I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
wer
E
lect
ro
nics
a
nd
Driv
e
S
y
s
t
em
(
I
J
P
E
DS)
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
1
7
5
5
~
1
7
6
7
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
1
7
.
i
3
.
p
p
1
7
5
5
-
1
7
6
7
1755
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
Deep learni
ng
-
ba
sed intell
ig
ent
isla
nding
det
e
ction
for g
rid
-
co
nnected
photo
v
o
ltaic sy
stems us
i
ng
conv
o
lutiona
l
neura
l net
wo
rks
Do
nd
a
pa
t
i R
a
v
i K
is
ho
re
1
,
T
.
Vij
a
y
M
un
i
2
,
K
.
Venk
a
t
a
K
i
s
ho
re
3
,
V.
Su
re
s
h
1
,
S.
Sa
a
hithi
4
,
T
ha
nd
a
v
a
K
rish
na
Sa
i P
a
nd
ra
j
u
5
,
S.
N.
Cha
it
ra
6
,
B
.
L
o
g
esh
wa
ry
7
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
,
G
o
d
a
v
a
r
i
G
l
o
b
a
l
U
n
i
v
e
r
s
i
t
y
,
R
a
j
a
h
m
u
n
d
r
y
,
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
,
K
o
n
e
r
u
L
a
k
sh
m
a
i
a
h
E
d
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
V
a
d
d
e
sw
a
r
a
m,
I
n
d
i
a
3
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
,
D
r
.
R
V
R
N
R
I
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
D
e
e
m
e
d
t
o
b
e
U
n
i
v
e
r
si
t
y
,
V
i
j
a
y
a
w
a
d
a
R
u
r
a
l
,
I
n
d
i
a
4
S
c
h
o
o
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
s
En
g
i
n
e
e
r
i
n
g
,
R
EV
A
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
D
h
a
n
e
k
u
l
a
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
En
g
i
n
e
e
r
i
n
g
,
N
I
TTE
(
D
e
e
m
e
d
t
o
b
e
U
n
i
v
e
r
si
t
y
)
,
N
M
A
M
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
(
N
M
A
M
I
T)
,
N
i
t
t
e
,
I
n
d
i
a
7
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
A
g
u
r
c
h
a
n
d
M
a
n
m
u
l
l
Ja
i
n
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
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
Ma
y
8
,
2
0
2
6
R
ev
is
ed
Au
g
1
,
2
0
2
6
Acc
ep
ted
Au
g
2
4
,
2
0
2
6
Th
e
in
c
re
a
sin
g
in
teg
ra
ti
o
n
o
f
p
h
o
t
o
v
o
lt
a
ic
(P
V)
s
y
ste
m
s
in
to
sm
a
rt
g
rid
s
re
q
u
ires
fa
st
a
n
d
re
li
a
b
le
islan
d
i
n
g
d
e
tec
ti
o
n
to
m
a
in
tai
n
g
ri
d
sta
b
il
it
y
a
n
d
o
p
e
ra
ti
o
n
a
l
sa
fe
ty
.
Co
n
v
e
n
t
io
n
a
l
d
e
tec
ti
o
n
m
e
th
o
d
s
o
fte
n
fa
c
e
c
h
a
ll
e
n
g
e
s
su
c
h
a
s
d
e
lay
e
d
re
sp
o
n
se
,
re
d
u
c
e
d
a
c
c
u
ra
c
y
,
a
n
d
larg
e
n
o
n
-
d
e
tec
t
io
n
z
o
n
e
s
u
n
d
e
r
v
a
ry
i
n
g
o
p
e
ra
ti
n
g
c
o
n
d
it
io
n
s.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
in
telli
g
e
n
t
islan
d
in
g
d
e
tec
ti
o
n
m
e
th
o
d
fo
r
g
rid
-
c
o
n
n
e
c
ted
P
V
sy
ste
m
s
u
sin
g
a
d
v
a
n
c
e
d
a
rti
ficia
l
in
tel
li
g
e
n
c
e
a
n
d
d
e
e
p
lea
rn
in
g
tec
h
n
iq
u
e
s.
El
e
c
tri
c
a
l
p
a
ra
m
e
ters
in
c
lu
d
in
g
v
o
l
tag
e
,
c
u
rre
n
t,
fre
q
u
e
n
c
y
,
a
n
d
p
o
we
r
si
g
n
a
ls
a
re
a
n
a
ly
z
e
d
u
si
n
g
sig
n
a
l
p
r
o
c
e
ss
in
g
m
e
th
o
d
s
a
n
d
c
las
sified
th
ro
u
g
h
a
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
m
o
d
e
l
d
e
v
e
lo
p
e
d
in
M
ATLAB/S
imu
l
in
k
.
S
imu
lati
o
n
re
su
l
ts
d
e
m
o
n
stra
te
th
a
t
t
h
e
p
ro
p
o
se
d
AI
-
b
a
se
d
a
p
p
ro
a
c
h
a
c
h
iev
e
s
ra
p
id
a
n
d
a
c
c
u
ra
te
d
e
tec
ti
o
n
o
f
isla
n
d
i
n
g
e
v
e
n
ts
with
imp
r
o
v
e
d
se
n
siti
v
it
y
a
n
d
re
d
u
c
e
d
fa
lse
d
e
tec
ti
o
n
s
c
o
m
p
a
re
d
t
o
c
o
n
v
e
n
ti
o
n
a
l
tec
h
n
iq
u
e
s.
Th
e
p
ro
p
o
se
d
fra
m
e
wo
rk
e
n
h
a
n
c
e
s
th
e
re
li
a
b
il
it
y
,
sa
fe
ty
,
a
n
d
p
r
o
tec
ti
o
n
p
e
rfo
r
m
a
n
c
e
o
f
m
o
d
e
rn
p
h
o
to
v
o
l
taic
p
o
we
r
s
y
ste
m
s in
teg
ra
ted
wit
h
sm
a
rt
g
ri
d
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
NN
Dee
p
lear
n
in
g
Gr
id
s
af
ety
I
s
lan
d
in
g
d
etec
tio
n
Ma
ch
in
e
lear
n
in
g
Ph
o
to
v
o
ltaic
s
y
s
tem
s
R
en
ewa
b
le
en
er
g
y
i
n
teg
r
atio
n
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
:
T
.
Vijay
Mu
n
i
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
,
Ko
n
er
u
L
ak
s
h
m
aiah
E
d
u
ca
tio
n
Fo
u
n
d
atio
n
Gr
ee
n
Field
s
,
Vad
d
eswar
am
,
I
n
d
ia
E
m
ail:
v
ijay
m
u
n
i1
9
8
6
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ap
i
d
g
r
o
wth
o
f
r
en
ewa
b
le
en
er
g
y
i
n
teg
r
atio
n
,
p
a
r
ticu
lar
ly
p
h
o
to
v
o
ltaic
(
PV)
s
y
s
tem
s
,
h
as
s
ig
n
if
ican
tly
tr
an
s
f
o
r
m
ed
m
o
d
er
n
p
o
wer
n
etwo
r
k
s
an
d
s
m
ar
t
g
r
id
in
f
r
astru
ctu
r
e
s
.
Gr
id
-
co
n
n
ec
te
d
p
h
o
to
v
o
ltaic
s
y
s
tem
s
ar
e
in
cr
e
asin
g
ly
d
ep
lo
y
e
d
d
u
e
to
th
eir
en
v
ir
o
n
m
en
tal
b
en
ef
its
,
lo
w
o
p
er
atin
g
co
s
ts
,
an
d
co
n
tr
ib
u
tio
n
to
s
u
s
tain
ab
le
e
n
er
g
y
g
en
e
r
atio
n
.
Ho
wev
er
,
th
e
lar
g
e
-
s
ca
le
p
en
etr
atio
n
o
f
d
i
s
tr
ib
u
ted
g
e
n
er
atio
n
(
DG)
u
n
its
in
tr
o
d
u
ce
s
s
ev
er
al
o
p
er
atio
n
al
a
n
d
p
r
o
tectio
n
ch
allen
g
es,
am
o
n
g
wh
ic
h
is
lan
d
in
g
d
etec
tio
n
r
em
ain
s
o
n
e
o
f
th
e
m
o
s
t c
r
itical
is
s
u
es [
1
]
.
I
s
l
a
n
d
i
n
g
o
c
c
u
r
s
w
h
e
n
a
d
i
s
t
r
ib
u
t
e
d
e
n
e
r
g
y
r
e
s
o
u
r
c
e
c
o
n
t
i
n
u
e
s
s
u
p
p
l
y
i
n
g
p
o
w
e
r
t
o
a
l
o
c
a
l
l
o
a
d
e
v
e
n
a
f
t
e
r
d
i
s
c
o
n
n
e
c
ti
o
n
f
r
o
m
t
h
e
m
a
i
n
u
t
i
l
i
t
y
g
r
i
d
.
T
h
i
s
c
o
n
d
i
ti
o
n
m
a
y
l
e
a
d
t
o
s
e
v
e
r
e
s
a
f
e
t
y
h
a
z
ar
d
s
f
o
r
m
a
i
n
t
e
n
a
n
c
e
p
e
r
s
o
n
n
e
l
,
d
e
g
r
a
d
a
t
i
o
n
o
f
p
o
w
e
r
q
u
a
l
i
t
y
,
v
o
l
t
a
g
e
a
n
d
f
r
e
q
u
e
n
c
y
i
n
s
t
a
b
i
l
it
y
,
a
n
d
p
o
s
s
i
b
l
e
d
a
m
a
g
e
t
o
e
l
e
c
t
r
i
c
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
175
5
-
1
7
6
7
1756
eq
u
ip
m
en
t
[
2
]
.
T
h
er
ef
o
r
e,
in
t
er
n
atio
n
al
s
tan
d
a
r
d
s
s
u
ch
as
I
E
E
E
1
5
4
7
r
eq
u
ir
e
d
is
tr
ib
u
ted
g
en
er
atio
n
s
y
s
tem
s
to
d
etec
t isl
an
d
in
g
co
n
d
itio
n
s
r
ap
id
ly
an
d
d
is
co
n
n
ec
t f
r
o
m
th
e
g
r
id
with
in
a
s
p
ec
if
ie
d
tim
e
l
im
it [
3
]
.
Var
io
u
s
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
s
h
av
e
b
ee
n
d
ev
el
o
p
e
d
an
d
b
r
o
ad
l
y
class
if
ied
in
t
o
r
em
o
te
a
n
d
lo
ca
l
d
etec
tio
n
tech
n
iq
u
es.
R
em
o
te
tech
n
iq
u
es
u
tili
ze
co
m
m
u
n
icatio
n
-
b
ased
a
p
p
r
o
ac
h
es
s
u
ch
as
s
u
p
er
v
is
o
r
y
co
n
tr
o
l
an
d
d
ata
ac
q
u
is
itio
n
(
SC
ADA)
s
y
s
tem
s
an
d
tr
an
s
f
er
tr
ip
s
ch
em
es
to
id
e
n
tify
g
r
id
d
is
co
n
n
ec
tio
n
ev
en
ts
[
4
]
.
Alth
o
u
g
h
t
h
ese
m
eth
o
d
s
p
r
o
v
id
e
h
i
g
h
ac
c
u
r
ac
y
,
t
h
ey
r
eq
u
ir
e
ex
p
e
n
s
iv
e
co
m
m
u
n
icatio
n
in
f
r
astru
ctu
r
e
an
d
co
m
p
lex
im
p
lem
en
tatio
n
.
L
o
ca
l
tech
n
i
q
u
e
s
ar
e
f
u
r
th
er
ca
teg
o
r
ized
in
to
p
ass
iv
e,
ac
tiv
e,
an
d
h
y
b
r
id
m
et
h
o
d
s
[
5
]
.
Pas
s
iv
e
m
eth
o
d
s
m
o
n
ito
r
s
y
s
tem
p
ar
am
e
ter
s
s
u
ch
as v
o
ltag
e,
f
r
eq
u
en
c
y
,
p
h
ase
an
g
le,
an
d
h
ar
m
o
n
ic
d
is
to
r
tio
n
to
id
e
n
tify
ab
n
o
r
m
al
o
p
er
atin
g
c
o
n
d
it
io
n
s
[
6
]
-
[
1
0
]
.
