I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
39
,
No
.
2
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
7
6
1
~
7
7
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/
ijeec
s
.
v
39
.i
2
.
pp
761
-
7
7
3
761
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Artif
i
cia
l
neura
l
network
ba
sed lo
a
d f
lo
w
a
na
ly
sis
of
ra
dia
l
distribut
io
n sy
ste
m in
K
urdis
tan
r
eg
io
n
Wa
rda
H
us
s
ein
A
li
1
,
Da
na
O
.
Qad
e
r
1
,
M
o
ha
m
ed
A.
H
u
s
s
ein
2
1
D
e
p
a
r
t
me
n
t
o
f
P
o
w
e
r
a
n
d
C
o
n
t
r
o
l
En
g
i
n
e
e
r
i
n
g
,
T
e
c
h
n
i
c
a
l
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
S
u
l
a
i
m
a
n
i
P
o
l
y
t
e
c
h
n
i
c
U
n
i
v
e
r
si
t
y
,
S
u
l
a
i
ma
n
i
-
K
u
r
d
i
st
a
n
,
I
r
a
q
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
S
u
l
a
i
m
a
n
i
U
n
i
v
e
r
si
t
y
,
S
u
l
a
i
m
a
n
i
-
K
u
r
d
i
s
t
a
n
,
I
r
a
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
2
,
2
0
2
4
R
ev
is
ed
Ap
r
30
,
2
0
2
5
Acc
ep
ted
J
u
l
2
,
2
0
2
5
To
d
a
y
e
lec
tri
c
e
n
e
rg
y
is
th
e
m
o
st
c
o
m
m
o
n
l
y
u
se
d
so
u
rc
e
in
t
h
e
wo
rld
.
P
o
we
r
flo
w
(lo
a
d
flo
w)
a
n
a
ly
sis
is
c
o
n
c
id
e
r
d
a
s
th
e
b
a
c
k
b
o
n
e
o
f
a
n
y
p
o
we
r
sy
ste
m
a
n
a
ly
sis
a
n
d
d
e
sig
n
;
t
h
e
y
h
a
v
e
a
g
re
a
t
n
e
c
e
ss
it
y
fo
r
o
p
e
ra
ti
n
g
sy
ste
m
s,
fu
t
u
re
p
lan
n
i
n
g
,
fa
u
lt
a
n
a
ly
sis,
a
n
d
c
o
n
ti
n
g
e
n
c
y
a
n
a
ly
sis.
F
o
r
b
e
tt
e
r
u
ti
li
z
a
ti
o
n
o
f
e
lec
tri
c
a
l
p
o
we
r,
o
ff
-
li
n
e
m
o
d
e
li
n
g
a
n
d
sim
u
latio
n
o
f
p
o
we
r
sy
ste
m
s
u
sin
g
p
o
we
rfu
l
so
f
twa
re
a
re
e
ss
e
n
ti
a
l
a
n
d
sig
n
ifi
c
a
n
t
tas
k
e
sp
e
c
ially
in
d
e
v
e
lo
p
in
g
c
o
u
n
tri
e
s
a
n
d
re
g
io
n
s.
T
h
e
re
fo
re
,
th
is
p
a
p
e
r
p
e
rfo
rm
s
a
c
o
m
p
a
riso
n
st
u
d
y
o
f
c
o
n
v
e
n
t
io
n
a
l
a
n
d
n
o
n
-
c
o
n
v
e
n
ti
o
n
a
l
l
o
a
d
flo
w
tec
h
n
iq
u
e
s
fo
r
a
2
4
-
Bu
s
ra
d
ial
d
istri
b
u
ti
o
n
sy
ste
m
i
n
th
e
g
o
v
e
r
n
o
ra
te
o
f
S
u
lay
m
a
n
i
y
a
h
.
T
h
e
c
o
n
v
e
n
ti
o
n
a
l
p
o
we
r
flo
w
tec
h
n
i
q
u
e
s
in
c
lu
d
e
th
e
Ne
wto
n
-
Ra
p
h
s
o
n
(NR),
a
n
d
G
a
u
ss
-
S
e
id
e
l
(G
S
)
te
c
h
n
iq
u
e
s,
wh
il
e
th
e
n
o
n
-
c
o
n
v
e
n
ti
o
n
a
l
lo
a
d
flo
w
tec
h
n
iq
u
e
u
ti
li
z
e
s
th
e
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
(AN
N).
M
o
d
e
li
n
g
,
sim
u
latio
n
,
a
n
d
a
n
a
ly
sis
o
f
t
h
e
2
4
-
B
u
s
fe
e
d
e
r
a
re
p
e
rfo
rm
e
d
u
si
n
g
M
ATP
OWE
R
sim
u
latio
n
to
o
l.
Th
e
M
AT
P
O
WE
R
a
n
d
n
e
u
ra
l
n
e
two
r
k
tec
h
n
i
q
u
e
s
a
re
imp
lem
e
n
ted
in
d
e
p
e
n
d
e
n
tl
y
,
a
n
d
it
h
a
s
b
e
e
n
p
ro
v
e
d
t
h
a
t
AN
N
m
o
d
e
l
e
fficie
n
tl
y
e
stim
a
ted
t
h
e
p
o
we
r
f
lo
w
a
n
a
ly
sis
fo
r
th
e
sy
ste
m
m
e
n
ti
o
n
e
d
a
b
o
v
e
,
t
h
e
h
ig
h
re
g
re
ss
io
n
v
a
lu
e
s
o
f
n
e
a
rly
0
.
9
9
9
in
d
ica
tes
t
h
a
t
t
h
e
AN
N
m
o
d
e
l
c
a
n
b
e
u
se
d
a
s
a
n
e
fficie
n
t
to
o
l
t
o
p
e
rf
o
rm
p
o
we
r
flo
w
a
n
a
ly
sis.
K
ey
w
o
r
d
s
:
ANN
Dis
tr
ib
u
tio
n
s
y
s
tem
Gau
s
s
-
Se
id
el
L
o
ad
f
lo
w
a
n
aly
s
is
MA
T
POW
E
R
New
to
n
-
R
ap
h
s
o
n
Po
wer
s
y
s
tem
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
ar
d
a
Hu
s
s
e
in
Ali
Dep
ar
tm
en
t o
f
Po
wer
an
d
C
o
n
tr
o
l E
n
g
in
ee
r
in
g
,
T
ec
h
n
ical
C
o
lleg
e
o
f
E
n
g
in
ee
r
i
n
g
Su
laim
an
i Po
ly
tech
n
ic
Un
iv
er
s
ity
Su
laim
an
i
-
Ku
r
d
is
tan
,
I
r
a
q
E
m
ail:
war
d
a.
ali@
s
p
u
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
B
asically
,
a
p
o
wer
s
y
s
tem
is
a
v
er
y
co
m
p
lex
an
d
h
ig
h
ly
in
te
r
co
n
n
ec
ted
n
etwo
r
k
,
co
n
s
is
tin
g
o
f
p
o
wer
g
en
er
atio
n
p
la
n
ts
,
tr
an
s
m
is
s
i
o
n
lin
es,
tr
an
s
f
o
r
m
er
s
,
d
is
tr
i
b
u
tio
n
p
lan
ts
,
an
d
e
n
er
g
y
co
n
s
u
m
er
s
.
P
r
o
v
id
in
g
in
v
ar
iab
ly
h
ig
h
-
q
u
ality
s
er
v
ice
to
th
e
co
n
s
u
m
er
s
is
an
es
s
en
tial
r
eq
u
ir
em
en
t
f
o
r
p
o
wer
s
y
s
tem
s
[
1
]
.
Gr
id
o
p
er
ato
r
s
h
ig
h
ly
co
n
s
id
er
th
e
s
tead
y
s
tate
b
eh
a
v
io
r
o
f
p
o
wer
s
y
s
tem
s
to
esti
m
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
o
wer
s
y
s
tem
an
d
d
eter
m
i
n
e
if
th
e
p
o
wer
s
y
s
tem
p
er
f
o
r
m
s
p
r
o
p
er
l
y
f
r
o
m
b
o
th
g
en
er
atio
n
an
d
lo
ad
asp
ec
ts
.
T
h
e
s
tead
y
s
tate
b
eh
av
io
r
o
f
p
o
wer
s
y
s
tem
s
ca
n
b
e
o
b
tain
ed
f
r
o
m
th
e
p
o
wer
f
lo
w
an
aly
s
is
to
id
en
tify
th
e
b
est
o
p
er
atio
n
o
f
ex
is
tin
g
s
y
s
tem
s
,
r
eq
u
ir
ed
co
n
tr
o
l a
lg
o
r
ith
m
,
f
u
t
u
r
e
p
la
n
n
in
g
an
d
d
esig
n
i
n
g
th
e
f
u
tu
r
e
ex
p
a
n
s
io
n
,
p
o
wer
f
lo
w
an
aly
s
is
in
d
icate
s
th
e
m
o
s
t
ef
f
ec
tiv
e
way
to
d
o
th
at.
T
h
e
lo
ad
f
lo
w
an
aly
s
is
in
v
o
lv
es
co
m
p
u
tatio
n
o
f
th
e
m
a
g
n
itu
d
e
an
d
p
h
ase
a
n
g
le
o
f
t
h
e
v
o
ltag
es
ac
r
o
s
s
all
b
u
s
es
in
elec
tr
ic
p
o
wer
s
y
s
tem
ex
ce
p
t
th
e
s
la
ck
b
u
s
.
T
h
e
p
o
wer
f
lo
w
t
h
r
o
u
g
h
th
e
tr
an
s
m
is
s
io
n
lin
e
ca
n
b
e
d
e
ter
m
in
ed
wh
e
r
e
th
e
v
o
ltag
e
m
ag
n
itu
d
e
a
n
d
p
h
ase
an
g
les
f
o
r
all
b
u
s
es
ar
e
k
n
o
wn
.
T
h
e
m
o
s
t
u
s
ed
alg
o
r
ith
m
s
u
s
ed
f
o
r
lo
ad
f
l
o
w
s
o
lu
tio
n
ar
e
Gau
s
s
-
Seid
el
(
GS)
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
2
,
Au
g
u
s
t
20
25
:
76
1
-
7
7
3
762
New
to
n
-
R
ap
h
s
o
n
(
NR
)
,
an
d
f
ast
d
ec
o
u
p
le
d
(
FD)
lo
ad
f
lo
w
[
2
]
–
[
5
]
.
Ash
r
ith
et
a
l.
