I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
wer
E
lect
ro
nics
a
nd
Driv
e
S
y
s
t
em
(
I
J
P
E
DS)
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
2
1
0
1
~
2
1
1
1
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
1
7
.
i
3
.
p
p
2
1
0
1
-
2
1
1
1
2101
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
M
ulti
-
o
utpu
t
d
ee
p learning
f
ra
mewo
rk f
o
r
joint
for
ecas
ting o
f
so
la
r irradia
nce and wind
speed
wi
th
cros
s
-
regi
o
na
l
trans
ferability
an
a
ly
sis
S.
Selv
i
1
,
Anna
m
a
la
i Mu
t
hu
2
,
M
ura
li Na
ra
y
a
na
m
urt
hy
2
,
B
.
Ardly
M
el
ba
Ree
na
3
,
G
o
bim
o
ha
n
S
iv
a
s
ub
ra
m
a
nia
n
2
,
T
.
L
o
g
eswa
ra
n
4
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
P
a
n
i
m
a
l
a
r
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
S
e
c
t
i
o
n
,
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
s
i
t
y
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s (
U
TA
S
)
,
N
i
z
w
a
,
O
ma
n
3
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
S
.
A
.
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
K
o
n
g
u
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
P
e
r
u
n
d
u
r
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
1
,
2
0
2
5
R
ev
is
ed
J
u
l 2
8
,
2
0
2
6
Acc
ep
ted
Au
g
1
4
,
2
0
2
6
Ac
c
u
ra
te
f
o
re
c
a
st
i
n
g
o
f
s
o
lar
i
r
ra
d
ia
n
c
e
a
n
d
wi
n
d
s
p
e
e
d
is
e
ss
e
n
ti
a
l
f
o
r
im
p
r
o
v
i
n
g
h
y
b
ri
d
re
n
e
w
a
b
le
e
n
e
r
g
y
s
y
ste
m
s
a
n
d
e
n
s
u
ri
n
g
g
ri
d
st
a
b
il
it
y
.
T
h
i
s
st
u
d
y
d
e
v
e
l
o
p
s
a
n
d
e
v
a
l
u
a
tes
a
m
u
l
t
i
-
o
u
t
p
u
t
d
e
e
p
lea
r
n
i
n
g
f
ra
m
e
w
o
r
k
f
o
r
t
h
e
sim
u
l
ta
n
e
o
u
s p
re
d
i
c
t
i
o
n
o
f
g
l
o
b
a
l
h
o
r
iz
o
n
t
a
l
ir
ra
d
i
a
n
c
e
(G
HI
)
a
n
d
w
in
d
s
p
e
e
d
a
c
r
o
ss
m
u
l
t
ip
le
I
n
d
ia
n
re
g
i
o
n
s.
H
o
u
r
l
y
d
a
ta
f
r
o
m
t
h
e
Na
t
i
o
n
a
l
S
o
la
r
Ra
d
iat
i
o
n
Da
ta
b
a
se
(N
S
R
DB)
f
o
r
t
h
e
p
e
r
io
d
2
0
1
5
–
2
0
2
0
we
re
u
se
d
t
o
t
ra
i
n
li
g
h
t
g
ra
d
ie
n
t
b
o
o
st
i
n
g
m
a
c
h
i
n
e
(
Li
g
h
tG
BM
)
,
l
o
n
g
s
h
o
r
t
-
term
m
e
m
o
r
y
(
L
S
T
M)
,
b
i
d
ir
e
c
t
i
o
n
a
l
l
o
n
g
s
h
o
r
t
-
term
m
e
m
o
r
y
(B
iL
S
TM
)
,
a
n
d
c
o
n
v
o
l
u
t
i
o
n
a
l
l
o
n
g
sh
o
r
t
-
te
rm
m
e
m
o
r
y
(
C
o
n
v
L
S
T
M
)
m
o
d
e
ls,
wi
t
h
c
r
o
ss
-
re
g
i
o
n
a
l
t
ra
n
sfe
r
lea
r
n
i
n
g
a
p
p
li
e
d
a
c
r
o
s
s
Tam
il
Na
d
u
,
Ke
ra
l
a
,
Ka
rn
a
ta
k
a
,
a
n
d
A
n
d
h
r
a
P
ra
d
e
s
h
.
Am
o
n
g
t
h
e
m
o
d
e
ls,
C
o
n
v
L
S
TM
a
c
h
ie
v
e
d
th
e
b
e
s
t
p
e
r
f
o
rm
a
n
c
e
wi
th
a
m
e
a
n
a
b
s
o
l
u
te
e
r
r
o
r
(
M
AE
)
o
f
0
.
0
6
1
a
n
d
a
n
R
²
v
a
l
u
e
o
f
a
p
p
r
o
x
ima
tel
y
0
.
9
1
,
w
h
il
e
Bi
LS
T
M
d
e
m
o
n
s
tra
te
d
c
o
m
p
a
ra
b
le
a
c
c
u
ra
c
y
wi
t
h
l
o
we
r
c
o
m
p
u
ta
ti
o
n
a
l
c
o
s
t
.
T
h
e
p
r
o
p
o
se
d
f
ra
m
e
w
o
r
k
e
m
p
h
a
s
ize
s
c
r
o
ss
-
re
g
i
o
n
a
l
tra
n
sfe
ra
b
il
i
ty
,
d
e
m
o
n
s
tra
ti
n
g
r
o
b
u
s
t
g
e
n
e
ra
li
z
a
t
i
o
n
a
c
r
o
ss
h
e
ter
o
g
e
n
e
o
u
s
c
l
ima
ti
c
c
o
n
d
i
t
i
o
n
s.
Err
o
r
d
is
tr
i
b
u
t
i
o
n
a
n
a
l
y
si
s
f
u
r
th
e
r
i
n
d
ica
tes
im
p
r
o
v
e
d
p
re
d
ic
ti
o
n
sta
b
i
li
t
y
,
wit
h
C
o
n
v
L
S
TM
e
x
h
i
b
it
i
n
g
l
o
w
e
r
v
a
r
ia
b
i
l
it
y
c
o
m
p
a
re
d
t
o
o
t
h
e
r
m
o
d
e
ls
.
T
h
e
se
re
s
u
l
ts
s
u
p
p
o
r
t
sc
a
la
b
le
a
n
d
re
l
ia
b
le
re
n
e
wa
b
le
e
n
e
r
g
y
f
o
re
c
a
s
ti
n
g
,
wi
t
h
p
ra
c
t
ica
l
im
p
li
c
a
t
i
o
n
s
fo
r
g
r
i
d
o
p
e
ra
t
i
o
n
,
p
o
w
e
r
e
lec
tr
o
n
ic
c
o
n
t
r
o
l
,
a
n
d
h
y
b
r
i
d
e
n
e
r
g
y
s
y
s
tem
m
a
n
a
g
e
m
e
n
t
.
K
ey
w
o
r
d
s
:
C
lim
ate
v
ar
iab
ilit
y
C
r
o
s
s
-
r
eg
io
n
al
co
r
r
elatio
n
Dee
p
lear
n
in
g
m
o
d
els
R
en
ewa
b
le
f
o
r
ec
asti
n
g
Sp
atio
tem
p
o
r
al
an
aly
s
is
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
:
S.
Selv
i
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
Pan
i
m
alar
E
n
g
in
ee
r
in
g
C
o
lleg
e
C
h
en
n
ai
,
T
am
il
N
ad
u
,
I
n
d
ia
E
m
ail:
s
elv
is
elv
ar
aj@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
R
en
e
wa
b
l
e
en
e
r
g
y
d
e
p
l
o
y
m
e
n
t
is
r
a
p
i
d
l
y
i
n
c
r
e
asi
n
g
w
o
r
l
d
wi
d
e
,
m
ak
in
g
a
cc
u
r
at
e
f
o
r
ec
asti
n
g
o
f
s
o
la
r
ir
r
a
d
ia
n
ce
an
d
wi
n
d
s
p
ee
d
ess
e
n
ti
al
f
o
r
e
n
s
u
r
i
n
g
g
r
id
s
tab
ilit
y
,
e
f
f
i
cie
n
t
e
n
e
r
g
y
d
is
p
at
c
h
,
a
n
d
r
ed
u
ce
d
em
is
s
io
n
s
[
1
]
,
[
2
]
.
As
t
h
e
p
en
e
tr
a
ti
o
n
o
f
r
en
ew
ab
le
s
o
u
r
c
es
c
o
n
ti
n
u
es
t
o
g
r
o
w
,
s
y
s
te
m
o
p
e
r
ato
r
s
r
e
q
u
i
r
e
p
r
ec
is
e
an
d
r
e
lia
b
l
e
p
r
e
d
i
cti
o
n
s
t
o
m
ain
tai
n
s
u
p
p
l
y
–
d
em
a
n
d
b
al
an
ce
a
n
d
m
in
im
i
ze
e
n
e
r
g
y
w
ast
ag
e
[
3
]
.
T
r
a
d
iti
o
n
a
l
p
h
y
s
i
ca
l
a
n
d
n
u
m
e
r
i
ca
l
we
at
h
e
r
p
r
e
d
ic
ti
o
n
(
NW
P
)
m
o
d
e
l
s
,
al
th
o
u
g
h
e
f
f
ec
t
iv
e
f
o
r
la
r
g
e
-
s
ca
l
e
at
m
o
s
p
h
er
ic
d
y
n
am
ics
,
o
f
te
n
f
a
il
to
c
a
p
t
u
r
e
l
o
c
ali
ze
d
m
e
te
o
r
o
lo
g
i
ca
l
v
a
r
ia
ti
o
n
s
a
n
d
m
i
cr
o
c
li
m
ati
c
ef
f
ec
ts
,
p
a
r
t
ic
u
la
r
l
y
i
n
tr
o
p
ic
al
r
e
g
i
o
n
s
s
u
ch
as
s
o
u
t
h
er
n
I
n
d
ia
[
4
]
,
[
5
]
.
T
o
o
v
er
co
m
e
t
h
ese
li
m
it
ati
o
n
s
,
m
ac
h
i
n
e
le
ar
n
i
n
g
(
M
L
)
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
2101
-
2
1
1
1
2102
d
e
ep
l
ea
r
n
in
g
(
D
L
)
ap
p
r
o
ac
h
es
h
av
e
em
er
g
ed
as
p
o
w
e
r
f
u
l
al
t
er
n
a
ti
v
es
ca
p
a
b
l
e
o
f
m
o
d
ell
in
g
c
o
m
p
l
ex
n
o
n
l
in
ea
r
r
el
ati
o
n
s
h
i
p
s
b
etw
ee
n
m
ete
o
r
o
lo
g
ic
al
v
a
r
i
ab
les
a
n
d
r
e
n
ew
a
b
l
e
e
n
e
r
g
y
o
u
t
p
u
ts
[
6
]
-
[
8
]
.
T
h
es
e
m
o
d
els
l
e
v
e
r
a
g
e
lar
g
e
-
s
ca
l
e
d
atas
ets
,
in
cl
u
d
i
n
g
g
r
o
u
n
d
m
ea
s
u
r
e
m
e
n
ts
,
s
at
ell
ite
-
d
er
iv
e
d
o
b
s
e
r
v
at
io
n
s
,
a
n
d
r
e
an
al
y
s
is
d
at
a,
t
o
p
r
o
d
u
c
e
a
d
a
p
ti
v
e
a
n
d
d
a
ta
-
d
r
i
v
e
n
f
o
r
e
ca
s
ts
.
E
n
s
em
b
l
e
-
b
as
e
d
te
c
h
n
iq
u
es
s
u
c
h
as
r
an
d
o
m
f
o
r
est
(
R
F)
,
g
r
ad
ie
n
t
b
o
o
s
t
in
g
(
GB
)
,
e
x
t
r
e
m
e
g
r
a
d
i
e
n
t
b
o
o
s
ti
n
g
(
X
GB
o
o
s
t
)
,
a
n
d
ca
teg
o
r
i
ca
l
b
o
o
s
t
in
g
(
C
atB
o
o
s
t
)
h
a
v
e
d
e
m
o
n
s
t
r
ate
d
r
o
b
u
s
t
n
ess
i
n
h
a
n
d
li
n
g
n
o
is
y
an
d
in
c
o
m
p
l
ete
d
at
a
w
h
i
le
ac
h
ie
v
i
n
g
h
i
g
h
p
r
e
d
i
cti
v
e
a
cc
u
r
ac
y
[
9
]
,
[
1
0
]
.
