I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
74
~
85
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
36.
i
1
.
p
p
74
-
85
74
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
So
la
r irradia
tion
intensity
foreca
sti
ng
f
o
r so
la
r panel
power
o
utput
ana
ly
ze
T
a
s
m
a
Su
cit
a
,
Da
da
ng
L
uk
m
a
n H
a
k
im
,
Rizk
y
H
er
y
a
nt
o
H
ida
y
a
htullo
h,
Dik
i F
a
hri
za
l
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
Ed
u
c
a
t
i
o
n
,
F
a
c
u
l
t
y
o
f
Te
c
h
n
o
l
o
g
y
a
n
d
V
o
c
a
t
i
o
n
a
l
E
d
u
c
a
t
i
o
n
,
U
n
i
v
e
r
s
i
t
a
s P
e
n
d
i
d
i
k
a
n
I
n
d
o
n
e
s
i
a
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
8
,
2
0
2
4
R
ev
is
ed
Ma
y
15
,
2
0
2
4
Acc
ep
ted
J
u
n
5
,
2
0
2
4
Ac
c
u
ra
te
fo
re
c
a
stin
g
o
f
g
l
o
b
a
l
h
o
rizo
n
tal
irra
d
ian
c
e
(G
HI)
is
c
rit
ica
l
fo
r
o
p
ti
m
izi
n
g
so
lar
p
o
we
r
p
lan
t
(S
P
P
)
o
u
t
p
u
t,
p
a
rti
c
u
larl
y
in
tr
o
p
ic
a
l
lo
c
a
les
wh
e
re
so
lar
p
o
ten
ti
a
l
is
h
i
g
h
y
e
t
u
n
d
e
r
u
ti
li
z
e
d
d
u
e
t
o
fo
re
c
a
stin
g
c
h
a
ll
e
n
g
e
s.
Th
is
re
se
a
rc
h
a
ims
to
e
n
h
a
n
c
e
GH
I
p
re
d
icti
o
n
in
o
n
e
o
f
t
h
e
m
a
jo
r
c
it
ies
o
f
In
d
o
n
e
sia
,
wh
e
re
e
x
isti
n
g
m
o
d
e
l
s
stru
g
g
le
with
th
e
a
re
a
’s
n
a
tu
r
a
l
c
li
m
a
te
u
n
p
re
d
icta
b
il
i
ty
.
Ou
r
a
n
a
ly
sis
h
a
rn
e
ss
e
s
a
d
e
c
a
d
e
o
f
d
a
ta
2
0
1
1
-
2
0
2
0
,
in
c
lu
d
in
g
G
HI,
tem
p
e
ra
tu
re
,
a
n
d
th
e
S
k
y
I
n
s
o
lati
o
n
Clea
rn
e
ss
In
d
e
x
,
t
o
c
a
li
b
ra
te
a
n
d
c
o
m
p
a
re
t
h
e
se
m
e
t
h
o
d
o
l
o
g
ies
.
We
e
v
a
lu
a
te
a
n
d
c
o
n
tras
t
th
e
e
x
p
o
n
e
n
ti
a
l
sm
o
o
t
h
in
g
m
e
th
o
d
v
e
rsu
s
th
e
m
o
re
c
o
m
p
li
c
a
ted
a
rti
fi
c
ial
n
e
u
ra
l
n
e
two
rk
(AN
N).
O
u
r
fi
n
d
i
n
g
s
r
e
v
e
a
l
th
a
t
th
e
AN
N
m
e
th
o
d
,
n
o
tab
l
y
it
s
fo
u
rt
h
it
e
ra
t
io
n
m
o
d
e
l
wit
h
1
2
i
n
p
u
t
a
n
d
h
id
d
e
n
lay
e
rs,
s
u
b
sta
n
ti
a
ll
y
o
u
t
p
e
rfo
rm
s
e
x
p
o
n
e
n
ti
a
l
sm
o
o
th
i
n
g
with
a
l
o
w
e
rro
r
ra
te
o
f
1
.
1
2
%
.
Th
e
u
se
o
f
th
e
se
m
e
th
o
d
o
l
o
g
ies
fo
re
c
a
sts
a
n
a
v
e
ra
g
e
e
n
e
rg
y
o
u
t
p
u
t
o
f
2
5
2
,
4
0
5
Watt
fo
r
a
so
lar
p
a
n
e
l
wit
h
sp
e
c
ifi
c
a
t
io
n
1
5
.
3
%
e
fficie
n
c
y
a
n
d
1
.
3
1
m
2
su
rfa
c
e
a
re
a
th
ro
u
g
h
o
u
t
th
e
2
0
2
1
t
o
2
0
2
5
ti
m
e
fra
m
e
.
Th
e
wo
rk
o
ffe
rs
th
e
AN
N
m
e
th
o
d
a
s
a
str
o
n
g
p
re
d
icti
o
n
t
o
o
l
f
o
r
S
P
P
d
e
v
e
lo
p
m
e
n
t
a
n
d
u
r
g
e
s
a
fu
r
th
e
r
e
x
p
lo
ra
ti
o
n
in
t
o
m
o
re
a
d
v
a
n
c
e
d
f
o
re
c
a
stin
g
m
e
th
o
d
o
l
o
g
ies
to
b
e
tt
e
r
h
a
rn
e
ss
so
lar e
n
e
rg
y
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
E
x
p
o
n
e
n
tial
s
m
o
o
th
in
g
Fo
r
ec
asti
n
g
m
eth
o
d
Glo
b
al
h
o
r
izo
n
tal
ir
r
ad
ian
ce
So
lar
p
o
wer
p
la
n
t
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
asm
a
Su
cita
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
E
d
u
ca
tio
n
,
Facu
lty
o
f
T
ec
h
n
o
lo
g
y
a
n
d
Vo
ca
tio
n
al
E
d
u
ca
tio
n
Un
iv
er
s
itas
Pen
d
id
ik
an
I
n
d
o
n
esia
B
an
d
u
n
g
,
I
n
d
o
n
esia
E
m
ail:
tasma
s
u
cita
@
u
p
i.e
d
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
n
esia,
as
a
tr
o
p
ical
n
ati
o
n
,
is
d
r
en
ch
ed
in
s
o
lar
r
ad
i
atio
n
th
r
o
u
g
h
o
u
t
th
e
y
ea
r
,
d
eliv
er
in
g
a
p
len
tifu
l
s
u
p
p
l
y
o
f
s
o
lar
en
er
g
y
with
an
a
v
er
ag
e
in
ten
s
ity
o
f
r
o
u
g
h
ly
4
.
8
k
W
h
/m
2
[
1
]
,
[
2
]
.
T
h
is
p
len
tifu
l
r
eso
u
r
ce
is
at
th
e
h
ea
r
t
o
f
th
e
co
u
n
tr
y
’
s
ag
en
d
a
f
o
r
r
en
ewa
b
le
en
er
g
y
g
r
o
wth
.
T
h
e
p
r
o
m
is
e
o
f
s
o
lar
en
er
g
y
,
a
clea
n
an
d
s
u
s
tain
ab
le
r
eso
u
r
ce
,
m
atch
es n
icely
with
n
atio
n
al
g
o
als,
as it o
f
f
er
s
No
.
en
v
ir
o
n
m
en
tal
h
az
ar
d
s
an
d
is
lim
itles
s
.
T
h
ese
p
r
o
p
e
r
ties
m
ak
e
s
o
lar
p
o
we
r
a
h
ig
h
ly
v
i
ab
le
ch
o
ice
f
o
r
e
n
er
g
y
g
en
er
a
tio
n
,
p
o
s
itio
n
ed
to
m
ee
t a
r
an
g
e
o
f
s
o
cieta
l n
ee
d
s
[
3
]
,
[
4
]
.
W
ith
th
e
n
atio
n
’
s
cf
f
o
r
ec
ast
to
in
cr
ea
s
e
b
etwe
en
7
%
to
1
0
%
y
ea
r
ly
u
n
til
2
0
2
5
,
a
co
m
p
a
r
ab
le
s
p
ik
e
in
p
o
wer
d
em
an
d
is
an
ticip
at
ed
[
5
]
.
T
h
e
Natio
n
al
E
n
er
g
y
Po
licy
,
is
s
u
ed
b
y
Pre
s
id
en
tial
Dec
r
ee
No
.
5
o
f
2
0
0
6
,
r
eq
u
ir
es
th
e
g
r
o
wth
o
f
alter
n
ativ
e
an
d
r
en
ewa
b
le
en
e
r
g
y
s
o
u
r
ce
s
,
s
u
ch
as
m
ic
r
o
h
y
d
r
o
,
b
io
m
ass
,
win
d
,
an
d
s
o
lar
to
f
u
lf
ill
th
is
ex
p
an
d
in
g
n
ee
d
[
6
]
.
T
h
e
g
o
v
e
r
n
m
en
t
r
eg
u
latio
n
o
f
2
0
1
4
f
u
r
t
h
er
en
co
u
r
ag
es
th
is
ten
d
en
cy
b
y
ca
llin
g
f
o
r
en
e
r
g
y
d
iv
er
s
if
icatio
n
,
estab
lis
h
in
g
a
tar
g
et
f
o
r
r
en
ewa
b
le
en
e
r
g
y
to
co
n
tr
ib
u
te
at
least
2
3
%
o
f
to
tal
c
o
n
s
u
m
p
tio
n
b
y
2
0
2
5
.
I
n
th
is
co
n
tex
t,
So
lar
Po
wer
Plan
ts
em
er
g
e
as
a
s
tr
ateg
ic
alter
n
ativ
e,
lo
wer
in
g
d
e
p
en
d
e
n
cy
o
n
f
o
s
s
il
f
u
els
[
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
o
la
r
ir
r
a
d
ia
tio
n
in
ten
s
ity
fo
r
ec
a
s
tin
g
fo
r
s
o
la
r
p
a
n
el
p
o
w
er o
u
tp
u
t
a
n
a
lyze
(
Ta
s
ma
S
u
cita
)
75
Desp
ite
m
o
r
e
s
tead
y
s
o
lar
r
ad
iatio
n
co
m
p
a
r
ed
to
n
atio
n
s
lik
e
Ger
m
an
y
an
d
J
ap
an
,
r
eliab
le
f
o
r
ec
asti
n
g
r
em
ain
s
a
m
ajo
r
co
n
ce
r
n
in
I
n
d
o
n
esia.
Pre
v
io
u
s
r
esear
ch
h
as
u
tili
ze
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
ap
p
r
o
a
ch
es
f
o
r
esti
m
atin
g
s
u
n
r
ad
iatio
n
ac
r
o
s
s
th
ir
ty
I
n
d
o
n
esian
cities,
p
r
o
v
i
d
in
g
a
b
r
o
ad
s
p
ec
tr
u
m
o
f
in
ten
s
ities
with
Ku
p
an
g
r
ec
o
r
d
in
g
th
e
h
ig
h
est
an
d
B
an
d
u
n
g
b
elo
w
th
e
av
er
ag
e
.
Su
ch
r
ese
ar
ch
u
n
d
er
lin
es
th
e
v
ar
iety
in
s
o
lar
r
ad
iatio
n
a
n
d
t
h
e
n
ec
ess
ity
f
o
r
p
r
ec
is
io
n
f
o
r
e
ca
s
tin
g
s
y
s
tem
s
[
8
]
,
[
9
]
.
Fo
r
ec
asti
n
g
ac
cu
r
ac
y
h
as
b
ee
n
in
v
esti
g
ated
th
o
r
o
u
g
h
l
y
,
with
a
r
an
g
e
o
f
m
eth
o
d
o
lo
g
ie
s
d
em
o
n
s
tr
atin
g
v
ar
ied
d
e
g
r
ee
s
o
f
ef
f
ec
tiv
en
ess
.
T
ec
h
n
iq
u
es
s
u
ch
as
f
u
zz
y
lo
g
ic
an
d
th
e
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U)
h
av
e
b
ee
n
in
v
esti
g
ated
,
ea
ch
with
its
s
tr
en
g
th
s
an
d
lim
itatio
n
s
[
1
0
]
,
[
1
1
]
.
Sp
ec
if
ica
lly
,
in
J
a
v
a
I
s
lan
d
,
th
e
ef
f
icien
cy
o
f
ANN
m
o
d
el
s
in
p
r
e
d
ictin
g
s
o
lar
ir
r
ad
ian
c
e
an
d
p
o
wer
g
en
e
r
atio
n
h
as
b
ee
n
v
alid
ated
,
alb
eit
with
r
ec
o
g
n
ized
f
au
lts
in
th
e
e
s
tim
ate
p
r
o
ce
s
s
[
1
2
]
,
[
1
3
]
.