[
6
]
e
x
a
m
in
ed
t
h
e
GS,
NR
,
an
d
FD
m
eth
o
d
s
to
d
eter
m
in
e
th
e
s
tead
y
-
s
tate
o
p
er
atin
g
co
n
d
itio
n
s
,
GS
was
b
est
o
p
tio
n
f
o
r
s
m
all
s
y
s
tem
s
as
it c
o
n
v
er
g
e
d
ad
eq
u
ately
,
T
h
e
ac
cu
r
ac
y
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
o
f
t
h
e
NR
an
d
FD
m
e
th
o
d
s
wo
r
k
e
d
m
o
r
e
ef
f
icien
tly
with
m
ed
iu
m
s
ca
led
s
ey
s
tem
s
.
Als
o
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
m
o
d
els
h
av
e
ap
p
ea
r
ed
a
n
d
ef
f
ec
tiv
ely
wo
r
k
ed
in
s
o
lv
in
g
p
o
wer
s
y
s
tem
lo
ad
f
lo
w
an
aly
s
is
[
7
]
,
[
8
]
.
C
o
m
p
ar
e
d
to
t
h
e
a
v
ailab
le
d
eter
m
in
is
tic
iter
ativ
e
alg
o
r
ith
m
s
,
r
esu
lts
o
b
tain
ed
ef
f
icien
tly
f
r
o
m
th
e
ANN
m
o
d
el,
an
d
it
ca
n
b
e
ad
ap
ted
to
v
ar
io
u
s
p
r
o
b
le
m
s
ets
in
d
if
f
er
en
t
ap
p
licatio
n
s
[
9
],
[
10
]
.
W
h
ile
d
eter
m
in
is
tic
ap
p
r
o
ac
h
ca
n
p
er
f
o
r
m
lo
a
d
f
lo
w
u
s
in
g
its
o
wn
l
o
ad
f
lo
w
i
n
p
u
t d
ata
s
et
an
d
g
en
er
ates
th
e
c
o
r
r
esp
o
n
d
in
g
lo
ad
f
lo
w
o
u
tp
u
t
d
ata
s
et
[
11
]
,
ANN
ca
n
b
e
ap
p
lied
in
th
e
p
o
we
r
f
lo
w
a
n
a
l
y
s
i
s
a
f
t
e
r
i
t
h
a
s
b
e
e
n
t
r
a
i
n
e
d
v
e
r
y
w
e
l
l
w
i
t
h
a
l
o
a
d
f
l
o
w
i
n
p
u
t
d
a
t
a
s
e
t
a
n
d
c
o
r
r
e
s
p
o
n
d
i
n
g
o
u
t
p
u
t
d
a
t
a
s
e
t
[
12
].
Ho
wev
er
,
af
ter
th
e
ANN
m
o
d
el
is
tr
ain
ed
,
it
wo
r
k
s
lik
e
th
e
d
eter
m
in
is
tic
m
o
d
el
[
11
]
.
J
aiswal
et
a
l.
[
13
]
th
e
lo
ad
f
lo
w
an
al
y
s
is
m
eth
o
d
s
b
ased
o
n
ar
tific
ial
n
e
u
r
al
n
et
wo
r
k
is
ap
p
lied
o
n
I
E
E
E
3
0
,
5
7
,
a
n
d
1
1
8
b
u
s
s
y
s
tem
s
,
co
m
p
ar
in
g
r
esu
lts
to
co
n
v
en
tio
n
al
m
eth
o
d
r
esu
lts
,
th
e
in
tellig
en
t
p
o
wer
f
lo
w
te
ch
n
iq
u
e
r
esu
lts
ar
e
m
o
r
e
ac
c
u
r
ate.
I
n
v
esti
g
atin
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
m
icr
o
g
r
id
s
y
s
tem
f
o
cu
s
in
g
o
n
lo
ad
f
lo
w
s
tu
d
ies,
s
h
o
ws
th
at
th
e
lo
ad
f
lo
w
ca
lc
u
latio
n
s
u
s
i
n
g
th
e
m
o
d
er
n
in
teleg
en
ce
m
eth
o
d
s
lik
e
ANN
e
x
p
er
ien
ce
h
ig
h
e
f
f
icien
cy
an
d
m
in
im
u
m
lo
s
s
es
wh
en
co
m
p
air
in
g
with
co
n
v
en
tio
n
al
m
eth
o
d
[
14
]
.
R
an
i
an
d
R
ao
[
15
]
s
u
g
g
ested
a
n
eu
r
al
n
etwo
r
k
with
m
u
ltil
ay
er
f
ee
d
f
o
r
war
d
f
o
r
o
n
lin
e
p
o
wer
f
lo
w
ass
ess
m
en
t
u
n
d
er
d
ata
u
n
ce
r
tain
ty
,
th
e
o
b
s
er
v
e
d
r
esu
lts
s
h
o
ws
th
at
m
u
ltil
ay
er
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
r
esu
lts
is
v
er
y
s
im
ilar
to
th
e
in
ter
v
al
ar
ith
m
etic
tech
n
iq
u
e
.
An
ex
ten
s
iv
e
r
ev
ie
w
is
im
p
lem
en
ted
o
n
m
o
s
t
tr
a
d
itio
n
al
an
d
n
o
n
co
n
v
en
tio
n
al
tech
n
iq
u
e
lo
ad
f
lo
w
s
o
lu
tio
n
s
,
th
e
aim
was
ev
alu
atin
g
th
eir
s
tr
en
g
th
s
a
n
d
wea
k
n
ess
es,
an
d
its
co
n
clu
d
e
d
th
at
NR
is
th
e
m
o
s
t
ef
f
ec
tiv
e
b
etwe
en
c
o
n
v
e
n
tio
n
al
m
eth
o
d
s
an
d
n
o
n
co
n
v
en
ti
o
n
al
ar
tific
ial
in
teleg
en
ce
m
e
th
o
d
es
ten
d
to
b
e
co
m
p
u
tatio
n
ally
q
u
ick
[
16
].
W
ell
p
r
o
v
ed
d
eter
m
in
is
tic
lo
a
d
f
lo
w
alg
o
r
ith
m
s
,
s
u
ch
as
NR
an
d
GS
m
eth
o
d
s
,
ca
n
p
r
o
v
id
e
th
e
t
r
ain
in
g
i
n
p
u
t
-
o
u
tp
u
t
d
ataset
f
o
r
an
ANN
[
14
].
T
h
is
ar
ticle
aim
s
to
s
tu
d
y
p
o
wer
f
lo
w
p
r
o
b
lem
u
s
in
g
th
e
c
o
n
v
en
tio
n
al
m
eth
o
d
s
(
NR
an
d
GS)
an
d
th
e
Neu
r
al
-
Netwo
r
k
ap
p
r
o
ac
h
,
p
o
wer
f
lo
w
s
o
lu
tio
n
s
p
r
esen
ted
u
s
in
g
d
ev
elo
p
e
d
ANN,
NR
an
d
GS
o
n
2
4
-
B
u
s
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
,
d
et
er
m
in
in
g
t
h
e
b
est
way
to
p
e
r
f
o
r
m
p
o
wer
f
l
o
w
s
o
lu
tio
n
is
an
o
th
er
o
b
jectiv
e
o
f
th
e
wo
r
k
.
T
h
e
r
esu
lts
s
h
o
w
th
at
p
o
wer
f
lo
w
an
aly
s
is
ca
n
b
e
ca
r
r
ied
o
u
t
u
s
in
g
th
e
ANN
with
m
in
m
u
m
er
r
o
r
s
wh
en
co
m
p
air
i
n
g
th
e
ac
tu
al
v
alu
es
o
f
b
u
s
v
o
ltag
e
an
d
th
e
A
NN
o
u
tp
u
t.
Usi
n
g
ANN
in
lo
ad
f
lo
w
an
aly
s
is
f
o
r
p
o
wer
s
y
s
tem
s
s
o
lv
es
m
an
y
p
r
o
b
lem
s
,
th
e
ANN
tech
n
iq
u
es
h
av
e
th
e
a
d
v
an
ta
g
e
o
f
n
ee
d
i
n
g
f
ew
p
ar
am
eter
s
to
o
b
tain
m
o
r
e
e
f
f
icien
t
s
o
lu
tio
n
with
lo
w
co
m
p
u
tatio
n
al
tim
e
with
v
er
y
h
ig
h
ac
c
u
r
ac
y
,
d
esp
ite
it
is
in
s
en
s
itiv
it
y
to
in
itial
v
alu
es
f
o
r
in
p
u
t
v
ar
i
ab
les
o
n
t
h
e
o
t
h
er
h
an
d
tr
ad
iti
o
n
al
lo
a
d
f
lo
w
tech
n
iq
u
es
(
N
R
an
d
GS)
a
r
e
v
e
r
y
co
m
p
lex
at
d
esig
n
in
g
,
f
ailed
to
co
n
v
er
g
e
an
d
n
ee
d
s
lar
g
e
co
n
tr
o
llin
g
p
ar
a
m
eter
s
,
m
o
r
e
o
v
er
t
h
e
p
u
r
p
o
s
e
o
f
u
s
in
g
ANN
is
to
m
ak
e
a
n
etwo
r
k
th
at
wo
r
k
s
p
er
f
ec
tly
ev
en
wh
en
n
ew
in
s
tan
ce
s
th
at
n
ev
er
ex
p
er
ien
ce
d
o
r
tr
ain
ed
p
r
ev
io
u
s
ly
.
T
h
e
r
eq
u
ir
ed
d
atasets
f
o
r
tr
ain
in
g
AN
N
ar
e
g
e
n
er
ated
b
y
a
well
-
k
n
o
wn
c
o
n
v
e
n
tio
n
al
m
eth
o
d
o
f
N
-
R
tech
n
iq
u
e
an
d
it
is
u
s
ed
to
tr
ain
p
r
o
p
o
s
ed
AN
N
in
MA
T
L
AB
to
o
l.
2.
P
AP
E
R
S
T
RUC
T
UR
E
T
h
is
p
ap
er
is
s
tr
u
ctu
r
ed
as
th
e
f
o
llo
win
g
:
s
ec
tio
n
3
in
tr
o
d
u
ce
s
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
ies
an
d
Sectio
n
4
p
r
o
v
id
es
d
etails
o
f
a
ca
s
e
s
tu
d
y
f
o
r
th
e
p
o
we
r
f
lo
w.
R
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
es
ar
e
p
r
esen
ted
an
d
d
is
cu
s
s
ed
in
Sectio
n
5
.
Fin
ally
,
c
o
n
clu
s
io
n
s
a
r
e
d
r
awn
in
Sectio
n
6
.
3.
M
AT
E
R
I
AL
S
AND
M
E
T
H
O
DS
T
h
e
f
ee
d
er
b
u
s
is
a
n
o
d
e
t
h
at
co
n
n
ec
ts
m
o
r
e
t
h
an
o
n
e
lin
e,
l
o
ad
,
o
r
a
g
e
n
er
ato
r
.
