I
nte
rna
t
io
na
l J
o
urna
l o
f
Appl
ied P
o
wer
E
ng
i
neer
ing
(
I
J
AP
E
)
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
1
0
0
9
~
1
022
I
SS
N:
2252
-
8
7
9
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijap
e
.
v
1
5
.
i
3
.
pp
1
0
0
9
-
1
0
2
2
1009
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//
ija
p
e.
ia
esco
r
e.
co
m/
Intellig
ent
f
a
ult
d
ia
g
no
sis
and pro
tect
io
n in
DG
-
co
n
nected
sy
stems us
ing
resi
stiv
e superco
ndu
c
ting fault
curr
ent
limiter
a
nd ANN
-
ba
sed d
etec
tion
L
ek
s
hm
i R
.
Cha
nd
ra
n
1
,
I
la
n
g
o
K
a
rupp
a
s
a
m
y
2
,
M
a
njula
G
.
Na
ir
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
A
mr
i
t
a
V
i
sh
w
a
V
i
d
y
a
p
e
e
t
h
a
m
,
A
mr
i
t
a
p
u
r
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
A
mr
i
t
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
A
mr
i
t
a
V
i
s
h
w
a
V
i
d
y
a
p
e
e
t
h
a
m
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
6
,
2
0
2
5
R
ev
is
ed
Ma
y
1
2
,
2
0
2
6
Acc
ep
ted
J
u
n
9
,
2
0
2
6
En
su
ri
n
g
re
li
a
b
le
fa
u
lt
d
iag
n
o
sis
a
n
d
ra
p
id
re
c
o
v
e
ry
in
d
istr
ib
u
ted
g
e
n
e
ra
to
r
(DG
)
-
c
o
n
n
e
c
ted
d
istri
b
u
t
io
n
sy
st
e
m
s
is
c
rit
ica
l,
a
s
th
e
in
teg
ra
ti
o
n
o
f
DG
so
u
rc
e
s
sig
n
ifi
c
a
n
t
ly
e
lev
a
tes
fa
u
lt
c
u
rre
n
t
lev
e
ls.
Th
is
st
u
d
y
p
r
o
p
o
se
s
a
n
in
teg
ra
ted
a
p
p
r
o
a
c
h
t
h
a
t
c
o
m
b
in
e
s
a
re
sistiv
e
su
p
e
rc
o
n
d
u
c
ti
n
g
fa
u
lt
c
u
rre
n
t
li
m
it
e
r
(RS
F
CL)
with
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N)
-
b
a
se
d
in
telli
g
e
n
t
fa
u
lt
d
ia
g
n
o
sis
fra
m
e
wo
rk
.
Th
e
o
b
jec
ti
v
e
is
to
li
m
it
e
x
c
e
ss
iv
e
fa
u
l
t
c
u
rre
n
ts
wh
il
e
imp
ro
v
in
g
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
u
n
d
e
r
v
a
ry
in
g
n
e
two
r
k
c
o
n
fi
g
u
ra
ti
o
n
s
.
Th
e
RS
F
CL
is
stra
teg
ica
ll
y
p
lac
e
d
b
y
a
n
a
l
y
z
in
g
fa
u
lt
c
u
rre
n
t
m
a
g
n
it
u
d
e
,
v
o
lt
a
g
e
q
u
a
li
ty
,
a
n
d
re
sista
n
c
e
v
a
lu
e
to
a
c
h
iev
e
e
ffe
c
ti
v
e
c
u
rre
n
t
li
m
it
a
ti
o
n
with
o
u
t
c
o
m
p
ro
m
isin
g
sy
ste
m
sta
b
il
it
y
.
M
e
a
n
wh
il
e
,
t
h
e
AN
N
e
m
p
lo
y
s
sy
m
m
e
tri
c
a
l
c
o
m
p
o
n
e
n
ts
o
f
c
u
rr
e
n
t
a
n
d
v
o
lt
a
g
e
a
s
d
iag
n
o
st
ic
fe
a
tu
re
s.
T
o
e
n
h
a
n
c
e
ro
b
u
st
n
e
ss
,
c
o
rre
late
d
v
a
riab
les
a
re
id
e
n
t
ifi
e
d
a
n
d
e
li
m
in
a
t
e
d
d
u
rin
g
fe
a
tu
re
se
lec
ti
o
n
,
stre
n
g
th
e
n
i
n
g
t
h
e
m
o
d
e
l’s
fa
u
lt
d
isc
rimin
a
ti
o
n
c
a
p
a
b
il
it
y
.
S
imu
latio
n
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
th
e
o
p
ti
m
a
l
RS
F
CL
p
lac
e
m
e
n
t
re
d
u
c
e
s
fa
u
lt
c
u
rre
n
t
c
o
n
tri
b
u
ti
o
n
ra
ti
o
s
b
y
u
p
t
o
8
2
.
1
6
%
u
n
d
e
r
sy
m
m
e
tri
c
a
l
fa
u
l
t
co
n
d
i
ti
o
n
s.
T
h
e
AN
N
-
b
a
se
d
fa
u
lt
d
e
tec
ti
o
n
m
o
d
e
l
a
c
h
iev
e
s
a
v
a
li
d
a
ti
o
n
a
c
c
u
ra
c
y
o
f
9
9
.
7
%
,
o
u
tp
e
rfo
rm
i
n
g
c
o
n
v
e
n
ti
o
n
a
l
th
re
sh
o
ld
-
b
a
se
d
m
e
th
o
d
s
b
y
m
in
imiz
in
g
n
u
isa
n
c
e
tri
p
p
i
n
g
a
n
d
imp
r
o
v
i
n
g
c
ircu
it
b
re
a
k
e
r
c
o
o
rd
in
a
ti
o
n
.
Ov
e
ra
ll
,
t
h
e
c
o
m
b
in
e
d
RS
F
CL
–
AN
N
fra
m
e
wo
rk
p
r
o
v
id
e
s
a
n
e
ff
e
c
ti
v
e
a
n
d
in
telli
g
e
n
t
so
l
u
ti
o
n
f
o
r
fa
u
l
t
d
ia
g
n
o
sis a
n
d
p
ro
tec
ti
o
n
i
n
DG
-
in
teg
ra
ted
p
o
we
r
sy
ste
m
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
Dis
tr
ib
u
ted
g
en
er
atio
n
Fau
lt d
iag
n
o
s
is
Su
p
er
co
n
d
u
ctin
g
f
au
lt
c
u
r
r
e
n
t
lim
iter
Sy
m
m
etr
ical
co
m
p
o
n
en
ts
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
:
L
ek
s
h
m
i R
.
C
h
an
d
r
an
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
Am
r
ita
Vis
h
wa
Vid
y
ap
ee
th
am
Am
r
itap
u
r
i Cam
p
u
s
Am
r
itap
u
r
i,
C
lap
p
an
a
P.
O.
,
Ko
llam
–
6
9
0
5
2
5
,
Ker
ala,
I
n
d
ia
E
m
ail:
lek
s
h
m
ich
an
d
r
a
n
@
am
.
am
r
ita.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
teg
r
atio
n
o
f
d
is
tr
ib
u
ted
g
en
er
atio
n
s
(
DG)
in
to
d
is
tr
ib
u
tio
n
s
y
s
tem
s
h
as
b
ec
o
m
e
n
ec
e
s
s
ar
y
d
u
e
to
th
e
r
is
in
g
p
o
wer
d
em
an
d
,
p
o
wer
lo
s
s
in
lo
n
g
tr
an
s
m
is
s
io
n
lin
es,
an
d
th
e
em
er
g
en
ce
o
f
d
ec
en
tr
alize
d
p
o
wer
g
en
er
atio
n
.
T
h
e
d
is
tr
ib
u
tio
n
s
y
s
tem
is
co
n
n
ec
ted
to
DG
u
n
its
,
s
u
ch
as
p
h
o
to
v
o
ltaic
(
PV)
s
y
s
t
em
s
,
win
d
tu
r
b
in
es,
an
d
en
er
g
y
s
to
r
ag
e,
u
s
in
g
a
v
ar
iety
o
f
d
ev
ices,
s
u
ch
as
cir
cu
it
b
r
ea
k
er
s
,
s
o
lid
-
s
tate
b
r
ea
k
er
s
,
o
r
p
o
wer
elec
tr
o
n
ics
in
ter
f
ac
es.
Alth
o
u
g
h
DG
in
c
r
ea
s
es
s
y
s
tem
r
eliab
ilit
y
,
it
ca
n
also
in
cr
ea
s
e
s
h
o
r
t
-
cir
cu
it
cu
r
r
en
t
a
n
d
h
ar
m
o
n
ic
p
o
llu
tio
n
,
esp
ec
ially
wh
en
lin
k
ed
t
o
p
o
wer
elec
tr
o
n
ic
in
ter
f
ac
es.
T
h
ese
in
ter
f
ac
e
s
also
m
ak
e
it
ea
s
ier
f
o
r
f
alse
f
ee
d
e
r
tr
ip
s
,
lo
s
s
o
f
r
elay
co
o
r
d
in
atio
n
,
o
v
er
v
o
l
tag
e,
an
d
u
n
wan
ted
is
lan
d
in
g
to
o
cc
u
r
[
1
]
-
[
3
]
.
Mo
n
ito
r
in
g
a
n
d
p
r
o
tectio
n
is
s
u
es
ar
is
e
with
th
e
in
teg
r
atio
n
o
f
d
is
tr
ib
u
ted
g
en
er
atio
n
s
(
DG)
in
to
th
e
elec
tr
ical
d
is
tr
ib
u
tio
n
s
y
s
tem
.
T
h
e
u
s
e
o
f
cu
r
r
en
t
lim
itin
g
f
u
s
es,
cir
c
u
it
b
r
ea
k
er
s
m
ad
e
to
h
an
d
le
e
x
tr
em
ely
h
ig
h
f
au
lt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
0
9
-
1
0
2
2
1010
cu
r
r
en
ts
,
f
ee
d
er
s
p
litt
in
g
,
h
i
g
h
im
p
ed
an
ce
tr
an
s
f
o
r
m
er
s
,
r
aisi
n
g
g
en
er
atio
n
v
o
ltag
e
,
air
co
r
e
r
ea
cto
r
s
,
an
d
s
er
ies
r
ea
cto
r
s
ar
e
j
u
s
t
a
f
ew
o
f
t
h
e
t
ec
h
n
iq
u
es
u
s
ed
to
en
s
u
r
e
s
af
e
o
p
er
atio
n
in
p
o
wer
s
y
s
tem
s
.
Pas
s
iv
e
f
au
lt
cu
r
r
e
n
t
lim
itatio
n
m
eth
o
d
s
in
tr
o
d
u
c
e
i
m
p
ed
an
ce
in
n
o
r
m
al
a
n
d
f
au
lt
co
n
d
itio
n
s
an
d
ca
n
cr
ea
te
p
o
w
er
q
u
ality
is
s
u
es
an
d
s
tab
ilit
y
is
s
u
es.
W
h
er
ea
s
a
ctiv
e
tech
n
i
q
u
es
estab
lis
h
a
s
m
all
im
p
ed
an
ce
d
u
r
in
g
n
o
r
m
al
o
p
er
atin
g
co
n
d
itio
n
s
an
d
a
h
i
g
h
im
p
e
d
an
ce
u
n
d
er
f
au
lty
co
n
d
itio
n
s
[3
]
-
[
5
]
.
Fau
lt
cu
r
r
en
t
lim
iter
s
(
FC
L
s
)
as
lo
w
im
p
ed
an
ce
elem
en
ts
in
n
o
r
m
al
o
p
er
atio
n
an
d
p
r
o
v
id
e
h
ig
h
im
p
ed
an
ce
d
u
r
in
g
f
au
lts
to
li
m
it
h
ig
h
f
a
u
lt
cu
r
r
e
n
ts
to
an
ac
ce
p
tab
le
lev
el.
T
h
e
g
en
er
ali
ze
d
FC
L
o
p
er
atio
n
d
u
r
in
g
n
o
r
m
al
an
d
f
au
lt
co
n
d
iti
o
n
s
is
s
h
o
wn
in
Fig
u
r
e
1
[
6
]
.
