I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
,
p
p
.
3
1
9
8
~
3
2
0
6
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ec
e.
v
7
i
6
.
pp
3
1
9
8
-
3206
3198
J
o
ur
na
l
ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
S
CNN
Ba
sed
Elec
trical Cha
ra
ct
eris
tics
o
f
So
la
r
Photo
v
o
ltaic Cell
M
o
del
B
a
m
ba
ng
P
urw
a
hy
ud
i
1
,
K
us
pija
ni
2
,
Ah
m
a
di
3
1,
2,
3
De
p
a
rtem
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsity
o
f
Bh
a
y
a
n
g
k
a
ra
,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
1
4
,
2
0
1
7
R
ev
i
s
ed
J
u
n
2
3
,
2
0
1
7
A
cc
ep
ted
J
u
l
18
,
2
0
1
7
S
o
lar
p
h
o
to
v
o
lt
a
ic
(P
V
)
c
e
ll
is
o
n
e
o
f
th
e
re
n
e
wa
b
le
e
n
e
rg
y
so
u
rc
e
s
a
n
d
a
m
a
in
c
o
m
p
o
n
e
n
t
o
f
P
V
p
o
w
e
r
s
y
ste
m
s.
T
h
e
d
e
sig
n
o
f
P
V
p
o
w
e
r
s
y
ste
m
s
re
q
u
ires
a
c
c
u
ra
tel
y
it
s
e
lec
tri
c
a
l
o
u
t
p
u
t
c
h
a
ra
c
teristics
.
T
h
e
e
lec
tri
c
a
l
c
h
a
ra
c
teristics
o
f
so
lar
P
V
c
e
ll
c
o
n
sist
o
f
I
-
V
a
n
d
P
-
V
c
h
a
ra
c
teristics
.
T
h
e
y
d
e
p
e
n
d
o
n
t
h
e
p
a
ra
m
e
ters
o
f
P
V
c
e
ll
su
c
h
a
s
sh
o
r
t
c
ircu
it
c
u
r
re
n
t,
o
p
e
n
c
ircu
it
v
o
lt
a
g
e
a
n
d
m
a
x
i
m
u
m
p
o
w
e
r
.
S
o
lar
P
V
c
e
ll
m
o
d
e
l
c
a
n
b
e
d
e
sc
rib
e
d
th
ro
u
g
h
a
n
e
q
u
iv
a
len
t
c
ircu
it
in
c
lu
d
i
n
g
a
c
u
rre
n
t
so
u
rc
e
,
a
d
io
d
e
,
a
se
rie
s
re
sisto
r
a
n
d
a
sh
u
n
t
re
sisto
r
.
I
n
th
is
p
a
p
e
r,
th
e
d
e
v
e
lo
p
m
e
n
t
so
lar
P
V
c
e
ll
m
o
d
e
l
is
b
u
il
t
b
y
u
sin
g
se
l
f
c
o
n
stru
c
ti
n
g
n
e
u
ra
l
n
e
tw
o
rk
(S
CNN
)
m
e
th
o
d
s.
T
h
is
S
C
N
N
tec
h
n
i
q
u
e
is
u
se
d
to
im
p
ro
v
e
th
e
a
c
c
u
ra
c
y
o
f
th
e
e
lec
tri
c
a
l
c
h
a
ra
c
teristic
o
f
so
lar
P
V
c
e
ll
m
o
d
e
l
.
S
CNN
so
lar
PV
c
e
ll
m
o
d
e
l
h
a
v
e
th
re
e
in
p
u
ts
a
n
d
tw
o
o
u
t
p
u
ts
.
T
h
e
y
a
r
e
re
sp
e
c
ti
v
e
l
y
so
lar
ra
d
iatio
n
,
tem
p
e
ra
tu
re
,
se
r
ies
re
sista
n
c
e
,
c
u
rre
n
t
a
n
d
p
o
w
e
r.
T
h
e
e
ffe
c
ti
v
e
n
e
s
s
o
f
S
C
N
N
te
c
h
n
iq
u
e
is
v
e
ri
f
ied
u
sin
g
sim
u
latio
n
re
su
lt
s
b
a
se
d
o
n
d
if
f
e
r
e
n
t
p
h
y
sic
a
l
a
n
d
e
n
v
iro
n
m
e
n
tal
c
o
n
d
i
ti
o
n
s
.
S
im
u
latio
n
s
a
re
c
o
n
d
u
c
ted
b
y
th
e
c
h
a
n
g
e
o
f
th
e
so
lar
irrad
iatio
n
,
tem
p
e
ra
tu
re
a
n
d
se
ries
r
e
sista
n
c
e
.
S
i
m
u
latio
n
re
su
lt
s
sh
o
w
S
CNN
m
o
d
e
l
c
a
n
y
ield
th
e
I
-
V
a
n
d
P
-
V
c
h
a
ra
c
teristics
a
c
c
o
rd
i
n
g
to
th
e
c
h
a
ra
c
teristics
o
f
so
lar P
V
c
e
ll
.
K
ey
w
o
r
d
:
So
lar
p
h
o
to
v
o
ltaic
c
ell
E
lectr
ical
c
h
ar
ac
ter
is
tic
s
Self
c
o
n
s
tr
u
c
tin
g
n
eu
r
al
n
et
w
o
r
k
C
u
r
r
en
t
-
v
o
lta
g
e
c
h
ar
ac
ter
is
t
ic
s
P
o
w
er
-
v
o
lta
g
e
c
h
ar
ac
ter
i
s
tics
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
B
am
b
a
n
g
P
u
r
w
a
h
y
u
d
i,
Dep
ar
te
m
en
t o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Un
i
v
er
s
it
y
o
f
B
h
a
y
a
n
g
k
ar
a
Su
r
ab
ay
a,
J
l.
A
.
Yan
i 1
1
4
,
Su
r
ab
a
y
a
6
0
3
2
1
,
I
n
d
o
n
esia
.
E
m
ail:
bm
p
_
p
u
r
@
u
b
h
ar
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
So
lar
en
er
g
y
is
a
p
r
o
m
is
i
n
g
alter
n
ati
v
e
en
er
g
y
s
o
u
r
ce
d
u
e
to
en
er
g
y
cr
is
i
s
an
d
en
v
ir
o
n
m
en
tal
is
s
u
e
s
s
u
c
h
as
g
lo
b
al
w
ar
m
in
g
e
f
f
ec
t
an
d
p
o
llu
tio
n
.
P
h
o
to
v
o
lt
aic
(
P
V)
p
o
w
er
g
e
n
er
atio
n
is
o
n
e
o
f
th
e
m
o
r
e
i
m
p
o
r
tan
t
r
en
e
w
ab
le
s
o
u
r
ce
s
s
in
ce
it
h
ad
g
r
ea
t
m
an
y
m
er
it
s
s
u
c
h
as
clea
n
,
f
r
ee
m
ai
n
te
n
an
ce
an
d
n
o
n
o
is
e.
Ho
w
e
v
er
,
P
V
g
e
n
er
atio
n
s
y
s
te
m
h
as t
w
o
d
is
ad
v
a
n
ta
g
es t
h
at
i
s
th
e
lo
w
co
n
v
er
s
io
n
ef
f
icie
n
c
y
i
n
elec
tr
ic
p
o
w
er
g
en
er
atio
n
a
n
d
th
e
ch
a
n
g
es
in
s
ev
er
al
w
ea
th
er
co
n
d
itio
n
s
.