I
n
a
p
o
wer
s
y
s
tem
,
ev
er
y
b
u
s
h
as
th
e
f
o
llo
win
g
v
ar
iab
les:
v
o
ltag
e
m
ag
n
itu
d
e
,
v
o
ltag
e
p
h
ase
an
g
le,
r
ea
l
p
o
wer
,
an
d
r
ea
ctiv
e
p
o
wer
,
two
o
f
t
h
ese
v
ar
iab
le
s
ar
e
alwa
y
s
k
n
o
wn
an
d
th
e
o
th
er
two
m
u
s
t
b
e
ca
lcu
lated
b
y
u
s
in
g
s
p
ec
if
ied
eq
u
atio
n
s
[
1
7
]
.
I
n
ad
d
itio
n
,
b
u
s
f
ee
d
er
s
ar
e
class
if
ied
in
to
th
r
ee
ty
p
es:
s
la
ck
b
u
s
,
v
o
ltag
e
co
n
tr
o
l
(
PV)
b
u
s
,
an
d
lo
ad
b
u
s
(
PQ)
,
as lis
ted
in
T
ab
le
1
.
T
ab
le
1
.
T
y
p
es o
f
f
ee
d
er
b
u
s
es
B
u
s
t
y
p
e
s
V
a
r
i
a
b
l
e
s
P
Q
V
δ
S
l
a
c
k
U
n
k
n
o
w
n
U
n
k
n
o
w
n
k
n
o
w
n
k
n
o
w
n
G
e
n
e
r
a
t
o
r
k
n
o
w
n
U
n
k
n
o
w
n
k
n
o
w
n
U
n
k
n
o
w
n
Lo
a
d
k
n
o
w
n
k
n
o
w
n
U
n
k
n
o
w
n
U
n
k
n
o
w
n
Stead
y
s
tate
p
o
wer
s
u
p
p
lied
b
y
v
ar
i
o
u
s
b
u
s
s
in
an
y
p
o
we
r
s
y
s
tem
ca
n
b
e
illu
s
tr
ated
in
ter
m
s
o
f
n
o
n
lin
ea
r
s
et
o
f
e
q
u
atio
n
s
,
m
a
n
y
n
u
m
er
ical
f
o
r
m
u
latio
n
s
wer
e
p
r
o
p
o
s
ed
an
d
u
s
ed
in
th
e
la
s
t
d
ec
ad
es
in
o
r
d
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
b
a
s
ed
lo
a
d
flo
w
a
n
a
lysi
s
o
f
r
a
d
ia
l
d
is
tr
ib
u
tio
n
s
ystem
…
(
Wa
r
d
a
Hu
s
s
ein
A
li
)
763
to
s
o
lv
e
lo
ad
f
lo
w
an
aly
s
is
n
o
n
lin
ea
r
ea
u
atio
n
s
.
As
m
en
tio
n
ed
p
r
e
v
io
u
s
ly
,
t
h
e
m
o
s
t
f
r
e
q
u
en
tly
u
s
ed
iter
ativ
e
tech
n
iq
u
es
ar
e
th
e
GS,
th
e
N
R
,
an
d
th
e
FD
[
1
8
]
,
th
r
ee
tech
n
iq
u
es
ar
e
u
s
ed
to
p
e
r
f
o
r
m
lo
ad
f
lo
w
o
n
a
2
4
-
B
u
s
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
ea
c
h
tech
n
iq
u
e
im
p
lem
en
te
d
s
ep
er
aitly
,
u
s
in
g
th
e
d
ata
o
f
th
e
m
en
t
io
n
ed
s
y
s
tem
as
an
in
p
u
t.
T
h
e
i
n
itial
wo
r
k
s
tag
e
in
p
er
f
o
r
m
in
g
p
o
wer
f
lo
w
an
aly
s
is
is
b
u
ild
in
g
th
e
Y
-
b
u
s
ad
m
ittan
ce
m
atr
ix
u
s
in
g
in
f
o
r
m
atio
n
f
r
o
m
th
e
tr
an
s
m
is
s
io
n
lin
es
an
d
th
e
t
r
an
s
f
o
r
m
er
s
o
f
th
e
s
y
s
tem
m
en
tio
n
ed
[
1
9
]
.
T
o
s
tu
d
y
th
e
p
o
wer
s
y
s
tem
,
n
etwo
r
k
a
n
o
d
al
f
o
r
m
u
la
u
s
in
g
th
e
Y
-
b
u
s
ca
n
b
e
g
i
v
en
in
(
1
)
.
I
=
Y
B
us
V
(
1
)
In
(
1
)
ca
n
b
e
ex
p
r
ess
ed
in
a
g
e
n
er
alize
d
f
o
r
m
f
o
r
an
n
b
u
s
s
y
s
tem
u
s
in
g
(
2
)
.
I
i
=
∑
Y
ij
n
j
=
1
V
j
for
i
=
1
,
2
,
3
,
…
…
,
n
(
2
)
T
h
e
ap
p
a
r
en
t p
o
wer
an
d
th
e
c
u
r
r
en
t
d
eliv
er
ed
to
th
e
b
u
s
(
i)
ar
e
g
iv
en
b
y
(
3
)
a
n
d
(
4
)
:
P
i
+
j
Q
i
=
V
i
I
i
∗
(
3
)
I
i
=
P
i
+
j
Q
i
V
i
∗
(
4
)
Su
b
s
titu
tin
g
(
3
)
a
n
d
(
4
)
in
t
o
(
2
)
,
(
5
)
is
d
eter
m
in
e
d
.
P
i
+
j
Q
i
V
i
∗
=
V
i
∑
Y
ij
n
j
=
1
−
∑
Y
ij
n
j
=
1
V
j
;
j
≠
i
(
5
)
T
h
e
co
m
p
le
x
p
o
we
r
in
jectio
n
o
f
th
e
s
y
s
tem
is
g
iv
en
b
y
(
6
)
a
n
d
(
7
)
.
S
i
=
S
Gi
−
S
Di
(
6
)
S
i
=
∑
S
ik
n
k
−
S
Di
(
7
)
I
n
(
6
)
a
n
d
(
7
)
:
k
=
1
,
2
…
n
;
i
=
1
,
2
…
n
.
S
i
m
i
l
a
r
l
y
,
t
h
e
p
h
a
s
o
r
o
f
c
u
r
r
e
n
t
i
n
j
e
c
t
i
o
n
s
i
s
g
i
v
e
n
b
y
(
8
)
,
(
9
)
,
a
n
d
(
1
0
)
.
I
i
=
I
Gi
−
I
Di
=
∑
Y
ik
n
k
V
ik
(
8
)
S
i
=
V
i
I
i
∗
=
V
i
∑
Y
ik
∗
n
k
V
k
∗
(
9
)
S
i
=
∑
|
V
i
|
n
k
|
V
k
|
e
j
δ
ik
(
G
ik
−
j
B
ik
)
(
1
0
)
Sep
ar
atio
n
o
f
th
e
p
o
wer
f
lo
w
f
o
r
m
u
latio
n
i
n
to
r
ea
l a
n
d
im
ag
i
n
ar
y
p
a
r
ts
is
g
iv
en
b
y
(
1
1
)
,
(
1
2
)
,
an
d
(
1
3
)
.
S
i
=
P
i
+
j
Q
i
=
∑
|
V
i
|
n
k
|
V
k
|
e
j
δ
ik
(
G
ik
−
j
B
ik
)
(
1
1
)
P
i
=
∑
|
V
i
|
n
k
|
V
k
|
[
G
ik
c
os
(
δ
ik
)
+
B
ik
s
in
(
δ
ik
)
]
(
1
2
)
Q
i
=
∑
|
V
i
|
n
k
|
V
k
|
[
G
ik
c
os
(
δ
ik
)
−
B
ik
s
in
(
δ
ik
)
]
(
1
3
)
I
n
(
1
1
)
,
(
1
2
)
,
a
n
d
(
1
3
)
u
s
e
i
ter
ativ
e
m
eth
o
d
s
to
s
o
lv
e
t
h
e
lo
ad
f
l
o
w
p
r
o
b
lem
s
.
T
h
er
e
f
o
r
e,
t
h
e
f
o
llo
win
g
s
u
b
s
e
c
t
i
o
n
s
p
r
o
v
i
d
e
r
e
v
i
e
w
o
f
t
h
e
g
e
n
e
r
a
l
f
o
r
m
s
f
o
r
t
h
r
e
e
d
i
f
f
e
r
e
n
t
s
o
l
u
t
i
o
n
t
e
c
h
n
i
q
u
e
s
:
G
S
,
N
R
a
n
d
A
N
N
[
2
0
]
.
3
.
1
.
G
a
us
s
-
Sid
el
m
et
ho
d
T
h
is
m
eth
o
d
is
an
iter
ativ
e
m
eth
o
d
o
f
s
o
lv
i
n
g
a
s
et
o
f
n
o
n
lin
ea
r
alg
eb
r
aic
eq
u
atio
n
s
[
2
0
]
.
T
h
e
m
eth
o
d
iter
ativ
ely
s
o
l
v
es
th
ese
n
o
n
lin
ea
r
eq
u
atio
n
s
an
d
ca
l
cu
lates
th
e
v
o
ltag
e
m
ag
n
itu
d
e
an
d
p
h
ase
an
g
le
at
ea
ch
b
u
s
u
n
til
co
n
v
er
g
e
n
ce
is
ac
h
iev
ed
s
in
ce
th
e
er
r
o
r
r
ea
c
h
es
ac
ce
p
tab
le
r
an
g
e
[
2
1
]
,
b
a
s
ed
o
n
th
e
s
y
s
tem
n
o
d
al
v
o
ltag
e
o
f
(
1
4
)
,
|
I
|
=
|
Y
B
us
|
|
V
|
(
1
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
2
,
Au
g
u
s
t
20
25
:
76
1
-
7
7
3
764
T
h
e
GS
m
eth
o
d
u
s
es
iter
ativ
e
m
eth
o
d
f
o
r
s
o
lv
in
g
th
e
p
o
we
r
f
lo
w
f
o
r
m
u
la
o
f
(
1
5
)
.
T
h
e
s
u
p
er
s
cr
ip
ts
(
*
)
a
n
d
(
T
)
d
en
o
te
th
e
co
n
ju
g
ates a
n
d
tr
an
s
p
o
s
e
p
r
o
ce
s
s
es r
esp
ec
tiv
ely
[
2
0
]
-
[
2
3
]
.
|
P
+
jQ
|
=
|
V
T
|
|
Y
B
us
∗
V
∗
|
(
1
5
)
T
h
is
tech
n
iq
u
e
is
wid
ely
u
s
ed
b
ec
au
s
e
o
f
its
s
im
p
licity
an
d
less
tim
e
r
eq
u
i
r
ed
f
o
r
c
o
m
p
u
tatio
n
o
f
o
n
e
iter
atio
n
,
b
u
t
it
h
as
c
o
n
v
e
r
g
e
n
ce
p
r
o
b
lem
b
ec
au
s
e
o
f
th
e
l
ar
g
e
n
u
m
b
er
o
f
iter
atio
n
s
,
Al
s
o
G
-
S
is
s
en
s
itiv
e
wh
en
s
elec
tin
g
s
lack
b
u
s
,
as th
e
co
n
v
er
g
en
ce
s
p
ee
d
is
d
ep
en
d
en
t o
n
it.
