a
ti
v
e
stu
d
y
,
”
En
g
.
Op
ti
m.
,
v
o
l
.
4
6
,
p
p
.
1
8
1
–
1
9
9
,
2
0
1
3
.
[2
1
]
M
.
Ula
g
a
m
m
a
i,
P
.
V
e
n
k
a
tes
h
,
P
.
S
.
Ka
n
n
a
n
,
a
n
d
N.
P
ra
sa
d
P
a
d
h
y
,
“
A
p
p
li
c
a
ti
o
n
o
f
b
a
c
teria
l
f
o
ra
g
in
g
tec
h
n
iq
u
e
train
e
d
a
rti
f
icia
l
a
n
d
w
a
v
e
let
n
e
u
ra
l
n
e
tw
o
rk
s in
lo
a
d
f
o
re
c
a
stin
g
,
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l
.
7
0
,
p
p
.
2
6
5
9
–
2
6
6
7
,
2
0
0
7
.
[2
2
]
Y.
L
i,
“
S
h
o
rt
-
T
e
rm
L
o
a
d
Fo
re
c
a
s
ti
n
g
Ba
se
d
o
n
L
S
-
S
VM
Op
ti
mize
d
b
y
BCC
Al
g
o
rit
h
m
,
”
in
2
0
0
9
1
5
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
telli
g
e
n
t
S
y
ste
m
A
p
p
li
c
a
ti
o
n
s t
o
P
o
w
e
r
S
y
ste
m
s
,
2
0
0
9
,
n
o
.
2
,
p
p
.
1
–
5.
[2
3
]
Z.
B.
S
h
i,
Y.
L
i,
a
n
d
T
.
Yu
,
“
S
h
o
rt
-
ter
m
lo
a
d
f
o
re
c
a
stin
g
b
a
s
e
d
o
n
L
S
-
S
VM
o
p
ti
mize
d
b
y
b
a
c
ter
ia
l
c
o
lo
n
y
c
h
e
mo
ta
x
is
a
lg
o
rith
m
,
”
in
2
0
0
9
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
f
o
r
m
a
ti
o
n
a
n
d
M
u
lt
im
e
d
ia
T
e
c
h
n
o
l
o
g
y
,
I
CIM
T
2
0
0
9
,
2
0
0
9
,
n
o
.
3
,
p
p
.
3
0
6
–
3
0
9
.
[2
4
]
V
.
Ho
o
a
n
d
J.
Ha
n
,
“
S
o
u
th
C
h
in
a
L
o
a
d
F
o
re
c
a
stin
g
b
a
se
d
o
n
BF
O,”
Ad
v
.
In
f
.
T
e
c
h
n
o
l.
a
n
d
M
a
n
a
g
e
me
n
t
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
3
3
–
3
7
,
2
0
1
2
.
[2
5
]
Y.
Zh
a
n
g
,
L
.
W
u
,
a
n
d
S
.
W
a
n
g
,
“
Ba
c
teria
l
F
o
ra
g
in
g
Op
ti
m
iz
a
ti
o
n
Ba
se
d
Ne
u
ra
l
Ne
t
w
o
rk
f
o
r
S
h
o
rt
-
term
L
o
a
d
F
o
re
c
a
stin
g
,
”
J
.
Co
mp
u
t.
I
n
f.
S
y
st
.
,
v
o
l.
7
,
p
p
.
2
0
9
9
–
2
1
0
5
,
2
0
1
0
.
[2
6
]
G
.
X
ie,
S
.
W
a
n
g
,
Y.
Z
h
a
o
,
a
n
d
K.
K.
L
a
i,
“
Hy
b
rid
a
p
p
r
o
a
c
h
e
s
b
a
se
d
o
n
L
S
S
V
R
m
o
d
e
l
f
o
r
c
o
n
tain
e
r
t
h
ro
u
g
h
p
u
t
f
o
re
c
a
stin
g
:
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
”
Ap
p
l
.
S
o
ft
C
o
mp
u
t.
,
v
o
l.
1
3
,
n
o
.
5
,
p
p
.
2
2
3
2
–
2
2
4
1
,
M
a
y
2
0
1
3
.
[2
7
]
H.
W
a
n
g
a
n
d
D.