I
n
ad
d
itio
n
,
th
e
elec
tr
ical
c
h
ar
ac
ter
is
tic
o
f
s
o
lar
P
V
ce
ll
is
n
o
n
l
in
ea
r
w
h
ic
h
i
s
af
f
ec
ted
b
y
s
o
lar
r
ad
iatio
n
(
S),
at
m
o
s
p
h
er
e
te
m
p
er
at
u
r
e
(
T
)
a
n
d
s
er
ies
r
e
s
is
ta
n
ce
(R
s
)
.
T
h
e
elec
tr
ical
ch
ar
ac
ter
i
s
tics
o
f
s
o
lar
P
V
ce
ll
co
n
s
is
t
o
f
I
-
V
a
n
d
P
-
V
c
h
ar
ac
ter
is
tic
s
.
So
lar
P
V
ce
ll
is
b
u
ilt f
r
o
m
a
c
u
r
r
en
t
s
o
u
r
ce
p
ar
allel
w
ith
d
io
d
e
(
D)
,
s
h
u
n
t r
esi
s
tan
ce
(
R
sh
)
an
d
s
er
ies r
esi
s
tan
ce
(
R
s
)
[
1
]
-
[
6
]
.
T
h
e
ap
p
licatio
n
s
o
f
ar
tif
icial
i
n
telli
g
e
n
t
in
s
o
lar
P
V
g
en
er
at
io
n
s
y
s
te
m
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
[
6
]
-
[
9
]
.
Neu
r
al
n
et
w
o
r
k
(
NN)
is
o
n
e
o
f
th
e
p
o
p
u
lar
ar
tif
icial
in
te
lli
g
en
ts
.
A
d
v
a
n
ta
g
es
o
f
NN
ar
e
ea
s
y
in
tr
ai
n
in
g
an
d
s
i
m
p
le
ar
ch
itec
tu
r
e.
Ho
w
e
v
er
,
NN
h
as
s
ev
er
al
d
r
a
w
b
ac
k
s
s
u
ch
as
i
n
d
eter
m
in
i
n
g
n
u
m
b
er
h
id
d
en
la
y
er
s
an
d
n
u
m
b
er
n
e
u
r
o
n
s
in
h
id
d
en
la
y
er
[
1
0
]
-
[
1
6
]
.
T
h
ese
m
atter
s
ca
n
b
e
s
o
lv
ed
b
y
s
el
f
co
n
s
tr
u
ct
i
n
g
n
e
u
r
al
n
et
w
o
r
k
(
SC
NN)
.
S
C
NN
ca
n
au
to
m
ati
ca
ll
y
co
n
s
tr
u
ct
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
h
id
d
en
la
y
er
a
n
d
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
[
1
1
]
-
[
1
3
]
.
I
n
th
is
p
ap
er
,
SC
NN
is
u
s
ed
to
cr
ea
te
s
o
lar
P
V
ce
ll
m
o
d
el
.
T
h
is
SC
NN
tech
n
iq
u
e
i
m
p
r
o
v
es
t
h
e
ac
cu
r
ac
y
o
f
elec
tr
ical
ch
ar
ac
ter
is
tic
b
eh
a
v
io
r
o
f
s
o
lar
P
V
ce
ll.
T
h
e
ef
f
ec
ti
v
e
n
es
s
o
f
SC
NN
m
et
h
o
d
is
ev
alu
a
ted
u
s
in
g
s
i
m
u
latio
n
r
esu
lt
s
b
ased
o
n
v
ar
y
i
n
g
s
o
lar
r
ad
iatio
n
,
te
m
p
er
at
u
r
e
an
d
s
er
i
es
r
esis
tan
ce
.
T
h
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
S
C
N
N
B
a
s
ed
E
lectr
ica
l Ch
a
r
a
cteris
tic
s
o
f
S
o
la
r
P
h
o
to
vo
lta
i
c
C
ell
Mo
d
el
(
B
a
mb
a
n
g
P
u
r
w
a
h
yu
d
i)
3199
p
ap
er
is
o
r
g
an
ized
as f
o
llo
w
s
:
th
e
s
o
lar
P
V
ce
ll
m
o
d
el
is
d
e
s
cr
ib
ed
in
Sectio
n
2
; Sec
tio
n
3
s
h
o
w
s
th
e
p
r
in
c
ip
al
o
f
SC
NN;
Sec
tio
n
4
s
h
o
w
s
th
e
d
esig
n
o
f
SC
N
N
s
o
lar
P
V
ce
l
l
m
o
d
el;
t
h
e
ef
f
ec
t
iv
e
n
es
s
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
m
et
h
o
d
is
clar
if
ied
th
r
o
u
g
h
a
MA
T
L
A
B
/
SIM
U
L
I
NK
s
i
m
u
latio
n
w
h
ic
h
i
s
p
r
esen
ted
in
Sectio
n
5
;
th
e
co
n
clu
s
io
n
,
an
d
r
ef
er
e
n
ce
s
li
s
t
en
d
th
is
p
ap
er
.
2.
SO
L
AR
P
H
O
T
O
VO
L
T
A
I
C
CE
L
L
M
O
DE
L
T
h
e
m
ain
co
m
p
o
n
e
n
t
o
f
s
o
lar
p
o
w
er
g
e
n
er
atio
n
s
y
s
te
m
s
is
p
h
o
to
v
o
ltaic
(
P
V)
.
P
V
ce
ll
o
r
k
n
o
w
n
a
s
th
e
s
o
lar
p
an
els
ar
e
m
ad
e
f
r
o
m
s
e
m
ico
n
d
u
cto
r
m
ater
ial
s
s
u
ch
as
s
i
lico
n
a
n
d
g
er
m
a
n
i
u
m
.
W
h
en
t
h
e
s
u
n
li
g
h
t
r
ea
ch
es
t
h
e
P
V
ce
ll,
t
h
e
s
ilic
o
n
ato
m
w
ill
r
elea
s
e
elec
tr
o
n
s
.
T
h
e
elec
tr
o
n
s
w
il
l
f
lo
w
m
ak
in
g
t
h
e
elec
tr
ic
cir
cu
it,
s
o
t
h
at
elec
tr
ical
e
n
er
g
y
ca
n
b
e
g
e
n
er
ated
.
T
h
is
P
V
ce
ll
ca
n
b
e
co
n
n
ec
ted
in
s
er
ies
o
r
p
ar
allel
to
p
r
o
d
u
ce
th
e
d
esire
d
v
o
ltag
e
an
d
cu
r
r
en
t
.
T
h
e
p
er
f
o
r
m
a
n
ce
s
o
f
t
h
e
P
V
c
ell
d
ep
en
d
o
n
t
h
e
i
n
te
n
s
it
y
o
f
t
h
e
s
u
n
li
g
h
t.
W
ea
th
er
co
n
d
itio
n
s
s
u
c
h
a
s
clo
u
d
s
an
d
f
o
g
a
f
f
ec
t
s
o
lar
e
n
er
g
y
r
ec
ei
v
ed
b
y
P
V
ce
ll,
s
o
t
h
at
t
h
e
y
w
ill
i
n
f
l
u
en
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
P
V
ce
ll.