T
h
ese
tech
n
iq
u
es
ar
e
s
im
p
le
an
d
ec
o
n
o
m
ical
b
u
t
s
u
f
f
er
f
r
o
m
l
ar
g
e
n
o
n
-
d
etec
tio
n
z
o
n
es
u
n
d
er
clo
s
ely
m
atch
ed
lo
ad
-
g
e
n
er
atio
n
c
o
n
d
itio
n
s
.
Activ
e
m
eth
o
d
s
in
te
n
tio
n
ally
in
ject
d
is
tu
r
b
a
n
ce
s
in
to
t
h
e
s
y
s
tem
an
d
a
n
aly
ze
t
h
e
r
es
u
ltin
g
r
esp
o
n
s
e
f
o
r
is
lan
d
in
g
id
en
tific
atio
n
[
1
1
]
.
Ho
wev
er
,
ac
tiv
e
tech
n
iq
u
es
m
ay
d
eg
r
ad
e
p
o
wer
q
u
ality
an
d
af
f
ec
t
s
y
s
tem
s
tab
ilit
y
.
Hy
b
r
id
ap
p
r
o
ac
h
es c
o
m
b
in
e
b
o
th
p
ass
iv
e
an
d
ac
tiv
e
m
eth
o
d
s
to
im
p
r
o
v
e
d
etec
tio
n
r
eliab
ilit
y
[
1
2
]
.
R
ec
en
tly
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
an
d
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
tec
h
n
iq
u
es
h
av
e
e
m
er
g
ed
as
p
r
o
m
is
in
g
s
o
lu
tio
n
s
f
o
r
p
o
we
r
s
y
s
tem
p
r
o
tectio
n
an
d
f
au
lt
d
iag
n
o
s
is
ap
p
licatio
n
s
.
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs),
d
ee
p
lear
n
in
g
(
DL
)
,
an
d
co
n
v
o
lu
tio
n
al
n
eu
r
a
l
n
etwo
r
k
s
(
C
NNs)
h
av
e
d
em
o
n
s
tr
ated
s
u
p
er
i
o
r
c
ap
ab
ilit
y
in
h
an
d
lin
g
n
o
n
lin
ea
r
an
d
c
o
m
p
lex
p
o
wer
s
y
s
tem
b
eh
av
io
r
s
[
1
3
]
.
AI
-
b
ased
is
lan
d
in
g
d
etec
tio
n
m
e
th
o
d
s
ca
n
ef
f
ec
tiv
ely
class
if
y
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
in
g
ev
en
ts
b
y
lear
n
in
g
p
atter
n
s
f
r
o
m
h
is
to
r
ical
an
d
s
im
u
lated
d
ata
u
n
d
er
d
i
f
f
er
e
n
t
o
p
er
atin
g
co
n
d
itio
n
s
[
1
4
]
.
I
n
p
a
r
ticu
lar
,
d
ee
p
lear
n
in
g
tech
n
iq
u
es
en
ab
le
au
to
m
ated
f
ea
t
u
r
e
e
x
tr
ac
tio
n
an
d
im
p
r
o
v
e
d
class
if
icatio
n
ac
c
u
r
ac
y
,
m
ak
in
g
th
e
m
s
u
itab
le
f
o
r
r
ea
l
-
tim
e
s
m
ar
t
g
r
i
d
ap
p
licatio
n
s
[
1
5
]
.
Desp
ite
s
ig
n
if
ican
t
ad
v
an
ce
s
in
ar
tific
ial
in
tellig
en
ce
-
b
ased
is
lan
d
in
g
d
etec
tio
n
,
s
ev
er
al
ch
allen
g
es
r
em
ain
u
n
r
eso
lv
e
d
.
Mo
s
t
ex
is
tin
g
ANN
-
b
ased
ap
p
r
o
ac
h
es
d
ep
en
d
h
ea
v
ily
o
n
m
an
u
ally
e
x
tr
ac
ted
f
ea
tu
r
es
an
d
ex
h
ib
it
r
ed
u
ce
d
p
er
f
o
r
m
a
n
c
e
u
n
d
er
v
ar
y
in
g
lo
ad
-
g
en
er
atio
n
m
is
m
atch
es
an
d
tr
an
s
ien
t
d
is
tu
r
b
an
ce
s
.
Fu
r
th
er
m
o
r
e
,
m
an
y
r
ep
o
r
ted
m
eth
o
d
s
p
r
o
v
i
d
e
lim
ited
d
is
cu
s
s
io
n
o
n
r
ed
u
cin
g
th
e
n
o
n
-
d
etec
tio
n
zo
n
e
wh
ile
m
ain
tain
in
g
f
ast
d
etec
tio
n
u
n
d
er
p
r
ac
tical
o
p
e
r
atin
g
c
o
n
d
itio
n
s
.
Alth
o
u
g
h
C
NN
-
b
ased
tech
n
iq
u
es
h
av
e
r
ec
en
tly
em
e
r
g
ed
,
c
o
m
p
r
e
h
e
n
s
iv
e
f
r
am
ew
o
r
k
s
i
n
teg
r
atin
g
au
to
m
atic
f
ea
tu
r
e
e
x
tr
ac
tio
n
with
r
ea
l
-
tim
e
p
h
o
to
v
o
ltaic
s
y
s
tem
p
r
o
tectio
n
r
em
ain
lim
ited
.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
f
o
r
a
r
o
b
u
s
t
d
ee
p
lear
n
in
g
-
b
ased
is
lan
d
in
g
d
etec
tio
n
f
r
a
m
ewo
r
k
ca
p
ab
le
o
f
p
r
o
v
id
in
g
h
i
g
h
d
etec
tio
n
ac
cu
r
ac
y
,
r
ed
u
ce
d
f
alse
d
etec
tio
n
s
,
an
d
r
ap
id
r
esp
o
n
s
e
u
n
d
e
r
d
iv
e
r
s
e
g
r
id
o
p
e
r
atin
g
s
ce
n
ar
io
s
.
T
h
e
m
ajo
r
co
n
tr
ib
u
tio
n
s
o
f
th
is
wo
r
k
ar
e
s
u
m
m
ar
ized
as
f
o
llo
ws:
i)
Dev
elo
p
m
en
t
o
f
a
C
NN
-
b
ased
in
tellig
en
t
is
lan
d
in
g
d
etec
tio
n
f
r
am
ewo
r
k
f
o
r
g
r
id
-
co
n
n
ec
te
d
p
h
o
to
v
o
ltaic
s
y
s
tem
s
;
ii)
Au
to
m
atic
ex
tr
ac
tio
n
o
f
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
m
ea
s
u
r
ed
elec
tr
ical
s
ig
n
als,
elim
in
atin
g
d
ep
en
d
en
ce
o
n
m
an
u
ally
en
g
in
ee
r
e
d
f
ea
tu
r
es
;
iii)
E
v
al
u
atio
n
u
n
d
er
m
u
ltip
le
o
p
e
r
atin
g
co
n
d
itio
n
s
,
in
clu
d
in
g
n
o
r
m
al
o
p
e
r
atio
n
,
l
o
ad
s
witch
in
g
,
g
r
i
d
d
is
tu
r
b
an
ce
s
,
an
d
is
lan
d
in
g
ev
en
ts
;
an
d
iv
)
Dev
elo
p
m
e
n
t
o
f
an
in
teg
r
ate
d
MA
T
L
AB
/Si
m
u
lin
k
–
C
NN
f
r
am
ewo
r
k
s
u
itab
le
f
o
r
in
tellig
en
t p
r
o
tectio
n
o
f
m
o
d
er
n
s
m
ar
t g
r
id
s
.
2.
SYST
E
M
DE
SCRI
P
T
I
O
N
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
d
e
s
ig
n
ed
f
o
r
in
tellig
en
t
is
lan
d
in
g
d
etec
tio
n
in
a
g
r
id
-
co
n
n
ec
ted
PV
p
o
wer
s
y
s
tem
u
s
in
g
ad
v
an
ce
d
ar
tific
ial
in
tellig
en
ce
tech
n
iq
u
es.
T
h
e
s
y
s
tem
in
teg
r
ates
a
p
h
o
to
v
o
ltaic
ar
r
ay
,
p
o
wer
elec
tr
o
n
ic
co
n
v
er
ter
s
,
g
r
id
in
ter
f
ac
e
co
m
p
o
n
e
n
ts
,
s
en
s
in
g
u
n
its
,
s
ig
n
al
p
r
o
ce
s
s
in
g
m
o
d
u
les,
an
d
a
d
ee
p
lear
n
in
g
-
b
ased
is
lan
d
in
g
d
ete
ctio
n
u
n
it
[
1
6
]
.
T
h
e
o
v
er
all
o
b
jectiv
e
o
f
th
e
s
y
s
tem
is
to
c
o
n
tin
u
o
u
s
ly
m
o
n
ito
r
elec
tr
ical
p
ar
am
eter
s
an
d
ac
c
u
r
ately
id
en
tify
is
lan
d
i
n
g
co
n
d
i
tio
n
s
u
n
d
er
d
if
f
er
e
n
t o
p
e
r
atin
g
s
ce
n
ar
io
s
[
1
7
]
.
T
h
e
p
h
o
to
v
o
ltaic
ar
r
ay
co
n
v
er
ts
s
o
lar
en
er
g
y
in
to
elec
tr
ical
en
er
g
y
an
d
s
u
p
p
lies
p
o
wer
to
th
e
u
tili
ty
g
r
id
t
h
r
o
u
g
h
a
DC
–
DC
b
o
o
s
t
co
n
v
er
ter
an
d
a
v
o
ltag
e
s
o
u
r
ce
co
n
v
er
ter
(
VSC
)
[
1
8
]
.
T
h
e
b
o
o
s
t
co
n
v
er
ter
is
em
p
lo
y
ed
t
o
r
eg
u
late
a
n
d
m
ai
n
tain
th
e
r
eq
u
i
r
ed
DC
-
lin
k
v
o
ltag
e,
wh
ile
th
e
m
ax
im
u
m
p
o
wer
p
o
in
t
tr
ac
k
in
g
(
MPPT)
co
n
tr
o
ller
en
s
u
r
es
m
ax
im
u
m
p
o
wer
ex
tr
ac
ti
o
n
f
r
o
m
th
e
PV
ar
r
ay
u
n
d
er
v
ar
y
in
g
ir
r
ad
ia
n
ce
co
n
d
itio
n
s
[
1
9
]
.
T
h
e
g
en
er
ate
d
DC
p
o
we
r
is
c
o
n
v
e
r
ted
i
n
to
AC
p
o
wer
th
r
o
u
g
h
th
e
in
v
er
t
er
an
d
in
jecte
d
in
to
th
e
g
r
id
v
ia
a
co
u
p
lin
g
tr
a
n
s
f
o
r
m
er
at
th
e
p
o
in
t o
f
co
m
m
o
n
c
o
u
p
lin
g
(
PC
C
)
.
T
h
e
p
r
o
p
o
s
ed
is
lan
d
in
g
d
etec
tio
n
f
r
am
ewo
r
k
co
n
tin
u
o
u
s
l
y
m
ea
s
u
r
es
s
y
s
tem
p
ar
am
eter
s
s
u
ch
as
v
o
ltag
e,
cu
r
r
en
t,
f
r
eq
u
en
cy
,
a
n
d
ac
tiv
e
p
o
wer
at
th
e
PC
C
[
2
0
]
.
T
h
ese
elec
tr
ical
s
ig
n
als
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
s
ig
n
al
co
n
d
itio
n
in
g
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es
b
ef
o
r
e
b
ein
g
s
u
p
p
lied
to
t
h
e
ar
tific
ial
in
tellig
en
ce
(
AI
)
m
o
d
u
le
[
2
1
]
-
[
2
3
]
.
A
C
NN
-
b
ased
class
if
ier
i
s
em
p
lo
y
ed
to
an
aly
ze
th
e
ex
tr
ac
ted
f
ea
tu
r
es
an
d
d
is
tin
g
u
is
h
is
lan
d
in
g
ev
en
ts
f
r
o
m
n
o
r
m
al
o
p
er
atin
g
d
is
tu
r
b
an
ce
s
an
d
lo
a
d
v
ar
iatio
n
s
.
Du
r
in
g
n
o
r
m
al
g
r
i
d
-
co
n
n
ec
te
d
o
p
e
r
atio
n
,
th
e
PV
s
y
s
tem
o
p
er
ates
s
y
n
ch
r
o
n
o
u
s
ly
with
th
e
u
tili
ty
g
r
id
.
