TELK
O
M
N
I
K
A
Te
l
e
c
ommu
n
i
c
at
i
on
,
C
omp
u
ti
n
g
,
El
e
c
t
r
on
i
c
s
an
d
C
on
tr
o
l
V
ol
.
18
,
N
o
.
2
,
A
pri
l
2020
,
p
p.
1089
~
109
4
IS
S
N
:
1693
-
6930
,
a
c
c
r
e
di
t
e
d
F
i
rs
t
G
r
a
de
by
K
e
m
e
n
ri
s
t
e
kdi
k
t
i
,
D
e
c
r
e
e
N
o:
21
/
E
/
K
P
T
/
2
018
D
O
I:
10
.
129
28/
T
E
L
K
O
M
N
IK
A
.
v1
8i
2
.
1481
6
1089
Jou
r
n
al
h
o
m
e
pa
ge
:
ht
t
p:
/
/
j
our
nal
.
uad
.
a
c
.
i
d/
i
nd
e
x
.
php
/
T
E
L
K
O
MNIKA
Sh
o
r
t
-
t
e
r
m
p
h
o
t
o
v
o
l
t
a
i
c
s
p
o
w
e
r
f
o
r
e
c
a
st
i
n
g
u
si
n
g
J
o
r
d
a
n
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
i
n
S
u
r
a
b
a
y
a
A
ji
A
k
b
ar
F
i
r
d
au
s
1
,
R
i
k
y
Tr
i
Y
u
n
a
r
d
i
2
,
Eva
I
n
ai
yah
A
gu
s
ti
n
3
,
T
e
s
a
E
r
an
ti
P
u
t
r
i
4
,
D
i
mas
O
k
k
y
A
ng
g
r
i
aw
an
5
1
,
2
,
3
,
4
D
e
pa
r
t
m
e
nt
o
f
E
ng
i
ne
e
r
i
ng
,
F
a
c
u
l
t
y
of
V
oc
a
t
i
on
a
l
,
U
ni
ve
r
s
i
t
a
s
A
i
r
l
a
ngg
a
S
ur
a
ba
y
a
,
I
ndo
ne
s
i
a
5
P
ol
i
t
e
k
ni
k
E
l
e
k
t
r
oni
ka
N
e
g
e
r
i
S
ur
a
ba
y
a
,
I
ndo
ne
s
i
a
A
r
ti
c
l
e
I
n
fo
A
BS
TR
A
C
T
Ar
t
i
c
l
e
h
i
s
t
or
y
:
Re
c
e
i
v
e
d
J
ul
19
,
20
19
Re
vi
s
e
d
D
e
c
25
,
20
19
A
c
c
e
pt
e
d
F
e
b
1
9
,
202
0
P
hot
o
vo
l
t
a
i
c
(
P
V
)
i
s
a
r
e
ne
w
a
b
l
e
e
l
e
c
t
r
i
c
e
n
e
r
gy
g
e
ne
r
a
t
o
r
t
ha
t
u
t
i
l
i
z
e
s
s
ol
a
r
e
ne
r
gy
.
P
V
i
s
ve
r
y
s
ui
t
a
b
l
e
t
o
b
e
de
ve
l
ope
d
i
n
S
ur
a
ba
y
a
,
I
nd
one
s
i
a
.
B
e
c
a
us
e
I
ndone
s
i
a
i
s
l
oc
a
t
e
d
a
r
ou
nd
t
he
e
qua
t
o
r
w
h
i
c
h
ha
s
2
s
e
a
s
o
ns
,
na
m
e
l
y
t
he
r
a
i
ny
s
e
a
s
o
n
a
nd
t
he
dr
y
s
e
a
s
on
.
T
he
d
r
y
s
e
a
s
o
n
i
n
I
ndon
e
s
i
a
oc
c
ur
s
i
n
A
pr
i
l
t
o
S
e
pt
e
m
be
r
.
T
he
pow
e
r
ge
ne
r
a
t
e
d
by
P
V
i
s
h
i
gh
l
y
de
p
e
nde
n
t
on
t
e
m
pe
r
a
t
u
r
e
a
n
d
s
o
l
a
r
r
a
di
a
t
i
on
.
T
h
e
r
e
f
o
r
e
,
a
c
c
ur
a
t
e
f
o
r
e
c
a
s
t
i
ng
o
f
s
hor
t
-
t
e
r
m
P
V
pow
e
r
i
s
i
m
por
t
a
nt
f
or
s
ys
t
e
m
r
e
l
i
a
b
i
l
i
t
y
a
n
d
l
a
r
g
e
-
s
c
a
l
e
P
V
d
e
ve
l
o
p
m
e
n
t
t
o
ov
e
r
c
o
m
e
t
he
p
ow
e
r
ge
n
e
r
a
t
e
d
by
i
nt
e
r
m
i
t
t
e
n
t
P
V
.
T
h
i
s
p
a
pe
r
p
r
opo
s
e
s
t
he
J
o
r
da
n
r
e
c
u
r
r
e
nt
ne
u
r
a
l
n
e
t
w
o
r
k
(
J
R
N
N
)
t
o
pr
e
d
i
c
t
s
h
or
t
-
t
e
r
m
P
V
pow
e
r
ba
s
e
d
o
n
t
e
m
p
e
r
a
t
u
r
e
a
n
d
s
ol
a
r
r
a
di
a
t
i
o
n.
J
R
N
N
i
s
t
he
de
ve
l
o
pm
e
nt
o
f
a
r
t
i
f
i
c
i
a
l
ne
u
r
a
l
ne
t
w
or
ks
(
A
N
N
)
t
ha
t
ha
v
e
f
e
e
dba
c
k
a
t
e
a
c
h
ou
t
p
ut
of
e
a
c
h
l
a
y
e
r
.
T
h
e
s
a
m
pl
e
s
of
t
e
m
pe
r
a
t
ur
e
a
nd
s
ol
a
r
r
a
di
a
t
i
on
w
e
r
e
o
bt
a
i
ne
d
f
r
o
m
A
pr
i
l
un
t
i
l
S
e
pt
e
m
be
r
i
n
S
ur
a
ba
y
a
.
F
r
o
m
t
he
r
e
s
ul
t
s
o
f
t
he
t
r
a
i
n
i
ng
s
i
m
u
l
a
t
i
o
n,
t
he
m
e
a
n
s
qu
a
r
e
e
r
r
o
r
(
M
S
E
)
a
nd
m
e
a
n
a
bs
o
l
u
t
e
pe
r
c
e
n
t
a
g
e
e
r
r
or
(
M
A
P
E
)
va
l
u
e
s
w
e
r
e
ob
t
a
i
n
e
d
a
t
1.
3311
a
nd
3
4.
8820
,
r
e
s
pe
c
t
i
v
e
l
y.
