I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
w
er
E
lect
ro
nics
a
nd
Driv
e
Sy
s
t
e
m
(
I
J
P
E
DS
)
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
1
8
,
p
p
.
397
~
405
I
SS
N:
2088
-
8
694
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
p
ed
s
.
v
9
.
i1
.
pp
3
9
7
-
405
397
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JP
E
DS
V
ery
-
Sh
o
rt Te
rm
Wind P
o
w
er F
o
rec
a
s
t
i
ng
thr
o
u
g
h
Wa
v
elet
Ba
sed
ANFIS
M
.
Na
nd
a
na
J
y
o
t
hi
1
,
P
.
V.
R
a
m
a
na
Ra
o
2
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
E
n
g
in
e
e
rin
g
,
A
NU
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
A
c
h
a
r
y
a
Na
g
a
rju
n
a
Un
iv
e
rsit
y
,
An
d
h
ra
P
ra
d
e
sh
,
5
2
2
5
1
0
,
In
d
ia.
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
,
2
0
1
7
R
ev
i
s
ed
Dec
2
9
,
2
0
1
7
A
cc
ep
ted
J
an
7
,
2
0
1
8
T
h
is
p
a
p
e
r
p
r
o
p
o
se
s
a
W
a
v
e
le
t
b
a
se
d
A
d
a
p
ti
v
e
Ne
u
ro
-
F
u
z
z
y
In
f
e
re
n
c
e
S
y
st
e
m
(
WA
NFIS
)
a
p
p
li
e
d
to
f
o
re
c
a
st
th
e
w
in
d
p
o
w
e
r
a
n
d
e
n
h
a
n
c
e
th
e
a
c
c
u
ra
c
y
o
f
o
n
e
ste
p
a
h
e
a
d
w
it
h
a
1
0
m
in
u
tes
re
so
l
u
ti
o
n
o
f
re
a
l
ti
m
e
d
a
ta
c
o
ll
e
c
ted
f
ro
m
a
w
in
d
f
a
r
m
in
No
rth
I
n
d
ia.
T
h
e
p
r
o
p
o
se
d
m
e
th
o
d
c
o
n
sists
tw
o
c
a
s
e
s.
In
th
e
f
irst
c
a
se
a
ll
th
e
in
p
u
ts
o
f
w
in
d
se
ries
a
n
d
o
u
tp
u
t
o
f
w
in
d
p
o
w
e
r
d
e
c
o
m
p
o
siti
o
n
c
o
e
ff
icie
n
ts
a
re
c
a
rried
o
u
t
to
p
re
d
ict
t
h
e
win
d
p
o
w
e
r.
In
th
e
se
c
o
n
d
c
a
se
a
ll
th
e
in
p
u
ts
o
f
w
in
d
se
ries
d
e
c
o
m
p
o
siti
o
n
c
o
e
ff
icie
n
ts
a
re
c
a
rried
o
u
t
to
g
e
t
w
in
d
p
o
w
e
r
p
re
d
icti
o
n
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
p
ro
p
o
se
d
WA
NFIS
is
c
o
m
p
a
re
d
to
W
a
v
e
le
t
Ne
u
ra
l
Ne
tw
o
rk
(W
NN
)
a
n
d
th
e
re
su
lt
s
o
f
th
e
p
r
o
p
o
se
d
m
o
d
e
l
a
re
sh
o
w
n
su
p
e
rio
r
t
o
c
o
m
p
a
re
d
m
e
th
o
d
s.
K
ey
w
o
r
d
:
W
av
elet
b
ased
an
f
is
(
W
ANFI
S)
W
av
elet
d
ec
o
m
p
o
s
itio
n
W
av
elet
n
e
u
r
al
n
et
w
o
r
k
(
W
NN)
W
in
d
p
o
w
er
f
o
r
ec
asti
n
g
Co
p
y
rig
h
t
©
201
8
In
s
t
it
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
M.
Nan
d
an
a
J
y
o
th
i,
Dep
ar
te
m
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
i
n
ee
r
in
g
,
A
N
U
C
o
lle
g
e
o
f
E
n
g
i
n
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
,
A
c
h
ar
y
a
Na
g
ar
j
u
n
a
U
n
i
v
er
s
it
y
,
Nag
ar
j
u
n
a
Na
g
ar
,
Gu
n
t
u
r
-
5
2
2
5
1
0
,
A
n
d
h
r
a
P
r
ad
esh
,
I
n
d
ia.
E
m
ail:
n
an
d
a
n
aj
y
o
t
h
i2
0
8
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
So
lv
i
n
g
t
h
e
w
i
n
d
p
o
w
er
f
o
r
ec
asti
n
g
p
r
o
b
le
m
is
t
h
e
m
o
s
t
s
ig
n
i
f
ica
n
t
to
in
teg
r
ate
t
h
e
p
o
w
er
g
r
id
.
W
in
d
p
o
w
er
f
o
r
ec
asti
n
g
also
h
elp
s
to
w
ar
d
s
t
h
e
v
o
lta
g
e
s
ta
b
ilit
y
f
o
r
tr
an
s
m
i
s
s
io
n
a
n
d
d
is
tr
ib
u
tio
n
o
f
s
y
s
te
m
,
q
u
alit
y
o
f
p
o
w
er
,
r
eliab
ilit
y
a
n
d
m
a
in
te
n
a
n
ce
s
c
h
ed
u
le
f
o
r
o
p
tim
a
l
o
p
er
atin
g
co
s
t,
r
ea
l
ti
m
e
d
is
p
atc
h
d
ec
is
io
n
f
o
r
elec
tr
ic
m
ar
k
et,
u
n
it
co
m
m
it
m
e
n
t,
lo
ad
s
ch
ed
u
li
n
g
,
p
o
w
er
r
eser
v
e
s
,
etc.
W
h
en
t
h
e
w
i
n
d
en
er
g
y
i
s
h
i
g
h
l
y
s
to
ch
ast
ic
n
o
n
li
n
ea
r
i
n
n
a
tu
r
e
th
en
t
h
e
w
i
n
d
p
o
w
er
p
r
o
d
u
ce
r
s
n
ee
d
to
g
i
v
e
v
er
y
ac
c
u
r
ate
i
n
f
o
r
m
atio
n
in
o
r
d
er
to
m
iti
g
ate
u
n
ce
r
tai
n
t
y
.
Ma
n
y
ad
v
an
ce
d
s
tu
d
ies
h
a
v
e
b
ee
n
co
m
m
itted
to
i
m
p
r
o
v
e
m
e
n
ts
o
f
w
in
d
p
o
w
er
f
o
r
ec
asti
n
g
tec
h
n
iq
u
es.