W
h
en
an
is
lan
d
in
g
ev
e
n
t
o
cc
u
r
s
d
u
e
to
g
r
id
d
is
co
n
n
e
ctio
n
,
s
ig
n
if
ican
t
d
ev
iatio
n
s
a
p
p
ea
r
in
elec
tr
ical
p
ar
am
eter
s
s
u
ch
as
f
r
eq
u
en
cy
an
d
v
o
ltag
e
m
ag
n
itu
d
e.
T
h
e
AI
-
b
ased
d
etec
tio
n
u
n
it
r
ap
i
d
ly
id
en
tifie
s
th
ese
ab
n
o
r
m
al
p
atter
n
s
a
n
d
g
en
er
a
tes
a
tr
ip
s
ig
n
al
to
d
is
co
n
n
ec
t
th
e
PV
s
y
s
tem
f
r
o
m
th
e
is
o
lated
g
r
id
s
ec
tio
n
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Dee
p
lea
r
n
in
g
-
b
a
s
ed
in
tellig
e
n
t isl
a
n
d
in
g
d
etec
tio
n
fo
r
g
r
id
-
co
n
n
ec
ted
…
(
Do
n
d
a
p
a
ti R
a
v
i Ki
s
h
o
r
e
)
1757
th
er
eb
y
en
s
u
r
in
g
s
y
s
tem
p
r
o
te
ctio
n
an
d
o
p
er
atio
n
al
s
af
ety
[
2
4
]
.
T
h
e
co
m
p
lete
s
y
s
tem
m
o
d
el
is
d
ev
elo
p
ed
an
d
s
im
u
lated
in
MA
T
L
AB
/Si
m
u
lin
k
u
n
d
e
r
v
ar
io
u
s
o
p
er
atin
g
co
n
d
itio
n
s
in
clu
d
i
n
g
lo
ad
s
wi
tch
in
g
,
g
r
i
d
f
au
lts
,
an
d
is
lan
d
in
g
s
ce
n
ar
i
o
s
.
T
h
e
p
r
o
p
o
s
ed
AI
-
d
r
iv
e
n
d
etec
tio
n
m
eth
o
d
p
r
o
v
i
d
es im
p
r
o
v
e
d
d
et
ec
tio
n
s
p
ee
d
,
h
i
g
h
e
r
class
if
icatio
n
ac
cu
r
ac
y
,
a
n
d
e
n
h
an
ce
d
r
eliab
ilit
y
c
o
m
p
ar
e
d
with
co
n
v
en
tio
n
al
p
ass
iv
e
a
n
d
ac
tiv
e
is
lan
d
in
g
d
etec
tio
n
tech
n
iq
u
es [
2
5
]
.
2
.
1
.
B
lo
c
k
dia
g
ra
m
des
cr
iptio
n
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
AI
-
b
ased
is
lan
d
in
g
d
ete
ctio
n
s
y
s
tem
f
o
r
a
g
r
id
-
co
n
n
ec
ted
PV
n
etwo
r
k
.
T
h
e
s
y
s
tem
co
n
s
is
ts
o
f
a
s
o
lar
PV
ar
r
ay
,
DC
–
D
C
b
o
o
s
t
co
n
v
er
ter
,
MPPT
co
n
tr
o
ll
er
,
VSC
,
co
u
p
lin
g
tr
an
s
f
o
r
m
er
,
m
ea
s
u
r
em
en
t
u
n
i
t,
s
ig
n
al
p
r
o
ce
s
s
in
g
m
o
d
u
le,
C
NN
-
b
ased
class
if
ier
,
an
d
p
r
o
tectio
n
r
elay
u
n
it.
I
n
itially
,
th
e
So
lar
PV
ar
r
ay
co
n
v
er
ts
s
o
lar
e
n
er
g
y
in
to
D
C
elec
tr
ical
p
o
wer
.
T
h
e
g
e
n
e
r
ated
DC
p
o
wer
is
s
u
p
p
lied
to
th
e
DC
–
DC
b
o
o
s
t
co
n
v
er
ter
,
wh
ich
r
eg
u
lates
th
e
o
u
t
p
u
t
v
o
ltag
e
an
d
m
ain
tain
s
a
s
tab
le
DC
-
lin
k
v
o
ltag
e.
T
h
e
MPPT
co
n
tr
o
ller
co
n
tin
u
o
u
s
ly
tr
ac
k
s
th
e
m
ax
i
m
u
m
o
p
er
atin
g
p
o
in
t o
f
th
e
P
V
ar
r
ay
to
m
ax
im
ize
en
er
g
y
e
x
tr
ac
tio
n
u
n
d
e
r
v
ar
y
i
n
g
ir
r
a
d
ian
ce
co
n
d
itio
n
s
.
T
h
e
r
eg
u
lated
d
ir
ec
t
cu
r
r
en
t
(
DC
)
p
o
wer
is
co
n
v
er
ted
i
n
to
alter
n
atin
g
cu
r
r
en
t
(
AC
)
p
o
we
r
u
s
in
g
th
e
VSC
.
T
h
e
in
v
er
ter
o
u
tp
u
t
is
c
o
n
n
ec
ted
to
th
e
u
tili
ty
g
r
id
an
d
lo
ca
l
lo
ad
th
r
o
u
g
h
a
co
u
p
lin
g
tr
an
s
f
o
r
m
er
at
th
e
PC
C
.
Du
r
in
g
n
o
r
m
al
o
p
er
ati
o
n
,
t
h
e
PV
s
y
s
tem
o
p
er
ates
s
y
n
ch
r
o
n
o
u
s
ly
with
th
e
u
tili
ty
g
r
id
a
n
d
s
u
p
p
lies
p
o
wer
to
b
o
th
t
h
e
g
r
i
d
an
d
co
n
n
ec
ted
lo
ad
s
.
T
h
e
m
ea
s
u
r
em
en
t
u
n
it
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
s
im
p
o
r
tan
t
elec
tr
ical
p
ar
am
eter
s
s
u
ch
as
v
o
ltag
e
(
V)
,
c
u
r
r
en
t
(
I
)
,
f
r
eq
u
en
cy
(
f
)
,
an
d
ac
tiv
e
p
o
wer
(
P)
at
th
e
PC
C
.
T
h
ese
m
ea
s
u
r
ed
s
ig
n
als
ar
e
p
ass
ed
to
th
e
s
ig
n
al
p
r
o
ce
s
s
in
g
a
n
d
f
ea
tu
r
e
ex
tr
ac
tio
n
m
o
d
u
l
e,
wh
er
e
im
p
o
r
tan
t
ch
ar
ac
ter
is
tics
r
elate
d
to
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
in
g
ev
en
ts
ar
e
ex
tr
ac
ted
.
T
h
e
ex
tr
ac
ted
f
ea
tu
r
es
ar
e
th
en
f
ed
in
to
th
e
C
NN
-
b
ased
AI
is
lan
d
in
g
d
etec
tio
n
s
y
s
tem
.
T
h
e
C
NN
class
if
ier
i
s
tr
ain
ed
u
s
in
g
d
if
f
er
en
t
o
p
er
atin
g
co
n
d
itio
n
s
in
clu
d
in
g
n
o
r
m
al
o
p
e
r
atio
n
,
l
o
ad
s
witch
in
g
,
g
r
id
d
is
tu
r
b
an
ce
s
,
an
d
is
lan
d
i
n
g
s
c
en
ar
io
s
.
W
h
en
ab
n
o
r
m
al
co
n
d
itio
n
s
co
r
r
esp
o
n
d
in
g
to
is
lan
d
in
g
ar
e
i
d
en
tifie
d
,
th
e
AI
class
if
ier
g
e
n
er
ates
a
d
ec
is
io
n
s
ig
n
al.
Fin
ally
,
th
e
p
r
o
tectio
n
r
elay
an
d
tr
ip
s
ig
n
al
g
en
er
ato
r
d
is
co
n
n
ec
t
th
e
PV
s
y
s
tem
f
r
o
m
th
e
u
tili
ty
g
r
id
to
e
n
s
u
r
e
s
af
ety
,
p
r
ev
en
t e
q
u
ip
m
en
t d
am
ag
e,
a
n
d
m
ai
n
tain
g
r
id
r
eliab
ilit
y
.
T
h
e
p
r
o
p
o
s
ed
AI
-
b
ased
s
y
s
tem
p
r
o
v
id
es
f
ast,
ac
cu
r
ate,
an
d
r
eliab
le
is
lan
d
in
g
d
etec
t
io
n
co
m
p
ar
e
d
with
co
n
v
en
tio
n
al
p
ass
iv
e
an
d
ac
tiv
e
m
eth
o
d
s
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
2
.
2
.
P
r
o
blem
s
t
a
t
e
m
ent
I
s
lan
d
in
g
o
cc
u
r
s
wh
en
a
g
r
id
-
co
n
n
ec
ted
p
h
o
t
o
v
o
ltaic
s
y
s
tem
co
n
tin
u
es
s
u
p
p
ly
i
n
g
p
o
wer
to
lo
ca
l
l
o
a
d
s
e
v
e
n
a
f
t
e
r
d
is
c
o
n
n
e
c
ti
o
n
f
r
o
m
t
h
e
m
a
i
n
u
t
i
l
it
y
g
r
i
d
.
T
h
i
s
c
o
n
d
i
t
i
o
n
c
r
ea
t
es
s
e
r
i
o
u
s
s
a
f
e
t
y
h
a
z
a
r
d
s
f
o
r
m
a
i
n
t
e
n
a
n
c
e
p
e
r
s
o
n
n
e
l
a
n
d
m
ay
c
a
u
s
e
i
n
s
ta
b
i
l
it
y
i
n
v
o
l
t
a
g
e
an
d
f
r
e
q
u
e
n
c
y
,
e
q
u
i
p
m
e
n
t
d
a
m
a
g
e
,
a
n
d
d
e
g
r
a
d
a
t
i
o
n
o
f
p
o
w
e
r
q
u
a
l
i
t
y
.
C
o
n
v
e
n
t
i
o
n
al
i
s
la
n
d
i
n
g
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
,
i
n
c
l
u
d
i
n
g
p
a
s
s
i
v
e
,
ac
t
i
v
e
,
a
n
d
h
y
b
r
i
d
t
e
c
h
n
i
q
u
e
s
,
o
f
ten
s
u
f
f
er
f
r
o
m
lim
itatio
n
s
s
u
ch
as
lar
g
e
n
o
n
-
d
etec
tio
n
z
o
n
es,
s
lo
w
d
etec
tio
n
s
p
ee
d
,
f
alse
tr
ip
p
in
g
,
an
d
r
ed
u
ce
d
p
e
r
f
o
r
m
an
ce
u
n
d
er
v
ar
y
in
g
o
p
er
atin
g
co
n
d
itio
n
s
.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
f
o
r
an
in
tellig
en
t,
f
ast,
ac
cu
r
ate,
an
d
r
o
b
u
s
t isl
an
d
in
g
d
etec
tio
n
tech
n
iq
u
e
s
u
itab
le
f
o
r
m
o
d
e
r
n
s
m
ar
t g
r
id
-
co
n
n
ec
te
d
PV sy
s
tem
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
175
5
-
1
7
6
7
1758
2
.
3
.
O
bje
c
t
iv
e
o
f
t
he
pro
po
s
ed
s
y
s
t
em
T
h
e
m
ain
o
b
jectiv
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
to
d
ev
elo
p
a
n
in
tellig
en
t
AI
-
b
ased
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
f
o
r
g
r
id
-
c
o
n
n
ec
ted
PV
s
y
s
tem
s
.
T
h
e
s
y
s
tem
aim
s
to
ac
cu
r
ately
d
etec
t
is
lan
d
in
g
co
n
d
itio
n
s
u
s
in
g
elec
tr
ical
p
ar
am
eter
s
s
u
ch
as
v
o
ltag
e,
cu
r
r
en
t,
f
r
eq
u
en
cy
,
a
n
d
ac
tiv
e
p
o
wer
m
ea
s
u
r
e
d
at
th
e
PC
C
.