3
.
2
.
New
t
o
n
-
Ra
ph
s
o
n m
et
ho
d
T
h
e
m
o
s
t
tech
n
iq
u
e
u
s
ed
f
o
r
p
o
wer
f
lo
w
s
o
lu
tio
n
is
NR
;
it
is
f
ast
in
co
m
p
u
tatio
n
with
ac
cu
r
ate
r
esu
lts
,
an
d
th
e
s
y
s
tem
s
ize
d
o
es
n
o
t
ef
f
ec
ts
s
o
m
u
ch
o
n
t
h
e
n
u
m
b
er
o
f
iter
atio
n
s
.
T
h
e
d
r
aw
b
ac
k
s
o
f
th
is
m
eth
o
d
ar
e
d
if
f
icu
lties
o
f
s
o
lu
tio
n
tech
n
iq
u
es,
wh
ich
r
eq
u
ir
e
h
ig
h
er
c
o
m
p
u
tatio
n
al
tim
e
p
e
r
iter
atio
n
.
T
h
e
NR
iter
ativ
e
m
eth
o
d
f
o
r
m
u
lates
a
n
d
s
o
lv
es
th
e
p
o
wer
f
l
o
w
d
es
cr
ib
ed
u
s
in
g
(
1
6
)
in
te
r
m
s
o
f
t
h
e
J
ac
o
b
ea
n
m
atr
ix
elem
en
ts
(
J
1
,
J
2
,
J
3
,
an
d
J
4
)
.
|
∆
P
∆
Q
|
=
|
J1
J2
J3
J4
|
|
∆
δ
∆
V
|
(
1
6
)
I
n
(
1
6
)
,
Δ
P a
n
d
Δ
Q
r
ef
er
to
th
e
d
if
f
er
en
ce
b
etwe
en
th
e
ca
lcu
lated
v
alu
e
an
d
th
e
s
p
ec
i
f
ied
v
alu
e
o
f
th
e
r
ea
l a
n
d
r
ea
ctiv
e
p
o
wer
o
f
t
h
e
f
ee
d
e
r
b
u
s
,
r
esp
ec
tiv
ely
.
Δ
V
an
d
Δ
δ
r
ep
r
esen
t
th
e
v
o
ltag
e
m
a
g
n
itu
d
e
an
d
v
o
ltag
e
p
h
ase
an
g
le
o
f
t
h
e
f
ee
d
e
r
b
u
s
,
r
esp
ec
tiv
el
y
[
2
0
]
,
[
2
2
]
.
3
.
3
.
Art
if
ici
a
l neura
l net
wo
rk
Ma
n
y
tim
es
co
n
v
e
n
tio
n
al
tec
h
n
iq
u
es
ar
e
n
o
t
ap
p
r
o
p
r
iate
f
o
r
lo
ad
f
lo
w
s
o
lu
tio
n
t
h
at
is
wh
y
n
ew
tech
n
iq
u
es
s
u
ch
as
ANN
ar
e
p
r
esen
ted
to
p
er
f
o
r
m
l
o
ad
f
l
o
w
s
o
lu
tio
n
in
p
o
we
r
s
y
s
tem
s
.
T
h
is
r
ec
en
t
tech
n
iq
u
e
h
as
th
e
ab
ilit
y
to
ap
p
ly
in
s
m
all
an
d
lar
g
e
s
y
s
tem
s
with
h
i
g
h
r
eliab
ilit
y
.
T
h
e
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
is
an
ef
f
ec
tiv
e
co
m
p
u
tatio
n
al
to
o
l
th
at
ca
n
b
e
u
s
ed
f
o
r
s
o
lv
in
g
n
o
n
lin
ea
r
eq
u
atio
n
s
[
2
4
]
,
[
2
5
]
.
ANN,
is
also
h
as
v
er
y
h
i
g
h
lev
el
o
f
ac
cu
r
ac
y
w
h
en
p
er
f
o
r
m
i
n
g
ca
lcu
latio
n
s
[
2
6
]
.
A
n
eu
r
al
n
etwo
r
k
(
NN)
m
o
d
el
co
n
s
is
ts
o
f
a
s
et
o
f
n
eu
r
o
n
s
in
h
ig
h
ly
in
ter
c
o
n
n
ec
ted
lay
e
r
s
[
1
8
]
.
T
h
ese
la
y
er
s
m
ay
b
e
an
i
n
p
u
t
lay
e
r
,
o
u
tp
u
t
lay
er
a
n
d
o
n
e
o
r
s
ev
er
al
h
id
d
en
lay
er
s
,
as
s
h
o
wn
in
Fig
u
r
e
1
[
2
7
]
,
th
e
in
p
u
t
lay
er
co
n
tain
n
u
m
b
er
o
f
i
n
p
u
t
n
eu
r
o
n
s
wh
ich
d
escr
ib
e
th
e
in
p
u
t
p
a
r
am
eter
s
to
ANN
m
o
d
el.
T
h
e
s
ec
o
n
d
la
y
er
u
s
u
ally
n
am
e
d
h
id
d
e
n
lay
er
co
n
tain
s
n
eu
r
o
n
s
o
f
h
i
d
d
en
lay
er
th
at
a
r
e
co
n
n
ec
ted
to
t
h
e
n
e
u
r
o
n
s
in
th
e
o
u
tp
u
t
lay
er
,
th
e
th
ir
d
(
o
r
o
u
tp
u
t)
lay
er
is
th
e
lay
e
r
wh
ich
r
ep
r
esen
t th
e
ANN
m
o
d
el
o
u
tp
u
t r
esp
o
n
s
e
[
2
8
]
.
T
h
e
co
n
n
ec
tio
n
s
b
etwe
en
th
e
n
eu
r
o
n
s
ar
e
ca
lled
v
ec
to
r
weig
h
ts
wh
ich
r
ep
r
esen
t
t
h
e
s
ig
n
al
s
tr
en
g
th
.
T
h
e
m
ain
f
ea
tu
r
e
o
f
an
ANN
is
its
ab
il
ity
to
lear
n
co
m
p
lex
n
o
n
-
lin
ea
r
r
elatio
n
s
h
i
p
b
etwe
en
th
e
in
p
u
ts
an
d
th
e
o
u
tp
u
ts
.
ANN
u
s
es
s
er
ies
tr
ai
n
in
g
p
r
o
ce
d
u
r
e
an
d
ca
n
m
o
d
i
f
y
its
elf
to
th
e
d
ata
ap
p
licatio
n
[
2
9
]
.
W
h
en
t
h
e
co
n
s
tr
u
ctio
n
o
f
t
h
e
n
etwo
r
k
is
ac
h
iev
ed
f
o
r
a
s
p
ec
if
ied
a
p
p
l
icatio
n
,
r
an
d
o
m
weig
h
ts
ar
e
s
elec
ted
to
s
tar
t
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
I
n
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
,
b
o
th
th
e
in
p
u
ts
an
d
th
e
o
u
t
p
u
ts
ar
e
p
r
o
v
id
ed
.
T
h
e
n
etwo
r
k
th
e
n
p
r
o
ce
s
s
es
th
e
in
p
u
ts
an
d
co
m
p
ar
es
th
e
o
u
tp
u
t
r
esu
lts
ag
ain
s
t
th
e
d
esire
d
o
u
tp
u
ts
an
d
th
e
we
ig
h
ts
ar
e
ad
ju
s
tin
g
ac
co
r
d
in
g
l
y
an
d
r
ep
ea
ted
l
y
[
2
7
]
.
Fig
u
r
e
1
.
A
n
eu
r
al
n
etwo
r
k
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
b
a
s
ed
lo
a
d
flo
w
a
n
a
lysi
s
o
f
r
a
d
ia
l
d
is
tr
ib
u
tio
n
s
ystem
…
(
Wa
r
d
a
Hu
s
s
ein
A
li
)
765
Neu
r
o
n
s
h
a
v
e
m
a
n
y
ac
tiv
ati
o
n
f
u
n
ctio
n
s
,
a
m
o
n
g
th
ese
f
u
n
ctio
n
s
o
f
th
e
n
eu
r
o
n
s
;
p
u
r
lin
e
an
d
tan
s
ig
m
o
ied
ac
tiv
atio
n
f
u
n
ctio
n
wh
ich
is
th
e
m
o
s
t
c
o
m
m
o
n
l
y
u
s
ed
[
3
0
]
,
is
u
s
ed
in
h
id
d
en
lay
er
n
eu
r
o
n
s
an
d
in
th
e
o
u
tp
u
t
lay
e
r
n
e
u
r
o
n
s
.
T
h
e
tr
ain
in
g
is
p
er
f
o
r
m
ed
with
th
e
L
ev
e
n
b
er
g
Ma
r
q
u
ar
d
t
b
as
ed
b
ac
k
p
r
o
p
a
g
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PN)
alg
o
r
ith
m
.
T
h
e
L
ev
en
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
is
s
p
ec
ially
d
esig
n
ed
to
g
iv
e
a
m
in
im
u
m
v
al
u
e
o
f
t
h
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
a
n
d
b
est
p
r
ed
ictio
n
r
esu
lts
[
3
1
]
.
T
h
e
MSE
is
ca
lcu
lated
u
s
in
g
(
1
7
)
b
ased
o
n
th
e
v
alu
es
o
f
d
esire
d
o
u
tp
u
t,
Yi,
an
d
th
e
ac
tu
al
o
u
tp
u
t,
Y
i
᷉
,
o
f
t
h
e
ANN
[
3
2
]
.
Fin
ally
,
ANN
is
r
ea
d
y
to
p
er
f
o
r
m
th
e
p
o
wer
f
lo
w
a
n
aly
s
is
.
T
h
e
p
r
o
c
ess
o
f
tr
ain
in
g
an
ANN
to
p
er
f
o
r
m
a
s
tead
y
s
tate
p
o
wer
f
lo
w
a
n
aly
s
is
is
s
h
o
wn
in
th
e
f
lo
w
ch
a
r
t in
F
ig
u
r
e
2
.
M
SE
=
(
1
)
∑
(
Y
i
−
Y
i
᷉
)
2
n
i
=
1
(
1
7
)
Fig
u
r
e
2
.
ANN
p
o
wer
f
lo
w
an
aly
s
is
m
o
d
el
f
lo
wch
ar
t f
o
r
ca
l
cu
latin
g
v
o
ltag
e
an
d
p
h
ase
an
g
le
4.