D
ee
p
lea
r
n
i
n
g
a
r
c
h
i
tec
tu
r
es
,
p
ar
tic
u
l
ar
l
y
l
o
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
(
L
S
T
M
)
an
d
c
o
n
v
o
l
u
t
io
n
a
l
L
S
T
M
(
C
o
n
v
L
STM
)
,
h
a
v
e
s
h
o
w
n
s
u
p
er
io
r
p
e
r
f
o
r
m
a
n
c
e
i
n
ti
m
e
-
s
e
r
i
es
f
o
r
ec
asti
n
g
o
f
s
o
l
ar
ir
r
a
d
i
a
n
ce
a
n
d
wi
n
d
s
p
e
ed
b
y
e
f
f
ec
ti
v
el
y
ca
p
t
u
r
in
g
te
m
p
o
r
al
d
e
p
e
n
d
e
n
cies
a
n
d
s
p
ati
al
v
ar
iat
io
n
s
[
1
1
]
-
[
1
3
]
.
T
h
ese
m
o
d
els
o
u
t
p
e
r
f
o
r
m
c
o
n
v
en
ti
o
n
al
s
tatis
t
ic
al
m
e
th
o
d
s
s
u
ch
as
A
R
I
MA
a
n
d
SAR
I
MA
b
y
d
y
n
am
i
ca
l
ly
l
ea
r
n
in
g
e
v
o
l
v
i
n
g
w
ea
t
h
e
r
p
att
er
n
s
[
1
4
]
.
Mo
r
e
r
ec
e
n
tl
y
,
t
r
a
n
s
f
o
r
m
e
r
-
b
a
s
ed
m
o
d
e
ls
h
a
v
e
b
ee
n
in
tr
o
d
u
ce
d
to
c
a
p
t
u
r
e
lo
n
g
-
r
an
g
e
d
e
p
en
d
e
n
cies
t
h
r
o
u
g
h
atte
n
t
io
n
m
ec
h
a
n
is
m
s
[
1
5
]
,
[
1
6
]
.
H
o
w
e
v
e
r
,
d
es
p
ite
t
h
e
ir
s
tr
o
n
g
p
er
f
o
r
m
an
ce
,
t
r
a
n
s
f
o
r
m
er
m
o
d
els
t
y
p
ic
all
y
r
e
q
u
i
r
e
s
ig
n
i
f
i
ca
n
tl
y
h
ig
h
er
c
o
m
p
u
t
ati
o
n
al
r
es
o
u
r
c
es
an
d
l
ar
g
e
-
s
c
ale
t
r
a
in
in
g
d
ata
,
wh
i
ch
m
ay
li
m
i
t
t
h
e
ir
p
r
ac
tic
al
d
e
p
l
o
y
m
e
n
t
in
r
e
al
-
tim
e
r
en
ewa
b
l
e
e
n
e
r
g
y
s
y
s
t
e
m
s
.
T
h
is
m
o
ti
v
a
tes
t
h
e
u
s
e
o
f
C
o
n
v
L
ST
M
as
a
co
m
p
u
tati
o
n
a
ll
y
ef
f
i
cie
n
t
a
lte
r
n
at
iv
e
wit
h
s
tr
o
n
g
s
p
a
ti
o
te
m
p
o
r
al
m
o
d
e
lli
n
g
ca
p
a
b
i
lit
y
.
W
h
i
l
e
e
x
is
ti
n
g
m
a
c
h
i
n
e
l
e
a
r
n
in
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
h
a
v
e
d
e
m
o
n
s
t
r
a
t
e
d
s
t
r
o
n
g
p
r
e
d
i
c
t
i
v
e
p
e
r
f
o
r
m
a
n
c
e
,
m
o
s
t
s
t
u
d
i
es
f
o
cu
s
o
n
s
i
n
g
l
e
-
o
u
t
p
u
t
p
r
e
d
i
c
t
i
o
n
a
n
d
s
i
t
e
-
s
p
ec
i
f
i
c
m
o
d
e
ls
,
l
i
m
it
i
n
g
t
h
e
i
r
a
b
i
l
it
y
t
o
f
u
l
l
y
e
x
p
l
o
i
t
t
h
e
i
n
t
e
r
d
e
p
e
n
d
e
n
c
e
b
e
t
w
e
e
n
m
u
l
ti
p
l
e
r
e
n
e
w
a
b
le
v
a
r
i
a
b
l
e
s
.
F
u
r
t
h
e
r
m
o
r
e
,
m
a
n
y
a
p
p
r
o
a
c
h
e
s
d
o
n
o
t
e
x
p
l
i
c
i
tl
y
c
o
n
s
i
d
e
r
c
r
o
s
s
-
r
e
g
i
o
n
a
l
g
e
n
e
r
a
l
i
za
t
i
o
n
,
w
h
i
c
h
i
s
ess
e
n
t
i
al
f
o
r
s
ca
l
a
b
l
e
d
e
p
l
o
y
m
e
n
t
a
c
r
o
s
s
g
e
o
g
r
a
p
h
i
c
a
l
l
y
d
i
v
e
r
s
e
e
n
v
i
r
o
n
m
e
n
t
s
[
1
7
]
-
[
2
0
]
.
D
e
s
p
i
te
t
h
e
s
e
a
d
v
a
n
c
e
m
e
n
t
s
,
s
e
v
e
r
a
l
c
r
it
i
c
al
c
h
a
l
l
e
n
g
e
s
r
e
m
a
i
n
.
F
i
r
s
t
,
s
p
at
i
al
t
r
a
n
s
f
e
r
a
b
i
l
it
y
,
d
e
f
i
n
e
d
a
s
t
h
e
a
b
i
li
t
y
o
f
m
o
d
e
ls
t
r
a
i
n
e
d
i
n
o
n
e
r
e
g
i
o
n
t
o
g
en
e
r
a
l
i
z
e
t
o
a
n
o
t
h
e
r
,
r
e
m
a
i
n
s
l
i
m
i
t
e
d
d
u
e
t
o
g
e
o
g
r
a
p
h
i
c
a
n
d
c
l
i
m
a
t
i
c
d
i
v
e
r
s
i
t
y
[
2
1
]
,
[
2
2
]
.
F
o
r
i
n
s
t
a
n
c
e
,
T
a
m
i
l
N
a
d
u
e
n
c
o
m
p
a
s
s
es
c
o
a
s
t
al
p
l
a
i
n
s
,
i
n
t
e
r
i
o
r
p
l
at
e
a
u
s
,
a
n
d
e
l
e
v
a
t
e
d
t
e
r
r
a
i
n
s
,
r
es
u
l
t
i
n
g
i
n
s
i
g
n
i
f
i
c
a
n
t
v
a
r
ia
b
i
l
it
y
i
n
i
r
r
a
d
i
a
n
c
e
a
n
d
w
i
n
d
p
a
t
t
e
r
n
s
.
S
e
c
o
n
d
,
t
e
m
p
o
r
a
l
non
-
s
t
a
ti
o
n
a
r
i
t
y
c
a
u
s
e
d
b
y
s
ea
s
o
n
al
v
a
r
i
a
b
i
li
t
y
a
n
d
c
h
a
n
g
i
n
g
a
t
m
o
s
p
h
e
r
i
c
c
o
n
d
i
t
i
o
n
s
m
a
k
e
s
i
t
d
i
f
f
i
c
u
l
t
t
o
m
a
i
n
t
ai
n
c
o
n
s
is
t
e
n
t
f
o
r
e
c
as
t
i
n
g
a
c
c
u
r
ac
y
o
v
e
r
t
i
m
e
[
2
3
]
-
[
2
5
]
.
T
h
i
r
d
,
t
h
e
i
n
t
e
g
r
a
t
i
o
n
o
f
f
o
r
e
c
a
s
t
i
n
g
m
o
d
e
ls
w
i
t
h
p
o
w
er
e
l
e
c
t
r
o
n
i
c
s
y
s
t
e
m
s
f
o
r
r
e
al
-
t
im
e
c
o
n
t
r
o
l
a
n
d
e
n
e
r
g
y
m
a
n
a
g
e
m
e
n
t
h
a
s
n
o
t
b
e
e
n
s
u
f
f
i
c
i
e
n
tl
y
e
x
p
l
o
r
e
d
[
2
6
]
,
[
2
7
]
.
T
h
e
s
e
l
i
m
i
t
a
ti
o
n
s
r
es
t
r
i
c
t
n
o
t
o
n
l
y
f
o
r
e
c
as
t
i
n
g
a
c
c
u
r
a
c
y
b
u
t
a
ls
o
t
h
e
e
f
f
e
ct
i
v
e
i
n
t
e
g
r
a
t
i
o
n
o
f
r
e
n
e
w
a
b
l
e
g
e
n
e
r
a
t
i
o
n
w
i
t
h
p
o
w
e
r
e
l
e
ct
r
o
n
i
c
c
o
n
v
e
r
t
e
r
s
a
n
d
g
r
i
d
c
o
n
t
r
o
l
s
y
s
t
em
s
.
T
o
ad
d
r
ess
th
ese
lim
itatio
n
s
,
th
is
s
tu
d
y
p
r
o
p
o
s
es
a
m
u
lti
-
o
u
tp
u
t
d
ee
p
lear
n
i
n
g
f
r
am
ewo
r
k
f
o
r
th
e
jo
in
t
p
r
ed
ictio
n
o
f
Glo
b
al
Ho
r
izo
n
tal
I
r
r
ad
ia
n
ce
(
GHI
)
an
d
win
d
s
p
ee
d
,
co
m
b
in
e
d
with
cr
o
s
s
-
r
eg
io
n
al
tr
an
s
f
er
ab
ilit
y
an
aly
s
is
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
s
y
s
tem
atica
lly
ev
alu
ates
h
o
w
f
o
r
ec
asti
n
g
m
o
d
els
tr
ain
ed
in
o
n
e
r
eg
io
n
ca
n
b
e
ad
a
p
ted
to
o
th
er
r
eg
io
n
s
with
d
if
f
er
en
t
clim
atic
co
n
d
itio
n
s
,
th
er
eb
y
im
p
r
o
v
in
g
s
ca
lab
ilit
y
an
d
g
en
e
r
aliza
tio
n
.
C
o
n
v
L
S
T
M
is
u
tili
ze
d
to
ca
p
tu
r
e
s
p
atio
tem
p
o
r
al
d
ep
en
d
en
cies,
wh
ile
SHAP
-
b
ased
in
ter
p
r
etab
ilit
y
is
em
p
lo
y
e
d
to
an
aly
s
e
f
ea
t
u
r
e
c
o
n
tr
ib
u
tio
n
s
an
d
e
n
h
an
ce
m
o
d
el
tr
an
s
p
a
r
en
cy
.
Un
lik
e
ex
is
tin
g
s
tu
d
ies
th
at
p
r
im
ar
ily
f
o
cu
s
o
n
s
in
g
le
-
o
u
tp
u
t
o
r
lo
ca
tio
n
-
s
p
ec
if
ic
f
o
r
ec
asti
n
g
,
th
is
wo
r
k
u
n
iq
u
ely
c
o
m
b
in
es
m
u
lti
-
o
u
tp
u
t
p
r
e
d
ictio
n
with
s
y
s
tem
atic
cr
o
s
s
-
r
eg
io
n
al
t
r
an
s
f
er
ab
ilit
y
an
al
y
s
is
,
en
ab
lin
g
s
ca
lab
le
d
ep
lo
y
m
en
t
ac
r
o
s
s
h
eter
o
g
en
e
o
u
s
clim
atic
en
v
ir
o
n
m
en
ts
.
T
h
e
p
r
im
ar
y
n
o
v
elty
o
f
th
is
wo
r
k
lies
in
in
teg
r
atin
g
m
u
lti
-
o
u
tp
u
t
f
o
r
ec
asti
n
g
with
cr
o
s
s
-
r
eg
io
n
al
tr
a
n
s
f
er
lear
n
in
g
wi
th
in
a
u
n
if
ied
f
r
am
ewo
r
k
,
w
h
ich
h
as
n
o
t
b
ee
n
ex
ten
s
iv
ely
ex
p
lo
r
ed
in
ex
is
tin
g
liter
atu
r
e.
I
n
a
d
d
itio
n
,
t
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
h
o
w
f
o
r
e
ca
s
tin
g
o
u
tp
u
ts
ca
n
b
e
u
tili
ze
d
in
p
o
wer
elec
tr
o
n
ic
s
y
s
tem
s
f
o
r
im
p
r
o
v
ed
in
v
er
ter
co
n
tr
o
l,
DC
–
DC
co
n
v
er
ter
o
p
er
atio
n
,
an
d
h
y
b
r
id
r
en
ewa
b
le
en
er
g
y
m
an
ag
em
en
t.
