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.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
1
1
6
8
~1
1
75
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs.
v
2
1
.
i
2
.
p
p
1
1
6
8
-
11
75
1168
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
M
o
dified
a
rti
ficia
l bee
c
o
lo
ny
o
pti
m
i
z
a
tion
a
lg
o
rithm
for
a
da
ptive
po
w
e
r scheduli
ng
in an
iso
la
ted
sy
ste
m
Vij
o
M
J
o
y
,
S K
rish
na
k
u
m
a
r
S
c
h
o
o
l
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s,
M
G
Un
iv
e
rsity
Re
s
e
a
rc
h
Ce
n
tre,
Ke
ra
la,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
M
ay
1
5
,
2
0
2
0
R
ev
i
s
ed
J
ul
23
,
2
0
2
0
A
cc
ep
ted
A
ug
7
,
2
0
2
0
T
h
e
o
b
jec
ti
v
e
o
f
th
is
w
o
rk
is
to
so
lv
e
th
e
p
o
w
e
r
sc
h
e
d
u
li
n
g
p
ro
b
lem
s
f
o
r
e
ff
ici
e
n
t
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
b
y
a
ss
i
g
n
in
g
th
e
o
p
ti
m
a
l
v
a
lu
e
s.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
a
re
u
se
d
w
id
e
l
y
in
t
h
e
f
ield
o
f
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
a
n
d
lo
a
d
sc
h
e
d
u
li
n
g
.
T
h
e
b
a
c
k
p
ro
p
a
g
a
ti
o
n
tec
h
n
iq
u
e
is
u
se
d
f
o
r
th
e
f
e
e
d
-
f
o
rwa
rd
n
e
u
ra
l
n
e
tw
o
rk
train
in
g
a
n
d
t
h
e
L
e
v
e
n
b
e
rg
-
M
a
rq
u
a
rd
t
a
lg
o
rit
h
m
is
u
se
d
to
m
in
i
m
ize
th
e
e
rro
rs.
T
h
e
slo
w
sp
e
e
d
o
f
c
o
n
v
e
rg
e
n
c
e
a
n
d
g
e
tt
in
g
stu
c
k
in
lo
c
a
l
m
in
i
m
a
a
r
e
so
m
e
n
e
g
a
ti
v
e
s
o
f
b
a
c
k
p
ro
p
a
g
a
ti
o
n
in
c
o
m
p
lex
c
o
m
p
u
tatio
n
.
T
o
o
v
e
rc
o
m
e
th
e
se
d
ra
w
b
a
c
k
s
a
n
in
n
o
v
a
ti
v
e
m
e
t
a
-
h
e
u
risti
c
se
a
rc
h
a
lg
o
rit
h
m
c
a
ll
e
d
m
o
d
if
ied
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
is
u
se
d
.
a
h
y
b
rid
n
e
u
ra
l
n
e
tw
o
rk
is
in
tro
d
u
c
e
d
i
n
th
is
w
o
rk
.
T
h
e
sim
u
latio
n
re
su
lt
sh
o
w
s
th
a
t
t
h
e
e
ff
icie
n
c
y
o
f
th
e
sy
ste
m
is
i
m
p
ro
v
e
d
w
h
e
n
h
y
b
rid
o
p
ti
m
iza
ti
o
n
is
u
se
d
.
W
it
h
t
h
is
m
e
th
o
d
,
t
h
e
sy
ste
m
a
c
h
iev
e
s
a
n
o
p
ti
m
a
l
a
c
c
u
ra
c
y
o
f
9
9
.
2
3
%
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
b
ee
c
o
lo
n
y
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
B
ac
k
p
r
o
p
ag
atio
n
Op
ti
m
izatio
n
P
o
w
er
s
c
h
ed
u
l
in
g
T
h
is
is
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Vij
o
M
J
o
y
Sch
o
o
l o
f
T
ec
h
n
o
lo
g
y
a
n
d
A
p
p
lied
Scien
ce
s
R
esear
ch
C
en
tr
e
Ma
h
at
m
a
Ga
n
d
h
i U
n
i
v
er
s
it
y
E
d
ap
p
ally
,
C
o
ch
in
-
2
4
,
Ker
ala,
I
n
d
ia
E
m
ail:
v
ij
o
m
j
o
y
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
an
in
ter
r
elate
d
p
o
w
er
s
y
s
te
m
,
th
e
l
o
ad
s
ch
ed
u
li
n
g
s
tr
ateg
y
i
s
co
n
ce
r
n
ed
w
ith
ac
c
u
r
ate
s
ch
ed
u
li
n
g
o
f
p
o
w
er
b
ased
o
n
th
e
p
ar
a
m
e
ter
s
li
k
e
a
v
ailab
ilit
y
,
e
x
p
en
s
e
,
an
d
o
n
-
d
e
m
a
n
d
.
P
o
w
er
g
e
n
er
atio
n
f
r
o
m
th
e
n
o
n
-
co
n
v
e
n
tio
n
al
en
er
g
y
s
o
u
r
ce
s
i
s
les
s
e
x
p
en
s
iv
e
w
h
en
co
m
p
a
r
e
d
w
it
h
o
t
h
er
p
o
w
er
s
o
u
r
ce
s
lik
e
h
y
d
r
o
elec
tr
ic,
th
er
m
a
l,
an
d
n
u
clea
r
.
I
n
t
h
is
,
m
an
y
p
ar
a
m
eter
s
ar
e
co
n
s
id
er
ed
f
o
r
th
e
g
e
n
er
atio
n
o
f
p
o
w
e
r
f
r
o
m
ea
ch
s
o
u
r
ce
[
1
]
.
T
h
e
in
te
n
s
it
y
o
f
li
g
h
t
i
s
o
n
e
o
f
t
h
e
m
aj
o
r
p
ar
am
eter
s
th
at
a
f
f
ec
t
t
h
e
r
esp
o
n
s
e
o
f
t
h
e
s
o
lar
s
y
s
te
m
.
T
h
e
h
y
d
r
o
p
o
w
er
s
tatio
n
m
ai
n
l
y
d
e
p
en
d
s
o
n
t
h
e
a
v
ailab
ilit
y
o
f
wate
r
.
T
h
at
is
,
b
o
th
p
o
w
er
s
tati
o
n
s
ar
e
a
f
f
ec
ted
b
y
w
ea
t
h
er
co
n
d
i
tio
n
s
.
I
n
a
t
h
er
m
al
p
o
w
er
s
ta
tio
n
,
it
is
n
o
t
a
f
f
ec
ted
b
y
th
e
w
ea
t
h
er
co
n
d
itio
n
s
,
b
u
t
it
s
p
r
o
d
u
ctio
n
co
s
t
is
h
i
g
h
.
I
n
t
h
e
d
e
m
a
n
d
s
id
e,
m
a
n
y
p
ar
a
m
eter
s
ar
e
co
n
s
id
er
ed
f
o
r
s
ch
ed
u
lin
g
[
2
,
3
]
.
T
y
p
e
o
f
u
s
e,
p
o
w
e
r
u
s
a
g
e
ar
ea
,
co
s
t,
p
o
p
u
latio
n
,
te
m
p
er
atu
r
e,
an
d
pr
io
r
it
y
-
b
a
s
e
d
allo
tm
e
n
t
ar
e
t
h
e
m
ai
n
p
ar
am
eter
s
co
n
s
id
er
ed
in
th
e
d
e
m
an
d
s
id
e
s
c
h
ed
u
li
n
g
[
4
]
.
A
r
tif
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
N
N)
is
th
e
b
est
ap
p
r
o
ac
h
in
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
[
5
]
.
I
t
d
esig
n
i
n
g
a
n
d
m
o
d
elin
g
is
b
ased
o
n
th
e
h
u
m
a
n
b
r
ain
co
n
ce
p
t.
Dep
en
d
in
g
o
n
t
h
e
s
tr
u
ctu
r
e
an
d
tr
ain
in
g
m
o
d
el
,
th
er
e
ar
e
m
an
y
t
y
p
e
s
o
f
ANNs
[
6
]
.
Her
e
,
b
ac
k
p
r
o
p
ag
atio
n
(
B
P
)
is
ass
u
m
ed
as
th
e
m
o
s
t
p
o
w
er
f
u
l
er
r
o
r
r
ed
u
cin
g
tec
h
n
iq
u
e.
A
h
y
b
r
id
ized
alg
o
r
it
h
m
-
A
r
ti
f
icial
B
ee
C
o
lo
n
y
-
B
ac
k
p
r
o
p
ag
atio
n
(
A
B
C
-
B
P
)
-
is
ad
o
p
te
d
f
o
r
th
e
en
h
a
n
ce
d
r
esu
lt.
I
n
I
n
d
ia
,
a
s
i
n
t
h
e
y
ea
r
2
0
1
9
,
th
e
g
r
o
s
s
in
s
talled
ca
p
ac
it
y
o
f
t
h
e
p
o
w
er
s
y
s
te
m
is
3
5
.
6
1
m
illi
o
n
k
ilo
w
att
s
.
I
n
th
i
s
,
6
4
%
m
ad
e
u
p
o
f
th
er
m
al
p
o
w
er
1
4
%
f
r
o
m
h
y
d
r
o
p
o
w
er
,
a
s
m
all
p
ar
t
o
f
n
u
clea
r
p
o
w
er
,
an
d
r
e
m
ain
in
g
f
r
o
m
o
th
er
r
en
e
w
a
b
le
p
o
w
er
s
o
u
r
ce
s
.
No
w
ad
a
y
s
,
th
e
i
m
p
o
r
tan
ce
o
f
o
p
ti
m
al
p
o
w
er
s
c
h
ed
u
li
n
g
is
a
m
aj
o
r
co
n
ce
r
n
in
t
h
e
r
esear
ch
f
ield
.
T
h
e
o
p
tim
al
p
o
w
er
s
ch
ed
u
lin
g
e
n
s
u
r
es
t
h
e
p
o
w
er
b
ased
o
n
co
s
t,
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
Mo
d
ified
a
r
tifi
cia
l b
ee
co
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
a
d
a
p
tive
p
o
w
er sch
ed
u
lin
g
…
(
V
ijo
M J
o
y
)
1169
av
ailab
ilit
y
,
a
n
d
d
e
m
an
d
.