A
g
o
o
d
n
u
m
b
er
o
f
m
et
h
o
d
s
ar
e
d
ev
elo
p
ed
o
n
th
ese
f
o
r
ec
asti
n
g
tech
n
iq
u
e
s
m
ai
n
l
y
Naïv
e
Me
t
h
o
d
,
P
h
y
s
ical
A
p
p
r
o
ac
h
,
Stat
is
tical
A
p
p
r
o
ac
h
es,
Ne
w
T
ec
h
n
iq
u
es,
an
d
H
y
b
r
id
A
p
p
r
o
ac
h
es
ex
p
lain
ed
b
y
So
m
a
n
S.
S
et
a
l.
[
1
]
.
Naïv
e
f
o
r
ec
asti
n
g
m
et
h
o
d
is
al
s
o
k
n
o
w
n
as
‘
P
er
s
is
te
n
c
e
Me
th
o
d
’
.
I
t
i
s
t
h
e
m
o
s
t
co
s
t
ef
f
ec
ti
v
e
m
eth
o
d
an
d
a
b
en
ch
m
ar
k
w
h
ic
h
is
m
o
r
e
s
o
p
h
is
ticated
an
d
it
is
a
s
s
u
m
e
d
to
h
av
e
th
e
w
i
n
d
s
p
ee
d
at
ti
m
e
‘
t+
Δ
t
’
.
P
h
y
s
ical
-
ap
p
r
o
ac
h
f
o
r
ec
asti
n
g
tec
h
n
o
lo
g
y
co
n
s
is
t
o
f
s
ev
er
al
s
u
b
-
m
eth
o
d
s
w
h
ich
alto
g
eth
er
an
d
d
eliv
er
th
e
tr
a
n
s
lat
io
n
f
r
o
m
t
h
e
w
i
n
d
p
r
ed
ictio
n
at
a
ce
r
tain
p
o
in
t a
n
d
m
o
d
el
le
v
el,
to
p
r
ed
ict
p
o
w
er
at
t
h
e
s
ite
co
n
s
id
er
ed
.
Statis
t
ical
ap
p
r
o
ac
h
f
o
r
ec
asti
n
g
m
et
h
o
d
s
ar
e
b
as
ed
o
n
h
i
s
to
r
ical
d
ata
o
f
m
eteo
r
o
lo
g
ical
v
ar
iab
les,
g
en
er
ated
p
o
w
er
an
d
w
i
n
d
p
o
w
er
m
ea
s
u
r
e
m
e
n
ts
.
T
h
ese
a
r
e
f
r
eq
u
en
tl
y
u
p
d
ated
d
u
r
in
g
o
n
lin
e
p
r
o
ce
s
s
f
o
r
ac
co
u
n
ti
n
g
r
ec
en
tl
y
a
v
ailab
le
in
f
o
r
m
a
tio
n
.
T
h
e
s
tatis
tical
m
o
d
el
s
co
n
s
i
s
t
o
f
n
o
n
lin
ea
r
an
d
lin
ea
r
.
Au
to
-
R
eg
r
es
s
i
v
e
Mo
v
i
n
g
Av
er
ag
e
(
A
R
M
A
)
ar
e
m
o
r
e
p
o
p
u
lar
in
th
e
ti
m
e
s
er
ie
s
ap
p
r
o
ac
h
,
Au
to
r
eg
r
es
s
i
v
e
in
te
g
r
ated
m
o
v
i
n
g
av
er
a
g
e
(
AR
I
M
A
)
,
s
ea
s
o
n
a
l
-
a
n
d
f
r
a
ctio
n
al
-
A
R
I
M
A
,
AR
M
A
w
i
t
h
ex
o
g
en
o
u
s
i
n
p
u
t
(
AR
M
A
X
o
r
AR
X)
ar
e
s
e
v
e
r
al
v
ar
iatio
n
s
to
p
r
ed
ict
w
in
d
s
p
ee
d
an
d
p
o
w
er
[
2
-
4
]
.
H
y
b
r
id
m
et
h
o
d
is
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i S
y
s
t
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
1
8
:
397
–
4
0
5
398
co
m
b
i
n
atio
n
o
f
p
h
y
s
ical
a
n
d
s
tatis
tica
l
ap
p
r
o
ac
h
es
f
o
r
s
h
o
r
t
ter
m
a
n
d
m
ed
iu
m
-
ter
m
f
o
r
ec
asti
n
g
m
o
d
els,
w
h
ic
h
is
co
n
s
id
er
ed
as
h
y
b
r
id
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
.
Fo
r
ex
a
m
p
le,
ar
tif
icia
l
n
e
u
r
al
n
et
w
o
r
k
tech
n
iq
u
es
w
it
h
NW
P
m
o
d
els to
g
et
w
i
n
d
s
p
ee
d
an
d
p
o
w
er
f
o
r
ec
asti
n
g
[
5
-
7
]
.
Fo
r
ec
asti
n
g
o
f
th
e
w
i
n
d
p
o
w
er
g
e
n
er
atio
n
ca
n
b
e
cla
s
s
i
f
ied
i
n
to
f
o
u
r
d
if
f
er
en
t
ti
m
e
s
ca
les,
d
ep
en
d
in
g
u
p
o
n
ap
p
licatio
n
.
F
r
o
m
m
il
lis
ec
o
n
d
s
to
f
e
w
m
in
u
tes,
f
o
r
v
er
y
s
h
o
r
t
ter
m
f
o
r
ec
a
s
tin
g
s
y
s
te
m
,
it
ca
n
b
e
u
s
ed
f
o
r
th
e
tu
r
b
i
n
e
ac
ti
v
e
p
o
w
er
co
n
tr
o
l,
E
lectr
icit
y
Ma
r
k
et,
an
d
R
e
g
u
latio
n
p
r
o
c
ed
u
r
es.
Fo
r
h
o
u
r
s
to
d
ay
s
,
f
o
r
ec
ast
m
a
y
b
e
co
n
s
id
e
r
ed
m
ed
iu
m
ter
m
f
o
r
ec
asti
n
g
s
y
s
te
m
.
I
t
m
a
y
b
e
u
s
ed
f
o
r
Gen
er
ato
r
On
/O
f
f
lin
e
Dec
is
io
n
s
,
Op
er
atio
n
al
Secu
r
i
t
y
.