T
h
is
en
ab
les
m
o
r
e
ef
f
icien
t
en
er
g
y
s
ch
e
d
u
l
in
g
,
en
h
an
ce
d
g
r
id
s
tab
ilit
y
,
an
d
p
r
ac
tical
ap
p
licatio
n
s
in
elec
tr
ic
v
eh
icle
ch
a
r
g
in
g
in
f
r
astru
ctu
r
e
an
d
en
er
g
y
s
to
r
ag
e
s
y
s
tem
s
.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
i
s
s
tu
d
y
ca
n
b
e
s
u
m
m
a
r
ized
as
:
i)
Dev
elo
p
m
en
t
o
f
a
m
u
lti
-
o
u
tp
u
t
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
f
o
r
th
e
s
i
m
u
ltan
eo
u
s
f
o
r
ec
asti
n
g
o
f
s
o
lar
ir
r
ad
ia
n
ce
a
n
d
win
d
s
p
ee
d
;
ii)
I
n
te
g
r
atio
n
o
f
cr
o
s
s
-
r
eg
io
n
al
tr
an
s
f
er
lear
n
in
g
to
ev
al
u
ate
m
o
d
el
g
en
er
aliza
tio
n
ac
r
o
s
s
d
iv
er
s
e
clim
atic
zo
n
es;
iii)
I
n
co
r
p
o
r
atio
n
o
f
SHAP
-
b
ased
in
ter
p
r
etab
ilit
y
to
im
p
r
o
v
e
m
o
d
el
tr
an
s
p
ar
e
n
cy
a
n
d
r
eliab
ilit
y
;
an
d
iv
)
Dem
o
n
s
tr
atio
n
o
f
th
e
p
r
ac
t
ical
ap
p
licab
ilit
y
o
f
f
o
r
ec
asti
n
g
o
u
tp
u
ts
in
p
o
we
r
elec
tr
o
n
ic
s
y
s
tem
s
,
in
clu
d
in
g
in
v
er
ter
co
n
tr
o
l,
DC
–
DC
co
n
v
er
ter
o
p
tim
izatio
n
,
an
d
h
y
b
r
id
r
en
ewa
b
le
en
er
g
y
m
a
n
ag
em
e
n
t.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
h
as si
g
n
if
ican
t
im
p
licatio
n
s
f
o
r
m
o
d
er
n
p
o
wer
s
y
s
tem
s
,
en
a
b
lin
g
im
p
r
o
v
e
d
g
r
id
s
tab
ilit
y
,
ef
f
icien
t
en
er
g
y
s
ch
ed
u
lin
g
,
an
d
e
n
h
an
c
ed
p
er
f
o
r
m
an
ce
o
f
elec
tr
ic
v
eh
icle
ch
ar
g
in
g
in
f
r
astru
ctu
r
e
an
d
en
e
r
g
y
s
to
r
ag
e
s
y
s
tem
s
.
T
h
u
s
,
th
is
wo
r
k
b
r
id
g
es
th
e
g
ap
b
etwe
en
d
ata
-
d
r
iv
en
r
e
n
ewa
b
le
f
o
r
ec
asti
n
g
an
d
p
r
ac
tical
p
o
wer
elec
tr
o
n
ic
ap
p
licatio
n
s
,
a
lig
n
in
g
with
th
e
ev
o
lv
in
g
r
e
q
u
ir
em
en
ts
o
f
s
m
ar
t
g
r
id
s
,
elec
tr
ic
d
r
iv
es,
a
n
d
h
y
b
r
id
en
er
g
y
s
y
s
tem
s
.
2.
M
E
T
H
O
DO
L
O
G
Y
2
.
1
.
Sy
s
t
e
m
im
ple
m
ent
a
t
io
n
f
ra
m
ewo
r
k
T
h
e
o
v
er
all
w
o
r
k
f
lo
w
a
d
o
p
t
e
d
i
n
t
h
is
s
t
u
d
y
is
il
lu
s
tr
ate
d
in
Fi
g
u
r
e
1
.
T
h
e
p
r
o
p
o
s
e
d
f
r
am
e
wo
r
k
co
n
s
is
ts
o
f
d
at
a
ac
q
u
is
i
ti
o
n
,
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
en
g
i
n
ee
r
i
n
g
,
m
o
d
el
d
e
v
el
o
p
m
e
n
t,
a
n
d
d
ep
l
o
y
m
e
n
t
-
o
r
i
en
te
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Mu
lti
-
o
u
tp
u
t d
ee
p
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
jo
in
t fo
r
ec
a
s
tin
g
o
f so
la
r
ir
r
a
d
ia
n
ce
…
(
S
.
S
elvi
)
2103
an
al
y
s
is
.
T
h
e
o
b
jec
ti
v
e
is
t
o
d
e
v
el
o
p
a
r
e
p
r
o
d
u
c
ib
le
an
d
s
ca
la
b
le
m
u
l
ti
-
o
u
t
p
u
t
f
o
r
ec
asti
n
g
s
y
s
tem
f
o
r
r
e
n
e
wa
b
le
en
er
g
y
ap
p
l
ic
ati
o
n
s
.
T
h
e
w
o
r
k
f
l
o
w
b
eg
in
s
wi
th
t
h
e
a
cq
u
is
iti
o
n
o
f
m
et
eo
r
o
l
o
g
ic
al
d
ata
f
r
o
m
t
h
e
N
ati
o
n
al
S
o
la
r
R
ad
i
ati
o
n
Da
ta
b
as
e
(
NSR
DB
)
.
T
h
e
d
a
ta
ar
e
s
u
b
s
eq
u
e
n
t
ly
s
u
b
je
cte
d
t
o
p
r
e
p
r
o
c
ess
i
n
g
a
n
d
f
e
at
u
r
e
e
n
g
i
n
ee
r
i
n
g
to
ex
tr
ac
t
r
ele
v
an
t
t
em
p
o
r
al
an
d
s
p
a
tia
l
c
h
a
r
a
ct
er
is
tics
.
T
h
e
p
r
o
ce
s
s
e
d
d
at
a
a
r
e
u
s
ed
a
s
in
p
u
ts
t
o
m
a
c
h
i
n
e
lea
r
n
i
n
g
a
n
d
d
e
ep
le
a
r
n
in
g
m
o
d
els,
i
n
cl
u
d
i
n
g
L
i
g
h
tGB
M,
L
ST
M,
B
iLS
T
M
,
an
d
C
o
n
v
L
STM
,
f
o
r
t
h
e
s
im
u
lt
an
eo
u
s
p
r
ed
ict
io
n
o
f
g
l
o
b
al
h
o
r
i
zo
n
t
al
i
r
r
a
d
ia
n
c
e
(
G
HI
)
an
d
wi
n
d
s
p
ee
d
.
T
h
e
p
r
ed
i
ct
ed
o
u
tp
u
ts
ar
e
f
u
r
t
h
er
i
n
te
g
r
at
e
d
i
n
t
o
a
c
o
n
tr
o
l
la
y
e
r
r
ep
r
es
e
n
ti
n
g
p
o
we
r
el
ec
t
r
o
n
ic
a
p
p
lic
ati
o
n
s
s
u
c
h
as
DC
–
DC
c
o
n
v
e
r
t
er
s
,
in
v
e
r
t
er
s
,
a
n
d
g
r
i
d
-
c
o
n
n
ec
te
d
r
e
n
ew
a
b
le
s
y
s
t
em
s
.
T
h
is
ar
c
h
i
tect
u
r
e
d
e
m
o
n
s
tr
ates
h
o
w
f
o
r
e
ca
s
ti
n
g
o
u
tp
u
ts
ca
n
s
u
p
p
o
r
t
r
ea
l
-
ti
m
e
e
n
er
g
y
m
a
n
a
g
e
m
e
n
t
,
c
o
n
v
e
r
t
er
c
o
n
t
r
o
l
,
an
d
h
y
b
r
id
s
y
s
te
m
o
p
t
im
iza
ti
o
n
.
Fig
u
r
e
1
.
Sy
s
tem
ar
c
h
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
u
lti
-
o
u
tp
u
t f
o
r
ec
asti
n
g
f
r
am
ew
o
r
k
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
a
nd
f
ea
t
ure
eng
ineering
Ho
u
r
ly
NSR
DB
m
e
te
o
r
o
l
o
g
ical
d
at
a
(
2
0
1
5
–
2
0
2
0
)
w
e
r
e
u
s
e
d
,
i
n
cl
u
d
i
n
g
GH
I
,
wi
n
d
s
p
ee
d
,
tem
p
e
r
at
u
r
e,
r
el
ati
v
e
h
u
m
i
d
i
ty
,
s
u
r
f
ac
e
p
r
ess
u
r
e,
d
ew
p
o
in
t,
s
o
la
r
z
en
it
h
an
g
l
e,
a
n
d
s
p
ati
al
att
r
i
b
u
tes
(
lat
it
u
d
e,
lo
n
g
it
u
d
e
,
an
d
e
le
v
at
io
n
)
.
Mi
s
s
in
g
v
al
u
es
we
r
e
h
a
n
d
l
ed
u
s
in
g
li
n
e
ar
i
n
t
er
p
o
l
ati
o
n
,
a
n
d
al
l
f
ea
t
u
r
es
we
r
e
n
o
r
m
al
iz
ed
u
s
i
n
g
Mi
n
–
Ma
x
s
ca
li
n
g
.
T
e
m
p
o
r
a
l
f
ea
t
u
r
es
(
h
o
u
r
,
d
a
y
,
m
o
n
th
)
a
n
d
la
g
g
e
d
v
ar
i
a
b
les
(
GH
I
_
p
r
e
v
an
d
W
i
n
d
_
p
r
e
v
)
we
r
e
g
e
n
e
r
at
e
d
t
o
ca
p
t
u
r
e
d
i
u
r
n
al,
s
e
aso
n
a
l,
an
d
t
em
p
o
r
al
d
ep
e
n
d
en
ci
es,
w
h
il
e
s
p
at
ial
f
ea
t
u
r
es
ac
c
o
u
n
te
d
f
o
r
g
e
o
g
r
a
p
h
ic
al
v
ar
iab
ilit
y
,
e
n
a
b
li
n
g
ac
cu
r
a
te
s
p
at
io
t
em
p
o
r
al
r
e
n
ew
ab
le
e
n
e
r
g
y
f
o
r
ec
asti
n
g
.
2
.
3
.
M
o
del
a
rc
hite
ct
ure
T
h
e
f
o
r
e
ca
s
tin
g
f
r
am
ewo
r
k
i
n
teg
r
ates
L
ig
h
tGB
M,
L
STM
,
B
iLST
M,
an
d
C
o
n
v
L
STM
t
o
ca
p
tu
r
e
n
o
n
lin
ea
r
,
tem
p
o
r
al,
a
n
d
s
p
a
tio
-
tem
p
o
r
al
r
elatio
n
s
h
i
p
s
in
r
en
ewa
b
le
en
er
g
y
d
ata.
Hy
p
er
p
ar
am
eter
s
wer
e
o
p
tim
ized
u
s
in
g
B
ay
esian
o
p
t
im
izatio
n
,
with
ea
r
ly
s
to
p
p
in
g
ap
p
lied
to
r
ed
u
ce
o
v
er
f
itti
n
g
.
T
h
e
m
o
d
els
wer
e
ev
alu
ated
u
s
in
g
a
tem
p
o
r
al
t
r
ain
–
test
s
p
lit
an
d
cr
o
s
s
-
r
eg
i
o
n
al
tr
an
s
f
er
lea
r
n
in
g
th
r
o
u
g
h
f
in
e
-
tu
n
in
g
with
tar
g
et
-
r
eg
io
n
d
ata.
All
m
o
d
els
wer
e
im
p
lem
en
ted
in
Py
t
h
o
n
u
s
in
g
T
en
s
o
r
Flo
w/Ker
as
an
d
L
ig
h
tGB
M.
T
h
e
d
etailed
m
o
d
el
c
o
n
f
ig
u
r
atio
n
a
n
d
im
p
lem
e
n
tatio
n
p
a
r
am
eter
s
ar
e
s
u
m
m
ar
ized
i
n
T
ab
le
1
.
T
ab
le
1
.