Mo
d
er
n
an
d
in
tellect
u
al
s
o
l
u
tio
n
s
ar
e
d
ev
elo
p
ed
in
r
ec
en
t
y
ea
r
s
,
s
u
c
h
a
s
th
e
g
e
n
etic
alg
o
r
ith
m
an
d
ar
ti
f
icia
l
n
eu
r
al
n
et
w
o
r
k
,
w
h
ic
h
h
a
v
e
h
i
g
h
ac
c
u
r
ac
y
w
h
en
co
m
p
ar
ed
w
it
h
th
e
tr
ad
itio
n
al
m
et
h
o
d
s
.
T
o
s
o
lv
e
t
h
e
d
i
f
f
er
en
t
o
p
ti
m
izatio
n
p
r
o
b
le
m
s
v
ar
i
o
u
s
o
p
ti
m
izatio
n
tec
h
n
iq
u
es
b
ased
o
n
p
o
p
u
latio
n
ar
e
u
s
ed
.
B
ei
n
g
t
h
e
co
llecti
v
e
in
te
lli
g
en
t
b
eh
a
v
io
r
,
t
h
e
s
war
m
i
n
telli
g
e
n
ce
-
r
elate
d
al
g
o
r
ith
m
s
ac
h
iev
ed
t
h
e
cr
ed
itab
le
r
esu
lt.
W
h
en
s
ea
r
c
h
in
g
f
o
r
a
b
etter
s
o
u
r
ce
o
f
f
o
o
d
,
t
h
e
r
ea
l
b
ee
s
h
av
e
u
n
i
f
o
r
m
n
at
u
r
e
.
Mo
u
ti
an
d
Ha
w
ar
y
[
7
]
p
r
o
p
o
s
ed
an
A
B
C
alg
o
r
it
h
m
b
ased
o
n
t
h
e
id
en
tical
b
eh
a
v
io
r
o
f
b
ee
s
.
MA
T
L
A
B
is
u
s
ed
f
o
r
th
e
s
i
m
u
lat
io
n
.
I
n
t
h
e
p
ast
f
e
w
d
ec
ad
es
,
a
n
u
m
b
er
o
f
r
esear
c
h
er
s
en
g
a
g
ed
in
s
t
u
d
y
i
n
g
th
e
s
c
h
ed
u
lin
g
p
r
o
b
le
m
.
Ho
ta,
et
al
.
[
8
]
p
r
o
p
o
s
ed
an
ef
f
ic
ie
n
t
s
h
o
r
t
-
ter
m
h
y
d
r
o
th
er
m
al
s
ch
ed
u
li
n
g
al
g
o
r
ith
m
b
ased
o
n
t
h
e
e
v
o
lu
tio
n
ar
y
p
r
o
g
r
am
m
i
n
g
tech
n
iq
u
e
.
Si
f
u
e
n
tes
et
al
.
[
9
]
d
ev
elo
p
ed
a
L
ag
r
an
g
ia
n
r
elax
atio
n
-
b
a
s
ed
o
p
tim
izatio
n
alg
o
r
ith
m
to
d
etec
t
th
e
id
ea
l
s
o
lu
tio
n
in
h
y
d
r
o
th
er
m
al
s
c
h
ed
u
li
n
g
.
B
asu
[
10
]
h
ig
h
li
g
h
ts
a
s
i
m
p
le
an
d
ef
f
ec
ti
v
e
ap
p
r
o
ac
h
to
th
er
m
a
l
p
lan
t
s
c
h
ed
u
li
n
g
w
it
h
h
y
d
r
o
elec
tr
ic
u
n
it
s
.
I
n
th
at
w
o
r
k
o
p
ti
m
iza
tio
n
r
elat
ed
n
eu
r
al
n
et
w
o
r
k
f
o
r
m
u
latio
n
is
u
s
ed
to
d
eter
m
i
n
e
t
h
e
h
y
d
r
o
th
er
m
al
s
c
h
ed
u
lin
g
.
A
m
et
h
o
d
-
d
i
f
f
er
e
n
tial e
v
o
l
u
tio
n
-
is
p
r
o
p
o
s
ed
b
y
L
e
et
al.
[
1
1
]
to
h
an
d
le
th
e
d
is
p
atch
p
r
o
b
lem
s
i
n
th
e
h
y
d
r
o
th
er
m
al
p
o
w
er
s
y
s
te
m
.
I
n
t
h
a
t
w
o
r
k
,
t
h
e
y
a
i
m
to
r
ed
u
ce
elec
tr
icit
y
g
e
n
er
atio
n
co
s
ts
.
C
h
ia
n
g
[
12
]
p
r
o
p
o
s
e
d
an
en
h
a
n
ce
d
g
e
n
etic
o
p
tim
izatio
n
alg
o
r
it
h
m
to
w
ar
d
s
t
h
e
o
p
ti
m
al
co
s
t
-
e
f
f
ec
tiv
e
e
m
is
s
io
n
d
i
s
p
atch
o
f
th
e
h
y
d
r
o
th
er
m
al
p
o
w
er
s
y
s
te
m
.
R
o
n
g
r
o
n
g
e
t.a
l
.
[
13
]
s
u
g
g
e
s
ted
a
m
o
d
el
i
n
t
h
e
p
o
w
er
m
ar
k
e
t
f
o
r
a
h
y
d
r
o
-
th
er
m
al
-
n
u
clea
r
p
o
w
er
s
y
s
te
m
.
A
t
w
o
-
s
tag
e
d
esi
g
n
m
et
h
o
d
f
o
r
an
e
f
f
icien
t
p
o
w
er
d
is
p
atch
i
n
g
i
s
i
n
tr
o
d
u
ce
d
b
y
C
h
e
n
et
al
.
[
14
]
an
d
th
e
y
co
n
t
r
o
l
th
e
co
o
r
d
in
atio
n
p
ar
am
eter
s
in
A
B
C
al
g
o
r
ith
m
f
o
r
ec
o
n
o
m
ic
p
o
w
er
s
c
h
ed
u
l
in
g
.
W
o
n
g
[
15
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
o
p
ti
m
iza
tio
n
tech
n
iq
u
e
f
o
r
a
s
h
o
r
t
ter
m
h
y
d
r
o
t
h
er
m
al
s
ch
ed
u
lin
g
.
I
n
t
h
at
w
o
r
k
,
t
h
e
y
p
r
ese
n
t
an
o
p
ti
m
izatio
n
tech
n
iq
u
e
b
ased
o
n
th
e
p
o
p
u
latio
n
to
s
o
lv
e
d
if
f
er
e
n
t
o
p
ti
m
izatio
n
p
r
o
b
lem
s
.
T
h
e
r
ea
l
b
ee
s
ar
e
m
ai
n
tai
n
in
g
s
w
ar
m
in
telli
g
e
n
ce
b
eh
a
v
io
r
w
h
e
n
s
ea
r
ch
in
g
f
o
r
f
o
o
d
s
o
u
r
ce
s
with
g
o
o
d
q
u
alit
y
.
B
ased
o
n
t
h
is
b
eh
a
v
io
r
A
B
C
alg
o
r
ith
m
i
s
d
ev
elo
p
ed
to
ex
p
lain
d
i
f
f
er
en
t
p
r
o
b
le
m
s
[
16
]
.
L
en
in
et
al
.
[1
7
]
in
t
r
o
d
u
ce
d
a
Hy
b
r
id
B
io
g
eo
g
r
ap
h
y
m
et
h
o
d
in
a
p
o
w
er
s
y
s
te
m
f
o
r
s
o
lv
i
n
g
th
e
m
u
lti
-
o
b
j
ec
tiv
e
r
ea
ctiv
e
p
o
w
er
d
is
p
atch
p
r
o
b
lem
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
B
a
ck
p
ro
pa
g
a
t
io
n neura
l net
w
o
rk
T
h
e
B
P
Neu
r
al
Net
w
o
r
k
(
B
P
NN)
is
a
p
o
w
er
f
u
l
tec
h
n
iq
u
e
b
ased
o
n
s
u
p
er
v
is
ed
lear
n
in
g
A
NN
to
d
is
tin
g
u
is
h
t
h
e
i
n
ter
r
u
p
tio
n
ac
tiv
itie
s
o
f
th
e
s
y
s
te
m
.
T
h
e
n
e
u
r
o
n
is
t
h
e
b
asic
ele
m
en
t
o
f
t
h
i
s
tech
n
iq
u
e
u
s
ed
to
p
r
o
ce
s
s
th
e
in
f
o
r
m
atio
n
f
r
o
m
its
m
e
m
o
r
y
[
1
8
,
19
]
.
T
h
e
er
r
o
r
-
co
r
r
ec
tio
n
p
r
o
ce
d
u
r
e
is
u
s
ed
b
y
B
P
NN
to
lear
n
.
T
h
is
m
eth
o
d
m
i
n
i
m
ize
s
th
e
er
r
o
r
b
y
m
o
d
i
f
y
i
n
g
th
e
co
n
n
ec
tio
n
w
e
ig
h
ts
.
T
o
r
e
d
u
ce
th
e
er
r
o
r
r
ate,
tu
n
e
th
e
w
ei
g
h
ts
i
n
a
p
r
o
p
er
m
a
n
n
er
,
an
d
to
cr
ea
te
th
e
m
o
d
el
p
r
ed
i
ctab
le
b
y
i
n
cr
ea
s
i
n
g
it
s
g
e
n
er
aliza
tio
n
.
T
h
e
er
r
o
r
f
u
n
ctio
n
is
s
h
o
w
n
in
(
1
)
an
d
it
is
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
ac
tu
al
an
d
a
n
ticip
ated
v
al
u
es [
2
0
]
.
)
(
i
i
i
o
t
e
(
1
)
2
0
)
(
2
1
i
j
i
i
o
t
E
(
2
)
W
h
er
e
i
is
t
h
e
i
n
d
ex
o
f
la
y
er
,
t
i
ex
p
ec
ted
r
esp
o
n
s
e
i
s
a
n
d
O
i
is
t
h
e
ac
t
u
al
r
esp
o
n
s
e
o
f
t
h
e
n
e
t
w
o
r
k
.
T
h
er
e
ar
e
th
r
ee
lay
er
s
i
n
a
t
y
p
ical
B
P
NN;
in
p
u
t
la
y
er
,
an
o
u
t
p
u
t
la
y
er
,
an
d
a
h
id
d
en
la
y
er
.