Fo
r
lo
n
g
er
ti
m
e
s
ca
le
s
f
r
o
m
d
a
y
s
to
w
ee
k
m
o
r
e
f
o
r
ec
ast
s
m
a
y
b
e
co
n
s
id
er
ed
as
lo
n
g
ter
m
f
o
r
ec
asti
n
g
s
y
s
t
e
m
,
f
o
r
p
lan
n
i
n
g
t
h
e
m
ai
n
te
n
an
ce
o
f
w
i
n
d
f
ar
m
s
,
p
o
w
er
r
eser
v
e
d
ec
is
io
n
s
,
m
ai
n
ten
a
n
ce
s
ch
ed
u
li
n
g
to
Ob
tain
Op
ti
m
al
Op
er
atin
g
C
o
s
t
[
8
]
.
M.
Nan
d
an
a
J
y
o
t
h
i
e
t
a
l
.
ex
p
lain
ed
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
,
ad
ap
tiv
e
n
e
u
r
o
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
(
ANFI
S)
an
d
W
av
elet
Neu
r
al
N
et
w
o
r
k
f
o
r
th
e
v
er
y
s
h
o
r
t
ter
m
an
d
s
h
o
r
t
ter
m
w
i
n
d
p
o
w
er
p
r
ed
ictio
n
o
f
r
ea
l
ti
m
e
w
i
n
d
p
o
w
er
g
en
er
ated
d
ata
[
1
9
-
2
0
]
.
T
h
e
p
r
esen
t
ar
ticle
w
o
r
k
f
o
cu
s
e
s
o
n
v
er
y
-
s
h
o
r
t
ter
m
w
in
d
p
o
w
er
f
o
r
ec
asti
n
g
p
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
an
d
ac
cu
r
ac
y
en
h
a
n
ce
m
en
t
th
r
o
u
g
h
W
av
ele
t
b
ased
A
d
ap
tiv
e
Neu
r
o
-
F
u
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
(
W
A
NFI
S).
T
h
e
h
y
b
r
id
w
i
n
d
p
o
w
er
f
o
r
ec
asti
n
g
m
o
d
el
is
u
s
ed
to
p
r
e
d
ict
th
e
w
i
n
d
p
o
w
er
f
r
o
m
r
ea
l ti
m
e
S
C
A
D
A
w
i
n
d
f
ar
m
s
y
s
te
m
.
2.
WI
ND
F
ARM
CH
ARAC
T
E
RIS
T
I
C
S ST
U
DY
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
ai
m
i
s
b
ased
o
n
m
ea
s
u
r
ed
d
ata
f
r
o
m
w
i
n
d
p
o
w
er
tu
r
b
in
e
i
n
a
w
in
d
f
ar
m
at
a
s
p
ec
if
ic
lo
ca
tio
n
i
n
No
r
t
h
I
n
d
ia.
T
h
e
ti
m
e
-
s
er
ies
o
f
1
0
m
in
u
tes
d
ata
o
f
w
i
n
d
s
p
ee
d
,
a
m
b
ien
t
te
m
p
ar
at
u
r
e,
w
i
n
d
d
ir
ec
tio
n
,
w
i
n
d
d
en
s
i
t
y
an
d
w
i
n
d
p
o
w
er
.
T
h
ese
ar
e
n
o
r
m
alize
d
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
f
o
r
ec
asti
n
g
m
o
d
el.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
t
y
p
ica
l p
o
w
er
v
ar
iatio
n
s
o
f
a
d
a
y
.
F
ig
u
r
e
2
an
d
3
s
h
o
w
s
t
h
e
n
o
r
m
alize
d
w
i
n
d
p
o
w
er
v
s
n
o
r
m
alize
d
w
i
n
d
s
p
ee
d
an
d
n
o
r
m
a
lized
w
i
n
d
p
o
w
er
v
s
n
o
r
m
alize
d
am
b
ien
t
te
m
p
er
atu
r
e.
W
in
d
p
o
w
er
c
u
r
v
e
i
s
c
u
b
ic
a
n
d
n
o
n
li
n
ea
r
n
at
u
r
e.
T
h
e
to
ta
l
n
u
m
b
er
o
f
i
n
d
iv
id
u
al
ti
m
e
s
er
ies
d
ata
o
f
w
i
n
d
s
p
ee
d
,
w
in
d
d
en
s
i
t
y
,
a
m
b
ie
n
t
te
m
p
er
atu
r
e
an
d
w
i
n
d
d
ir
ec
tio
n
ar
e
2
1
4
3
.
I
n
th
is
2
0
0
0
d
ata
s
a
m
p
les
w
er
e
tak
e
n
in
to
tr
ain
i
n
g
p
u
r
p
o
s
e
an
d
1
4
3
ti
m
e
s
er
ie
s
d
ata
s
a
m
p
le
s
ar
e
tak
en
f
o
r
test
i
n
g
o
f
w
i
n
d
p
o
w
er
f
o
r
ec
asti
n
g
m
o
d
el.
Fig
u
r
e
1
.
T
y
p
ical
W
in
d
P
o
w
er
Var
iatio
n
o
f
a
Da
y
Fig
u
r
e
2
.
No
r
m
alize
d
W
in
d
P
o
w
er
Vs No
r
m
alize
d
W
in
d
Sp
ee
d
Fig
u
r
e
.
3
.
No
r
m
alize
d
W
in
d
P
o
w
er
Vs No
r
m
alize
d
Am
b
ie
n
t
T
em
p
er
atu
r
e
3.
WAVE
L
E
T
B
AS
E
D
ANF
I
S
3
.
1
M
o
dellin
g
o
f
Wa
v
elet
ba
s
ed
ANF
I
S
T
h
e
W
av
elet
B
ased
A
NFI
S
s
tr
u
ctu
r
e
i
s
s
i
m
ilar
to
A
NFI
S
m
o
d
el
b
u
t
n
eu
r
al
w
ei
g
h
t
s
ar
e
,
b
ased
o
n
w
a
v
elet
f
u
n
ctio
n
v
al
u
e
a
s
w
e
l
l
as
d
ilat
io
n
a
n
d
tr
a
n
s
lat
io
n
p
a
r
a
m
eter
s
.
T
r
an
s
latio
n
a
n
d
d
ila
tio
n
p
ar
a
m
ete
r
s
ar
e
u
p
d
ated
at
ev
er
y
iter
atio
n
s
o
t
h
at
n
et
w
o
r
k
co
n
v
er
g
e
n
ce
is
f
a
s
ter
an
d
ac
c
u
r
ate
[
1
3
]
.