R
ec
o
g
n
izin
g
I
n
d
o
n
esian
tr
em
en
d
o
u
s
s
o
lar
p
o
ten
tial
an
d
th
e
im
p
o
r
tan
t
n
ec
ess
ity
o
f
ac
c
u
r
ate
s
o
lar
r
ad
iatio
n
p
r
ed
ictio
n
s
in
u
ti
lizin
g
th
is
r
eso
u
r
ce
,
th
is
r
esear
ch
tr
ies
to
b
r
id
g
e
th
e
k
n
o
wled
g
e
g
ap
in
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es.
I
t
an
al
y
ze
s
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
ANN
ap
p
r
o
a
ch
v
er
s
u
s
th
e
e
x
p
o
n
en
tial
s
m
o
o
th
in
g
m
et
h
o
d
f
o
r
esti
m
atin
g
s
o
lar
r
ad
iatio
n
in
te
n
s
ity
in
B
an
d
u
n
g
C
ity
o
v
er
a
f
iv
e
y
e
ar
h
o
r
izo
n
.
T
h
is
r
esear
ch
n
o
t
o
n
l
y
s
ee
k
s
to
b
o
o
s
t
f
o
r
ec
asti
n
g
p
r
ec
is
io
n
b
u
t
also
to
o
f
f
er
a
r
ig
o
r
o
u
s
an
aly
tical
f
r
am
ewo
r
k
f
o
r
th
e
co
n
s
tr
u
ctio
n
o
f
s
o
lar
p
o
wer
p
lan
ts
,
en
ab
lin
g
th
e
co
u
n
tr
y
'
s
tr
an
s
itio
n
to
a
s
u
s
tain
a
b
le
en
er
g
y
f
u
tu
r
e.
B
y
u
n
d
er
ta
k
in
g
a
co
m
p
ar
a
tiv
e
ex
am
in
atio
n
o
f
v
ar
io
u
s
m
eth
o
d
o
lo
g
ies,
th
e
s
tu
d
y
in
ten
d
s
to
o
f
f
e
r
f
o
r
ec
asts
o
f
b
etter
a
cc
u
r
ac
y
,
th
er
ef
o
r
e
in
f
lu
en
cin
g
s
tr
ateg
ic
en
er
g
y
p
l
an
n
in
g
a
n
d
allo
win
g
th
e
b
est u
s
ag
e
o
f
I
n
d
o
n
esia’
s
s
o
lar
r
eso
u
r
ce
s
.
2.
M
E
T
H
O
D
2
.
1
.
T
o
o
ls
I
n
th
is
r
esear
ch
,
we
co
n
d
u
ct
ed
a
th
o
r
o
u
g
h
co
n
ce
p
tu
al
d
e
v
elo
p
m
en
t,
c
o
n
s
u
ltin
g
a
wid
e
r
an
g
e
o
f
r
ep
u
tab
le
in
te
r
n
atio
n
al
j
o
u
r
n
al
s
an
d
b
o
o
k
s
av
ailab
le
th
r
o
u
g
h
d
ig
ital
lib
r
ar
ies.
T
h
ese
r
eso
u
r
ce
s
g
av
e
u
s
a
s
o
li
d
g
r
asp
o
f
t
h
e
th
eo
r
etica
l
asp
ec
ts
o
f
s
o
lar
ir
r
ad
ian
c
e
f
o
r
ec
ast
in
g
an
d
h
o
w
it
ca
n
b
e
ap
p
lied
in
th
e
r
e
n
ewa
b
le
en
er
g
y
in
d
u
s
tr
y
.
I
n
o
r
d
er
to
tack
le
th
e
f
o
r
ec
asti
n
g
ch
allen
g
e,
we
im
p
lem
en
ted
a
d
u
al
s
tr
ateg
y
.
T
h
e
f
ir
s
t
m
eth
o
d
th
at
was
u
s
ed
is
ex
p
o
n
en
tial
s
m
o
o
th
in
g
,
a
s
tatis
ti
ca
l
tech
n
iq
u
e
co
m
m
o
n
l
y
u
s
ed
f
o
r
an
aly
zi
n
g
tim
e
s
er
ies
d
ata.
it
was
s
elec
ted
f
o
r
its
s
im
p
licity
an
d
ab
ilit
y
to
ca
lcu
late
weig
h
ted
a
v
er
ag
es
b
ased
o
n
p
r
ev
i
o
u
s
o
b
s
er
v
atio
n
s
.
W
e
u
s
ed
Mic
r
o
s
o
f
t
E
x
ce
l
f
o
r
t
h
e
im
p
lem
en
tati
o
n
o
f
th
is
m
eth
o
d
,
tak
in
g
ad
v
an
tag
e
o
f
its
b
u
ilt
-
in
f
u
n
ctio
n
s
an
d
d
ata
an
aly
s
is
to
o
ls
to
m
o
d
el
an
d
f
o
r
ec
ast
th
e
g
lo
b
al
h
o
r
izo
n
tal
ir
r
ad
ia
n
c
e
(
GHI
)
d
ata.
T
h
e
s
ec
o
n
d
tech
n
iq
u
e
in
v
o
lv
ed
t
h
e
ANN,
s
elec
ted
f
o
r
its
ab
ilit
y
to
m
o
d
el
n
o
n
-
lin
ea
r
r
el
atio
n
s
h
ip
s
an
d
its
r
o
b
u
s
tn
ess
in
d
ea
lin
g
with
co
m
p
lex
v
ar
iab
les
[
1
4
]
.
T
h
e
AN
N
an
aly
s
is
wa
s
co
n
d
u
cted
u
s
i
n
g
th
e
za
itu
n
tim
e
-
s
er
ies
ap
p
licatio
n
,
wh
ic
h
was
s
elec
ted
f
o
r
its
s
p
ec
ialized
f
ea
tu
r
es
in
tim
e
s
er
ies
f
o
r
ec
asti
n
g
an
d
its
u
s
er
-
f
r
ien
d
ly
i
n
ter
f
ac
e
f
o
r
b
u
ild
in
g
an
d
v
alid
atin
g
n
eu
r
al
n
etwo
r
k
m
o
d
els.
Ou
r
an
aly
s
is
r
elied
o
n
d
ata
o
b
tain
ed
f
r
o
m
NR
E
L
an
d
NASA
POW
E
R
,
well
k
n
o
wn
s
o
u
r
c
es
o
f
o
p
en
s
o
u
r
ce
clim
ato
lo
g
y
d
ata.
T
h
es
e
p
latf
o
r
m
s
wer
e
ch
o
s
en
b
ec
a
u
s
e
o
f
th
eir
ex
ten
s
iv
e
d
atasets
o
n
GHI
,
al
o
n
g
with
o
th
er
im
p
o
r
tan
t
m
eteo
r
o
l
o
g
ic
al
v
ar
iab
les.
W
e
co
llected
r
el
ev
an
t
d
ata
f
o
r
B
an
d
u
n
g
C
ity
o
v
er
th
e
n
ex
t
f
iv
e
y
ea
r
s
to
g
ath
er
em
p
ir
ical
ev
id
en
ce
o
n
t
h
e
p
o
ten
tial
o
f
s
o
lar
en
e
r
g
y
g
e
n
er
atio
n
in
t
h
e
r
eg
io
n
.
W
ith
t
h
e
ap
p
r
o
ac
h
u
s
in
g
a
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
o
f
s
o
lar
ir
r
a
d
ian
ce
p
atter
n
s
an
d
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
was
co
n
d
u
cte
d
,
p
r
o
v
id
in
g
v
alu
a
b
le
in
s
ig
h
ts
to
th
e
f
ield
o
f
s
o
l
ar
e
n
er
g
y
a
n
aly
tics
[
1
5
]
.
2
.
2
.
Resea
rc
h
des
ig
n
T
h
e
r
esear
ch
c
o
n
d
u
cted
h
e
r
ein
f
alls
u
n
d
er
th
e
ca
teg
o
r
y
o
f
ex
p
er
im
en
tal
s
tu
d
ies,
wh
ich
a
r
e
d
ef
in
e
d
b
y
a
s
y
s
tem
atic
m
eth
o
d
aim
e
d
at
test
in
g
th
e
p
r
ec
is
io
n
o
f
f
o
r
ec
asti
n
g
m
o
d
els
u
s
in
g
p
r
eset
v
ar
iab
le
d
ata.
T
h
is
r
esear
ch
is
cr
ea
ted
o
n
an
e
x
p
er
im
en
tal
b
asis
,
wh
er
e
th
e
f
o
cu
s
p
o
in
t
is
th
e
v
alid
atio
n
o
f
p
r
e
d
ictio
n
m
o
d
el
ac
cu
r
ac
y
a
g
ain
s
t
k
n
o
wn
d
ata
v
ar
iab
les
[
1
6
]
.
T
h
e
f
in
d
in
g
s
g
en
er
ated
f
r
o
m
th
e
f
o
r
ec
asti
n
g
m
eth
o
d
will
b
e
ex
am
in
ed
to
ca
lcu
late
th
e
o
u
tp
u
t p
o
wer
o
f
s
o
lar
p
an
els in
s
id
e
a
p
h
o
to
v
o
ltaic
s
o
lar
p
o
wer
s
y
s
tem
.
T
h
is
ex
p
licit
m
eth
o
d
o
l
o
g
ical
r
o
u
te
is
d
em
o
n
s
tr
ated
in
Fig
u
r
e
1
,
wh
ich
s
et
s
o
u
t th
e
f
lo
w
o
f
th
e
r
esear
ch
d
esig
n
.
Har
n
ess
in
g
s
o
lar
en
er
g
y
,
cr
u
cial
to
th
e
r
en
ewa
b
le
en
er
g
y
g
r
id
,
r
elies
s
u
b
s
tan
tially
o
n
th
e
ex
ac
t
m
ea
s
u
r
em
en
t
an
d
f
o
r
ec
asti
n
g
o
f
GHI
.
GHI
esti
m
ates
th
e
s
o
lar
en
er
g
y
ac
ce
s
s
ib
le
at
th
e
e
ar
th
’
s
s
u
r
f
a
ce
an
d
is
cr
u
cial
f
o
r
e
v
alu
atin
g
th
e
p
o
te
n
tial
o
u
tp
u
t
o
f
p
h
o
to
v
o
ltaic
(
P
V)
s
y
s
tem
s
.
T
h
is
r
esear
ch
is
b
ased
o
n
p
r
o
jectin
g
GHI
to
d
is
co
v
er
th
e
en
er
g
y
th
at
s
o
lar
p
an
els in
B
an
d
u
n
g
C
ity
co
u
ld
p
o
ten
tially
g
en
er
ate
f
r
o
m
2
0
2
1
to
2
0
2
5
.
Ou
r
m
eth
o
d
o
l
o
g
y
co
m
p
r
is
es
a
d
u
al
ap
p
r
o
ac
h
f
o
r
ec
asti
n
g
f
r
am
ewo
r
k
.
I
n
itially
,
we
em
p
lo
y
ed
th
e
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
a
p
p
r
o
a
ch
to
p
r
o
ject
GHI
,
lev
e
r
ag
in
g
o
n
its
p
r
o
f
icien
cy
i
n
s
m
o
o
th
i
n
g
tim
e
s
er
ies
d
ata
an
d
r
ev
ea
lin
g
u
n
d
e
r
ly
in
g
p
atter
n
s
.
C
o
m
p
lem
en
tar
ily
,
th
e
A
N
N
tech
n
iq
u
e
was a
p
p
lied
to
ca
p
tu
r
e
th
e
n
o
n
lin
ea
r
co
m
p
lex
ity
o
f
clim
atic
f
ac
to
r
s
af
f
ec
tin
g
GHI
.
T
h
e
ju
x
tap
o
s
itio
n
o
f
v
ar
io
u
s
ap
p
r
o
ac
h
es,
as
in
d
icate
d
in
th
e
Fig
u
r
e
1
,
allo
ws f
o
r
a
f
u
ll e
x
a
m
in
atio
n
o
f
th
eir
p
r
ed
ictin
g
ac
cu
r
ac
y
.
T
h
e
f
lo
wch
ar
t
s
h
o
ws
th
e
r
esea
r
ch
p
ath
way
,
s
tar
tin
g
with
th
e
ass
im
ilatio
n
o
f
tem
p
er
atu
r
e
d
ata
an
d
th
e
Sk
y
I
n
s
o
latio
n
C
lear
n
ess
I
n
d
ex
,
with
GHI
v
alu
es,
to
in
p
u
t
in
to
th
e
f
o
r
ec
asti
n
g
m
o
d
e
ls
.
Af
ter
th
e
u
s
e
o
f
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
an
d
A
NN
ap
p
r
o
ac
h
es,
th
e
r
esear
ch
m
o
v
es
to
a
r
ig
o
r
o
u
s
co
m
p
a
r
is
o
n
ex
am
in
atio
n
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
74
-
85
76
th
eir
p
er
f
o
r
m
an
ce
.