Hu
,
“
Co
mp
a
ri
so
n
o
f
S
VM
a
n
d
L
S
-
S
VM
fo
r
Re
g
re
ss
io
n
,
”
in
2
0
0
5
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ne
u
ra
l
Ne
tw
o
rk
s a
n
d
Bra
in
,
2
0
0
5
,
n
o
.
5
,
p
p
.
2
7
9
–
2
8
3
.
[2
8
]
S
.
L
i
a
n
d
L
.
Da
i,
“
Clas
si
f
ic
a
ti
o
n
o
f
g
a
so
li
n
e
b
ra
n
d
a
n
d
o
rig
in
b
y
Ra
m
a
n
sp
e
c
tro
sc
o
p
y
a
n
d
a
n
o
v
e
l
R
-
w
e
ig
h
ted
L
S
S
V
M
a
lg
o
rit
h
m
,
”
Fu
e
l
,
v
o
l.
9
6
,
p
p
.
1
4
6
–
1
5
2
,
Ju
n
.
2
0
1
2
.
[2
9
]
H.
Zare
ip
o
u
r
,
K.
Bh
a
tt
a
c
h
a
ry
a
,
a
n
d
C.
a
.
Ca
ñ
iza
re
s,
“
El
e
c
tri
c
it
y
m
a
rk
e
t
p
rice
v
o
latil
it
y
:
T
h
e
c
a
s
e
o
f
On
tario
,
”
En
e
rg
y
Po
l
icy
,
v
o
l.
3
5
,
n
o
.
9
,
p
p
.
4
7
3
9
–
4
7
4
8
,
S
e
p
.
2
0
0
7
.
[3
0
]
I.
A
.
W
.
A
.
Ra
z
a
k
,
I.
Z.
A
b
id
in
,
K.
S
.
Ya
p
,
A
.
A
.
Z.
A
b
id
in
,
T
.
K.
A
.
Ra
h
m
a
n
,
a
n
d
M
.
N.
M
.
Na
sir,
“
A
n
o
v
e
l
h
y
b
ri
d
me
th
o
d
o
f
L
S
S
VM
-
GA
wit
h
m
u
lt
ip
le
sta
g
e
o
p
ti
miz
a
ti
o
n
fo
r
e
lec
tricity
p
ric
e
fo
re
c
a
stin
g
,
”
in
2
0
1
6
IEE
E
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
P
o
w
e
r
a
n
d
E
n
e
rg
y
(P
EC
o
n
)
,
2
0
1
6
,
p
p
.
3
9
0
–
3
9
5
.
[3
1
]
K.
P
ra
b
a
a
k
a
ra
n
,
S
.
Ja
isiv
a
,
A
.
S
e
l
v
a
k
u
m
a
r,
a
n
d
K.
S
.
Ku
m
a
r,
“
I
m
p
lem
e
n
tatio
n
o
f
Ba
c
teria
l
F
o
ra
g
in
g
A
lg
o
rit
h
m
f
o
r
En
h
a
n
c
i
n
g
Vo
lt
a
g
e
P
r
o
f
il
e
a
n
d
L
o
ss
M
in
im
iza
ti
o
n
u
sin
g
S
tatic
V
a
r
Co
m
p
e
n
sa
to
r,
”
In
t.
J
.
Res
.
De
v
.
En
g
.
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
4
3
–
5
0
,
2
0
1
3
.
[3
2
]
P
.
K.
M
a
jh
i,
R.
;
Bh
u
b
a
n
e
sw
a
r ;
P
a
n
d
a
,
G
.
;
S
a
h
o
o
,
G
.
;
Da
sh
,
“
S
to
c
k
ma
rk
e
t
p
re
d
ictio
n
o
f
S
&
P
5
0
0
a
n
d
DJ
IA
u
sin
g
Ba
c
ter
ia
l
F
o
ra
g
in
g
Op
ti
miza
ti
o
n
T
e
c
h
n
iq
u
e
,
”
in
IE
EE
Co
n
g
re
ss
o
n
Ev
o
l
u
ti
o
n
a
ry
Co
m
p
u
tatio
n
,
2
0
0
7
,
p
p
.
2
5
6
9
–
2
5
7
5
.
[3
3
]
J.
Da
n
g
,
A
.
Br
a
b
a
z
o
n
,
M
.