W
av
el
et
A
d
ap
tiv
e
Ne
u
r
o
-
Fu
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
(
AN
FIS)
m
o
d
el
is
s
h
o
w
n
i
n
Fi
g
u
r
e
4
,
w
h
ic
h
co
n
s
is
t
s
i
x
la
y
er
s
.
T
h
e
f
ir
s
t
la
y
er
is
in
p
u
t
la
y
er
,
s
ec
o
n
d
la
y
er
is
f
u
zz
if
ica
tio
n
la
y
er
,
th
ir
d
la
y
er
is
in
f
er
en
ce
la
y
er
a
n
d
f
o
u
r
th
la
y
er
is
d
ef
u
zz
i
f
icatio
n
la
y
er
,
f
if
th
la
y
er
is
w
a
v
elet
f
u
n
ctio
n
la
y
er
an
d
last
la
y
er
is
o
u
tu
t
la
y
er
.
First
s
tep
o
f
t
h
i
s
m
o
d
el
is
id
e
n
ti
f
icatio
n
o
f
s
ig
n
i
f
ica
n
t
n
u
m
b
er
o
f
in
p
u
ts
.
T
h
e
s
ec
o
n
d
s
tep
is
id
en
ti
f
i
ca
tio
n
o
f
ap
p
r
o
p
r
iate
n
u
m
b
er
an
d
s
h
ap
e
o
f
f
u
zz
y
0
50
100
150
0
100
200
300
400
500
600
700
1
0
M
i
n
u
t
e
s
o
f
t
h
e
D
a
y
W
i
n
d
P
o
w
e
r
i
n
K
W
h
0
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
-
0
.
2
0
0
.
2
0
.
4
0
.
6
0
.
8
1
1
.
2
N
o
r
m
a
l
i
z
e
d
W
i
n
d
S
p
e
e
d
N
o
r
m
a
l
i
z
e
d
W
i
n
d
P
o
w
e
r
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
-
0
.
2
0
0
.
2
0
.
4
0
.
6
0
.
8
1
1
.
2
A
m
b
i
e
n
t
T
e
m
p
a
r
a
t
u
r
e
W
i
n
d
S
p
e
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i
S
y
s
t
I
SS
N:
2088
-
8
694
V
ery
-
S
h
o
r
t Term
W
in
d
P
o
w
er F
o
r
ec
a
s
tin
g
th
r
o
u
g
h
…
(
M.
N
a
n
d
a
n
a
Jy
o
th
i
)
399
p
ar
titi
o
n
in
g
t
h
at
is
m
o
d
elin
g
o
f
f
u
zz
y
r
u
le
s
o
f
T
S
m
o
d
el.
T
h
en
th
e
s
tr
u
ct
u
r
e
o
f
t
h
e
n
e
t
w
o
r
k
is
k
n
o
w
n
.
E
v
er
y
n
eu
r
o
n
i
n
t
h
e
f
u
zz
i
f
icatio
n
la
y
er
s
ig
n
if
ies t
h
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
[
1
4
]
.
Fig
u
r
e
4
.
Stru
ct
u
r
e
o
f
W
av
elet
B
ased
A
NFI
S
T
h
e
f
u
zz
i
f
icatio
n
o
u
tp
u
t la
y
er
is
ex
p
r
ess
ed
as
ik
l
ik
i
ik
i
ik
u
w
u
w
u
)
e
x
p
(
)
(
0
0
(
1
)
W
h
er
e
ik
is
f
u
zz
y
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
o
f
t
h
e
it
h
v
ar
iab
l
e
o
f
in
p
u
t,
w
h
ic
h
co
r
r
esp
o
n
d
s
to
th
e
k
t
h
r
u
le
an
d
ik
l
T
h
e
o
u
tp
u
t o
f
I
n
f
er
en
ce
is
)
(
)
(
)
,
.
.
.
,
(
1
2
1
i
ik
n
i
k
n
k
u
u
u
u
u
(
2
)
T
h
e
co
m
b
in
a
tio
n
o
f
i
n
p
u
t a
n
d
th
e
f
u
zz
i
f
icatio
n
la
y
er
i
s
n
e
u
r
al
n
et
w
o
r
k
w
ei
g
h
t,
w
h
ic
h
i
s
ex
p
r
ess
ed
as
}
,
{
ik
ik
w
w
W
; W
h
er
e
i=1
,
2
.
.
n
an
d
k
=1
,
2
.
.
r
.
Her
e
th
e
w
eig
h
t
s
co
n
n
ec
ted
i
n
b
et
w
ee
n
th
ir
d
a
n
d
f
o
u
t
h
la
y
er
s
w
h
ich
ce
n
tr
al
v
alu
e
is
{
k
v
}.
T
h
ese
ar
e
lab
eled
by
)
,
.
.
2
,
1
:
(
r
k
v
V
k
.
T
h
e
o
u
tp
u
t o
f
d
ef
u
zz
if
ied
la
y
e
r
is
w
ei
g
h
ted
s
u
m
r
k
k
k
u
v
y
1
)
(
(
3
)
T
h
e
f
if
t
h
la
y
er
ea
ch
n
o
d
e
is
la
b
elled
w
it
h
l
w
.
So
th
e
ea
ch
n
o
d
e
f
u
n
ctio
n
is
l
n
i
il
l
w
W
)
(
1
l
il
n
i
il
l
w
v
v
W
)
)
2
e
x
p
(
(
2
1
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i S
y
s
t
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
1
8
:
397
–
4
0
5
400
W
h
er
e
il
is
Gau
s
s
ia
n
f
u
n
ctio
n
a
s
a
m
o
t
h
er
w
av
e
let
f
u
n
ctio
n
w
h
ich
r
ep
r
esen
ts
il
il
i
il
a
b
u
v
)
(
W
h
er
e
th
e
il
a
an
d
il
b
b
ein
g
t
h
e
d
ilati
o
n
an
d
tr
an
s
la
tio
n
p
ar
a
m
eter
s
o
f
w
a
v
elet
a
n
d
also
l
w
is
n
o
d
e
p
a
r
a
m
eter
T
h
e
5
th
la
y
er
o
u
tp
u
t i
s
in
t
h
e
f
o
r
m
o
f
l
l
l
v
w
O
(
5
)
T
h
e
f
in
al
o
u
tp
u
t la
y
er
o
f
W
ANFI
S
m
o
d
el
lab
eled
w
i
th
s
u
m
m
atio
n
o
f
all
i
n
co
m
i
n
g
s
i
g
n
al
f
r
o
m
la
y
er
f
i
v
e
is
l
n
l
l
v
w
Y
1
(
6
)
Fig
u
r
e
5
.