T
h
is
s
tag
e
is
cr
u
cial
in
d
eter
m
in
in
g
th
e
m
o
s
t
tr
u
s
two
r
th
y
m
o
d
el
b
ased
o
n
th
e
lo
west
er
r
o
r
in
d
ex
.
Su
b
s
eq
u
en
tly
,
th
e
i
d
ea
l
GHI
f
o
r
ec
asti
n
g
in
f
o
r
m
s
th
e
r
esear
ch
o
f
th
e
s
o
lar
p
a
n
els
p
o
wer
p
r
o
d
u
ctio
n
.
T
h
is
p
h
ase
ad
d
p
r
ec
i
s
e
f
ac
t
o
r
s
s
u
ch
as
th
e
p
a
n
els
ef
f
icie
n
cy
an
d
s
u
r
f
ac
e
ar
ea
t
o
ap
p
r
o
x
im
ate
r
ea
l
wo
r
ld
en
er
g
y
o
u
tp
u
t
[
1
7
]
.
T
h
ese
ca
lcu
latio
n
s
ar
e
v
ital
f
o
r
d
eter
m
in
in
g
th
e
a
ch
iev
ab
le
e
n
er
g
y
p
r
o
d
u
ctio
n
o
f
a
s
o
lar
p
o
wer
p
lan
t i
n
th
e
co
n
tex
t o
f
B
an
d
u
n
g
C
ity
g
e
o
g
r
ap
h
ic
an
d
clim
a
tic
cir
cu
m
s
tan
ce
s
.
T
h
e
f
in
d
in
g
s
p
r
o
d
u
ce
d
f
r
o
m
t
h
is
th
o
r
o
u
g
h
an
aly
tical
m
eth
o
d
will
g
iv
e
s
ig
n
if
ican
t
ev
id
en
c
e
to
in
f
o
r
m
p
o
licy
ch
o
ices
an
d
s
tr
ateg
ic
p
lan
n
in
g
f
o
r
s
o
lar
e
n
er
g
y
ad
o
p
tio
n
in
t
h
e
r
e
g
io
n
.
T
h
e
s
u
cc
e
ed
in
g
p
ar
ts
will
g
o
d
ee
p
er
in
t
o
th
e
m
o
d
el
co
n
s
tr
u
ctio
n
,
v
alid
atio
n
tech
n
i
q
u
es
a
n
d
th
e
s
ig
n
if
ican
ce
o
f
th
e
an
t
icip
ated
r
esu
lts
f
o
r
f
u
tu
r
e
e
n
er
g
y
s
o
lu
tio
n
s
.
Fig
u
r
e
1
.
R
esear
ch
d
esig
n
f
lo
wch
ar
t
2
.
3
.
F
o
re
ca
s
t
ing
m
e
t
ho
ds
E
n
s
u
r
in
g
th
e
a
cc
u
r
ac
y
o
f
G
HI
f
o
r
ec
asts
is
cr
u
cial
f
o
r
m
ax
im
izin
g
th
e
ef
f
icien
c
y
o
f
s
o
lar
p
o
wer
s
y
s
tem
s
.
T
h
is
r
esear
ch
u
tili
z
ed
two
s
ep
ar
ate
tech
n
iq
u
es
in
o
r
d
e
r
to
ac
h
iev
e
t
h
e
m
o
s
t
p
r
ec
is
e
f
o
r
ec
asti
n
g
m
o
d
el
f
o
r
GHI
in
te
n
s
ity
f
r
o
m
2
0
2
1
to
2
0
2
5
.
T
h
e
s
elec
tio
n
o
f
th
ese
tech
n
iq
u
es
was
b
ased
o
n
th
eir
estab
lis
h
ed
p
r
o
f
icien
c
y
in
m
ete
o
r
o
lo
g
ical
f
o
r
ec
asti
n
g
a
n
d
th
eir
s
p
ec
if
i
c
ap
titu
d
e
in
m
an
ag
in
g
th
e
i
n
tr
icac
ies
o
f
s
o
lar
r
ad
iatio
n
d
ata.
T
h
r
o
u
g
h
a
c
o
m
p
ar
ativ
e
an
aly
s
is
o
f
th
ese
two
f
o
r
ec
asti
n
g
m
eth
o
d
o
lo
g
ies,
o
u
r
g
o
al
is
to
d
eter
m
in
e
an
d
im
p
r
o
v
e
th
e
m
o
s
t
d
ep
en
d
a
b
le
s
tr
ateg
y
f
o
r
p
r
o
jectin
g
s
o
lar
ir
r
a
d
ian
ce
[
1
8
]
.
T
h
is
will
u
ltima
tely
co
n
tr
ib
u
te
to
th
e
o
v
er
all
p
u
r
p
o
s
e
o
f
in
cr
ea
s
in
g
s
o
lar
e
n
er
g
y
t
ec
h
n
o
lo
g
y
an
d
its
p
r
ac
tical
im
p
lem
en
tatio
n
.
2
.
3
.
1
.
E
x
po
nentia
l
s
m
o
o
t
hin
g
m
et
ho
d
T
o
en
h
an
ce
t
h
e
ac
cu
r
ac
y
o
f
s
o
lar
ir
r
a
d
ian
ce
f
o
r
ec
asts
,
we
u
tili
ze
d
ex
p
o
n
en
tial
s
m
o
o
th
in
g
,
a
wid
ely
r
ec
o
g
n
ized
tec
h
n
iq
u
e
f
o
r
an
al
y
zin
g
tr
en
d
s
in
tim
e
s
er
ies
d
a
ta.
Usi
n
g
th
e
f
ea
tu
r
es
with
Mic
r
o
s
o
f
t
E
x
ce
l,
we
an
aly
ze
d
a
d
ataset
in
clu
d
in
g
s
o
lar
r
ad
iatio
n
in
ten
s
ities
m
ea
s
u
r
ed
in
watts p
er
s
q
u
ar
e
m
eter
(
2
⁄
)
[
1
9
]
.
T
h
e
s
tr
ateg
ic
d
ep
lo
y
m
en
t
o
f
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
is
laid
o
u
t
in
Fig
u
r
e
2
,
wh
e
r
e
a
s
u
c
ce
s
s
io
n
o
f
m
o
d
els
was
p
r
o
d
u
ce
d
,
ea
ch
a
p
p
ly
in
g
a
d
is
tin
ct
d
am
p
in
g
f
a
cto
r
with
in
th
e
r
an
g
e
o
f
0
.
1
to
0
.
9
.
T
h
is
s
p
ec
tr
u
m
was
ch
o
s
en
to
ex
ten
s
iv
ely
ass
ess
th
e
m
eth
o
d
’
s
s
en
s
itiv
ity
to
ch
an
g
es
in
tr
en
d
ad
ju
s
tm
en
t
a
n
d
its
in
f
lu
en
ce
o
n
th
e
ac
cu
r
ac
y
o
f
th
e
f
o
r
ec
asts
[
2
0
]
.
T
h
e
id
ea
l
m
o
d
el,
d
ef
i
n
ed
b
y
th
e
lo
west
er
r
o
r
m
ea
s
u
r
e,
is
d
esig
n
ated
f
o
r
a
co
m
p
ar
is
o
n
e
v
alu
atio
n
a
g
ain
s
t th
e
ANN
m
o
d
el’
s
f
in
d
in
g
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
o
la
r
ir
r
a
d
ia
tio
n
in
ten
s
ity
fo
r
ec
a
s
tin
g
fo
r
s
o
la
r
p
a
n
el
p
o
w
er o
u
tp
u
t
a
n
a
lyze
(
Ta
s
ma
S
u
cita
)
77
Fig
u
r
e
2
.
E
x
p
o
n
en
tial
s
m
o
o
th
i
n
g
f
lo
w
E
r
r
o
r
q
u
an
tific
atio
n
was
a
cr
u
cial
co
m
p
o
n
en
t
o
f
th
is
p
r
o
ce
d
u
r
e,
with
th
e
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
ac
tin
g
as
th
e
m
ain
in
d
icato
r
f
o
r
ass
ess
m
en
t.
T
h
e
MA
PE
f
o
r
m
u
la,
as
f
o
llo
ws
g
iv
es
a
clea
r
in
d
icato
r
o
f
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
[
2
1
]
:
=
(
1
)
∑
|
−
|
×
100%
(
1
)
T
h
r
o
u
g
h
t
h
i
s
t
e
c
h
n
i
q
u
e
,
w
e
c
o
u
l
d
d
i
s
c
o
v
e
r
t
h
e
m
o
d
e
l
’
s
d
e
p
a
r
t
u
r
e
f
r
o
m
r
e
a
l
v
a
l
u
e
s
,
e
n
a
b
l
i
n
g
u
s
t
o
f
i
n
e
-
t
u
n
e
o
u
r
a
p
p
r
o
a
c
h
t
o
o
b
t
a
i
n
a
m
o
d
e
l
s
y
n
o
n
y
m
o
u
s
w
i
t
h
b
o
t
h
d
e
p
e
n
d
a
b
i
li
t
y
a
n
d
p
r
e
c
i
s
i
o
n
i
n
p
r
e
d
i
c
t
i
n
g
[
2
2
]
.
2
.
3
.
2
.
Art
if
icia
l
neura
l net
wo
rk
m
e
t
ho
d
ANN
ar
e
a
h
ig
h
l
y
a
d
v
an
ce
d
m
eth
o
d
o
l
o
g
y
in
p
r
e
d
ictiv
e
an
a
ly
tics
,
s
p
ec
if
ically
d
esig
n
ed
to
h
an
d
le
th
e
co
m
p
lex
ities
o
f
clim
ato
lo
g
ical
d
ata.
T
h
e
r
esear
c
h
u
tili
ze
d
t
h
e
ANN
m
eth
o
d
to
p
r
e
d
ict
th
e
in
ten
s
ity
o
f
GHI
.
T
h
e
ANN
m
eth
o
d
o
lo
g
y
was
ch
o
s
en
b
ec
a
u
s
e
it
is
ca
p
a
b
le
o
f
ef
f
ec
tiv
ely
d
ea
lin
g
with
in
tr
icate
r
elatio
n
s
h
ip
s
b
etwe
en
v
ar
iab
les,
s
u
ch
as
tem
p
er
atu
r
e
an
d
clo
u
d
c
o
v
er
,
wh
ich
g
r
ea
tly
in
f
lu
e
n
ce
th
e
f
lu
ctu
atio
n
o
f
s
o
lar
ir
r
ad
ian
ce
[
2
3
]
.
As
s
h
o
wn
in
Fig
u
r
e
3
,
th
e
p
r
o
ce
s
s
o
f
d
ev
elo
p
i
n
g
th
e
A
NN
m
o
d
el
s
tar
ted
with
ch
o
o
s
in
g
an
d
p
r
ep
ar
in
g
th
e
in
p
u
t
d
ataset.
T
h
e
d
ata
wer
e
p
r
o
ce
s
s
ed
u
s
i
n
g
th
e
za
itu
n
tim
e
-
s
er
ies
ap
p
licatio
n
,
wh
ich
h
as
n
eu
r
al
n
etwo
r
k
m
o
d
elin
g
ca
p
a
b
ilit
ies.
Ou
r
ANN
ar
ch
itectu
r
e
was
cr
ea
ted
u
s
in
g
a
b
ac
k
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
an
d
a
b
ip
o
lar
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
,
wh
i
ch
is
id
ea
l
f
o
r
h
an
d
lin
g
co
n
tin
u
o
u
s
in
p
u
t
d
ata
s
u
ch
as
ir
r
ad
ian
ce
lev
els
[
2
4
]
.
Du
r
in
g
th
e
m
o
d
el
tr
ain
i
n
g
p
h
ase,
we
p
er
f
o
r
m
ed
n
i
n
e
d
if
f
e
r
en
t
ex
p
e
r
im
en
ts
to
o
p
tim
ize
th
e
ANN
s
tr
u
ctu
r
e,
test
in
g
o
u
t
d
if
f
er
e
n
t
co
m
b
in
atio
n
s
o
f
in
p
u
t
an
d
h
id
d
en
lay
er
s
.
T
h
e
e
x
p
er
i
m
en
tal
d
esig
n
aim
ed
to
ca
lib
r
ate
th
e
n
etwo
r
k
to
m
in
im
ize
th
e
er
r
o
r
r
at
e
[
2
5
]
.
I
n
o
r
d
e
r
to
m
ai
n
tain
co
n
s
is
ten
cy
ac
r
o
s
s
ex
p
er
im
en
ts
,
we
k
e
p
t th
e
m
o
m
en
tu
m
an
d
lear
n
in
g
r
ate
v
alu
e
f
ix
ed
at
0
.
5
an
d
0
.
0
5
,
r
esp
ec
tiv
ely
.
Af
ter
co
n
d
u
ctin
g
th
ese
e
x
p
er
i
m
en
ts
,
th
e
ANN
m
o
d
el
th
at
p
r
o
d
u
ce
d
th
e
lo
west
er
r
o
r
was
s
elec
ted
f
o
r
a
co
m
p
ar
ativ
e
an
aly
s
is
with
th
e
ex
p
o
n
en
tial
s
m
o
o
t
h
in
g
m
o
d
el.