An
o
th
er
o
b
j
e
c
t
i
v
e
is
t
o
i
m
p
l
e
m
e
n
t
a
C
N
N
-
b
a
s
e
d
c
la
s
s
i
f
ie
r
c
a
p
a
b
l
e
o
f
d
i
s
t
i
n
g
u
is
h
i
n
g
i
s
la
n
d
i
n
g
a
n
d
n
o
n
-
i
s
l
a
n
d
i
n
g
e
v
e
n
ts
u
n
d
e
r
d
i
f
f
e
r
e
n
t
o
p
e
r
a
t
i
n
g
c
o
n
d
i
t
i
o
n
s
.
T
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
a
l
s
o
f
o
c
u
s
e
s
o
n
r
e
d
u
c
i
n
g
t
h
e
n
o
n
-
d
e
t
e
c
t
i
o
n
z
o
n
e
(
N
D
Z
)
,
i
m
p
r
o
v
i
n
g
d
e
t
e
c
ti
o
n
s
p
e
e
d
,
m
i
n
i
m
i
z
i
n
g
f
a
ls
e
t
r
i
p
p
i
n
g
,
a
n
d
e
n
h
a
n
c
i
n
g
o
v
e
r
a
l
l
g
r
i
d
s
a
f
et
y
a
n
d
r
e
l
i
a
b
i
li
t
y
.
2
.
4
.
K
ey
f
e
a
t
ures o
f
t
he
pro
po
s
ed
s
y
s
t
em
I
s
lan
d
in
g
o
cc
u
r
s
wh
en
a
g
r
id
-
co
n
n
ec
ted
p
h
o
t
o
v
o
ltaic
s
y
s
tem
co
n
tin
u
es
s
u
p
p
ly
i
n
g
p
o
wer
to
lo
ca
l
l
o
a
d
s
e
v
e
n
a
f
t
e
r
d
is
c
o
n
n
e
c
ti
o
n
f
r
o
m
t
h
e
m
a
i
n
u
t
i
l
it
y
g
r
i
d
.
T
h
i
s
c
o
n
d
i
t
i
o
n
c
r
ea
t
es
s
e
r
i
o
u
s
s
a
f
e
t
y
h
a
z
a
r
d
s
f
o
r
m
a
i
n
t
e
n
a
n
c
e
p
e
r
s
o
n
n
e
l
a
n
d
m
ay
c
a
u
s
e
i
n
s
ta
b
i
l
it
y
i
n
v
o
l
t
a
g
e
an
d
f
r
e
q
u
e
n
c
y
,
e
q
u
i
p
m
e
n
t
d
a
m
a
g
e
,
a
n
d
d
e
g
r
a
d
a
t
i
o
n
o
f
p
o
w
e
r
q
u
a
l
i
t
y
.
C
o
n
v
e
n
t
i
o
n
al
i
s
la
n
d
i
n
g
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
,
i
n
c
l
u
d
i
n
g
p
a
s
s
i
v
e
,
ac
t
i
v
e
,
a
n
d
h
y
b
r
i
d
t
e
c
h
n
i
q
u
e
s
,
o
f
ten
s
u
f
f
er
f
r
o
m
lim
itatio
n
s
s
u
ch
as
lar
g
e
n
o
n
-
d
etec
tio
n
z
o
n
es,
s
lo
w
d
etec
tio
n
s
p
ee
d
,
f
alse
tr
ip
p
in
g
,
an
d
r
ed
u
ce
d
p
e
r
f
o
r
m
an
ce
u
n
d
er
v
ar
y
in
g
o
p
er
atin
g
co
n
d
itio
n
s
.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
f
o
r
an
in
tellig
en
t,
f
ast,
ac
cu
r
ate,
an
d
r
o
b
u
s
t isl
an
d
in
g
d
etec
tio
n
tech
n
iq
u
e
s
u
itab
le
f
o
r
m
o
d
e
r
n
s
m
ar
t g
r
id
-
co
n
n
ec
te
d
PV sy
s
tem
s
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
f
o
r
en
h
an
ce
d
is
lan
d
in
g
d
etec
t
io
n
in
PV
s
y
s
tem
s
is
d
ev
elo
p
ed
u
s
in
g
ad
v
an
ce
d
AI
tech
n
iq
u
es
in
t
eg
r
ated
with
s
ig
n
al
p
r
o
ce
s
s
in
g
an
d
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
m
ec
h
an
is
m
s
.
T
h
e
m
eth
o
d
o
l
o
g
y
aim
s
to
im
p
r
o
v
e
th
e
s
p
ee
d
,
r
eliab
ilit
y
,
an
d
ac
cu
r
ac
y
o
f
is
lan
d
in
g
d
etec
tio
n
u
n
d
er
d
if
f
er
e
n
t
o
p
er
atin
g
co
n
d
itio
n
s
in
a
g
r
i
d
-
co
n
n
ec
ted
r
en
ewa
b
le
en
er
g
y
e
n
v
ir
o
n
m
en
t.
T
h
e
c
o
m
p
lete
m
e
th
o
d
o
lo
g
y
c
o
n
s
is
ts
o
f
s
y
s
tem
m
o
d
elin
g
,
s
ig
n
al
ac
q
u
is
itio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
AI
-
b
ased
class
if
icatio
n
,
s
im
u
latio
n
an
aly
s
is
,
an
d
p
r
o
tectio
n
c
o
n
tr
o
l
im
p
lem
en
tatio
n
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
is
v
alid
ated
u
s
in
g
MA
T
L
AB
/S
im
u
lin
k
u
n
d
e
r
v
ar
io
u
s
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
i
n
g
o
p
e
r
atin
g
c
o
n
d
itio
n
s
.
3
.
1
.
P
r
o
po
s
ed
s
y
s
t
em
a
rc
hit
ec
t
ure
T
h
e
p
r
o
p
o
s
ed
AI
-
b
ased
is
lan
d
in
g
d
etec
tio
n
s
y
s
tem
co
n
s
is
ts
o
f
a
g
r
id
-
co
n
n
ec
ted
p
h
o
to
v
o
ltaic
ar
r
ay
in
teg
r
ated
with
a
u
tili
ty
g
r
id
th
r
o
u
g
h
p
o
wer
elec
tr
o
n
ic
co
n
v
er
ter
s
,
tr
an
s
f
o
r
m
er
s
,
f
ilter
s
,
an
d
in
tellig
en
t
p
r
o
tectio
n
d
ev
ices.
T
h
e
o
v
er
a
ll
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
e
d
s
y
s
tem
is
s
h
o
wn
i
n
Fig
u
r
e
2
.
T
h
e
PV
s
y
s
tem
co
n
tin
u
o
u
s
ly
ex
ch
a
n
g
es
p
o
we
r
with
th
e
u
tili
ty
g
r
id
u
n
d
e
r
n
o
r
m
al
o
p
e
r
atin
g
co
n
d
itio
n
s
.
Ho
wev
er
,
wh
en
t
h
e
u
tili
ty
g
r
id
is
d
is
co
n
n
ec
ted
d
u
e
to
f
a
u
lts
,
m
ain
ten
an
ce
,
o
r
d
is
tu
r
b
a
n
ce
s
,
th
e
PV
s
y
s
tem
m
ay
co
n
tin
u
e
s
u
p
p
ly
in
g
l
o
ca
l
lo
ad
s
,
cr
ea
ti
n
g
an
is
lan
d
in
g
co
n
d
itio
n
.
S
u
ch
co
n
d
itio
n
s
m
ay
r
esu
lt
in
v
o
ltag
e
in
s
tab
ilit
y
,
f
r
eq
u
e
n
cy
f
lu
ct
u
atio
n
s
,
s
af
ety
h
az
ar
d
s
,
an
d
eq
u
i
p
m
en
t d
a
m
a
g
e
if
n
o
t
d
etec
ted
r
a
p
id
ly
[
1
]
-
[
3
]
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
in
teg
r
ates
an
AI
-
b
ased
is
lan
d
in
g
d
etec
tio
n
s
y
s
tem
(
I
DS)
at
th
e
PC
C
,
wh
er
e
s
y
s
tem
p
ar
am
eter
s
s
u
ch
as
v
o
ltag
e,
cu
r
r
en
t,
f
r
eq
u
en
cy
,
ac
tiv
e
p
o
wer
,
an
d
r
ea
ctiv
e
p
o
wer
ar
e
c
o
n
t
i
n
u
o
u
s
l
y
m
o
n
i
t
o
r
e
d
.
T
h
e
s
e
p
a
r
a
m
e
t
e
r
s
a
r
e
t
r
a
n
s
m
i
t
t
e
d
t
o
t
h
e
i
n
t
e
ll
i
g
e
n
t
p
r
o
c
es
s
i
n
g
u
n
i
t
f
o
r
r
e
a
l
-
t
i
m
e
a
n
a
l
y
s
is
a
n
d
cl
a
s
s
i
f
i
c
a
t
i
o
n
.
U
n
l
i
k
e
c
o
n
v
e
n
t
i
o
n
a
l
p
a
s
s
i
v
e
a
n
d
a
c
t
i
v
e
d
et
e
c
t
i
o
n
m
e
t
h
o
d
s
,
t
h
e
p
r
o
p
o
s
e
d
A
I
-
d
r
i
v
e
n
f
r
am
ewo
r
k
ca
n
r
ec
o
g
n
ize
n
o
n
l
in
ea
r
v
ar
iatio
n
s
an
d
h
id
d
en
p
a
tter
n
s
ass
o
ciate
d
with
is
lan
d
in
g
co
n
d
itio
n
s
.
As
illu
s
tr
ated
in
Fig
u
r
e
2
,
th
e
in
tellig
en
t
co
n
tr
o
ller
r
ec
eiv
es
elec
tr
ical
m
ea
s
u
r
em
en
ts
f
r
o
m
th
e
PV
s
y
s
tem
an
d
u
tili
ty
g
r
id
.
T
h
ese
m
ea
s
u
r
em
en
ts
ar
e
p
r
ep
r
o
ce
s
s
ed
an
d
s
u
p
p
lied
to
th
e
d
ee
p
lear
n
in
g
class
if
ier
,
wh
ich
id
en
tifie
s
wh
eth
er
th
e
o
p
er
atin
g
c
o
n
d
itio
n
c
o
r
r
esp
o
n
d
s
to
is
lan
d
in
g
o
r
n
o
n
-
is
lan
d
i
n
g
o
p
e
r
atio
n
.
On
ce
is
lan
d
in
g
is
d
etec
ted
,
th
e
p
r
o
te
ctio
n
m
o
d
u
le
g
en
e
r
ates tr
ip
s
ig
n
als to
is
o
late
th
e
PV sy
s
tem
f
r
o
m
th
e
g
r
id
.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
3
.
2
.
Sig
na
l
a
cquis
it
io
n a
nd
m
o
nito
ring
pro
ce
s
s
T
h
e
s
ig
n
al
ac
q
u
is
itio
n
s
tag
e
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
co
m
p
o
n
e
n
ts
o
f
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
b
ec
au
s
e
th
e
p
er
f
o
r
m
an
c
e
o
f
th
e
AI
class
if
ier
d
ep
en
d
s
o
n
th
e
q
u
ality
o
f
th
e
e
x
tr
ac
ted
s
ig
n
al
s
.
I
n
th
is
s
tag
e,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Dee
p
lea
r
n
in
g
-
b
a
s
ed
in
tellig
e
n
t isl
a
n
d
in
g
d
etec
tio
n
fo
r
g
r
id
-
co
n
n
ec
ted
…
(
Do
n
d
a
p
a
ti R
a
v
i Ki
s
h
o
r
e
)
1759
elec
tr
ical
p
ar
am
eter
s
f
r
o
m
th
e
PV
s
y
s
tem
an
d
u
tili
ty
g
r
i
d
ar
e
c
o
n
tin
u
o
u
s
ly
m
o
n
ito
r
e
d
u
s
in
g
m
ea
s
u
r
em
e
n
t
s
en
s
o
r
s
in
s
talled
at
th
e
PC
C
.
T
h
e
m
ea
s
u
r
ed
s
ig
n
als
in
clu
d
e
:
th
r
ee
-
p
h
ase
v
o
ltag
e,
t
h
r
ee
-
p
h
ase
cu
r
r
en
t,
f
r
eq
u
e
n
cy
d
e
v
iatio
n
,
ac
tiv
e
p
o
wer
,
r
ea
ctiv
e
p
o
wer
,
v
o
ltag
e
p
h
ase
an
g
le,
an
d
h
ar
m
o
n
ic
d
is
to
r
tio
n
T
h
e
ac
q
u
ir
ed
d
ata
is
s
am
p
led
at
d
if
f
er
en
t
f
r
eq
u
en
cies
s
u
ch
as
4
0
0
Hz,
8
0
0
Hz,
1
6
0
0
Hz,
3
2
0
0
Hz,
an
d
6
4
0
0
Hz,
as
d
is
cu
s
s
ed
in
C
NN
-
b
ased
is
lan
d
in
g
d
etec
ti
o
n
tech
n
iq
u
es
[
1
3
]
-
[
1
5
]
.