T
he
r
e
s
ul
t
s
of
t
e
s
t
i
n
g
s
i
m
u
l
a
t
i
o
n,
M
S
E
a
n
d
M
A
P
E
v
a
l
ue
s
w
e
r
e
o
bt
a
i
ne
d
a
t
0.
98
58
a
nd
1
.
3
311
,
w
i
t
h
a
t
i
m
e
of
4
.
591
204
.
T
h
e
f
or
e
c
a
s
t
i
ng
ha
s
m
i
ni
m
i
z
e
d
s
i
gn
i
f
i
c
a
n
t
e
r
r
o
r
s
a
nd
s
hor
t
pr
oc
e
s
s
i
ng
t
i
m
e
s
.
Ke
y
w
or
d
s
:
F
ore
c
a
s
t
i
n
g
J
RN
N
P
hot
ovo
l
t
a
i
c
T
hi
s
i
s
an
op
e
n
ac
c
e
s
s
ar
t
i
c
l
e
u
nde
r
t
he
C
C
B
Y
-
SA
l
i
c
e
n
s
e
.
Cor
r
e
s
pon
di
n
g
Au
t
h
or
:
A
j
i
A
k
ba
r
F
i
rd
a
us
,
D
e
pa
r
t
m
e
nt
of
E
ngi
n
e
e
r
i
ng
,
F
a
c
ul
t
y
of
V
oc
a
t
i
ona
l
,
U
ni
ve
rs
i
t
a
s
A
i
r
l
a
n
gga
S
ura
ba
y
a
,
Ind
one
s
i
a
.
E
m
a
i
l
:
a
a
.
f
i
rda
us
@
vo
ka
s
i
.
un
a
i
r
.
a
c
.
i
d
1.
I
N
TR
O
D
U
C
TI
O
N
In
r
e
ne
w
a
bl
e
e
n
e
rgy
,
P
V
g
e
t
s
a
l
o
t
of
a
t
t
e
n
t
i
o
n
t
o
re
p
l
a
c
e
fos
s
i
l
-
fu
e
l
e
d
pl
a
nt
s
[1
,
2]
.
Be
c
a
us
e
P
V
us
e
s
s
o
l
a
r
e
ne
rgy
t
o
ge
n
e
ra
t
e
e
l
e
c
t
ri
c
a
l
e
n
e
rgy
.
P
V
s
ys
t
e
m
s
ha
v
e
e
n
vi
ron
m
e
nt
a
l
b
e
ne
f
i
t
s
,
a
n
d
ha
v
e
l
ow
m
a
i
nt
e
na
n
c
e
c
os
t
s
[3
]
m
ore
ove
r
P
V
c
a
n
i
n
c
re
a
s
e
t
h
e
r
e
l
i
a
b
i
l
i
t
y
of
t
h
e
e
l
e
c
t
ri
c
pow
e
r
s
ys
t
e
m
[
4].
H
ow
e
v
e
r
,
t
he
i
nv
e
s
t
m
e
n
t
c
os
t
s
of
P
V
a
re
e
xp
e
n
s
i
ve
a
nd
t
he
va
l
ue
of
P
V
pow
e
r
e
ffi
c
i
e
nc
y
i
s
l
ow
.
P
V
pow
e
r
e
ffi
c
i
e
n
c
y
va
l
u
e
s
a
r
e
a
ff
e
c
t
e
d
by
s
ol
a
r
r
a
d
i
a
t
i
on
,
t
e
m
pe
r
a
t
ure
,
a
nd
c
ond
i
t
i
o
ns
of
t
he
P
V
pa
n
e
l
[5
,
6]
.
S
ol
a
r
r
a
d
i
a
t
i
on
a
nd
t
e
m
pe
r
a
t
u
re
c
a
nn
ot
b
e
de
t
e
r
m
i
ne
d
w
i
t
h
c
e
r
t
a
i
nt
y
.
T
he
r
e
for
e
,
P
V
pow
e
r
for
e
c
a
s
t
i
n
g
i
s
ve
ry
ne
c
e
s
s
a
ry
for
pre
di
c
t
i
ng
t
h
e
pow
e
r
g
e
ne
r
a
t
e
d
by
P
V
s
o
t
ha
t
t
h
e
l
oa
d
c
a
n
be
s
uppl
i
e
d
t
o
t
he
m
a
x
i
m
u
m
.
T
he
r
e
a
r
e
s
e
ve
r
a
l
m
e
t
h
ods
for
pr
e
di
c
t
i
ng
s
hort
-
t
e
rm
pow
e
r
s
uc
h
a
s
us
i
ng
A
rt
i
fi
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
rks
(A
N
N
)
[7
,
8],
S
upp
ort
V
e
c
t
o
r
M
a
c
h
i
n
e
(S
V
M)
[9]
w
i
t
h
s
o
l
a
r
ra
di
a
t
i
on
pa
r
a
m
e
t
e
rs
,
t
e
m
pe
r
a
t
ure
,
a
nd
o
t
he
r
e
nvi
r
onm
e
nt
a
l
pa
r
a
m
e
t
e
rs
[10
,
11
].
H
ow
e
v
e
r,
A
N
N
d
oe
s
no
t
ha
v
e
fe
e
db
a
c
k
s
o
t
h
a
t
t
he
out
p
ut
o
f
A
N
N
c
a
n
b
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
1089
-
1094
1090
c
orre
c
t
e
d
a
nd
g
e
t
op
t
i
m
a
l
re
s
u
l
t
s
.
A
s
f
or
S
V
M
,
k
e
rne
l
fun
c
t
i
on
a
nd
l
os
s
f
unc
t
i
o
ns
a
re
di
f
f
i
c
u
l
t
t
o
g
e
t
op
t
i
m
a
l
re
s
ul
t
s
[
12].
T
h
e
re
fore
,
a
c
c
ura
t
e
a
nd
f
a
s
t
P
V
pow
e
r
for
e
c
a
s
t
i
ng
m
e
t
hods
a
r
e
n
e
e
d
e
d
s
o
t
ha
t
i
n
t
e
r
m
i
t
t
e
nt
P
V
pow
e
r
c
a
n
b
e
ove
r
c
o
m
e
.
In
t
h
i
s
pa
pe
r
,
s
hor
t
-
t
e
r
m
P
V
pow
e
r
fo
re
c
a
s
t
i
ng
i
s
c
a
rr
i
e
d
out
us
i
ng
t
he
J
RN
N
m
e
t
ho
d.
J
RN
N
m
e
t
h
od
i
s
t
he
d
e
ve
l
op
m
e
nt
of
t
he
A
N
N
m
e
t
h
od.
J
RN
N
h
a
s
2
s
t
e
ps
,
n
a
m
e
l
y
t
ra
i
ni
n
g
a
nd
t
e
s
t
i
ng
s
t
e
ps
.
T
he
t
ra
i
ni
ng
s
t
e
p
c
ons
i
s
t
s
of
f
orw
a
rd
a
nd
b
a
c
kw
a
rd
ope
r
a
t
i
ons
.