FC
L
in
s
talla
tio
n
r
ed
u
ce
s
s
tr
ess
o
n
s
af
ety
eq
u
ip
m
en
t
b
y
r
e
d
u
cin
g
s
h
o
r
t
-
cir
cu
it
c
u
r
r
en
t
an
d
im
p
r
o
v
in
g
v
o
ltag
e
q
u
ality
in
th
e
s
y
s
tem
.
FC
L
s
ar
e
class
if
ied
as
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
cu
r
r
en
t
lim
iter
s
(
SF
C
L
s
)
an
d
n
o
n
-
s
u
p
er
co
n
d
u
ctin
g
FC
L
s
b
ased
o
n
t
h
eir
m
ater
i
al.
Fau
lt
cu
r
r
en
t
lim
iter
s
s
u
ch
as
p
y
r
o
tech
n
ic
f
a
u
lt
cu
r
r
en
t
lim
iter
s
(
I
s
-
lim
iter
s
)
,
s
u
p
er
co
n
d
u
cti
n
g
FC
L
-
m
ag
n
etic,
tr
an
s
f
o
r
m
er
,
r
esis
tiv
e,
f
lu
x
lo
c
k
ty
p
e,
s
o
lid
-
s
tate
FC
L
,
f
au
lt
cu
r
r
en
t
lim
itin
g
r
ea
cto
r
(
FC
L
R
)
,
e
lectr
o
m
ag
n
etic
FC
L
,
h
y
b
r
id
FC
L
ar
e
r
ep
o
r
ted
in
v
ar
io
u
s
r
esear
ch
wo
r
k
s
[
7
]
-
[
1
5
]
.
SF
C
L
ca
n
b
e
ef
f
ec
tiv
ely
u
s
ed
f
o
r
f
au
lt
cu
r
r
en
t
lim
itatio
n
with
o
u
t
an
y
d
eg
r
ad
a
tio
n
in
h
i
g
h
v
o
ltag
e
AC
g
r
i
d
,
DC
g
r
id
,
an
d
in
ter
co
n
n
ec
ted
h
y
b
r
id
g
r
id
[
1
6
]
-
[
1
8
]
.
Acc
o
r
d
in
g
to
s
tu
d
ies,
SF
C
L
m
ay
r
e
d
u
ce
b
o
th
tr
an
s
ien
t
an
d
s
u
s
tain
ed
f
au
lt
c
u
r
r
e
n
ts
in
a
n
in
te
r
co
n
n
ec
ted
s
y
s
tem
an
d
h
as
a
f
ast
r
esp
o
n
s
e
tim
e.
Stu
d
ies
s
h
o
w
th
at
b
y
ch
o
o
s
in
g
cir
cu
it b
r
ea
k
er
s
with
lo
wer
cu
r
r
en
t
ca
p
ac
ities
an
d
co
o
r
d
in
atin
g
th
eir
u
s
e,
SF
C
L
a
ls
o
en
h
an
ce
s
th
e
s
y
s
tem
[
1
9
]
-
[
2
1
]
.
Su
p
er
c
o
n
d
u
cto
r
n
o
n
li
n
ea
r
ity
an
d
p
o
wer
h
an
d
lin
g
ca
p
ac
ity
ar
e
u
s
ed
f
o
r
FC
L
.
Su
p
er
c
o
n
d
u
cto
r
s
'
n
o
n
li
n
ea
r
r
esp
o
n
s
e
to
f
lu
c
tu
atio
n
s
in
c
u
r
r
en
t,
tem
p
er
atu
r
e,
an
d
m
ag
n
etic
f
ie
ld
d
eter
m
in
es
th
e
f
au
lt
cu
r
r
en
t
s
lim
itin
g
[
2
0
]
-
[
2
4
]
.
As
an
y
o
f
th
ese
p
ar
am
eter
’
s
ch
an
g
e,
th
e
s
u
p
e
r
co
n
d
u
cto
r
s
witch
es
f
r
o
m
its
u
s
u
al
o
p
e
r
atin
g
r
eg
im
e
to
a
s
u
p
e
r
co
n
d
u
ctin
g
o
n
e.
L
iq
u
id
n
itr
o
g
en
is
o
f
ten
u
s
ed
as
a
c
o
o
lan
t
f
o
r
HT
S
SF
C
L
.
So
m
e
o
f
th
e
e
x
ten
s
iv
ely
u
s
ed
HT
S
s
u
p
e
r
co
n
d
u
ctin
g
m
ater
ial
co
m
b
in
atio
n
s
u
s
ed
in
i
n
d
u
s
tr
i
al
ap
p
licatio
n
s
ar
e
B
is
m
u
t
-
Str
o
n
tiu
m
-
C
alciu
m
-
C
o
p
p
e
r
-
Ox
id
e
(
co
m
p
o
u
n
d
o
f
B
i
-
2
2
1
2
/B
i
-
2
2
2
3
)
a
n
d
Yittriu
m
-
B
ar
iu
m
-
C
o
p
p
er
-
Ox
id
e
(
YB
C
O)
[
2
3
]
-
[
2
5
]
.
Fau
lt
cu
r
r
en
t
li
m
iter
s
(
FC
L
s
)
ar
e
s
til
l
b
ein
g
d
ev
elo
p
ed
an
d
r
esear
ch
ed
at
v
ar
io
u
s
lev
els
u
s
in
g
cu
t
tin
g
-
ed
g
e
tech
n
o
lo
g
ies,
i
n
clu
d
in
g
s
o
lid
-
s
tate
an
d
s
u
p
er
co
n
d
u
ctin
g
m
ater
ials
.
Fau
lt
cu
r
r
e
n
t
lim
iter
s
(
FC
L
s
)
ar
e
s
till
b
ein
g
d
e
v
elo
p
e
d
an
d
r
e
s
ea
r
ch
ed
at
v
ar
i
o
u
s
lev
els
u
s
in
g
cu
ttin
g
-
ed
g
e
tech
n
o
lo
g
ies,
in
clu
d
in
g
s
o
lid
-
s
tate
an
d
s
u
p
er
co
n
d
u
ctin
g
m
ater
ials
.
Du
e
to
th
eir
s
im
p
le
d
esig
n
an
d
r
ap
id
r
ed
u
ctio
n
o
f
f
au
lt
cu
r
r
e
n
ts
,
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
c
u
r
r
en
t
lim
iter
s
(
R
SF
C
L
s
)
s
tan
d
o
u
t a
m
o
n
g
th
em
.
R
SF
C
L
s
ar
e
a
d
esira
b
le
o
p
tio
n
f
o
r
u
s
e
in
th
e
cu
r
r
en
t i
n
v
esti
g
atio
n
d
u
e
to
t
h
ese
q
u
alities
.
Fig
u
r
e
1
.
C
u
r
r
e
n
t in
ter
r
u
p
tio
n
ch
ar
ac
ter
is
tics
o
f
FC
L
in
g
en
e
r
al
[
6
]
Pro
tectio
n
en
h
a
n
ce
m
en
t
is
n
o
t
lim
ited
to
a
r
e
d
u
ctio
n
in
f
a
u
lt
cu
r
r
en
t
lev
el.
An
i
n
tellig
en
t
m
o
n
ito
r
in
g
an
d
d
iag
n
o
s
is
s
y
s
tem
to
d
is
ti
n
g
u
is
h
th
e
s
y
s
tem
’
s
n
o
r
m
al
o
p
er
atio
n
a
n
d
ab
n
o
r
m
al
o
p
er
atio
n
in
a
ch
an
g
in
g
en
v
ir
o
n
m
en
t
is
also
v
er
y
cr
u
ci
al.
Ma
ch
in
e
lear
n
in
g
a
n
d
AI
-
b
ased
alg
o
r
ith
m
s
ar
e
b
ec
o
m
i
n
g
p
o
p
u
lar
d
u
e
to
th
eir
ad
ap
tiv
en
ess
an
d
im
p
lem
en
tat
io
n
ef
f
icien
cy
f
o
r
f
a
u
lt
d
etec
t
io
n
an
d
d
iag
n
o
s
is
.
ML
P,
d
ee
p
n
e
u
r
al
n
etwo
r
k
s
,
KNN,
d
ec
is
io
n
t
r
ee
m
o
d
els,
with
s
p
ec
if
ic
f
ea
tu
r
es
ar
e
u
s
ed
as
AI
m
o
d
els
f
o
r
d
if
f
e
r
en
t
f
au
lt
class
if
icatio
n
ap
p
licatio
n
s
[
2
6
]
-
[
3
0
]
.
ANN
-
b
ased
f
au
lt
d
iag
n
o
s
is
s
y
s
tem
s
ar
e
u
s
ed
in
th
is
wo
r
k
s
in
ce
th
ey
ca
n
b
e
tr
ain
ed
with
ch
an
g
in
g
n
etwo
r
k
p
ar
a
m
eter
s
with
less
co
m
p
lex
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
I
n
tellig
en
t fa
u
lt d
i
a
g
n
o
s
is
a
n
d
p
r
o
tectio
n
in
DG
-
co
n
n
ec
ted
s
ystems
…
(
Leksh
mi
R
.
C
h
a
n
d
r
a
n
)
1011
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
s
tr
u
ct
u
r
ed
in
to
two
d
is
tin
ct
p
h
ases
,
ea
ch
m
ak
i
n
g
s
ig
n
if
ican
t
c
o
n
tr
i
b
u
tio
n
s
to
th
e
o
v
er
all
r
esear
c
h
en
d
ea
v
o
r
:
i)
Firstl
y
,
th
e
wo
r
k
f
o
cu
s
es
o
n
th
e
s
tu
d
y
o
f
b
u
s
v
o
ltag
e
a
n
d
cu
r
r
en
t
b
y
p
lacin
g
th
e
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
cu
r
r
en
t
lim
iter
(
R
SF
C
L
)
in
d
if
f
er
en
t
l
o
ca
tio
n
s
with
in
th
e
d
is
tr
ib
u
tio
n
s
y
s
tem
.
T
h
is
p
lace
m
en
t
is
d
eter
m
i
n
ed
b
y
c
o
n
s
id
er
in
g
th
r
ee
cr
itical
f
ac
to
r
s
:
th
e
m
ag
n
itu
d
e
o
f
f
a
u
lt
cu
r
r
e
n
t,
v
o
ltag
e
q
u
ality
,
an
d
r
esis
tan
ce
v
al
u
e.
B
y
ass
ess
in
g
th
e
ef
f
ec
tiv
en
e
s
s
o
f
th
e
R
SF
C
L
in
lim
iti
n
g
f
au
lt
cu
r
r
en
ts
an
d
en
h
an
cin
g
v
o
ltag
e
q
u
ality
,
th
e
s
tu
d
y
estab
lis
h
es
a
co
m
p
r
eh
e
n
s
iv
e
f
r
am
ewo
r
k
f
o
r
its
ap
p
licat
io
n
in
DG
-
ass
is
ted
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
s
.
ii)
Seco
n
d
ly
,
t
h
e
r
esear
c
h
em
p
lo
y
s
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
b
ased
f
au
lt
d
iag
n
o
s
is
tech
n
iq
u
e,
u
tili
zin
g
th
e
s
y
m
m
etr
ical
co
m
p
o
n
en
ts
o
f
cu
r
r
en
t
an
d
v
o
ltag
e
as
k
e
y
elec
tr
ical
s
ig
n
atu
r
e
f
ea
tu
r
es.
T
h
is
in
n
o
v
ativ
e
ap
p
r
o
ac
h
en
ab
les
ac
cu
r
ate
d
etec
tio
n
an
d
id
en
tific
atio
n
o
f
f
a
u
lts
with
in
th
e
s
y
s
tem
.
B
y
lev
er
ag
in
g
th
e
i
n
h
er
en
t
ch
ar
a
cter
is
tics
o
f
s
y
m
m
etr
ical
co
m
p
o
n
en
ts
,
th
e
ANN
-
b
ased
f
au
l
t
d
iag
n
o
s
is
s
ch
em
e
o
f
f
er
s
a
r
o
b
u
s
t
s
o
lu
tio
n
f
o
r
f
a
u
lt
d
etec
tio
n
,
co
n
tr
i
b
u
tin
g
t
o
th
e
o
v
er
all
r
eliab
ilit
y
an
d
ef
f
icie
n
cy
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
T
h
e
ANN
r
ed
u
ce
s
th
e
n
u
is
an
ce
tr
ip
s
o
f
th
e
c
ir
cu
it
b
r
ea
k
er
b
y
p
r
o
v
id
in
g
a
n
ad
d
i
tio
n
al
lay
er
o
f
f
au
lt
d
etec
tio
n
b
ey
o
n
d
th
e
p
r
eset th
r
esh
o
ld
s
.