Hig
h
er
s
am
p
lin
g
r
ates
p
r
o
v
id
e
im
p
r
o
v
ed
s
ig
n
al
r
eso
l
u
tio
n
an
d
en
a
b
le
b
etter
i
d
en
tif
icatio
n
o
f
t
r
an
s
ien
t
d
is
tu
r
b
a
n
c
es
ass
o
ciate
d
with
is
lan
d
in
g
co
n
d
itio
n
s
.
A
co
m
p
lete
elec
tr
ical
cy
cle
is
co
n
s
id
er
ed
as o
n
e
an
al
y
s
is
win
d
o
w
f
o
r
f
ea
tu
r
e
g
e
n
er
atio
n
.
T
h
e
in
p
u
t
f
ea
tu
r
es
co
n
s
is
tin
g
o
f
R
MS
v
o
ltag
e
(
U)
,
R
MS
cu
r
r
en
t
(
I
)
,
f
r
eq
u
e
n
cy
(
f
)
,
ac
tiv
e
p
o
wer
(
P),
an
d
r
ea
ctiv
e
p
o
wer
(
Q)
wer
e
s
elec
ted
b
ec
au
s
e
th
ey
ex
h
i
b
it
s
ig
n
if
ican
t
d
ev
iatio
n
s
d
u
r
in
g
is
lan
d
in
g
co
n
d
itio
n
s
.
Vo
ltag
e
an
d
f
r
eq
u
en
cy
ar
e
t
h
e
p
r
im
ar
y
p
a
r
am
eter
s
s
p
ec
if
i
ed
in
I
E
E
E
1
5
4
7
f
o
r
is
lan
d
i
n
g
d
etec
tio
n
,
wh
ile
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
wer
r
e
f
lect
th
e
p
o
wer
m
is
m
atch
b
e
twee
n
th
e
d
is
tr
ib
u
ted
g
e
n
er
at
o
r
an
d
lo
ca
l
l
o
ad
.
C
u
r
r
en
t
m
ea
s
u
r
em
e
n
ts
p
r
o
v
id
e
ad
d
itio
n
al
tr
an
s
ien
t
in
f
o
r
m
at
io
n
th
at
im
p
r
o
v
es
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
co
m
b
in
atio
n
o
f
th
ese
elec
tr
ic
al
q
u
an
titi
es
en
ab
les
th
e
C
NN
to
ac
cu
r
ately
d
is
tin
g
u
is
h
i
s
lan
d
in
g
f
r
o
m
n
o
n
-
is
lan
d
in
g
d
is
tu
r
b
an
ce
s
.
3
.
3
.
Da
t
a
prepro
ce
s
s
ing
a
nd
no
rm
a
liza
t
i
o
n
Af
ter
ac
q
u
ir
in
g
th
e
elec
tr
ical
m
ea
s
u
r
em
en
ts
,
th
e
co
llected
s
ig
n
als
ar
e
p
r
ep
r
o
ce
s
s
ed
to
elim
in
ate
n
o
is
e,
im
p
r
o
v
e
s
ig
n
al
q
u
ality
,
an
d
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
AI
class
if
ier
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
in
clu
d
es
s
ig
n
al
f
ilter
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
d
ata
s
eg
m
en
tatio
n
p
r
o
ce
s
s
es.
Sin
ce
r
ea
l
-
t
im
e
p
o
wer
s
y
s
tem
s
ig
n
als
o
f
ten
co
n
tain
s
witch
i
n
g
h
ar
m
o
n
ics,
tr
an
s
ien
t
n
o
is
e,
an
d
m
ea
s
u
r
em
en
t
d
is
tu
r
b
a
n
ce
s
,
d
ig
ital
f
ilter
in
g
tech
n
iq
u
es a
r
e
a
p
p
lied
to
o
b
tai
n
s
tab
le
an
d
m
ea
n
in
g
f
u
l sig
n
al
ch
ar
ac
ter
is
tics
.
No
r
m
aliza
tio
n
is
p
er
f
o
r
m
e
d
to
s
ca
le
all
in
p
u
t
p
a
r
am
eter
s
with
in
a
c
o
m
m
o
n
r
an
g
e,
th
e
r
eb
y
i
m
p
r
o
v
i
n
g
n
eu
r
al
n
etwo
r
k
co
n
v
er
g
en
ce
d
u
r
in
g
tr
ain
i
n
g
.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
s
tag
e
also
d
i
v
id
es
th
e
m
ea
s
u
r
ed
wav
e
f
o
r
m
d
ata
in
to
f
ix
ed
-
len
g
t
h
win
d
o
ws
co
r
r
esp
o
n
d
in
g
to
o
n
e
elec
tr
ical
cy
cle.
T
h
ese
s
eg
m
en
ted
win
d
o
ws
ar
e
th
en
co
n
v
er
ted
in
to
f
ea
tu
r
e
v
ec
to
r
s
f
o
r
m
ac
h
in
e
lear
n
i
n
g
a
n
aly
s
is
.
Similar
p
r
ep
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
u
s
ed
in
wav
elet
-
tr
an
s
f
o
r
m
an
d
C
NN
-
b
ased
is
lan
d
in
g
d
etec
t
io
n
m
eth
o
d
s
[
1
4
]
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
an
d
f
ea
tu
r
e
p
r
ep
ar
atio
n
s
tag
es
ar
e
illu
s
tr
ated
in
Fig
u
r
e
3
.
T
h
at
f
i
g
u
r
e
s
h
o
ws
th
e
p
r
ep
r
o
ce
s
s
in
g
m
o
d
u
le
r
em
o
v
es
u
n
wan
te
d
d
is
tu
r
b
an
ce
s
an
d
p
r
ep
a
r
es st
an
d
ar
d
ized
f
ea
tu
r
e
v
ec
t
o
r
s
f
o
r
ac
cu
r
ate
class
if
icatio
n
b
y
th
e
AI
m
o
d
el.
Fig
u
r
e
3
.
Pre
p
r
o
ce
s
s
in
g
an
d
f
e
atu
r
e
p
r
e
p
ar
atio
n
s
tag
es
3.
4
.
F
e
a
t
ure
e
x
t
r
a
ct
io
n a
nd
CNN
-
ba
s
ed
cla
s
s
if
ica
t
io
n
I
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
,
f
ea
t
u
r
e
e
x
tr
ac
tio
n
an
d
AI
-
b
ased
class
if
icatio
n
ar
e
co
m
b
in
ed
to
ac
cu
r
ately
d
etec
t
is
lan
d
in
g
co
n
d
itio
n
s
in
PV
s
y
s
tem
s
.
E
lectr
ical
p
ar
am
eter
s
s
u
ch
a
s
v
o
ltag
e,
c
u
r
r
e
n
t,
f
r
eq
u
e
n
cy
,
ac
tiv
e
p
o
wer
,
r
ea
c
tiv
e
p
o
wer
,
an
d
h
ar
m
o
n
ic
d
is
to
r
tio
n
ar
e
co
n
ti
n
u
o
u
s
ly
m
o
n
i
to
r
ed
at
th
e
PC
C
.
Du
r
in
g
is
lan
d
in
g
co
n
d
itio
n
s
,
t
h
ese
p
ar
am
eter
s
ex
h
i
b
it
ab
n
o
r
m
al
v
ar
iatio
n
s
th
at
ca
n
b
e
id
e
n
tifie
d
u
s
in
g
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
es.
Sig
n
a
l
p
r
o
ce
s
s
in
g
m
eth
o
d
s
s
u
ch
as
f
ast
Fo
u
r
ier
tr
an
s
f
o
r
m
(
FF
T
)
an
d
wav
elet
tr
an
s
f
o
r
m
ar
e
u
s
ed
to
ex
tr
ac
t
im
p
o
r
tan
t
f
ea
tu
r
es
in
clu
d
in
g
R
MS
v
o
ltag
e,
R
MS
cu
r
r
en
t,
f
r
eq
u
en
c
y
d
ev
iatio
n
,
r
ate
o
f
ch
an
g
e
o
f
f
r
eq
u
e
n
cy
(
R
OC
O
F),
an
d
to
tal
h
ar
m
o
n
i
c
d
is
to
r
tio
n
(
T
HD)
[
1
4
]
,
[
1
5
]
.
T
h
ese
ex
tr
ac
ted
f
ea
tu
r
es a
r
e
co
n
v
er
ted
i
n
to
f
ea
tu
r
e
v
ec
to
r
s
an
d
s
u
p
p
lie
d
to
th
e
C
NN
clas
s
if
ier
f
o
r
in
tellig
en
t d
ec
is
io
n
-
m
ak
in
g
.
R
OC
OF
was
s
elec
ted
b
ec
au
s
e
it
ca
p
tu
r
es
th
e
d
y
n
am
ic
b
e
h
av
io
r
im
m
e
d
iately
f
o
llo
win
g
is
lan
d
in
g
.
Alth
o
u
g
h
f
r
e
q
u
en
c
y
d
e
v
iatio
n
s
m
ay
b
e
s
m
all
u
n
d
er
ce
r
tain
o
p
er
atin
g
co
n
d
itio
n
s
,
R
OC
OF
is
h
ig
h
ly
s
en
s
itiv
e
to
th
e
i
n
itial
tr
an
s
ien
t
ca
u
s
ed
b
y
g
r
id
d
is
co
n
n
ec
tio
n
.
Fu
r
t
h
e
r
m
o
r
e,
R
OC
OF
is
n
o
t
u
s
ed
in
d
ep
en
d
e
n
tly
b
u
t
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
175
5
-
1
7
6
7
1760
co
m
b
in
atio
n
with
v
o
ltag
e,
cu
r
r
en
t,
ac
tiv
e
p
o
wer
,
an
d
r
ea
ctiv
e
p
o
wer
,
en
a
b
lin
g
th
e
C
NN
to
lear
n
d
is
cr
im
in
ativ
e
p
atter
n
s
ev
en
wh
en
f
r
e
q
u
en
c
y
v
ar
iatio
n
s
ar
e
m
in
im
al.
As
illu
s
tr
ated
in
Fig
u
r
e
4
,
th
e
co
n
v
o
l
u
tio
n
lay
er
s
au
t
o
m
atica
lly
ex
tr
ac
t
d
ee
p
f
ea
t
u
r
es
f
r
o
m
th
e
in
p
u
t
s
ig
n
als,
wh
ile
p
o
o
lin
g
lay
er
s
r
ed
u
ce
co
m
p
u
tatio
n
al
co
m
p
lex
ity
.
T
h
e
f
u
lly
co
n
n
ec
ted
lay
er
s
p
er
f
o
r
m
f
i
n
al
class
if
icatio
n
b
y
ca
teg
o
r
izin
g
th
e
o
p
er
atin
g
c
o
n
d
itio
n
as e
ith
er
i
s
lan
d
in
g
o
r
n
o
n
-
is
lan
d
in
g
.
T
h
e
C
NN
m
o
d
el
is
tr
ain
ed
u
s
in
g
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es
with
lab
ele
d
d
atasets
co
n
tain
in
g
b
o
th
is
lan
d
in
g
a
n
d
n
o
n
-
is
lan
d
in
g
o
p
er
atin
g
s
ce
n
ar
io
s
.
B
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
s
ar
e
u
s
ed
to
m
in
im
ize
class
if
icatio
n
er
r
o
r
s
d
u
r
in
g
th
e
tr
ain
in
g
p
h
ase.
Op
tim
izatio
n
tech
n
iq
u
es
s
u
ch
as
g
en
etic
alg
o
r
ith
m
s
(
GA)
an
d
cu
ck
o
o
o
p
tim
izatio
n
alg
o
r
ith
m
s
ca
n
also
b
e
in
teg
r
ated
to
im
p
r
o
v
e
n
eu
r
al
n
etwo
r
k
p
er
f
o
r
m
an
ce
[
1
3
]
.