T
h
e
di
f
fe
re
nc
e
b
e
t
w
e
e
n
J
RN
N
a
nd
A
N
N
a
r
e
t
h
e
fe
e
db
a
c
k
out
pu
t
fro
m
e
a
c
h
A
N
N
l
a
ye
r
t
o
t
h
e
c
ont
e
xt
l
a
ye
r
[13]
.
T
h
e
b
a
c
kw
a
rd
o
pe
r
a
t
i
on
w
i
l
l
c
orre
c
t
t
h
e
ou
t
pu
t
of
e
a
c
h
l
a
y
e
r
s
o
t
h
a
t
t
he
e
r
ror
v
a
l
u
e
f
rom
t
h
e
J
RN
N
pre
d
i
c
t
i
on
re
s
ul
t
i
s
s
m
a
l
l
e
r.
T
h
e
p
a
r
a
m
e
t
e
rs
us
e
d
i
n
t
h
i
s
s
hort
-
t
e
rm
P
V
pow
e
r
for
e
c
a
s
t
i
ng
a
re
t
e
m
p
e
ra
t
ure
a
nd
s
ol
a
r
r
a
di
a
t
i
on
fro
m
A
p
ri
l
unt
i
l
S
e
pt
e
m
be
r
i
n
S
u
r
a
b
a
ya
Indone
s
i
a
.
In
ge
ne
r
a
l
,
t
h
e
t
e
m
p
e
r
a
t
ur
e
a
n
d
s
o
l
a
r
r
a
d
i
a
t
i
on
d
a
t
a
s
us
e
d
a
r
e
da
t
a
i
n
t
h
e
dry
s
e
a
s
on
t
ha
t
oc
c
urs
for
s
i
x
m
ont
hs
.
2.
R
ES
EA
R
C
H
M
ET
H
O
D
2.
1
.
P
V
m
od
e
l
In
t
hi
s
c
a
s
e
,
t
he
P
V
m
odul
e
us
e
d
ha
s
c
ha
r
a
c
t
e
ri
s
t
i
c
s
s
uc
h
a
s
F
i
gure
1
a
nd
F
i
gur
e
2.
M
a
t
h
e
m
a
t
i
c
a
l
l
y
,
t
he
c
urre
n
t
a
nd
v
ol
t
a
g
e
c
ha
ra
c
t
e
ri
s
t
i
c
s
ge
ne
r
a
t
e
d
fro
m
a
s
ol
a
r
c
e
l
l
w
i
t
h
i
d
e
a
l
c
ond
i
t
i
ons
(t
e
m
p
e
r
a
t
ur
e
25
o
C
a
nd
i
r
ra
d
i
a
n
c
e
1
000
W
/m
2
)
a
re
l
i
k
e
(
1
)
[
14].
T
hus
,
for
a
P
V
pa
ne
l
t
h
a
t
pr
a
c
t
i
c
a
l
l
y
c
ons
i
s
t
s
o
f
va
r
i
ous
c
om
p
one
n
t
s
[
15],
t
he
c
u
rre
n
t
a
nd
vo
l
t
a
ge
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
g
e
ne
ra
t
e
d
m
a
t
h
e
m
a
t
i
c
a
l
l
y
a
re
l
i
ke
(
2
)
:
=
−
0
[
{
(
+
.
)
.
.
}
−
1
]
−
+
.
(1)
=
.
−
.
0
[
{
(
+
.
)
.
.
.
}
]
−
.
+
.
(2)
w
he
re
,
I
=
ou
t
pu
t
c
urr
e
nt
(a
m
p
e
re
)
I
L
=
t
he
c
u
rre
n
t
produ
c
e
d
by
pho
t
ovo
l
t
a
i
c
s
(
a
m
p
e
r
e
)
I
0
=
r
e
ve
rs
e
s
a
t
ur
a
t
i
on
c
u
rre
n
t
(
a
m
pe
r
e
)
q
=
e
l
e
m
e
nt
l
o
a
d
,
1
.
6
*
10
-
23
C
V
=
vo
l
t
a
ge
b
e
t
w
e
e
n
ou
t
put
t
e
r
m
i
n
a
l
s
(vol
t
)
R
S
=
s
e
ri
e
s
re
s
i
s
t
a
nc
e
(o
hm
)
n
=
i
de
a
l
di
o
de
fa
c
t
o
r
(r
a
ng
e
1
-
1.
75)
K
=
Bo
l
t
z
m
a
nn
c
ons
t
a
nt
,
1
.
38
*
10
-
19
J
/K
T
=
a
bs
ol
u
t
e
t
e
m
pe
r
a
t
ur
e
R
SH
=
r
e
s
i
s
t
a
nc
e
s
h
unt
(oh
m
)
N
P
=
t
he
nu
m
be
r
of
pho
t
ovo
l
t
a
i
c
s
c
onn
e
c
t
e
d
i
n
p
a
ra
l
l
e
l
N
S
=
t
he
nu
m
be
r
of
pho
t
ovo
l
t
a
i
c
s
c
onn
e
c
t
e
d
i
n
s
e
r
i
e
s
F
i
gure
1
.
I
-
V
P
V
c
ha
ra
c
t
e
ri
s
t
i
c
s
[16]
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
Shor
t
-
t
e
r
m
ph
ot
o
v
ol
t
ai
c
s
p
owe
r
f
or
e
c
as
t
i
ng
us
i
ng
J
or
dan…
(
A
j
i
A
k
bar
F
i
r
daus
)
1091
F
i
gure
2
.
P
-
V
P
V
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
[
16]
2.
2
.
Jo
r
d
an
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
tw
or
k
(JR
N
N
)
J
RN
N
i
s
t
he
de
ve
l
opm
e
n
t
of
A
N
N
[1
7].
In
t
h
i
s
p
a
pe
r,
J
RN
N
i
s
us
e
d
t
o
pre
di
c
t
P
V
pow
e
r
w
i
t
h
i
np
ut
pa
ra
m
e
t
e
rs
s
u
c
h
a
s
t
e
m
p
e
r
a
t
ur
e
a
nd
s
o
l
a
r
r
a
di
a
t
i
on
i
n
S
ur
a
ba
ya
.
T
e
m
pe
r
a
t
ur
e
a
n
d
s
o
l
a
r
r
a
d
i
a
t
i
on
d
a
t
a
w
e
r
e
obt
a
i
ne
d
fro
m
A
pr
i
l
t
o
S
e
pt
e
m
b
e
r
.
J
RN
N
ha
s
t
h
e
t
r
a
i
n
i
ng
a
n
d
t
e
s
t
i
ng
s
t
e
p
[18]
.
In
t
h
e
t
r
a
i
ni
ng
s
t
e
p
,
t
he
r
e
a
re
t
w
o
ope
r
a
t
i
ons
na
m
e
l
y
forw
a
rd
op
e
ra
t
i
on
a
nd
b
a
c
kw
a
rd
ope
ra
t
i
on.