T
h
is
ev
alu
atio
n
is
ess
en
tial
f
o
r
d
ete
r
m
in
in
g
th
e
m
o
s
t
ef
f
ec
tiv
e
f
o
r
ec
asti
n
g
m
eth
o
d
in
ter
m
s
o
f
ac
cu
r
a
cy
an
d
r
eliab
ilit
y
f
o
r
GHI
p
r
ed
ictio
n
w
ith
in
th
e
co
n
tex
t o
f
o
u
r
r
esear
ch
[
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
74
-
85
78
Fig
u
r
e
3
.
Ar
tific
ial
n
e
u
r
al
n
et
wo
r
k
alg
o
r
ith
m
f
lo
w
2
.
4
.
O
utput
po
wer
ca
lcula
t
i
o
n
T
h
e
p
r
ac
tical
ap
p
licatio
n
o
f
o
u
r
r
esear
ch
en
d
s
in
th
e
p
o
wer
o
u
tp
u
t
ca
lcu
latio
n
,
wh
ich
is
r
elian
t
o
n
th
e
p
r
o
jecte
d
GHI
d
ata
p
r
o
d
u
ce
d
f
r
o
m
t
h
e
m
o
s
t
ex
ac
t
f
o
r
e
ca
s
tin
g
m
o
d
el
id
en
tifie
d
.
T
h
e
s
e
ca
lcu
latio
n
s
ar
e
cr
u
cial
s
in
ce
th
ey
tr
an
s
f
o
r
m
t
h
eo
r
etica
l
GHI
v
alu
es
in
to
ac
tio
n
ab
le
d
ata
r
e
g
ar
d
in
g
th
e
e
n
er
g
y
g
e
n
er
atio
n
o
f
s
o
lar
p
an
els
[
2
7
]
.
Fo
r
o
u
r
r
ese
ar
ch
,
we
co
m
b
i
n
ed
t
h
e
s
o
lar
p
a
n
els
u
n
iq
u
e
attr
ib
u
tes
n
am
ely
,
an
ef
f
icien
cy
r
ate
o
f
1
5
.
1
3
%
a
n
d
a
s
u
r
f
ac
e
ar
e
a
o
f
1
.
3
1
m
2
in
to
th
e
p
o
wer
o
u
tp
u
t
ca
lcu
latio
n
.
T
h
is
is
in
ac
co
r
d
an
ce
with
in
d
u
s
tr
y
s
tan
d
ar
d
s
f
o
r
s
o
lar
p
an
el
s
p
ec
s
wid
ely
u
tili
ze
d
in
co
m
p
ar
ab
le
clim
es
to
B
an
d
u
n
g
C
ity
.
T
h
e
ca
lcu
latio
n
o
f
p
o
wer
o
u
tp
u
t w
as e
ased
u
s
in
g
th
e
f
o
llo
win
g
[
2
8
]
.
(
)
=
(
2
⁄
)
×
(
%
)
×
(
2
)
(
2
)
E
m
p
lo
y
in
g
th
is
eq
u
atio
n
allo
ws
u
s
to
ap
p
r
o
x
im
ate
th
e
en
er
g
y
p
r
o
d
u
ctio
n
d
u
r
in
g
th
e
an
tic
ip
ated
tim
e
f
r
am
e,
g
iv
in
g
a
b
aselin
e
f
o
r
t
h
e
p
r
o
s
p
ec
tiv
e
p
o
wer
g
en
e
r
atio
n
f
r
o
m
s
o
lar
ar
r
ay
s
.
I
t’
s
v
ia
th
is
ess
en
tial
p
h
ase
th
at
we
ca
n
a
n
aly
ze
t
h
e
f
ea
s
i
b
ilit
y
an
d
ef
f
icien
cy
o
f
s
o
lar
en
er
g
y
s
o
lu
tio
n
s
ad
a
p
ted
f
o
r
th
e
g
eo
g
r
ap
h
ic
an
d
ec
o
n
o
m
ic
c
o
n
tex
t o
f
th
e
lo
ca
ti
o
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
c
o
n
tr
ib
u
tes
to
e
x
is
tin
g
r
esear
ch
o
n
p
r
ed
ictin
g
t
h
e
in
ten
s
ity
o
f
(
GHI
)
b
y
c
o
n
d
u
ctin
g
a
co
m
p
ar
is
o
n
b
etwe
en
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
tech
n
iq
u
es
in
B
an
d
u
n
g
C
ity
[
2
9
]
,
[
3
0
]
.
T
h
is
is
s
u
e
h
as
n
o
t
b
ee
n
ex
ten
s
iv
ely
s
tu
d
ied
in
t
h
e
co
n
tex
t
o
f
v
a
r
iab
le
tr
o
p
ical
clim
ates.
T
h
e
r
esu
lts
o
f
o
u
r
r
esear
ch
d
em
o
n
s
tr
ate
th
at
ar
tific
ial
n
eu
r
al
n
etwo
r
k
ac
h
iev
es
h
ig
h
er
ac
cu
r
ac
y
co
m
p
a
r
ed
to
ex
p
o
n
en
tial
s
m
o
o
th
in
g
.
Ou
r
f
in
d
in
g
s
in
d
icate
th
at
ANN
o
u
tp
er
f
o
r
m
s
e
x
p
o
n
e
n
tial
s
m
o
o
th
i
n
g
i
n
ac
cu
r
ac
y
,
r
ef
lectin
g
its
s
u
p
er
io
r
ca
p
a
b
ilit
y
to
h
a
n
d
le
t
h
e
co
m
p
le
x
d
y
n
am
ics
o
f
s
o
la
r
ir
r
ad
ian
ce
i
n
th
is
r
eg
io
n
.
T
h
er
ef
o
r
e,
u
tili
zin
g
a
m
o
r
e
ac
cu
r
ate
ar
tific
ial
n
eu
r
a
l
n
etwo
r
k
m
o
d
el
will
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
o
u
r
esti
m
at
es
f
o
r
s
o
lar
p
a
n
el
p
o
wer
p
r
o
d
u
ctio
n
,
th
e
r
eb
y
i
n
c
r
ea
s
in
g
th
e
d
e
p
en
d
a
b
ilit
y
o
f
s
o
lar
en
er
g
i
p
r
ed
ictio
n
s
f
r
o
m
2
0
2
1
to
2
0
2
5
[
3
1
]
.
3
.
1
.
E
x
po
nentia
l
s
m
o
o
t
hin
g
m
et
ho
d r
esu
lt
Prio
r
to
esti
m
atin
g
B
an
d
u
n
g
C
ity
GHI
in
ten
s
ity
f
o
r
th
e
2
0
2
1
to
2
0
2
5
p
er
io
d
u
s
in
g
th
e
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
ap
p
r
o
ac
h
,
it
was
i
m
p
o
r
tan
t
to
f
ir
s
t
d
eter
m
in
e
th
e
d
ata
s
et
th
at
wo
u
ld
s
er
v
e
as
th
e
f
o
u
n
d
atio
n
f
o
r
o
u
r
f
o
r
ec
asts
.
Fo
r
th
is
m
eth
o
d
,
o
n
ly
GHI
d
ata
f
r
o
m
2
0
1
1
to
2
0
2
0
wer
e
ev
alu
ated
.
T
h
e
GHI
d
ata
u
tili
ze
d
,
as
illu
s
tr
ated
in
th
e
f
o
llo
win
g
g
r
a
p
h
at
Fig
u
r
e
4
,
d
em
o
n
s
tr
ates
th
at
s
u
n
ir
r
ad
ian
ce
i
n
B
an
d
u
n
g
h
as
a
ch
an
g
in
g
ten
d
en
cy
.
No
tab
ly
,
th
e
m
a
x
i
m
u
m
ir
r
a
d
ian
ce
in
te
n
s
ity
was
r
ec
o
r
d
ed
in
2
0
1
5
at
1
,
9
4
2
,
2
8
6
W
/m
2
,
wh
ile
th
e
lo
west
was
r
ep
o
r
ted
i
n
2
0
1
1
at
1
,
6
7
0
,
9
7
8
W
/m
2
.
T
h
is
u
n
d
u
latin
g
tr
e
n
d
illu
s
tr
ate
s
th
e
f
lu
ctu
atio
n
o
f
s
o
lar
ir
r
ad
ian
ce
in
B
an
d
u
n
g
,
with
in
ten
s
ity
r
is
in
g
an
d
d
ec
lin
i
n
g
y
e
ar
b
y
y
ea
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
o
la
r
ir
r
a
d
ia
tio
n
in
ten
s
ity
fo
r
ec
a
s
tin
g
fo
r
s
o
la
r
p
a
n
el
p
o
w
er o
u
tp
u
t
a
n
a
lyze
(
Ta
s
ma
S
u
cita
)
79
Fig
u
r
e
4
.
GHI
d
ata
tr
en
d
Up
o
n
s
tu
d
y
i
n
g
th
e
f
o
r
ec
asted
r
esu
lts
as
th
ey
co
r
r
esp
o
n
d
w
ith
th
e
d
am
p
i
n
g
f
ac
t
o
r
s
in
T
a
b
le
1
,
we
o
b
s
er
v
ed
th
at
th
e
v
ar
iatio
n
in
th
e
p
r
ed
icted
v
al
u
es
lo
wer
s
as
th
e
d
am
p
in
g
f
ac
t
o
r
in
cr
ea
s
es.
Fo
r
ec
asts
wi
th
lo
wer
d
am
p
in
g
f
ac
to
r
s
r
e
v
ea
led
m
o
r
e
s
ig
n
if
ica
n
t
v
ar
iatio
n
s
,
wh
ils
t
th
o
s
e
with
d
am
p
in
g
f
ac
to
r
s
clo
s
er
to
1
o
f
f
er
ed
a
m
o
r
e
s
tab
le
tr
en
d
,
as
is
s
h
o
wn
with
a
d
a
m
p
in
g
f
ac
to
r
o
f
0
.
9
,
w
h
ich
d
em
o
n
s
tr
ated
n
eg
lig
i
b
le
ch
an
g
es.
T
ab
le
1
.
Fo
r
ec
asted
GHI
r
esu
lts
an
d
er
r
o
r
r
ates b
y
d
am
p
in
g
f
ac
to
r
Y
e
a
r
G
H
I
d
a
t
a
D
a
mp
i
n
g
f
a
c
t
o
r
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
2
0
1
1
1
,
6
7
0
,
9
7
8
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
#
N
/
A
2
0
1
2
1
,
6
8
5
,
7
5
0
1
,
6
7
0
,
9
7
8
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
1
,
6
7
0
,
9
78
2
0
1
3
1
,
6
8
0
,
3
3
6
1
,
6
8
4
,
2
7
3
1
,
6
8
2
,
7
96
1
,
6
8
1
,
3
18
1
,
6
7
9
,
8
41
1
,
6
7
8
,
3
64
1
,
6
7
6
,
8
87
1
,
6
7
5
,
4
10
1
,
6
7
3
,
9
32
1
,
6
7
2
,
4
55
2
0
1
4
1
,
8
2
3
,
9
5
9
1
,
6
8
0
,
7
3
0
1
,
6
8
0
,
8
28
1
,
6
8
0
,
6
31
1
,
6
8
0
,
1
38
1
,
6
7
9
,
3
50
1
,
6
7
8
,
2
66
1
,
6
7
6
,
8
88
1
,
6
7
5
,
2
13
1
,
6
7
3
,
2
43
2
0
1
5
1
,
9
4
2
,
2
8
6
1
,
8
0
9
,
6
3
6
1
,
7
9
5
,
3
33
1
,
7
8
0
,
9
61
1
,
7
6
6
,
4
31
1
,
7
5
1
,
6
55
1
,
7
3
6
,
5
43
1
,
7
2
1
,
0
09
1
,
7
0
4
,
9
62
1
,
6
8
8
,
3
15
2
0
1
6
1
,
6
9
8
,
7
3
6
1
,
9
2
9
,
0
2
1
1
,
9
1
2
,
8
95
1
,
8
9
3
,
8
88
1
,
8
7
1
,
9
44
1
,
8
4
6
,
9
70
1
,
8
1
8
,
8
40
1
,
7
8
7
,
3
92
1
,
7
5
2
,
4
27
1
,
7
1
3
,
7
12
2
0
1
7
1
,
7
5
5
,
6
0
9
1
,
7
2
1
,
7
6
5
1
,
7
4
1
,
5
68
1
,
7
5
7
,
2
82
1
,
7
6
8
,
0
19
1
,
7
7
2
,
8
53
1
,
7
7
0
,
7
99
1
,
7
6
0
,
7
95
1
,
7
4
1
,
6
89
1
,
7
1
2
,
2
14
2
0
1
8
1
,
8
5
5
,
5
8
9
1
,
7
5
2
,
2
2
5
1
,
7
5
2
,
8
01
1
,
7
5
6
,
1
11
1
,
7
6
0
,
5
73
1
,
7
6
4
,
2
31
1
,
7
6
4
,
7
23
1
,
7
5
9
,
2
39
1
,
7
4
4
,
4
73
1
,
7
1
6
,
5
54
2
0
1
9
1
,
9
2
7
,
9
5
8
1
,
8
4
5
,
2
5
3
1
,
8
3
5
,
0
31
1
,
8
2
5
,
7
46
1
,
8
1
7
,
5
83
1
,
8
0
9
,
9
10
1
,
8
0
1
,
0
69
1
,
7
8
8
,
1
44
1
,
7
6
6
,
6
96
1
,
7
3
0
,
4
57
2
0
2
0
1
,
8
0
5
,
0
0
3
1
,
9
1
9
,
6
8
7
1
,
9
0
9
,
3
73
1
,
8
9
7
,
2
94
1
,
8
8
3
,
8
08
1
,
8
6
8
,
9
34
1
,
8
5
1
,
8
25
1
,
8
3
0
,
0
88
1
,
7
9
8
,
9
48
1
,
7
5
0
,
2
07
Fig
u
r
e
5
f
u
r
t
h
er
illu
s
tr
ates
th
at
a
d
am
p
in
g
f
ac
to
r
o
f
0
.