C
A
SE
ST
U
D
Y
T
h
is
s
ec
tio
n
p
er
f
o
r
m
s
a
co
m
p
ar
is
o
n
s
tu
d
y
o
f
th
e
co
n
v
en
tio
n
al
p
o
wer
f
lo
w
m
et
h
o
d
s
o
f
G
-
S
an
d
N
-
R
with
th
e
n
o
n
-
co
n
v
en
tio
n
al
A
NN
b
ased
ap
p
r
o
ac
h
u
s
in
g
a
2
4
-
b
u
s
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
.
T
h
e
d
is
tr
ib
u
tio
n
s
y
s
tem
is
s
u
p
p
lied
f
r
o
m
a
h
ig
h
v
o
ltag
e
Sh
ah
i
d
Su
b
s
tatio
n
(
3
3
/1
1
k
V)
in
Slem
an
y
city
o
f
,
Ku
r
d
is
tan
r
ejo
in
-
I
r
aq
an
d
it
co
n
s
is
ts
o
f
2
4
b
u
s
es.
T
h
e
s
lack
b
u
s
is
as
s
ig
n
ed
to
th
e
b
u
s
1
o
f
t
h
e
s
y
s
tem
n
etwo
r
k
,
wh
ile
th
e
r
est
2
3
b
u
s
es a
r
e
th
e
lo
ad
b
u
s
es.
Fig
u
r
e
3
s
h
o
ws th
e
s
im
u
lated
s
y
s
tem
u
s
in
g
p
o
wer
s
y
s
tem
an
al
y
s
is
to
o
l (
PS
AT
)
.
T
h
e
p
o
wer
f
lo
w
s
im
u
latio
n
m
o
d
el
o
f
b
o
th
th
e
c
o
n
v
e
n
tio
n
al
an
d
t
h
e
n
o
n
-
c
o
n
v
e
n
tio
n
al
tech
n
iq
u
es
ar
e
im
p
lem
en
ted
u
s
in
g
MA
T
L
A
B
s
o
f
twar
e.
T
ab
le
2
lis
t
s
p
o
wer
f
lo
w
an
aly
s
is
r
esu
lts
o
b
tai
n
ed
u
s
in
g
G
-
S,
N
-
R
an
d
ANN
m
eth
o
d
s
.
I
n
p
u
t
-
o
u
t
p
u
t
d
ata
s
ets
o
b
tain
ed
f
r
o
m
th
e
d
eter
m
in
is
tic
N
-
R
m
eth
o
d
i
s
th
en
u
s
ed
to
tr
ai
n
an
d
v
alid
ate
th
e
ANN
an
d
th
e
n
p
er
f
o
r
m
th
e
p
o
wer
f
lo
w
an
a
ly
s
is
.
T
wo
ANN
m
o
d
els
ar
e
u
s
ed
,
o
n
e
m
o
d
el
to
ca
lcu
late
th
e
m
ag
n
itu
d
e
an
d
t
h
e
p
h
ase
an
g
le
o
f
t
h
e
lo
ad
b
u
s
v
o
ltag
e,
an
d
th
e
o
th
er
m
o
d
el
to
o
b
tain
th
e
p
o
we
r
f
lo
w
th
r
o
u
g
h
th
e
tr
an
s
m
is
s
io
n
lin
es c
o
n
n
ec
ted
b
etwe
en
two
s
p
e
cif
ied
b
u
s
es in
th
e
s
y
s
tem
.
4
.
1
.
O
utput
v
o
lt
a
g
e
o
f
ANN
m
o
del
T
h
e
in
p
u
t
d
ataset
o
f
th
e
f
ir
s
t
ANN
m
o
d
el
wer
e
(
P1
-
Q1
,
P2
-
Q2
,
P3
-
Q3
…
Pn
-
Qn
)
f
o
r
all
lo
ad
b
u
s
es.
T
h
e
co
r
r
esp
o
n
d
in
g
o
u
t
p
u
t
d
a
ta
s
et
was
(
V1
-
δ1
,
V2
-
δ2
,
V
3
-
δ3
….
Vn
-
δn
)
.
T
h
e
s
y
s
tem
c
o
n
s
is
ts
o
f
2
3
lo
a
d
b
u
s
es,
s
o
th
e
ANN
m
o
d
el
h
as
4
6
in
p
u
ts
an
d
4
6
o
u
tp
u
ts
,
a
n
d
a
lar
g
e
n
u
m
b
er
o
f
th
e
lo
a
d
f
lo
w
p
r
o
ce
s
s
es
wer
e
p
er
f
o
r
m
ed
r
ep
ea
ted
l
y
u
s
in
g
th
e
N
-
R
m
eth
o
d
.
T
h
e
r
ea
l
a
n
d
th
e
r
ea
ctiv
e
p
o
wer
lo
a
d
s
in
cr
e
ased
s
im
u
ltan
eo
u
s
l
y
to
2
0
0
%at
all
lo
ad
b
u
s
es
o
f
th
e
2
4
-
b
u
s
s
y
s
t
em
in
o
r
d
er
to
o
b
tain
d
ata
s
et
f
o
r
ANN.
All
th
ese
d
ata
s
et
s
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
2
,
Au
g
u
s
t
20
25
:
76
1
-
7
7
3
766
s
to
r
ed
,
th
e
r
esu
lts
th
en
p
r
ep
ar
ed
to
b
e
u
s
ed
as
an
in
p
u
t
a
n
d
o
u
tp
u
t
s
et
f
o
r
tr
ain
in
g
an
d
v
alid
atin
g
th
e
ANN
m
o
d
el.
7
0
%
o
f
t
h
ese
d
ata
is
u
s
ed
lear
n
in
g
p
r
o
ce
s
s
o
r
tr
ain
in
g
th
e
ANN
m
o
d
el,
1
5
%
f
o
r
v
alid
atin
g
,
an
d
1
5
%
f
o
r
p
r
e
d
ictin
g
th
e
r
esu
lts
.
Af
ter
th
e
s
u
cc
ess
f
u
l
tr
ain
in
g
o
f
th
e
ANN
m
o
d
el,
th
e
ANN
-
(
B
PN)
is
r
ea
d
y
f
o
r
p
r
ed
ictin
g
t
h
e
m
ag
n
itu
d
e
a
n
d
th
e
p
h
ase
an
g
le
o
f
b
u
s
v
o
ltag
e
with
a
h
ig
h
p
r
ec
is
io
n
an
d
a
m
in
im
u
m
ex
e
cu
tio
n
tim
e
f
o
r
an
y
g
iv
e
n
in
p
u
t l
o
ad
d
ata.
Fig
u
r
e
4
s
h
o
ws
a
s
cr
ee
n
s
h
o
t
o
f
th
e
ANN
m
o
d
el
u
s
ed
in
t
h
e
s
tu
d
y
.
T
h
e
n
e
u
r
al
n
etwo
r
k
is
f
o
r
m
ed
with
a
p
u
r
e
lin
e
tr
a
n
s
f
er
f
u
n
ct
io
n
(
PUR
L
I
N)
in
th
e
h
id
d
en
lay
er
u
s
in
g
2
0
n
eu
r
o
n
s
.
T
h
e
tr
ain
in
g
is
p
er
f
o
r
m
e
d
u
s
in
g
th
e
L
ev
en
b
er
g
-
Ma
r
q
u
a
r
d
t
b
ased
b
ac
k
p
r
o
p
a
g
atio
n
al
g
o
r
ith
m
.
T
h
e
n
etwo
r
k
is
d
esig
n
ed
b
y
4
6
i
n
p
u
ts
co
r
r
esp
o
n
d
in
g
to
th
e
ac
tiv
e
a
n
d
r
ea
ctiv
e
p
o
wer
lo
a
d
o
f
2
3
b
u
s
es,
an
d
4
6
o
u
tp
u
ts
f
o
r
th
e
v
o
ltag
e
m
ag
n
itu
d
e
an
d
th
e
p
h
ase
an
g
les f
o
r
all
2
3
b
u
s
es.
Fig
u
r
e
5
s
h
o
ws
th
e
MSE
p
er
f
o
r
m
an
ce
o
f
th
e
ANN
m
o
d
el
d
u
r
in
g
th
e
tr
ain
i
n
g
a
n
d
th
e
v
alid
atio
n
.
I
t
is
clea
r
f
r
o
m
th
e
f
ig
u
r
e
th
at
th
e
MSE
d
ec
r
ea
s
ed
f
r
o
m
o
r
d
er
o
f
1
0
-
2
at
th
e
s
tar
t
to
o
r
d
er
o
f
1
0
-
4
af
ter
a
n
u
m
b
er
o
f
iter
atio
n
s
.
A
MSE
o
f
6
.
8
9
x
1
0
-
5
ca
n
b
e
o
b
s
er
v
ed
at
e
p
o
ch
(
iter
atio
n
)
1
2
7
,
wh
ich
is
an
a
cc
ep
tab
le
v
alu
e
f
o
r
ANN
tr
ain
in
g
a
n
d
v
alid
atio
n
[
3
2
]
.
T
h
e
co
r
r
elatio
n
b
etwe
en
th
e
in
p
u
ts
an
d
th
e
o
u
tp
u
t
o
f
th
e
ANN
m
o
d
el
is
illu
s
tr
ated
u
s
in
g
th
e
r
eg
r
ess
io
n
p
lo
t
o
f
Fig
u
r
e
6
,
th
e
co
r
r
ela
tio
n
r
esu
lts
ar
e
o
b
tain
ed
f
r
o
m
th
e
d
ata
u
s
ed
an
d
co
llected
in
t
h
e
tr
ain
i
n
g
,
v
alid
atio
n
an
d
test
all
p
r
o
ce
s
s
es
s
ep
ar
ately
an
d
all
tr
ain
in
g
v
alid
atin
g
test
in
g
in
(
All)
to
g
eth
er
o
f
th
e
ANN
m
o
d
e
l.
I
t
ca
n
b
e
n
o
ticed
th
at
th
e
r
ela
tio
n
s
h
ip
b
etwe
en
th
e
in
p
u
t
v
a
r
iab
les
an
d
o
u
tp
u
t
v
ar
iab
les
is
ap
p
r
o
x
im
ately
0
.
9
9
9
,
wh
ic
h
is
s
u
f
f
icien
tly
h
ig
h
v
alu
e,
v
al
u
es
ab
o
v
e
0
.
9
8
8
co
n
f
ir
m
s
th
at
th
e
ANN
m
o
d
el
is
g
o
o
d
th
er
e
f
o
r
e;
th
e
ANN
m
o
d
el
ca
n
b
e
u
s
ed
to
ca
r
r
y
o
u
t p
o
wer
f
lo
w
a
n
aly
s
is
o
n
t
h
e
s
y
s
tem
[
3
3
]
.