F
orw
a
rd
op
e
ra
t
i
o
n
i
s
us
e
d
t
o
e
n
t
e
r
t
e
m
pe
r
a
t
u
re
a
nd
s
o
l
a
r
r
a
di
a
t
i
on
d
a
t
a
a
nd
c
a
l
c
ul
a
t
e
P
V
pow
e
r
t
hroug
h
t
h
e
h
i
dde
n
l
a
ye
r
t
o
pr
oduc
e
t
he
o
ut
pu
t
l
a
y
e
r.
T
h
e
n
b
a
c
kw
a
rd
op
e
ra
t
i
on
,
t
he
out
put
l
a
ye
r
re
s
ul
t
s
a
re
put
b
a
c
k
i
n
t
o
t
he
de
l
a
y
bl
o
c
k
,
a
nd
c
ont
e
xt
l
a
ye
r
t
o
ge
t
t
h
e
f
i
na
l
o
ut
pu
t
[
19
-
21]
.
F
i
gur
e
3
i
s
a
di
a
gra
m
of
J
RN
N
a
nd
t
h
e
i
npu
t
,
ou
t
put
,
c
on
t
e
x
t
l
a
y
e
r
,
nu
m
b
e
r
o
f
hi
dde
n
l
a
y
e
r,
a
nd
de
l
a
y
bl
oc
k
a
r
e
(
−
1
)
,
(
)
,
(
−
1
)
,
,
a
nd
−
1
,
s
u
c
c
e
s
s
i
ve
l
y
.
T
he
m
ode
l
fro
m
J
RN
N
ba
s
e
d
o
n
F
i
gu
re
3
ha
s
e
qu
a
t
i
ons
l
i
ke
(
3
)
a
nd
(
4
)
.
L
e
t
,
0
(
1
)
a
nd
0
(
2
)
a
re
w
e
i
ght
s
of
t
h
e
f
i
rs
t
a
nd
s
e
c
on
d
l
a
ye
r
,
re
s
pe
c
t
i
ve
l
y.
T
he
n
,
i
s
non
l
i
n
e
a
r
t
ra
ns
f
e
r
func
t
i
o
n.
(
−
1
)
=
0
(
2
)
+
∑
(
2
)
(
(
)
)
=
0
(3)
(
)
=
,
0
(
1
)
+
,
1
(
1
)
(
−
1
)
+
,
2
(
1
)
(
−
1
)
(4)
F
i
gure
3
.
B
l
oc
k
d
i
a
gra
m
o
f
J
RN
N
J
RN
N
h
a
s
3
hi
d
de
n
l
a
ye
rs
i
m
p
l
e
m
e
n
t
e
d,
t
he
num
b
e
r
of
t
he
fi
rs
t
t
o
t
h
e
t
h
i
rd
h
i
dde
n
l
a
ye
rs
a
re
12,
5,
1,
re
s
p
e
c
t
i
v
e
l
y
[22
].
In
t
he
i
nput
l
a
ye
r
,
t
h
e
nu
m
b
e
r
o
f
n
e
uron
uni
t
s
a
re
2
a
nd
2
n
e
uro
ns
a
r
e
e
nt
e
r
e
d
s
o
l
a
r
ra
di
a
t
i
on
a
nd
t
e
m
pe
r
a
t
u
re
da
t
a
.
T
h
e
n
,
a
not
he
r
ne
uron
w
a
s
a
n
offs
e
t
ne
u
ron
w
hi
c
h
a
l
w
a
ys
p
rodu
c
e
s
a
va
l
ue
of
1
[23]
.
T
he
num
be
r
of
ou
t
put
l
a
ye
rs
i
s
1.
T
h
e
ou
t
pu
t
l
a
ye
r
produ
c
e
s
P
V
pow
e
r
for
e
c
a
s
t
i
ng
e
ve
r
y
m
ont
h
i
n
t
he
ne
x
t
m
ont
h.
T
h
e
e
poc
h
i
s
us
e
d
a
s
t
he
nu
m
be
r
of
i
t
e
ra
t
i
o
n
s
,
w
hi
c
h
i
s
100
0.
A
nd
a
l
l
ow
e
d
e
rro
r
r
e
w
a
rd
w
a
s
s
e
t
t
o
10
-
4.
A
ft
e
r
a
l
l
n
e
ur
a
l
n
e
t
w
or
ks
a
r
e
t
r
a
i
n
e
d
,
t
h
e
ne
xt
s
t
e
p
i
s
t
e
s
t
i
ng
s
t
e
p.
T
e
s
t
i
ng
s
t
e
p
i
s
do
n
e
t
o
t
e
s
t
P
V
pow
e
r
fore
c
a
s
t
i
ng
c
a
p
a
bi
l
i
t
i
e
s
.
T
h
e
n
,
t
he
r
e
s
ul
t
s
of
t
he
t
e
s
t
i
n
g
s
t
e
p
a
r
e
c
o
m
pa
r
e
d
w
i
t
h
t
he
a
c
t
ua
l
P
V
pow
e
r
i
n
J
ul
y.
T
h
e
m
a
i
n
di
ffe
r
e
nc
e
s
be
t
w
e
e
n
J
RN
N
a
nd
A
N
N
a
re
s
ho
w
n
i
n
F
i
gu
re
4
a
nd
F
i
gu
re
5,
s
e
v
e
r
a
l
l
y.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
1089
-
1094
1092
F
i
gure
4
.
D
e
s
i
gn
of
J
RN
N
F
i
gure
5
.
D
e
s
i
gn
of
A
N
N
In
J
RN
N
a
nd
A
N
N
,
P
V
P
ow
e
r
for
e
c
a
s
t
i
ng
re
s
u
l
t
s
a
r
e
e
va
l
ua
t
e
d
w
i
t
h
t
he
M
e
a
n
S
qu
a
r
e
E
rr
or
(M
S
E
)
a
nd
M
e
a
n
A
bs
ol
u
t
e
P
e
r
c
e
n
t
a
g
e
E
rror
(M
A
P
E
)
.
T
he
M
S
E
a
nd
M
A
P
E
a
r
e
r
e
f
e
re
n
c
e
s
for
m
e
a
s
uri
ng
e
rrors
from
t
r
a
i
n
e
d
m
od
e
l
s
.
If
t
he
M
S
E
a
nd
M
A
P
E
va
l
ue
s
a
r
e
l
ow
e
r
,
t
he
r
e
s
ul
t
i
ng
m
o
de
l
i
s
be
t
t
e
r
a
nd
m
ore
a
c
c
ura
t
e
.
T
h
e
e
qu
a
t
i
on
(
5
)
a
nd
(
6
)
a
r
e
e
qu
a
t
i
on
of
S
u
m
of
S
qua
re
E
rror
(S
S
E
)
a
nd
M
S
E
,
s
u
c
c
e
s
s
i
v
e
l
y
[24]
.