O.
Ne
il
l,
a
n
d
D.
Ed
e
lm
a
n
,
“
Op
ti
o
n
M
o
d
e
l
Ca
li
b
ra
ti
o
n
Us
in
g
a
Ba
c
teria
l
F
o
ra
g
in
g
Op
ti
m
iza
ti
o
n
A
lg
o
rit
h
m
,
”
in
Ap
p
l
ica
ti
o
n
s o
f
Evo
l
u
ti
o
n
a
ry
Co
mp
u
ti
n
g
,
2
0
0
8
,
p
p
.
1
1
3
–
1
2
2
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
In
tan
A
z
m
ira
Wan
A
b
d
u
l
Ra
z
a
k
re
c
e
iv
e
d
th
e
B.
S
c
.
d
e
g
re
e
in
E
lec
tri
c
a
l
E
n
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
sia
M
e
lak
a
(U
T
e
M
)
,
M
a
la
y
sia
in
2
0
0
6
,
c
o
m
p
lete
d
h
e
r
M
a
ste
r
e
n
g
in
e
e
rin
g
stu
d
ies
in
El
e
c
tri
c
a
l
-
P
o
w
e
r
a
t
Un
iv
e
rsit
i
T
e
k
n
o
lo
g
i
M
a
la
y
sia
(U
T
M
)
in
2
0
0
8
a
n
d
P
h
D f
ro
m
T
h
e
Na
ti
o
n
a
l
En
e
rg
y
U
n
iv
e
rsity
(UN
I
T
EN),
M
a
la
y
sia
in
2
0
1
7
.
Cu
rre
n
tl
y
s
he
w
o
rk
s
a
s
se
n
io
r
lec
tu
re
r
a
t
In
d
u
strial
P
o
w
e
r
De
p
a
rt
m
e
n
t
a
t
th
e
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
t
U
T
e
M
.
He
r
m
a
in
in
tere
st i
s
p
o
w
e
r
s
y
ste
m
p
lan
n
in
g
a
n
d
o
p
ti
m
iza
ti
o
n
.
Iz
h
a
m
Zain
a
l
A
b
id
in
re
c
e
iv
e
d
t
h
e
Ord
i
n
a
ry
Na
ti
o
n
a
l
Dip
l
o
m
a
in
E
n
g
in
e
e
rin
g
f
ro
m
Co
v
e
n
tr
y
T
e
c
h
n
ica
l
Co
ll
e
g
e
in
1
9
9
4
,
B.
E
n
g
in
El
e
c
tri
c
a
l
En
g
in
e
e
r
in
g
f
ro
m
Un
iv
e
rsit
y
o
f
S
o
u
th
a
m
p
to
n
i
n
1
9
9
7
,
a
n
d
P
h
D
i
n
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
(
P
o
w
e
r)
f
ro
m
S
trath
c
l
y
d
e
Un
iv
e
rsity
in
2002
.
Cu
rre
n
tl
y
h
e
is
p
ro
f
e
ss
o
r
a
t
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
a
t
UN
I
T
EN
.
His
m
a
in
in
tere
st i
s
p
o
we
r
s
y
ste
m
a
n
a
l
y
sis
a
n
d
sta
b
il
it
y
.
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
Ho
u
r
A
h
e
a
d
E
lectricity P
r
ice
F
o
r
ec
a
s
tin
g
w
it
h…
(
I
n
ta
n
A
z
mir
a
W
a
n
A
b
d
u
l R
a
z
a
k
)
755
Ya
p
Ke
e
m
S
iah
re
c
e
iv
e
d
B.
En
g
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
(Ho
n
s)
f
ro
m
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
a
la
y
sia
(U
T
M
)
in
1
9
9
8
,
M
a
ste
r
o
f
En
g
in
e
e
rin
g
(El
e
c
tri
c
a
l)
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
(U
T
M
)
in
2
0
0
0
,
a
n
d
P
h
D
f
ro
m
Un
iv
e
rsiti
S
a
in
s
M
a
la
y
sia
(USM
)
in
20
10
.
C
u
rre
n
t
ly
h
e
is
p
ro
f
e
ss
o
r
a
t
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
t
UN
IT
EN
.