Fig
u
r
e
3
.
A
s
in
g
le
lin
e
d
iag
r
a
m
o
f
2
4
-
b
u
s
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
Fig
u
r
e
4
.
T
h
e
ANN
Mo
d
el
f
o
r
m
ag
n
itu
d
e
an
d
p
h
ase
an
g
le
o
f
th
e
b
u
s
v
o
ltag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
b
a
s
ed
lo
a
d
flo
w
a
n
a
lysi
s
o
f
r
a
d
ia
l
d
is
tr
ib
u
tio
n
s
ystem
…
(
Wa
r
d
a
Hu
s
s
ein
A
li
)
767
Fig
u
r
e
5
.
Me
an
s
q
u
ar
ed
er
r
o
r
p
er
f
o
r
m
an
ce
d
u
r
in
g
th
e
tr
ain
in
g
o
f
th
e
o
u
tp
u
t v
o
lta
g
e
ANN
m
o
d
el
Fig
u
r
e
6
.
T
h
e
lear
n
in
g
cu
r
v
e
f
o
r
th
e
o
u
tp
u
t
v
o
ltag
e
in
ANN
m
o
d
el
4
.
2
.
O
utput
p
o
wer
o
f
ANN
m
o
del
T
h
e
o
u
t
p
u
t
p
o
wer
o
f
ANN
m
o
d
el
is
u
s
ed
f
o
r
d
ete
r
m
in
in
g
t
h
e
p
o
wer
f
lo
w
o
f
th
e
tr
an
s
m
i
s
s
io
n
lin
e.
T
h
e
in
p
u
t
d
atasets
ar
e
(
V1
-
δ1
,
V2
-
δ2
,
a
n
d
V3
-
δ
3
……Vn
-
δn
)
f
o
r
all
ex
is
tin
g
tr
an
s
m
is
s
io
n
lin
es.
T
h
e
co
r
r
esp
o
n
d
in
g
o
u
t
p
u
t
d
ata
s
et
f
o
r
t
h
e
tr
an
s
m
is
s
io
n
lin
e
b
etw
ee
n
b
u
s
j
an
d
b
u
s
k
ar
e
(
Pjk
-
Qjk
,
Pk
j
-
Qk
j……)
.
T
h
is
is
ap
p
lied
to
t
h
e
all
-
tr
an
s
m
is
s
io
n
lin
es.
Fig
u
r
e
7
s
h
o
w
s
th
e
ANN
n
etwo
r
k
u
s
ed
to
p
r
ed
ict
th
e
r
ea
l
an
d
r
ea
ctiv
e
p
o
wer
f
lo
w
in
th
e
t
r
a
n
s
m
is
s
io
n
lin
es
.
T
h
e
s
y
s
tem
co
n
tain
s
2
2
tr
a
n
s
m
is
s
io
n
lin
es,
to
ca
lcu
la
te
lo
s
s
es
o
f
ea
ch
tr
an
s
m
is
s
io
n
li
n
e
v
o
ltag
e
m
ag
n
itu
d
e
an
d
p
h
ase
an
g
le
o
f
ea
ch
s
en
d
in
g
a
n
d
r
ec
eiv
in
g
en
d
n
ee
d
ed
f
o
r
o
n
e
d
ir
ec
tio
n
o
f
p
o
wer
f
lo
w
an
d
t
h
e
p
o
wer
f
lo
w
in
o
p
p
o
s
ite
d
i
r
ec
tio
n
also
n
ee
d
ed
,
t
h
er
ef
o
r
e
f
o
r
ea
ch
tr
an
s
m
is
s
io
n
lin
e
f
o
u
r
i
n
p
u
t
d
ata
n
ee
d
e
d
s
o
to
tal
in
p
u
t
f
o
r
2
2
tr
an
s
m
is
s
io
n
lin
e
will
b
e
8
8
a
n
d
8
8
o
u
tp
u
t
f
o
r
ac
t
iv
e
a
n
d
r
ea
cti
v
e
p
o
wer
also
n
ee
d
ed
.
A
lar
g
e
n
u
m
b
e
r
o
f
lo
ad
f
lo
w
p
r
o
ce
s
s
es
ar
e
p
er
f
o
r
m
ed
r
e
p
ea
ted
ly
u
s
in
g
th
e
N
-
R
m
eth
o
d
.
T
h
e
P
an
d
Q
at
a
ll
th
e
lo
ad
b
u
s
es
o
f
2
4
-
b
u
s
s
y
s
tem
ar
e
in
cr
ea
s
ed
s
im
u
ltan
eo
u
s
ly
u
p
to
2
0
0
%
an
d
all
o
f
th
ese
d
ata
s
ets
ar
e
s
to
r
ed
.
T
h
en
th
e
r
esu
lts
ar
e
p
r
e
p
ar
ed
to
r
ep
r
esen
t
th
e
in
p
u
t
an
d
t
h
e
o
u
tp
u
t
s
et.
T
h
e
n
e
u
r
al
n
etwo
r
k
is
f
o
r
m
ed
with
a
tr
an
s
f
er
f
u
n
ctio
n
(
T
ANSI
G)
a
n
d
2
0
n
eu
r
o
n
s
in
its
h
id
d
en
la
y
er
.
T
h
e
n
etwo
r
k
is
d
esig
n
ed
b
y
8
8
in
p
u
ts
co
r
r
esp
o
n
d
in
g
to
th
e
v
o
ltag
e
m
ag
n
itu
d
e
a
n
d
th
e
p
h
ase
an
g
le
f
o
r
2
3
b
u
s
es,
an
d
8
8
o
u
tp
u
ts
f
o
r
th
e
ac
tiv
e
an
d
th
e
r
ea
cti
v
e
p
o
we
r
f
lo
w
f
o
r
2
2
tr
a
n
s
m
is
s
io
n
lin
es
in
th
e
s
y
s
tem
.
T
h
e
m
ea
n
s
q
u
a
r
ed
e
r
r
o
r
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
i
s
s
h
o
wn
in
Fig
u
r
e
8
Similar
to
th
e
o
u
tp
u
t
v
o
lta
g
e
ANN
m
o
d
el,
th
e
MSE
o
f
th
e
o
u
tp
u
t
p
o
we
r
ANN
m
o
d
el
d
ec
r
ea
s
es
as
th
e
n
u
m
b
er
o
f
iter
atio
n
s
in
cr
ea
s
es.
An
d
Fig
u
r
e
9
r
e
p
r
esen
ts
th
e
r
eg
r
ess
io
n
v
alu
es f
o
r
th
e
tr
ai
n
in
g
,
test
in
g
,
an
d
v
alid
atio
n
p
h
ases
o
f
t
h
e
ANN
m
o
d
el.
Fig
u
r
e
7
.
T
h
e
ANN
m
o
d
el
f
o
r
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
wer
f
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
2
,
Au
g
u
s
t
20
25
:
76
1
-
7
7
3
768
Fig
u
r
e
8
.
Mean
s
q
u
ar
e
e
r
r
o
r
b
eh
av
io
r
d
u
r
in
g
tr
ain
in
g
ANN
m
o
d
el
Fig
u
r
e
9
.
T
h
e
lear
n
in
g
cu
r
v
e
o
f
ANN
m
o
d
el
5.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
is
s
ec
tio
n
p
r
esen
ts
an
d
co
m
p
ar
es
th
e
o
b
tain
ed
r
esu
lts
o
f
th
e
o
u
t
p
u
t
v
o
ltag
e
m
o
d
el
an
d
th
e
o
u
t
p
u
t
p
o
wer
m
o
d
el
u
s
in
g
t
h
e
NR
,
GS,
an
d
th
e
ANN
m
o
d
el.
Fig
u
r
e
1
0
an
d
Fig
u
r
e
1
1
s
h
o
w
th
e
o
b
tain
ed
m
a
g
n
itu
d
e
an
d
p
h
ase
a
n
g
le,
r
esp
ec
tiv
ely
,
o
f
th
e
b
u
s
es
u
s
in
g
th
e
NR
,
GS
,
an
d
th
e
ANN
m
eth
o
d
.
Fro
m
F
ig
u
r
e1
0
it
is
clea
r
th
at
v
o
ltag
e
m
ag
n
itu
d
e
o
f
n
u
m
b
er
o
f
b
u
s
es
(
f
o
r
m
b
u
s
No
.
1
to
b
u
s
No
.
1
2
)
ar
e
n
ea
r
t
o
o
n
e
p
er
u
n
it
wh
ic
h
in
d
icate
th
at
th
o
s
e
b
u
s
es
ar
e
s
tr
o
n
g
e
n
o
u
g
h
a
n
d
th
is
r
ef
e
r
s
to
th
at
th
o
s
e
b
u
s
es
ar
e
n
o
t
o
v
er
lo
ad
ed
,
m
ea
n
wh
ile
b
u
s
es
1
8
,
19,
20,
21,
2
2
,
23
,
an
d
2
4
h
av
e
lo
w
v
o
ltag
e
m
ag
n
itu
d
e
an
d
e
x
p
lan
atio
n
f
o
r
th
i
s
is
th
o
s
e
b
u
s
s
ar
e
o
v
er
lo
a
d
ed
a
n
d
f
ar
awa
y
f
r
o
m
s
u
b
s
tatio
n
s
.
Vo
ltag
e
p
h
ase
an
g
le
o
f
all
b
u
s
es
h
as
ac
ce
p
ta
b
le
v
alu
e
(
clo
s
e
to
ze
r
o
)
th
at
is
b
ec
au
s
e
th
e
ty
p
e
o
f
th
e
lo
a
d
d
o
es
n
o
t a
f
f
ec
t t
h
e
p
h
ase
an
g
le.
Fig
u
r
e
10
.
T
h
e
m
a
g
n
itu
d
e
o
f
t
h
e
b
u
s
v
o
ltag
e
u
s
in
g
th
e
GS,
NR
,
ANN
p
o
wer
f
lo
w
an
aly
s
is
m
o
d
els
Fig
u
r
e
11
.
Ph
ase
an
g
le
o
f
th
e
b
u
s
v
o
ltag
e
u
s
in
g
th
e
GS,
NR
,
ANN
p
o
wer
f
lo
w
an
aly
s
is
m
o
d
els
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
k
b
a
s
ed
lo
a
d
flo
w
a
n
a
lysi
s
o
f
r
a
d
ia
l
d
is
tr
ib
u
tio
n
s
ystem
…
(
Wa
r
d
a
Hu
s
s
ein
A
li
)
769
T
h
e
n
u
m
er
ical
v
alu
es
o
f
th
e
o
u
tp
u
t
v
o
ltag
es
an
d
p
h
ase
an
g
l
es
u
s
in
g
GS,
N
R
an
d
ANN
ar
e
lis
ted
in
T
ab
le
2
,
v
o
ltag
es
o
f
all
b
u
s
es
ar
e
in
ac
ce
p
ted
r
ag
e
v
alu
es,
we
ca
n
also
n
o
te
th
at
s
o
m
e
b
u
s
es
h
av
e
n
e
g
ativ
e
an
g
les
(
lag
g
in
g
)
wh
ich
m
ea
n
s
th
at
ac
tiv
e
p
o
wer
wil
l
f
lo
w
to
th
ese
b
u
s
es
b
ec
au
s
e,
ac
ti
v
e
p
o
wer
will
f
lo
w
alwa
y
s
f
r
o
m
lea
d
in
g
an
g
le
to
lag
g
in
g
a
n
g
le.