E
lectr
ical
s
ig
n
als
wer
e
g
en
e
r
ated
u
s
in
g
MA
T
L
AB
/Si
m
u
lin
k
,
a
n
d
f
ea
tu
r
e
ex
tr
ac
tio
n
,
n
o
r
m
aliza
tio
n
,
an
d
d
ataset
p
r
ep
ar
atio
n
wer
e
ca
r
r
i
ed
o
u
t u
s
in
g
MA
T
L
AB
s
cr
ip
ts
.
T
h
e
ex
tr
ac
ted
f
ea
tu
r
e
v
ec
to
r
s
wer
e
s
u
b
s
eq
u
en
tly
u
s
ed
to
tr
ain
a
n
d
v
alid
ate
t
h
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el.
3.
5
.
P
r
o
po
s
ed
CNN
s
t
ruct
ur
e
T
h
e
p
r
o
p
o
s
ed
in
tellig
en
t
is
lan
d
in
g
d
etec
tio
n
f
r
am
ewo
r
k
em
p
lo
y
s
a
o
n
e
-
d
im
en
s
io
n
al
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
1
D
-
C
NN)
to
au
to
m
atica
lly
class
if
y
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
in
g
c
o
n
d
iti
o
n
s
u
s
in
g
elec
tr
ical
s
ig
n
als
ac
q
u
ir
ed
f
r
o
m
th
e
PC
C
.
T
h
e
in
p
u
t
f
ea
tu
r
es
in
clu
d
e
R
MS
v
o
ltag
e,
R
M
S
cu
r
r
en
t,
f
r
eq
u
en
c
y
,
ac
tiv
e
p
o
wer
,
r
ea
ctiv
e
p
o
wer
,
an
d
T
HD.
B
ef
o
r
e
tr
ain
i
n
g
,
th
e
m
ea
s
u
r
ed
s
ig
n
als
ar
e
p
r
e
p
r
o
ce
s
s
e
d
th
r
o
u
g
h
f
ilter
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
s
eg
m
e
n
ta
tio
n
to
im
p
r
o
v
e
f
ea
tu
r
e
q
u
al
ity
an
d
en
h
an
ce
th
e
co
n
v
er
g
en
ce
o
f
th
e
d
ee
p
lear
n
in
g
m
o
d
el.
Fig
u
r
e
4
illu
s
tr
ates
th
e
o
v
er
all
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el,
co
n
s
is
tin
g
o
f
an
in
p
u
t
lay
er
,
two
co
n
v
o
l
u
tio
n
al
lay
er
s
,
two
m
ax
-
p
o
o
lin
g
lay
e
r
s
,
a
f
u
lly
co
n
n
ec
te
d
lay
er
,
a
d
r
o
p
o
u
t
lay
er
,
an
d
a
So
f
tm
ax
o
u
tp
u
t
lay
er
.
T
h
e
co
n
v
o
lu
tio
n
al
lay
er
s
au
to
m
atica
l
ly
ex
tr
ac
t
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
s
ig
n
als,
wh
ile
th
e
p
o
o
lin
g
lay
e
r
s
r
ed
u
ce
th
e
d
im
e
n
s
io
n
ality
o
f
th
e
ex
tr
ac
ted
f
ea
tu
r
e
m
ap
s
.
T
h
e
f
u
lly
c
o
n
n
ec
ted
lay
er
p
er
f
o
r
m
s
h
ig
h
-
lev
el
f
e
atu
r
e
lear
n
in
g
,
an
d
th
e
So
f
t
m
ax
class
if
ier
g
en
er
ates
th
e
f
in
al
d
ec
is
io
n
b
y
class
if
y
in
g
th
e
o
p
er
atin
g
co
n
d
itio
n
as
eith
er
is
lan
d
in
g
o
r
n
o
n
-
is
lan
d
in
g
.
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
e
n
ab
les
au
to
m
atic
f
ea
tu
r
e
ex
tr
ac
tio
n
with
o
u
t
r
ely
in
g
o
n
h
an
d
c
r
af
t
ed
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
th
e
r
e
b
y
im
p
r
o
v
i
n
g
t
h
e
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
o
f
is
lan
d
in
g
d
etec
tio
n
.
Fig
u
r
e
4
a
ls
o
s
h
o
ws
th
e
s
eq
u
en
tial
p
r
o
c
ess
in
g
o
f
th
e
in
p
u
t
f
ea
tu
r
es th
r
o
u
g
h
ea
c
h
C
NN
lay
er
b
ef
o
r
e
th
e
f
in
al
class
if
icatio
n
.
(
a)
(
b
)
Fig
u
r
e
4
.
C
NN
-
b
ased
in
tellig
e
n
t isl
an
d
in
g
d
etec
tio
n
:
(
a)
p
r
o
p
o
s
ed
C
NN
ar
ch
itectu
r
e
an
d
(
b
)
d
is
tr
ib
u
tio
n
o
f
C
NN
r
esid
u
als f
o
r
is
lan
d
in
g
a
n
d
n
o
n
-
is
lan
d
in
g
co
n
d
itio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Dee
p
lea
r
n
in
g
-
b
a
s
ed
in
tellig
e
n
t isl
a
n
d
in
g
d
etec
tio
n
fo
r
g
r
id
-
co
n
n
ec
ted
…
(
Do
n
d
a
p
a
ti R
a
v
i Ki
s
h
o
r
e
)
1761
3.
6
.
Da
t
a
s
et
prepa
ra
t
io
n
a
nd
t
ra
ini
ng
pro
ce
du
re
T
h
e
d
ataset
u
s
ed
f
o
r
tr
ain
i
n
g
an
d
test
in
g
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
was
g
en
er
ated
f
r
o
m
th
e
MA
T
L
AB
/S
im
u
lin
k
-
b
ased
p
h
o
to
v
o
ltaic
s
y
s
tem
u
n
d
er
d
i
f
f
er
en
t
o
p
er
atin
g
co
n
d
itio
n
s
,
in
clu
d
in
g
n
o
r
m
al
o
p
er
atio
n
,
lo
a
d
s
witch
in
g
,
g
r
id
d
is
tu
r
b
an
ce
s
,
an
d
in
ten
tio
n
al
is
lan
d
in
g
ev
en
ts
.
E
ac
h
o
p
er
atin
g
co
n
d
itio
n
g
en
er
ated
o
n
e
-
c
y
cle
s
ig
n
al
wi
n
d
o
ws
co
n
s
is
tin
g
o
f
v
o
ltag
e
,
cu
r
r
en
t,
f
r
eq
u
en
cy
,
ac
tiv
e
p
o
wer
,
r
ea
ctiv
e
p
o
wer
,
an
d
T
HD
m
ea
s
u
r
em
en
ts
.
T
h
e
co
llected
d
ataset
was
n
o
r
m
al
ized
u
s
in
g
m
in
-
m
ax
n
o
r
m
aliz
atio
n
an
d
r
an
d
o
m
ly
d
iv
id
ed
in
t
o
7
0
% tr
ain
i
n
g
,
1
5
% v
alid
atio
n
,
an
d
1
5
% testi
n
g
d
atasets
to
en
s
u
r
e
u
n
b
iased
m
o
d
el
ev
alu
atio
n
.
T
h
e
C
N
N
m
o
d
e
l
w
a
s
t
r
a
i
n
e
d
u
s
i
n
g
t
h
e
A
d
a
m
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
w
i
t
h
a
l
e
a
r
n
i
n
g
r
a
t
e
o
f
0
.
0
0
1
,
a
m
i
n
i
-
b
a
t
c
h
s
i
z
e
o
f
3
2
,
a
n
d
5
0
t
r
a
i
n
i
n
g
e
p
o
c
h
s
.
D
u
r
i
n
g
t
r
a
i
n
i
n
g
,
t
h
e
v
a
l
i
d
a
t
i
o
n
d
a
t
a
s
e
t
w
a
s
u
s
e
d
t
o
m
o
n
i
t
o
r
t
h
e
l
e
a
r
n
i
n
g
p
r
o
c
e
s
s
a
n
d
p
r
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g
t
h
r
o
u
g
h
e
a
r
l
y
s
t
o
p
p
i
n
g
.
T
h
e
e
v
o
l
u
t
i
o
n
o
f
t
h
e
t
r
a
i
n
i
n
g
a
n
d
v
a
l
i
d
a
t
i
o
n
a
c
c
u
r
a
c
y
i
s
i
l
l
u
s
t
r
a
t
e
d
i
n
F
i
g
u
r
e
5
.
A
s
o
b
s
e
r
v
e
d
,
b
o
t
h
c
u
r
v
e
s
g
r
a
d
u
a
l
l
y
c
o
n
v
e
r
g
e
a
n
d
s
t
a
b
i
l
i
z
e
a
f
t
e
r
a
p
p
r
o
x
i
m
a
t
e
l
y
3
0
ep
o
ch
s
,
in
d
icatin
g
s
u
cc
ess
f
u
l le
ar
n
in
g
a
n
d
g
o
o
d
g
en
e
r
aliza
tio
n
ca
p
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el.
3.
7
.
M
o
del v
a
lid
a
t
io
n
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
was
ev
alu
at
ed
u
s
in
g
s
tan
d
a
r
d
class
if
icatio
n
m
etr
ics,
in
clu
d
in
g
o
v
e
r
all
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
.
I
n
ad
d
itio
n
,
a
c
o
n
f
u
s
io
n
m
atr
ix
was
u
s
ed
to
v
is
u
alize
th
e
class
if
icatio
n
p
e
r
f
o
r
m
an
ce
u
n
d
er
b
o
t
h
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
i
n
g
co
n
d
itio
n
s
.
Fig
u
r
e
6
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
at
r
ix
o
b
tain
e
d
f
r
o
m
th
e
test
in
g
d
ataset.
I
t
ca
n
b
e
o
b
s
er
v
e
d
th
at
th
e
p
r
o
p
o
s
ed
class
if
ier
co
r
r
ec
tly
id
e
n
tifie
d
th
e
m
ajo
r
ity
o
f
o
p
er
atin
g
c
o
n
d
itio
n
s
w
ith
o
n
ly
a
f
ew
m
is
class
if
icati
o
n
s
,
d
em
o
n
s
tr
atin
g
ex
ce
llen
t
class
if
icatio
n
ca
p
a
b
ilit
y
.
T
h
e
q
u
a
n
titativ
e
p
e
r
f
o
r
m
an
ce
m
etr
ics
d
er
iv
ed
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
iev
ed
an
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
o
f
a
p
p
r
o
x
i
m
ately
9
9
.
2
%,
with
h
ig
h
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
ese
r
esu
lts
co
n
f
ir
m
t
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
f
o
r
r
eliab
le
is
lan
d
in
g
d
etec
tio
n
u
n
d
er
d
if
f
e
r
en
t o
p
er
atin
g
c
o
n
d
iti
o
n
s
.
Fig
u
r
e
5
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
an
d
p
er
f
o
r
m
an
ce
ev
alu
atio
n
o
f
t
h
e
p
r
o
p
o
s
ed
C
NN
class
if
ier
4.
SYST
E
M
UND
E
R
S
T
UDY
T
h
e
p
r
o
p
o
s
ed
is
lan
d
in
g
d
ete
ctio
n
m
o
d
el
is
d
ev
elo
p
e
d
an
d
ev
alu
ated
u
s
in
g
a
g
r
i
d
-
co
n
n
ec
ted
PV
s
y
s
tem
m
o
d
eled
in
MA
T
L
A
B
/Si
m
u
lin
k
.
T
h
e
u
tili
ty
g
r
id
i
s
r
ated
at
1
2
0
k
V
an
d
o
p
e
r
ates
at
a
f
r
eq
u
en
c
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
175
5
-
1
7
6
7
1762
5
0
Hz.
A
100
-
kW
p
h
o
to
v
o
ltai
c
ar
r
ay
is
co
n
n
ec
ted
to
th
e
d
is
tr
ib
u
tio
n
f
ee
d
er
th
r
o
u
g
h
a
th
r
ee
-
p
h
ase
tr
an
s
f
o
r
m
e
r
an
d
VSC
.
T
h
e
PV
s
y
s
tem
in
co
r
p
o
r
ates
a
DC
–
DC
b
o
o
s
t
co
n
v
er
ter
an
d
MPPT
co
n
tr
o
ller
to
en
s
u
r
e
m
ax
im
u
m
p
o
wer
ex
tr
ac
tio
n
u
n
d
er
v
a
r
y
in
g
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
.