His
m
a
in
in
tere
st
s
a
re
c
o
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
a
n
d
sig
n
a
l
p
ro
c
e
ss
in
g
.
A
id
il
A
z
w
in
Zain
u
l
A
b
id
i
n
re
c
e
i
v
e
d
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
El
e
c
tr
ica
l
En
g
in
e
e
rin
g
f
ro
m
In
d
ian
a
Un
iv
e
rsit
y
P
e
rd
u
e
Un
iv
e
rsity
In
d
ian
a
p
o
li
s
in
1
9
9
9
,
M
a
ste
rs
in
E
lec
tri
c
a
l
E
n
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsiti
T
e
n
a
g
a
Na
sio
n
a
l
in
2
0
0
5
,
a
n
d
P
h
D
i
n
E
n
g
i
n
e
e
rin
g
f
ro
m
UN
IT
EN
in
2012
.
C
u
rre
n
tl
y
h
e
is
se
n
io
r
lec
tu
re
r
a
t
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
t
UN
IT
EN
.
His
m
a
in
in
tere
st
s
a
re
re
n
e
wa
b
le
e
n
e
rg
y
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
.
T
it
ik
Kh
a
w
a
A
b
d
u
l
Ra
h
m
a
n
is
a
P
r
o
f
e
ss
o
r
in
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
.
He
r
m
a
in
in
tere
st
s
a
re
P
o
w
e
r
S
y
ste
m
Op
e
ra
ti
o
n
a
n
d
A
rti
f
icia
l
In
telli
g
e
n
c
e
A
p
p
li
c
a
ti
o
n
.
Nu
rli
y
a
n
a
Ba
h
a
rin
re
c
e
i
v
e
d
B.
En
g
.
(El
e
c
tri
c
a
l)
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
lay
sia
(
U
T
M
)
a
n
d
M
.
En
g
.
in
E
lec
tri
c
a
l
En
g
in
e
e
ri
n
g
,
UN
IT
EN
.
Cu
rre
n
tl
y
sh
e
is
lec
tu
re
r
a
t
UT
e
M
.
He
r
m
a
in
in
tere
st
s
a
re
p
o
w
e
r
s
y
ste
m
a
n
a
l
y
s
is an
d
p
o
w
e
r
q
u
a
li
ty
.
M
o
h
d
Ha
f
iz
Ja
li
re
c
e
iv
e
d
B.
S
c
.
d
e
g
re
e
in
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ic
e
n
g
in
e
e
rin
g
w
it
h
f
irst
c
las
s
h
o
n
o
u
rs
f
ro
m
M
A
R
A
Un
iv
e
rsit
y
o
f
T
e
c
h
n
o
lo
g
y
(UiT
M
),
M
a
la
y
s
ia
in
2
0
0
7
a
n
d
c
o
m
p
lete
d
h
is
M
a
ste
r
e
n
g
in
e
e
rin
g
stu
d
ies
w
it
h
d
isti
n
c
ti
o
n
in
In
d
u
str
ial
El
e
c
tro
n
i
c
s
a
n
d
C
o
n
tr
o
l
a
t
Un
iv
e
rsity
o
f
M
a
la
y
a
(UM)
,
M
a
la
y
sia
.
He
wa
s
w
it
h
th
e
a
u
to
m
o
ti
v
e
c
o
m
p
a
n
y
,
P
ro
to
n
S
d
n
.
Bh
d
f
ro
m
2
0
0
7
t
o
2
0
1
0
a
s a
Tes
t
En
g
in
e
e
r
u
n
d
e
r
t
h
e
Co
m
p
lete
V
e
h
icle
Tes
ti
n
g
(CV
T)
d
e
p
a
rtm
e
n
t.
In
2
0
1
2
,
h
e
w
a
s
a
p
p
o
i
n
ted
a
s
a
L
e
c
tu
re
r
a
t
Un
iv
e
rsiti
Tek
n
ik
a
l
M
a
la
y
sia
M
e
la
k
a
(U
T
e
M
),
M
a
la
y
sia
.
He
is
c
u
rre
n
tl
y
a
P
h
D stu
d
e
n
t
u
n
d
e
r
Na
n
o
tec
h
n
o
l
o
g
y
a
n
d
S
e
n
so
r
L
a
b
o
ra
t
o
ry
a
t
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
M
a
la
y
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.