W
he
r
e
,
i
s
t
h
e
nu
m
b
e
r
of
t
he
d
a
t
a
pro
c
e
s
s
e
d
a
nd
o
bs
e
rv
e
d
.
T
h
e
n
,
′
a
nd
a
r
e
t
h
e
pr
e
di
c
t
e
d
a
n
d
a
c
t
u
a
l
va
l
u
e
,
s
e
v
e
r
a
l
l
y.
=
∑
(
′
−
−
−
)
2
1
(5)
=
(6)
2.
3
.
D
ata
p
r
e
p
a
r
at
i
on
T
hi
s
s
t
ud
y
us
e
d
s
ol
a
r
r
a
di
a
t
i
on
a
n
d
t
e
m
p
e
ra
t
ur
e
da
t
a
i
n
t
h
e
S
ura
ba
ya
a
re
a
.
D
a
t
a
re
t
ri
e
va
l
w
a
s
c
a
rri
e
d
out
fr
om
A
pri
l
t
o
S
e
p
t
e
m
b
e
r.
T
he
da
t
a
re
c
ordi
ng
w
a
s
c
a
rri
e
d
out
e
ve
r
y
30
m
i
nu
t
e
s
f
or
24
hours
[25]
.
F
i
gure
6
a
nd
F
i
gur
e
7
a
re
s
a
m
pl
e
s
of
d
a
t
a
fr
om
s
ol
a
r
ra
d
i
a
t
i
on
a
nd
t
e
m
pe
r
a
t
ure
for
24
hours
,
r
e
s
pe
c
t
i
ve
l
y
.
F
i
gure
6
.
S
a
m
p
l
e
of
da
t
a
fro
m
s
o
l
a
r
r
a
di
a
t
i
on
F
i
gure
7
.
S
a
m
p
l
e
of
da
t
a
fro
m
t
e
m
p
e
ra
t
ur
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
Shor
t
-
t
e
r
m
ph
ot
o
v
ol
t
ai
c
s
p
owe
r
f
or
e
c
as
t
i
ng
us
i
ng
J
or
dan…
(
A
j
i
A
k
bar
F
i
r
daus
)
1093
3.
R
ES
U
LTS
A
N
D
A
N
A
LY
S
I
S
F
i
gure
s
8
a
n
d
9
a
r
e
t
h
e
p
re
d
i
c
t
i
on
of
P
V
p
ow
e
r
w
i
t
h
t
h
e
J
R
N
N
a
nd
A
N
N
m
e
t
hod
.
T
he
pi
c
t
u
re
s
a
re
a
rra
n
ge
d
s
i
de
by
s
i
d
e
w
i
t
h
t
h
e
a
c
t
ua
l
da
t
a
.
F
ro
m
t
h
e
pr
e
di
c
t
i
on
re
s
u
l
t
s
,
t
h
e
J
RN
N
m
e
t
hod
h
a
s
s
uc
c
e
e
de
d
i
n
produc
i
ng
t
h
e
e
xp
e
c
t
e
d
P
V
pow
e
r
pr
e
di
c
t
i
ons
.
In
f
a
c
t
,
t
h
e
r
e
s
ul
t
s
of
J
RN
N
a
nd
A
N
N
a
re
a
l
m
os
t
t
he
s
a
m
e
.
T
he
re
s
u
l
t
i
ng
p
re
d
i
c
t
i
on
a
p
proa
c
h
e
s
t
h
e
a
c
t
ua
l
d
a
t
a
fr
om
t
h
e
P
V
pow
e
r
p
rodu
c
e
d
.
H
ow
e
ve
r,
t
h
e
re
a
r
e
s
o
m
e
di
s
a
dv
a
nt
a
g
e
s
t
ha
t
a
r
e
ge
ne
r
a
t
e
d
by
A
N
N
.
T
hi
s
c
a
n
b
e
s
e
e
n
i
n
T
a
b
l
e
1
.
T
a
bl
e
1
s
how
s
t
h
a
t
J
RN
N
ha
s
s
m
a
l
l
e
r
M
S
E
a
n
d
M
A
P
E
v
a
l
u
e
s
t
ha
n
A
N
N
.
T
hi
s
s
how
s
t
ha
t
t
he
p
re
di
c
t
i
ons
p
rodu
c
e
d
by
t
h
e
J
RN
N
a
re
c
l
os
e
r
t
o
t
he
a
c
t
u
a
l
da
t
a
.
S
o
t
h
a
t
t
he
J
RN
N
c
a
n
be
s
a
i
d
t
o
b
e
m
or
e
a
c
c
ura
t
e
b
e
c
a
us
e
J
RN
N
h
a
s
a
l
ow
e
rr
or
r
a
t
e
.
Be
s
i
de
s
t
ha
t
,
t
h
e
t
i
m
e
n
e
e
d
e
d
for
t
h
e
J
RN
N
t
o
prod
uc
e
t
he
s
e
p
re
d
i
c
t
i
ons
i
s
l
ong
e
r
t
h
a
n
A
N
N
.
F
i
gure
8
.
T
he
pr
e
di
c
t
i
on
of
P
V
pow
e
r
w
i
t
h
t
h
e
J
RN
N
F
i
gure
9
.
T
he
pr
e
di
c
t
i
on
of
P
V
pow
e
r
w
i
t
h
t
h
e
A
N
N
T
a
b
l
e
1
.
M
S
E
,
M
A
P
E
a
nd
t
i
m
e
of
t
he
t
e
s
t
re
s
u
l
t
J
RN
N
ANN
T
ra
i
n
i
n
g
T
e
s
t
i
n
g
T
i
m
e
T
ra
i
n
i
n
g
T
e
s
t
i
n
g
T
i
m
e
M
S
E
M
A
P
E
M
S
E
M
A
P
E
M
S
E
M
A
P
E
M
S
E
M
A
P
E
2
.
1
1
8
0
3
4
.
8
8
2
0
0
.
9
8
5
8
1
.
3
3
1
1
4
.
5
9
1
2
0
4
3
.
1
0
7
7
4
0
.
0
6
0
0
4
.
2
4
2
5
2
.
0
8
3
8
4
.
3
6
1
6
6
9
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
1089
-
1094
1094
4.
C
O
N
C
LU
S
I
O
N
P
V
pow
e
r
p
re
d
i
c
t
i
ons
ha
v
e
b
e
e
n
s
uc
c
e
s
s
fu
l
l
y
c
a
rri
e
d
o
ut
w
i
t
h
t
he
J
RN
N
m
e
t
ho
d,
w
hi
c
h
g
i
ve
s
l
ow
M
S
E
a
nd
M
A
P
E
v
a
l
ue
s
.
be
c
a
us
e
t
h
e
l
ow
e
r
t
h
e
M
S
E
a
nd
M
A
P
E
,
t
h
e
pr
e
di
c
t
i
ons
ge
ne
r
a
t
e
d
c
a
n
b
e
c
l
os
e
t
o
t
he
a
c
t
u
a
l
da
t
a
.