No
r
m
alize
d
W
in
d
S
p
ee
d
Dec
o
m
p
o
s
itio
n
Fig
u
r
e
6
.
No
r
m
alize
d
Am
b
ien
t T
em
p
er
atu
r
e
De
co
m
p
o
s
itio
n
Fig
u
r
e
7
.
No
r
m
alize
d
W
in
d
D
ir
ec
tio
n
Dec
o
m
p
o
s
itio
n
Fig
u
r
e
8
.
No
r
m
alize
d
W
in
d
D
en
s
it
y
Dec
o
m
p
o
s
itio
n
Her
e
th
e
p
r
o
p
o
s
ed
p
r
o
b
lem
i
s
co
n
s
id
er
ed
in
t
w
o
ca
s
es.
I
n
th
e
f
ir
s
t
ca
s
e
all
th
e
i
n
p
u
t
an
d
o
u
tp
u
t
s
ig
n
al
s
d
etailed
an
d
ap
p
r
o
x
i
m
ated
co
ef
f
icie
n
t
s
w
er
e
g
iv
e
n
to
t
h
e
n
e
t
w
o
r
k
,
f
in
a
ll
y
all
p
r
ed
icted
co
ef
f
icien
t
s
ar
e
co
m
b
in
ed
to
g
et
h
er
to
g
et
ac
tu
al
f
o
r
ec
asted
w
i
n
d
p
o
w
er
.
I
n
th
e
s
ec
o
n
d
o
n
l
y
t
h
e
i
n
p
u
t
s
ig
n
al
co
ef
f
icie
n
ts
w
er
e
g
i
v
en
to
th
e
n
et
w
o
r
k
f
r
o
m
t
h
e
w
a
v
elet
tr
an
s
f
o
r
m
a
tio
n
s
.
Fi
n
all
y
f
o
u
n
d
th
e
f
o
r
ec
aste
d
w
i
n
d
p
o
w
er
.
T
h
e
tr
ain
i
n
g
o
f
W
av
elet
b
ased
ANFI
S
n
et
w
o
r
k
is
h
a
v
in
g
f
o
u
r
in
p
u
t
s
,
f
o
r
ea
ch
in
p
u
t
t
h
r
ee
s
ets
o
f
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
w
er
e
u
s
ed
to
g
et
f
u
z
z
y
r
u
les.
A
g
r
ad
ie
n
t
d
esce
n
t
m
et
h
o
d
w
ith
a
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
i
s
u
s
ed
to
m
in
i
m
ize
co
s
t
o
f
f
u
n
ctio
n
.
T
h
ese
ar
e
d
if
f
er
en
tiab
le
w
i
th
r
esp
ec
t
to
tr
an
s
latio
n
,
d
ilatio
n
u
n
k
n
o
w
n
v
ar
iab
le
w
ei
g
h
ts
a
n
d
b
ias
o
f
t
h
e
n
et
w
o
r
k
[
1
5
-
1
6
]
.
W
av
elet
h
as
t
w
o
p
r
o
p
er
ties
.
T
h
e
f
ir
s
t
is
l
o
ca
lizatio
n
o
f
ti
m
e
-
f
r
eq
u
en
c
y
e
n
er
g
y
s
i
g
n
al
r
ep
r
esen
ted
b
y
a
f
e
w
ex
p
a
n
s
io
n
an
d
co
m
p
r
es
s
io
n
co
ef
f
icie
n
ts
.
T
h
e
s
ec
o
n
d
is
Mu
lt
i
R
eso
l
u
tio
n
An
al
y
s
is
(
M
R
A
)
o
f
en
er
g
y
s
i
g
n
al.
T
h
e
s
elec
ti
o
n
o
f
w
a
v
elet
tr
an
s
f
o
r
m
d
ep
en
d
s
o
n
th
e
t
y
p
e
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i
S
y
s
t
I
SS
N:
2088
-
8
694
V
ery
-
S
h
o
r
t Term
W
in
d
P
o
w
er F
o
r
ec
a
s
tin
g
th
r
o
u
g
h
…
(
M.
N
a
n
d
a
n
a
Jy
o
th
i
)
401
ap
p
licatio
n
.
Dau
b
ec
h
ie
s
w
av
elet
is
u
s
ed
to
d
ec
o
m
p
o
s
e
th
e
s
ig
n
als,
b
ec
au
s
e
it’s
h
a
v
i
n
g
h
i
g
h
er
n
u
m
b
er
o
f
v
an
i
s
h
in
g
p
o
in
t
s
.
I
n
th
i
s
w
a
v
e
let
m
u
lti
r
e
s
o
lu
tio
n
a
n
al
y
s
is
te
ch
n
iq
u
e
w
a
s
u
s
ed
to
d
ec
o
m
p
o
s
e
th
e
w
in
d
s
p
ee
d
,
w
i
n
d
d
en
s
it
y
,
a
m
b
i
e
n
t
te
m
p
er
atu
r
e,
w
i
n
d
d
ir
ec
tio
n
an
d
also
f
o
u
n
d
th
e
ap
p
r
o
x
i
m
ated
an
d
d
etailed
co
ef
f
icie
n
ts
.
T
h
ese
t
w
o
co
e
f
f
icien
t
s
co
m
b
i
n
atio
n
is
u
s
ed
to
e
v
alu
a
te
th
e
s
ig
n
al
at
a
ll
le
v
els
a
n
d
eli
m
i
n
a
te
n
o
is
e
f
r
o
m
s
i
g
n
al
w
h
ic
h
i
m
p
r
o
v
es
p
r
ed
icted
ac
cu
r
ac
y
.
Fi
g
u
r
e
5
-
8
s
h
o
w
s
t
h
e
w
i
n
d
s
p
ee
d
,
w
i
n
d
d
en
s
it
y
,
am
b
ien
t
te
m
p
er
atu
r
e
an
d
w
in
d
d
ir
ec
tio
n
d
ec
o
m
p
o
s
itio
n
at
8
lev
el.
T
h
ese
ar
e
f
o
u
n
d
f
r
o
m
w
a
v
elet
to
o
l
b
o
x
in
th
e
Ma
tlab
2
0
1
2
a
v
er
s
io
n
[
1
0
-
1
3
]
.
4.
WAVE
L
E
T
N
E
AURA
L
N
E
T
WO
RK
(
WNN)
A.
M
o
dellin
g
o
f
Wa
v
elet
Neura
l N
et
w
o
rk
I
n
th
i
s
m
o
d
el
in
p
u
ts
ar
e
u
1
,
u
2
….