Dif
f
er
en
t
o
p
er
ati
n
g
co
n
d
it
io
n
s
s
u
ch
as
lo
ad
v
ar
iatio
n
,
n
o
r
m
al
g
r
id
o
p
er
at
io
n
,
an
d
is
lan
d
in
g
ev
e
n
ts
ar
e
co
n
s
id
er
ed
f
o
r
e
v
alu
atin
g
t
h
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
-
b
ased
d
etec
tio
n
s
ch
em
e
.
T
h
e
C
NN
-
b
ased
is
lan
d
in
g
d
etec
tio
n
alg
o
r
ith
m
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
s
v
o
ltag
e,
cu
r
r
en
t,
an
d
f
r
eq
u
e
n
cy
s
ig
n
als
at
th
e
PC
C
.
T
h
e
ac
q
u
ir
ed
d
ata
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
d
if
f
er
en
t
s
am
p
lin
g
f
r
eq
u
en
cies
r
a
n
g
in
g
f
r
o
m
0
.
4
k
Hz
to
6
.
4
k
Hz.
T
h
e
ex
tr
ac
ted
s
ig
n
al
f
ea
tu
r
es
ar
e
p
r
o
v
id
e
d
as
in
p
u
ts
to
th
e
tr
ain
ed
n
eu
r
al
n
etwo
r
k
f
o
r
class
if
icatio
n
o
f
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
in
g
co
n
d
itio
n
s
.
5.
SI
M
UL
A
T
I
O
N
R
E
S
UL
T
S
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
AI
-
b
ased
is
lan
d
in
g
d
e
tectio
n
tech
n
iq
u
e
was
ev
alu
ated
u
s
in
g
MA
T
L
AB
/S
im
u
lin
k
u
n
d
er
d
if
f
er
en
t
o
p
er
atin
g
co
n
d
itio
n
s
o
f
th
e
PV
s
y
s
tem
.
T
h
e
s
im
u
latio
n
m
o
d
el
co
n
s
is
ts
o
f
a
100
-
kW
g
r
i
d
-
co
n
n
ec
ted
PV
ar
r
ay
in
teg
r
ate
d
with
t
h
e
u
til
ity
g
r
id
th
r
o
u
g
h
a
th
r
ee
-
p
h
ase
VSC
,
tr
an
s
f
o
r
m
er
,
an
d
f
ilter
in
g
cir
cu
it.
T
h
e
PV
s
y
s
tem
o
p
er
ates
u
n
d
er
n
o
r
m
al
co
n
d
itio
n
s
b
ef
o
r
e
an
in
ten
tio
n
al
is
lan
d
in
g
ev
en
t
is
in
tr
o
d
u
ce
d
b
y
d
is
co
n
n
ec
tin
g
t
h
e
u
tili
ty
g
r
id
at
t
=
5
s
.
T
h
e
p
r
o
p
o
s
ed
d
etec
tio
n
alg
o
r
ith
m
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
s
elec
tr
ical
p
ar
am
eter
s
s
u
c
h
as
v
o
ltag
e,
cu
r
r
en
t,
f
r
eq
u
e
n
cy
,
a
n
d
p
h
ase
an
g
le
at
th
e
PC
C
.
T
h
ese
m
ea
s
u
r
ed
s
ig
n
als
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
th
e
tr
ain
e
d
C
NN
m
o
d
el
to
class
if
y
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
i
n
g
o
p
e
r
atin
g
co
n
d
itio
n
s
.
Dif
f
er
en
t d
is
tu
r
b
a
n
ce
s
ce
n
ar
io
s
,
in
clu
d
in
g
lo
ad
v
a
r
iatio
n
,
g
r
id
d
is
co
n
n
ec
tio
n
,
an
d
tr
an
s
ien
t
o
p
er
ati
n
g
c
o
n
d
itio
n
s
,
wer
e
c
o
n
s
id
e
r
ed
to
v
e
r
if
y
th
e
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
I
n
th
e
s
im
u
latio
n
s
tu
d
y
,
is
lan
d
in
g
was
in
ten
tio
n
ally
cr
ea
ted
b
y
o
p
en
in
g
th
e
cir
cu
it
b
r
ea
k
er
co
n
n
ec
tin
g
th
e
u
tili
ty
g
r
id
to
th
e
PC
C
a
t
t
=
5
s
.
T
h
is
co
n
t
r
o
lled
ev
en
t
en
a
b
les
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
d
etec
tio
n
alg
o
r
ith
m
u
n
d
e
r
r
e
p
ea
tab
le
o
p
er
atin
g
c
o
n
d
itio
n
s
.
T
h
e
elec
tr
ical
p
a
r
am
eter
s
(
U,
I
,
f
,
P,
an
d
Q)
u
s
ed
f
o
r
tr
ain
in
g
an
d
test
in
g
th
e
C
NN
wer
e
o
b
tain
ed
f
r
o
m
MA
T
L
AB
/Si
m
u
lin
k
s
im
u
latio
n
s
o
f
th
e
g
r
id
-
co
n
n
ec
ted
p
h
o
to
v
o
ltaic
s
y
s
tem
u
n
d
er
v
a
r
io
u
s
o
p
er
atin
g
c
o
n
d
itio
n
s
,
in
clu
d
in
g
n
o
r
m
al
o
p
e
r
atio
n
,
lo
ad
s
witch
in
g
,
g
r
id
d
is
tu
r
b
an
ce
s
,
an
d
is
lan
d
in
g
e
v
en
ts
.
Fig
u
r
e
7
s
h
o
ws
th
e
f
r
eq
u
en
c
y
r
esp
o
n
s
e
o
f
th
e
PV
s
y
s
tem
d
u
r
in
g
is
lan
d
in
g
.
B
ef
o
r
e
t
=
5
s
,
th
e
f
r
eq
u
e
n
cy
r
em
ai
n
s
s
tab
le
at
5
0
Hz.
Af
ter
g
r
i
d
d
is
co
n
n
ec
tio
n
,
n
o
ticea
b
le
f
r
eq
u
en
cy
d
ev
iat
io
n
s
an
d
o
s
cillatio
n
s
o
cc
u
r
d
u
e
to
lo
s
s
o
f
s
y
n
c
h
r
o
n
izatio
n
.
T
h
e
p
r
o
p
o
s
ed
C
NN
m
o
d
el
r
a
p
id
ly
d
etec
ts
th
e
ab
n
o
r
m
al
co
n
d
itio
n
a
n
d
ac
tiv
ates
th
e
p
r
o
tectio
n
m
ec
h
an
is
m
.
Fig
u
r
e
8
illu
s
tr
ates
th
e
PV
s
id
e
v
o
ltag
e
a
n
d
c
u
r
r
e
n
t
wav
ef
o
r
m
s
d
u
r
in
g
n
o
r
m
al
g
r
i
d
-
co
n
n
ec
ted
o
p
er
ati
o
n
.
T
h
e
wav
e
f
o
r
m
s
r
em
ain
s
in
u
s
o
id
al,
b
alan
ce
d
,
a
n
d
s
tab
le
at
5
0
Hz,
in
d
icatin
g
p
r
o
p
er
s
y
n
ch
r
o
n
izatio
n
b
etwe
en
th
e
PV in
v
er
ter
an
d
t
h
e
u
til
ity
g
r
id
.
Fig
u
r
e
9
p
r
esen
ts
th
e
PV
s
id
e
v
o
ltag
e
an
d
c
u
r
r
en
t
c
h
ar
ac
t
er
is
tics
d
u
r
in
g
is
lan
d
in
g
.
Af
t
er
t
=
5
s
,
wav
ef
o
r
m
d
is
to
r
tio
n
s
an
d
o
s
cillatio
n
s
ap
p
ea
r
d
u
e
to
g
r
id
d
is
co
n
n
ec
tio
n
a
n
d
lo
s
s
o
f
s
y
n
ch
r
o
n
izatio
n
.
T
h
e
p
r
o
p
o
s
ed
C
NN
class
if
ier
ef
f
ec
tiv
ely
id
en
tifie
s
th
ese
ab
n
o
r
m
al
v
ar
iatio
n
s
f
o
r
ac
c
u
r
ate
i
s
lan
d
in
g
d
etec
tio
n
.
Fig
u
r
e
1
0
s
h
o
ws
th
e
g
r
id
-
s
id
e
v
o
ltag
e
an
d
cu
r
r
en
t
r
esp
o
n
s
e
s
d
u
r
in
g
is
lan
d
in
g
.
Du
r
in
g
n
o
r
m
al
o
p
er
atio
n
,
th
e
wav
ef
o
r
m
s
r
em
ain
s
tab
le
an
d
b
alan
ce
d
.
Af
ter
th
e
is
lan
d
in
g
ev
e
n
t
at
t
=
5
s
,
s
u
d
d
e
n
d
is
tu
r
b
a
n
ce
s
an
d
wav
ef
o
r
m
v
a
r
iatio
n
s
ar
e
o
b
s
er
v
ed
.
T
h
e
p
r
o
p
o
s
ed
AI
-
b
ased
m
eth
o
d
q
u
ick
ly
d
etec
ts
th
ese
ch
an
g
es
an
d
d
is
co
n
n
ec
ts
th
e
PV in
v
er
ter
f
r
o
m
th
e
is
o
lated
s
y
s
tem
.
Fig
u
r
e
7
.
Fre
q
u
en
cy
r
esp
o
n
s
e
d
u
r
in
g
th
e
is
lan
d
in
g
co
n
d
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Dee
p
lea
r
n
in
g
-
b
a
s
ed
in
tellig
e
n
t isl
a
n
d
in
g
d
etec
tio
n
fo
r
g
r
id
-
co
n
n
ec
ted
…
(
Do
n
d
a
p
a
ti R
a
v
i Ki
s
h
o
r
e
)
1763
Fig
u
r
e
8
.
PV sid
e
v
o
ltag
e
an
d
cu
r
r
en
t
d
u
r
in
g
n
o
r
m
al
g
r
i
d
-
co
n
n
ec
ted
o
p
er
atio
n
Fig
u
r
e
9
.
PV sid
e
v
o
ltag
e
an
d
cu
r
r
en
t
d
u
r
in
g
is
lan
d
in
g
c
o
n
d
i
tio
n
Fig
u
r
e
1
0
.
Gr
id
s
id
e
v
o
ltag
e
a
n
d
cu
r
r
en
t r
esp
o
n
s
es d
u
r
in
g
is
lan
d
in
g
T
h
e
s
im
u
latio
n
r
esu
lts
co
n
f
i
r
m
th
at
th
e
p
r
o
p
o
s
ed
C
NN
-
ass
is
ted
is
lan
d
in
g
d
etec
tio
n
tech
n
iq
u
e
p
r
o
v
id
es
h
i
g
h
d
etec
tio
n
ac
cu
r
ac
y
,
f
ast
r
esp
o
n
s
e
tim
e,
an
d
r
eliab
le
o
p
e
r
atio
n
u
n
d
e
r
d
i
f
f
er
en
t
d
is
tu
r
b
an
ce
co
n
d
itio
n
s
.
C
o
m
p
ar
e
d
with
tr
a
d
itio
n
al
p
ass
iv
e
an
d
ac
tiv
e
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
s
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates
s
u
p
er
io
r
ca
p
a
b
il
ity
in
id
e
n
tify
in
g
is
lan
d
in
g
e
v
en
ts
with
r
ed
u
ce
d
d
etec
tio
n
tim
e
an
d
i
m
p
r
o
v
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
175
5
-
1
7
6
7
1764
s
y
s
tem
s
tab
ilit
y
.
T
h
e
o
b
tain
ed
r
esu
lts
v
alid
ate
th
e
e
f
f
ec
t
iv
en
ess
o
f
ar
tific
ial
in
tellig
e
n
ce
tech
n
iq
u
es
f
o
r
en
h
an
cin
g
th
e
p
r
o
tectio
n
a
n
d
r
eliab
ilit
y
o
f
m
o
d
er
n
g
r
id
-
c
o
n
n
ec
ted
p
h
o
t
o
v
o
ltaic
s
y
s
tem
s
.
5
.
1
.
Co
m
pa
riso
n o
f
is
la
nd
ing
det
ec
t
io
n m
et
ho
ds
T
ab
le
1
p
r
esen
ts
th
e
n
u
m
er
ical
co
m
p
ar
is
o
n
o
f
v
ar
io
u
s
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
s
u
s
ed
in
p
h
o
to
v
o
ltaic
s
y
s
tem
s
.