Mo
d
el
co
n
f
ig
u
r
atio
n
an
d
im
p
lem
e
n
tatio
n
p
a
r
am
eter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
Li
g
h
t
G
B
M
e
s
t
i
mat
o
r
s
1
0
0
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
5
LSTM
h
i
d
d
e
n
l
a
y
e
r
s
2
H
i
d
d
e
n
u
n
i
t
s
p
e
r
l
a
y
e
r
64
C
o
n
v
LST
M
k
e
r
n
e
l
si
z
e
3
×
3
H
y
p
e
r
p
a
r
a
me
t
e
r
s
o
p
t
i
mi
z
a
t
i
o
n
B
a
y
e
s
i
a
n
o
p
t
i
m
i
z
a
t
i
o
n
Ea
r
l
y
st
o
p
p
i
n
g
A
p
p
l
i
e
d
Tr
a
i
n
i
n
g
st
r
a
t
e
g
y
Te
mp
o
r
a
l
s
p
l
i
t
(
2
0
1
5
–
2
0
1
8
t
r
a
i
n
i
n
g
;
2
0
1
9
–
2
0
2
0
t
e
st
i
n
g
)
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
F
i
n
e
-
t
u
n
i
n
g
u
si
n
g
1
0
%
t
a
r
g
e
t
-
r
e
g
i
o
n
d
a
t
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
2101
-
2
1
1
1
2104
2
.
4
.
T
ra
ini
ng
a
nd
v
a
lid
a
t
io
n
s
t
ra
t
eg
y
T
h
e
d
ataset
was
d
iv
id
ed
u
s
in
g
an
8
0
:2
0
tem
p
o
r
al
s
p
lit,
wh
er
e
d
ata
f
r
o
m
2
0
1
5
–
2
0
1
8
wer
e
u
s
ed
f
o
r
tr
ain
in
g
a
n
d
d
ata
f
r
o
m
2
0
1
9
–
2
0
2
0
wer
e
u
s
ed
f
o
r
test
in
g
.
T
h
is
ap
p
r
o
ac
h
p
r
eser
v
es
te
m
p
o
r
al
o
r
d
er
i
n
g
a
n
d
p
r
ev
en
ts
d
ata
leak
a
g
e.
T
o
e
v
al
u
ate
g
en
er
aliza
b
ilit
y
,
m
o
d
els
tr
ain
ed
o
n
T
am
il
Nad
u
d
ata
wer
e
d
ir
ec
tly
ap
p
lied
to
n
eig
h
b
o
r
in
g
s
tates,
in
clu
d
in
g
Ker
ala,
Kar
n
atak
a,
an
d
An
d
h
r
a
Pra
d
esh
.
Fin
e
-
tu
n
i
n
g
ex
p
er
im
en
ts
wer
e
co
n
d
u
cte
d
u
s
in
g
a
s
u
b
s
et
(
1
0
%)
o
f
tar
g
et
-
r
eg
i
o
n
d
ata
to
a
s
s
es
s
ad
ap
tab
ilit
y
.
T
h
is
cr
o
s
s
-
r
eg
io
n
al
v
alid
atio
n
f
r
am
ewo
r
k
en
ab
les r
o
b
u
s
t e
v
a
lu
atio
n
o
f
m
o
d
el
tr
a
n
s
f
er
ab
ilit
y
.
2
.
5
.
E
v
a
lua
t
i
o
n
m
et
rics
Mo
d
el
p
er
f
o
r
m
an
ce
was
ev
a
lu
ated
u
s
in
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
an
d
th
e
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
²)
.
T
h
ese
m
etr
ics
p
r
o
v
i
d
e
a
c
o
m
p
r
e
h
en
s
iv
e
ass
es
s
m
en
t
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
,
e
r
r
o
r
m
ag
n
itu
d
e,
an
d
v
a
r
ian
ce
e
x
p
lan
atio
n
.
T
h
e
u
s
e
o
f
co
n
s
is
ten
t
p
r
ep
r
o
ce
s
s
in
g
,
s
tan
d
ar
d
ized
t
r
ain
in
g
p
r
o
ce
d
u
r
es,
an
d
cr
o
s
s
-
r
eg
io
n
al
v
ali
d
atio
n
e
n
s
u
r
es
m
eth
o
d
o
lo
g
ic
al
tr
an
s
p
ar
en
c
y
a
n
d
en
h
an
ce
s
th
e
g
e
n
er
aliza
b
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
ac
r
o
s
s
d
iv
er
s
e
clim
atic
co
n
d
itio
n
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
x
plo
ra
t
o
ry
da
t
a
a
na
l
y
s
is
T
h
e
tem
p
o
r
al
v
a
r
iatio
n
o
f
g
l
o
b
al
h
o
r
iz
o
n
tal
ir
r
a
d
ian
ce
(
GHI
)
an
d
win
d
s
p
ee
d
ex
h
ib
its
s
tr
o
n
g
d
i
u
r
n
al
an
d
s
ea
s
o
n
al
p
atter
n
s
,
as
s
h
o
wn
in
Fig
u
r
e
2
.
GHI
ex
h
i
b
its
a
ty
p
ical
b
ell
-
s
h
ap
ed
d
iu
r
n
al
p
atter
n
,
wh
ile
win
d
s
p
ee
d
s
h
o
ws
g
r
ea
ter
v
ar
iab
il
ity
d
u
e
to
lo
ca
l
atm
o
s
p
h
er
ic
co
n
d
itio
n
s
.
R
eg
io
n
al
d
if
f
er
e
n
ce
s
in
g
eo
g
r
a
p
h
y
in
f
lu
en
ce
r
en
ewa
b
le
r
eso
u
r
ce
av
ailab
ilit
y
an
d
ar
e
r
ef
lecte
d
in
th
e
s
p
atial
co
r
r
elatio
n
p
atter
n
s
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
s
tr
o
n
g
c
o
r
r
elati
o
n
s
am
o
n
g
n
ei
g
h
b
o
r
in
g
r
eg
io
n
s
s
u
p
p
o
r
t
th
e
f
ea
s
ib
ilit
y
o
f
cr
o
s
s
-
r
eg
io
n
al
tr
an
s
f
e
r
lear
n
in
g
.
Fu
r
th
er
m
o
r
e,
th
e
co
r
r
elatio
n
h
ea
tm
ap
p
r
esen
ted
in
Fig
u
r
e
4
h
ig
h
lig
h
ts
s
tr
o
n
g
r
el
atio
n
s
h
ip
s
b
etwe
en
lag
g
ed
v
ar
iab
les
(
GHI
_
p
r
ev
a
n
d
W
in
d
_
p
r
ev
)
an
d
th
eir
r
esp
e
ctiv
e
tar
g
ets,
wh
ile
m
eteo
r
o
l
o
g
ical
v
ar
iab
les
s
u
ch
as
tem
p
er
atu
r
e
an
d
s
o
lar
ze
n
it
h
an
g
le
also
d
em
o
n
s
tr
ate
s
ig
n
if
ican
t
co
r
r
elatio
n
s
,
co
n
f
ir
m
in
g
th
eir
im
p
o
r
tan
ce
f
o
r
r
e
n
ewa
b
le
en
er
g
y
f
o
r
ec
asti
n
g
.
3
.
2
.
M
o
del per
f
o
rma
nce
ev
a
lua
t
io
n
T
h
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
r
esu
lts
in
T
ab
le
2
s
h
o
w
t
h
at
th
e
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
m
o
d
els
c
o
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
th
e
p
e
r
s
is
ten
ce
an
d
L
ig
h
tGB
M
ap
p
r
o
ac
h
es,
with
C
o
n
v
L
STM
ac
h
iev
in
g
th
e
l
o
west
av
er
ag
e
MA
E
o
f
0
.
0
6
1
a
n
d
th
e
h
ig
h
est
R
²
v
alu
es
o
f
0
.
9
3
f
o
r
GHI
an
d
0
.
9
1
f
o
r
win
d
s
p
ee
d
.
B
iLST
M
also
d
em
o
n
s
tr
ates
s
tr
o
n
g
p
r
ed
ictiv
e
p
e
r
f
o
r
m
an
ce
,
with
an
av
er
ag
e
MA
E
o
f
0
.
0
6
4
an
d
R
²
v
alu
es
o
f
0
.
9
2
an
d
0
.
9
0
f
o
r
GHI
an
d
win
d
s
p
ee
d
,
r
esp
ec
tiv
ely
,
in
d
icatin
g
its
ef
f
ec
tiv
en
ess
in
le
ar
n
in
g
tem
p
o
r
al
d
ep
e
n
d
en
cie
s
.
T
h
e
co
r
r
elatio
n
h
ea
tm
ap
in
Fig
u
r
e
4
f
u
r
th
er
s
u
p
p
o
r
ts
th
e
m
o
d
el
r
esu
lts
b
y
s
h
o
win
g
s
tr
o
n
g
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
tar
g
et
v
ar
iab
les
an
d
th
eir
lag
g
ed
in
p
u
ts
,
p
ar
ticu
lar
ly
GHI
_
p
r
e
v
(
0
.
8
5
with
GHI
)
an
d
W
in
d
_
p
r
ev
(
0
.
8
0
with
win
d
s
p
ee
d
)
,
wh
ile
tem
p
er
at
u
r
e
an
d
s
o
lar
ze
n
ith
an
g
le
also
ex
h
ib
it
m
ea
n
in
g
f
u
l c
o
r
r
elatio
n
s
with
GHI
.
Fig
u
r
e
2
.
Diu
r
n
al
v
ar
iatio
n
o
f
g
lo
b
al
h
o
r
izo
n
tal
ir
r
a
d
ian
ce
(
GHI
)
,
win
d
s
p
ee
d
,
an
d
p
atter
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Mu
lti
-
o
u
tp
u
t d
ee
p
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
jo
in
t fo
r
ec
a
s
tin
g
o
f so
la
r
ir
r
a
d
ia
n
ce
…
(
S
.
S
elvi
)
2105
Fig
u
r
e
3
.
Sp
atial
co
r
r
elatio
n
a
cr
o
s
s
r
eg
io
n
al
s
tatio
n
s
Fig
u
r
e
4
.
C
o
r
r
elatio
n
h
ea
tm
a
p
o
f
in
p
u
t v
ar
ia
b
les
T
ab
le
2
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
o
n
T
am
il Na
d
u
test
s
et
M
o
d
e
l
M
A
G
H
I
M
A
E
W
i
n
d
A
v
g
.
M
A
E
R
² G
H
I
R
² Wi
n
d
P
e
r
si
st
e
n
c
e
0
.
1
4
5
0
.
1
2
5
0
.
1
3
5
0
.
6
5
0
.
6
1
Li
g
h
t
G
B
M
0
.
0
7
2
0
.
0
6
8
0
.
0
7
0
0
.
8
9
0
.
8
7
LSTM
0
.
0
6
8
0
.
0
6
5
0
.
0
6
7
0
.
9
1
0
.
8
8
B
i
LST
M
0
.
0
6
5
0
.
0
6
3
0
.
0
6
4
0
.
9
2
0
.
9
0
C
o
n
v
LST
M
0
.
0
6
2
0
.
0
6
0
0
.
0
6
1
0
.
9
3
0
.
9
1
3
.
3
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
a
nd
m
o
del beha
v
io
r
A
co
m
p
ar
ativ
e
an
al
y
s
is
o
f
a
ll
m
o
d
els
lis
ted
in
T
ab
le
2
s
h
o
ws
th
at
d
ee
p
lear
n
i
n
g
a
r
ch
itectu
r
es
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
in
ca
p
tu
r
in
g
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
.
C
o
n
v
L
STM
p
r
o
v
id
es
s
u
p
er
io
r
p
er
f
o
r
m
a
n
c
e
d
u
e
to
its
h
y
b
r
id
co
n
v
o
lu
ti
o
n
al
-
r
ec
u
r
r
en
t
s
tr
u
ctu
r
e.
Fig
u
r
e
5
(
a
)
s
h
o
ws
th
e
p
r
ed
icted
v
er
s
u
s
ac
tu
al
win
d
s
p
ee
d
v
alu
es,
with
t
h
e
p
o
in
ts
clo
s
ely
alig
n
ed
alo
n
g
t
h
e
d
ia
g
o
n
al
lin
e
a
n
d
a
n
R
²
v
alu
e
o
f
ap
p
r
o
x
im
ately
0
.