.
u
n
,
h
id
d
en
la
y
er
n
o
d
es
ar
e
z1
,
z
2
….
.
zn
an
d
w
ei
g
h
ts
(
W
m
)
ar
e
v
1
,
v
2
….
.
v
n
.
T
h
e
w
eig
h
t
s
ar
e
co
n
n
ec
ted
i
n
b
et
w
ee
n
h
id
d
en
la
y
er
an
d
o
u
tp
u
t
f
u
n
ctio
n
o
f
w
a
v
elet.
Dau
b
ec
h
ie
s
w
a
v
elet
allo
w
s
to
p
ick
in
g
u
p
th
e
o
v
er
lap
p
ed
ap
p
r
o
x
i
m
ated
a
n
d
d
etailed
co
e
f
f
icien
t
s
ea
s
ier
t
h
an
o
th
er
w
a
v
elet
f
a
m
ilie
s
f
o
r
d
es
cr
ib
in
g
d
is
cr
ete
w
a
v
elet
tr
a
n
s
f
o
r
m
s
in
f
o
r
ec
asti
n
g
p
r
o
b
le
m
.
Fig
u
r
e
9
.
s
h
o
w
s
t
h
e
w
a
v
elet
n
e
u
r
al
n
et
w
o
r
k
m
o
d
el
[
1
7
]
.
A
f
ee
d
-
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
is
u
s
ed
as
n
o
n
li
n
ea
r
au
to
-
r
eg
r
es
s
iv
e
w
it
h
ex
o
g
e
n
o
u
s
w
i
n
d
s
er
ies
i
n
p
u
ts
an
d
w
i
n
d
p
o
w
er
o
u
tp
u
t
s
(
N
AR
X)
f
o
r
s
i
g
m
o
id
ac
ti
v
atio
n
in
h
id
d
en
la
y
er
.
T
o
tr
ain
th
e
n
et
w
o
r
k
a
b
ac
k
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
i
s
e
m
p
lo
y
ed
i
n
W
NN.
Fig
u
r
e
9
.
W
av
elet
Neu
r
al
Ne
t
w
o
r
k
Hid
d
en
la
y
er
o
u
tp
u
t is g
iv
e
n
b
y
n
i
im
im
i
m
a
b
u
Z
1
)
(
n
j
(
8
)
W
h
er
e
a,
b
ar
e
tr
an
s
latio
n
an
d
d
ilatio
n
p
ar
a
m
eter
s
.
T
h
e
w
av
ele
t n
e
u
r
al
n
et
w
o
r
k
o
u
tp
u
t r
ep
r
esen
tatio
n
i
s
g
i
v
e
n
b
elo
w
g
u
v
Z
W
y
i
n
i
i
m
n
m
m
1
1
(
9
)
T
h
e
W
av
elet
Neu
r
al
Net
w
o
r
k
is
co
n
s
i
s
tin
g
o
f
f
o
u
r
in
p
u
ts
(
i.e
.
w
in
d
s
p
ee
d
,
am
b
ie
n
t
te
m
p
ar
at
u
r
e,
w
i
n
d
d
ir
ec
tio
n
,
w
i
n
d
d
en
s
it
y
)
an
d
o
n
e
o
u
tp
u
t
(
i.e
.
w
i
n
d
p
o
w
er
)
.
to
tr
ain
t
h
e
n
et
w
o
r
k
a
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
i
s
u
s
ed
to
m
i
tig
a
te
co
s
t
f
u
n
c
tio
n
.
T
h
ese
ar
e
d
i
f
f
er
en
tiab
le
w
it
h
r
esp
ec
t
to
tr
an
s
lat
io
n
,
d
ilatio
n
u
n
k
n
o
w
n
v
ar
iab
le
w
ei
g
h
ts
a
n
d
b
ias
o
f
t
h
e
n
et
w
o
r
k
,
w
h
i
ch
ar
e
ta
k
en
f
r
o
m
d
ec
o
m
p
o
s
itio
n
co
ef
f
ic
ien
t
s
o
f
s
ig
n
al
s
(
i.e
.
w
i
n
d
s
p
ee
d
,
am
b
i
en
t te
m
p
ar
at
u
r
e,
w
in
d
d
ir
ec
tio
n
,
w
in
d
d
en
s
it
y
a
n
d
w
i
n
d
p
o
w
er
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i S
y
s
t
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
1
8
:
397
–
4
0
5
402
5.
RE
SU
L
T
S
AND
DI
SCUS
SI
O
N
As alr
ea
d
y
d
is
cu
s
s
ed
ea
ch
f
o
r
ec
asti
n
g
m
o
d
el
h
as b
ee
n
ap
p
li
ed
in
th
e
f
o
llo
w
in
g
t
w
o
ca
s
es
:
a.
A
p
p
licatio
n
o
f
i
n
p
u
t
a
n
d
o
u
tp
u
t
w
av
ele
t
co
ef
f
ic
ien
t
s
ar
e
g
iv
en
in
to
W
A
NFI
S,
W
NN
f
o
r
ec
asted
m
o
d
els
o
n
a
tr
ain
in
g
o
f
2
0
0
0
s
am
p
l
es
an
d
o
n
a
test
in
g
o
f
1
4
3
s
a
m
p
les
w
it
h
th
e
co
m
b
i
n
ed
f
o
r
ec
asted
w
in
d
p
o
w
er
.
b.
A
p
p
licatio
n
o
f
i
n
p
u
t
w
a
v
elet
co
ef
f
icie
n
t
s
ar
e
g
i
v
e
n
in
to
t
w
o
m
o
d
el
s
o
n
a
tr
ai
n
in
g
p
er
io
d
o
f
2
0
0
0
s
a
m
p
les a
n
d
o
n
a
test
i
n
g
p
er
io
d
o
f
1
4
3
s
am
p
les
f
o
r
W
A
NFI
S,
W
NN
f
o
r
ec
asted
m
o
d
els.
T
h
e
ti
m
e
s
er
ie
s
w
i
n
d
d
ata
lik
e
w
i
n
d
s
p
ee
d
,
w
in
d
d
en
s
it
y
,
a
m
b
ien
t
te
m
p
er
at
u
r
e,
w
in
d
d
i
r
ec
tio
n
ar
e
tak
en
as
i
n
p
u
t
s
a
n
d
w
i
n
d
p
o
wer
is
o
u
tp
u
t,
w
h
ich
ar
e
co
llect
ed
f
r
o
m
No
r
th
I
n
d
ia.