I
t
is
clea
r
f
r
o
m
Fig
u
r
e
1
0
th
at
th
e
b
u
s
v
o
ltag
e
m
a
g
n
itu
d
e
o
b
tain
ed
u
s
in
g
th
e
ANN
m
eth
o
d
p
r
o
v
id
es
clo
s
er
r
esu
lts
to
th
e
N
-
R
th
an
th
e
G
-
S
m
o
d
el
.
W
h
ile,
Fig
u
r
e
1
1
s
h
o
ws th
at
th
e
th
r
ee
m
eth
o
d
s
ap
p
r
o
x
im
ately
r
esu
lt in
th
e
s
am
e
v
o
ltag
e
p
h
ase
an
g
le
r
esu
lts
.
A
co
m
p
ar
is
o
n
b
etwe
en
th
e
N
-
R
an
d
th
e
G
-
S
p
o
wer
f
l
o
w
m
e
th
o
d
s
to
th
e
ANN
m
o
d
el
is
p
r
esen
ted
in
T
ab
le
3
.
T
h
e
co
m
p
ar
is
o
n
is
p
er
f
o
r
m
e
d
in
ter
m
s
o
f
t
h
e
p
e
r
c
en
tag
e
er
r
o
r
[
2
4
]
o
f
th
e
b
u
s
v
o
ltag
e
m
a
g
n
itu
d
e
b
etwe
en
ANN
m
o
d
el
an
d
ea
ch
o
f
th
e
c
o
n
v
e
n
tio
n
al
p
o
wer
f
lo
w
tech
n
iq
u
es u
s
in
g
(
1
8
)
.
%E
r
r
o
r
=
(
−
)
∗
100
(
1
8
)
T
ab
le
2
.
L
o
ad
f
lo
w
r
esu
lts
o
f
v
o
ltag
e
m
ag
n
itu
d
e
a
n
d
p
h
ase
an
g
le
B
u
s
N
o
.
(G
-
S)
(N
-
R)
(ANN)
V
o
l
t
a
g
e
m
a
g
n
i
t
u
d
e
(V)
P
h
a
se
a
n
g
l
e
(
R
a
d
)
V
o
l
t
a
g
e
m
a
g
n
i
t
u
d
e
(V)
P
h
a
se
A
n
g
l
e
(
R
a
d
)
V
o
l
t
a
g
e
m
a
g
n
i
t
u
d
e
(V)
P
h
a
se
a
n
g
l
e
(
R
a
d
)
2
0
.
9
5
4
0
0
.
9
5
4
0
0
.
9
5
4
0
3
0
.
9
5
2
-
0
.
0
4
3
0
.
9
5
2
-
0
.
0
4
4
0
.
9
5
1
1
-
0
.
0
4
5
1
4
0
.
9
5
2
-
0
.
0
4
6
0
.
9
5
2
-
0
.
0
4
2
9
0
.
9
5
2
-
0
.
0
4
2
5
0
.
9
5
1
-
0
.
0
7
0
.
9
5
1
-
0
.
0
7
0
.
9
5
1
-
0
.
0
7
1
3
6
0
.
9
4
8
-
0
.
1
3
1
0
.
9
4
8
-
0
.
1
3
1
0
.
9
4
6
-
0
.
1
3
0
3
7
0
.
9
4
8
-
0
.
1
3
3
0
.
9
4
6
-
0
.
1
3
9
0
.
9
4
5
-
0
.
1
4
1
3
8
0
.
9
4
8
-
0
.
1
3
5
0
.
9
4
8
-
0
.
1
3
6
0
.
9
4
6
4
-
0
.
1
4
2
9
9
0
.
9
4
8
-
0
.
1
3
6
0
.
9
4
6
-
0
.
1
3
7
0
.
9
4
4
-
0
.
1
4
4
4
10
0
.
9
4
8
-
0
.
1
3
8
0
.
9
4
8
-
0
.
1
3
8
0
.
9
4
8
-
0
.
1
4
5
8
11
0
.
9
4
8
-
0
.
1
5
3
0
.
9
4
7
-
0
.
1
5
4
0
.
9
4
7
-
0
.
1
6
2
4
12
0
.
9
4
5
-
0
.
2
2
5
0
.
9
4
4
-
0
.
2
2
5
0
.
9
4
3
-
0
.
2
3
8
4
13
0
.
9
4
2
-
0
.
2
7
5
0
.
9
4
2
-
0
.
2
7
6
0
.
9
4
3
-
0
.
2
9
2
4
14
0
.
9
4
2
-
0
.
2
9
5
0
.
9
4
1
-
0
.
2
9
6
0
.
9
4
1
-
0
.
3
1
3
7
15
0
.
9
4
1
-
0
.
2
9
8
0
.
9
4
1
-
0
.
2
9
9
0
.
9
4
0
9
-
0
.
3
1
6
3
16
0
.
9
4
1
-
0
.
3
1
1
0
.
9
4
1
-
0
.
3
1
3
0
.
9
4
0
4
-
0
.
3
3
1
4
17
0
.
9
4
1
-
0
.
3
1
2
0
.
9
4
1
-
0
.
3
1
4
0
.
9
4
0
5
-
0
.
3
3
2
3
18
0
.
9
4
1
-
0
.
3
1
5
0
.
9
4
-
0
.
3
1
7
0
.
9
4
-
0
.
3
3
5
1
19
0
.
9
4
1
-
0
.
3
1
7
0
.
9
4
-
0
.
3
1
9
0
.
9
4
-
0
.
3
3
7
8
20
0
.
9
4
-
0
.
3
2
1
0
.
9
4
-
0
.
3
2
3
0
.
9
3
9
9
-
0
.
3
4
2
2
21
0
.
9
4
1
-
0
.
3
1
8
0
.
9
4
-
0
.
3
1
9
0
.
9
4
-
0
.
3
3
7
7
22
0
.
9
4
1
-
0
.
3
1
9
0
.
9
4
-
0
.
3
2
0
.
9
3
9
8
-
0
.
3
3
8
3
23
0
.
9
4
-
0
.
3
2
2
0
.
9
4
-
0
.
3
2
4
0
.
9
3
9
9
-
0
.
3
4
2
7
24
0
.
9
4
-
0
.
3
2
6
0
.
9
4
-
0
.
3
2
8
0
.
9
3
9
9
-
0
.
3
4
7
1
T
ab
le
3
.
Vo
ltag
e
m
ag
n
itu
d
e
p
e
r
ce
n
tag
e
er
r
o
r
s
B
u
s
N
o
.
V
o
l
t
a
g
e
m
a
g
n
i
t
u
d
e
%
Er
r
o
r
(
A
N
N
a
n
d
N
-
R)
%
Er
r
o
r
(
A
N
N
a
n
d
G
-
S)
2
0
0
3
0
.
0
9
4
5
3
7
8
1
5
0
.
0
9
4
5
3
7
8
1
5
4
0
0
5
0
0
6
0
.
2
1
0
9
7
0
4
6
4
0
.
2
1
0
9
7
0
4
6
4
7
0
.
4
2
1
9
4
0
9
2
8
0
.
4
2
1
9
4
0
9
2
8
8
0
.
1
6
8
7
7
6
3
7
1
0
.
1
6
8
7
7
6
3
7
1
9
0
.
5
2
7
4
2
6
1
6
0
.
5
2
7
4
2
6
1
6
10
0
0
11
0
0
.
1
0
5
4
8
5
2
3
2
12
0
.
1
0
5
9
3
2
2
0
3
0
.
2
1
1
6
4
0
2
1
2
13
-
0
.
1
0
6
1
5
7
1
1
3
-
0
.
1
0
6
1
5
7
1
1
3
14
0
0
.
1
0
6
1
5
7
1
1
3
15
0
.
0
1
0
6
2
6
9
9
3
0
.
0
1
0
6
2
6
9
9
3
16
0
.
0
6
3
7
6
1
9
5
5
0
.
0
6
3
7
6
1
9
5
5
17
0
.
0
5
3
1
3
4
9
6
3
0
.
0
5
3
1
3
4
9
6
3
18
0
0
.
1
0
6
2
6
9
9
2
6
19
0
0
.
1
0
6
2
6
9
9
2
6
20
0
.
0
1
0
6
3
8
2
9
8
0
.
0
1
0
6
3
8
2
9
8
21
0
0
.
1
0
6
2
6
9
9
2
6
22
0
.
0
2
1
2
7
6
5
9
6
0
.
1
2
7
5
2
3
9
1
1
23
0
.
0
1
0
6
3
8
2
9
8
0
.
0
1
0
6
3
8
2
9
8
24
0
.
0
1
0
6
3
8
2
9
8
0
.
0
1
0
6
3
8
2
9
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
2
,
Au
g
u
s
t
20
25
:
76
1
-
7
7
3
770
I
t
is
o
b
v
io
u
s
f
r
o
m
th
e
T
a
b
le
3
th
at
t
h
e
er
r
o
r
s
ar
e
e
q
u
al
t
o
ze
r
o
o
n
m
an
y
b
u
s
es;
th
e
r
esu
lts
also
in
d
icate
th
at
th
e
er
r
o
r
b
etwe
e
n
N
-
R
m
eth
o
d
an
d
ANN
m
eth
o
d
is
less
th
an
th
e
er
r
o
r
b
etwe
en
th
e
G
-
S
m
eth
o
d
an
d
ANN
m
eth
o
d
,
t
h
at
is
b
ec
au
s
e
N
-
R
m
eth
o
d
r
esu
lts
ar
e
m
o
r
e
ac
cu
r
ate
t
h
an
G
-
S
m
eth
o
d
co
n
s
eq
u
en
tly
th
e
er
r
o
r
b
etwe
en
N
-
R
an
d
ANN
is
les
s
th
an
th
e
er
r
o
r
b
etwe
en
G
-
S
an
d
ANN.
T
ab
le
4
lis
ts
t
h
e
r
esu
lts
o
f
ac
tiv
e
an
d
r
e
ac
tiv
e
p
o
wer
f
lo
w
b
etwe
en
ex
is
tin
g
b
u
s
es
o
f
th
e
s
y
s
tem
u
s
in
g
th
e
G
-
S,
N
-
R
,
an
d
t
h
e
ANN
p
o
wer
f
lo
w
tech
n
iq
u
es,
it
ca
n
b
e
u
s
ed
to
ca
lcu
late
lo
s
s
es
o
f
tr
an
s
m
is
s
io
n
lin
e.