7
r
e
s
u
lts
in
th
e
lo
west
er
r
o
r
r
ate
o
f
4
.
4
4
%,
s
h
o
win
g
th
e
b
est
lev
el
o
f
p
r
ed
ictin
g
p
r
ec
is
io
n
.
T
h
is
d
is
co
v
er
y
is
cr
u
cial
b
ec
au
s
e
it
in
d
icate
s
th
at
s
elec
tin
g
an
ap
p
r
o
p
r
iate
d
a
m
p
in
g
f
ac
t
o
r
m
ay
g
r
ea
tly
en
h
an
ce
th
e
p
r
ec
is
io
n
o
f
s
o
lar
ir
r
a
d
ian
ce
f
o
r
ec
ast
s
,
wh
ich
is
ess
en
tial
f
o
r
o
p
tim
izin
g
th
e
o
p
e
r
atio
n
o
f
s
o
lar
p
o
wer
p
la
n
ts
.
Du
e
t
o
th
e
p
r
o
v
en
e
f
f
icac
y
o
f
th
e
0
.
7
d
am
p
in
g
f
ac
to
r
,
it
was
ch
o
s
en
to
p
r
o
ject
f
u
tu
r
e
GHI
v
alu
es.
T
h
e
p
r
o
jectio
n
s
f
o
r
th
e
p
e
r
io
d
f
r
o
m
2
0
2
1
to
2
0
2
5
ar
e
s
h
o
wn
i
n
T
ab
le
2
.
T
ab
le
2
s
h
o
ws a
co
n
s
is
ten
tly
s
tead
y
GHI
in
ten
s
ity
ex
p
ec
ted
o
v
er
th
e
n
e
x
t f
iv
e
y
ea
r
s
,
with
an
av
er
ag
e
y
ea
r
ly
v
alu
e
o
f
1
,
8
2
4
,
0
3
2
W
/m
2
.
T
h
e
r
eg
u
lar
ity
o
f
s
o
lar
en
er
g
y
a
v
ailab
ilit
y
in
B
an
d
u
n
g
i
s
ad
v
an
tag
e
o
u
s
f
o
r
en
er
g
y
p
lan
n
i
n
g
,
as
it
p
r
o
v
i
d
es
a
d
ep
en
d
ab
le
f
o
u
n
d
atio
n
f
o
r
o
p
tim
izin
g
th
e
u
s
ag
e
o
f
s
o
lar
en
er
g
y
.
T
h
is
p
o
r
tio
n
o
f
th
e
r
esear
ch
n
o
t
o
n
ly
co
n
f
ir
m
s
th
e
u
s
ef
u
ln
ess
o
f
th
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
a
p
p
r
o
ac
h
in
tr
o
p
ical
en
v
ir
o
n
m
en
ts
b
u
t
also
em
p
h
as
izes
th
e
cr
u
cial
n
ee
d
o
f
ad
ju
s
t
i
n
g
m
o
d
el
p
ar
am
eter
s
to
o
b
tain
r
eliab
le
f
o
r
ec
asts
.
Fu
r
th
er
im
p
r
o
v
in
g
th
ese
p
a
r
am
eter
s
,
p
ar
ticu
lar
ly
th
e
d
am
p
in
g
f
ac
to
r
,
m
ig
h
t
b
o
o
s
t
th
e
ac
cu
r
ac
y
an
d
d
ep
en
d
a
b
ilit
y
o
f
s
o
lar
i
r
r
ad
ian
ce
esti
m
ates in
s
im
ilar
en
v
ir
o
n
m
en
tal
s
itu
atio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
74
-
85
80
Fig
u
r
e
5
.
E
r
r
o
r
r
ates a
cr
o
s
s
d
a
m
p
in
g
f
ac
t
o
r
s
T
ab
le
2
.
Fo
r
ec
asted
GHI
i
n
ten
s
ity
f
o
r
2
0
2
1
-
2
0
2
5
Y
e
a
r
F
o
r
e
c
a
st
i
n
g
r
e
su
l
t
(
W
/
m
2
)
2
0
2
1
1
,
8
2
2
,
5
6
3
2
0
2
2
1
,
8
2
4
,
8
2
0
2
0
2
3
1
,
8
2
4
,
1
4
3
2
0
2
4
1
,
8
2
4
,
3
4
6
2
0
2
5
1
,
8
2
4
,
2
8
5
A
v
e
r
a
g
e
1
,
8
2
4
,
0
3
2
3
.
2
.
Art
if
ici
a
l
neura
l net
wo
rk
m
e
t
ho
d r
esu
lt
Prio
r
to
im
p
lem
en
tin
g
th
e
f
o
r
ec
asti
n
g
o
f
GHI
in
ten
s
ity
u
s
in
g
th
e
ANN
m
eth
o
d
,
a
d
etailed
r
ev
iew
o
f
th
e
k
ey
in
p
u
t
d
ata
GHI
(
W
/m
²)
,
tem
p
e
r
atu
r
e
(
°C
)
,
an
d
Sk
y
I
n
s
o
latio
n
C
lear
n
ess
I
n
d
ex
(
SICI)
was
r
eq
u
ir
e
d
.
T
h
ese
in
p
u
ts
co
n
s
titu
te
th
e
co
r
e
o
f
o
u
r
ANN
m
o
d
el,
wh
ich
attem
p
ts
to
b
o
o
s
t
th
e
ac
cu
r
ac
y
o
f
s
o
lar
ir
r
a
d
ian
ce
f
o
r
ec
asts
in
B
an
d
u
n
g
C
ity
.
Fig
u
r
e
6
d
e
m
o
n
s
tr
ates
th
e
i
n
ter
d
ep
en
d
en
cies
with
in
th
e
d
ata.
T
h
e
GHI
,
tem
p
er
atu
r
e
,
an
d
SICI
s
tatis
t
ics
f
r
o
m
2
0
1
1
to
2
0
2
0
s
h
o
w
s
ig
n
if
ican
t v
ar
iatio
n
s
th
at
ar
e
cr
u
cial
f
o
r
t
r
ain
in
g
th
e
A
NN
m
o
d
el.
No
tab
l
y
,
wh
ile
th
e
tem
p
er
atu
r
e
r
em
ain
s
r
elativ
ely
s
tab
le
with
an
a
v
er
ag
e
o
f
ap
p
r
o
x
im
ately
2
3
°C
,
th
e
SICI
in
d
ex
f
lu
ctu
ates
m
o
r
e
s
u
b
s
tan
tially
,
r
ea
ch
in
g
its
p
ea
k
in
2
0
1
9
an
d
its
lo
west
in
2
0
1
6
.
T
h
is
v
ar
ia
b
ilit
y
in
d
icate
s
th
e
co
m
p
lex
n
at
u
r
e
o
f
th
e
clim
ati
c
f
ac
to
r
s
in
f
lu
en
cin
g
s
o
lar
ir
r
a
d
ian
ce
,
wh
ich
th
e
ANN
m
eth
o
d
is
well
-
eq
u
ip
p
ed
to
h
an
d
le
d
u
e
to
its
ab
ilit
y
to
m
o
d
el
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
.
Du
r
in
g
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
o
f
th
e
ANN,
d
if
f
er
en
t
co
m
b
in
atio
n
s
o
f
in
p
u
t
an
d
h
id
d
e
n
la
y
er
v
alu
es
wer
e
test
ed
,
wh
ile
k
ee
p
i
n
g
o
th
er
p
ar
am
eter
s
s
u
c
h
as
th
e
lear
n
in
g
r
ate
an
d
m
o
m
e
n
tu
m
c
o
n
s
tan
t.
T
h
is
ap
p
r
o
ac
h
o
f
r
an
d
o
m
c
o
m
b
in
atio
n
in
th
e
tr
ials
was
cr
u
cial
to
estab
li
s
h
in
g
th
e
co
n
f
ig
u
r
atio
n
th
at
p
r
o
d
u
c
e
d
th
e
lo
west
er
r
o
r
i
n
d
ex
i
n
p
r
e
d
ictin
g
o
u
tp
u
t.
Nin
e
iter
atio
n
s
wer
e
u
n
d
e
r
tak
en
to
id
e
n
tify
th
e
m
o
d
el
co
n
f
ig
u
r
atio
n
with
th
e
s
m
allest
er
r
o
r
,
as
s
u
m
m
ar
ized
in
T
ab
le
3
.
E
ac
h
iter
atio
n
ex
p
lo
r
ed
v
ar
y
i
n
g
ar
r
a
n
g
em
e
n
ts
o
f
th
e
in
p
u
t
an
d
h
id
d
en
lay
e
r
s
to
r
ef
in
e
th
e
a
cc
u
r
ac
y
o
f
o
u
r
f
o
r
ec
asts
,
d
e
m
o
n
s
tr
atin
g
th
e
ad
a
p
tiv
e
ca
p
ab
ilit
y
o
f
th
e
ANN
m
eth
o
d
to
o
p
tim
ize
b
ased
o
n
t
h
e
in
tr
icate
p
atter
n
s
o
b
s
er
v
ed
i
n
th
e
in
p
u
t d
ata
.
Fig
u
r
e
6
.
B
an
d
u
n
g
C
ity
GHI
,
t
em
p
er
atu
r
e,
an
d
SICI
d
ata
t
r
e
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
o
la
r
ir
r
a
d
ia
tio
n
in
ten
s
ity
fo
r
ec
a
s
tin
g
fo
r
s
o
la
r
p
a
n
el
p
o
w
er o
u
tp
u
t
a
n
a
lyze
(
Ta
s
ma
S
u
cita
)
81
T
ab
le
3
. A
NN
m
o
d
el
er
r
o
r
r
at
es d
u
r
in
g
tr
ai
n
in
g
Tr
a
i
n
i
n
g
Le
a
r
n
i
n
g
r
a
t
e
M
o
me
n
t
u
m
I
n
p
u
t
l
a
y
e
r
H
i
d
d
e
n
l
a
y
e
r
Er
r
o
r
I
t
e
r
a
t
e
1
0
.
0
5
0
.
5
12
10
0
.
0
2
5
9
4
0
I
t
e
r
a
t
e
2
10
10
0
.
1
9
8
3
8
7
I
t
e
r
a
t
e
3
10
12
0
.
1
2
0
5
5
7
I
t
e
r
a
t
e
4
12
12
0
.
0
1
1
9
8
6
I
t
e
r
a
t
e
5
10
11
0
.
0
6
1
3
3
8
I
t
e
r
a
t
e
6
12
11
0
.
0
3
2
0
9
4
I
t
e
r
a
t
e
7
11
10
0
.
0
5
0
9
0
9
I
t
e
r
a
t
e
8
11
11
0
.
0
3
6
6
4
0
I
t
e
r
a
t
e
9
11
12
0
.
0
6
2
1
8
2
A
v
e
r
a
g
e
0
.
0
6
6
6
7
0
Up
o
n
c
o
m
p
letin
g
th
e
ANN
tr
ain
in
g
t
r
ials
,
ab
r
o
a
d
r
an
g
e
o
f
er
r
o
r
v
alu
es
was
r
ec
o
r
d
e
d
,
with
th
e
av
er
ag
e
e
r
r
o
r
r
ate
th
r
o
u
g
h
o
u
t
all
iter
atio
n
s
at
6
.
6
7
%,
p
ea
k
in
g
at
1
9
.
8
4
%
a
n
d
d
ec
r
ea
s
in
g
t
o
a
lo
w
o
f
1
.