I
f
th
e
s
ig
n
i
f
ica
n
t
o
f
class
i
f
icatio
n
s
e
x
ce
ed
th
e
li
m
i
t
(
>2
0
)
th
en
th
e
h
id
d
en
la
y
er
s
h
o
u
ld
b
e
in
cr
ea
s
ed
to
t
w
o
o
r
m
o
r
e.
T
h
e
B
P
NN
tech
n
iq
u
e
i
s
s
u
m
m
ar
ized
as
f
o
llo
w
s
: (
a)
co
m
p
u
tatio
n
u
s
in
g
f
ee
d
-
f
o
r
w
ar
d
NN
(
b
)
b
ac
k
w
ar
d
p
r
o
p
ag
atio
n
o
f
t
h
e
er
r
o
r
to
th
e
h
id
d
en
la
y
er
an
d
o
u
tp
u
t
la
y
er
,
(
c)
b
r
in
g
u
p
to
d
ate
th
e
co
n
n
ec
tio
n
w
e
ig
h
ts
.
T
h
e
w
ei
g
h
t
m
o
d
i
f
y
in
g
p
r
o
ce
s
s
ca
n
b
e
ex
p
r
ess
ed
as f
o
llo
w
s
ji
ji
w
E
w
,
ji
ji
ji
w
w
w
,
(
3
)
W
h
er
e
i
an
d
j
ar
e
t
h
e
i
n
d
ex
o
f
la
y
er
s
,
ji
w
is
th
e
u
p
d
ates
o
f
w
ei
g
h
t
v
ec
to
r
s
f
o
r
t
h
e
n
e
t
w
o
r
k
co
n
n
ec
tio
n
s
;
η
is
t
h
e
lear
n
i
n
g
r
ate
co
n
s
ta
n
t
an
d
,
ji
w
is
th
e
s
u
m
o
f
r
ec
en
t
an
d
u
p
d
ated
co
n
n
ec
tio
n
w
ei
g
h
t
s
b
et
w
ee
n
t
h
e
la
y
er
s
[
2
1
]
.
T
h
e
alg
o
r
ith
m
s
to
p
s
it
s
r
ef
i
n
i
n
g
p
r
o
ce
s
s
w
h
en
th
e
er
r
o
r
f
u
n
ctio
n
v
al
u
e
b
ec
o
m
e
s
les
s
th
an
th
e
s
tan
d
ar
d
v
al
u
e
[
2
2
]
.
Fo
r
th
e
b
etter
s
tab
ilizatio
n
,
t
h
e
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
t
o
p
tim
izatio
n
tech
n
iq
u
e
i
s
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
68
-
11
75
1170
u
s
ed
in
t
h
e
B
P
NN
.
B
P
is
c
o
n
s
id
er
ed
as
a
s
u
itab
le
alg
o
r
it
h
m
i
n
th
e
m
u
lti
-
la
y
er
p
er
ce
p
t
r
o
n
[
2
3
]
.
T
h
e
f
ee
d
-
f
o
r
w
ar
d
A
NN
s
t
r
u
ct
u
r
e
is
lear
n
ed
u
s
i
n
g
th
e
B
P
alg
o
r
ith
m
w
i
th
th
e
co
n
s
tr
ai
n
ts
a
s
s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
A
NN
p
ar
a
m
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
T
h
r
e
sh
o
l
d
r
a
n
g
e
[
−
1
,
1
]
L
e
a
r
n
i
n
g
c
o
e
f
f
i
c
i
e
n
t
0
.
2
M
o
me
n
t
u
m
0
.
8
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
S
i
g
mo
i
d
W
e
i
g
h
t
r
a
n
g
e
[
−
1
,
1
]
S
t
o
p
p
i
n
g
r
u
l
e
1
0
0
0
No
w
ad
a
y
s
,
it
is
t
h
e
o
n
g
o
i
n
g
lead
in
g
d
ev
e
lo
p
m
en
ta
l
alg
o
r
it
h
m
s
d
u
e
to
its
o
p
ti
m
i
s
tic
f
ea
tu
r
es
li
k
e
f
le
x
ib
ilit
y
,
s
i
m
p
le
i
n
co
n
ce
p
t
,
an
d
im
p
le
m
e
n
tatio
n
[
2
4
]
.
T
o
s
o
lv
e
d
if
f
er
e
n
t
o
p
ti
m
izati
o
n
an
d
en
g
i
n
ee
r
i
n
g
co
m
p
lica
tio
n
s
,
t
h
i
s
al
g
o
r
ith
m
is
s
u
cc
ess
f
u
ll
y
ap
p
lied
.
T
h
e
in
tellig
e
n
t
s
ea
r
c
h
i
n
g
b
e
h
av
io
r
o
f
b
ee
s
is
s
i
m
u
lated
co
m
p
lica
tio
n
s
,
th
i
s
al
g
o
r
ith
m
is
s
u
cc
ess
f
u
ll
y
ap
p
lied
.
T
h
e
in
tellig
e
n
t
s
ea
r
c
h
i
n
g
b
e
h
av
io
r
o
f
b
ee
s
is
s
i
m
u
lated
f
o
r
th
e
o
p
ti
m
izat
io
n
p
r
o
b
le
m
s
[
2
5
]
.
T
h
ese
alg
o
r
ith
m
s
m
ain
l
y
h
av
e
e
m
p
lo
y
ed
b
ee
s
,
s
co
u
t
b
ee
s
,
o
n
lo
o
k
er
b
ee
s
,
an
d
f
o
o
d
s
o
u
r
ce
s
.
T
h
e
ef
f
ec
t
iv
e
tea
m
w
o
r
k
b
et
w
ee
n
th
e
s
e
b
ee
s
ca
n
ex
a
m
i
n
e
t
h
e
b
est s
o
u
r
ce
s
o
f
f
o
o
d
.
An
e
m
p
lo
y
ed
b
ee
u
p
d
ates
th
e
s
o
u
r
ce
p
o
s
itio
n
i
n
h
er
m
e
m
o
r
y
a
n
d
tr
ac
k
s
d
o
w
n
a
n
e
w
f
o
o
d
s
o
u
r
ce
p
o
s
itio
n
.
T
h
ey
an
a
l
y
ze
t
h
e
n
e
ctar
am
o
u
n
t
o
f
t
h
e
n
e
w
f
o
o
d
s
o
u
r
ce
w
i
th
ex
is
ti
n
g
an
d
m
e
m
o
r
ize
t
h
e
b
est
o
n
e.
T
h
ey
co
m
e
b
ac
k
to
t
h
e
h
iv
e
an
d
d
an
ci
n
g
w
i
th
o
t
h
er
s
to
s
h
ar
e
th
e
i
n
f
o
r
m
atio
n
r
eg
ar
d
in
g
n
ec
tar
a
m
o
u
n
t
s
.
Dan
ce
d
u
r
atio
n
d
ep
en
d
s
o
n
t
h
e
n
ec
tar
a
m
o
u
n
t
o
f
f
o
o
d
s
o
u
r
c
es.
On
lo
o
k
er
b
ee
s
d
eter
m
i
n
e
a
g
o
o
d
q
u
alit
y
f
o
o
d
s
o
u
r
ce
b
y
w
atch
in
g
t
h
e
d
an
ce
s
o
f
e
m
p
lo
y
ed
b
ee
s
[
2
6
]
.
T
h
e
s
a
m
e
e
m
p
lo
y
ed
b
ee
b
ec
o
m
es
a
s
co
u
t
w
h
e
n
th
e
s
o
u
r
ce
is
ab
an
d
o
n
ed
an
d
r
esta
r
ts
to
s
ea
r
ch
f
o
r
d
if
f
er
e
n
t
f
o
o
d
s
o
u
r
ce
s
r
an
d
o
m
l
y
[
2
7
]
.
I
n
th
e
p
r
esen
t
alg
o
r
it
h
m
,
th
e
n
u
m
b
er
o
f
e
m
p
lo
y
ed
b
ee
s
is
eq
u
al
to
t
h
e
n
u
m
b
er
o
f
f
o
o
d
s
o
u
r
ce
s
[
2
8
]
.
Si
m
ilar
l
y
,
t
h
e
n
u
m
b
er
o
f
e
m
p
lo
y
ed
b
ee
s
an
d
o
n
lo
o
k
er
b
ee
s
ar
e
th
e
s
a
m
e.
T
h
at
is
,
f
i
f
t
y
p
er
ce
n
t o
f
th
e
b
ee
co
lo
n
y
is
o
cc
u
p
ied
b
y
an
e
m
p
lo
y
ed
b
ee
.
A
l
g
o
r
ith
m
1:
a)
P
o
p
u
latio
n
I
n
itializatio
n
b)
Dis
tr
ib
u
te
e
m
p
lo
y
ed
b
ee
s
f
o
r
a
n
e
w
f
o
o
d
s
o
u
r
ce
c)
Sto
r
e
th
e
b
est s
o
u
r
ce
o
f
f
o
o
d
b
y
e
v
al
u
at
i
n
g
th
e
f
it
n
es
s
d)
Dev
elo
p
m
e
n
t o
f
O
n
lo
o
k
er
b
ee
s
e)
C
alcu
late
P
r
o
b
ab
ilit
ies f
o
r
On
l
o
o
k
er
s
f)
Dev
elo
p
m
e
n
t o
f
Sco
u
t B
ee
s
g)
R
e
m
e
m
b
er
th
e
b
est
-
r
ea
lized
s
o
lu
tio
n
s
o
f
ar
h)
Sto
p
th
e
p
r
o
ce
d
u
r
e
w
h
e
n
th
e
un
it
c
y
c
le
eq
u
al
to
Ma
x
i
m
u
m
C
y
cle
Nu
m
b
er
i)
Oth
er
w
i
s
e,
g
o
b
ac
k
to
Step
2
T
h
is
alg
o
r
ith
m
,
b
y
u
s
i
n
g
(
1
)
,
r
an
d
o
m
l
y
d
eter
m
i
n
es t
h
e
f
o
o
d
s
o
u
r
ce
s
[
2
9
]
.