T
h
e
s
i
m
p
le
eq
u
i
v
alen
t
ci
r
cu
it
o
f
s
o
lar
P
V
ce
ll
is
a
cu
r
r
en
t
s
o
u
r
ce
p
ar
allel
w
it
h
a
d
io
d
e.
So
lar
ce
ll
m
o
d
el
is
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
s
o
lar
P
V
ce
ll
m
o
d
el
co
n
s
i
s
ts
o
f
a
cu
r
r
en
t
s
o
u
r
ce
(
I
ph
)
,
a
d
io
d
e
(
D)
,
a
s
h
u
n
t
r
esis
ta
n
ce
(
R
sh
)
,
an
d
a
s
er
ies r
esis
ta
n
ce
(
R
s
)
[1
]
-
[
6]
.
R
s
R
s
h
D
I
p
h
I
p
v
V
p
v
I
D
I
R
s
h
Fig
u
r
e
1
.
E
q
u
iv
ale
n
t c
ir
cu
it o
f
s
o
lar
P
V
ce
ll
Dio
d
e
d
eter
m
i
n
es t
h
e
I
-
V
ch
ar
ac
ter
is
tics
o
f
P
V
ce
ll.
C
u
r
r
en
t
s
o
u
r
ce
o
u
tp
u
t
is
p
r
o
p
o
r
tio
n
al
to
th
e
lig
h
t
f
alli
n
g
o
n
t
h
e
P
V
ce
ll.
Op
en
ci
r
cu
it v
o
lta
g
e
i
n
cr
ea
s
es
as t
h
e
l
o
g
ar
ith
m
ac
co
r
d
in
g
S
h
o
ck
le
y
d
io
d
e
eq
u
atio
n
th
at
d
escr
ib
es
th
e
i
n
ter
d
ep
en
d
en
c
e
b
et
w
ee
n
th
e
v
o
lta
g
e
an
d
c
u
r
r
en
t
i
n
P
V
ce
ll
as
s
h
o
w
n
i
n
eq
u
atio
n
(
1
)
an
d
eq
u
atio
n
(
2
)
.
1
/
0
kT
qU
PV
e
I
I
I
(
1
)
O
PV
I
I
I
q
kT
V
1
ln
(
2
)
w
h
er
e
k
,
T
,
q
,
V
,
I
0
an
d
I
PV
ar
e
r
esp
ec
tiv
el
y
B
o
ltz
m
a
n
co
n
s
ta
n
t (
1
.
3
8
0
6
x
1
0
-
23
J
/K)
,
tem
p
er
atu
r
e
(
0
K)
,
elec
tr
o
n
ch
ar
g
e
(1
.
6
0
2
1
x
1
0
-
19
C
)
,
th
e
P
V
ce
ll
ter
m
i
n
al
v
o
lta
g
e
,
th
e
r
ev
er
s
e
s
at
u
r
atio
n
cu
r
r
en
t
an
d
th
e
li
g
h
t
g
en
er
ated
cu
r
r
en
t.
Fro
m
eq
u
atio
n
(
1
)
an
d
eq
u
atio
n
(
2
)
ca
n
b
e
d
eter
m
i
n
ed
th
e
ch
ar
ac
ter
is
tics
o
f
t
h
e
s
o
lar
p
an
el.
T
h
at
is
th
e
I
-
V
c
h
ar
ac
ter
is
tic
s
an
d
th
e
P
-
V
ch
ar
ac
ter
is
tics
.
T
h
ese
ch
ar
ac
ter
is
tic
s
o
f
th
e
P
V
ce
ll
ar
e
n
o
n
-
li
n
ea
r
an
d
m
o
r
e
i
n
f
lu
e
n
ce
d
b
y
t
h
e
in
te
n
s
i
t
y
o
f
s
o
lar
r
ad
iatio
n
an
d
te
m
p
e
r
atu
r
e
o
f
P
V
ce
ll su
r
f
ac
e
[1
]
-
[
6
]
.
3.
P
RINCI
P
A
L
O
F
SE
L
F
CO
NST
RU
CT
I
N
G
NE
URAL N
E
T
WO
RK
A
r
ti
f
icial
n
eu
r
al
n
e
t
w
o
r
k
(
ANN)
is
a
m
ac
h
i
n
e
th
at
th
e
wo
r
k
p
r
in
cip
le
em
u
late
s
th
e
h
u
m
an
b
r
ain
.
A
N
N
h
a
s
th
e
ab
il
ities
o
f
lear
n
in
g
a
n
d
g
e
n
er
aliza
tio
n
.
Stru
ctu
r
e
o
f
A
N
N
co
n
s
i
s
t
s
o
f
t
h
r
ee
la
y
er
s
,
an
in
p
u
t
la
y
er
,
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
er
s
,
an
d
an
o
u
tp
u
t
la
y
er
.
Desi
g
n
o
f
A
NN
i
s
co
n
d
u
cted
in
t
wo
s
tep
s
.
First
s
tep
is
d
eter
m
in
i
n
g
o
f
its
s
tr
u
ctu
r
e
c
o
n
s
is
t
o
f
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
h
id
d
en
la
y
er
s
an
d
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
.
Seco
n
d
s
tep
is
d
eter
m
i
n
in
g
o
f
th
e
d
esire
d
e
r
r
o
r
v
al
u
e
an
d
m
a
x
i
m
u
m
lear
n
i
n
g
ep
o
ch
.
Dete
r
m
i
n
in
g
o
f
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
th
e
h
id
d
en
la
y
er
an
d
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
is
g
en
er
all
y
d
o
n
e
tr
ial
an
d
er
r
o
r
[
1
0
]
-
[
1
6
]
.
T
h
e
d
is
ad
v
an
ta
g
es
o
f
ANN
ca
n
b
e
s
o
l
v
ed
b
y
Self
C
o
n
s
tr
u
cti
n
g
Ne
u
r
al
Net
w
o
r
k
(
SC
NN)
m
et
h
o
d
.
B
asic
s
tr
u
ct
u
r
e
o
f
s
elf
co
n
s
tr
u
ctin
g
n
e
u
r
al
n
et
w
o
r
k
(
S
C
NN)
is
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
(
ANN)
.
T
h
e
d
if
f
er
e
n
t
b
et
w
ee
n
b
o
th
m
et
h
o
d
s
is
in
d
eter
m
in
i
n
g
th
e
s
tr
u
ct
u
r
es.
SC
NN
ca
n
a
u
to
m
atica
ll
y
ar
r
an
g
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
i
n
h
id
d
en
la
y
er
an
d
n
u
m
b
er
o
f
h
id
d
en
la
y
er
.
Str
u
ct
u
r
e
o
f
SC
NN
i
s
s
h
o
w
n
i
n
Fi
g
u
r
e
2
[
1
1
]
-
[
1
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
:
3
1
9
8
–
3
2
0
6
3200
I
n
p
u
t
L
a
y
e
r
H
i
d
d
e
n
L
a
y
e
r
O
u
t
p
u
t
L
a
y
e
r
…
…
…
…
…
…
…
.
.
.
…
.
.
.
I
n
p
u
t
1
I
n
p
u
t
2
O
u
t
p
u
t
Fig
u
r
e
2
.