1
2
%.
T
h
ese
n
u
m
b
er
s
will
b
e
co
n
tr
asted
ag
ain
s
t
th
e
o
u
tp
u
ts
o
f
th
e
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
a
p
p
r
o
ac
h
f
o
r
a
co
m
p
ar
ativ
e
ass
ess
m
en
t.
T
h
e
f
o
r
ec
asted
GHI
f
o
r
th
e
n
ex
t
f
iv
e
y
ea
r
s
,
as
p
r
ed
icted
u
s
in
g
th
e
ANN
m
eth
o
d
d
em
o
n
s
tr
ated
v
ar
y
in
g
er
r
o
r
r
at
es a
n
d
f
o
r
ec
ast v
al
u
es.
T
ab
le
4
o
f
f
er
s
a
co
m
p
lete
r
ev
iew
o
f
th
e
an
ticip
ated
GHI
v
alu
es
f
o
r
ea
ch
y
ea
r
f
r
o
m
2
0
2
1
to
2
0
2
5
,
ac
r
o
s
s
s
ev
er
al
ex
p
er
i
m
en
tal
m
o
d
els.
T
h
e
d
ata
s
u
g
g
ests
th
at
th
e
m
a
x
im
u
m
ex
p
ec
ted
GHI
in
ten
s
ity
is
an
ticip
ated
in
2
0
2
3
d
u
r
i
n
g
th
e
f
if
th
iter
atio
n
at
1
,
9
5
4
,
5
1
9
W
/m
²,
s
u
g
g
esti
n
g
th
at
th
is
m
o
d
el
co
n
f
ig
u
r
atio
n
wo
u
ld
p
r
o
d
u
ce
th
e
m
o
s
t
r
o
b
u
s
t
f
o
r
ec
ast
f
o
r
th
at
tim
e.
C
o
n
v
er
s
ely
,
th
e
lo
west
an
ticip
ated
GHI
em
er
g
es
in
2
0
2
5
d
u
r
i
n
g
th
e
s
ev
e
n
th
iter
ati
o
n
at
7
8
8
,
1
0
7
W
/m
²,
s
h
o
win
g
p
o
s
s
ib
le
ar
ea
s
f
o
r
m
o
d
el
d
e
v
elo
p
m
en
t.
T
h
ese
r
esu
lts
in
d
icate
t
h
e
AN
N
ap
titu
d
e
to
a
d
ap
t
t
o
c
o
m
p
lic
ated
d
a
tasets
an
d
its
p
r
o
m
is
e
f
o
r
r
e
f
in
in
g
s
o
lar
ir
r
ad
ia
n
ce
esti
m
ates.
H
o
wev
er
,
th
e
ch
an
g
es
in
f
o
r
ec
ast
ac
cu
r
ac
y
o
v
er
m
u
ltip
le
iter
atio
n
s
im
p
ly
th
at
m
o
r
e
in
-
d
e
p
th
in
v
esti
g
atio
n
s
ar
e
n
ee
d
ed
to
tu
n
e
m
o
d
el
p
ar
am
eter
s
co
n
s
tan
tly
.
B
y
ex
p
an
d
i
n
g
o
u
r
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
lin
k
a
g
es b
etwe
en
in
p
u
t
v
ar
iab
les an
d
t
h
eir
in
f
lu
en
ce
o
n
GHI
f
o
r
ec
asts
,
f
u
tu
r
e
v
er
s
io
n
s
o
f
th
e
m
o
d
el
m
i
g
h
t p
o
s
s
ib
ly
m
in
im
ize
f
o
r
ec
asti
n
g
er
r
o
r
s
an
d
b
o
o
s
t d
ep
en
d
a
b
ilit
y
f
o
r
s
o
lar
en
e
r
g
y
p
la
n
n
in
g
.
T
ab
le
4
.
Fo
r
ec
asted
GHI
b
y
A
NN
m
eth
o
d
tr
ials
Tr
a
i
n
i
n
g
G
H
I
f
o
r
e
c
a
st
i
n
g
(
W
/
m
2
)
A
v
e
r
a
g
e
(
W
/
m2
)
2
0
2
1
2
0
2
2
2
0
2
3
2
0
2
4
2
0
2
5
I
t
e
r
a
t
e
1
1
,
8
5
5
,
1
3
9
1
,
8
6
2
,
6
9
3
1
,
1
9
3
,
5
1
2
1
,
6
0
7
,
5
3
9
9
4
3
,
9
0
8
1
,
4
9
2
,
5
5
8
I
t
e
r
a
t
e
2
1
,
6
9
0
,
9
7
9
9
5
1
,
6
2
5
1
,
8
2
0
,
0
1
7
9
6
7
,
7
8
1
1
,
4
4
8
,
8
1
2
1
,
3
7
5
,
8
4
3
I
t
e
r
a
t
e
3
1
,
8
4
5
,
5
1
2
1
,
5
4
9
,
0
3
8
1
,
2
7
7
,
2
9
7
1
,
5
5
3
,
7
5
0
1
,
2
9
8
,
3
2
7
1
,
5
0
4
,
7
8
5
I
t
e
r
a
t
e
4
1
,
7
4
4
,
8
2
7
1
,
4
2
7
,
5
1
7
1
,
1
0
8
,
5
7
1
1
,
0
2
8
,
4
8
2
9
8
7
,
1
7
8
1
,
2
5
9
,
3
1
5
I
t
e
r
a
t
e
5
1
,
8
5
2
,
2
6
6
1
,
7
0
4
,
1
3
5
1
,
9
5
4
,
5
1
9
1
,
8
4
5
,
5
0
0
1
,
9
4
0
,
9
1
6
1
,
8
5
9
,
4
6
7
I
t
e
r
a
t
e
6
1
,
8
3
3
,
8
1
6
1
,
4
6
6
,
8
9
7
1
,
3
2
7
,
0
8
3
1
,
2
8
5
,
3
7
8
1
,
2
4
7
,
7
9
4
1
,
4
3
2
,
1
9
4
I
t
e
r
a
t
e
7
1
,
9
0
2
,
6
7
4
1
,
3
5
2
,
1
9
5
1
,
8
0
0
,
4
1
2
1
,
8
6
2
,
0
1
1
7
8
8
,
1
0
7
1
,
5
4
1
,
0
8
0
I
t
e
r
a
t
e
8
1
,
8
0
4
,
2
1
1
1
,
8
8
0
,
2
6
8
1
,
2
1
5
,
7
7
2
1
,
7
0
3
,
1
4
9
1
,
8
0
7
,
4
2
6
1
,
6
8
2
,
1
6
5
I
t
e
r
a
t
e
9
1
,
8
9
8
,
5
2
6
1
,
8
9
3
,
9
4
5
1
,
9
4
4
,
5
7
9
1
,
2
0
1
,
7
4
6
1
,
4
0
4
,
7
8
9
1
,
6
6
8
,
7
1
7
3
.
3
.
Co
m
pa
riso
n
perf
o
rma
nce
o
f
m
et
ho
d
T
h
e
p
er
f
o
r
m
an
ce
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
an
d
ANN
ap
p
r
o
a
ch
es
is
d
ep
en
d
e
n
t
o
n
th
e
m
o
d
els
th
at
attain
ed
th
e
lo
west
er
r
o
r
in
d
ex
f
r
o
m
ea
c
h
ap
p
r
o
ac
h
.
T
h
e
e
x
p
o
n
en
tial
s
m
o
o
th
in
g
m
o
d
el
with
a
d
a
m
p
in
g
f
ac
to
r
o
f
0
.
7
a
n
d
th
e
ANN
m
o
d
el
f
r
o
m
th
e
f
o
u
r
th
iter
atio
n
with
1
2
in
p
u
t
an
d
h
id
d
en
lay
er
s
wer
e
id
en
tifie
d
f
o
r
th
i
s
co
m
p
ar
ativ
e
s
tu
d
y
.
T
h
ese
p
ick
s
wer
e
b
ased
o
n
th
e
s
u
p
er
io
r
er
r
o
r
in
d
ices
p
r
o
d
u
ce
d
in
t
h
eir
r
esp
ec
tiv
e
a
p
p
r
o
ac
h
es.
T
h
e
s
tatis
tic
s
f
r
o
m
T
ab
le
5
,
s
h
o
wed
th
e
d
iv
er
s
e
p
r
ed
ictin
g
o
u
tco
m
es
ac
h
iev
ed
b
y
th
e
e
x
p
o
n
e
n
tial
s
m
o
o
th
in
g
a
n
d
ANN
m
eth
o
d
.
T
h
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
m
eth
o
d
g
a
v
e
r
at
h
er
s
tead
y
GHI
f
o
r
ec
asts
y
ea
r
o
v
er
y
ea
r
,
a
v
er
ag
in
g
a
n
e
x
p
ec
ted
v
alu
e
o
f
ar
o
u
n
d
1
,
8
2
4
,
0
3
2
W
/
m
2
.
I
n
co
m
p
ar
is
o
n
,
th
e
ANN
t
ec
h
n
iq
u
e
g
av
e
m
o
r
e
v
ar
iab
le
p
r
o
jectio
n
s
,
with
th
e
GHI
p
ea
k
in
g
at
1
,
7
4
4
,
8
2
7
W
/m
2
an
d
p
lu
m
m
etin
g
to
9
8
7
,
1
7
8
W
/m
2
,
d
em
o
n
s
tr
atin
g
a
co
n
s
id
er
a
b
le
d
iv
er
g
en
ce
in
th
e
p
r
ed
ictin
g
o
u
tco
m
es.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
f
o
r
ec
a
s
tin
g
r
esu
lts
b
y
m
eth
o
d
Y
e
a
r
Ex
p
o
n
e
n
t
i
a
l
sm
o
o
t
h
i
n
g
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
2
0
2
1
1
,
8
2
2
,
5
6
3
1
,
7
4
4
,
8
2
7
2
0
2
2
1
,
8
2
4
,
8
2
0
1
,
4
2
7
,
5
1
7
2
0
2
3
1
,
8
2
4
,
1
4
3
1
,
1
0
8
,
5
7
1
2
0
2
4
1
,
8
2
4
,
3
4
6
1
,
0
2
8
,
4
8
2
2
0
2
5
1
,
8
2
4
,
2
8
5
9
8
7
,
1
7
8
A
v
e
r
a
g
e
1
,
8
2
4
,
0
3
2
1
,
2
5
9
,
3
1
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
74
-
85
82
As
s
ee
n
in
Fig
u
r
e
7
,
th
e
e
r
r
o
r
r
ates
d
if
f
er
ed
d
r
am
atica
lly
b
etwe
en
th
e
two
s
tr
ateg
ies.
E
x
p
o
n
e
n
tial
s
m
o
o
th
in
g
m
ai
n
tain
ed
a
co
n
s
tan
t
er
r
o
r
r
ate
b
etwe
en
4
-
6
%,
wh
er
ea
s
ANN
d
is
p
lay
ed
ch
an
g
in
g
e
r
r
o
r
r
ates,
cu
lm
in
atin
g
at
1
9
.
8
4
%.
T
h
is
v
ar
ian
ce
is
r
elate
d
to
t
h
e
i
n
tr
i
n
s
ic
d
is
p
ar
ities
in
th
eir
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
es.
T
h
e
s
tab
ilit
y
o
f
ex
p
o
n
en
tial
s
m
o
o
t
h
in
g
im
p
lies
a
clo
s
e
alig
n
m
en
t
with
th
e
ac
tu
al
GHI
d
ata,
wh
ile
th
e
f
lex
ib
ilit
y
o
f
ANN,
co
n
tr
o
lled
b
y
th
e
ar
r
a
n
g
em
en
t
o
f
its
lay
er
s
an
d
n
eu
r
o
n
s
,
allo
ws
it
to
ca
p
tu
r
e
m
o
r
e
co
m
p
licated
p
atter
n
s
,
alb
eit
at
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Ou
r
an
aly
s
is
r
ev
ea
l
s
th
at
wh
ile
th
e
av
er
ag
e
er
r
o
r
r
ate
was
lo
wer
f
o
r
ex
p
o
n
e
n
tial
s
m
o
o
th
in
g
(
4
.
8
6
%)
co
m
p
ar
e
d
to
ANN
(
6
.
6
7
%
)
,
th
e
latter
'
s
b
est
m
o
d
el
in
th
e
f
o
u
r
th
iter
atio
n
h
a
d
th
e
lo
west
er
r
o
r
r
ate
o
f
1
.
1
2
%,
in
d
icatin
g
its
p
o
ten
tial
wh
en
o
p
tim
ally
ad
j
u
s
ted
.