)
](
1
,
0
[
m
i
n
,
m
a
x
,
m
i
n
,
j
j
j
ij
x
x
r
a
n
d
x
x
(
4
)
W
h
er
e
i
r
ep
r
esen
ts
t
h
e
f
o
o
d
s
o
u
r
ce
an
d
j
r
ep
r
esen
ts
t
h
e
co
n
s
tr
ain
t
to
b
e
o
p
ti
m
ized
,
m
i
n
x
an
d
m
a
x
x
ar
e
lo
w
er
a
n
d
u
p
p
er
b
o
u
n
d
ar
y
p
ar
a
m
eter
s
f
o
r
t
h
e
s
o
l
u
tio
n
r
esp
ec
tiv
el
y
,
an
d
r
a
n
d
[
0
,
1
]
cr
ea
tes
ar
b
itra
r
y
s
ig
n
i
f
ica
n
t
v
al
u
e
s
a
m
o
n
g
0
an
d
1
.
A
p
o
s
s
ib
le
s
o
lu
tio
n
i
s
g
e
n
er
ated
b
y
t
h
e
e
m
p
lo
y
ed
b
ee
s
b
y
u
p
d
atin
g
th
e
(
4
)
u
s
i
n
g
th
e
e
x
p
r
ess
io
n
)
](
1
,
1
[
kj
ij
ij
ij
x
x
r
a
n
d
x
v
(
5
)
W
h
er
e
k
an
d
j
ar
e
r
an
d
o
m
l
y
s
elec
ted
i
n
d
ices
t
h
at
d
e
n
o
te
th
e
f
o
o
d
s
o
u
r
ce
an
d
o
p
ti
m
izat
io
n
p
ar
am
e
ter
s
r
esp
ec
tiv
el
y
an
d
]
1
,
1
[
r
a
n
d
is
a
r
an
d
o
m
n
u
m
b
er
th
at
c
o
n
tr
o
ls
th
e
n
e
ig
h
b
o
r
f
o
o
d
s
o
u
r
ce
p
r
o
d
u
ctio
n
.
T
h
e
f
itn
e
s
s
o
f
th
e
o
p
tim
u
m
s
o
lu
tio
n
is
ev
a
lu
ated
b
y
th
e
e
m
p
lo
y
ed
b
ee
s
an
d
th
e
n
e
w
s
o
l
u
tio
n
i
s
to
r
ep
lace
th
e
ex
i
s
te
n
ce
i
n
th
e
m
e
m
o
r
y
o
f
e
m
p
lo
y
ed
b
ee
s
.
T
h
e
b
ee
r
em
a
in
s
it
s
f
o
o
d
s
o
u
r
ce
i
f
t
h
e
n
ec
tar
a
m
o
u
n
t
o
f
th
e
r
ec
en
t
s
o
u
r
ce
o
f
f
o
o
d
is
less
er
th
a
n
t
h
at
o
f
t
h
e
cu
r
r
en
t o
n
e.
Usi
n
g
t
h
e
p
r
o
b
ab
ilit
y
co
m
p
a
r
is
o
n
m
eth
o
d
,
t
h
e
o
n
lo
o
k
er
b
ee
s
ch
o
o
s
e
t
h
eir
s
o
u
r
ce
s
o
f
f
o
o
d
.
T
h
e
p
r
o
b
a
b
ilit
y
f
u
n
ctio
n
i
P
is
ca
lc
u
l
ated
u
s
i
n
g
t
h
e
f
it
n
es
s
v
al
u
e.
T
h
e
n
ec
tar
s
o
u
r
ce
s
o
f
g
o
o
d
p
r
o
b
ab
ilit
y
ar
e
ca
r
ef
u
ll
y
c
h
o
s
en
a
n
d
th
e
p
r
o
b
ab
ilit
y
o
f
b
ei
n
g
s
e
lecte
d
f
o
r
th
e
f
o
o
d
s
o
u
r
ce
s
is
ca
lc
u
lated
as f
o
llo
w
s
:
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
Mo
d
ified
a
r
tifi
cia
l b
ee
co
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
a
d
a
p
tive
p
o
w
er sch
ed
u
lin
g
…
(
V
ijo
M J
o
y
)
1171
SN
n
n
i
i
f
i
t
f
i
t
P
1
(
6
)
W
h
er
e,
f
it
n
ess
o
r
p
r
o
f
itab
ilit
y
(
q
u
alit
y
o
f
t
h
e
p
o
s
s
ib
le
s
o
l
u
tio
n
)
v
al
u
e
o
f
t
h
e
th
i
s
o
lu
tio
n
i
s
i
f
i
t
,
w
h
ic
h
is
d
er
iv
ed
f
r
o
m
th
e
(
7
)
an
d
SN,
is
t
h
e
e
m
p
lo
y
ed
o
r
o
n
lo
o
k
er
b
ee
s
s
ize.
i
i
i
f
f
f
i
t
1
1
1
0
0
f
f
i
(
7
)
W
h
er
e,
in
d
ep
en
d
en
t
f
u
n
c
tio
n
v
alu
e
f
o
r
i
is
i
f
,
an
d
it
is
d
is
tin
ct
f
o
r
th
e
o
p
tim
iza
tio
n
p
r
o
b
lem
.
T
h
e
s
y
s
te
m
w
ill
r
ep
lace
th
e
p
o
s
iti
o
n
o
f
ex
i
s
ti
n
g
f
o
o
d
s
o
u
r
ce
s
w
it
h
t
h
e
r
ec
en
t
s
o
u
r
ce
s
o
f
f
o
o
d
w
h
e
n
th
e
r
ec
e
n
t
s
o
u
r
ce
p
o
s
itio
n
h
as
en
h
a
n
ce
d
q
u
alit
y
th
a
n
th
e
ex
i
s
ti
n
g
f
o
o
d
s
o
u
r
ce
p
o
s
itio
n
.
Fo
r
th
e
w
ell
-
o
p
ti
m
iza
tio
n
ap
p
licatio
n
s
,
t
h
e
p
r
e
m
is
e
o
f
AB
C
m
e
th
o
d
o
lo
g
y
is
u
s
ed
a
n
d
t
h
e
s
y
s
te
m
atte
m
p
ts
to
to
u
ch
th
e
g
lo
b
al
m
i
n
i
m
u
m
.
T
h
e
im
p
o
r
tan
t
A
B
C
p
ar
a
m
eter
s
an
d
th
eir
s
ig
n
i
f
ica
n
t u
s
e
in
t
h
is
w
o
r
k
ar
e
g
i
v
en
i
n
T
ab
le
2
.
T
ab
le
2
.
A
B
C
p
ar
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
L
o
w
e
r
b
o
u
n
d
10
U
p
p
e
r
b
o
u
n
d
10
S
i
z
e
o
f
C
o
l
o
n
y
50
L
i
mi
t
o
f
f
o
o
d
so
u
r
c
e
1
0
0
M
a
x
c
y
c
l
e
1
0
0
0
Gettin
g
s
t
u
ck
in
lo
ca
l
m
in
i
m
a
is
a
m
aj
o
r
d
r
aw
b
ac
k
o
f
b
ac
k
p
r
o
p
ag
atio
n
.
So
,
a
n
e
f
f
ic
ien
t
o
p
ti
m
izatio
n
alg
o
r
ith
m
lik
e
A
B
C
is
u
s
ed
f
o
r
th
e
o
p
ti
m
izatio
n
an
d
th
e
r
esu
lt
is
tr
ain
ed
w
it
h
t
h
e
B
P
alg
o
r
it
h
m
.
Her
e,
a
h
y
b
r
id
A
B
C
-
B
P
m
et
h
o
d
ca
lled
Mo
d
if
ied
A
B
C
is
i
n
tr
o
d
u
ce
d
.
2
.
2
L
o
a
d sched
uli
ng
f
o
r
m
ula
t
io
n
T
o
r
ed
u
ce
th
e
co
s
t o
f
elec
tr
ic
en
er
g
y
,
f
i
n
d
th
e
o
p
ti
m
al
co
m
b
in
atio
n
o
f
s
o
u
r
ce
s
b
ased
o
n
d
e
m
an
d
.
Fo
r
an
y
u
n
it,
th
e
co
s
t c
u
r
v
e
i
s
s
u
p
p
o
s
ed
b
y
q
u
ad
r
atic
f
u
n
c
tio
n
s
e
g
m
e
n
t
s
o
f
t
h
e
ac
tiv
e
r
esp
o
n
s
e
o
f
th
e
s
o
u
r
ce
s
[
3
0
]
.
Fo
r
a
p
o
w
er
s
y
s
te
m
,
t
h
e
o
p
ti
m
izatio
n
o
f
co
s
t i
s
d
ef
i
n
ed
b
y
t
h
e
eq
u
atio
n
:
n
i
n
i
i
i
i
i
i
i
t
o
t
c
P
b
P
a
P
F
F
1
1
2
)
(
)
(
(
8
)
W
h
er
e
t
o
t
F
is
th
e
to
tal
co
s
t
o
f
g
en
er
atio
n
,
i
a
,
i
b
an
d
i
c
ar
e
th
e
co
s
t
co
ef
f
icie
n
t
s
an
d
i
P
is
th
e
g
en
er
ated
p
o
w
er
b
y
t
h
e
th
i
u
n
it
a
n
d
n
is
t
h
e
n
u
m
b
er
o
f
s
o
u
r
ce
s
.
T
h
e
o
p
ti
m
izatio
n
o
f
co
s
t
is
s
u
b
j
ec
ted
to
th
e
in
eq
u
ali
t
y
co
n
s
tr
ai
n
ts
o
f
t
h
e
s
y
s
te
m
:
Fo
r
i=1
,
2
,
3
……n
(
9
)
w
h
er
e
m
i
n
,
m
a
x
,
i
i
P
and
P
ar
e
th
e
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
p
o
w
er
o
u
tp
u
ts
.
T
h
e
to
tal
p
o
w
er
d
e
m
a
n
d
,
D
P
=
n
i
L
i
P
P
1
(
1
0
)
w
h
er
e
L
P
is
t
h
e
to
tal
tr
an
s
m
i
s
s
io
n
lo
s
s
.
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
68
-
11
75
1172
2
.
3
M
o
dified
AB
C
a
lg
o
rit
h
m
B
P
alg
o
r
ith
m
is
ca
p
ab
le
to
f
i
n
d
lo
ca
l
o
p
ti
m
is
tic
r
esp
o
n
s
e
an
d
A
B
C
h
a
s
to
f
i
n
d
g
lo
b
al
o
p
tim
is
tic
r
esp
o
n
s
e
[
3
1
]
.