I
n
t
h
is
e
v
er
y
1
0
m
i
n
u
tes
d
ata
s
ets
ar
e
tak
e
n
f
o
r
an
al
y
s
i
s
.
Data
s
ets
w
er
e
n
o
r
m
alize
d
i
n
th
e
r
a
n
g
e
[
-
1
,
1
]
to
im
p
r
o
v
es
p
er
f
o
r
m
a
n
ce
o
f
f
o
r
ec
asti
n
g
m
o
d
els.
Af
ter
n
o
r
m
aliza
tio
n
i
n
p
u
t
a
n
d
o
u
tp
u
t
s
i
g
n
al
s
ar
e
d
ec
o
m
p
o
s
ed
w
it
h
D
au
b
ec
h
ie
w
a
v
elet
a
t
a
least
as
y
m
m
etr
y
-
8
(LA
-
8
)
ap
p
lied
to
p
r
o
p
o
s
ed
w
i
n
d
f
o
r
ec
asti
n
g
m
o
d
el
s
[
1
8
]
.
Dau
b
e
ch
ie
w
av
e
let
g
i
v
es
s
m
o
o
th
m
u
lt
i
r
eso
lu
tio
n
s
i
g
n
al
w
it
h
least
p
h
ase
s
h
i
f
ti
n
g
i
n
o
r
d
er
to
g
et
m
o
r
e
ac
c
u
r
ate
f
o
r
ec
asti
n
g
r
esu
lts
.
Her
e,
th
e
d
ec
o
m
p
o
s
ed
s
i
g
n
a
ls
at
lev
el
8
is
tak
e
n
s
o
th
at
s
m
o
o
th
an
d
least
p
h
ase
s
h
i
f
t
s
ig
n
al
ca
n
b
e
p
r
ed
icted
ac
cu
r
atel
y
Fi
g
u
r
e
5
to
8
ill
u
s
tr
ated
D1
to
D8
an
d
A
8
d
et
ailed
an
d
ap
p
r
o
x
i
m
ate
co
ef
f
i
cien
ts
o
f
i
n
p
u
t
a
n
d
o
u
tp
u
t si
g
n
als
Fig
u
r
e
1
0
s
h
o
ws
w
in
d
p
o
w
er
d
ec
o
m
p
o
s
itio
n
[
1
9
-
2
0
]
.
Fig
u
r
e
10
.
W
in
d
Po
w
er
Deco
m
p
o
s
itio
n
I
n
ca
s
e
1
a
n
d
ca
s
e
2
W
A
NFI
S
m
o
d
els
t
h
e
n
u
m
b
er
o
f
n
o
d
es
ar
e
ta
k
en
as
1
9
3
.
T
h
e
n
u
m
b
er
o
f
li
n
ea
r
an
d
n
o
n
li
n
ea
r
p
ar
a
m
eter
s
is
t
ak
en
as
8
1
a
n
d
4
8
.
T
h
e
f
u
zz
y
i
n
f
er
en
ce
m
o
d
el
is
S
u
g
e
n
o
an
d
th
e
n
u
m
b
er
o
f
f
u
zz
y
r
u
les
is
8
1
.
Fo
r
‘
an
d
’
Me
th
o
d
,
‘
o
r
’
Me
t
h
o
d
an
d
d
ef
u
zz
i
f
icatio
n
w
er
e
c
h
o
s
en
a
s
p
r
o
d
,
p
r
o
b
ab
ilis
tic,
w
ta
v
er
(
w
ei
g
h
ted
av
er
ag
e)
cu
s
to
m
o
p
er
atio
n
.
T
o
tr
a
in
th
e
n
et
w
o
r
k
a
b
ac
k
p
r
o
p
ag
atio
n
a
lg
o
r
ith
m
u
s
ed
.
T
h
e
m
i
n
i
m
u
m
test
i
n
g
er
r
o
r
0
.
0
2
5
6
o
cc
u
r
s
i
n
ca
s
e
1
o
f
W
A
N
FIS
in
p
u
t
a
n
d
o
u
tp
u
t
d
ec
o
m
p
o
s
it
i
o
n
w
it
h
co
m
b
in
ed
f
o
r
ec
asted
o
u
tp
u
t
s
,
w
h
ich
is
m
o
r
e
ac
c
u
r
ate
t
h
an
th
e
o
t
h
er
m
et
h
o
d
s
.
T
h
e
Me
an
Sq
u
ar
e
E
r
r
o
r
,
R
o
o
t
Me
an
S
q
u
ar
e
E
r
r
o
r
an
d
No
r
m
alize
d
R
o
o
t
Me
an
Sq
u
ar
e
E
r
r
o
r
s
o
f
ca
s
e
1
W
A
NFI
S
m
o
d
el
ar
e
0
.
0
0
0
6
5
,
0
.
0
0
9
2
8
an
d
0
.
0
0
9
1
9
.
T
h
e
s
ec
o
n
d
ca
s
e
o
f
W
A
NFI
S
m
o
d
el
te
s
ti
n
g
er
r
o
r
is
0
.
0
7
4
2
7
Fig
u
r
e
1
1
.
Sh
o
w
s
t
h
e
ac
t
u
al
w
i
n
d
p
o
w
er
v
s
f
o
r
ec
asted
w
i
n
d
p
o
w
er
t
h
r
o
u
g
h
W
A
NFI
S
w
i
th
i
n
p
u
t
a
n
d
o
u
tp
u
t
d
ec
o
m
p
o
s
itio
n
.
Fig
u
r
e
1
2
.
s
h
o
w
s
th
e
r
ea
l
w
in
d
p
o
w
er
v
s
f
o
r
ec
as
ted
w
i
n
d
p
o
w
er
th
r
o
u
g
h
W
A
N
FIS
in
p
u
t d
ec
o
m
p
o
s
itio
n
s
.
T
h
e
m
i
n
i
m
u
m
test
i
n
g
er
r
o
r
is
0
.
0
3
9
1
in
t
h
e
m
et
h
o
d
o
f
W
a
v
elet
Ne
u
r
al
Net
w
o
r
k
s
w
i
th
a
n
in
p
u
t
a
n
d
o
u
tp
u
t
d
ec
o
m
p
o
s
itio
n
w
it
h
co
m
b
in
ed
f
o
r
ec
asted
o
u
tp
u
t
o
cc
u
r
s
at
f
ir
s
t
h
id
d
en
la
y
er
,
t
w
o
i
n
p
u
t
d
ela
y
s
a
n
d
t
w
o
Fed
b
ac
k
d
el
a
y
s
ar
e
tak
e
n
i
n
to
th
e
n
et
w
o
r
k
.