Stru
ct
u
r
e
o
f
SC
N
N
T
h
e
d
eter
m
i
n
i
n
g
p
r
o
ce
s
s
o
f
S
C
NN
s
tr
u
ct
u
r
e
ca
n
b
e
d
escr
ib
ed
u
s
i
n
g
f
lo
w
c
h
ar
t
s
h
o
w
n
i
n
Fig
u
r
e
3
.
T
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
i
n
h
id
d
en
la
y
er
s
w
ill a
u
to
m
atica
ll
y
i
n
cr
ea
s
e
w
h
e
n
er
r
o
r
is
g
r
ea
ter
th
an
m
ax
i
m
u
m
er
r
o
r
.
An
d
also
,
t
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
w
il
l
i
n
cr
ea
s
e
w
h
e
n
m
ax
i
m
u
m
er
r
o
r
is
s
m
aller
th
an
er
r
o
r
an
d
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
h
id
d
en
l
a
y
er
is
s
m
aller
t
h
an
m
a
x
i
m
u
m
n
eu
r
o
n
s
.
S
t
a
r
t
S
C
N
N
p
a
r
a
m
e
t
e
r
s
m
a
x
n
e
u
,
m
a
x
h
i
d
,
m
a
x
e
r
r
n
e
u
=
n
e
u
+
1
t
r
a
i
n
i
n
g
p
r
o
c
e
s
s
o
f
S
C
N
N
e
r
r
<
m
a
x
e
r
r
n
e
u
=
m
a
x
n
e
u
h
i
d
=
m
a
x
h
i
d
h
i
d
=
h
i
d
+
1
n
e
u
=
1
s
a
v
e
t
r
a
i
n
i
n
g
r
e
s
u
l
t
S
t
o
p
T
T
T
Y
Y
Y
Fig
u
r
e
3
.
Flo
w
c
h
ar
t
o
f
S
C
NN
p
r
o
ce
s
s
4.
D
E
S
I
G
N
O
F
SCNN
P
H
O
T
O
VO
L
T
A
I
C
(
P
V)
CE
L
L
M
O
DE
L
SC
NN
s
o
lar
P
V
m
o
d
el
i
s
d
e
s
ig
n
ed
to
i
m
itate
elec
tr
ical
c
h
ar
ac
ter
is
tic
b
eh
a
v
io
r
o
f
s
o
la
r
P
V
ce
ll.
SC
NN
s
o
lar
P
V
m
o
d
el
is
s
h
o
w
n
i
n
Fi
g
u
r
e
4
.
SC
NN
s
o
lar
P
V
m
o
d
el
h
a
v
e
t
h
r
ee
i
n
p
u
t
s
a
n
d
t
w
o
o
u
tp
u
ts
s
u
c
h
as
s
o
lar
r
ad
iatio
n
(
S),
ce
ll
t
e
m
p
er
atu
r
e
(
T
)
,
s
er
ies
r
esi
s
t
o
r
(
R
s
)
,
ce
ll
c
u
r
r
en
t
(
I
pv
)
a
n
d
ce
ll
p
o
w
er
(
P
pv
)
,
r
esp
ec
tiv
el
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
S
C
N
N
B
a
s
ed
E
lectr
ica
l Ch
a
r
a
cteris
tic
s
o
f
S
o
la
r
P
h
o
to
vo
lta
i
c
C
ell
Mo
d
el
(
B
a
mb
a
n
g
P
u
r
w
a
h
yu
d
i)
3201
P
V
M
o
d
e
l
w
i
t
h
S
C
N
N
I
p
v
*
T
S
R
S
P
p
v
*
Fig
u
r
e
4
.
SC
NN
s
o
lar
P
V
m
o
d
el
SC
NN
s
o
lar
P
V
m
o
d
el
i
s
b
ase
d
o
n
i
n
p
u
t
an
d
o
u
tp
u
t
v
al
u
es
o
f
m
at
h
e
m
a
tical
m
o
d
el
o
f
s
o
l
ar
P
V
ce
ll.
T
h
is
SC
N
N
s
o
lar
P
V
m
o
d
el
m
u
s
t
b
e
tr
ai
n
ed
b
ef
o
r
e
b
ein
g
u
s
ed
as
s
o
lar
P
V
m
o
d
el.
T
h
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
o
f
SC
NN
m
et
h
o
d
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
5
.
T
r
ain
in
g
al
g
o
r
ith
m
o
f
SC
N
N
s
o
lar
P
V
ce
ll
m
o
d
el
u
s
es
b
ac
k
p
r
o
p
ag
atio
n
.
Data
tr
ain
i
n
g
o
f
S
C
NN
is
ta
k
e
n
f
r
o
m
m
at
h
e
m
atica
l
m
o
d
el
o
f
s
o
lar
P
V
ce
ll.
P
V
M
o
d
e
l
S
C
N
N
+
-
+
-
B
a
c
k
p
r
o
p
a
g
a
t
i
o
n
I
p
v
P
p
v
I
p
v
*
P
p
v
*
e
I
e
P
T
S
R
S
Fig
u
r
e
5
.
T
r
ain
in
g
p
r
o
ce
s
s
o
f
SC
NN
s
o
lar
P
V
ce
ll
5.
S
I
M
UL
AT
I
O
N
R
E
S
UL
T
A
ND
DIS
C
USS
I
O
N
T
h
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
P
V
ce
ll
m
o
d
el
is
test
ed
b
y
a
SIM
U
L
I
NK/
MA
T
L
A
B
s
i
m
u
lat
io
n
.
T
h
er
ef
o
r
e,
SC
NN
P
V
ce
ll
m
o
d
el
is
co
m
p
ar
ed
w
it
h
t
h
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
P
V
m
o
d
el
b
ased
o
n
ch
an
g
e
o
f
o
p
er
atin
g
co
n
d
it
io
n
s
s
u
ch
as
s
o
lar
r
ad
iatio
n
(
S
)
,
tem
p
er
atu
r
e
(
T
)
an
d
s
er
ies
r
esis
ta
n
ce
(
R
S
)
.
T
h
e
p
ar
am
eter
s
o
f
s
o
lar
P
V
ce
ll
a
n
d
t
h
e
p
ar
a
m
eter
s
o
f
S
C
NN
e
m
p
lo
y
ed
i
n
s
i
m
u
latio
n
ar
e
s
h
o
w
n
i
n
T
ab
le
1
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
T
ab
le
1
.
E
lectr
ical
s
p
ec
if
icatio
n
o
f
t
h
e
s
o
lar
P
V
m
o
d
u
le
P
a
r
a
me
t
e
r
V
a
l
u
e
M
a
x
i
m
u
m
P
o
w
e
r
(
P
PV
)
6
0
W
V
o
l
t
a
g
e
a
t
M
a
x
.
P
o
w
e
r
(
V
MP
)
1
7
.
1
V
C
u
r
r
e
n
t
a
t
M
a
x
.
P
o
w
e
r
(
I
MP
)
3
.
4
A
O
p
e
n
C
i
r
c
u
i
t
V
o
l
t
a
g
e
(
V
O
C
)
2
1
.
1
V
S
h
o
r
t
C
i
r
c
u
i
t
C
u
r
r
e
n
t
(
I
S
C
)
3
.
8
A
T
ab
le
2.