9
9
,
in
d
icatin
g
h
ig
h
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Fig
u
r
e
5
(
b
)
p
r
esen
ts
th
e
p
r
ed
icted
v
er
s
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
2101
-
2
1
1
1
2106
ac
tu
al
GHI
v
alu
es,
wh
ich
also
s
h
o
w
clo
s
e
ag
r
ee
m
en
t
with
th
e
d
iag
o
n
al
lin
e
an
d
a
n
R
²
v
alu
e
o
f
ap
p
r
o
x
im
ately
0
.
9
9
,
c
o
n
f
ir
m
in
g
t
h
e
h
ig
h
ac
cu
r
ac
y
o
f
th
e
C
o
n
v
L
STM
m
o
d
el
f
o
r
s
o
lar
ir
r
ad
ian
ce
p
r
ed
ictio
n
.
Alth
o
u
g
h
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
h
av
e
b
ee
n
r
ep
o
r
ted
to
ac
h
iev
e
s
tr
o
n
g
p
er
f
o
r
m
an
c
e
in
r
en
ewa
b
le
en
er
g
y
f
o
r
ec
asti
n
g
,
th
eir
h
ig
h
er
co
m
p
u
tatio
n
al
co
m
p
lex
ity
an
d
r
eq
u
ir
e
m
en
t
f
o
r
lar
g
e
-
s
ca
le
tr
ain
in
g
d
ata
lim
it
th
eir
s
u
itab
ilit
y
f
o
r
r
ea
l
-
tim
e
d
ep
lo
y
m
en
t.
I
n
c
o
n
tr
ast,
th
e
p
r
o
p
o
s
ed
C
o
n
v
L
STM
-
b
ased
f
r
a
m
ewo
r
k
p
r
o
v
id
es
a
co
m
p
u
tatio
n
ally
ef
f
icien
t
s
o
lu
tio
n
wh
ile
m
ain
tain
in
g
h
ig
h
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
s
tr
o
n
g
g
e
n
er
aliza
tio
n
ca
p
ab
ilit
y
ac
r
o
s
s
r
eg
io
n
s
.
T
h
e
k
ey
n
o
v
elty
o
f
th
is
s
tu
d
y
li
es
in
th
e
s
y
s
tem
atic
ev
alu
atio
n
o
f
cr
o
s
s
-
r
eg
i
o
n
al
tr
an
s
f
er
ab
ilit
y
f
o
r
m
u
lti
-
o
u
t
p
u
t
r
en
ewa
b
le
f
o
r
ec
asti
n
g
.
U
n
lik
e
p
r
io
r
wo
r
k
s
th
at
f
o
c
u
s
o
n
s
in
g
le
-
lo
ca
tio
n
o
r
s
in
g
le
-
v
ar
iab
le
p
r
ed
ictio
n
,
t
h
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
d
em
o
n
s
tr
ates
th
e
ab
ilit
y
to
g
en
er
alize
ac
r
o
s
s
h
eter
o
g
en
e
o
u
s
clim
atic
r
e
g
io
n
s
wh
ile
m
ain
tain
in
g
h
ig
h
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
is
estab
lis
h
es
th
e
f
r
am
ewo
r
k
as a
s
ca
lab
le
s
o
lu
tio
n
f
o
r
r
en
e
wab
le
en
er
g
y
f
o
r
ec
asti
n
g
ac
r
o
s
s
g
eo
g
r
ap
h
ically
d
iv
er
s
e
en
v
i
r
o
n
m
en
ts
.
(
a)
(
b
)
Fig
u
r
e
5
.
Pre
d
icte
d
v
er
s
u
s
ac
t
u
al
v
alu
es f
o
r
(
a)
win
d
s
p
ee
d
a
n
d
(
b
)
g
lo
b
al
h
o
r
izo
n
tal
ir
r
a
d
ian
ce
(
GHI
)
.
T
h
e
d
ash
ed
d
iag
o
n
al
lin
e
r
ep
r
esen
ts
p
er
f
ec
t p
r
ed
ictio
n
3
.
4
.
Cro
s
s
-
re
g
io
na
l
t
ra
ns
f
er
a
bil
it
y
a
na
ly
s
is
T
o
ev
alu
ate
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
,
m
o
d
els
tr
ain
ed
o
n
T
am
il
Nad
u
d
ata
we
r
e
ap
p
lie
d
to
Ker
ala,
Kar
n
atak
a,
an
d
An
d
h
r
a
Pra
d
e
s
h
with
o
u
t
r
etr
ain
in
g
.
C
r
o
s
s
-
s
tate
ev
alu
atio
n
r
esu
lts
ar
e
p
r
e
s
en
ted
in
T
ab
le
3
C
o
n
v
L
STM
co
n
s
is
ten
tly
ac
h
i
ev
ed
th
e
l
o
west
MA
E
ac
r
o
s
s
all
r
eg
io
n
s
,
in
d
icatin
g
s
tr
o
n
g
t
r
an
s
f
er
ab
ilit
y
.
Fin
e
-
tu
n
in
g
e
x
p
er
im
e
n
ts
u
s
in
g
o
n
ly
1
0
%
o
f
tar
g
et
-
r
eg
io
n
d
ata
r
esu
lted
in
an
a
d
d
itio
n
al
5
–
8
%
r
ed
u
ctio
n
in
MA
E
.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
at
s
p
a
tio
-
tem
p
o
r
al
m
o
d
els
ar
e
m
o
r
e
r
o
b
u
s
t
to
d
o
m
ain
s
h
if
ts
an
d
th
at
tr
an
s
f
er
lear
n
in
g
s
ig
n
if
ican
tly
en
h
a
n
ce
s
ad
ap
tab
ilit
y
in
r
eg
io
n
-
s
p
ec
if
ic
f
o
r
ec
as
tin
g
s
ce
n
ar
io
s
.
T
ab
le
4
illu
s
tr
ates
th
e
im
p
ac
t
o
f
f
in
e
-
tu
n
in
g
o
n
tr
an
s
f
er
lear
n
in
g
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
d
if
f
e
r
en
t
tar
g
et
s
tates.
I
t
is
o
b
s
er
v
ed
th
at
f
in
e
-
tu
n
in
g
with
a
s
m
all
s
u
b
s
et
o
f
tar
g
et
-
r
eg
io
n
d
ata
lea
d
s
to
a
c
o
n
s
is
ten
t
r
ed
u
ctio
n
in
MA
E
co
m
p
ar
ed
to
d
ir
ec
t
t
r
an
s
f
er
,
with
im
p
r
o
v
em
en
ts
r
an
g
in
g
b
etwe
en
a
p
p
r
o
x
im
ately
5
–
8
%.
T
h
e
d
ata
q
u
an
tify
th
is
im
p
r
o
v
em
en
t,
co
n
f
ir
m
in
g
th
at
lim
ited
r
eg
i
o
n
al
ad
a
p
tatio
n
s
ig
n
if
ican
tly
en
h
an
ce
s
m
o
d
el
p
er
f
o
r
m
an
ce
a
n
d
r
o
b
u
s
tn
ess
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
tr
a
n
s
f
er
lear
n
in
g
in
ad
d
r
ess
in
g
r
eg
io
n
al
v
a
r
iab
ilit
y
an
d
im
p
r
o
v
in
g
g
e
n
er
aliza
tio
n
ac
r
o
s
s
d
iv
er
s
e
clim
atic
co
n
d
itio
n
s
.
T
ab
le
3
.
C
r
o
s
s
-
s
tate
MA
E
C
o
m
p
ar
is
o
n
S
t
a
t
e
L
ight
G
B
M
L
S
T
M
B
iL
S
T
M
C
onvL
S
T
M
K
e
r
a
l
a
0
.
0
8
5
0
.
0
8
0
0
.
0
7
7
0
.
0
7
4
K
a
r
n
a
t
a
k
a
0
.
0
8
8
0
.
0
8
3
0
.
0
8
0
0
.
0
7
8
A
n
d
h
r
a
P
r
a
d
e
sh
0
.
0
9
0
0
.
0
8
5
0
.
0
8
2
0
.
0
7
9
T
ab
le
4
.
E
f
f
ec
t o
f
f
in
e
-
tu
n
in
g
o
n
tr
an
s
f
er
lea
r
n
in
g
p
er
f
o
r
m
a
n
ce
(
a
v
er
ag
e
MA
E
)
S
t
a
t
e
D
i
r
e
c
t
t
r
a
n
sf
e
r
M
A
E
F
i
n
e
-
t
u
n
e
d
M
A
E
I
mp
r
o
v
e
m
e
n
t
(
%)
K
e
r
a
l
a
0
.
0
7
4
0
.
0
6
9
6
.
8
K
a
r
n
a
t
a
k
a
0
.
0
7
8
0
.
0
7
2
7
.
7
A
n
d
h
r
a
P
r
a
d
e
sh
0
.
0
7
9
0
.
0
7
3
7
.
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Mu
lti
-
o
u
tp
u
t d
ee
p
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
jo
in
t fo
r
ec
a
s
tin
g
o
f so
la
r
ir
r
a
d
ia
n
ce
…
(
S
.
S
elvi
)
2107
3
.
5
.
F
e
a
t
ure
im
po
rt
a
nce
a
n
d inte
rpre
t
a
bil
it
y
F
i
g
u
r
e
6
i
l
l
u
s
t
r
at
e
s
t
h
e
d
e
p
e
n
d
e
n
c
e
o
f
m
o
d
e
l
p
r
e
d
i
c
t
i
o
n
s
o
n
e
l
e
v
a
t
i
o
n
.
A
g
e
n
e
r
al
l
y
i
n
c
r
e
as
in
g
t
r
e
n
d
is
o
b
s
e
r
v
e
d
,
i
n
d
i
c
a
t
i
n
g
t
h
at
e
l
e
v
a
t
i
o
n
p
o
s
i
ti
v
e
l
y
i
n
f
l
u
e
n
c
es
t
h
e
p
r
e
d
i
c
t
e
d
o
u
t
p
u
t
.
T
h
e
s
p
r
e
ad
o
f
S
H
A
P
v
al
u
es
r
e
f
l
e
c
ts
i
n
t
e
r
a
ct
i
o
n
s
wi
t
h
o
t
h
er
s
p
a
t
i
a
l
f
e
at
u
r
e
s
,
p
a
r
ti
c
u
l
a
r
l
y
l
o
n
g
i
t
u
d
e
,
h
i
g
h
l
i
g
h
t
i
n
g
t
h
e
c
o
m
p
l
e
x
r
e
l
a
t
i
o
n
s
h
i
p
s
c
a
p
t
u
r
e
d
b
y
t
h
e
m
o
d
e
l
.
T
o
e
n
s
u
r
e
m
o
d
e
l
t
r
a
n
s
p
a
r
e
n
c
y
,
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
c
e
a
n
a
l
y
s
is
w
as
c
o
n
d
u
c
t
e
d
u
s
i
n
g
L
i
g
h
t
G
B
M
a
n
d
S
H
AP
.
A
s
s
h
o
w
n
i
n
Fi
g
u
r
e
s
6
(
a
)
a
n
d
6
(
b
)
,
l
ag
g
e
d
v
a
r
i
a
b
l
e
s
(
G
H
I
p
r
e
v
a
n
d
W
i
n
d
p
r
e
v
)
a
r
e
t
h
e
m
o
s
t
i
n
f
l
u
e
n
t
i
al
f
e
a
t
u
r
e
s
,
c
o
n
f
ir
m
i
n
g
s
t
r
o
n
g
t
e
m
p
o
r
a
l
p
e
r
s
i
s
t
en
c
e
.
M
e
t
e
o
r
o
l
o
g
i
c
a
l
v
a
r
i
a
b
le
s
s
u
c
h
a
s
t
e
m
p
e
r
a
t
u
r
e
a
n
d
s
o
l
a
r
z
e
n
it
h
a
n
g
l
e
a
ls
o
p
l
a
y
s
i
g
n
i
f
ic
a
n
t
r
o
l
es
.
W
h
i
l
e
S
H
AP
a
n
a
l
y
s
is
w
as
p
r
i
m
a
r
il
y
p
e
r
f
o
r
m
e
d
u
s
i
n
g
L
i
g
h
t
G
B
M
,
t
h
e
o
b
s
e
r
v
e
d
f
ea
tu
r
e
i
m
p
o
r
t
a
n
c
e
t
r
e
n
d
s
a
r
e
c
o
n
s
is
t
e
n
t
w
i
t
h
t
h
e
b
e
h
a
v
i
o
r
o
f
d
ee
p
l
e
a
r
n
i
n
g
m
o
d
e
ls
.