T
o
g
eth
er
,
t
h
ese
co
n
tr
ib
u
tio
n
s
en
h
an
ce
th
e
f
a
u
lt
m
an
ag
e
m
en
t
ca
p
ab
ilit
ies
o
f
DG
-
ass
is
t
ed
r
ad
ial
d
is
tr
ib
u
tio
n
s
y
s
tem
s
,
p
av
in
g
th
e
way
f
o
r
im
p
r
o
v
ed
s
y
s
tem
p
er
f
o
r
m
a
n
ce
.
T
h
e
r
est
o
f
th
is
wo
r
k
is
o
r
g
an
ized
as
f
o
llo
ws.
Sectio
n
2
g
iv
es
th
e
o
p
er
atio
n
,
r
elate
d
wo
r
k
,
an
d
an
al
y
s
is
o
f
R
SF
C
L
in
th
e
test
s
y
s
te
m
.
Sectio
n
3
d
ef
i
n
es
th
e
ANN
ar
ch
itectu
r
e,
r
elate
d
wo
r
k
s
,
an
d
p
r
o
p
o
s
ed
f
au
lt
d
iag
n
o
s
is
m
o
d
el.
Sectio
n
4
d
ef
in
es
th
e
in
teg
r
ated
s
y
s
tem
ap
p
r
o
ac
h
.
T
h
e
c
o
n
clu
s
io
n
is
p
r
esen
ted
in
s
ec
tio
n
5
.
2.
RE
S
I
ST
I
V
E
SUP
E
RCO
ND
UCTI
NG
F
AUL
T
CURR
E
N
T
L
I
M
I
T
E
R
I
N
D
I
S
T
RI
B
U
T
I
O
N
SYST
E
M
A
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
cu
r
r
e
n
t
lim
iter
(
R
SF
C
L
)
,
as
s
h
o
wn
in
Fig
u
r
e
2
,
with
m
o
d
ellin
g
as
in
(
1
)
,
is
u
s
ed
in
th
is
wo
r
k
d
u
e
to
th
e
s
im
p
licity
o
f
m
o
d
elin
g
an
d
f
ast
r
esp
o
n
s
e.
T
h
e
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
cu
r
r
e
n
t
lim
iter
co
n
s
is
ts
o
f
a
s
u
p
er
co
n
d
u
ctin
g
elem
e
n
t
(
H
T
S)
h
o
u
s
ed
in
a
v
ac
u
u
m
-
in
s
u
la
ted
co
n
tain
er
f
illed
with
co
o
lan
t.
I
t
is
co
n
n
ec
ted
in
s
er
ies
with
th
e
p
o
wer
d
is
tr
ib
u
tio
n
n
etwo
r
k
.
Du
r
i
n
g
n
o
r
m
al
o
p
e
r
atio
n
,
th
e
R
SF
C
L
h
as
a
s
m
all
r
esi
s
tan
ce
(
R
FCL
)
an
d
d
is
s
ip
ates
lo
w
e
n
er
g
y
.
Ho
we
v
er
,
wh
en
a
f
a
u
lt
o
cc
u
r
s
,
th
e
cu
r
r
e
n
t
(I
FCL
)
ex
ce
ed
s
th
e
cr
itical
cu
r
r
en
t
v
alu
e,
ca
u
s
in
g
R
FC
L
to
in
cr
ea
s
e
ex
p
o
n
en
tially
.
T
h
is
lead
s
to
th
e
h
ea
tin
g
o
f
th
e
s
u
p
er
c
o
n
d
u
cto
r
ab
o
v
e
its
c
r
itical
tem
p
er
atu
r
e
(
T
c
)
,
ca
u
s
in
g
a
tr
an
s
itio
n
f
r
o
m
its
s
u
p
e
r
c
o
n
d
u
ctin
g
s
tate
to
a
h
ig
h
ly
r
esis
tiv
e
s
tate.
As
a
r
esu
lt,
th
e
R
SF
C
L
ef
f
ec
tiv
ely
r
ed
u
ce
s
th
e
f
au
lt
cu
r
r
en
t
b
y
e
x
p
lo
iti
n
g
th
e
p
h
e
n
o
m
en
o
n
k
n
o
wn
as
"q
u
en
ch
o
f
s
u
p
er
c
o
n
d
u
ct
o
r
s
".
On
ce
th
e
f
au
lt
cu
r
r
en
t
d
ec
r
ea
s
es,
th
e
s
u
p
er
c
o
n
d
u
ctin
g
m
ater
ial
is
co
o
led
u
s
in
g
cr
y
o
g
e
n
ics,
allo
win
g
R
FCL
to
r
etu
r
n
to
its
s
u
p
er
co
n
d
u
ctin
g
s
tate.
T
h
e
p
ar
allel
r
e
s
is
tan
ce
(
R
sh
)
h
elp
s
d
is
tr
ib
u
te
h
ea
t
d
u
r
in
g
th
e
q
u
e
n
ch
,
r
eg
u
lates
th
e
cu
r
r
e
n
t
lim
itatio
n
,
an
d
p
r
e
v
en
ts
o
v
er
-
v
o
l
tag
e
d
u
e
to
t
h
e
f
ast
cu
r
r
en
t
lim
itatio
n
s
[
2
5
]
,
[
3
1
]
-
[
3
8
]
.
R
SF
C
L
is
m
o
d
eled
as
a
n
o
n
lin
ea
r
r
esis
tan
ce
d
ep
en
d
in
g
o
n
tim
e
as
in
(
1
)
[
2
5
]
,
[
3
5
]
,
[
3
6
]
.
R
F
C
L
(
t
)
=
{
0
t
<
t
a0
R
F
C
L
[
1
−
e
xp
(
−
t
−
t
ao
τ
)
]
1
2
⁄
t
a0
≤
t
<
t
a1
a
1
(
t
−
t
a1
)
+
b
1
t
a1
≤
t
<
t
a2
a
2
(
t
−
t
a2
)
+
b
2
t
a2
≤
t
(1
)
W
h
er
e
R
FCL
is
th
e
n
o
m
in
al
s
ta
te
r
esis
tan
ce
o
f
R
SF
C
L
,
τ
is
th
e
tim
e
co
n
s
tan
t,
t
a0
is
th
e
q
u
en
ch
-
s
tar
tin
g
tim
e,
t
a1
is
th
e
f
ir
s
t
-
s
tag
e
r
ec
o
v
er
y
-
s
tar
tin
g
tim
e,
t
a2
is
th
e
s
ec
o
n
d
ar
y
-
s
tag
e
r
ec
o
v
er
y
-
s
tar
tin
g
tim
e,
an
d
t
co
m
p
leted
r
ec
o
v
er
y
tim
e.
a
1
, a
2
,
b
1
,
an
d
b
2
ar
e
ex
p
r
ess
ed
as th
e
m
o
d
el
c
o
ef
f
icien
ts
.
Fig
u
r
e
2
.
Su
p
er
co
n
d
u
ctin
g
r
esis
tiv
e
f
au
lt c
u
r
r
en
t lim
iter
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
0
9
-
1
0
2
2
1012
T
h
e
ef
f
ec
tiv
en
ess
o
f
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt
cu
r
r
e
n
t
lim
iter
s
to
im
p
r
o
v
e
th
e
v
o
ltag
e
q
u
ality
is
s
u
es
lik
e
v
o
ltag
e
s
ag
an
d
v
o
ltag
e
s
well
is
s
tu
d
ied
in
[
3
2
]
.
R
SF
C
L
m
ad
e
with
YB
C
O
s
h
o
ws
b
etter
tr
an
s
ien
t
s
tab
ilit
y
p
er
f
o
r
m
an
ce
i
n
a
m
u
l
ti
-
m
ac
h
in
e
p
o
wer
s
y
s
tem
t
h
an
I
-
SF
C
L
in
a
co
m
p
a
r
ativ
e
s
tu
d
y
with
YB
C
O
an
d
B
i2
2
1
2
[
2
4
]
,
[
2
5
]
.
T
h
e
c
o
m
p
ar
ativ
e
an
aly
s
is
o
f
d
if
f
er
e
n
t
lo
ca
tio
n
p
lace
m
en
ts
o
f
R
SF
C
L
an
d
I
SF
C
L
f
o
r
tr
an
s
ien
t
s
tab
ilit
y
im
p
r
o
v
em
en
t
s
h
o
ws
th
at
th
e
s
y
s
tem
b
eh
av
es
b
etter
wh
en
R
SF
C
L
i
s
b
etter
th
an
I
SF
C
L
,
ir
r
esp
ec
tiv
e
o
f
its
lo
ca
tio
n
[
39
]
.
W
h
er
ea
s
ac
co
r
d
in
g
t
o
a
s
tu
d
y
in
[
3
3
]
,
th
e
o
p
tim
al
s
izin
g
a
n
d
allo
ca
tio
n
h
ad
a
co
n
s
id
er
ab
le
ef
f
ec
t
o
n
b
etter
p
er
f
o
r
m
a
n
ce
to
th
e
s
ec
u
r
ity
o
f
th
e
n
etwo
r
k
.
T
h
e
b
est
p
r
ac
tices
o
f
FC
L
im
p
lem
en
tatio
n
in
th
e
UK
a
n
d
th
e
USA
r
ep
o
r
ted
th
eir
e
f
f
ec
tiv
en
ess
in
s
y
s
tem
r
esil
ien
ce
an
d
p
r
o
tectio
n
im
p
r
o
v
em
e
n
t [
4
0
]
-
[
4
3
]
.
Fau
lt
cu
r
r
en
t
r
ed
u
ctio
n
ca
p
a
b
ilit
y
,
v
o
ltag
e
q
u
ality
im
p
r
o
v
e
m
en
t,
an
d
m
in
im
al
s
u
p
er
co
n
d
u
ctin
g
f
a
u
lt
cu
r
r
en
t
r
esis
tan
ce
f
ac
to
r
s
ar
e
co
n
s
id
er
ed
f
o
r
th
e
p
lace
m
en
t
o
f
R
SF
C
L
in
th
e
g
iv
e
n
s
y
s
tem
in
th
is
wo
r
k
.
T
h
e
r
esis
tan
ce
v
alu
e
o
f
R
FS
C
L
is
co
n
s
id
er
ed
s
in
ce
th
e
co
s
t
o
f
in
s
tallatio
n
is
h
ig
h
ly
d
ep
e
n
d
e
n
t
o
n
th
e
r
esis
tan
ce
v
alu
e.
T
h
e
h
ig
h
e
r
th
e
r
esis
tan
ce
v
alu
e
h
ig
h
er
th
e
i
n
s
tallatio
n
co
s
t.
T
h
e
test
s
y
s
tem
to
s
tu
d
y
th
e
ef
f
ec
tiv
en
ess
o
f
R
FS
C
L
in
a
DG
-
co
n
n
ec
ted
d
is
tr
ib
u
tio
n
s
y
s
tem
is
s
h
o
wn
in
Fig
u
r
e
3
with
p
a
r
am
eter
s
a
s
s
h
o
wn
in
T
ab
le
1
.
DG’
s
m
e
n
tio
n
ed
in
t
h
is
s
tu
d
y
ca
n
b
e
a
r
ep
r
esen
tatio
n
o
f
s
o
lar
/win
d
/an
y
lo
ca
l
g
e
n
er
ati
o
n
.
T
ab
le
2
s
h
o
ws
t
h
e
s
y
m
m
etr
ical
an
d
u
n
s
y
m
m
etr
ical
f
a
u
lt
cu
r
r
en
ts
o
b
s
er
v
e
d
n
ea
r
th
e
1
1
k
V/4
1
5
V
d
is
tr
ib
u
tio
n
tr
an
s
f
o
r
m
er
b
ef
o
r
e
an
d
af
ter
th
e
in
s
tallatio
n
o
f
DG
at
th
e
P3
lo
ca
tio
n
o
f
th
e
s
y
s
tem
.