T
h
e
p
ar
am
eter
s
o
f
S
C
NN
P
a
r
a
me
t
e
r
V
a
l
u
e
M
a
x
i
m
u
m
H
i
d
e
n
L
a
y
e
r
s
5
M
a
x
i
m
u
m
N
e
u
r
o
n
s i
n
H
i
d
d
e
n
L
a
y
e
r
20
M
a
x
i
m
u
m
Er
r
o
r
1e
-
4
M
a
x
i
m
u
m
Ep
o
c
h
1
0
0
0
SC
NN
m
u
s
t
b
e
tr
ai
n
ed
b
ef
o
r
e
b
ein
g
u
s
ed
a
s
s
o
lar
P
V
ce
l
l
m
o
d
el.
T
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
p
r
o
v
id
es
t
h
e
o
p
tim
a
l
s
tr
u
ct
u
r
e
o
f
SC
NN.
T
h
e
tr
ain
in
g
r
es
u
lt
s
o
f
S
C
NN
s
o
lar
P
V
m
o
d
el
f
o
r
I
-
V
c
h
ar
ac
ter
is
tics
a
n
d
P
-
V
ch
ar
ac
ter
is
tic
s
ar
e
s
h
o
w
n
i
n
T
ab
le
3
.
T
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
S
C
NN
d
u
r
i
n
g
t
h
e
tr
ain
i
n
g
p
r
o
c
ess
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
6
an
d
Fig
u
r
e
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
:
3
1
9
8
–
3
2
0
6
3202
T
ab
le
3
.
T
h
e
tr
ain
in
g
r
esu
lt
s
o
f
S
C
NN
s
o
lar
P
V
m
o
d
el
P
a
r
a
me
t
e
r
I
-
V
C
h
a
r
a
c
t
e
r
i
s
t
i
c
P
-
V
C
h
a
r
a
c
t
e
r
i
st
i
c
N
u
mb
e
r
o
f
H
i
d
e
n
L
a
y
e
r
s
1
3
N
u
mb
e
r
o
f
N
e
u
r
o
n
s
i
n
H
i
d
d
e
n
L
a
y
e
r
9
13
Ep
o
c
h
s
2
1
5
2
4
6
Fig
u
r
e
6
.
P
er
f
o
r
m
a
n
ce
o
f
S
C
N
N
s
o
lar
P
V
m
o
d
el
f
o
r
th
e
I
-
V
c
h
ar
ac
ter
is
tic
s
Fig
u
r
e
7
.
P
er
f
o
r
m
a
n
ce
o
f
S
C
N
N
s
o
lar
P
V
m
o
d
el
f
o
r
th
e
P
-
V
c
h
ar
ac
ter
is
tic
s
5
.
1
.
I
nfluence
s
o
f
So
la
r
Ra
dia
t
io
n Va
ria
t
io
n
T
h
e
v
ar
iatio
n
s
o
f
s
o
lar
r
ad
iatio
n
in
s
i
m
u
latio
n
p
r
o
ce
s
s
ar
e
1
k
W
/m
2
,
0
.
8
k
W
/
m
2
,
0
.
6
k
W
/
m
2
,
0
.
4
k
W
/
m
2
an
d
0
.
2
k
W
/
m
2
,
r
esp
e
ctiv
el
y
.
Fi
g
u
r
e
8
s
h
o
w
th
e
I
-
V
ch
ar
ac
ter
is
t
ic
s
f
o
r
v
ar
iatio
n
o
f
s
o
lar
r
ad
iatio
n
s
.
T
h
e
s
i
m
u
la
tio
n
r
esu
lts
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
m
o
d
el
an
d
th
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
th
e
s
o
lar
P
V
ce
ll
ar
e
s
h
o
w
n
b
y
t
h
e
cir
cu
lar
(
o
)
an
d
s
o
lid
lin
e.
Fro
m
F
ig
u
r
e
8
ca
n
b
e
s
ee
n
th
at
s
h
o
r
t
cir
cu
it
cu
r
r
e
n
t
an
d
o
p
en
cir
cu
it
v
o
ltag
e
o
f
s
o
lar
p
h
o
to
v
o
ltaic
c
ell
w
i
ll in
cr
ea
s
e
w
h
e
n
s
o
lar
r
ad
iatio
n
in
cr
ea
s
e.
Fig
u
r
e
9
s
h
o
w
P
-
V
c
h
ar
ac
ter
is
tic
s
f
o
r
s
o
lar
r
ad
iatio
n
v
ar
i
atio
n
.
T
h
e
s
i
m
u
latio
n
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
m
o
d
el
a
n
d
th
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
th
e
s
o
lar
P
V
ce
ll
ar
e
s
h
o
w
n
b
y
t
h
e
cir
cu
lar
(
o
)
an
d
s
o
lid
lin
e.
Fig
u
r
e
9
s
h
o
w
t
h
a
t
m
a
x
i
m
u
m
p
o
w
er
an
d
o
p
en
cir
cu
i
t
v
o
lta
g
e
o
f
s
o
lar
p
h
o
to
v
o
lta
ic
ce
ll
w
il
l
i
n
cr
ea
s
e
w
h
e
n
s
o
lar
r
ad
iatio
n
in
cr
ea
s
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
S
C
N
N
B
a
s
ed
E
lectr
ica
l Ch
a
r
a
cteris
tic
s
o
f
S
o
la
r
P
h
o
to
vo
lta
i
c
C
ell
Mo
d
el
(
B
a
mb
a
n
g
P
u
r
w
a
h
yu
d
i)
3203
Fig
u
r
e
8
.
T
h
e
I
-
V
ch
ar
ac
ter
is
ti
c
s
f
o
r
v
ar
iatio
n
o
f
s
o
lar
r
ad
iatio
n
Fig
u
r
e
9
.
T
h
e
P
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
s
o
lar
r
ad
iatio
n
5
.
2
.
I
nfluence
s
o
f
T
e
m
pera
t
ure
Va
ria
t
io
n
T
h
e
te
m
p
er
atu
r
e
v
ar
iatio
n
s
ar
e
r
esp
ec
tiv
el
y
0
0
C
,
2
5
0
C
,
5
0
0
C
,
7
5
0
C
a
n
d
1
0
0
0
C
.
Fig
u
r
e
10
s
h
o
w
I
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
te
m
p
er
at
u
r
e.
T
h
e
s
i
m
u
l
atio
n
o
f
t
h
e
p
r
o
p
o
s
ed
SC
N
N
m
o
d
el
a
n
d
t
h
e
m
at
h
e
m
a
tical
m
o
d
el
o
f
t
h
e
s
o
lar
P
V
ce
ll
a
r
e
s
h
o
w
n
b
y
th
e
ci
r
cu
lar
(
o
)
an
d
s
o
lid
lin
e.
Sh
o
r
t
cir
cu
it
cu
r
r
en
t
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
w
i
ll
i
n
cr
ea
s
e
w
h
e
n
ce
ll
te
m
p
er
atu
r
e
in
cr
ea
s
e.
Ho
w
e
v
er
,
o
p
en
cir
cu
it
v
o
l
tag
e
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
w
ill d
ec
r
ea
s
e
w
h
en
te
m
p
er
atu
r
e
i
n
cr
ea
s
e.
Fig
u
r
e
10
.