T
h
e
d
o
m
i
n
a
n
c
e
o
f
l
a
g
g
e
d
a
n
d
m
e
t
e
o
r
o
l
o
g
i
c
a
l
f
e
a
t
u
r
es
i
n
d
i
ca
t
e
s
t
h
a
t
t
h
e
l
e
a
r
n
e
d
r
el
a
t
i
o
n
s
h
i
p
s
a
r
e
p
h
y
s
i
c
a
ll
y
m
e
a
n
i
n
g
f
u
l
a
n
d
c
o
n
s
i
s
t
e
n
t
a
c
r
o
s
s
d
i
f
f
e
r
e
n
t
m
o
d
e
l
a
r
c
h
i
t
e
ct
u
r
e
s
.
F
i
g
u
r
e
7
s
h
o
w
s
t
h
at
e
l
e
v
a
t
i
o
n
h
a
s
a
p
o
s
i
t
i
v
e
i
n
f
l
u
e
n
c
e
o
n
m
o
d
e
l
p
r
e
d
i
c
t
i
o
n
s
,
w
i
t
h
s
o
m
e
v
a
r
i
a
b
il
i
t
y
a
t
h
i
g
h
e
r
e
l
e
v
a
t
i
o
n
s
.
F
i
g
u
r
e
8
s
h
o
w
s
th
a
t
C
o
n
v
L
S
T
M
h
as
t
h
e
l
o
w
es
t
a
n
d
m
o
s
t
c
o
m
p
a
c
t
p
r
e
d
i
c
t
i
o
n
-
e
r
r
o
r
d
i
s
t
r
i
b
u
t
i
o
n
,
i
n
d
i
c
a
t
i
n
g
b
e
tt
e
r
p
r
e
d
i
c
ti
o
n
c
o
n
s
is
te
n
c
y
.
(
a)
(
b
)
Fig
u
r
e
6
.
SHAP a
n
aly
s
is
o
f
th
e
L
ig
h
tGB
M
m
o
d
el:
(
a)
f
ea
tu
r
e
im
p
o
r
tan
ce
r
an
k
i
n
g
an
d
(
b
)
SHAP
-
b
ased
f
ea
tu
r
e
im
p
ac
t a
n
aly
s
is
s
h
o
win
g
th
e
c
o
n
tr
ib
u
tio
n
o
f
in
p
u
t v
a
r
iab
les to
m
o
d
el
p
r
ed
ictio
n
s
Fig
u
r
e
7
.
SHAP d
ep
en
d
en
ce
p
lo
t illu
s
tr
atin
g
th
e
ef
f
ec
t o
f
ele
v
atio
n
o
n
m
o
d
el
p
r
ed
ictio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
2101
-
2
1
1
1
2108
3
.
6
.
H
y
perpa
ra
m
e
t
er
s
ens
it
iv
it
y
a
na
ly
s
is
T
o
im
p
r
o
v
e
m
et
h
o
d
o
lo
g
ic
al
tr
an
s
p
ar
en
cy
,
s
en
s
itiv
ity
an
aly
s
is
was
co
n
d
u
cted
o
n
k
ey
h
y
p
er
p
ar
am
eter
s
,
in
clu
d
i
n
g
C
o
n
v
L
STM
k
er
n
el
s
ize,
B
iL
STM
d
ep
th
,
an
d
L
ig
h
tGB
M
lear
n
in
g
r
ate.
T
h
e
r
esu
lts
s
u
m
m
ar
ized
in
T
ab
le
5
in
d
icate
th
at
m
o
d
el
p
er
f
o
r
m
an
ce
is
m
o
d
er
ately
s
en
s
itiv
e
to
th
ese
p
ar
am
eter
s
,
with
o
p
tim
al
c
o
n
f
ig
u
r
atio
n
s
y
ield
in
g
s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
r
eg
i
o
n
s
.
Am
o
n
g
t
h
e
ev
al
u
ated
p
ar
am
eter
s
,
th
e
lear
n
in
g
r
ate
s
h
o
wed
a
r
elativ
ely
g
r
ea
ter
in
f
l
u
en
ce
o
n
MA
E
,
wh
ile
v
a
r
iatio
n
s
in
C
o
n
v
L
STM
k
er
n
el
s
ize
an
d
B
iLST
M
d
ep
th
p
r
o
d
u
ce
d
co
m
p
ar
ativ
el
y
s
m
aller
ch
an
g
es,
in
d
icatin
g
th
at
th
e
s
elec
ted
co
n
f
ig
u
r
atio
n
s
p
r
o
v
id
e
a
s
u
itab
le
b
alan
ce
b
etwe
en
m
o
d
el
c
o
m
p
lex
ity
an
d
f
o
r
ec
asti
n
g
p
er
f
o
r
m
an
ce
.
T
ab
le
5
.
Hy
p
er
p
ar
a
m
eter
s
en
s
itiv
ity
an
aly
s
is
P
a
r
a
me
t
e
r
V
a
r
i
a
t
i
o
n
I
mp
a
c
t
o
n
M
A
E
C
o
n
v
LST
M
K
e
r
n
e
l
3
×
3
-
5
×
5
+2
–
3%
B
i
LST
M
D
e
p
t
h
1
-
3
l
a
y
e
r
s
+1
–
2%
Le
a
r
n
i
n
g
R
a
t
e
0
.
0
1
-
0
.
0
5
−3
–
4%
3
.
7
.
Uncer
t
a
inty
a
nd
re
lia
bil
it
y
a
na
ly
s
is
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
is
d
eter
m
in
is
tic,
u
n
ce
r
tain
ty
was
an
aly
ze
d
th
r
o
u
g
h
th
e
d
is
tr
ib
u
tio
n
o
f
p
r
ed
ictio
n
er
r
o
r
s
.
Fig
u
r
e
8
illu
s
tr
ates
th
e
s
p
r
e
ad
o
f
er
r
o
r
s
ac
r
o
s
s
d
if
f
er
e
n
t
m
o
d
els.
C
o
n
v
L
STM
ex
h
ib
its
a
n
ar
r
o
wer
er
r
o
r
d
i
s
tr
ib
u
tio
n
an
d
f
ewe
r
o
u
tlier
s
co
m
p
ar
e
d
to
o
t
h
er
m
o
d
els,
in
d
icatin
g
r
e
d
u
ce
d
u
n
ce
r
tain
ty
a
n
d
im
p
r
o
v
ed
p
r
e
d
ictio
n
s
tab
ilit
y
.
T
h
e
lo
wer
v
a
r
iab
ilit
y
in
C
o
n
v
L
STM
p
r
ed
ic
tio
n
s
h
ig
h
lig
h
ts
its
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
f
o
r
r
ea
l
-
wo
r
ld
r
en
ewa
b
le
en
er
g
y
f
o
r
ec
asti
n
g
ap
p
licatio
n
s
.
Fig
u
r
e
8
.
Dis
tr
ib
u
tio
n
o
f
p
r
ed
i
ctio
n
er
r
o
r
s
ac
r
o
s
s
m
o
d
els
3
.
8
.
P
r
a
ct
ica
l i
m
pli
ca
t
io
ns
,
lim
it
a
t
io
ns
,
a
nd
f
uture
wo
rk
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
h
as p
r
ac
tical
r
elev
an
ce
f
o
r
p
o
wer
elec
tr
o
n
ic
s
y
s
tem
s
b
y
en
a
b
lin
g
im
p
r
o
v
ed
m
ax
im
u
m
p
o
wer
p
o
in
t
tr
ac
k
i
n
g
(
MPPT)
,
ad
ap
tiv
e
in
v
e
r
te
r
co
n
tr
o
l,
an
d
o
p
tim
ized
s
ch
ed
u
lin
g
o
f
DC
–
DC
co
n
v
er
ter
s
an
d
e
n
er
g
y
s
to
r
a
g
e
s
y
s
tem
s
.
B
y
in
teg
r
atin
g
f
o
r
ec
asti
n
g
o
u
tp
u
ts
in
to
co
n
tr
o
l
s
tr
ateg
ies,
th
e
f
r
am
ewo
r
k
s
u
p
p
o
r
ts
p
r
ed
ictiv
e
en
er
g
y
m
a
n
ag
em
e
n
t,
im
p
r
o
v
ed
o
p
er
atio
n
al
ef
f
icien
cy
,
an
d
en
h
a
n
ce
d
g
r
id
s
tab
ilit
y
.
Fu
r
th
er
m
o
r
e,
im
p
r
o
v
ed
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
h
as
th
e
p
o
ten
tial
to
r
ed
u
ce
r
en
ewa
b
le
en
er
g
y
cu
r
tailm
en
t
an
d
im
b
alan
ce
p
en
alties,
alth
o
u
g
h
th
ese
b
en
e
f
its
r
eq
u
ir
e
v
alid
atio
n
th
r
o
u
g
h
d
etailed
tech
n
o
-
ec
o
n
o
m
ic
an
d
g
r
id
-
lev
el
s
tu
d
ies.
T
h
e
p
r
esen
t
s
tu
d
y
is
b
ased
o
n
NSR
DB
d
ata
an
d
d
o
es
n
o
t
in
co
r
p
o
r
ate
r
ea
l
-
tim
e
m
ea
s
u
r
em
en
ts
o
r
p
h
y
s
ics
-
b
ased
co
n
s
tr
ain
ts
.
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
wa
s
ev
alu
ated
ac
r
o
s
s
f
o
u
r
I
n
d
ian
s
tates,
f
u
r
th
er
v
ali
d
atio
n
ac
r
o
s
s
ad
d
itio
n
al
clim
atic
r
eg
io
n
s
is
r
eq
u
ir
ed
.
I
n
ad
d
it
io
n
,
in
ter
p
r
etab
ilit
y
was
lim
ited
to
SHAP
an
aly
s
is
f
o
r
L
ig
h
tGB
M,
an
d
ex
te
n
d
in
g
e
x
p
lain
ab
ilit
y
tech
n
iq
u
e
s
to
d
ee
p
lea
r
n
in
g
m
o
d
els
wo
u
ld
p
r
o
v
i
d
e
f
u
r
t
h
er
in
s
ig
h
ts
.
Fu
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
r
ea
l
-
tim
e
v
ali
d
atio
n
,
p
h
y
s
ics
-
in
f
o
r
m
ed
an
d
p
r
o
b
a
b
ilis
tic
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es,
an
d
r
ep
ea
ted
ex
p
er
im
en
tal
tr
ials
w
ith
s
tat
is
tica
l
s
ig
n
if
ican
ce
test
in
g
to
f
u
r
th
er
e
n
h
an
ce
th
e
r
o
b
u
s
tn
ess
an
d
p
r
ac
tical
ap
p
licab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
o
p
o
s
ed
a
m
u
lti
-
o
u
tp
u
t
d
ee
p
lear
n
in
g
f
r
am
ew
o
r
k
f
o
r
t
h
e
s
im
u
ltan
eo
u
s
f
o
r
e
ca
s
tin
g
o
f
g
lo
b
al
h
o
r
izo
n
tal
ir
r
ad
ian
ce
(
GHI
)
an
d
win
d
s
p
ee
d
,
em
p
h
a
s
izin
g
cr
o
s
s
-
r
eg
io
n
al
t
r
an
s
f
er
a
b
ilit
y
ac
r
o
s
s
d
iv
er
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
I
SS
N:
2088
-
8
6
9
4
Mu
lti
-
o
u
tp
u
t d
ee
p
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
jo
in
t fo
r
ec
a
s
tin
g
o
f so
la
r
ir
r
a
d
ia
n
ce
…
(
S
.
S
elvi
)
2109
clim
atic
co
n
d
itio
n
s
.
Am
o
n
g
th
e
ev
alu
ated
m
o
d
els,
C
o
n
v
L
STM
ac
h
iev
ed
th
e
b
est
p
er
f
o
r
m
an
ce
(
MA
E
=
0
.
0
6
1
,
R
²
≈
0
.
9
1
)
,
d
e
m
o
n
s
t
r
atin
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
s
p
atio
-
tem
p
o
r
al
lear
n
i
n
g
f
o
r
r
en
ewa
b
le
en
er
g
y
f
o
r
ec
asti
n
g
.