Similar
t
o
th
e
b
u
s
v
o
ltag
e
m
a
g
n
itu
d
e
r
esu
lts
o
f
Fig
u
r
e
1
0
,
th
e
tab
le
s
h
o
w
th
at
th
e
ac
tiv
e
a
n
d
r
ea
ctiv
e
p
o
wer
r
esu
lts
o
f
th
e
ANN
m
o
d
el
m
atch
v
er
y
well
with
th
e
r
esu
lts
f
r
o
m
th
e
N
-
R
m
eth
o
d
b
ec
au
s
e
th
e
a
ctiv
e
an
d
r
ea
ctiv
e
p
o
wer
f
lo
w
d
ep
en
d
s
o
n
b
u
s
v
o
ltag
es
wh
ich
is
m
o
r
e
eq
u
at
e
with
N
-
R
m
eth
o
d
.
Als
o
,
th
er
e
is
a
g
o
o
d
m
atch
b
etwe
en
t
h
e
ANN
r
esu
lts
an
d
th
e
GS m
o
d
el.
T
ab
le
4
.
L
o
ad
f
lo
w
r
esu
lts
o
f
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
we
r
R
o
m
b
u
s
t
o
b
u
s
ANN
N
-
R
G
-
S
A
c
t
i
v
e
p
o
w
e
r
f
l
o
w
R
e
a
c
t
i
v
e
p
o
w
e
r
f
l
o
w
A
c
t
i
v
e
p
o
w
e
r
f
l
o
w
R
e
a
c
t
i
v
e
p
o
w
e
r
f
l
o
w
A
c
t
i
v
e
p
o
w
e
r
f
l
o
w
R
e
a
c
t
i
v
e
p
o
w
e
r
f
l
o
w
1
—
2
5
.
1
8
1
9
3
.
2
5
0
8
5
.
1
8
3
.
2
5
5
.
1
7
3
.
2
1
2
–
1
-
5
.
1
7
4
2
-
3
.
2
3
9
1
-
5
.
1
7
-
3
.
2
4
-
5
.
1
7
-
3
.
2
4
2
—
3
0
.
2
7
8
9
0
.
1
7
2
6
0
.
2
8
0
.
1
7
0
.
2
7
9
0
.
1
6
9
3
—
2
-
0
.
2
7
9
-
0
.
1
7
3
3
-
0
.
2
8
-
0
.
1
7
1
-
0
.
2
7
9
-
0
.
1
6
9
2
—
4
4
.
8
8
9
9
3
.
0
5
9
7
4
.
8
9
3
.
0
6
4
.
8
6
3
.
0
5
4
—
2
-
4
.
8
7
9
9
-
3
.
0
5
6
9
-
4
.
8
8
-
3
.
0
6
-
4
.
8
8
-
3
.
0
5
4
—
5
4
.
6
0
1
5
2
.
8
7
8
6
4
.
6
2
.
8
8
4
.
5
6
2
.
8
4
5
—
4
-
4
.
5
8
9
7
-
2
.
8
6
1
2
-
4
.
5
9
-
2
.
8
6
-
4
.
5
4
9
-
2
.
8
2
5
—
6
0
.
2
7
8
9
0
.
1
7
3
4
0
.
2
8
0
.
1
7
2
0
.
2
7
3
0
.
1
7
6
—
5
-
0
.
2
7
9
3
-
0
.
1
7
3
1
-
0
.
2
8
-
0
.
1
7
-
0
.
2
7
3
-
0
.
1
7
5
—
7
0
.
5
6
2
4
0
.
3
4
9
1
0
.
5
6
0
.
3
5
0
.
5
5
3
0
.
3
4
8
7
—
5
-
0
.
5
6
2
7
-
0
.
3
4
9
3
-
0
.
5
6
-
0
.
3
5
-
0
.
5
3
4
-
0
.
3
4
9
7
—
8
0
.
2
7
9
4
0
.
1
7
3
6
0
.
2
8
0
.
1
7
2
0
.
2
7
3
0
.
1
7
8
—
7
-
0
.
2
7
9
-
0
.
1
7
2
9
-
0
.
2
8
-
0
.
1
7
1
-
0
.
2
7
4
-
0
.
1
7
7
—
9
0
.
2
7
9
2
0
.
1
7
3
5
0
.
2
8
0
.
1
7
2
0
.
2
7
8
0
.
1
7
1
9
—
7
-
0
.
2
7
8
7
-
0
.
1
7
3
5
-
0
.
2
8
-
0
.
1
7
3
-
0
.
2
7
9
-
0
.
1
7
2
5
—
10
3
.
4
6
1
7
2
.
1
5
9
6
3
.
4
6
2
.
1
6
3
.
4
5
5
2
.
1
5
2
10
—
5
-
3
.
4
5
9
-
2
.
1
6
0
6
-
3
.
4
6
-
2
.
1
6
-
3
.
4
5
5
-
2
.
1
5
1
10
--
11
3
.
0
0
6
5
1
.
8
7
9
2
3
.
0
1
1
.
8
8
3
1
.
8
8
11
--
10
-
2
.
9
9
7
8
-
1
.
8
6
8
3
-
3
-
1
.
8
7
-
2
.
9
9
9
-
1
.
8
6
11
--
12
2
.
5
4
9
6
1
.
5
8
5
5
2
.
5
5
1
.
5
9
2
.
5
4
1
.
5
8
12
--
11
-
2
.
5
3
7
8
-
1
.
5
7
9
2
-
2
.
5
4
-
1
.
5
8
-
2
.
5
3
-
1
.
5
7
12
--
13
2
.
2
5
9
3
1
.
4
0
4
2
2
.
2
6
1
.
4
2
.
2
4
1
.
3
9
13
--
12
-
2
.
2
6
2
-
1
.
3
9
7
7
-
2
.
2
6
-
1
.
4
-
2
.
2
4
-
1
.
3
9
13
--
14
0
.
4
4
9
7
0
.
2
8
0
2
0
.
4
5
0
.
2
8
0
.
4
4
0
.
2
7
9
14
--
13
-
0
.
4
4
9
8
-
0
.
2
8
0
3
-
0
.
4
5
-
0
.
2
8
-
0
.
4
4
-
0
.
2
7
8
13
--
15
1
.
8
0
8
1
.
1
2
0
6
1
.
8
1
1
.
1
2
1
.
8
1
.
1
1
15
--
13
-
1
.
7
9
8
8
-
1
.
1
1
6
9
-
1
.
8
-
1
.
1
2
-
1
.
7
9
-
1
.
1
1
15
--
16
0
.
5
6
2
0
.
3
4
8
9
0
.
5
6
0
.
3
5
0
.
5
5
0
.
3
4
16
--
15
-
0
.
5
6
1
9
-
0
.
3
4
9
3
-
0
.
5
6
-
0
.
3
5
-
0
.
5
5
-
0
.
3
4
16
--
17
0
.
2
7
9
3
0
.
1
7
2
8
0
.
2
8
0
.
1
7
0
.
2
7
0
.
1
6
9
17
--
16
-
0
.
2
7
9
3
-
0
.
1
7
3
4
-
0
.
2
8
-
0
.
1
7
2
-
0
.
2
7
-
0
.
1
7
15
--
18
0
.
5
6
2
4
0
.
3
4
9
6
0
.
5
6
0
.
3
5
0
.
5
4
0
.
3
4
18
--
15
-
0
.
5
6
2
5
-
0
.
3
4
9
-
0
.
5
6
-
0
.
3
5
-
0
.
5
4
-
0
.
3
4
18
--
19
0
.
2
7
9
4
0
.
1
7
2
9
0
.
2
8
0
.
1
7
0
.
2
7
0
.
1
6
19
--
18
-
0
.
2
7
9
2
-
0
.
1
7
3
2
-
0
.
2
8
-
0
.
1
7
-
0
.
2
7
-
0
.
1
6
9
15
--
20
0
.
6
7
8
0
.
4
1
9
8
0
.
6
8
0
.
4
2
0
.
6
7
0
.
4
1
20
--
15
-
0
.
6
7
8
2
-
0
.
4
1
9
9
-
0
.
6
8
-
0
.
4
2
-
0
.
6
7
-
0
.
4
1
20
--
21
0
.
1
1
1
0
.
0
6
9
2
0
.
1
1
0
.
0
7
0
.
1
0
9
0
.
0
6
9
21
--
20
-
0
.
1
1
1
7
-
0
.
0
7
0
7
-
0
.
1
1
-
0
.
0
7
-
0
.
1
0
8
-
0
.
0
6
9
20
--
22
0
.
5
6
2
1
0
.
3
4
9
1
0
.
5
6
0
.
3
5
0
.
5
5
9
0
.
3
4
22
--
20
-
0
.
5
6
2
3
-
0
.
3
4
9
6
-
0
.
5
6
-
0
.
3
5
-
0
.
5
5
8
-
0
.
3
4
22
--
23
0
.
2
7
8
4
0
.
1
7
2
7
0
.
2
8
0
.
1
7
0
.
2
7
9
0
.
1
6
9
23
--
22
-
0
.
2
7
9
4
-
0
.
1
7
1
8
-
0
.
2
8
-
0
.
1
7
-
0
.
2
7
9
-
0
.
1
6
9
22
--
24
0
.
2
1
2
2
0
.
1
8
9
9
0
.
2
1
3
3
0
.
1
8
8
0
.
2
1
3
2
0
.
1
8
5
24
--
22
-
0
.
2
1
5
2
-
0
.
1
8
7
9
-
0
.
2
1
6
2
-
0
.
1
8
9
-
0
.
2
1
5
-
0
.
1
8
6
Fin
ally
,
a
c
o
m
p
ar
is
o
n
is
p
er
f
o
r
m
ed
f
o
r
t
h
e
s
o
f
twar
e
im
p
lem
en
tatio
n
o
f
th
e
s
im
u
latio
n
m
o
d
els
b
etwe
en
th
e
th
r
ee
lo
ad
f
lo
w
tech
n
iq
u
es.
T
h
e
co
m
p
a
r
is
o
n
is
p
er
f
o
r
m
ed
in
ter
m
s
o
f
th
e
av
er
ag
e
n
u
m
b
er
o
f
iter
atio
n
s
an
d
th
e
r
eq
u
ir
e
d
co
m
p
u
tatio
n
tim
e
as
s
u
m
m
ar
i
ze
d
in
T
ab
le
5
.
I
t
is
clea
r
th
at
th
er
e
is
a
b
etter
Evaluation Warning : The document was created with Spire.PDF for Python.