T
h
e
I
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
ce
ll te
m
p
e
r
atu
r
e
0
4
8
12
16
20
24
0
1
2
3
4
5
V
p
v
(
V
)
I
p
v(
A
)
1
k
W
/
m2
0
.
8
k
W
/
m2
0
.
6
k
W
/
m2
0
.
4
k
W
/
m2
0
.
2
k
W
/
m2
0
5
10
15
20
0
10
20
30
40
50
60
70
V
p
v
(
V
)
P
p
v(
W
)
0
.
6
k
W
/
m2
0
.
4
k
W
/
m2
0
.
2
k
W
/
m2
0
.
8
k
W
/
m2
1
k
W
/
m2
0
4
8
12
16
20
24
0
1
2
3
4
5
V
p
v
(
V
)
I
p
v(
A
)
100deC
50deC
25deC
0deC
75deC
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
:
3
1
9
8
–
3
2
0
6
3204
Fig
u
r
e
11
s
h
o
w
th
e
P
-
V
c
h
a
r
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
c
ell
te
m
p
er
at
u
r
e.
T
h
e
s
i
m
u
la
ti
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
m
o
d
el
an
d
th
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
t
h
e
s
o
lar
P
V
ce
ll
a
r
e
s
h
o
w
n
b
y
t
h
e
cir
cu
lar
(
o
)
an
d
s
o
lid
lin
e.
Ma
x
i
m
u
m
p
o
w
er
an
d
o
p
en
cir
cu
it
v
o
ltag
e
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
w
ill
d
ec
r
ea
s
e
w
h
e
n
te
m
p
er
atu
r
e
i
n
cr
ea
s
e.
Fig
u
r
e
11
.
T
h
e
P
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
ce
l
l te
m
p
er
atu
r
e
5
.
3
.
I
nfluence
s
o
f
Series R
esi
s
t
a
n
ce
Va
ria
t
io
n
I
n
th
e
s
i
m
u
latio
n
,
th
e
c
h
a
n
g
e
s
o
f
s
er
ies
r
esi
s
ta
n
ce
ar
e
0
Ω
,
5
m
Ω
,
1
0
m
Ω
,
1
5
m
Ω
a
n
d
2
0
m
Ω
,
r
esp
ec
tiv
el
y
.
Fi
g
u
r
e
1
2
s
h
o
w
th
e
I
-
V
c
h
ar
ac
ter
is
t
ic
s
f
o
r
v
ar
iatio
n
o
f
s
er
ies
r
esis
to
r
.
T
h
e
s
i
m
u
latio
n
o
f
t
h
e
p
r
o
p
o
s
ed
SC
NN
m
o
d
el
an
d
th
e
m
at
h
e
m
atica
l
m
o
d
el
o
f
t
h
e
s
o
lar
P
V
ce
ll
a
r
e
s
h
o
w
n
b
y
th
e
cir
cu
lar
(
o
)
an
d
s
o
lid
lin
e.
Sh
o
r
t
cir
cu
it
c
u
r
r
en
t
an
d
o
p
en
cir
cu
it
v
o
ltag
e
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
w
ill
n
o
t
ch
an
g
e
w
h
e
n
t
h
er
e
ar
e
v
ar
iatio
n
o
f
s
er
ies
r
esi
s
t
o
r
.
T
h
e
v
ar
iatio
n
o
f
s
er
ies
r
esis
ta
n
ce
ca
u
s
es
t
h
e
s
lo
p
e
an
g
le
o
f
t
h
e
I
-
V
ch
ar
ac
ter
is
tic
s
.
Fig
u
r
e
1
2
.
T
h
e
I
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
s
er
ie
s
r
esi
s
tan
ce
Fig
u
r
e
1
3
s
h
o
w
th
e
P
-
V
c
h
a
r
ac
ter
is
tic
s
f
o
r
ch
an
g
e
o
f
s
er
ies
r
esis
to
r
.
Ma
x
i
m
u
m
p
o
w
e
r
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
w
ill
d
ec
r
ea
s
e
s
er
ies
r
e
s
is
ta
n
ce
in
cr
ea
s
e.
Ho
w
e
v
er
,
o
p
en
cir
c
u
it
v
o
lta
g
e
o
f
s
o
lar
p
h
o
to
v
o
ltai
c
ce
ll st
il
l c
o
n
s
ta
n
t.
0
4
8
12
16
20
24
0
10
20
30
40
50
60
70
V
p
v
(
V
)
P
p
v(
W
)
0degC
25degC
75degC
50degC
100degC
0
4
8
12
16
20
24
0
1
2
3
4
5
V
p
v
(
V
)
I
p
v(
A
)
0
.
0
2
0
0
.
0
1
5
0
.
0
0
5
0
0
.
0
1
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
S
C
N
N
B
a
s
ed
E
lectr
ica
l Ch
a
r
a
cteris
tic
s
o
f
S
o
la
r
P
h
o
to
vo
lta
i
c
C
ell
Mo
d
el
(
B
a
mb
a
n
g
P
u
r
w
a
h
yu
d
i)
3205
Fig
u
r
e
1
3
.
T
h
e
P
-
V
ch
ar
ac
ter
is
tic
s
f
o
r
v
ar
iatio
n
o
f
s
er
ies r
es
is
tan
ce
6.
CO
NCLU
SI
O
N
Self
co
n
s
tr
u
ct
in
g
n
e
u
r
al
n
et
wo
r
k
(
SC
NN)
b
ased
elec
tr
ical
ch
ar
ac
ter
is
tic
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
m
o
d
el
h
a
s
b
ee
n
p
r
ese
n
ted
a
n
d
d
is
cu
s
s
ed
.
S
C
C
N
tec
h
n
iq
u
e
is
u
s
ed
to
i
m
p
r
o
v
e
ac
cu
r
atel
y
t
h
e
elec
tr
ical
ch
ar
ac
ter
is
tic
o
f
s
o
lar
p
h
o
to
v
o
ltaic
ce
ll
m
o
d
el.
T
h
e
e
f
f
ec
tiv
e
n
ess
o
f
SC
C
N
tech
n
iq
u
e
i
s
clar
i
f
ied
b
y
s
i
m
u
lat
io
n
an
d
co
m
p
ar
ed
w
it
h
m
ate
m
atica
l
m
o
d
el
o
f
s
o
lar
P
V
m
o
d
el
.
Si
m
u
la
tio
n
is
d
o
n
e
b
y
th
e
ch
a
n
g
e
o
f
o
p
er
atin
g
co
n
d
itio
n
s
s
u
c
h
as
th
e
s
o
lar
r
ad
iatio
n
(
S),
te
m
p
e
r
atu
r
e
(
T
)
an
d
s
er
ies
r
esis
tan
ce
(
R
s
)
.