T
h
e
r
esu
lts
f
u
r
th
er
s
h
o
wed
th
at
m
o
d
els
tr
ain
e
d
in
o
n
e
r
eg
i
o
n
ca
n
b
e
s
u
cc
ess
f
u
lly
ad
ap
ted
t
o
n
eig
h
b
o
r
in
g
r
e
g
io
n
s
th
r
o
u
g
h
tr
an
s
f
er
lear
n
in
g
with
m
in
im
al
p
er
f
o
r
m
a
n
ce
d
eg
r
ad
ati
o
n
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
h
as
p
r
ac
tical
r
ele
v
an
ce
f
o
r
r
e
n
ewa
b
le
en
e
r
g
y
s
y
s
tem
s
b
y
s
u
p
p
o
r
tin
g
im
p
r
o
v
ed
MPPT,
in
v
e
r
ter
o
p
er
atio
n
,
DC
–
DC
co
n
v
er
ter
co
n
tr
o
l,
an
d
en
er
g
y
m
an
ag
em
en
t.
I
m
p
r
o
v
ed
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
also
h
as
th
e
p
o
ten
tial
to
r
ed
u
ce
r
en
ewa
b
le
en
er
g
y
cu
r
tailm
en
t
an
d
im
b
al
an
ce
p
en
alties
wh
ile
en
h
an
cin
g
th
e
u
tili
za
tio
n
o
f
r
en
ewa
b
le
r
eso
u
r
ce
s
.
T
h
e
s
tu
d
y
is
lim
ited
b
y
th
e
u
s
e
o
f
NSR
DB
d
ata,
th
e
ab
s
en
ce
o
f
r
ea
l
-
ti
m
e
m
ea
s
u
r
em
en
ts
,
an
d
th
e
lack
o
f
p
h
y
s
ics
-
b
ased
co
n
s
tr
ain
ts
.
Fu
tu
r
e
wo
r
k
will
f
o
cu
s
o
n
r
ea
l
-
tim
e
v
alid
ati
o
n
,
p
h
y
s
ics
-
in
f
o
r
m
ed
an
d
p
r
o
b
a
b
ilis
tic
f
o
r
ec
asti
n
g
m
o
d
els,
b
r
o
a
d
er
clim
atic
e
v
alu
atio
n
,
an
d
en
h
a
n
ce
d
in
te
r
p
r
etab
ilit
y
o
f
d
ee
p
lear
n
in
g
m
o
d
els.
Ov
er
all,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
p
r
o
v
id
es
a
tr
an
s
p
ar
en
t,
s
ca
lab
le,
an
d
p
r
ac
tically
ap
p
licab
le
s
o
lu
tio
n
f
o
r
r
en
ewa
b
le
e
n
er
g
y
f
o
r
ec
asti
n
g
an
d
p
o
we
r
elec
tr
o
n
ic
s
y
s
tem
ap
p
licatio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
S.
Selv
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
An
n
am
alai
Mu
th
u
✓
✓
✓
✓
✓
✓
✓
Mu
r
ali
Nar
ay
an
am
u
r
th
y
✓
✓
✓
✓
✓
✓
✓
✓
B
.
Ar
d
ly
Me
lb
a
R
ee
n
a
✓
✓
✓
✓
✓
✓
Go
b
im
o
h
an
Siv
asu
b
r
am
an
ian
✓
✓
✓
✓
✓
✓
✓
✓
T.
L
o
g
eswar
an
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
licts
o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
in
f
o
r
m
ed
co
n
s
en
t w
as o
b
tai
n
ed
f
r
o
m
all
in
d
iv
id
u
als in
clu
d
ed
in
th
is
wo
r
k
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
is
p
u
b
licly
a
v
ailab
le
f
r
o
m
th
e
Natio
n
al
So
lar
R
ad
iatio
n
Data
b
ase
(
NSR
D
B
)
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
K
o
n
d
u
r
u
,
N
.
C
.
,
a
n
d
J.
S
.
M
.
,
“
A
d
v
a
n
c
e
d
s
o
l
a
r
i
r
r
a
d
i
a
n
c
e
f
o
r
e
c
a
s
t
i
n
g
u
si
n
g
h
y
b
r
i
d
e
n
sem
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
m
u
l
t
i
s
i
t
e
d
a
t
a
a
n
a
l
y
t
i
c
s
f
o
r
o
p
t
i
ma
l
so
l
a
r
‐
h
y
d
r
o
h
y
b
r
i
d
p
o
w
e
r
p
l
a
n
t
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
T
ra
n
s
a
c
t
i
o
n
s
o
n
E
l
e
c
t
r
i
c
a
l
E
n
e
r
g
y
S
y
s
t
e
m
s
,
v
o
l
.
2
0
2
5
,
n
o
.
1
,
Jan
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
5
/
e
t
e
p
/
6
6
9
4
5
0
4
.
[
2
]
S
a
r
i
t
a
S
h
e
o
r
a
n
,
R
.
S
.
S
i
n
g
h
,
S
.
P
a
s
a
r
i
,
a
n
d
R
.
K
u
l
s
h
r
e
st
h
a
,
“
F
o
r
e
c
a
st
i
n
g
o
f
so
l
a
r
i
r
r
a
d
i
a
n
c
e
s
u
si
n
g
t
i
me
se
r
i
e
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s:
A
c
a
s
e
s
t
u
d
y
f
r
o
m
I
n
d
i
a
,
”
A
p
p
l
i
e
d
S
o
l
a
r
En
e
r
g
y
,
v
o
l
.
5
8
,
n
o
.
1
,
p
p
.
1
3
7
–
1
5
1
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
1
0
3
/
S
0
0
0
3
7
0
1
X
2
2
0
1
0
1
7
0
.
[
3
]
K
.
S
u
d
h
a
r
s
h
a
n
,
C
.
N
a
v
e
e
n
,
P
.
V
i
s
h
n
u
r
a
m,
D
.
V
.
S
.
K
.
R
.
K
a
sa
g
a
n
i
,
a
n
d
B
.
N
a
s
t
a
si
,
“
S
y
st
e
ma
t
i
c
r
e
v
i
e
w
o
n
i
mp
a
c
t
o
f
d
i
f
f
e
r
e
n
t
i
r
r
a
d
i
a
n
c
e
f
o
r
e
c
a
st
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
s
o
l
a
r
e
n
e
r
g
y
p
r
e
d
i
c
t
i
o
n
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
5
,
n
o
.
1
7
,
p
.
6
2
6
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
1
7
6
2
6
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
2101
-
2
1
1
1
2110
[
4
]
A
.
K
u
mar,
Y
.
K
a
s
h
y
a
p
,
a
n
d
P
.
K
o
sm
o
p
o
u
l
o
s,
“
E
n
h
a
n
c
i
n
g
so
l
a
r
e
n
e
r
g
y
f
o
r
e
c
a
s
t
u
s
i
n
g
m
u
l
t
i
-
c
o
l
u
mn
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
m
u
l
t
i
p
o
i
n
t
t
i
me
s
e
r
i
e
s a
p
p
r
o
a
c
h
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
1
0
7
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
5
0
1
0
1
0
7
.
[
5
]
D
.
V
.
P
o
m
b
o
,
H
.
W
.
B
i
n
d
n
e
r
,
S
.
V
.
S
p
a
t
a
r
u
,
P
.
E
.
S
ø
r
e
n
se
n
,
a
n
d
P
.
B
a
c
h
e
r
,
“
I
n
c
r
e
a
s
i
n
g
t
h
e
a
c
c
u
r
a
c
y
o
f
h
o
u
r
l
y
m
u
l
t
i
-
o
u
t
p
u
t
s
o
l
a
r
p
o
w
e
r
f
o
r
e
c
a
s
t
w
i
t
h
p
h
y
si
c
s
-
i
n
f
o
r
m
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
3
,
p
.
7
4
9
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
0
3
0
7
4
9
.
[
6
]
Q
.
Li
,
D
.
Z
h
a
n
g
,
a
n
d
K
.
Y
a
n
,
“
A
s
o
l
a
r
i
r
r
a
d
i
a
n
c
e
f
o
r
e
c
a
s
t
i
n
g
f
r
a
mew
o
r
k
b
a
sed
o
n
t
h
e
C
E
E
-
W
G
A
N
-
LSTM
M
o
d
e
l
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
5
,
p
.
2
7
9
9
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
5
2
7
9
9
.
[
7
]
H
.
D
o
n
g
,
P
.
T
a
n
g
,
B
.
H
e
,
L.
C
h
e
n
,
Z
.
Zh
a
n
g
,
a
n
d
C
.
Ji
a
,
“
M
u
l
t
i
-
st
e
p
so
l
a
r
r
a
d
i
a
t
i
o
n
p
r
e
d
i
c
t
i
o
n
u
si
n
g
t
r
a
n
sf
o
r
m
e
r
:
A
c
a
se
s
t
u
d
y
f
r
o
m
so
l
a
r
r
a
d
i
a
t
i
o
n
d
a
t
a
i
n
T
o
k
y
o
,
”
J
o
u
rn
a
l
o
f
Bu
i
l
d
i
n
g
P
h
y
si
c
s
,
v
o
l
.
4
7
,
n
o
.
4
,
p
p
.
4
2
1
–
4
3
8
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
7
7
/
1
7
4
4
2
5
9
1
2
3
1
2
1
8
8
3
1
.
[
8
]
Z.
W
a
n
g
,
Y
.
Z
h
a
n
g
,
G
.
L
i
,
J
.
Z
h
a
n
g
,
H
.
Zh
o
u
,
a
n
d
J.
W
u
,
“
A
n
o
v
e
l
so
l
a
r
i
r
r
a
d
i
a
n
c
e
f
o
r
e
c
a
st
i
n
g
me
t
h
o
d
b
a
s
e
d
o
n
m
u
l
t
i
-
p
h
y
s
i
c
a
l
p
r
o
c
e
ss
o
f
a
t
mo
s
p
h
e
r
e
o
p
t
i
c
s
a
n
d
LST
M
-
B
P
m
o
d
e
l
,
”
Re
n
e
w
a
b
l
e
En
e
r
g
y
,
v
o
l
.
2
2
6
,
p
.
1
2
0
3
6
7
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
n
e
n
e
.
2
0
2
4
.
1
2
0
3
6
7
.
[
9
]
S
.
S
h
r
i
n
g
i
,
L
.
M
.
S
a
i
n
i
,
a
n
d
S
.
K
.
A
g
g
a
r
w
a
l
,
“
A
r
e
v
i
e
w
o
f
d
a
t
a
-
d
r
i
v
e
n
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
so
l
a
r
a
n
d
w
i
n
d
e
n
e
r
g
y
f
o
r
e
c
a
st
i
n
g
,
”
R
e
n
e
w
a
b
l
e
E
n
e
r
g
y
Fo
c
u
s
,
v
o
l
.
5
5
,
p
.
1
0
0
7
3
9
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
f
.
2
0
2
5
.
1
0
0
7
3
9
.
[
1
0
]
S
.
M
.
M
i
r
a
f
t
a
b
z
a
d
e
h
,
C
.
G
.
C
o
l
o
m
b
o
,
M
.
Lo
n
g
o
,
a
n
d
F
.
F
o
i
a
d
e
l
l
i
,
“
A
d
a
y
-
a
h
e
a
d
p
h
o
t
o
v
o
l
t
a
i
c
p
o
w
e
r
p
r
e
d
i
c
t
i
o
n
v
i
a
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
2
1
3
–
2
2
8
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
f
o
r
e
c
a
s
t
5
0
1
0
0
1
2
.
[
1
1
]
D
.
A
l
v
e
s,
F
.
M
e
n
d
o
n
ç
a
,
S
.
S
.
M
o
st
a
f
a
,
a
n
d
F
.
M
o
r
g
a
d
o
-
D
i
a
s
,
“
T
h
e
p
o
t
e
n
t
i
a
l
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
w
i
n
d
s
p
e
e
d
a
n
d
d
i
r
e
c
t
i
o
n
sh
o
r
t
-
t
e
r
m
f
o
r
e
c
a
s
t
i
n
g
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
1
0
,
p
.
2
0
6
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s1
2
1
0
0
2
0
6
.
[
1
2
]
S
.
L
i
a
n
g
,
L.
N
g
u
y
e
n
,
a
n
d
F
.
Ji
n
,
“
A
mu
l
t
i
-
v
a
r
i
a
b
l
e
s
t
a
c
k
e
d
l
o
n
g
-
s
h
o
r
t
t
e
r
m
me
mo
r
y
n
e
t
w
o
r
k
f
o
r
w
i
n
d
s
p
e
e
d
f
o
r
e
c
a
s
t
i
n
g
,
”
i
n
2
0
1
8
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
B
i
g
D
a
t
a
(
B
i
g
D
a
t
a
)
,
I
EEE,
D
e
c
.
2
0
1
8
,
p
p
.
4
5
6
1
–
4
5
6
4
.
d
o
i
:
1
0
.