I
t
is
o
b
s
er
v
ed
th
at
th
e
in
s
tallatio
n
o
f
DG
ca
u
s
es
th
e
f
au
lt
cu
r
r
e
n
t
to
in
cr
ea
s
e
ab
n
o
r
m
ally
.
T
h
e
d
is
tr
ib
u
tio
n
s
y
s
tem
is
th
en
a
n
a
ly
ze
d
f
o
r
f
a
u
lt c
u
r
r
e
n
t lim
i
tin
g
ab
ilit
y
,
g
r
i
d
v
o
ltag
e
q
u
ality
,
a
n
d
m
in
im
u
m
v
al
u
e
o
f
R
SF
C
L
at
d
if
f
er
en
t a
llo
ca
tio
n
s
o
f
R
SF
C
L
with
p
o
s
itio
n
s
P1
,
P2
,
P3
,
P1
-
P2
,
a
n
d
P1
-
P3
.
T
h
e
p
er
f
o
r
m
an
ce
an
aly
s
is
o
f
th
e
s
y
s
tem
i
s
s
tu
d
ied
u
s
in
g
p
ar
a
m
eter
s
cu
r
r
en
t
r
ed
u
ctio
n
r
atio
an
d
v
o
ltag
e
s
ag
Per
ce
n
tag
e
f
o
r
s
y
m
m
etr
ic
al
f
au
lts
at
F1
an
d
F2
u
s
in
g
(
2
)
an
d
(
3
)
.
C
urr
e
n
t
R
e
duc
tion
R
a
tio
(
C
R
R
)
=
I
s
f
au
l
t
−
I
s
f
c
l
I
s
f
au
l
t
(
2
)
Vol
ta
ge
Sa
g
Pe
r
c
e
n
ta
ge
(
VSP
)
=
(
V
no
m
−
V
s
f
au
l
t
V
no
m
)
x100
(
3
)
W
h
er
e
I
sfault
is
r
m
s
v
alu
e
o
f
f
au
lt
cu
r
r
en
t
with
o
u
t
R
SF
C
L
,
I
sf
cl
r
m
s
v
alu
e
o
f
f
a
u
lt
c
u
r
r
e
n
t
with
R
SF
C
L
,
V
sfault
is
r
m
s
lin
e
v
o
ltag
e
o
f
s
y
s
tem
d
u
r
in
g
f
au
lt,
V
nom
is
n
o
m
i
n
al
r
m
s
s
y
s
tem
v
o
ltag
e.
T
ab
le
1
.
T
est s
y
s
tem
p
ar
am
ete
r
s
P
a
r
a
me
t
e
r
s
V
a
l
u
e
D
i
st
r
i
b
u
t
i
o
n
s
y
st
e
m
v
o
l
t
a
g
e
(
l
i
n
e
t
o
l
i
n
e
,
R
M
S
)
11
kV
N
o
mi
n
a
l
s
y
st
e
m fr
e
q
u
e
n
c
y
50
Hz
S
o
u
r
c
e
X
/
R
r
a
t
i
o
7
Tr
a
n
sf
o
r
mer
1
1
0
0
M
V
A
,
3
3
k
V
/
1
1
kV
Tr
a
n
sf
o
r
mer
2
2
5
0
K
V
A
,
1
1
k
V
/
4
1
5
V
D
i
st
r
i
b
u
t
i
o
n
g
e
n
e
r
a
t
o
r
5
0
k
W
-
5
k
V
A
R
N
e
t
d
o
mest
i
c
a
n
d
c
o
mm
e
r
c
i
a
l
l
o
a
d
s
60
k
W
,
1
0
k
V
A
R
N
e
t
i
n
d
u
st
r
i
a
l
l
o
a
d
s
45
k
W
,
2
k
V
A
R
T
ab
le
2
.
Peak
R
MS
o
f
f
a
u
lt c
u
r
r
en
t o
f
th
e
test
s
y
s
tem
with
an
d
with
o
u
t D
G
F
a
u
l
t
p
o
si
t
i
o
n
F1
F2
F
a
u
l
t
t
y
p
e
W
i
t
h
o
u
t
D
G
W
i
t
h
D
G
W
i
t
h
o
u
t
D
G
W
i
t
h
D
G
I
max
(A)
I
min
(A)
I
max
(A)
I
min
(A)
I
max
(A)
I
min
(A)
I
max
(A)
I
min
(A)
S
y
mm
e
t
r
i
c
a
l
f
a
u
l
t
(
A
B
C
G
)
4
2
2
0
3
5
6
0
4
5
5
0
4
1
2
5
4
4
0
0
3
5
0
0
4
5
6
0
4
1
0
0
A
sy
mm
e
t
r
i
c
a
l
f
a
u
l
t
(
A
G
)
2
6
5
4
1
5
5
0
3
1
0
0
2
0
7
9
2
6
0
0
1
4
4
0
2
9
9
5
2
0
2
5
T
ab
le
3
(
s
ee
Ap
p
en
d
ix
)
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
a
n
aly
s
is
o
f
t
h
e
s
y
s
tem
f
o
r
s
y
m
m
etr
ical
f
au
lts
F1
an
d
F2
with
R
FS
C
L
p
lace
d
at
d
if
f
er
en
t p
o
s
itio
n
s
.
T
h
e
v
ar
io
u
s
o
b
s
er
v
atio
n
s
f
o
r
ea
ch
R
FS
C
L
p
o
s
itio
n
b
ased
o
n
th
e
p
r
o
v
id
e
d
s
y
m
m
etr
ical
f
a
u
lt F1
an
d
F2
s
ce
n
ar
io
s
ar
e
as f
o
llo
ws:
i)
P1
p
o
s
itio
n
:
T
h
e
P1
p
o
s
itio
n
d
em
o
n
s
tr
ates
a
s
tr
o
n
g
ab
ilit
y
to
r
e
d
u
ce
f
au
lt
cu
r
r
en
ts
,
wi
th
th
e
cu
r
r
en
t
r
ed
u
ctio
n
r
atio
(
C
R
R
)
r
ea
ch
in
g
6
7
.
9
3
%
at
a
r
esis
tan
ce
o
f
4
0
Ω
f
o
r
b
o
t
h
F1
a
n
d
F2
s
ce
n
ar
io
s
.
I
t
als
o
m
ain
tain
s
v
o
ltag
e
q
u
ality
well,
ev
id
en
ce
d
b
y
a
lo
w
v
o
ltag
e
s
ag
p
er
ce
n
tag
e
(
VSP)
o
f
2
.
6
4
%
at
th
e
s
am
e
r
esis
tan
ce
lev
el.
T
h
is
in
d
icate
s
th
at
P1
is
ef
f
ec
tiv
e
in
b
o
th
cu
r
r
en
t lim
itatio
n
an
d
v
o
ltag
e
s
tab
ilizatio
n
.
ii)
P2
p
o
s
itio
n
:
T
h
e
P2
p
o
s
itio
n
h
as
n
o
im
p
ac
t
o
n
f
au
lt
cu
r
r
en
t
r
ed
u
ctio
n
in
th
e
F1
s
ce
n
ar
io
,
b
u
t
it
s
h
o
ws
a
m
ar
k
ed
im
p
r
o
v
em
en
t
in
t
h
e
F2
s
ce
n
ar
io
as
r
esis
tan
ce
in
cr
ea
s
es.
Sp
ec
if
ically
,
at
4
0
Ω
,
it
ac
h
iev
es
a
C
R
R
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
I
n
tellig
en
t fa
u
lt d
i
a
g
n
o
s
is
a
n
d
p
r
o
tectio
n
in
DG
-
co
n
n
ec
ted
s
ystems
…
(
Leksh
mi
R
.
C
h
a
n
d
r
a
n
)
1013
o
f
8
7
.
2
6
%
an
d
a
VSP
o
f
1
.
7
3
%
f
o
r
F2
,
s
h
o
wca
s
in
g
its
p
o
ten
tial
f
o
r
s
ig
n
if
ican
t
cu
r
r
en
t
lim
itatio
n
an
d
v
o
ltag
e
q
u
ality
m
ain
ten
a
n
ce
u
n
d
er
ce
r
tain
f
au
lt
c
o
n
d
itio
n
s
.
H
o
wev
er
,
th
e
p
er
f
o
r
m
an
ce
is
h
ig
h
ly
d
ep
e
n
d
en
t
o
n
th
e
f
a
u
lt ty
p
e,
w
h
ich
m
ay
lim
it its
b
r
o
ad
er
ap
p
licab
ilit
y
.
iii)
P3
p
o
s
itio
n
:
T
h
e
P3
p
o
s
itio
n
i
s
less
ef
f
ec
tiv
e
co
m
p
ar
ed
t
o
P1
,
with
C
R
R
v
alu
es
co
n
s
id
er
ab
ly
lo
wer
a
n
d
VSP
f
ig
u
r
es
th
at
r
e
m
ain
r
elativ
ely
h
i
g
h
ac
r
o
s
s
all
r
esis
tan
ce
v
alu
es
f
o
r
b
o
th
f
a
u
lt
s
ce
n
ar
io
s
.
At
4
0
Ω
,
th
e
C
R
R
i
s
ar
o
u
n
d
1
2
%
f
o
r
b
o
th
F1
an
d
F2
,
an
d
th
e
VSP
i
s
9
9
.
1
8
%,
in
d
icatin
g
th
at
P3
is
n
o
t
as
ca
p
ab
le
in
m
an
ag
in
g
f
au
lt c
u
r
r
en
ts
o
r
m
a
in
tain
in
g
v
o
ltag
e
q
u
ality
as th
e
o
th
er
p
o
s
itio
n
s
.
iv
)
P1
-
P2
p
o
s
itio
n
:
C
o
m
b
in
in
g
P1
an
d
P2
p
o
s
itio
n
s
o
f
f
er
s
a
b
a
lan
ce
d
s
o
lu
tio
n
.
At
a
r
esis
tan
c
e
o
f
4
0
Ω
,
th
e
co
m
b
in
ed
P1
-
P2
p
o
s
itio
n
d
eliv
er
s
a
h
ig
h
C
R
R
o
f
ar
o
u
n
d
6
7
%
f
o
r
F1
an
d
8
9
%
f
o
r
F2
,
alo
n
g
with
a
lo
w
VSP
o
f
2
.
6
4
%
f
o
r
b
o
th
f
au
lts
.
T
h
is
co
m
b
in
atio
n
em
er
g
es
as
a
s
t
r
o
n
g
co
n
ten
d
er
f
o
r
R
FS
C
L
p
lace
m
en
t,
ac
h
iev
in
g
s
ig
n
if
ica
n
t c
u
r
r
e
n
t r
ed
u
ctio
n
a
n
d
g
o
o
d
v
o
ltag
e
s
ta
b
ilizatio
n
.
v)
P2
-
P3
p
o
s
itio
n
:
P2
-
P3
,
wh
ile
o
f
f
er
in
g
im
p
r
o
v
em
e
n
ts
in
f
au
l
t
cu
r
r
en
t
r
ed
u
ctio
n
in
th
e
F2
s
ce
n
ar
io
,
d
o
es
n
o
t
p
r
o
v
i
d
e
as
c
o
m
p
ellin
g
r
es
u
lts
in
th
e
F1
s
ce
n
ar
io
,
with
n
o
im
p
ac
t
o
n
f
a
u
lt
cu
r
r
en
t
r
ed
u
ctio
n
o
b
s
er
v
ed
.
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
th
is
p
o
s
itio
n
co
m
b
in
atio
n
is
m
o
r
e
p
r
o
n
o
u
n
ce
d
in
th
e
F2
s
ce
n
ar
io
,
wh
er
e
at
2
0
Ω
,
a
C
R
R
o
f
o
v
er
7
5
% is
ac
h
iev
ed
,
alth
o
u
g
h
th
is
is
less
th
an
wh
at
is
s
ee
n
in
th
e
P1
-
P2
co
m
b
in
at
io
n
.
v
i)
P1
-
P3
p
o
s
itio
n
:
T
h
is
p
o
s
itio
n
p
r
o
v
id
es
a
n
o
ta
b
le
C
R
R
f
o
r
b
o
th
F1
a
n
d
F2
at
m
o
d
er
ate
r
es
is
tan
ce
v
alu
es,
m
ain
tain
in
g
g
o
o
d
v
o
ltag
e
q
u
a
lity
at
h
ig
h
er
r
esis
tan
ce
lev
els.