I
n
th
is
p
ap
er
,
t
h
e
h
y
b
r
id
alg
o
r
ith
m
A
B
C
-
B
P
is
m
o
d
i
f
ied
an
d
is
ter
m
ed
as
a
Mo
d
if
ied
A
B
C
Op
ti
m
izatio
n
al
g
o
r
ith
m
(
M
A
B
C
O)
.
I
n
t
h
is
h
y
b
r
id
tec
h
n
o
lo
g
y
,
i
n
t
h
e
in
i
tial
s
tag
e
o
f
co
m
p
u
tatio
n
,
t
h
e
o
p
tim
izatio
n
tech
n
iq
u
e
A
B
C
is
u
s
ed
to
f
i
n
d
t
h
e
o
p
ti
m
u
m
v
alu
e
s
f
r
o
m
t
h
e
tr
ai
n
i
n
g
p
ar
am
eter
s
,
a
n
d
B
P
is
co
n
tin
u
ed
w
it
h
th
i
s
o
p
ti
m
ized
r
esu
lt.
A
l
g
o
r
ith
m
2
:
a)
I
n
itialize
t
h
e
p
o
p
u
latio
n
b
y
s
ettin
g
th
e
co
n
s
tr
ain
ts
li
k
e
co
lo
n
y
s
ize,
h
e
u
r
is
tic
f
i
g
u
r
es,
an
d
en
d
in
g
th
e
f
u
n
ctio
n
.
b)
Gen
er
ate
a
n
e
w
s
o
l
u
tio
n
f
o
r
em
p
lo
y
ed
b
ee
s
an
d
ap
p
l
y
a
g
r
e
ed
y
s
elec
tio
n
p
r
o
ce
s
s
.
c)
Sh
ar
i
n
g
t
h
e
i
n
f
o
r
m
atio
n
b
et
wee
n
e
m
p
lo
y
ed
an
d
o
n
lo
o
k
er
b
ee
s
.
T
h
e
ev
alu
a
tio
n
o
f
s
h
ar
ed
in
f
o
r
m
atio
n
is
ca
r
r
ied
o
u
t
b
y
th
e
O
n
lo
o
k
e
r
b
ee
an
d
r
an
d
o
m
l
y
s
e
lects
a
p
r
o
b
ab
ilit
y
-
b
ased
f
o
o
d
s
o
u
r
ce
.
T
h
is
is
p
r
o
p
o
r
tio
n
al
to
th
e
f
o
o
d
s
o
u
r
ce
q
u
alit
y
.
C
alcu
late
th
e
p
r
o
b
ab
ilit
y
u
s
i
n
g
th
e
m
o
d
if
ied
e
x
p
r
ess
io
n
d)
C
o
n
s
tr
u
ct
a
n
d
ev
al
u
ate
t
h
e
f
it
n
es
s
f
u
n
ctio
n
s
o
f
a
ll
s
o
l
u
tio
n
s
in
th
e
p
o
p
u
latio
n
a
n
d
m
e
m
o
r
ize
th
e
b
est
s
o
lu
tio
n
.
e)
R
ep
ea
t th
e
p
r
o
ce
s
s
to
o
b
tain
t
h
e
o
p
ti
m
ized
v
al
u
e
s
,
an
d
th
e
n
ex
it.
f)
Up
d
atin
g
o
f
i
n
it
ial
w
ei
g
h
t
s
o
f
B
P
w
ill ta
k
e
p
lace
w
h
e
n
t
h
e
e
x
it c
o
n
d
itio
n
b
ec
o
m
e
f
u
l
f
illed
g)
T
r
ain
th
e
B
P
NN
an
d
ca
lcu
late
th
e
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
.
T
h
e
s
y
s
te
m
th
e
n
g
o
es
t
h
r
o
u
g
h
th
e
s
to
p
p
in
g
co
n
d
itio
n
.
h)
I
f
t
h
e
s
y
s
te
m
d
ec
li
n
es
th
e
s
to
p
p
in
g
co
n
d
itio
n
t
h
e
n
r
eiter
ate
t
h
e
s
y
s
te
m
u
s
in
g
s
tep
7
.
Or
els
e,
m
ai
n
tai
n
t
h
e
o
u
tco
m
es
f
o
r
MSE
an
d
R
e
g
r
es
s
io
n
.
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
T
h
e
s
im
u
la
t
i
o
n
s
h
av
e
b
e
en
c
o
n
d
u
c
t
e
d
w
i
th
d
i
f
f
e
r
e
n
t
r
e
q
u
i
r
em
en
ts
o
f
t
h
e
p
o
w
e
r
s
y
s
t
em
.
T
h
e
m
o
d
if
ie
d
s
ch
e
d
u
l
in
g
al
g
o
r
i
th
m
,
MA
B
C
r
u
n
s
m
an
y
tim
e
s
an
d
th
e
av
e
r
ag
e
m
ak
e
s
p
an
v
a
lu
e
i
s
c
o
m
p
u
t
e
d
.
I
n
a
l
l th
e
t
r
a
in
in
g
,
t
h
e
o
p
t
im
u
m
s
o
lu
ti
o
n
s
a
r
e
c
au
s
e
d
b
e
f
o
r
e
r
e
a
ch
i
n
g
th
e
m
ax
im
u
m
i
t
e
r
at
i
o
n
.
T
h
e
r
e
s
u
lt
i
s
c
o
m
p
a
r
e
d
w
i
th
th
e
B
PN
N
a
n
d
A
B
C
-
B
P a
lg
o
r
i
th
m
.
T
h
e
o
b
t
a
in
e
d
v
al
u
e
w
ith
d
if
f
er
e
n
t
A
NN
s
t
r
u
c
tu
r
e
i
s
s
h
o
w
n
in
T
a
b
l
e
3
an
d
T
a
b
l
e
4
.
I
n
T
a
b
l
e
3
t
h
e
A
N
N
s
t
r
u
c
tu
r
e
c
o
n
s
i
s
t
s
o
f
6
i
n
p
u
t
l
ay
e
r
s
,
1
0
h
i
d
d
en
l
ay
e
r
s
,
a
n
d
1
o
u
t
p
u
t
lay
e
r
s
(
6
-
10
-
1
)
.
T
h
e
s
e
s
y
s
tem
s
t
ak
e
1
4
2
.
1
1
s
e
c
o
n
d
s
f
o
r
t
h
e
ex
e
cu
ti
o
n
an
d
it
s
a
c
cu
r
ac
y
i
s
9
8
.
8
8
.
I
n
T
a
b
l
e
4
,
th
e
n
u
m
b
e
r
o
f
th
e
h
i
d
d
e
n
l
ay
e
r
i
s
ch
an
g
e
d
t
o
f
i
f
t
e
en
(
6
-
15
-
1
)
.
I
t
r
e
s
u
l
t
s
in
an
im
p
r
o
v
em
e
n
t
i
n
a
c
cu
r
a
cy
.
Fig
u
r
e
1
illu
s
tr
ate
s
th
e
b
est
tr
a
in
i
n
g
b
eh
a
v
io
r
o
f
th
e
m
o
d
if
ied
alg
o
r
it
h
m
-
M
A
B
C
.
T
h
e
MSE
is
1
.
0
3
9
3
0
e
-
1
2
at
E
p
o
ch
2
2
0
as
s
h
o
w
n
in
T
ab
le
4
.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
s
y
s
te
m
i
s
an
al
y
z
ed
u
s
in
g
MSE
a
n
d
E
p
o
ch
s
.
T
h
e
g
r
ap
h
s
h
o
w
s
th
e
tr
en
d
s
in
tr
ain
i
n
g
,
v
alid
atio
n
,
an
d
test
d
ata
i
n
ter
m
s
o
f
MSE
an
d
E
p
o
ch
s
.
Fro
m
th
e
g
r
ap
h
,
it
is
clea
r
th
at
th
e
MSE
d
ec
r
ea
s
es
w
ith
a
n
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
ep
o
ch
s
f
o
r
all
tr
ain
ed
,
v
alid
atio
n
,
a
n
d
test
d
ata.
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
s
y
s
te
m
i
s
9
9
.
2
3
% o
n
th
e
b
asi
s
o
f
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
s
.
T
ab
le
3
.
T
im
e,
MSE
an
d
e
p
o
ch
s
f
o
r
6
-
10
-
1
A
N
N
ar
ch
itect
u
r
e
A
l
g
o
r
i
t
h
m
B
P
N
N
A
B
C
-
BP
M
A
B
C
O
C
P
U
TI
M
E
6
8
.
1
4
1
7
8
.
2
3
1
4
2
.
1
1
EPO
C
H
S
1
0
0
0
8
2
0
2
7
4
M
S
E
6
.
4
5
x
1
0
-
3
1
.
8
9
x
1
0
-
7
1
.
8
8
x
1
0
-
12
A
C
C
U
R
A
C
Y
(
%)
8
6
.
1
2
97
.
6
1
9
8
.
8
8
T
ab
le
4
.
T
im
e,
MSE
an
d
e
p
o
ch
s
f
o
r
6
-
15
-
1
A
N
N
ar
ch
itect
u
r
e
A
l
g
o
r
i
t
h
m
B
P
N
N
A
B
C
-
BP
M
A
B
C
O
C
P
U
TI
M
E
7
4
.
2
5
1
8
2
.
2
3
1
4
2
.
88
EPO
C
H
S
1
0
0
0
8
12
2
20
M
S
E
4
.
3
6
x
1
0
-
3
1
.
4
5
x
1
0
-
7
1
.
0
4
x
1
0
-
12
A
C
C
U
R
A
C
Y
(
%)
8
8
9
8
.
1
1
9
9
.
2
3
I
n
th
i
s
lo
ad
s
ch
ed
u
li
n
g
ap
p
r
o
ac
h
,
a
th
r
ee
-
la
y
er
–
in
p
u
t,
o
u
tp
u
t,
an
d
h
id
d
en
la
y
er
s
–
f
ee
d
-
f
o
r
w
ar
d
A
N
Ns
ar
e
u
s
ed
.
Fo
r
th
e
o
p
tim
izatio
n
o
f
lo
ad
,
a
s
w
ar
m
-
b
a
s
ed
m
eta
-
h
e
u
r
is
t
ic
s
c
h
ed
u
li
n
g
alg
o
r
ith
m
,
M
A
B
C
O
is
in
tr
o
d
u
ce
d
.