Pas
s
iv
e
d
etec
tio
n
m
et
h
o
d
s
p
r
o
v
id
e
a
s
im
p
le
an
d
ec
o
n
o
m
ical
s
o
lu
ti
o
n
b
u
t
s
u
f
f
er
f
r
o
m
lo
wer
d
etec
tio
n
ac
cu
r
ac
y
an
d
l
ar
g
er
n
o
n
-
d
etec
tio
n
zo
n
es.
Ac
tiv
e
m
eth
o
d
s
im
p
r
o
v
e
th
e
d
ete
ctio
n
ca
p
ab
ilit
y
b
y
in
tr
o
d
u
cin
g
s
y
s
tem
p
er
tu
r
b
atio
n
s
;
h
o
wev
er
,
t
h
ey
m
a
y
af
f
e
ct
p
o
wer
q
u
ality
.
Hy
b
r
id
m
e
th
o
d
s
co
m
b
i
n
e
th
e
ad
v
an
tag
es
o
f
p
ass
iv
e
an
d
ac
t
iv
e
ap
p
r
o
ac
h
es
to
ac
h
iev
e
b
et
ter
r
eliab
ilit
y
a
n
d
f
aster
r
esp
o
n
s
e.
T
h
e
p
r
o
p
o
s
ed
AI
-
b
ased
C
NN
m
eth
o
d
d
em
o
n
s
tr
ates
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
with
a
d
etec
tio
n
ac
cu
r
ac
y
o
f
a
p
p
r
o
x
im
ately
9
9
%,
r
ed
u
ce
d
f
alse
d
etec
tio
n
r
ate,
m
in
im
al
n
o
n
-
d
etec
tio
n
zo
n
e,
an
d
f
aster
d
etec
tio
n
r
esp
o
n
s
e
co
m
p
ar
ed
to
co
n
v
en
tio
n
al
tech
n
iq
u
es.
T
h
e
s
e
r
esu
lts
h
ig
h
lig
h
t
th
e
ef
f
ec
tiv
en
ess
o
f
ar
tific
ial
in
tellig
en
ce
tech
n
iq
u
es
in
en
h
an
cin
g
th
e
s
af
ety
a
n
d
r
elia
b
ilit
y
o
f
g
r
id
-
co
n
n
ec
ted
PV sy
s
tem
s
.
T
ab
le
1
.
Nu
m
e
r
ical
co
m
p
a
r
is
o
n
o
f
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
s
f
o
r
PV
s
y
s
tem
s
D
e
t
e
c
t
i
o
n
m
e
t
h
o
d
D
e
t
e
c
t
i
o
n
t
i
m
e
D
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
F
a
l
se
d
e
t
e
c
t
i
o
n
ra
te
NDZ
S
a
mp
l
i
n
g
r
e
q
u
i
r
e
m
e
n
t
P
o
w
e
r
q
u
a
l
i
t
y
i
mp
a
c
t
P
a
ssi
v
e
m
e
t
h
o
d
2
5
0
–
5
0
0
ms
85
–
9
0
%
8
–
1
2
%
La
r
g
e
Lo
w
N
o
i
m
p
a
c
t
A
c
t
i
v
e
me
t
h
o
d
1
0
0
–
2
5
0
ms
90
–
9
4
%
5
–
8%
M
e
d
i
u
m
M
e
d
i
u
m
M
o
d
e
r
a
t
e
d
i
s
t
u
r
b
a
n
c
e
H
y
b
r
i
d
met
h
o
d
80
–
1
5
0
m
s
94
–
9
6
%
3
–
5%
S
mal
l
M
e
d
i
u
m
–
h
i
g
h
S
l
i
g
h
t
d
i
s
t
u
r
b
a
n
c
e
P
r
o
p
o
se
d
A
I
-
b
a
se
d
C
N
N
m
e
t
h
o
d
20
–
5
0
ms
9
8
.
7
–
9
9
.
2
%
0
.
8
–
1
.
5
%
V
e
r
y
smal
l
H
i
g
h
N
o
d
i
s
t
u
r
b
a
n
c
e
5
.
2
.
P
er
f
o
r
m
a
nce
e
v
a
lua
t
io
n o
f
t
he
CNN
m
o
del
T
o
q
u
a
n
titativ
ely
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
C
NN
-
b
ased
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
,
th
e
tr
ain
ed
m
o
d
el
was
test
ed
u
s
in
g
p
r
ev
i
o
u
s
ly
u
n
s
ee
n
d
ata
o
b
tain
ed
f
r
o
m
d
if
f
er
en
t
PV
o
p
er
atin
g
s
ce
n
ar
io
s
.
Fig
u
r
e
6
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
p
r
o
p
o
s
ed
cl
ass
if
ier
,
illu
s
tr
atin
g
th
e
n
u
m
b
er
s
o
f
co
r
r
ec
tly
an
d
in
co
r
r
ec
tly
class
if
ied
is
lan
d
in
g
an
d
n
o
n
-
is
lan
d
i
n
g
ev
en
ts
.
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
s
u
cc
ess
f
u
lly
class
if
ied
alm
o
s
t
all
o
p
er
atin
g
c
o
n
d
itio
n
s
with
o
n
ly
a
f
ew
m
is
class
if
icatio
n
s
.
T
h
e
class
if
icatio
n
p
er
f
o
r
m
a
n
c
e
was
f
u
r
t
h
er
e
v
alu
ated
u
s
in
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
a
n
d
o
v
er
all
ac
cu
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
C
NN
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
9
.
2
%,
p
r
ec
is
io
n
o
f
9
9
.
0
%,
r
ec
al
l
o
f
9
9
.
1
%,
an
d
an
F1
-
s
co
r
e
o
f
9
9
.
0
%,
co
n
f
ir
m
in
g
its
s
u
p
er
io
r
ca
p
ab
ilit
y
in
d
is
tin
g
u
is
h
in
g
is
lan
d
in
g
e
v
en
ts
f
r
o
m
o
th
er
t
r
an
s
ien
t
d
is
tu
r
b
an
ce
s
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
p
r
o
v
id
es
f
ast,
r
eliab
le,
an
d
h
ig
h
ly
ac
cu
r
ate
is
lan
d
in
g
d
etec
tio
n
s
u
itab
le
f
o
r
p
r
ac
tical
g
r
id
-
c
o
n
n
ec
ted
p
h
o
to
v
o
ltaic
s
y
s
tem
s
.
6.
CO
NCLU
SI
O
NS
T
h
e
p
r
o
p
o
s
ed
A
I
-
b
ase
d
is
l
an
d
i
n
g
d
e
te
cti
o
n
te
ch
n
i
q
u
e
a
c
h
i
ev
ed
s
u
p
e
r
i
o
r
p
e
r
f
o
r
m
a
n
c
e
c
o
m
p
ar
e
d
to
co
n
v
e
n
ti
o
n
a
l
p
ass
i
v
e,
a
cti
v
e
,
a
n
d
h
y
b
r
i
d
m
e
th
o
d
s
in
t
er
m
s
o
f
s
p
ee
d
,
a
cc
u
r
ac
y
,
an
d
r
eli
ab
ilit
y
.
T
h
e
C
NN
-
b
as
ed
m
o
d
el
a
ch
ie
v
e
d
ap
p
r
o
x
i
m
a
tel
y
9
9
%
d
ete
cti
o
n
a
cc
u
r
ac
y
wit
h
a
f
ast
r
es
p
o
n
s
e
ti
m
e
o
f
2
0
–
5
0
m
s
,
s
atis
f
y
i
n
g
I
E
E
E
p
r
o
t
ec
ti
o
n
s
t
an
d
ar
d
s
.
S
im
u
l
ati
o
n
r
es
u
l
ts
s
h
o
we
d
t
h
at
h
i
g
h
e
r
s
a
m
p
li
n
g
r
at
es
im
p
r
o
v
ed
d
e
t
ec
ti
o
n
p
er
f
o
r
m
a
n
ce
,
wh
e
r
e
a
cc
u
r
ac
y
in
cr
ea
s
ed
f
r
o
m
9
0
.
5
%
a
t
4
0
0
Hz
to
9
9
.
2
%
at
6
4
0
0
Hz
.
T
h
e
A
I
-
b
ase
d
I
DS
s
u
c
ce
s
s
f
u
ll
y
d
et
ec
te
d
is
l
an
d
i
n
g
at
5
s
e
co
n
d
s
b
y
i
d
e
n
ti
f
y
i
n
g
v
o
lt
a
g
e
d
ev
i
ati
o
n
s
(
±
1
2
%)
an
d
f
r
eq
u
e
n
c
y
c
h
a
n
g
es
(
5
9
.
1
–
6
0
.
8
Hz
)
,
a
n
d
d
is
co
n
n
e
cte
d
t
h
e
PV
i
n
v
e
r
t
er
w
it
h
i
n
4
5
m
s
.
Ov
e
r
all
,
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
p
r
o
v
id
es
a
f
ast
,
r
el
ia
b
le
,
a
n
d
ad
ap
ti
v
e
s
o
l
u
ti
o
n
f
o
r
e
n
h
a
n
ci
n
g
t
h
e
s
a
f
et
y
a
n
d
s
t
ab
i
lit
y
o
f
g
r
i
d
-
c
o
n
n
ec
t
e
d
p
h
o
to
v
o
lta
ic
s
y
s
te
m
s
.
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
C
NN
-
b
ased
is
lan
d
in
g
d
etec
tio
n
m
eth
o
d
d
em
o
n
s
tr
ates
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
an
d
f
ast
r
esp
o
n
s
e
u
n
d
er
MA
T
L
AB
/Si
m
u
lin
k
s
im
u
latio
n
en
v
ir
o
n
m
en
ts
,
th
e
p
r
ese
n
t
s
tu
d
y
is
lim
ited
to
s
im
u
latio
n
-
b
ased
v
alid
atio
n
u
s
in
g
g
en
er
ate
d
d
atasets
.
Pra
c
tical
im
p
lem
en
tatio
n
m
ay
b
e
i
n
f
lu
en
ce
d
b
y
n
o
is
e
m
ea
s
u
r
em
en
t,
co
m
m
u
n
icatio
n
d
elay
s
,
ch
an
g
in
g
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
an
d
u
n
ce
r
tain
ti
es
ass
o
ciate
d
wi
th
r
ea
l
-
wo
r
ld
p
h
o
to
v
o
ltaic
s
y
s
tem
s
.
T
h
er
ef
o
r
e,
f
u
tu
r
e
wo
r
k
wi
ll
f
o
cu
s
o
n
v
alid
atin
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
u
s
in
g
r
ea
l
-
tim
e
h
ar
d
war
e
p
latf
o
r
m
s
s
u
ch
as
h
ar
d
war
e
-
in
-
th
e
-
lo
o
p
(
HI
L
)
s
y
s
tem
s
an
d
ex
p
e
r
im
en
tal
PV
test
b
ed
s
.
I
n
ad
d
itio
n
,
th
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
ca
n
b
e
e
x
ten
d
e
d
b
y
in
c
o
r
p
o
r
ati
n
g
ad
v
a
n
ce
d
d
ee
p
lea
r
n
in
g
ar
ch
itectu
r
es,
in
clu
d
in
g
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
,
T
r
an
s
f
o
r
m
er
-
b
ased
n
etwo
r
k
s
,
an
d
h
y
b
r
id
d
e
ep
lear
n
in
g
m
o
d
els,
to
f
u
r
th
e
r
en
h
a
n
ce
d
etec
tio
n
a
cc
u
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
ad
ap
t
ab
ilit
y
in
m
o
d
e
r
n
s
m
ar
t g
r
id
a
p
p
licatio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
s
u
p
p
o
r
t
ed
b
y
Ko
n
er
u
L
a
k
s
h
m
aiah
E
d
u
ca
tio
n
Fo
u
n
d
atio
n
,
Scien
ce
an
d
E
n
g
in
ee
r
in
g
R
esear
ch
B
o
ar
d
,
Dep
ar
tm
en
t o
f
Scien
ce
an
d
T
e
ch
n
o
lo
g
y
,
I
n
d
ia.
(
Fil
e
No
: E
E
Q/2
0
2
3
/0
0
0
7
4
4
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.