T
h
is
s
u
g
g
ests
th
at
th
e
P1
-
P3
co
m
b
in
atio
n
co
u
ld
b
e
c
o
n
s
id
er
ed
f
o
r
R
FS
C
L
p
lace
m
en
t,
esp
ec
ially
at
a
r
e
s
is
tan
ce
lev
el
o
f
a
r
o
u
n
d
4
0
Ω
,
wh
ich
b
alan
ce
s
p
er
f
o
r
m
an
ce
with
co
s
t c
o
n
s
id
er
atio
n
s
.
v
ii)
P1
-
P2
-
P3
p
o
s
itio
n
:
W
h
ile
th
e
P1
-
P2
-
P3
p
o
s
itio
n
d
e
m
o
n
s
tr
at
es
h
ig
h
C
R
R
v
alu
es
at
h
ig
h
er
r
esis
tan
ce
s
,
it
m
ay
n
o
t
b
e
as
co
s
t
-
ef
f
ec
tiv
e
d
u
e
to
th
e
im
p
licatio
n
s
o
f
i
n
s
tallin
g
R
FS
C
L
s
ac
r
o
s
s
m
u
ltip
le
l
o
ca
tio
n
s
.
T
h
e
p
er
f
o
r
m
an
ce
at
h
ig
h
er
r
esis
tan
ce
s
is
o
p
tim
al,
b
u
t
f
o
r
co
s
t
-
ef
f
e
ctiv
en
ess
,
th
e
r
ec
o
m
m
en
d
atio
n
is
to
co
n
s
id
er
o
th
er
p
o
s
itio
n
co
m
b
i
n
atio
n
s
.
v
iii)
A
tr
ad
eo
f
f
is
co
n
s
id
er
e
d
f
o
r
th
e
p
r
o
p
e
r
p
lace
m
en
t
o
f
ac
co
u
n
t
in
g
f
au
lt
cu
r
r
en
t
lim
itin
g
ab
ilit
y
,
g
r
id
v
o
ltag
e
q
u
ality
,
an
d
m
in
im
u
m
v
alu
e
o
f
R
SF
C
L
.
T
h
u
s
,
p
o
s
itio
n
P1
-
P2
with
a
m
ax
im
u
m
r
esis
tan
ce
o
f
2
0
Ω
is
s
elec
ted
b
ased
o
n
th
is
tr
ad
e
o
f
f
.
At
2
0
Ω
r
esis
tan
ce
,
P1
-
P2
s
h
o
ws a
C
R
R
o
f
5
7
.
7
9
% f
o
r
s
y
m
m
etr
ical
f
au
l
t
F1
an
d
8
2
.
1
6
%
f
o
r
s
y
m
m
etr
ic
al
f
au
lt
F2
.
T
h
is
in
d
icate
s
a
h
i
g
h
ef
f
icac
y
in
lim
itin
g
t
h
e
f
a
u
lt
cu
r
r
en
t
f
o
r
b
o
th
ty
p
es o
f
f
a
u
lts
.
A
r
ed
u
ctio
n
o
f
o
v
er
5
0
%
in
f
a
u
lt
cu
r
r
e
n
t
is
s
ig
n
if
ica
n
t
an
d
i
m
p
lies
th
at
th
e
p
r
o
tectiv
e
e
q
u
i
p
m
en
t
a
n
d
th
e
r
est
o
f
th
e
s
y
s
tem
ar
e
s
u
b
jecte
d
to
m
u
ch
lo
wer
s
tr
ess
d
u
r
in
g
f
au
lt
co
n
d
itio
n
s
.
T
h
e
VSP
at
2
0
Ω
f
o
r
P1
-
P2
is
8
.
0
9
%
f
o
r
F1
an
d
-
3
.
2
7
%
f
o
r
F2
.
A
VSP
o
f
8
.
0
9
%
s
u
g
g
ests
th
at
th
e
v
o
ltag
e
s
ag
is
with
in
ac
ce
p
tab
le
lim
its
,
m
ain
tain
in
g
g
r
i
d
s
tab
ilit
y
clo
s
e
to
th
e
n
o
m
in
al
v
o
lta
g
e
d
u
r
in
g
a
f
au
lt.
T
h
e
VSP
g
o
es
s
lig
h
tly
n
eg
ativ
e
(
-
1
.
9
1
%),
wh
ich
m
ig
h
t im
p
ly
a
s
lig
h
t o
v
er
v
o
ltag
e
co
n
d
itio
n
,
b
u
t sti
ll s
u
g
g
ests
g
o
o
d
v
o
lta
g
e
co
n
tr
o
l
d
u
r
in
g
f
au
lts
.
L
o
wer
r
esis
tan
ce
v
alu
es
u
s
u
ally
tr
a
n
s
late
in
to
lo
wer
m
ater
ial
c
o
s
ts
an
d
p
o
ten
tially
r
ed
u
ce
d
co
o
lin
g
r
eq
u
i
r
em
en
ts
,
th
u
s
r
esu
ltin
g
in
o
v
er
all
s
av
in
g
s
in
th
e
im
p
lem
en
tatio
n
an
d
o
p
er
atio
n
al
p
h
ases
.
T
h
e
f
a
u
lt
cu
r
r
en
t
r
e
d
u
ctio
n
an
d
v
o
ltag
e
q
u
ality
im
p
r
o
v
em
e
n
t
ar
e
o
b
s
er
v
ed
in
all
f
au
lt
ca
s
es.
T
h
e
v
o
ltag
e
q
u
ality
o
f
th
e
s
y
s
tem
ca
n
f
u
r
th
er
b
e
im
p
r
o
v
e
d
u
s
in
g
p
o
wer
c
o
m
p
e
n
s
ato
r
s
.
Fig
u
r
e
3
.
T
est s
y
s
tem
o
f
th
e
DG
-
co
n
n
ec
ted
d
is
tr
ib
u
tio
n
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
0
9
-
1
0
2
2
1014
3.
P
RO
P
O
SE
D
F
AUL
T
D
I
AG
NO
SI
S
M
E
T
H
O
DO
L
O
G
Y:
I
NT
E
L
L
I
G
E
N
T
F
AUL
T
DI
AG
NO
SI
S
USI
NG
AR
T
I
F
I
CIA
L
N
E
U
RAL N
E
T
WO
RK
I
n
tellig
en
t
s
y
s
tem
s
ar
e
m
o
r
e
w
id
ely
u
s
ed
n
o
wa
d
ay
s
s
in
ce
th
e
y
ca
n
o
p
e
r
ate
au
t
o
n
o
m
o
u
s
ly
,
with
h
ig
h
er
lev
els
o
f
ac
cu
r
ac
y
a
n
d
r
eliab
il
ity
.
An
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
aid
ed
in
tellig
en
t
f
a
u
lt
d
iag
n
o
s
is
is
also
m
o
d
eled
in
th
is
s
tu
d
y
,
alo
n
g
with
th
e
p
r
o
tectio
n
en
h
a
n
ce
m
en
t
o
f
th
e
s
y
s
tem
u
s
in
g
R
FS
C
L
.
Un
s
y
m
m
etr
ical
f
au
lt a
n
aly
s
is
with
o
u
t c
o
n
s
id
er
in
g
s
y
m
m
et
r
ical
f
au
lts
u
s
in
g
ANN
is
m
en
tio
n
ed
in
th
e
wo
r
k
[
4
4
]
.
T
r
a
n
s
m
is
s
io
n
lin
e
f
au
lt
d
etec
tio
n
an
d
l
o
ca
tio
n
id
en
tific
atio
n
with
R
MS
v
alu
es
o
f
cu
r
r
en
t
an
d
v
o
ltag
e
a
s
f
ea
tu
r
e
v
ar
iab
les
is
m
en
tio
n
ed
in
th
e
wo
r
k
[
4
5
]
.
ANN
an
d
w
av
elet
-
b
ased
f
au
lt
id
en
tific
atio
n
an
d
lo
ca
lizatio
n
ar
e
an
aly
ze
d
in
th
e
wo
r
k
[
4
6
]
.
An
t
co
lo
n
y
o
p
tim
iz
atio
n
-
b
ased
wa
v
elet
tr
an
s
f
o
r
m
an
d
ANN
to
d
etec
t
f
au
lts
in
H
VDC tr
an
s
m
is
s
io
n
lin
es
is
m
en
tio
n
ed
in
th
e
wo
r
k
[
4
7
]
.
Hig
h
im
p
e
d
an
ce
f
au
lt
d
etec
tio
n
u
s
in
g
d
is
cr
ete
wav
elet
an
d
d
ec
is
io
n
tr
ee
,
f
au
lt
d
etec
tio
n
an
d
lo
ca
tio
n
p
r
ed
ictio
n
u
s
in
g
s
p
ac
e
v
ec
to
r
m
ac
h
in
e
(
SVM
)
an
d
Gau
s
s
ian
r
eg
r
ess
io
n
,
ad
ap
tiv
e
f
u
zz
y
-
b
ased
r
elay
p
r
o
tectio
n
,
an
d
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ar
e
also
m
en
tio
n
e
d
in
v
ar
io
u
s
wo
r
k
s
[
4
8
]
-
[
5
0
]
.
ANN
-
b
ased
f
au
lt
id
en
tific
atio
n
u
s
es
R
MS
v
alu
es
o
r
wav
elet
c
o
ef
f
icien
ts
,
o
r
th
eir
s
tatic
o
r
d
y
n
am
ic
f
ea
tu
r
e
d
er
iv
ativ
es,
as
th
e
f
ea
t
u
r
es
f
o
r
tr
ain
in
g
.
W
av
elet
-
b
as
ed
f
au
lt
class
if
icatio
n
u
s
in
g
S
VM
[
5
1
]
an
d
ANN
[5
2
]
f
o
r
tr
an
s
m
is
s
io
n
lin
es
h
as
b
ee
n
s
tu
d
ied
.
T
h
e
s
tu
d
y
in
[5
3
]
an
aly
ze
s
f
au
lt
d
etec
tio
n
an
d
class
if
icatio
n
in
co
m
p
en
s
ated
tr
a
n
s
m
is
s
io
n
lin
es
u
s
in
g
in
s
tan
tan
eo
u
s
v
o
ltag
e
an
d
cu
r
r
en
t
s
ig
n
als.
PC
A
-
b
ased
f
ea
tu
r
e
ex
tr
ac
tio
n
r
ed
u
ce
s
d
im
en
s
io
n
ality
,
ca
p
tu
r
in
g
k
ey
tim
e
-
f
r
eq
u
en
cy
f
ea
tu
r
es.
Ma
ch
in
e
lear
n
in
g
class
if
ier
s
(
KNN,
MN
N,
QSVM)
ar
e
co
m
p
ar
ed
,
with
QSVM
ac
h
iev
in
g
9
9
.
3
%
ac
cu
r
ac
y
.
T
h
e
v
ar
io
u
s
f
ea
tu
r
e
s
u
s
ed
f
o
r
tr
ain
i
n
g
i
n
s
tu
d
ies
[
4
4
]
-
[
5
3
]
ar
e
m
ain
ly
in
s
tan
ta
n
eo
u
s
v
al
u
es,
R
MS
v
alu
es,
an
d
wav
elet
c
o
ef
f
icien
t
s
,
o
r
th
eir
s
tatis
tical
d
er
iv
ativ
es
o
f
eith
er
v
o
ltag
e
o
r
cu
r
r
en
t
o
r
b
o
th
.
T
h
e
elec
tr
ical
s
ig
n
atu
r
e
f
ea
tu
r
es
id
en
tifie
d
f
o
r
th
e
c
u
r
r
e
n
t
wo
r
k
ar
e
th
e
s
y
m
m
etr
ical
co
m
p
o
n
e
n
ts
o
f
v
o
ltag
e
an
d
cu
r
r
en
t.