I
t
ad
v
is
es
t
o
m
i
n
i
m
ize
t
h
e
co
s
t
o
f
e
n
er
g
y
,
m
i
n
i
m
ize
t
h
e
en
er
g
y
co
n
c
ep
tio
n
d
u
r
in
g
p
ea
k
ti
m
e
,
an
d
m
ak
e
t
h
e
av
ailab
ili
t
y
o
f
t
h
e
p
o
w
er
to
th
e
h
ig
h
l
y
d
e
m
a
n
d
ed
ar
ea
s
.
T
h
e
elec
tr
icit
y
d
e
m
an
d
is
n
o
t
r
ed
u
ce
d
,
b
u
t
it
tr
ie
s
to
s
h
i
f
t
t
h
e
d
e
m
an
d
f
r
o
m
p
ea
k
to
o
f
f
-
p
ea
k
p
er
io
d
by
co
n
s
id
er
i
n
g
a
ll
o
t
h
er
p
ar
a
m
eter
s
.
T
h
e
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
Mo
d
ified
a
r
tifi
cia
l b
ee
co
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
a
d
a
p
tive
p
o
w
er sch
ed
u
lin
g
…
(
V
ijo
M J
o
y
)
1173
tr
ad
itio
n
al
lo
ad
s
h
ed
d
i
n
g
p
r
o
ce
s
s
i
s
co
m
p
letel
y
a
v
o
id
ed
b
y
u
s
i
n
g
t
h
is
s
ch
ed
u
li
n
g
p
r
o
ce
s
s
.
T
h
e
co
n
s
u
m
p
tio
n
s
of
u
n
s
c
h
ed
u
led
an
d
s
c
h
ed
u
led
lo
ad
ar
e
s
h
o
w
n
in
F
ig
u
r
e
2
an
d
Fig
u
r
e
3
r
esp
ec
tiv
el
y
.
Fig
u
r
e
1
.
T
r
ain
in
g
p
er
f
o
r
m
a
n
c
e
o
f
MA
B
C
-
BP
Fig
u
r
e
2
.
Un
s
c
h
ed
u
led
p
o
w
er
co
n
s
u
m
p
tio
n
Fig
u
r
e
3
.
Sch
ed
u
led
p
o
w
er
co
n
s
u
m
p
t
io
n
T
h
e
s
ch
ed
u
led
p
o
w
er
s
y
s
te
m
m
i
n
i
m
izes
th
e
er
r
o
r
.
I
t
also
r
ed
u
ce
s
t
h
e
co
s
t
o
f
e
n
er
g
y
a
n
d
m
a
k
e
s
t
h
e
av
ailab
ilit
y
to
m
ee
t
t
h
e
d
e
m
an
d
ed
lo
ad
.
B
ef
o
r
e
th
e
s
c
h
ed
u
li
n
g
p
r
o
ce
s
s
,
6
.
7
%
o
f
a
d
d
itio
n
al
en
er
g
y
is
d
eliv
er
ed
,
b
u
t
a
f
ter
th
e
s
c
h
ed
u
li
n
g
,
it
r
ed
u
ce
s
to
0
.
8
%.
Af
ter
s
ch
ed
u
lin
g
th
e
e
s
s
e
n
tial
e
n
er
g
y
to
m
ee
t
t
h
e
d
em
a
n
d
ed
lo
ad
is
r
ed
u
ce
d
f
r
o
m
8
.
0
4
%
to
0
.
9
6
%.
Fig
u
r
e
4
(
a)
s
h
o
w
s
th
e
p
er
ce
n
tag
e
o
f
e
x
tr
a
g
en
er
ated
p
o
w
er
f
o
r
b
o
th
s
ch
ed
u
led
a
n
d
u
n
s
ch
ed
u
led
s
y
s
te
m
s
.
Fi
g
u
r
e
4
(
b
)
s
h
o
w
s
th
e
p
er
ce
n
ta
g
e
o
f
p
o
w
er
n
ee
d
ed
to
m
ee
t
t
h
e
d
em
a
n
d
ed
lo
ad
in
b
o
th
s
y
s
te
m
s
.
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
68
-
11
75
1174
(
a)
(
b
)
Fig
u
r
e
4
.
(
a)
E
x
tr
a
en
er
g
y
a
n
d
(
b
)
E
s
s
en
tial e
n
er
g
y
f
o
r
th
e
u
n
s
c
h
ed
u
led
an
d
s
c
h
ed
u
led
s
y
s
t
e
m
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
th
e
MA
B
C
h
a
s
b
ee
n
in
tr
o
d
u
ce
d
f
o
r
o
p
tim
al
s
ch
ed
u
li
n
g
.
T
h
e
B
P
NN
tr
ain
in
g
alg
o
r
ith
m
is
u
s
ed
f
o
r
o
p
tim
iz
in
g
of
t
h
e
f
ee
d
-
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
.
Slo
w
s
p
ee
d
an
d
lo
ca
l
m
i
n
i
m
izatio
n
ar
e
s
o
m
e
d
r
a
w
b
ac
k
s
o
f
t
h
is
alg
o
r
it
h
m
.
T
h
er
ef
o
r
e
,
s
o
m
e
m
eta
-
h
eu
r
i
s
ti
c
o
p
ti
m
izatio
n
al
g
o
r
ith
m
s
i
n
s
p
ir
ed
b
y
n
at
u
r
e
ar
e
u
s
ed
to
s
o
lv
e
th
e
s
o
p
h
is
tica
ted
p
r
o
b
lem
s
.
I
n
t
h
i
s
w
o
r
k
,
t
h
e
M
A
B
C
i
s
u
s
ed
to
tr
ain
t
h
e
B
P
NN
.
I
n
itiall
y
,
to
tr
ain
th
e
n
e
t
w
o
r
k
M
A
B
C
al
g
o
r
ith
m
is
u
s
ed
,
t
h
en
t
h
e
lear
n
in
g
p
r
o
ce
s
s
is
ad
v
a
n
ci
n
g
w
i
th
B
P
NN
b
y
ac
ce
p
tin
g
t
h
e
f
i
n
est
w
e
ig
h
t
s
et
s
f
r
o
m
th
e
o
p
ti
m
ized
al
g
o
r
ith
m
.
I
t
m
i
n
i
m
iz
es
th
e
er
r
o
r
an
d
g
iv
e
s
a
b
etter
ac
cu
r
ac
y
r
ate.
T
h
e
p
er
f
o
r
m
a
n
ce
i
s
co
m
p
ar
ed
w
ith
o
th
er
ex
is
tin
g
al
g
o
r
ith
m
s
li
k
e
B
P
NN
an
d
A
B
C
-
BP
.
T
h
e
s
ch
ed
u
led
s
y
s
te
m
h
as
b
etter
p
er
f
o
r
m
a
n
ce
an
d
it
h
e
l
p
s
to
m
in
i
m
ize
t
h
e
en
er
g
y
u
ti
l
izatio
n
w
it
h
o
u
t
a
f
f
ec
ti
n
g
t
h
e
d
em
a
n
d
ed
p
o
w
er
.
I
t
also
h
elp
s
to
r
ed
u
ce
en
er
g
y
co
s
ts
.
T
h
e
ex
p
er
im
e
n
t
al
r
es
u
l
t
s
in
d
icate
th
a
t
th
i
s
h
y
b
r
id
al
g
o
r
ith
m
p
er
f
o
r
m
ed
b
etter
th
an
its
in
d
i
v
id
u
al
i
m
p
l
e
m
en
tatio
n
s
.
T
h
er
ef
o
r
e,
it
is
co
n
clu
d
ed
th
a
t
t
h
e
p
r
esen
t
s
y
s
te
m
ca
n
p
r
o
d
u
ce
a
b
etter
o
p
tim
al
s
c
h
ed
u
le
ef
f
icie
n
tl
y
.
RE
F
E
R
E
NC
E
S
[1
]
V
.
M
o
o
rt
h
y
,
e
t
a
l.
,
“
In
v
e
s
ti
g
a
ti
o
n
o
n
th
e
e
ff
e
c
ti
v
e
n
e
ss
o
f
ABC
a
lg
o
rit
h
m
f
o
r
h
y
d
ro
th
e
rm
a
l
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
c
o
n
sid
e
ri
n
g
e
m
is
sio
n
a
sp
e
c
ts,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
e
rg
y
S
e
c
to
r M
a
n
a
g
e
me
n
t
,
v
o
l.
9
,
p
p
.
2
5
1
-
2
7
3
,
2
0
1
5
.
[2
]
Ka
b
a
lci,
e
t
a
l.
,
“
A
m
o
d
if
ied
A
BC
a
lg
o
rit
h
m
a
p
p
ro
a
c
h
f
o
r
p
o
w
e
r
sy
st
e
m
h
a
r
m
o
n
ic
e
stim
a
ti
o
n
p
ro
b
l
e
m
s,”
El
e
c
tric
Po
we
r S
y
ste
ms
Res
e
a
rc
h
,
v
o
l.
1
5
4
,
p
p
.
1
6
0
-
1
7
3
,
2
0
1
8
.
[3
]
Die
u
,
V
.
N
.
a
n
d
O
n
g
sa
k
u
l,
W
,
“
I
m
p
ro
v
e
d
m
e
rit
o
rd
e
r
a
n
d
a
u
g
m
e
n
ted
L
a
g
ra
n
g
e
Ho
p
f
ield
n
e
tw
o
rk
f
o
r
sh
o
rt
term
h
y
d
ro
th
e
rm
a
l
sc
h
e
d
u
li
n
g
,
”
En
e
rg
y
Co
n
v
e
rs
io
n
a
n
d
M
a
n
a
g
e
me
n
t,
v
o
l.
5
0
,
n
o
.
1
2
,
p
p
.
3
0
1
5
-
3
0
2
3
,
2
0
0
9
.
[4
]
A
.
I.
S
e
l
v
a
k
u
m
a
r,
“
Ci
v
il
ize
d
s
w
a
r
m
o
p
ti
m
iz
a
ti
o
n
f
o
r
m
u
lt
i
-
o
b
jec
ti
v
e
sh
o
rt
-
term
h
y
d
ro
th
e
rm
a
l
sc
h
e
d
u
li
n
g
,
”
El
e
c
trica
l
Po
we
r a
n
d
En
e
rg
y
S
y
st
e
ms
,
v
o
l.
5
1
,
p
p
.
1
7
8
-
1
8
9
,
2
0
1
3
.
[5
]
Ba
sh
e
e
r,
I.
A
.