Si
m
u
latio
n
r
esu
lt
s
s
h
o
w
t
h
at
S
C
NN
s
o
lar
PV
ce
ll
m
o
d
el
ca
n
p
r
o
d
u
ce
th
e
I
-
V
an
d
P
-
V
c
h
ar
ac
ter
i
s
tic
s
ac
co
r
d
in
g
to
th
e
ch
ar
ac
ter
is
tic
s
o
f
s
o
lar
P
V
ce
ll
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
p
ap
er
is
s
u
p
p
o
r
ted
an
d
f
u
n
d
ed
b
y
Mi
n
i
s
tr
y
o
f
R
e
s
ea
r
ch
,
T
ec
h
n
o
lo
g
y
an
d
Hi
g
h
er
E
d
u
ca
tio
n
R
ep
u
b
lic
o
f
I
n
d
o
n
e
s
ia
t
h
r
o
u
g
h
C
o
o
r
d
in
atio
n
o
f
P
u
b
lic
Hi
g
h
e
r
E
d
u
ca
tio
n
,
R
eg
io
n
VI
I
E
ast J
av
a
in
2
0
1
6
.
RE
F
E
R
E
NC
E
S
[1
]
R.
Ch
e
n
n
i,
e
t
a
l.
,
“
A
De
tailed
M
o
d
e
ll
i
n
g
M
e
th
o
d
f
o
r
P
h
o
to
v
o
lt
a
i
c
Ce
ll
s
,
”
En
e
rg
y
,
El
se
v
i
e
r
,
v
ol
/i
s
su
e
:
32
(
9
)
,
pp
.
1
7
2
4
-
1
7
3
0
,
2
0
0
7
.
[2
]
J.
S
.
Ku
m
a
ri
a
n
d
C.
S
.
Ba
b
u
,
“
M
a
th
e
m
a
ti
c
a
l
M
o
d
e
ll
i
n
g
a
n
d
S
im
u
latio
n
o
f
P
h
o
t
o
v
o
lt
a
ic Ce
ll
u
si
n
g
M
a
tl
a
b
-
S
im
u
li
n
k
En
v
iro
n
m
e
n
t
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
E
lec
trica
l
a
n
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
ol
/
issu
e
:
2
(
1
)
,
pp
.
2
6
-
34
,
2
0
1
2
.
[3
]
J
.
Bik
a
n
e
ria,
e
t
a
l.
,
“
M
o
d
e
li
n
g
a
n
d
sim
u
latio
n
o
f
P
V
c
e
ll
u
sin
g
o
n
e
-
d
io
d
e
m
o
d
e
l,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
fi
c
a
n
d
Res
e
a
rc
h
P
u
b
l
ica
ti
o
n
s
,
v
ol
/i
ss
u
e
:
3
(
10
)
,
p
p
.
1
-
4
,
2
0
1
3
.
[4
]
S
.
S
h
o
n
g
w
e
a
n
d
M
.
Ha
n
if
,
“
Co
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
d
iffere
n
t
sin
g
le
-
d
io
d
e
P
V
m
o
d
e
li
n
g
m
e
th
o
d
s,”
IEE
E
J
o
u
rn
a
l
o
f
P
h
o
t
o
v
o
lt
a
ic
,
v
ol
/
issu
e
:
5
(
3
)
,
p
p
.
9
3
8
-
9
4
6
,
2
0
1
5
.
[5
]
E.
Ba
tze
li
s,
e
t
a
l.
,
“
Dire
c
t
M
P
P
c
a
lcu
latio
n
in
term
s
o
f
th
e
sin
g
le
-
d
io
d
e
P
V
m
o
d
e
l
p
a
ra
m
e
t
e
r,
”
IE
EE
T
ra
n
s
a
c
ti
o
n
o
n
E
n
e
rg
y
Co
n
v
e
rs
io
n
,
v
ol
/i
ss
u
e
:
30
(
1
)
,
p
p
.
2
2
6
-
2
3
6
,
2
0
1
5
.
[6
]
F
.
Bo
n
a
n
n
o
,
e
t
a
l
.
,
“
A
r
a
d
ial
b
a
sis
f
u
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
b
a
se
d
a
p
p
ro
a
c
h
f
o
r
th
e
e
lec
tri
c
a
l
c
h
a
ra
c
teristics
e
sti
m
a
ti
o
n
o
f
a
p
h
o
t
o
v
o
lt
a
ic m
o
d
u
le,”
Ap
p
li
e
d
En
e
rg
y
,
v
o
l.
9
7
,
p
p
.
9
5
6
-
9
6
1
,
2
0
1
2
.
[7
]
N
.
M
o
h
a
m
m
a
d
,
e
t
a
l.
,
“
Im
p
ro
v
e
d
S
o
lar
P
h
o
t
o
v
o
lt
a
ic
A
rra
y
M
o
d
e
l
w
it
h
F
L
C
Ba
se
d
M
a
x
i
m
u
m
P
o
w
e
r
P
o
in
t
T
ra
c
k
in
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
, v
ol
/i
ss
u
e
:
2
(
6
)
,
pp
.
7
1
7
-
7
2
9
,
2
0
1
2
.
[8
]
S
.
Ka
rth
ik
a
,
e
t
a
l
.
,
“
F
u
z
z
y
L
o
g
i
c
Ba
se
d
M
a
x
i
m
u
m
P
o
w
e
r
P
o
i
n
t
T
ra
c
k
in
g
De
sig
n
f
o
r
1
0
k
W
S
o
lar
P
h
o
to
v
o
lt
a
ic
S
y
st
e
m
w
it
h
Di
ff
e
r
e
n
t
M
e
m
b
e
rsh
ip
F
u
n
c
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l,
Co
mp
u
t
e
r,
En
e
rg
e
ti
c
,
El
e
c
tro
n
ic a
n
d
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
ol
/i
ss
u
e
:
8
(
6
)
,
p
p
.
1
0
1
5
-
1
0
1
9
,
2
0
1
4
.
[9
]
A
.
E
.
F
il
a
li
,
e
t
a
l.
,
“
M
o
d
e
li
n
g
a
n
d
sim
u
latio
n
o
f
p
h
o
t
o
v
o
lt
a
ic
s
y
ste
m
e
m
p
lo
y
in
g
p
e
rtu
rb
a
n
d
o
b
se
re
M
P
P
T
a
lg
o
rit
h
m
a
n
d
f
u
z
z
y
lo
g
ic
c
o
n
tro
l
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
Ap
p
li
e
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
J
AT
IT
)
,
v
ol
/
issu
e
:
89
(
2
)
,
p
p
.
4
7
0
-
4
7
5
,
2
0
1
6
.
[1
0
]
B
.
P
u
rw
a
h
y
u
d
i,
e
t
a
l.
,
“
P
e
r
b
a
n
d
i
n
g
a
n
Ne
u
ra
l
Ne
t
w
o
rk
(
NN
)
Ob
s
e
rv
e
r
d
a
n
N
e
u
ra
l
Ne
t
w
o
rk
–
Ge
n
e
ti
c
A
lg
o
rit
h
m
(NN
-
GA
)
Ob
se
rv
e
r
u
n
tu
k
Esti
m
a
si
Ke
c
e
p
a
tan
M
o
to
r
In
d
u
k
si,”
S
e
min
a
r
N
a
sio
n
a
l
Ap
li
k
a
si
T
e
k
n
o
lo
g
i
I
n
fo
rm
a
s
i
2
0
0
5
(
S
NAT
I
2
0
0
5
)
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
,
p
p
.
C
71
-
C
7
7
,
2
0
0
5
.
[1
1
]
H.
C.
L
u
a
n
d
M
.
H.