Ass
u
m
in
g
S
A
,
S
B
,
an
d
S
C
ar
e
th
e
p
h
ase
v
o
ltag
es
(
o
r
cu
r
r
en
ts
)
o
f
an
u
n
b
alan
ce
d
th
r
ee
-
p
h
ase
s
y
s
tem
,
th
e
tr
an
s
f
o
r
m
atio
n
to
s
y
m
m
etr
ical
co
m
p
o
n
en
ts
ca
n
b
e
r
ep
r
esen
te
d
b
y
(
4
)
.
[
1
2
0
]
=
1
3
[
1
2
1
2
1
1
1
]
[
]
(
4
)
S
1
,
S
2
,
S
0
r
ep
r
esen
t
th
e
p
o
s
itiv
e,
n
eg
ativ
e,
an
d
ze
r
o
s
eq
u
en
c
e
co
m
p
o
n
e
n
ts
,
r
esp
ec
tiv
ely
,
an
d
a
is
th
e
co
m
p
lex
o
p
er
ato
r
d
ef
in
e
d
as
a
=c
o
s
(
1
2
0
°
)+
j
s
in
(
1
2
0
°
)
.
T
h
e
co
llectiv
e
in
f
o
r
m
atio
n
ab
o
u
t
th
ese
f
ea
tu
r
e
v
ar
ia
b
les
co
m
m
u
n
icate
d
to
th
e
u
tili
ty
ce
n
ter
h
elp
s
in
id
en
tify
in
g
th
e
t
y
p
e
an
d
zo
n
e/l
o
ca
tio
n
o
f
th
e
f
au
lt.
T
h
is
co
n
c
ep
t o
f
in
tellig
en
t f
au
lt d
ia
g
n
o
s
is
b
y
u
tili
ty
ce
n
ter
s
u
s
in
g
s
y
m
m
etr
ical
co
m
p
o
n
e
n
ts
o
f
v
o
ltag
e
a
n
d
c
u
r
r
en
t is th
e
f
o
cu
s
o
f
t
h
is
r
esear
ch
wo
r
k
.
T
h
e
m
eth
o
d
o
lo
g
y
f
o
r
d
e
v
elo
p
in
g
an
d
im
p
lem
e
n
tin
g
th
e
in
te
llig
en
t
f
au
lt
d
etec
to
r
u
s
in
g
A
NN
is
i
llu
s
tr
ated
in
Fig
u
r
e
4
.
I
t
co
n
s
is
ts
o
f
th
e
f
o
ll
o
win
g
s
tep
s
:
-
Step
1
:
Data
c
o
llectio
n
:
T
h
r
ee
-
p
h
ase
in
s
tan
tan
eo
u
s
v
o
ltag
e
an
d
cu
r
r
e
n
t
d
ata
at
b
u
s
2
an
d
b
u
s
4
o
f
th
e
test
s
y
s
tem
(
as
in
Fig
u
r
e
3
)
a
r
e
co
ll
ec
ted
f
o
r
n
o
r
m
al
a
n
d
v
ar
io
u
s
f
a
u
lt
co
n
d
itio
n
s
.
T
h
e
f
au
lt
c
o
n
d
it
io
n
s
ar
e
cr
ea
ted
b
y
v
ar
y
in
g
f
au
lt r
esis
tan
ce
,
lo
ad
,
an
d
DG
lev
els at
d
if
f
er
en
t
f
au
lt lo
ca
tio
n
s
.
-
Step
2
:
Featu
r
e
ex
tr
ac
tio
n
:
Sy
m
m
etr
ical
co
m
p
o
n
e
n
ts
o
f
v
o
lt
ag
e
an
d
cu
r
r
en
t
at
b
u
s
2
a
n
d
b
u
s
4
f
o
r
f
au
lts
at
F1
an
d
F2
,
b
o
t
h
in
th
e
p
r
esen
c
e
an
d
a
b
s
en
ce
o
f
DG
an
d
R
SF
C
L
,
ar
e
an
aly
ze
d
an
d
ex
tr
ac
te
d
.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
an
aly
zin
g
th
e
d
ata
d
u
r
in
g
f
a
u
lt
an
d
p
r
e
-
f
a
u
lt
co
n
d
itio
n
s
.
A
d
ata
s
et
o
f
2
5
0
0
s
am
p
les
p
er
lab
el
is
co
llected
as in
p
u
t f
ea
tu
r
es f
o
r
tr
ain
in
g
th
e
ANN
m
o
d
el.
-
Step
3
:
No
r
m
aliza
tio
n
an
d
tr
an
s
f
o
r
m
atio
n
:
T
h
e
in
p
u
t
f
ea
tu
r
es
ar
e
n
o
r
m
alize
d
a
n
d
tr
an
s
f
o
r
m
ed
to
a
r
an
g
e
o
f
-
1
to
+1
.
T
h
is
n
o
r
m
aliza
tio
n
p
r
o
ce
s
s
h
elp
s
im
p
r
o
v
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
n
e
u
r
al
n
etwo
r
k
s
.
-
Step
4
: Fau
lt
l
ab
elin
g
: D
if
f
er
en
t f
au
lt c
o
n
d
itio
n
s
,
s
u
ch
as sy
m
m
etr
ical
f
au
lts
,
u
n
s
y
m
m
etr
ic
al
f
au
lts
,
an
d
n
o
f
au
lts
at
b
u
s
2
(
Z
o
n
e
1
)
an
d
b
u
s
4
(
Z
o
n
e
4
)
,
ar
e
la
b
eled
as
F1
to
F2
3
.
On
e
-
h
o
t
en
co
d
in
g
is
u
s
ed
to
r
e
p
r
esen
t
th
e
f
au
lt lab
els/
tar
g
ets in
th
is
s
tu
d
y
.
-
Step
5
:
ANN
t
r
ain
in
g
:
T
h
e
A
NN
m
o
d
el
is
tr
ain
ed
b
y
tu
n
in
g
th
e
m
o
d
el
p
ar
am
eter
s
an
d
h
y
p
er
p
a
r
am
eter
s
u
n
til
th
e
d
esire
d
n
etwo
r
k
s
ettin
g
p
a
r
am
eter
s
ar
e
ac
h
ie
v
ed
.
T
h
e
n
e
u
r
al
n
etwo
r
k
'
s
weig
h
ts
an
d
b
iases
ar
e
ad
ju
s
ted
d
u
r
in
g
th
is
p
r
o
c
ess
t
o
m
in
im
ize
th
e
er
r
o
r
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
f
au
lt
lab
els.
7
0
%
o
f
th
e
d
ata
is
u
s
ed
f
o
r
tr
ai
n
in
g
a
n
d
3
0
% f
o
r
test
in
g
.
-
Step
6
:
T
est
an
d
p
er
f
o
r
m
an
ce
a
n
aly
s
is
:
T
h
e
tr
ain
ed
ANN
m
o
d
el
is
test
ed
u
s
in
g
u
n
s
ee
n
d
at
a
to
e
v
alu
ate
its
p
er
f
o
r
m
an
ce
.
Per
f
o
r
m
an
ce
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
e
ca
lc
u
lated
to
ass
ess
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
m
o
d
el
in
d
etec
tin
g
an
d
class
if
y
in
g
f
au
lt
s
.
-
Step
7
:
Selectio
n
a
n
d
d
ep
lo
y
m
en
t:
B
ased
o
n
t
h
e
p
e
r
f
o
r
m
an
ce
an
aly
s
is
,
th
e
b
est
-
p
er
f
o
r
m
in
g
ANN
m
o
d
el
is
s
elec
ted
an
d
d
ep
lo
y
ed
f
o
r
r
ea
l
-
wo
r
ld
f
a
u
lt d
etec
tio
n
in
DG
-
c
o
n
n
ec
ted
d
is
tr
ib
u
tio
n
s
y
s
tem
s
.
Mu
lti
-
co
llin
ea
r
ity
ef
f
ec
t
o
f
f
ea
tu
r
e
v
ar
iab
les
is
an
aly
ze
d
u
s
in
g
b
iv
ar
iate
co
r
r
elatio
n
.
Hig
h
ly
d
ep
en
d
e
n
t
f
ea
tu
r
e
v
ar
iab
les
h
av
e
h
ig
h
co
r
r
elatio
n
v
alu
es.
I
n
s
u
c
h
ca
s
es,
o
n
e
o
f
th
e
v
ar
iab
les
ca
n
b
e
e
lim
in
ated
.
Fig
u
r
e
5
s
h
o
ws
th
e
co
r
r
elatio
n
g
r
ap
h
an
d
p
air
p
l
o
t
o
f
all
1
2
f
ea
tu
r
e
v
ar
iab
les.
T
h
e
v
ar
iab
les
(
1
2
n,
v
2
n
)
ar
e
h
ig
h
l
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
I
n
tellig
en
t fa
u
lt d
i
a
g
n
o
s
is
a
n
d
p
r
o
tectio
n
in
DG
-
co
n
n
ec
ted
s
ystems
…
(
Leksh
mi
R
.
C
h
a
n
d
r
a
n
)
1015
co
r
r
elate
d
with
a
co
r
r
elatio
n
o
f
0
.
8
1
.
Hen
ce
,
v
2
n
is
d
r
o
p
p
ed
f
r
o
m
f
u
r
th
er
tr
ain
i
n
g
o
f
th
e
s
y
s
tem
.
A
d
en
s
e
n
eu
r
al
n
etwo
r
k
is
u
s
ed
f
o
r
m
o
d
elin
g
i
n
th
is
wo
r
k
[
4
7
]
,
[
5
4
].
T
h
e
g
en
er
al
s
tr
u
ctu
r
e
o
f
th
e
d
en
s
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
m
o
d
el
ca
n
b
e
r
ep
r
e
s
en
ted
as
f
o
llo
ws
.
I
n
p
u
t
v
ec
to
r
with
n
u
m
b
er
o
f
f
ea
tu
r
e
in
p
u
ts
I
,
is
x
R
I
.
Fo
r
th
e
l
th
h
i
d
d
en
lay
er
with
N
l
n
u
m
b
er
o
f
n
eu
r
o
n
s
,
th
e
o
u
t
p
u
t is ca
lcu
lated
u
s
in
g
th
e
f
o
r
m
u
la
as in
(
5
)
.
ℎ
(
)
=
(
)
(
(
)
ℎ
(
−
1
)
+
(
)
)
(
ℎ
ℎ
(
0
)
=
)
(
5
)
W
h
er
e
th
e
h
id
d
e
n
lay
er
weig
h
t m
atr
ix
is
(
)
−
1
(
ℎ
0
=
)
an
d
b
ias m
atr
ix
is
(
)
∈
.
Fig
u
r
e
4
.
ANN
-
b
ased
f
au
lt d
ia
g
n
o
s
is
s
y
s
tem
Fig
u
r
e
5
.
C
o
r
r
elatio
n
g
r
a
p
h
o
f
f
ea
tu
r
e
v
ar
ia
b
les
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
0
9
-
1
0
2
2
1016
T
h
e
o
u
tp
u
t v
ec
to
r
y
in
th
e
o
u
t
p
u
t la
y
er
is
ca
lcu
lated
u
s
in
g
th
e
f
o
r
m
u
la
as in
(
6)
.
=
(
)
(
(
)
ℎ
(
)
+
(
)
)
(
6
)
W
h
er
e
th
e
o
u
tp
u
t
weig
h
t
m
at
r
ix
is
(
)
an
d
th
e
b
ias
m
atr
i
x
is
(
)
∈
,
L
is
th
e
n
u
m
b
er
o
f
h
i
d
d
en
lay
er
s
an
d
o
is
th
e
n
u
m
b
er
o
f
o
u
tp
u
t
class
es.
T
h
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
,
r
ep
r
esen
ted
as
f
(
l
)
u
s
ed
i
n
h
id
d
en
lay
e
r
s
is
d
ef
in
ed
as in
(
7
)
.
T
h
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
in
th
e
o
u
t
p
u
t la
y
e
r
tr
a
n
s
f
o
r
m
s
th
e
o
u
tp
u
t in
to
a
p
r
o
b
a
b
ilit
y
d
i
s
tr
ib
u
tio
n
o
v
e
r
th
e
2
3
o
u
tp
u
t c
lass
es.