,
a
n
d
Ha
j
m
e
e
r,
“
A
rti
f
ic
ial
n
e
u
ra
l
n
e
tw
o
rk
s
:
f
u
n
d
a
m
e
n
tals,
c
o
m
p
u
ti
n
g
,
d
e
sig
n
,
a
n
d
a
p
p
li
c
a
ti
o
n
,
”
J
o
u
rn
a
l
o
f
M
icr
o
b
i
o
lo
g
ica
l
M
e
th
o
d
s
,
v
o
l
.
4
3
,
n
o
.
1
,
p
p
.
3
-
3
1
,
2
0
0
0
.
[6
]
M
o
h
d
Na
w
i,
e
t
a
l.
,
“
A
n
a
c
c
e
ler
a
ted
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iza
ti
o
n
b
a
se
d
lev
e
n
b
e
rg
m
a
rq
u
a
rd
t
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
lg
o
rit
h
m
,
”
.
In
:
L
o
o
C.
K
.
,
e
t
a
l
.
,
(
e
d
s),
Ne
u
ra
l
I
n
f
o
rm
a
ti
o
n
Pr
o
c
e
ss
in
g
.
ICONIP
2
0
1
4
.
L
e
c
tu
re
No
te
s
in
Co
m
p
u
ter
S
c
ien
c
e
,
S
p
ri
n
g
e
r,
C
h
a
m
,
v
o
l.
8
8
3
5
,
p
p
.
2
4
5
-
2
5
3
,
2
0
1
4
.
[7
]
F
.
S
.
A
b
u
-
M
o
u
ti
a
n
d
M
.
E
.
El
-
Ha
w
a
r
y
,
"
O
v
e
rv
i
e
w
o
f
A
rti
f
icia
l
Be
e
Co
lo
n
y
(
A
BC)
a
lg
o
rit
h
m
a
n
d
it
s
a
p
p
l
ica
ti
o
n
s,"
2
0
1
2
IE
EE
I
n
ter
n
a
t
io
n
a
l
S
y
ste
ms
Co
n
fer
e
n
c
e
,
V
a
n
c
o
u
v
e
r,
p
p
.
1
-
6
,
2
0
1
2
.
[8
]
Ho
ta,
e
t
a
l.
,
“
S
h
o
rt
-
term
h
y
d
ro
th
e
r
m
a
l
sc
h
e
d
u
li
n
g
th
ro
u
g
h
e
v
o
lu
ti
o
n
a
ry
p
ro
g
ra
m
m
in
g
te
c
h
n
iq
u
e
,
”
El
e
c
tric
Po
we
r
S
y
ste
ms
Res
e
a
rc
h
,
v
o
l.
5
2
,
n
o
.
2
,
p
p
.
1
8
9
-
1
9
6
,
1
9
9
9
.
[9
]
S
if
u
e
n
tes
,
e
t
a
l.
,
“
Hy
d
ro
th
e
rm
a
l
sc
h
e
d
u
li
n
g
u
si
n
g
b
e
n
d
e
rs
d
e
c
o
m
p
o
siti
o
n
:
a
c
c
e
lera
ti
n
g
tec
h
n
iq
u
e
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Po
we
r
S
y
ste
ms
,
v
o
l.
2
2
n
o
.
3
,
p
p
.
1
3
5
1
-
1
3
5
9
,
2
0
0
7
.
[1
0
]
B
.
M
o
u
su
m
i,
“
Ho
p
f
ield
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
o
p
ti
m
a
l
sc
h
e
d
u
li
n
g
o
f
f
ix
e
d
h
e
a
d
h
y
d
ro
th
e
rm
a
l
p
o
w
e
r
s
y
st
e
m
s,”
El
e
c
tric P
o
we
r S
y
ste
ms
Res
e
a
rc
h
,
v
o
l.
6
4
,
n
o
.
1
,
p
p
.
1
1
-
1
5
,
2
0
0
3
.
[1
1
]
K
.
C
.
L
e
,
e
t
a
l.
,
“
En
v
iro
n
m
e
n
tal
e
c
o
n
o
m
ic
h
y
d
ro
th
e
rm
a
l
s
y
ste
m
d
isp
a
tch
b
y
u
sin
g
a
n
o
v
e
l
d
if
f
e
re
n
ti
a
l
e
v
o
lu
ti
o
n
,
”
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
ic
a
l
S
c
ien
c
e
s
,
v
o
l
.
5
0
,
n
o
.
1
,
p
p
.
1
-
2
0
,
2
0
1
8
.
[1
2
]
Ch
a
o
-
L
u
n
g
Ch
ian
g
,
“
Op
ti
m
a
l
e
c
o
n
o
m
ic
e
m
issio
n
d
isp
a
tch
o
f
h
y
d
ro
th
e
rm
a
l
p
o
we
r
s
y
ste
m
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
&
En
e
rg
y
S
y
ste
ms
,
v
o
l.
2
9
,
n
o
.
6
,
p
p
.
4
6
2
-
4
6
9
,
2
0
0
7
.
[1
3
]
Zh
a
i
Ro
n
g
ro
n
g
,
e
t
a
l.
,
“
T
h
e
Op
ti
m
iza
ti
o
n
o
f
P
o
w
e
r
Disp
a
tch
f
o
r
H
y
d
ro
-
th
e
rm
a
l
P
o
w
e
r
S
y
ste
m
s,”
Pro
c
e
d
i
a
En
v
iro
n
me
n
ta
l
S
c
ien
c
e
s
,
v
o
l.
1
1
,
p
a
rt
B,
p
p
.
6
2
4
-
6
3
0
,
2
0
1
1
.
[1
4
]
Ch
e
n
,
X
.
,
e
t
a
l.
,
”
A
Tw
o
-
S
tag
e
stra
teg
y
to
h
a
n
d
le
e
q
u
a
li
ty
c
o
n
stra
in
ts
in
A
BC
-
b
a
se
d
p
o
w
e
r
e
c
o
n
o
m
ic
d
isp
a
tch
p
ro
b
lem
s,”
S
o
ft
Co
mp
u
ti
n
g
.
d
o
i:
1
0
.
1
0
0
7
/s0
0
5
0
0
-
0
1
8
-
0
3
7
2
3
-
4
,
v
o
l
.
2
3
,
n
o
.
1
5
,
p
p
.
6
6
7
9
-
6
6
9
6
,
2
0
1
9
.
[1
5
]
S.
Y
.
W
.
W
o
n
g
.
“
H
y
b
rid
si
m
u
late
d
a
n
n
e
a
li
n
g
/g
e
n
e
ti
c
a
lg
o
rit
h
m
a
p
p
r
o
a
c
h
to
sh
o
rt
-
term
h
y
d
ro
-
th
e
r
m
a
l
sc
h
e
d
u
li
n
g
w
it
h
m
u
lt
ip
le t
h
e
rm
a
l
p
lan
ts,
”
El
e
c
trica
l
Po
we
r a
n
d
En
e
rg
y
S
y
ste
ms
,
v
o
l.
2
3
,
n
o
.
7
,
p
p
.
5
6
5
-
5
7
5
,
2
0
0
1
.
[1
6
]
D.
Ka
ra
b
o
g
a
a
n
d
A
.
Ba
h
ri
y
e
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
,
”
Ap
p
li
e
d
M
a
th
e
ma
t
ics
a
n
d
Co
mp
u
t
a
ti
o
n
,
v
o
l.
2
1
4
,
n
o
.
1
,
p
p
.
1
0
8
-
1
3
2
,
2
0
0
9
.
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
Mo
d
ified
a
r
tifi
cia
l b
ee
co
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
a
d
a
p
tive
p
o
w
er sch
ed
u
lin
g
…
(
V
ijo
M J
o
y
)
1175
[1
7
]
K
.
L
e
n
in
a
n
d
B
.
Ra
v
in
d
h
ra
n
a
t
h
Re
d
d
y
,
“
V
o
lt
a
g
e
p
ro
f
il
e
e
n
h
a
n
c
e
m
e
n
t
a
n
d
re
d
u
c
ti
o
n
o
f
re
a
l
p
o
w
e
r
lo
ss
b
y
h
y
b
rid
b
io
g
e
o
g
ra
p
h
y
b
a
se
d
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
(
IJ
EE
I)
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
8
6
-
9
5
,
2
0
1
4
.
[1
8
]
Ra
sh
id
,
e
t
a
l.
,
“
A
h
y
b
rid
o
f
a
rt
if
icia
l
b
e
e
c
o
lo
n
y
,
g
e
n
e
ti
c
a
l
g
o
rit
h
m
,
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
d
iab
e
ti
c
m
e
ll
it
u
s
d
iag
n
o
sin
g
,
”
ARO
-
T
h
e
S
c
ie
n
ti
fi
c
J
o
u
rn
a
l
o
f
Ko
y
a
Un
ive
rs
it
y
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
5
5
-
6
4
,
2
0
1
8
.
[1
9
]
C
.
S
.
Ra
o
,
“
De
sig
n
o
f
a
rti
f
icia
l
in
telli
g
e
n
t
c
o
n
tr
o
ll
e
r
f
o
r
a
u
to
m
a
t
ic
g
e
n
e
ra
ti
o
n
c
o
n
tro
l
o
f
tw
o
a
re
a
h
y
d
ro
th
e
rm
a
l
s
y
ste
m
,
”
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
)
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
1
8
3
,
2
0
1
2
.
[2
0
]
A
.
S
u
li
m
a
n
a
n
d
Y
.
Zh
a
n
g
,
“
A
Re
v
ie
w
o
n
Ba
c
k
-
P
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
tw
o
rk
s in
th
e
A
p
p
li
c
a
ti
o
n
o
f
Re
m
o
te S
e
n
sin
g
Im
a
g
e
Cla
ss
i
f
ica
ti
o
n
,
”
J
o
u
r
n
a
l
o
f
Ea
rth
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
v
o
l.
5,
pp.
52
-
6
5
,
2
0
1
5
.
[2
1
]
M.
A
ls
m
a
d
i.
,
e
t
a
l.
,
“
Ba
c
k
p
ro
p
a
g
a
ti
o
n
a
lg
o
rit
h
m
:
th
e
b
e
st
a
lg
o
rit
h
m
a
m
o
n
g
th
e
m
u
lt
i
-
lay
e
r
p
e
rc
e
p
tro
n
a
lg
o
ri
th
m
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
Ne
two
rk
S
e
c
u
rity
,
v
o
l.