T
h
is
s
h
o
ws
th
at
ANN
m
o
d
els,
with
th
eir
ca
p
ac
ity
to
in
clu
d
e
v
ar
io
u
s
p
ar
am
eter
s
an
d
alter
th
eir
lear
n
in
g
p
r
o
ce
s
s
,
co
u
ld
g
iv
e
an
ed
g
e
in
ca
p
tu
r
in
g
th
e
f
l
u
ctu
atio
n
s
o
f
s
o
lar
ir
r
ad
ian
ce
m
o
r
e
ef
f
ec
ti
v
ely
th
an
e
x
p
o
n
en
tial sm
o
o
th
i
n
g
.
Fu
tu
r
e
r
esear
ch
m
a
y
co
n
s
id
er
m
o
d
if
y
in
g
ANN
co
n
f
ig
u
r
atio
n
s
to
b
o
o
s
t
s
tab
ilit
y
an
d
m
in
im
ize
v
ar
iab
ilit
y
in
f
o
r
ec
asts
.
I
n
v
esti
g
atin
g
h
o
w
d
if
f
er
en
t
co
n
f
ig
u
r
atio
n
s
ef
f
ec
t
th
e
lear
n
in
g
p
r
o
ce
s
s
an
d
p
r
e
d
ictio
n
ac
cu
r
ac
y
m
ig
h
t
lead
to
m
o
r
e
r
o
b
u
s
t
f
o
r
ec
asti
n
g
m
o
d
els
ca
p
ab
le
o
f
r
esp
o
n
d
in
g
to
alter
in
g
en
v
ir
o
n
m
en
ta
l
v
ar
iab
les
with
o
u
t
o
v
er
f
itti
n
g
.
R
ec
en
t
d
ata
im
p
ly
th
at
th
e
r
esil
ien
ce
o
f
f
o
r
ec
asti
n
g
m
o
d
els
is
v
ital
f
o
r
tr
u
s
two
r
th
y
s
o
lar
p
o
wer
p
r
o
d
u
ctio
n
esti
m
ate.
Ou
r
f
in
d
in
g
s
g
iv
e
clea
r
ev
i
d
en
ce
th
at
th
e
c
h
o
ice
o
f
m
o
d
el
an
d
its
co
n
f
ig
u
r
atio
n
co
n
s
id
er
a
b
l
y
in
f
lu
en
ce
s
p
r
ed
ictio
n
ac
c
u
r
ac
y
,
u
n
d
e
r
s
co
r
in
g
th
e
n
ee
d
o
f
s
elec
tin
g
an
d
m
o
d
if
y
in
g
f
o
r
ec
asti
n
g
m
o
d
els b
ased
o
n
u
n
iq
u
e
g
eo
g
r
ap
h
ical
an
d
clim
atic
v
ar
iab
les
.
Fig
u
r
e
7
.
E
r
r
o
r
co
m
p
a
r
is
o
n
ac
r
o
s
s
m
eth
o
d
s
3
.
4
.
Ana
ly
ze
o
utput
po
wer
T
h
e
p
o
ten
tial
o
u
tp
u
t
o
f
s
o
lar
p
an
els
in
B
an
d
u
n
g
C
ity
h
as b
ee
n
q
u
an
titativ
ely
a
n
aly
ze
d
u
s
in
g
th
e
GHI
v
alu
es
an
ticip
ated
b
y
th
e
AN
N
ap
p
r
o
ac
h
.
A
s
o
lar
p
an
el
p
o
wer
g
en
er
atio
n
is
lar
g
ely
c
o
n
t
r
o
lled
b
y
th
e
s
o
lar
ir
r
ad
iatio
n
it
r
ec
eiv
es,
w
h
ich
in
co
n
j
u
n
ctio
n
with
th
e
p
a
n
els
ch
ar
ac
ter
is
tics
,
s
ets
th
e
f
o
u
n
d
atio
n
f
o
r
o
u
tp
u
t
p
o
wer
ca
lcu
latio
n
s
.
Su
ch
ass
ess
m
en
ts
ar
e
cr
u
cial
f
o
r
esti
m
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
a
p
h
o
to
v
o
ltaic
s
o
lar
p
o
wer
p
lan
ts
.
Usi
n
g
th
e
f
o
r
ec
asted
GH
I
d
ata
an
d
ap
p
ly
in
g
th
e
d
etails
o
f
th
e
s
o
lar
p
an
el,
we
h
av
e
esti
m
ated
th
e
p
r
o
s
p
ec
tiv
e
p
o
wer
p
r
o
d
u
ct
io
n
u
s
in
g
(
2
)
,
as in
d
icate
d
in
T
ab
le
6
.
T
ab
le
6
.
Fo
r
ec
asts
b
etwe
en
G
HI
an
d
p
o
wer
Ef
f
i
c
i
e
n
c
y
C
r
o
ss
s
e
c
t
i
o
n
a
r
e
a
Y
e
a
r
G
H
I
(
W
/
m
2
)
P
o
w
e
r
(
W
)
1
5
.
3
%
1
.
3
1
m2
2
0
2
1
1
,
7
4
4
,
8
2
7
3
4
9
,
7
1
6
2
0
2
2
1
,
4
2
7
,
5
1
7
2
8
6
,
1
1
7
2
0
2
3
1
,
1
0
8
,
5
7
1
2
2
2
,
1
9
1
2
0
2
4
1
,
0
2
8
,
4
8
2
2
0
6
,
1
3
9
2
0
2
5
9
8
7
,
1
7
8
1
9
7
,
8
6
0
A
v
e
r
a
g
e
o
u
t
p
u
t
p
o
w
e
r
(W)
2
5
2
,
4
0
5
T
ab
le
6
p
r
esen
ts
th
e
p
o
wer
o
u
tp
u
t
esti
m
atio
n
s
b
ased
o
n
th
e
ANN
p
r
o
jecte
d
GHI
v
alu
es,
u
s
in
g
th
e
ch
ar
ac
ter
is
tics
o
f
a
ty
p
ical
GH2
0
0
M4
8
s
o
lar
p
an
el
with
an
ef
f
icien
cy
o
f
1
5
.
3
%
an
d
a
c
r
o
s
s
-
s
ec
tio
n
al
ar
ea
o
f
1
.
3
1
m
2
.
T
h
ese
s
p
ec
s
g
iv
e
a
d
etailed
v
iew
in
to
th
e
p
o
wer
p
o
ten
tial,
elim
in
atin
g
o
th
er
ess
en
tial
elem
en
ts
s
u
ch
as
o
p
e
r
atio
n
al
tem
p
e
r
atu
r
e,
in
clin
atio
n
an
g
le,
p
o
wer
lo
s
s
,
a
n
d
e
x
tr
a
c
o
m
p
o
n
en
t
s
p
ec
if
icatio
n
s
.
Fro
m
th
e
d
ata,
we
f
in
d
a
s
tead
y
f
all
in
y
ea
r
ly
o
u
tp
u
t,
s
tr
o
n
g
ly
ass
o
ciate
d
with
th
e
GHI
v
alu
es
wh
er
e
g
r
ea
ter
an
n
u
al
GHI
lead
s
to
an
in
cr
ea
s
e
i
n
elec
tr
i
ca
l
p
o
wer
g
en
e
r
a
tio
n
p
o
ten
tia
l.
T
h
u
s
,
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
s
o
lar
p
an
els
is
ess
en
tially
co
n
n
ec
ted
to
th
e
i
n
ten
s
ity
o
f
GHI
.
Ov
er
t
h
e
f
o
r
ec
ast
p
er
io
d
f
r
o
m
2
0
2
1
t
o
2
0
2
5
,
th
e
av
er
ag
e
a
n
n
u
al
en
er
g
y
p
r
o
d
u
ctio
n
is
ex
p
ec
ted
at
2
5
2
,
4
0
5
w
atts
,
with
th
e
to
t
al
p
o
ten
tial
p
o
we
r
o
u
t
p
u
t
esti
m
ated
at
1
,
2
6
2
,
0
2
3
w
atts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
o
la
r
ir
r
a
d
ia
tio
n
in
ten
s
ity
fo
r
ec
a
s
tin
g
fo
r
s
o
la
r
p
a
n
el
p
o
w
er o
u
tp
u
t
a
n
a
lyze
(
Ta
s
ma
S
u
cita
)
83
T
h
is
s
tu
d
y
h
ig
h
lig
h
ts
th
e
d
i
r
ec
t
ass
o
ciatio
n
b
etwe
en
GHI
an
d
th
e
o
u
tp
u
t
p
o
wer
o
f
s
o
lar
p
an
els,
s
tr
ess
in
g
th
e
n
ec
ess
ity
o
f
ex
ac
t
an
d
d
ep
e
n
d
ab
le
s
o
lar
ir
r
a
d
ian
ce
p
r
e
d
ictio
n
s
.
Fu
tu
r
e
s
tu
d
y
s
h
o
u
ld
aim
o
n
b
o
o
s
tin
g
th
e
ac
c
u
r
ac
y
o
f
G
HI
f
o
r
e
ca
s
ts
,
p
o
ten
tially
u
s
in
g
m
o
r
e
ad
v
a
n
ce
d
ANN
m
o
d
els
o
r
alter
n
ativ
e
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es
th
at
co
m
b
in
e
wid
er
clim
ate
d
ata
co
m
p
o
n
en
ts
.
Ad
d
itio
n
al
ly
,
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
im
p
licatio
n
s
o
f
d
if
f
e
r
en
t
s
o
lar
p
an
el
ef
f
icien
cies
an
d
c
o
n
f
ig
u
r
atio
n
s
ac
r
o
s
s
d
iv
er
s
e
en
v
ir
o
n
m
en
tal
cir
cu
m
s
tan
ce
s
m
ig
h
t
f
u
r
th
er
en
h
a
n
ce
en
er
g
y
p
r
o
d
u
ctio
n
p
r
o
jectio
n
s
an
d
s
o
lar
p
lan
t
p
er
f
o
r
m
an
ce
.
T
h
e
f
i
n
d
in
g
s
f
r
o
m
th
is
in
v
esti
g
atio
n
clea
r
ly
illu
s
tr
ate
th
at
th
e
ef
f
ec
tiv
e
n
ess
o
f
s
o
lar
p
an
els
in
co
n
v
er
tin
g
s
o
lar
ir
r
ad
ian
ce
to
elec
tr
ic
ity
is
d
ir
ec
tly
co
n
tr
o
lled
b
y
th
e
v
ar
y
in
g
lev
els
o
f
G
HI
,
r
ath
er
th
an
ju
s
t
b
y
tech
n
o
lo
g
ical
elem
en
ts
o
f
th
e
p
an
els
o
r
ex
ter
n
al
clim
atic
v
ar
iab
les.
T
h
is
as
s
o
ciati
o
n
is
ess
en
tial
f
o
r
r
eg
u
lato
r
s
an
d
in
v
esto
r
s
in
th
e
s
o
lar
en
er
g
y
s
ec
to
r
,
as
it
s
t
r
ess
es
th
e
n
ec
e
s
s
ity
f
o
r
s
o
p
h
is
ticated
f
o
r
ec
asti
n
g
m
eth
o
d
s
to
o
p
tim
ize
th
e
u
tili
ty
an
d
p
r
o
f
itab
ilit
y
o
f
s
o
lar
en
e
r
g
y
in
s
tallatio
n
s
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
s
et
o
u
t
to
test
th
e
u
s
ef
u
ln
ess
o
f
th
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
an
d
ANN
m
eth
o
d
in
f
o
r
ec
asti
n
g
th
e
GHI
f
o
r
B
an
d
u
n
g
C
ity
.
T
h
e
ex
p
o
n
en
tial
s
m
o
o
th
in
g
m
eth
o
d
ex
h
i
b
ited
en
c
o
u
r
ag
in
g
r
esu
lts
in
its
s
ev
en
th
iter
atio
n
,
ap
p
ly
in
g
a
d
am
p
in
g
f
ac
to
r
o
f
0
.
7
an
d
o
b
tain
in
g
an
er
r
o
r
r
ate
o
f
4
.
4
4
%.
T
h
e
GHI
v
alu
es
v
ar
ied
f
r
o
m
a
l
o
w
o
f
1
,
8
2
2
,
5
6
6
3
W
/m
2
in
2
0
2
1
to
a
m
a
x
im
u
m
o
f
1
,
8
2
4
,
8
2
0
W
/m
2
in
2
0
2
2
,
a
v
er
ag
in
g
1
,
8
2
4
,
0
3
2
W
/m
2
y
e
ar
ly
.
T
h
e
ANN
m
eth
o
d
,
h
o
wev
er
,
s
u
r
p
a
s
s
ed
th
is
p
er
f
o
r
m
an
ce
in
its
f
o
u
r
th
iter
atio
n
,
with
a
co
m
p
licated
d
esig
n
o
f
1
2
in
p
u
t
an
d
h
id
d
en
lay
er
s
,
o
b
tain
in
g
a
co
n
s
id
er
ab
ly
r
ed
u
ce
d
er
r
o
r
r
ate
o
f
1
.
1
2
%.