(
)
(
)
=
ma
x
(
0
,
)
(
7
)
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
e
test
s
y
s
tem
with
R
FS
C
L
p
lace
d
at
th
e
p
o
s
itio
n
P1
-
P2
i
n
a
DG
-
c
o
n
n
ec
te
d
d
is
tr
ib
u
tio
n
s
y
s
tem
,
as
s
h
o
wn
in
Fig
u
r
e
3
,
with
p
ar
a
m
eter
s
as
s
h
o
wn
in
T
ab
le
1
,
i
s
an
aly
ze
d
f
o
r
v
ar
io
u
s
f
au
lt
c
lass
if
icatio
n
s
u
s
in
g
d
if
f
er
en
t
ANN
m
o
d
els.
T
h
e
s
ize
o
f
th
e
in
p
u
t
lay
er
o
f
th
e
A
NN
d
ep
en
d
s
o
n
th
e
in
p
u
t
f
ea
t
u
r
es,
an
d
th
e
o
u
tp
u
t
lay
er
d
ep
en
d
s
o
n
th
e
tar
g
et.
A
d
r
o
p
o
u
t
o
f
0
.
2
is
u
s
ed
f
o
r
r
eg
u
lar
izatio
n
.
T
h
e
tr
ain
in
g
o
f
th
e
ANN
in
v
o
lv
es
ad
ju
s
tin
g
th
e
weig
h
ts
an
d
b
iases
to
m
in
im
ize
th
e
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
.
ANN
m
o
d
el
s
u
s
e
d
f
o
r
tr
ain
in
g
th
e
m
o
d
el
ar
e
s
h
o
wn
in
T
ab
le
4
.
Mo
d
el
6
s
h
o
ws
9
9
.
7
%
ac
cu
r
ac
y
.
Mo
d
el
6
is
s
elec
ted
f
o
r
d
e
p
lo
y
m
en
t
b
ased
o
n
th
e
ac
cu
r
ac
y
.
Per
f
o
r
m
an
ce
m
et
r
ics
u
s
ed
f
o
r
ev
alu
atio
n
o
f
ANN,
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
Sco
r
e,
ar
e
ca
lcu
lated
as in
(
8
)
-
(
1
0
)
.
Pr
e
c
ision
=
PT
PT
+
PF
(
8
)
R
e
c
a
l
l
=
PT
PT
+
NF
(
9
)
F1
−
Score
=
2
∗
PT
2
∗
PT
+
PF
+
NF
(
10
)
W
h
er
e
PT
is
tr
u
e
p
o
s
itiv
e
,
PF
is
f
alse p
o
s
itiv
e
,
an
d
NF is
f
alse n
eg
ativ
e
.
Fig
u
r
e
6
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
a
class
if
icatio
n
m
o
d
el
f
o
r
d
if
f
er
e
n
t
ty
p
es
o
f
f
a
u
lts
(
F1
to
F2
3
)
,
u
s
in
g
t
h
r
ee
k
e
y
ev
alu
ati
o
n
cr
iter
ia:
p
r
ec
is
io
n
,
r
ec
all
,
a
n
d
th
e
F1
s
co
r
e
u
s
in
g
m
o
d
el
6
.
T
h
e
m
ajo
r
ity
o
f
th
e
f
au
lt
ty
p
es
(
F2
to
F9
,
F1
2
t
o
F
2
0
,
a
n
d
F2
3
)
h
av
e
p
er
f
ec
t
s
co
r
es
(
1
.
0
0
)
in
p
r
ec
is
io
n
,
r
ec
all
,
a
n
d
F1
s
co
r
e.
Fau
lt
ty
p
es
F1
,
F1
0
,
F1
1
,
F2
1
,
an
d
F2
2
s
h
o
w
s
lig
h
tly
lo
we
r
s
co
r
e
s
in
o
n
e
o
r
m
o
r
e
m
etr
ics,
b
u
t
t
h
ese
s
co
r
es
ar
e
s
till
v
er
y
h
ig
h
(
all
ab
o
v
e
0
.
9
3
)
.
T
h
e
F1
s
co
r
e,
wh
ich
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
e
ca
ll
,
is
v
er
y
h
ig
h
f
o
r
all
f
au
lt
ty
p
es,
with
t
h
e
lo
we
s
t
b
ein
g
0
.
9
6
.
T
h
is
in
d
icate
s
a
well
-
b
alan
ce
d
m
o
d
el
th
at
i
s
ef
f
ec
tiv
e
i
n
b
o
th
id
en
tify
in
g
th
e
c
o
r
r
ec
t
f
au
lt
ty
p
es
(
p
r
ec
is
io
n
)
an
d
co
v
e
r
in
g
all
ac
tu
al
in
s
tan
ce
s
o
f
ea
ch
f
au
lt
ty
p
e
(
r
ec
all)
.
ANN
m
o
d
el
6
d
e
m
o
n
s
tr
ates
ex
ce
p
t
io
n
al
ef
f
ec
tiv
en
ess
in
f
au
lt
d
i
ag
n
o
s
is
with
a
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
8
.
6
%
an
d
v
alid
atio
n
ac
c
u
r
ac
y
o
f
9
9
.
7
%.
T
h
e
ab
ilit
y
to
ac
cu
r
ately
clas
s
if
y
a
wid
e
v
ar
iety
o
f
f
a
u
lt
ty
p
es
is
in
d
icativ
e
o
f
a
r
o
b
u
s
t
an
d
r
eliab
le
d
ia
g
n
o
s
tic
to
o
l.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
r
ep
o
r
ted
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
u
s
in
g
ANN
m
o
d
els,
in
clu
d
in
g
1
0
0
%
ac
cu
r
ac
y
with
in
s
tan
tan
eo
u
s
v
o
ltag
e
an
d
cu
r
r
e
n
t
as
f
ea
tu
r
es
[
5
5
]
,
a
n
d
a
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
MSE
)
o
f
0
.
0
1
1
1
8
9
wh
e
n
u
s
in
g
R
MS
v
alu
es
o
f
c
u
r
r
en
t
an
d
v
o
ltag
e
[
4
5
]
.
T
h
e
p
r
esen
t
wo
r
k
in
t
r
o
d
u
ce
s
a
n
o
v
el
s
elec
tio
n
o
f
f
ea
tu
r
e
v
a
r
iab
les
(
s
y
m
m
etr
ical
co
m
p
o
n
e
n
ts
o
f
v
o
ltag
e
an
d
cu
r
r
en
ts
)
,
ex
p
licitly
ad
d
r
ess
es
m
u
ltico
llin
ea
r
ity
,
an
d
r
ed
u
ce
s
f
ea
tu
r
e
r
ed
u
n
d
a
n
cy
.
Fu
r
t
h
er
m
o
r
e,
it
ex
p
an
d
s
th
e
s
co
p
e
b
y
i
n
co
r
p
o
r
atin
g
a
g
r
ea
te
r
n
u
m
b
er
o
f
f
au
lt c
l
ass
es (
1
2
class
es p
er
zo
n
e)
,
ac
h
iev
i
n
g
im
p
r
o
v
ed
ac
c
u
r
ac
y
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
d
en
s
e
ANN
m
o
d
els
P
a
r
a
me
t
e
r
M
o
d
e
l
1
M
o
d
e
l
2
M
o
d
e
l
3
M
o
d
e
l
4
M
o
d
e
l
5
M
o
d
e
l
6
N
o
o
f
f
e
a
t
u
r
e
i
n
p
u
t
s
11
11
11
11
11
11
N
o
o
f
h
i
d
d
e
n
l
a
y
e
r
s
-
2
2
2
2
2
2
2
N
o
o
f
n
e
u
r
o
n
s i
n
d
e
n
s
e
h
i
d
d
e
n
l
a
y
e
r
-
1
10
12
10
12
24
48
N
o
o
f
n
e
u
r
o
n
s i
n
d
e
n
s
e
h
i
d
d
e
n
l
a
y
e
r
-
2
10
12
20
24
48
48
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
h
i
d
d
e
n
l
a
y
e
r
R
e
l
u
R
e
l
u
R
e
l
u
R
e
l
u
R
e
l
u
R
e
l
u
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
o
u
t
p
u
t
l
a
y
e
r
S
o
f
t
ma
x
S
o
f
t
ma
x
S
o
f
t
ma
x
S
o
f
t
ma
x
S
o
f
t
ma
x
S
o
f
t
ma
x
N
o
o
f
o
u
t
p
u
t
s
23
23
23
23
23
23
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
1
0
.
0
1
0
.
0
1
0
.
0
1
0
.
0
1
0
.
0
1
O
p
t
i
mi
z
e
r
A
d
a
m
A
d
a
m
A
d
a
m
A
d
a
m
A
d
a
m
A
d
a
m
D
r
o
p
o
u
t
0
.
2
0
.
2
0
.
2
0
.
2
0
.
2
0
.
2
Ep
o
c
h
s
50
50
50
50
50
50
Tr
a
i
n
i
n
g
a
c
c
u
r
a
c
y
(
%)
68
76
8
3
.
7
87
9
7
.
7
9
8
.
6
V
a
l
i
d
a
t
i
o
n
a
c
c
u
r
a
c
y
(
%)
78
84
90
82
99
9
9
.
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
I
n
tellig
en
t fa
u
lt d
i
a
g
n
o
s
is
a
n
d
p
r
o
tectio
n
in
DG
-
co
n
n
ec
ted
s
ystems
…
(
Leksh
mi
R
.
C
h
a
n
d
r
a
n
)
1017
Fig
u
r
e
6
.
Per
f
o
r
m
an
c
e
m
etr
ic
o
f
m
o
d
el
6
I
n
th
is
s
tu
d
y
,
R
SF
C
L
is
p
lac
ed
in
th
e
s
y
s
tem
co
n
s
id
er
in
g
f
au
lt
r
ed
u
ctio
n
ca
p
a
b
ilit
y
,
g
r
id
v
o
ltag
e
q
u
ality
,
an
d
r
ed
u
ce
d
r
esis
tan
ce
to
lim
it
th
e
f
au
lt
cu
r
r
e
n
ts
.
T
h
e
s
en
s
itiv
ity
an
d
n
u
is
an
ce
tr
i
p
p
in
g
o
f
th
e
cir
c
u
it
b
r
ea
k
er
in
a
DG
-
co
n
n
ec
ted
s
y
s
tem
ar
e
n
o
r
m
all
y
ad
d
r
ess
ed
u
s
in
g
ad
ap
tiv
e
an
d
n
o
n
-
a
d
ap
tiv
e
p
r
o
tectio
n
co
o
r
d
in
atio
n
m
eth
o
d
s
[
5
6
]
,
[
5
7
]
.
Fau
lt
cu
r
r
en
t
lim
iter
s
(
FC
L
)
ca
n
b
e
p
lace
d
to
r
ed
u
ce
th
e
ex
tr
a
f
au
lt
c
u
r
r
en
t
co
n
tr
ib
u
ted
b
y
th
e
DG
an
d
m
ain
tain
th
e
p
r
eset
r
elay
s
ettin
g
.
Ad
ap
tiv
e
p
r
o
tectio
n
s
ch
em
es
with
o
u
t
FC
L
[
5
8
]
,
[
59
]
o
r
with
FC
L
[
6
0
]
-
[
6
3
]
ca
n
b
e
u
s
ed
to
im
p
r
o
v
e
th
e
s
en
s
itiv
ity
.
T
h
is
s
tu
d
y
also
in
tr
o
d
u
ce
s
a
n
o
n
-
ad
ap
tiv
e
p
r
o
tectio
n
ap
p
r
o
ac
h
to
r
ed
u
ce
t
h
e
n
u
is
an
ce
tr
ip
p
in
g
o
f
cir
c
u
it
b
r
ea
k
er
s
(
C
B
s
)
b
y
in
teg
r
atin
g
an
Ar
tific
ial
Neu
r
al
Netwo
r
k
-
b
ased
class
if
ier
d
ec
is
io
n
alo
n
g
with
th
e
co
n
v
en
ti
o
n
al
r
elay
lo
g
ic
f
o
r
cir
c
u
it b
r
ea
k
er
s
.