Ch
a
n
g
,
“
On
li
n
e
S
p
e
e
d
Co
n
tro
l
o
f
P
e
rm
a
n
e
n
t
M
a
g
n
e
t
S
y
n
c
h
ro
n
o
u
s
M
o
to
r
Us
in
g
S
e
lf
Co
n
stru
c
ti
n
g
Re
c
u
rre
n
t
F
u
z
z
y
Ne
u
ra
l
Ne
t
w
o
rk
,
”
Pro
c
e
e
d
in
g
o
f
th
e
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
Cy
b
e
rn
e
ti
c
s,
K
u
n
m
in
g
,
Ch
i
n
a
,
p
p
.
3
8
5
7
-
3
8
6
2
,
2
0
0
8
.
[1
2
]
J.
S
.
L
e
e
,
e
t
a
l.
,
“
S
e
l
f
Or
g
a
n
izin
g
Ne
u
ra
l
N
e
t
w
o
rk
s
b
y
Co
n
stru
c
ti
o
n
a
n
d
P
ru
n
i
n
g
,
”
IEI
CE
T
ra
n
sa
c
ti
o
n
o
n
In
fo
rm
a
t
io
n
&
S
y
ste
m
,
v
ol
/i
ss
u
e
:
E8
7
-
D
(
11
)
,
p
p
.
2
4
8
9
-
2
4
9
8
,
2
0
0
4
.
0
5
10
15
16
20
24
0
10
20
30
40
50
60
70
V
p
v
(
V
)
P
p
v(
W
)
0
0
.
0
0
5
0
.
0
1
0
0
.
0
1
5
0
.
0
2
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
:
3
1
9
8
–
3
2
0
6
3206
[1
3
]
C
.
F
.
Hs
u
,
“
In
telli
g
e
n
t
P
o
siti
o
n
T
ra
c
k
in
g
Co
n
tro
l
f
o
r
L
CM
Driv
e
Us
in
g
S
tab
le
On
li
n
e
S
e
lf
Co
n
stru
c
ti
n
g
Re
c
u
rre
n
t
Ne
u
ra
l
Ne
tw
o
rk
Co
n
tro
ll
e
r
w
it
h
Bo
u
n
d
A
rc
h
it
e
c
tu
re
,
”
Co
n
tro
l
En
g
in
e
e
rin
g
Pra
c
ti
c
e
,
v
o
l
.
1
7
,
p
p
.
7
1
4
-
7
2
2
,
2
0
0
9
.
[1
4
]
B
.
P
u
rw
a
h
y
u
d
i,
e
t
a
l.
,
“
F
e
e
d
-
f
o
r
w
o
rd
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
d
irec
t
to
rq
u
e
c
o
n
tr
o
l
o
f
in
d
u
c
ti
o
n
m
o
to
r
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
Co
mp
u
ti
n
g
,
In
fo
rm
a
ti
o
n
a
n
d
Co
n
tro
l
(
IJ
ICIC
)
,
v
ol
/i
ss
u
e
:
7
(
11
)
,
p
p
.
6
1
3
5
-
6
1
4
5
,
2
0
1
1
.
[1
5
]
B
.
P
u
rw
a
h
y
u
d
i,
e
t
a
l.
,
“
RNN
b
a
se
d
ro
to
r
f
lu
x
a
n
d
sp
e
e
d
e
stim
a
ti
o
n
o
f
in
d
u
c
ti
o
n
m
o
to
r,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Po
we
r E
lec
trin
ics
a
n
d
Dr
ive
S
y
st
e
m (
IJ
PE
DS
)
, v
ol
/i
ss
u
e
:
1
(
1
)
,
pp
.
58
-
64
,
2
0
1
1
.
[1
6
]
B
.
P
u
rw
a
h
y
u
d
i,
e
t
a
l.
,
“
Ne
u
ra
l
n
e
tw
o
rk
tec
h
n
iq
u
e
f
o
r
d
irec
t
to
r
q
u
e
c
o
n
tro
l
o
f
in
d
u
c
ti
o
n
m
o
to
r
u
se
d
i
n
e
lec
tri
c
a
ll
y
d
riv
e
n
m
a
rin
e
p
ro
p
e
ll
e
r,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Aca
d
e
mic
Res
e
a
rc
h
,
v
o
l/
issu
e
:
3
(
5
)
,
p
p
.
3
5
8
-
3
6
4
,
2
0
1
1
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
B
a
m
b
a
n
g
Pu
r
w
a
h
y
u
d
i
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r,
m
a
ste
r
a
n
d
d
o
c
to
r
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r
(IT
S
)
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
,
in
1
9
9
5
,
2
0
0
5
a
n
d
2
0
1
3
re
sp
e
c
ti
v
e
l
y
.
He
h
a
s
jo
in
e
d
Bh
a
y
a
n
g
k
a
ra
Un
iv
e
rsit
y
o
f
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
,
sin
c
e
2
0
0
0
.
His
a
re
a
s
o
f
in
tere
st
a
re
si
m
u
latio
n
a
n
d
d
e
sig
n
o
f
p
o
we
r
e
le
c
tro
n
i
c
s
a
n
d
d
riv
e
s,
p
o
w
e
r
q
u
a
li
ty
,
re
n
e
wa
b
le en
e
rg
y
,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
t
a
p
p
li
c
a
ti
o
n
.
K
u
sp
ija
n
i
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
f
ro
m
B
ra
w
ij
a
y
a
Un
iv
e
rsit
y
,
M
a
lan
g
,
In
d
o
n
e
sia
in
1
9
8
6
a
n
d
M
a
ste
r
d
e
g
re
e
in
tec
h
n
o
lo
g
y
m
a
n
a
g
e
m
e
n
t
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
(IT
S
)
S
u
ra
b
a
y
a
in
2
0
1
0
.
S
h
e
h
a
s
jo
in
e
d
Bh
a
y
a
n
g
k
a
ra
Un
iv
e
rsit
y
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
,
sin
c
e
1
9
8
7
.
He
r
re
se
a
rc
h
in
tere
st
o
n
d
istri
b
u
ti
o
n
p
o
w
e
r
s
y
ste
m
,
p
o
we
r
s
y
ste
m
s
a
n
d
p
o
w
e
r
s
y
ste
m
g
e
n
e
ra
ti
o
n
.
Ahm
a
d
i
re
c
e
i
v
e
d
h
is
b
a
c
h
e
lo
r
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
f
ro
m
Bh
a
y
a
n
g
k
a
ra
Un
iv
e
rsit
y
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
in
2
0
0
0
a
n
d
M
a
ste
r
d
e
g
re
e
in
c
o
n
tro
l
e
n
g
in
e
e
rin
g
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
(IT
S
)
S
u
ra
b
a
y
a
in
2
0
1
4
.
S
h
e
h
a
s
j
o
in
e
d
Bh
a
y
a
n
g
k
a
r
a
U
n
iv
e
rsity
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
,
sin
c
e
2
0
1
6
.
His
re
se
a
rc
h
in
tere
st
a
re
o
n
p
o
w
e
r
e
lec
tro
n
ics
,
in
d
u
s
tri
a
l
c
o
n
tro
l
sy
st
e
m
,
a
rti
f
icia
l
in
telli
g
e
n
t
a
p
p
li
c
a
ti
o
n
,
a
n
d
r
o
b
o
ti
c
.
Evaluation Warning : The document was created with Spire.PDF for Python.