T
h
e
GHI
r
an
g
ed
f
r
o
m
a
lo
w
o
f
9
8
7
,
1
7
8
W
/m
2
in
2
0
2
5
to
a
h
ig
h
o
f
1
,
7
4
4
,
8
2
7
W
/m
2
in
2
0
2
1
,
av
er
ag
in
g
1
,
2
5
9
,
3
1
5
W
/m
2
y
ea
r
ly
.
T
h
e
co
m
p
ar
is
o
n
r
esear
c
h
in
d
i
s
p
u
tab
ly
r
ev
ea
ls
th
e
g
r
ea
ter
ac
cu
r
ac
y
o
f
th
e
ANN
m
eth
o
d
in
p
r
ed
ictin
g
GHI
,
as
in
d
ic
ated
b
y
its
r
ed
u
c
ed
er
r
o
r
r
ate.
T
h
e
r
am
if
icatio
n
s
f
o
r
s
o
lar
p
o
wer
g
e
n
er
atio
n
a
r
e
en
o
r
m
o
u
s
,
with
th
e
an
ticip
ated
G
HI
v
alu
es
d
ir
ec
tly
g
u
i
d
in
g
t
h
e
p
o
s
s
ib
le
en
er
g
y
y
ield
.
Ov
er
th
e
2
0
2
1
–
2
0
2
5
p
er
io
d
,
th
e
av
er
ag
e
p
o
wer
p
r
o
d
u
ctio
n
is
p
r
ed
icted
to
b
e
2
5
2
,
4
0
5
w
att
with
a
h
ig
h
o
f
3
4
9
,
7
1
6
w
att
in
2
0
2
1
an
d
a
lo
w
o
f
1
9
7
,
8
6
0
w
att
in
2
0
2
5
.
C
o
n
s
e
q
u
en
tly
,
a
s
o
lar
p
a
n
el
with
a
s
p
ec
if
icatio
n
o
f
1
5
.
3
%
ef
f
icien
cy
a
n
d
1
.
3
1
m
2
s
u
r
f
ac
e
ar
e
co
u
ld
g
e
n
er
ate
a
to
tal
o
f
1
,
2
6
2
,
023
w
att
th
r
o
u
g
h
o
u
t
th
is
f
iv
e
y
ea
r
tim
e
f
r
am
e.
W
h
ile
th
e
co
n
c
l
u
s
io
n
s
o
f
th
is
r
esear
ch
ar
e
in
f
o
r
m
ativ
e,
th
e
lim
itatio
n
s
o
win
g
t
o
th
e
d
atase
t’
s
b
r
ea
d
th
an
d
th
e
r
a
n
g
e
o
f
ch
ar
ac
te
r
is
tics
em
p
lo
y
e
d
s
h
o
u
ld
b
e
ac
k
n
o
wled
g
ed
.
Fu
t
u
r
e
s
tu
d
y
co
u
ld
ex
am
in
e
i
n
cr
ea
s
in
g
th
e
d
ataset
an
d
in
clu
d
i
n
g
a
lar
g
er
ar
r
ay
o
f
f
ac
to
r
s
to
b
o
o
s
t
th
e
p
r
ec
is
io
n
o
f
th
e
p
r
o
jec
tio
n
s
.
Ad
d
itio
n
ally
,
em
p
lo
y
in
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
tr
ial
an
d
er
r
o
r
a
p
p
r
o
ac
h
with
s
ev
er
al
iter
atio
n
s
m
ay
en
h
an
ce
th
e
m
o
d
els
f
u
r
th
er
.
I
t
is
also
e
n
co
u
r
a
g
ed
to
s
tu
d
y
an
d
in
teg
r
ate
m
o
r
e
co
m
p
lex
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es
to
en
h
an
ce
th
e
ac
cu
r
ac
y
o
f
GHI
f
o
r
ec
asts
.
T
h
is
wo
r
k
s
ee
k
s
to
ac
t
as
a
s
p
r
in
g
b
o
a
r
d
f
o
r
o
n
g
o
in
g
r
esear
ch
in
th
is
s
ec
to
r
,
s
ee
k
in
g
to
p
r
o
g
r
ess
iv
ely
p
er
f
e
ct
th
e
f
o
r
ec
asti
n
g
m
o
d
els
f
o
r
s
o
lar
ir
r
ad
ian
ce
an
d
co
n
tr
ib
u
te
to
th
e
o
p
tim
izatio
n
o
f
s
o
lar
en
e
r
g
y
h
ar
n
ess
in
g
s
y
s
tem
s
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
K
.
N
e
m
a
t
c
h
o
u
a
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
p
h
a
se
c
h
a
n
g
e
m
a
t
e
r
i
a
l
s,
t
h
e
r
m
a
l
i
n
s
u
l
a
t
i
o
n
,
a
n
d
e
x
t
e
r
n
a
l
s
h
a
d
i
n
g
f
o
r
t
h
e
r
m
a
l
c
o
mf
o
r
t
i
mp
r
o
v
e
me
n
t
a
n
d
c
o
o
l
i
n
g
e
n
e
r
g
y
d
e
man
d
r
e
d
u
c
t
i
o
n
i
n
a
n
o
f
f
i
c
e
b
u
i
l
d
i
n
g
u
n
d
e
r
d
i
f
f
e
r
e
n
t
c
o
a
s
t
a
l
t
r
o
p
i
c
a
l
c
l
i
m
a
t
e
s,”
S
o
l
a
r
E
n
e
r
g
y
,
v
o
l
.
2
0
7
,
p
p
.
4
5
8
–
4
7
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
o
l
e
n
e
r
.
2
0
2
0
.
0
6
.
1
1
0
.
[
2
]
S
.
K
u
ş
k
a
y
a
,
F
.
B
i
l
g
i
l
i
,
E
.
M
u
ğ
a
l
o
ğ
l
u
,
K
.
K
h
a
n
,
M
.
E
.
H
o
q
u
e
,
a
n
d
N
.
T
o
g
u
ç
,
“
T
h
e
r
o
l
e
o
f
so
l
a
r
e
n
e
r
g
y
u
sa
g
e
i
n
e
n
v
i
r
o
n
m
e
n
t
a
l
su
st
a
i
n
a
b
i
l
i
t
y
:
F
r
e
s
h
e
v
i
d
e
n
c
e
t
h
r
o
u
g
h
t
i
m
e
-
f
r
e
q
u
e
n
c
y
a
n
a
l
y
ses
,
”
Re
n
e
w
E
n
e
r
g
y
,
v
o
l
.
2
0
6
,
p
p
.
8
5
8
–
8
7
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
n
e
n
e
.
2
0
2
3
.
0
2
.
0
6
3
.
[
3
]
W
.
D
i
n
g
a
n
d
T.
B
a
u
e
r
,
“
P
r
o
g
r
e
ss
i
n
r
e
sea
r
c
h
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
m
o
l
t
e
n
c
h
l
o
r
i
d
e
s
a
l
t
t
e
c
h
n
o
l
o
g
y
f
o
r
n
e
x
t
g
e
n
e
r
a
t
i
o
n
c
o
n
c
e
n
t
r
a
t
e
d
so
l
a
r
p
o
w
e
r
p
l
a
n
t
s
,”
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
3
3
4
–
3
4
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
.
2
0
2
0
.
0
6
.
0
2
7
.
[
4
]
N
.
K
r
i
s
h
n
a
n
,
K
.
R
.
K
u
mar,
a
n
d
C
.
S
.
I
n
d
a
,
“
H
o
w
s
o
l
a
r
r
a
d
i
a
t
i
o
n
f
o
r
e
c
a
st
i
n
g
i
m
p
a
c
t
s
t
h
e
u
t
i
l
i
z
a
t
i
o
n
o
f
so
l
a
r
e
n
e
r
g
y
:
A
c
r
i
t
i
c
a
l
r
e
v
i
e
w
,
”
J
C
l
e
a
n
Pro
d
,
v
o
l
.
3
8
8
,
p
.
1
3
5
8
6
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
e
p
r
o
.
2
0
2
3
.
1
3
5
8
6
0
.
[
5
]
G
.
E.
H
a
l
k
o
s
a
n
d
E.
C
.
G
k
a
m
p
o
u
r
a
,
“
R
e
v
i
e
w
i
n
g
u
s
a
g
e
,
p
o
t
e
n
t
i
a
l
s
,
a
n
d
l
i
mi
t
a
t
i
o
n
s
o
f
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
so
u
r
c
e
s,”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
3
,
n
o
.
1
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
1
1
2
9
0
6
.
[
6
]
J.
T.
P
u
t
r
a
,
S
a
r
j
i
y
a
,
a
n
d
M
.
I
.
B
.
S
e
t
y
o
n
e
g
o
r
o
,
“
M
o
d
e
l
i
n
g
o
f
h
i
g
h
u
n
c
e
r
t
a
i
n
t
y
p
h
o
t
o
v
o
l
t
a
i
c
g
e
n
e
r
a
t
i
o
n
i
n
q
u
a
s
i
d
y
n
a
mi
c
p
o
w
e
r
f
l
o
w
o
n
d
i
st
r
i
b
u
t
i
o
n
sy
st
e
ms:
A
c
a
s
e
st
u
d
y
i
n
Ja
v
a
I
sl
a
n
d
,
I
n
d
o
n
e
si
a
,
”
R
e
su
l
t
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
1
,
p
.
1
0
1
7
4
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
3
.
1
0
1
7
4
7
.
[
7
]
D
.
A
r
y
a
n
i
,
S
.
P
r
a
n
o
t
o
,
F
.
F
a
j
a
r
,
A
.
N
.
I
n
t
a
n
g
,
a
n
d
F
.
Z
.
R
h
a
ma
d
h
a
n
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
p
r
e
d
i
c
t
i
o
n
t
o
i
d
e
n
t
i
f
y
so
l
a
r
e
n
e
r
g
y
p
o
t
e
n
t
i
a
l
i
n
E
a
st
e
r
n
I
n
d
o
n
e
si
a
,
”
i
n
2
0
2
3
I
EE
E
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
i
n
P
o
w
e
r
En
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
(
I
C
PE
A)
,
2
0
2
3
,
p
p
.
2
5
2
–
257
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
EA
5
6
9
1
8
.
2
0
2
3
.
1
0
0
9
3
1
8
4
.
[
8
]
D
.
A
.
W
i
d
o
d
o
,
P
.
P
u
r
w
a
n
t
o
,
a
n
d
H
.
H
e
r
maw
a
n
,
“
M
o
d
e
l
i
n
g
s
o
l
a
r
p
o
t
e
n
t
i
a
l
i
n
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
si
a
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
,
v
o
l
.
1
9
,
n
o
.
3
,
p
p
.
5
7
8
–
5
8
5
,
2
0
2
1
,
d
o
i
:
1
0
.
5
9
3
7
/
j
a
e
s0
-
2
9
0
2
5
.
[
9
]
S
.
S
.
H
o
s
sei
n
i
D
e
h
s
h
i
r
i
a
n
d
B
.
F
i
r
o
o
z
a
b
a
d
i
,
“
C
o
m
p
a
r
i
s
o
n
,
e
v
a
l
u
a
t
i
o
n
a
n
d
p
r
i
o
r
i
t
i
z
a
t
i
o
n
o
f
s
o
l
a
r
p
h
o
t
o
v
o
l
t
a
i
c
t
r
a
c
k
i
n
g
s
y
st
e
ms
u
si
n
g
mu
l
t
i
c
r
i
t
e
r
i
a
d
e
c
i
si
o
n
ma
k
i
n
g
met
h
o
d
s,
”
S
u
s
t
a
i
n
a
b
l
e
En
e
r
g
y
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
Assessm
e
n
t
s
,
v
o
l
.
5
5
,
p
.
1
0
2
9
8
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
se
t
a
.
2
0
2
2
.
1
0
2
9
8
9
.
[
1
0
]
W
.
H
.
Te
e
,
C
.
K
.
G
a
n
,
a
n
d
J
.
S
a
r
d
i
,
“
B
e
n
e
f
i
t
s
o
f
e
n
e
r
g
y
s
t
o
r
a
g
e
s
y
st
e
ms
a
n
d
i
t
s
p
o
t
e
n
t
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s
i
n
M
a
l
a
y
si
a
:
A
r
e
v
i
e
w
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
9
2
,
p
.
1
1
4
2
1
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
s
e
r
.
2
0
2
3
.
1
1
4
2
1
6
.
[
1
1
]
P
.
K
u
m
a
r
i
a
n
d
D
.
T
o
sh
n
i
w
a
l
,
“
D
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
s
o
l
a
r
i
r
r
a
d
i
a
n
c
e
f
o
r
e
c
a
st
i
n
g
:
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
C
l
e
a
n
e
r
Pr
o
d
u
c
t
i
o
n
,
v
o
l
.
3
1
8
,
p
.
1
2
8
5
6
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
e
p
r
o
.
2
0
2
1
.
1
2
8
5
6
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.