Fig
u
r
e
7
s
h
o
ws
th
e
in
teg
r
ate
d
s
y
s
tem
c
o
n
ce
p
t
to
r
ed
u
ce
th
e
n
u
is
an
ce
tr
ip
p
in
g
o
f
th
e
cir
cu
it
b
r
ea
k
er
.
W
h
en
a
f
au
lt
is
co
n
f
i
r
m
ed
,
th
e
ANN
s
ig
n
als
th
e
n
ea
r
est
C
B
to
is
o
late
th
e
f
au
lt.
T
h
is
r
esp
o
n
s
e
is
ca
r
ef
u
lly
co
o
r
d
i
n
ate
d
with
o
th
er
C
B
s
a
lo
n
g
th
e
lin
e,
m
ain
tain
in
g
a
co
o
r
d
in
atio
n
tim
e
in
ter
v
al
(
C
T
I
)
o
f
0
.
3
s
ec
o
n
d
s
to
en
s
u
r
e
th
at
t
h
e
n
e
ar
est b
r
ea
k
er
to
th
e
f
au
lt
tr
ip
s
f
ir
s
t,
lo
ca
lizin
g
th
e
f
au
lt
an
d
m
in
im
izin
g
its
im
p
ac
t
o
n
th
e
n
etwo
r
k
.
T
h
e
d
ec
is
io
n
to
tr
ip
a
C
B
is
b
ased
o
n
th
e
ANN'
s
co
n
f
ir
m
atio
n
,
e
n
h
an
cin
g
th
e
d
ec
is
io
n
'
s
ac
cu
r
ac
y
b
ey
o
n
d
tr
ad
itio
n
al
d
etec
tio
n
m
eth
o
d
s
,
wh
ich
r
ely
s
o
lely
o
n
p
r
ed
e
f
in
ed
s
ettin
g
s
.
T
h
e
tim
e
d
ial
(
T
D)
an
d
p
lu
g
s
ettin
g
(
PS
)
o
f
ea
c
h
r
elay
f
o
r
cir
cu
it
b
r
ea
k
er
s
u
s
in
g
th
e
s
tan
d
a
r
d
in
v
er
s
e
cu
r
v
e
an
d
C
T
r
atio
o
f
2
0
0
/5
A
f
o
r
s
y
s
tem
s
with
an
d
with
o
u
t
R
SF
C
L
ar
e
s
h
o
wn
in
T
ab
le
5
f
o
r
a
C
T
I
o
f
0
.
3
s
.
Fig
u
r
e
7
.
I
n
teg
r
ated
s
y
s
tem
ap
p
r
o
ac
h
t
o
r
ed
u
ce
cir
cu
it b
r
ea
k
er
n
u
is
an
ce
tr
ip
p
in
g
T
ab
le
5
.
R
elay
s
ettin
g
o
f
C
B
’
s
with
an
d
with
o
u
t
R
FS
C
L
R
e
l
a
y
W
i
t
h
o
u
t
R
S
F
C
L
W
i
t
h
R
S
F
C
L
TD
PS
TD
PS
R
C
B
2
0
.
3
1
2
3
1
.
7
6
0
.
3
0
1
0
1
.
8
7
R
C
B
4
2
.
6
6
3
2
6
.
1
9
2
.
5
6
7
1
5
.
7
3
R
C
B
1
5
.
0
3
1
6
5
.
6
5
4
.
8
5
0
8
5
.
2
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
0
9
-
1
0
2
2
1018
5.
CO
NCLU
SI
O
N
I
n
c
o
n
clu
s
io
n
,
th
is
s
tu
d
y
h
as
m
ad
e
s
ig
n
if
ica
n
t
s
tr
id
es
in
ad
v
an
cin
g
f
au
lt
d
iag
n
o
s
is
an
d
p
r
o
tectio
n
in
DG
-
co
n
n
ec
ted
elec
tr
ical
s
y
s
te
m
s
,
em
p
lo
y
in
g
a
co
m
b
in
atio
n
o
f
r
esis
tiv
e
s
u
p
er
co
n
d
u
ctin
g
f
au
lt c
u
r
r
en
t lim
iter
s
(
R
SF
C
L
)
an
d
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
(
ANN)
-
b
ased
f
au
lt
i
d
en
tific
atio
n
m
eth
o
d
s
.
T
h
e
v
ar
i
o
u
s
in
s
ig
h
ts
o
f
th
e
s
tu
d
y
ar
e
as
f
o
llo
ws
:
i)
s
tr
ateg
i
c
p
lace
m
en
t
o
f
R
SF
C
L
with
in
th
e
d
is
tr
ib
u
tio
n
n
etwo
r
k
ca
n
b
e
d
o
n
e
b
y
ca
r
ef
u
lly
co
n
s
id
er
in
g
f
ac
to
r
s
s
u
ch
as
f
au
lt
cu
r
r
e
n
t
m
ag
n
itu
d
e,
v
o
lta
g
e
q
u
ality
,
an
d
r
esis
tan
ce
v
a
lu
e,
to
r
ed
u
ce
th
e
m
ax
im
u
m
r
esis
tan
ce
v
alu
e
wh
ile
m
ain
tain
in
g
f
au
lt
cu
r
r
en
t
lim
itati
o
n
.
Po
s
itio
n
P1
-
P2
with
a
m
ax
im
u
m
r
esis
tan
ce
o
f
2
0
Ω
is
s
elec
ted
b
ased
o
n
th
is
tr
ad
e
o
f
f
.
P1
-
P2
s
h
o
ws
a
C
R
R
o
f
5
7
.
7
9
% f
o
r
Sy
m
m
etr
ical
f
au
lt
F1
an
d
8
2
.
1
6
%
f
o
r
s
y
m
m
etr
ical
f
au
lt
F2
.
ii)
T
h
e
ANN
-
b
ased
f
au
lt
d
iag
n
o
s
is
tech
n
iq
u
e
u
ti
lizin
g
s
y
m
m
etr
ical
co
m
p
o
n
en
ts
o
f
cu
r
r
en
t a
n
d
v
o
l
tag
e
as e
lectr
ical
f
ea
t
u
r
es h
as s
h
o
wn
r
em
ar
k
a
b
le
v
alid
ati
o
n
a
cc
u
r
ac
y
with
a
r
ate
o
f
9
9
.
7
%.
T
h
is
h
ig
h
lev
el
o
f
p
r
ec
is
io
n
is
p
ar
tly
attr
ib
u
ted
t
o
th
e
ca
r
ef
u
l
an
aly
s
is
o
f
f
ea
tu
r
e
v
a
r
iab
les,
p
ar
ticu
lar
ly
ad
d
r
ess
in
g
m
u
ltico
llin
ea
r
ity
.
B
y
id
en
tify
in
g
a
n
d
s
u
b
s
eq
u
e
n
t
ly
elim
in
atin
g
h
ig
h
ly
co
r
r
elate
d
v
ar
iab
les,
s
u
ch
as
'
v
2
n
'
d
u
e
to
its
s
u
b
s
tan
tial
co
r
r
elatio
n
o
f
0
.
8
1
with
an
o
th
e
r
f
ea
tu
r
e,
th
e
m
o
d
el'
s
r
o
b
u
s
tn
es
s
an
d
ef
f
ec
tiv
en
es
s
wer
e
s
ig
n
if
ican
tly
en
h
a
n
ce
d
.
i
ii)
T
h
e
d
ec
is
io
n
to
ac
tiv
ate
a
cir
cu
it
b
r
ea
k
er
is
co
n
f
ir
m
ed
b
y
th
e
ANN,
wh
ich
m
ea
n
s
it
o
n
ly
tr
ip
s
wh
e
n
th
e
A
NN
d
etec
ts
a
r
ea
l
f
au
lt.
T
h
is
is
m
o
r
e
ac
cu
r
ate
th
an
o
ld
er
m
eth
o
d
s
th
at
tr
ip
b
ased
o
n
s
im
p
le
p
r
eset
lim
its
.
iv
)
H
o
wev
er
,
th
e
c
u
r
r
e
n
t
s
tu
d
y
is
li
m
ited
to
in
co
r
p
o
r
atin
g
th
e
th
e
r
m
al
an
d
elec
tr
ical
p
r
o
p
er
ties
o
f
R
FS
C
L
an
d
th
e
t
r
an
s
ien
t
s
tab
ilit
y
o
f
th
e
s
y
s
tem
with
R
FS
C
L
p
lace
m
en
t.
T
h
e
ANN
is
tr
ain
ed
f
o
r
v
ar
io
u
s
f
au
lt
ty
p
es
with
an
d
w
ith
o
u
t
R
SF
C
L
an
d
DG.
I
n
th
e
f
u
tu
r
e,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
ca
n
b
e
e
x
ten
d
ed
to
co
n
s
id
er
v
ar
y
i
n
g
DG
p
e
n
etr
atio
n
lev
els,
r
en
ewa
b
le
in
ter
m
i
tten
cy
,
an
d
r
ea
l
-
tim
e
d
y
n
a
m
ics,
alo
n
g
with
h
y
b
r
id
AI
m
o
d
els
s
u
ch
as
C
NN
–
L
STM
f
o
r
im
p
r
o
v
e
d
tem
p
o
r
al
f
a
u
lt
d
etec
tio
n
.
Fu
r
t
h
er
m
o
r
e,
ad
a
p
tiv
e
an
d
s
elf
-
le
ar
n
in
g
p
r
o
tectio
n
s
ch
em
es
th
at
ev
o
l
v
e
with
c
h
an
g
i
n
g
n
etwo
r
k
t
o
p
o
lo
g
y
a
n
d
s
m
ar
t
g
r
id
ar
ch
itectu
r
es
r
em
ain
a
p
r
o
m
is
in
g
d
i
r
ec
tio
n
f
o
r
ad
v
an
cin
g
th
e
r
eliab
ilit
y
o
f
DG
-
co
n
n
ec
ted
s
y
s
tem
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
in
v
o
lv
e
d
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
L
ek
s
h
m
i R
.
C
h
an
d
r
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
lan
g
o
Kar
u
p
p
asam
y
✓
✓
✓
✓
✓
✓
✓
Ma
n
ju
la
G
.
Nair
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
in
f
l
u
en
ce
d
th
e
wo
r
k
r
e
p
o
r
ted
in
th
is
p
ap
e
r
.
T
h
e
au
th
o
r
s
d
ec
lar
e
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
i
n
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
i
n
g
au
th
o
r
,
[
LR
C
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
D
.
I
w
e
h
,
S
.
G
y
a
mf
i
,
E.
Ta
n
y
i
,
a
n
d
E.
Ef
f
a
h
-
D
o
n
y
i
n
a
,
“
D
i
st
r
i
b
u
t
e
d
g
e
n
e
r
a
t
i
o
n
a
n
d
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
i
n
t
e
g
r
a
t
i
o
n
i
n
t
o
t
h
e
g
r
i
d
:
p
r
e
r
e
q
u
i
si
t
e
s
,
p
u
s
h
f
a
c
t
o
r
s,
p
r
a
c
t
i
c
a
l
o
p
t
i
o
n
s,
i
ss
u
e
s
a
n
d
mer
i
t
s,
”
E
n
e
rg
i
e
s
,
v
o
l
.
1
4
,
n
o
.
1
7
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
4
1
7
5
3
7
5
.
[
2
]
M
.
S
i
n
g
h
,
“
P
r
o
t
e
c
t
i
o
n
c
o
o
r
d
i
n
a
t
i
o
n
i
n
d
i
s
t
r
i
b
u
t
i
o
n
s
y
s
t
e
ms
w
i
t
h
a
n
d
w
i
t
h
o
u
t
d
i
s
t
r
i
b
u
t
e
d
e
n
e
r
g
y
r
e
s
o
u
r
c
e
s
-
a
r
e
v
i
e
w
,
”
Pr
o
t
e
c
t
i
o
n
a
n
d
C
o
n
t
r
o
l
o
f
Mo
d
e
rn
P
o
w
e
r
S
y
st
e
m
s
,
v
o
l
.
2
,
n
o
.
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
1
6
0
1
-
0
1
7
-
0
0
6
1
-
1.
Evaluation Warning : The document was created with Spire.PDF for Python.