9
,
p
p
.
3
7
8
-
3
8
3
,
2
0
0
9
.
[2
2
]
D.
G
r
a
u
p
e
.
“
P
ri
n
c
ip
les
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
,
”
Ad
v
a
n
c
e
d
S
e
rie
s
in
Circ
u
it
s
a
n
d
S
y
ste
ms
,
S
in
g
a
p
o
re
,
Ha
c
k
e
n
sa
c
k
,
N.
J.:
W
o
rld
S
c
ien
ti
f
ic,
v
o
l.
7
,
n
o
.
3
,
2
0
1
3
.
[2
3
]
V
ij
o
M
Jo
y
a
n
d
S
Krish
n
a
k
u
m
a
r,
“
Eff
icie
n
t
lo
a
d
sc
h
e
d
u
li
n
g
m
e
th
o
d
f
o
r
p
o
w
e
r
m
a
n
a
g
e
m
e
n
t
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
Of
S
c
ien
ti
fi
c
&
T
e
c
h
n
o
lo
g
y
Res
e
a
rc
h
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
99
-
1
0
1
,
2
0
1
6
[2
4
]
D.
Ka
ra
b
o
g
a
a
n
d
B.
Ba
stu
rk
,
“
On
th
e
p
e
rf
o
rm
a
n
c
e
o
f
a
rti
f
i
c
ia
l
b
e
e
c
o
lo
n
y
(
A
BC)
a
l
g
o
rit
h
m
,
”
Ap
p
li
e
d
S
o
f
t
Co
mp
u
t
in
g
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
6
8
7
-
6
9
7
,
2
0
0
8
.
[2
5
]
A.
A.
S
e
k
e
r
a
n
d
M
.
H
.
Ho
c
a
o
g
l
u
,
"
A
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
f
o
r
o
p
ti
m
a
l
p
lac
e
m
e
n
t
a
n
d
siz
in
g
o
f
d
istri
b
u
ted
g
e
n
e
ra
ti
o
n
,
"
8
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
E
lec
trica
l
a
n
d
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
,
2
0
1
3
,
p
p
.
1
2
7
-
1
3
1
.
[2
6
]
D.
Ka
ra
b
o
g
a
a
n
d
B.
A
k
a
y
,
“
A
m
o
d
if
ied
A
rti
f
icia
l
Be
e
Co
lo
n
y
(A
BC)
a
lg
o
rit
h
m
f
o
r
c
o
n
stra
in
e
d
o
p
ti
m
iza
ti
o
n
p
ro
b
lem
s,”
Ap
p
li
e
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
3
0
2
1
-
3
0
3
1
,
2
0
1
1
[2
7
]
W
.
G
a
o
,
e
t
a
l.
,
“
A
g
lo
b
a
l
b
e
st
a
r
ti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
f
o
r
g
lo
b
a
l
o
p
ti
m
iz
a
ti
o
n
,
”
J
o
u
rn
a
l
o
f
Co
mp
u
t
a
ti
o
n
a
l
a
n
d
Ap
p
li
e
d
M
a
th
e
ma
ti
c
s
,
v
o
l.
2
3
6
,
n
o
.
1
1
,
p
p
.
2
7
4
1
-
2
7
5
3
,
2
0
1
2
.
[2
8
]
De
rv
is
Ka
ra
b
o
g
a
a
n
d
Ba
h
riy
e
A
k
a
y
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
,
”
Ap
p
li
e
d
M
a
th
e
ma
ti
c
s
&
Co
mp
u
t
a
ti
o
n
,
v
o
l
.
2
1
4
,
n
o
.
1
,
p
p
.
1
0
8
-
1
3
2
,
2
0
0
9.
[2
9
]
Ka
ra
b
o
g
a
,
D.
a
n
d
Ba
stu
rk
,
B.
,
“
A
p
o
w
e
r
f
u
l
a
n
d
e
ff
ici
e
n
t
a
lg
o
rit
h
m
f
o
r
n
u
m
e
rica
l
f
u
n
c
ti
o
n
o
p
t
im
i
z
a
ti
o
n
:
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
(
A
BC)
a
lg
o
rit
h
m
,
”
J
o
u
rn
a
l
o
f
Glo
b
a
l
Op
ti
miza
ti
o
n
,
v
o
l
.
3
9
,
n
o
.
3
,
p
p
.
4
5
9
-
4
7
1
,
2
0
0
7
.
[3
0
]
H.
Ha
rd
ian
sy
a
h
,
“
A
rti
f
ici
a
l
Be
e
Co
lo
n
y
A
lg
o
rit
h
m
f
o
r
Eco
n
o
m
i
c
L
o
a
d
Disp
a
tch
P
ro
b
lem
,
”
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
IJ
AI)
,
v
o
l.
2
,
n
o
.
2,
p
p
.
90
-
9
8
,
2
0
1
3
.
[3
1
]
C.
Oz
tu
rk
,
a
n
d
D.
Ka
ra
b
o
g
a
.
“
H
y
b
rid
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
f
o
r
n
e
u
ra
l
n
e
tw
o
rk
train
i
n
g
,
”
IEE
E
Co
n
g
re
ss
o
f
Evo
l
u
ti
o
n
a
ry
Co
mp
u
ta
ti
o
n
(
CEC),
p
p
.
8
4
-
88
,
2
0
1
1
.
B
I
O
G
RAP
H
Y
O
F
AUTHO
RS
V
ijo
M
J
o
y
re
c
e
iv
e
d
h
is
M
a
s
ter'
s
d
e
g
re
e
in
El
e
c
tro
n
ics
in
2
0
0
6
f
ro
m
M
a
h
a
tma
G
a
n
d
h
i
Un
iv
e
risit
y
,
Ko
tt
a
y
a
m
,
Ke
r
a
la.
Co
m
p
lete
d
h
is
M
.
T
e
c
h
in
El
e
c
tro
n
ics
w
it
h
a
sp
e
c
ializa
ti
o
n
i
n
Em
b
e
d
d
e
d
S
y
ste
m
De
si
g
n
f
ro
m
IG
NO
U
in
2
0
1
1
.
He
w
o
rk
in
g
a
s
f
a
c
u
lt
y
a
n
d
He
a
d
o
f
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
,
A
q
u
in
a
s
Co
ll
e
g
e
,
Ed
a
c
o
c
h
i
n
,
Ko
c
h
i,
I
n
d
ia
a
n
d
is
p
u
rs
u
in
g
h
is
re
se
a
rc
h
in
El
e
c
tro
n
ics
a
t
S
c
h
o
o
l
o
f
T
e
c
h
n
o
lo
g
y
&
A
p
p
li
e
d
S
c
ien
c
e
s,
M
a
h
a
t
m
a
Ga
n
d
h
i
Un
iv
e
risit
y
Re
g
io
n
a
l
Ce
n
ter,
E
d
a
p
p
a
ll
y
,
Ko
c
h
i.
His
c
u
rre
n
t
a
re
a
s
o
f
re
se
a
rc
h
in
c
lu
d
e
A
rti
f
icia
l
In
telli
g
e
n
c
e
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s
.
He
se
rv
e
d
a
s
a
r
e
v
ie
we
r
o
f
i
n
d
e
x
e
d
in
ter
n
a
ti
o
n
a
l
jo
u
rn
a
ls
in
c
lu
d
in
g
A
d
v
a
n
c
e
s
in
S
c
ien
c
e
,
T
e
c
h
n
o
lo
g
y
a
n
d
En
g
in
e
e
rin
g
S
y
ste
m
s
Jo
u
rn
a
l,
a
n
d
Am
e
rica
n
Jo
u
rn
a
l
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
a
n
d
A
p
p
li
c
a
ti
o
n
s.
He
h
a
s
ten
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
Dr
.
S
K
r
ish
n
a
k
u
m
a
r
is
a
d
o
c
to
ra
l
d
e
g
re
e
h
o
ld
e
r
in
T
h
in
F
il
m
D
e
v
ice
s
f
ro
m
M
a
h
a
t
m
a
G
a
n
d
h
i
Un
iv
e
rsit
y
,
Ko
tt
a
y
a
m
,
Ke
ra
la,
In
d
ia
in
1
9
9
5
.
C
o
m
p
lete
d
h
is
M
.
T
e
c
h
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
S
a
m
Hig
g
in
b
o
tt
o
m
Un
iv
e
rsity
o
f
Ag
ricu
lt
u
re
,
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
ien
c
e
s,
f
o
rm
e
rl
y
A
ll
a
h
a
b
a
d
Ag
r
icu
lt
u
ra
l
In
stit
u
te,
i
n
2
0
0
6
a
n
d
a
lso
g
o
t
M
CA
f
ro
m
I
G
N
OU
in
2
0
1
0
.
F
ro
m
2
0
1
3
t
o
2
0
1
7
h
e
w
o
rk
e
d
a
s
th
e
R
e
g
io
n
a
l
Dire
c
to
r
a
t
th
e
S
c
h
o
o
l
o
f
Tec
h
n
o
lo
g
y
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s,
Co
c
h
in
.
P
re
se
n
tl
y
h
e
is
a
re
se
a
rc
h
g
u
id
e
in
El
e
c
tro
n
ics
a
t
M
a
h
a
tma
Ga
n
d
h
i
Un
iv
e
rsit
y
.
H
is
c
u
rre
n
t
a
re
a
o
f
re
se
a
r
c
h
a
c
ti
v
it
ies
is
in
A
rti
f
ic
ial
In
telli
g
e
n
c
e
,
Circu
it
De
sig
n
,
a
n
d
Im
a
g
e
p
ro
c
e
ss
in
g
.
He
h
a
s
tw
e
n
t
y
-
f
o
u
r
y
e
a
r
s
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
a
n
A
ss
o
c
iate
M
e
m
b
e
r
o
f
th
e
In
stit
u
te
o
f
En
g
in
e
e
rs,
In
d
ia.
He
se
rv
e
d
a
s
a
m
e
m
b
e
r
o
f
th
e
A
c
a
d
e
m
ic
c
o
u
n
c
il
o
f
M
G
Un
iv
e
rsity
,
Ko
tt
a
y
a
m
a
n
d
a
m
e
m
b
e
r
o
f
th
e
Bo
a
rd
o
f
stu
d
ies
o
f
Ca
li
c
u
t
Un
iv
e
rsit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.