T
h
e
M
S
E
a
nd
M
A
P
E
ge
n
e
ra
t
e
d
i
n
t
he
t
ra
i
ni
n
g
s
t
e
p
a
re
2
.
1180
a
nd
3
4.
8
820
,
r
e
s
pe
c
t
i
ve
l
y.
t
he
n
t
he
M
S
E
a
nd
M
A
P
E
ge
n
e
ra
t
e
d
i
n
t
he
t
e
s
t
i
ng
s
t
e
ps
a
re
0.
985
8
a
nd
1
.
3311
,
re
s
p
e
c
t
i
v
e
l
y
.
a
nd
t
h
e
t
i
m
e
ne
e
de
d
i
s
4
.
59120
4.
P
re
d
i
c
t
e
d
r
e
s
ul
t
s
fro
m
J
RN
N
a
r
e
m
or
e
a
c
c
ur
a
t
e
t
ha
n
A
N
N
.
H
ow
e
v
e
r
,
t
he
t
i
m
e
t
a
ke
n
i
s
l
on
ge
r
.
R
EF
ER
EN
C
ES
[
1]
M
.
N
.
A
bdu
l
l
a
h
,
e
t
al
.
,
"
E
s
t
i
m
a
t
i
o
n
of
P
hot
ovo
l
t
a
i
c
M
odu
l
e
P
a
r
a
m
e
t
e
r
s
b
a
s
e
d
on
T
o
t
a
l
E
r
r
o
r
M
i
n
i
m
i
z
a
t
i
on
of
I
-
V
C
ha
r
a
c
t
e
r
i
s
t
i
c
,
"
B
u
l
l
e
t
i
n
o
f
E
l
e
c
t
r
i
c
al
E
n
gi
n
e
e
r
i
n
g
a
nd
I
n
f
o
r
m
at
i
c
s
,
v
ol
.
7,
n
o
.
3,
p
p.
42
5
-
4
32
,
2
018
.
[
2]
S
uya
n
t
o
,
S
o
e
di
byo
,
a
nd
A
.
A
.
F
i
r
da
u
s
,
“
D
e
s
i
g
n
a
n
d
S
i
m
ul
a
t
i
on
of
N
e
u
r
a
l
N
e
t
w
or
k
P
r
e
di
c
t
i
v
e
C
on
t
r
o
l
l
e
r
P
i
t
c
h
-
A
ngl
e
i
n
P
e
r
m
a
ne
nt
M
a
gn
e
t
i
c
S
yn
c
hr
onou
s
G
e
ne
r
a
t
o
r
W
i
n
d
T
ur
b
i
ne
V
a
r
i
a
bl
e
P
i
t
c
h
S
ys
t
e
m
,
”
1
st
I
nt
.
C
onf
.
on
I
nf
or
m
.
T
e
c
h
nol
ogy
,
C
om
p
.
a
nd
E
l
e
c
t
.
E
ng
i
n
e
e
,
v
ol
.
1,
p
p.
34
5
-
3
49,
201
4.
[
3]
Y
.
K
.
S
e
m
e
r
o,
J
.
Z
ha
n
g,
a
n
d
D
.
Z
he
n
g,
"
P
V
P
ow
e
r
F
o
r
e
c
a
s
t
i
ng
U
s
i
ng
a
n
I
n
t
e
g
r
a
t
e
d
G
A
-
PSO
-
A
N
F
I
S
A
p
pr
o
a
c
h
a
n
d
G
a
us
s
i
a
n
P
r
oc
e
s
s
R
e
gr
e
s
s
i
o
n
B
a
s
e
d
F
e
a
t
ur
e
S
e
l
e
c
t
i
on
S
t
r
a
t
e
g
y,
"
J
.
of
P
ow
e
r
a
nd
E
ne
r
gy
S
y
s
,
v
ol
.
4,
n
o.
2
,
2018
.
[
4]
A
.
A
.
F
i
r
d
a
us
,
e
t
a
l
.
,
"
D
i
s
t
r
i
b
ut
i
on
N
e
t
w
o
r
k
R
e
c
on
f
i
g
ur
a
t
i
on
U
s
i
ng
B
i
n
a
r
y
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
m
i
z
a
t
i
on
t
o
M
i
n
i
m
i
z
e
L
o
s
s
e
s
a
nd
D
e
c
r
e
a
s
e
V
o
l
t
a
ge
S
t
a
b
i
l
i
t
y
I
nde
x
,
"
B
E
E
I
,
vol
.
7
,
n
o.
4
,
pp
.
5
14
-
521
,
2018
.
[
5]
H
a
di
S
uy
ono
,
e
t
a
l
.
,
“
C
o
m
pa
r
i
s
on
of
S
o
l
a
r
R
a
d
i
a
t
i
o
n
I
n
t
e
n
s
i
t
y
F
or
e
c
a
s
t
i
ng
U
s
i
ng
A
N
F
I
S
a
nd
M
ul
t
i
pl
e
L
i
ne
a
r
R
e
gr
e
s
s
i
on
M
e
t
hod
s
,
”
B
ul
l
e
t
i
n
of
E
l
e
c
t
r
i
c
a
l
E
ng
i
ne
e
r
i
ng
an
d
I
n
f
or
m
at
i
c
s
,
v
ol
.
7
,
n
o.
2
,
pp
.
1
91
-
198
,
201
8
.
[
6]
M
.
D
I
N
G
,
a
nd
N
.
Z
.
X
u
,
“
A
M
e
t
ho
d
t
o
F
o
r
e
c
a
s
t
S
ho
r
t
-
T
e
r
m
O
u
t
pu
t
P
ow
e
r
of
P
ho
t
ov
ol
t
a
i
c
G
e
n
e
r
a
t
i
on
S
y
s
t
e
m
ba
s
e
d
on
M
a
r
ko
v
C
ha
i
n,
”
P
ow
e
r
S
y
s
t
e
m
T
e
c
hno
l
og
y
,
vo
l
.
35,
n
o.
1
,
pp
.
152
-
157
,
201
1.
[
7]
A
.
Y
ona
,
e
t
a
l
.
,
“
A
ppl
i
c
a
t
i
on
of
N
e
ur
a
l
N
e
t
w
o
r
k
t
o
24
-
H
ou
r
-
A
he
a
d
G
e
ne
r
a
t
i
ng
P
ow
e
r
F
o
r
e
c
a
s
t
i
n
g
f
or
P
V
Sy
s
t
e
m
,
”
P
ow
e
r
a
nd
E
ne
r
gy
S
oc
i
e
t
y
G
e
ne
r
a
l
M
e
e
t
i
n
g
-
C
o
nve
r
.
a
nd
D
e
l
i
ve
r
y
o
f
E
l
e
c
t
.