1
1
0
9
/
B
i
g
D
a
t
a
.
2
0
1
8
.
8
6
2
2
3
3
2
.
[
1
3
]
H
.
S
h
u
,
W
.
S
o
n
g
,
Z.
S
o
n
g
,
H
.
G
u
o
,
C
.
L
i
,
a
n
d
Y
.
W
a
n
g
,
“
M
u
l
t
i
st
e
p
s
h
o
r
t
‐
t
e
r
m
w
i
n
d
s
p
e
e
d
p
r
e
d
i
c
t
i
o
n
w
i
t
h
r
a
n
k
p
o
o
l
i
n
g
a
n
d
f
a
st
F
o
u
r
i
e
r
t
r
a
n
sf
o
r
ma
t
i
o
n
,
”
W
i
n
d
E
n
e
rg
y
,
v
o
l
.
2
7
,
n
o
.
7
,
p
p
.
6
6
7
–
6
9
4
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
w
e
.
2
9
0
6
.
[
1
4
]
N
.
R
a
t
h
o
r
e
,
P
.
R
a
t
h
o
r
e
,
A
.
B
a
sa
k
,
S
.
H
.
N
i
st
a
l
a
,
a
n
d
V
.
R
u
n
k
a
n
a
,
“
M
u
l
t
i
S
c
a
l
e
G
r
a
p
h
W
a
v
e
n
e
t
f
o
r
w
i
n
d
s
p
e
e
d
f
o
r
e
c
a
s
t
i
n
g
,”
a
rXi
v
,
O
c
t
.
2
0
2
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
1
0
9
.
1
5
2
3
9
[
1
5
]
J.
H
e
,
H
.
Y
a
n
g
,
S
.
Zh
o
u
,
J.
C
h
e
n
,
a
n
d
M
.
C
h
e
n
,
“
A
d
u
a
l
-
a
t
t
e
n
t
i
o
n
-
me
c
h
a
n
i
sm
m
u
l
t
i
-
c
h
a
n
n
e
l
c
o
n
v
o
l
u
t
i
o
n
a
l
LST
M
f
o
r
s
h
o
r
t
-
t
e
r
m
w
i
n
d
s
p
e
e
d
p
r
e
d
i
c
t
i
o
n
,”
At
m
o
sp
h
e
r
e
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
7
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
t
m
o
s
1
4
0
1
0
0
7
1
.
[
1
6
]
H
.
S
u
n
,
T.
S
o
n
g
,
Y
.
L
i
,
K
.
Y
a
n
g
,
D
.
X
u
,
a
n
d
F
.
M
e
n
g
,
“
EE
M
D
-
C
o
n
v
LST
M
:
a
m
o
d
e
l
f
o
r
s
h
o
r
t
-
t
e
r
m
p
r
e
d
i
c
t
i
o
n
o
f
t
w
o
-
d
i
m
e
n
s
i
o
n
a
l
w
i
n
d
s
p
e
e
d
i
n
t
h
e
S
o
u
t
h
C
h
i
n
a
S
e
a
,
”
A
p
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
3
,
n
o
.
2
4
,
p
p
.
3
0
1
8
6
–
3
0
2
0
2
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
8
9
-
0
2
3
-
0
5
0
4
2
-
0.
[
1
7
]
D
.
W
e
i
a
n
d
Z
.
Ti
a
n
,
“
A
h
y
b
r
i
d
m
u
l
t
i
v
a
r
i
a
t
e
mu
l
t
i
st
e
p
w
i
n
d
-
sp
e
e
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
b
a
se
d
o
n
a
d
e
e
p
-
l
e
a
r
n
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
En
e
rg
y
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
5
0
,
n
o
.
6
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
6
1
/
J
L
EED
9
.
EY
EN
G
-
5
4
7
4
.
[
1
8
]
Z.
Z
h
a
n
g
,
L.
Li
n
,
S
.
G
a
o
,
J
.
W
a
n
g
,
H
.
Z
h
a
o
,
a
n
d
H
.
Y
u
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
h
u
b
-
h
e
i
g
h
t
s
h
o
r
t
-
t
e
r
m
w
i
n
d
s
p
e
e
d
p
r
e
d
i
c
t
i
o
n
,
”
N
a
t
u
r
e
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
n
o
.
1
,
p
.
3
1
9
5
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
4
6
7
-
025
-
5
8
4
5
6
-
4.
[
1
9
]
L.
Z
h
e
n
g
,
W
.
L
u
,
a
n
d
Q
.
Z
h
o
u
,
“
W
e
a
t
h
e
r
i
ma
g
e
-
b
a
s
e
d
s
h
o
r
t
-
t
e
r
m
d
e
n
s
e
w
i
n
d
s
p
e
e
d
f
o
r
e
c
a
s
t
w
i
t
h
a
C
o
n
v
LS
TM
-
LST
M
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
Bu
i
l
d
i
n
g
a
n
d
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
3
9
,
p
.
1
1
0
4
4
6
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
u
i
l
d
e
n
v
.
2
0
2
3
.
1
1
0
4
4
6
.
[
2
0
]
X
.
L
i
u
,
L.
Z
h
a
n
g
,
J
.
W
a
n
g
,
Y
.
Z
h
o
u
,
a
n
d
W
.
G
a
n
,
“
A
u
n
i
f
i
e
d
m
u
l
t
i
-
s
t
e
p
w
i
n
d
s
p
e
e
d
f
o
r
e
c
a
st
i
n
g
f
r
a
mew
o
r
k
b
a
sed
o
n
n
u
m
e
r
i
c
a
l
w
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
g
r
i
d
s
a
n
d
w
i
n
d
f
a
r
m
m
o
n
i
t
o
r
i
n
g
d
a
t
a
,
”
Re
n
e
w
a
b
l
e
E
n
e
rg
y
,
v
o
l
.
2
1
1
,
p
p
.
9
4
8
–
9
6
3
,
J
u
l
.
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
5
.
0
0
6
.
[
2
1
]
S
.
G
o
sw
a
mi
,
S
.
M
a
l
a
k
a
r
,
B
.
G
a
n
g
u
l
i
,
a
n
d
A
.
C
h
a
k
r
a
b
a
r
t
i
,
“
A
n
o
v
e
l
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
se
d
sh
o
r
t
-
t
e
r
m
s
o
l
a
r
f
o
r
e
c
a
st
i
n
g
a
p
p
r
o
a
c
h
f
o
r
I
n
d
i
a
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
1
9
,
p
p
.
1
6
8
2
9
–
1
6
8
4
3
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
2
-
0
7
3
2
8
-
9.
[
2
2
]
E.
S
a
r
m
a
s,
N
.
D
i
mi
t
r
o
p
o
u
l
o
s,
V
.
M
a
r
i
n
a
k
i
s,
Z.
M
y
l
o
n
a
,
a
n
d
H
.
D
o
u
k
a
s,
“
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
st
r
a
t
e
g
i
e
s
f
o
r
s
o
l
a
r
p
o
w
e
r
f
o
r
e
c
a
s
t
i
n
g
u
n
d
e
r
d
a
t
a
sc
a
r
c
i
t
y
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
4
6
4
3
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
2
-
1
8
5
1
6
-
x.
[
2
3
]
C
.
S
y
me
o
n
i
d
i
s
a
n
d
N
.
N
i
k
o
l
a
i
d
i
s,
“
Ef
f
i
c
i
e
n
t
d
e
t
e
r
m
i
n
i
st
i
c
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
f
o
r
e
c
a
s
t
i
n
g
g
u
i
d
e
d
b
y
mu
l
t
i
p
l
e
-
l
o
c
a
t
i
o
n
w
e
a
t
h
e
r
d
a
t
a
,
”
a
rXi
v
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
2
4
-
1
0
6
0
7
-
2.
[
2
4
]
M
.
L
.
S
ø
r
e
n
s
e
n
,
P
.
N
y
st
r
u
p
,
M
.
B
.
B
j
e
r
r
e
g
å
r
d
,
J
.
K
.
M
ø
l
l
e
r
,
P
.
B
a
c
h
e
r
,
a
n
d
H
.
M
a
d
se
n
,
“
R
e
c
e
n
t
d
e
v
e
l
o
p
m
e
n
t
s
i
n
mu
l
t
i
v
a
r
i
a
t
e
w
i
n
d
a
n
d
s
o
l
a
r
p
o
w
e
r
f
o
r
e
c
a
s
t
i
n
g
,
”
W
I
REs
E
n
e
r
g
y
a
n
d
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
1
2
,
n
o
.
2
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
w
e
n
e
.
4
6
5
.
[
2
5
]
Q
.
P
a
l
e
t
t
a
e
t
a
l
.
,
“
A
d
v
a
n
c
e
s
i
n
s
o
l
a
r
f
o
r
e
c
a
st
i
n
g
:
C
o
mp
u
t
e
r
v
i
si
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Ad
v
a
n
c
e
s
i
n
A
p
p
l
i
e
d
E
n
e
r
g
y
,
v
o
l
.
1
1
,
p
.
1
0
0
1
5
0
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
a
p
e
n
.
2
0
2
3
.
1
0
0
1
5
0
.
[
2
6
]
A
.
V
e
r
d
o
n
e
,
M
.
P
a
n
e
l
l
a
,
E.
D
e
S
a
n
t
i
s
,
a
n
d
A
.
R
i
z
z
i
,
“
A
r
e
v
i
e
w
o
f
s
o
l
a
r
a
n
d
w
i
n
d
e
n
e
r
g
y
f
o
r
e
c
a
st
i
n
g
:
F
r
o
m s
i
n
g
l
e
-
si
t
e
t
o
mu
l
t
i
-
si
t
e
p
a
r
a
d
i
g
m
,
”
Ap
p
l
i
e
d
En
e
rg
y
,
v
o
l
.
3
9
2
,
p
.
1
2
6
0
1
6
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
2
5
.
1
2
6
0
1
6
.
[
2
7
]
Y
.
C
h
u
,
Y
.
W
a
n
g
,
D
.
Y
a
n
g
,
S
.
C
h
e
n
,
a
n
d
M
.
Li
,
“
A
r
e
v
i
e
w
o
f
d
i
st
r
i
b
u
t
e
d
s
o
l
a
r
f
o
r
e
c
a
st
i
n
g
w
i
t
h
r
e
m
o
t
e
s
e
n
s
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
9
8
,
p
.
1
1
4
3
9
1
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.
2
0
2
4
.
1
1
4
3
9
1
.
B
IOG
RA
PHIE
S
OF A
UTH
ORS
S.
S
e
lv
i
is
a
p
ro
fe
ss
o
r
a
n
d
He
a
d
o
f
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
a
t
P
a
n
ima
lar
E
n
g
i
n
e
e
rin
g
C
o
ll
e
g
e
.
S
h
e
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
ri
n
g
d
e
g
re
e
i
n
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ics
e
n
g
i
n
e
e
rin
g
fr
o
m
t
h
e
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
G
u
in
d
y
,
An
n
a
Un
i
v
e
rsity
.
S
h
e
o
b
tain
e
d
h
e
r
M
a
ste
r
o
f
En
g
i
n
e
e
rin
g
d
e
g
r
e
e
in
p
o
we
r
e
lec
tro
n
ics
a
n
d
d
riv
e
s
a
n
d
h
e
r
d
o
c
to
ra
l
d
e
g
re
e
fro
m
S
a
th
y
a
b
a
m
a
Un
i
v
e
rsity
,
C
h
e
n
n
a
i.
S
h
e
h
a
s
a
p
p
r
o
x
ima
tely
3
0
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
r
a
re
a
s
o
f
re
se
a
r
c
h
in
tere
st
in
c
l
u
d
e
li
g
h
t
n
i
n
g
a
n
d
i
n
d
u
strial
d
riv
e
s.
S
h
e
h
a
s
p
u
b
l
ish
e
d
se
v
e
ra
l
re
se
a
rc
h
a
rti
c
les
in
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
j
o
u
r
n
a
ls.
S
h
e
h
a
s
a
lso
se
c
u
re
d
a
p
p
ro
x
ima
tely
Rs.
1
5
la
k
h
s
in
r
e
se
a
rc
h
fu
n
d
i
n
g
,
i
n
c
lu
d
in
g
a
g
ra
n
t
fr
o
m
th
e
All
-
In
d
ia
Co
u
n
c
il
fo
r
Tec
h
n
ica
l
E
d
u
c
a
ti
o
n
(AICT
E).
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
se
lv
ise
lv
a
ra
j@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.