E
ne
r
gy
i
n
t
he
21
st
C
e
n
t
ur
y,
pp.
1
-
6,
2
008
.
[
8]
S
.
X
.
W
a
ng
,
N
.
Z
h
a
ng
,
Y
.
S
.
Z
ha
o
a
n
d
J
.
Z
ha
n
.
“
P
h
ot
o
vol
t
a
i
c
S
y
s
t
e
m
P
ow
e
r
F
o
r
e
c
a
s
t
i
ng
ba
s
e
d
on
C
o
m
bi
n
e
d
G
r
e
y
M
od
e
l
a
n
d
B
P
N
e
ur
a
l
N
e
t
w
or
k
,
”
I
nt
.
C
on
f
.
on
E
l
e
c
t
.
a
nd
C
on
t
.
E
n
g
i
ne
e
.
,
pp
.
4
623
-
462
6
,
20
11
.
[
9]
R
ui
do
ng
X
u
,
H
a
o
C
he
n
a
nd
X
i
a
o
ya
n
S
un,
“
S
ho
r
t
-
t
e
r
m
P
hot
ovo
l
t
a
i
c
P
ow
e
r
F
or
e
c
a
s
t
i
ng
w
i
t
h
W
e
i
g
ht
e
d
S
up
por
t
V
e
c
t
o
r
M
a
c
h
i
ne
,
”
I
nt
.
C
on
f
.
on
A
u
t
om
a
t
i
on
an
d
L
ogi
s
t
i
c
s
,
p
p.
24
8
-
257,
2
012
.
[
10]
S
obha
n
D
or
a
ha
k
i
.
,
"
A
S
ur
v
e
y
o
n
M
a
xi
m
um
P
ow
e
r
P
o
i
n
t
T
r
a
c
k
i
ng
M
e
t
h
o
ds
i
n
P
h
ot
o
vol
t
a
i
c
P
ow
e
r
S
y
s
t
e
m
s
,
"
B
ul
l
e
t
i
n
o
f
E
l
e
c
t
r
i
c
a
l
E
ngi
ne
e
r
i
ng
and
I
nf
o
r
m
a
t
i
c
s
,
v
ol
.
4,
n
o.
3
,
pp.
169
-
17
5,
20
15
.
[
11]
A
.
S
.
S
a
m
o
s
i
r
,
H
.
G
us
m
e
di
,
S
.
P
u
r
w
i
ya
n
t
i
,
a
nd
E
.
K
o
m
a
l
a
s
a
r
i
,
“
M
od
e
l
i
ng
a
nd
S
i
m
u
l
a
t
i
on
of
F
uz
z
y
L
og
i
c
ba
s
e
d
M
a
x
i
m
u
m
P
ow
e
r
P
oi
nt
T
r
a
c
k
i
n
g
(
M
P
P
T
)
f
or
P
V
A
pp
l
i
c
a
t
i
o
n,
”
I
n
t
e
r
nat
i
o
nal
J
our
nal
o
f
E
l
e
c
t
r
i
c
a
l
and
C
om
p
ut
e
r
E
ngi
n
e
e
r
i
n
g
(
I
J
E
C
E
)
,
vo
l
.
8
,
no
.
3
,
pp
.
131
5
-
1
323
,
2018
.
[
12]
P
.
F
.
P
a
i
a
nd
W
.
C
.
H
on
g,
"
F
o
r
e
c
a
s
t
i
ng
R
e
g
i
on
a
l
E
l
e
c
t
r
i
c
i
t
y
L
oa
d
b
a
s
e
d
on
R
e
c
ur
r
e
n
t
S
up
por
t
V
e
c
t
o
r
M
a
c
h
i
ne
s
w
i
t
h
G
e
ne
t
i
c
A
l
go
r
i
t
h
m
s
,
"
E
l
e
c
t
r
i
c
P
ow
e
r
Sy
s
t
e
m
s
R
e
s
e
a
r
c
h
,
vo
l
.
7
4,
pp
.
417
-
425
,
200
5.
[
13]
C
.
S
.
C
he
n,
S
.
X
.
D
u
a
n,
T
.
C
a
i
a
n
d
B
.
Y
.
L
i
u
,
“
O
n
l
i
ne
24
-
h
S
o
l
a
r
P
ow
e
r
F
o
r
e
c
a
s
t
i
ng
b
a
s
e
d
o
n
W
e
a
t
he
r
T
y
pe
C
l
a
s
s
i
f
i
c
a
t
i
on
us
i
ng
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
or
k
,
”
S
ol
a
r
E
ne
r
gy
,
vo
l
.
8
5,
no
.
11
,
pp.
2
856
-
287
0,
20
11.
[
14]
S
.
I
.
S
ul
a
i
m
a
n
,
e
t
a
l
.
,
“
O
pt
i
m
i
z
i
n
g
t
h
r
e
e
-
L
a
y
e
r
N
e
u
r
a
l
N
e
t
w
or
k
M
od
e
l
f
o
r
G
r
i
d
-
C
onne
c
t
e
d
P
ho
t
ov
ol
t
a
i
c
S
ys
t
e
m
O
ut
pu
t
P
r
e
di
c
t
i
on
,
”
C
on
f
.
on
I
nn
ov
a
t
i
v
e
T
e
c
hno
l
o
gi
e
s
i
n
I
nt
e
l
l
i
ge
n
t
Sy
s
.
and
I
n
dus
t
r
i
a
l
A
pp
.
,
pp
.
338
-
34
3
,
20
09
.
[
15]
T
.
C
a
i
,
S
.
X
.
D
ua
n,
a
nd
C
.
S
.
C
he
n
,
“
F
o
r
e
c
a
s
t
i
ng
P
ow
e
r
O
ut
put
f
or
gr
i
d
-
C
onn
e
c
t
e
d
P
ho
t
ov
ol
t
a
i
c
P
ow
e
r
S
y
s
t
e
m
w
i
t
h
out
u
s
i
n
g
S
ol
a
r
R
a
d
i
a
t
i
o
n
M
e
a
s
u
r
e
m
e
nt
,”
I
E
E
E
I
nt
.
Sy
m
pos
i
um
o
n
P
ow
e
r
E
l
e
c
t
r
o
.
f
o
r
D
i
s
t
r
i
bu
t
e
d
G
e
ne
r
at
i
on
Sy
s
.
,
pp
.
77
3
-
7
77
,
2
010
.
[
16]
S
.
K
.
K
o
l
l
i
m
a
l
l
a
,
a
nd
M
.
K
.
M
i
s
hr
a
,
“
V
a
r
i
a
bl
e
P
e
r
t
ur
ba
t
i
on
S
i
z
e
A
da
p
t
i
v
e
P
&
O
M
P
P
T
A
l
g
or
i
t
hm
f
o
r
S
udde
n
C
ha
nge
s
i
n
I
r
r
a
d
i
a
n
c
e
,
”
I
E
E
E
T
r
an
s
.
Su
s
t
ai
n
.
E
ne
r
gy
,
vo
l
.
5
,
no
.
4
,
pp.
71
8
–
72
8,
20
14.
[
17]
Z
.
K
a
s
i
r
a
n,
Z
.
I
b
r
a
h
i
m
a
nd
M
.
S
.
M
.
R
i
bu
a
n
,
"
M
ob
i
l
e
P
hon
e
C
u
s
t
o
m
e
r
s
C
hu
r
n
P
r
e
d
i
c
t
i
o
n
u
s
i
ng
E
l
m
a
n
A
nd
J
o
r
da
n
R
e
c
ur
r
e
nt
N
e
u
r
a
l
N
e
t
w
o
r
k
,
"
I
n
t
.
C
on
f
.
o
n
C
o
m
put
i
ng
a
nd
C
onv
e
r
g
e
nc
e
T
e
c
hno
l
og
y
,
20
12.
[
18]
H
.
H
i
ka
w
a
a
nd
Y
.
A
r
a
g
a
,
"
S
t
udy
o
n
G
e
s
t
ur
e
R
e
c
o
gni
t
i
on
S
y
s
t
e
m
U
s
i
ng
P
o
s
t
ur
e
C
l
a
s
s
i
f
i
e
r
a
nd
J
o
r
d
a
n
R
e
c
ur
r
e
n
t
N
e
ur
a
l
N
e
t
w
or
k
,
"
I
n
t
e
r
na
t
i
o
n
a
l
J
oi
nt
C
on
f
e
r
e
n
c
e
on
N
e
u
r
a
l
N
e
t
w
o
r
k
s
,
2
011
.
[
19]
Z
.
C
.
L
i
p
t
on
,
"
A
C
r
i
t
i
c
a
l
R
e
v
i
e
w
of
R
e
c
ur
r
e
n
t
N
e
u
r
a
l
N
e
t
w
or
ks
f
o
r
S
e
qu
e
nc
e
L
e
a
r
ni
n
g,
"
M
a
y
2015
.
[
O
n
l
i
ne
]
.
A
va
i
l
a
b
l
e
:
ht
t
p
:
/
/
a
r
x
i
v.
or
g
/
a
bs
/
150
6.
0001
9.
[
A
c
c
e
s
s
e
d
10
7
2018]
.
[
20]
Ö
.
F
.
E
r
t
ug
r
u
l
,
"
F
or
e
c
a
s
t
i
ng
E
l
e
c
t
r
i
c
i
t
y
L
oa
d
by
a
N
o
ve
l
R
e
c
ur
r
e
nt
E
xt
r
e
m
e
L
e
a
r
n
i
ng
,
"
E
l
e
c
t
r
i
c
a
l
P
ow
e
r
and
E
ne
r
g
y
Sy
s
t
e
m
s
,
vo
l
.
7
8,
p
p.
42
9
-
4
35,
2
016
.
[
21]
M
.
R
a
n
a
a
nd
I
.
K
op
r
i
n
s
ka
,
"
F
or
e
c
a
s
t
i
ng
E
l
e
c
t
r
i
c
i
t
y
L
oa
d
w
i
t
h
A
dv
a
nc
e
d
W
a
ve
l
e
t
N
e
ur
a
l
N
e
t
w
or
ks
,
"
N
e
ur
o
c
om
pu
t
i
ng
,
v
ol
.
182
,
pp
.
118
-
132
,
201
6.
[
22]
T
.
E
.
P
ut
r
i
,
A
.
A
.
F
i
r
da
us
,
a
nd
W
.
I
.
S
a
bi
l
l
a
,
"
S
hor
t
-
T
e
r
m
F
o
r
e
c
a
s
t
i
ng
of
E
l
e
c
t
r
i
c
i
t
y
C
ons
u
m
pt
i
on
R
e
ve
nue
on
J
a
va
-
B
a
l
i
E
l
e
c
t
r
i
c
i
t
y
S
ys
t
e
m
U
s
i
ng
J
or
da
n
R
e
c
u
r
r
e
n
t
N
e
u
r
a
l
N
e
t
w
o
r
k
,
"
J
ou
r
na
l
o
f
I
nf
or
m
a
t
i
on
S
y
s
t
e
m
s
E
ngi
n
e
e
r
i
n
g
and
B
us
i
n
e
s
s
I
nt
e
l
l
i
ge
n
c
e
,
vol
.
4
,
n
o.
2
,
pp
.
9
6
-
1
05
,
20
18.
[
23]
Y
.
K
a
s
hy
a
p
,
A
.
B
a
ns
a
l
,
a
nd
A
.
K
.
S
a
o,
“
S
ol
a
r
R
a
d
i
a
t
i
on
F
or
e
c
a
s
t
i
ng
w
i
t
h
M
ul
t
i
pl
e
P
a
r
a
m
e
t
e
r
s
N
e
ur
a
l
N
e
t
w
or
ks
,
”
R
e
ne
w
a
bl
e
a
nd
Sus
t
a
i
na
bl
e
E
ne
r
gy
R
e
v
i
e
w
s
,
vo
l
.
49,
p
p.
82
5
-
8
35,
2015
.
[
24]
M
.
M
or
dj
a
ou
i
,
S
.
H
a
dda
d,
A
.
M
e
d
oue
d
a
nd
A
.
L
a
oua
f
i
,
"
E
l
e
c
t
r
i
c
L
o
a
d
F
o
r
e
c
a
s
t
i
n
g
by
U
s
i
ng
D
yna
m
i
c
N
e
u
r
a
l
N
e
t
w
o
r
k,
"
I
nt
e
r
na
t
i
ona
l
J
ou
r
na
l
of
H
y
d
r
og
e
n
E
ne
r
gy
,
vo
l
.
42
,
pp
.
1
7655
-
176
63,
2
017
.
[
25]
W
.
L
i
a
ol
i
a
o,
C
.
C
he
ng
ga
ng
,
Y
.
N
i
ng
,
a
nd
C
.
H
u
i
,
"
E
va
l
ua
t
i
on
o
f
s
o
l
a
r
i
r
r
a
d
i
a
nc
e
on
i
nc
l
i
ne
d
s
u
r
f
a
c
e
s
m
od
e
l
s
in
t
h
e
S
hor
t
-
T
e
r
m
P
h
ot
o
vo
l
t
a
i
c
P
ow
e
r
F
o
r
e
c
a
s
t
i
ng
,
"
T
h
e
J
.
o
f
E
ng
i
n
e
e.
,
v
o
l
.
20
17
,
n
o.
13
,
pp
.
2226
–
22
30,
2
017
.
Evaluation Warning : The document was created with Spire.PDF for Python.