I
n
C
a
s
e
1
o
f
W
A
N
FIS
a
n
d
W
NN
m
e
th
o
d
ac
cu
r
ac
y
i
s
i
n
cr
ea
s
ed
th
an
t
h
e
ca
s
e
2
W
A
NFI
S
an
d
W
NN
m
eth
o
d
s
.
So
t
h
at
t
h
e
i
n
p
u
t
an
d
o
u
tp
u
t
d
ec
o
m
p
o
s
itio
n
w
i
th
r
ec
o
m
b
in
ed
p
r
ed
icted
o
u
tp
u
ts
ca
s
e
is
p
r
ef
e
r
r
ed
to
g
et
m
o
r
e
ac
cu
r
ate
w
i
n
d
p
o
w
er
f
o
r
ec
asti
n
g
r
es
u
lts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i
S
y
s
t
I
SS
N:
2088
-
8
694
V
ery
-
S
h
o
r
t Term
W
in
d
P
o
w
er F
o
r
ec
a
s
tin
g
th
r
o
u
g
h
…
(
M.
N
a
n
d
a
n
a
Jy
o
th
i
)
403
Fig
u
r
e
11
.
W
A
NFI
S Fo
r
ec
aste
d
W
in
d
P
o
w
er
f
o
r
C
ase
1
Fig
u
r
e
12
.
W
A
NFI
S Fo
r
ec
aste
d
W
in
d
P
o
w
er
f
o
r
C
ase
2
An
d
s
ec
o
n
d
ca
s
e
o
f
W
av
e
let
Neu
r
al
Net
w
o
r
k
te
s
ti
n
g
er
r
o
r
is
0
.
1
4
o
b
tain
ed
at
1
-
8
-
8
an
d
3
-
8
-
8
o
f
h
id
d
en
la
y
er
s
,
i
n
p
u
t
d
ela
y
s
a
n
d
f
ee
d
b
ac
k
d
ela
y
.
Fi
g
u
r
e
13
.
an
d
1
4
s
h
o
w
s
r
ea
l
w
i
n
d
p
o
w
er
v
s
f
o
r
ec
asted
w
i
n
d
p
o
w
er
th
r
o
u
g
h
W
NN
f
o
r
b
o
th
ca
s
e
s
.
Hen
ce
,
t
h
e
p
r
o
p
o
s
ed
W
av
elet
B
ased
A
NFI
S
ca
s
e
1
m
et
h
o
d
g
ets
m
o
r
e
ac
cu
r
ate
v
al
u
es
t
h
an
t
h
e
o
th
er
co
m
p
ar
ed
m
et
h
o
d
s
.
T
h
e
p
er
f
o
r
m
an
ce
a
n
d
r
eg
r
ess
io
n
an
al
y
s
i
s
o
f
w
av
elet
n
e
u
r
al
n
et
w
o
r
k
i
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
5
,
1
6
.
Fig
u
r
e
13
.
W
NN
Fo
r
ec
asted
W
in
d
P
o
w
er
f
o
r
C
ase
1
Fig
u
r
e
14
.
W
NN
Fo
r
ec
asted
W
in
d
P
o
w
er
f
o
r
C
ase
2
6.
E
RRO
R
ANA
L
YS
I
S
T
h
e
p
er
f
o
r
m
a
n
ce
in
d
e
x
p
r
o
v
i
d
es
r
esu
lt
s
an
al
y
s
is
w
h
ic
h
d
ep
en
d
s
o
n
er
r
o
r
ca
lcu
latio
n
s
o
f
ME
,
A
ME
,
MSE
,
R
MSE
,
an
d
N
R
MSE
.
T
h
e
er
r
o
r
s
ca
n
b
e
ca
lcu
lated
b
y
u
s
i
n
g
th
e
g
i
v
en
b
elo
w
f
o
r
m
u
la
s
.
a.
Me
an
E
r
r
o
r
(
ME
)
:
)
(
1
1
j
n
j
j
P
A
n
ME
(
1
0
)
b.
A
b
s
o
l
u
te
Me
a
n
E
r
r
o
r
(
A
ME
)
:
n
j
j
j
j
A
P
A
n
A
ME
1
1
(
1
1
)
0
50
100
150
-
0
.
0
5
0
0
.
0
5
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
N
o
r
m
a
l
i
s
e
d
W
i
n
d
P
o
w
e
r
1
0
m
i
n
o
n
e
d
a
y
t
i
m
e
s
e
r
i
e
s
R
e
a
l
W
A
N
F
S
P
r
e
d
i
c
t
i
o
n
i
n
c
a
s
e
1
0
50
100
150
-
0
.
0
5
0
0
.
0
5
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
1
0
m
i
n
o
n
e
d
a
y
t
i
m
e
s
e
r
i
e
N
o
r
m
a
l
i
s
e
d
w
i
n
d
p
o
w
e
r
R
e
a
l
W
A
N
F
I
S
P
r
e
d
i
c
t
i
o
n
i
n
c
a
s
e
2
0
50
100
150
-
0
.
0
5
0
0
.
0
5
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
1
0
m
i
n
o
n
e
d
a
y
t
i
m
e
s
e
r
i
e
s
N
o
r
m
a
l
i
s
e
d
W
i
n
d
p
o
w
e
r
R
e
a
l
W
N
N
P
r
e
d
i
c
t
i
o
n
i
n
c
a
s
e
1
0
50
100
150
-
0
.
1
-
0
.
0
5
0
0
.
0
5
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
1
0
m
i
n
o
n
e
d
a
y
t
i
m
e
s
e
r
i
e
s
N
o
r
m
a
l
i
s
e
d
W
i
n
d
P
o
w
e
r
R
e
a
l
W
N
N
P
r
e
d
i
c
t
i
o
n
i
n
c
a
s
e
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
694
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i S
y
s
t
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
2
0
1
8
:
397
–
4
0
5
404
c.
Me
an
Sq
u
ar
e
E
r
r
o
r
(
MSE
)
:
n
j
j
j
j
A
P
A
n
M
S
E
1
2
1
(
1
2
)
d.
R
o
o
t M
ea
n
Sq
u
ar
e
E
r
r
o
r
(
R
MSE
)
:
n
j
j
j
j
A
P
A
n
R
M
S
E
1
2
1
(
1
3
)
e.
No
r
m
a
lized
R
o
o
t
Me
an
Sq
u
ar
e
E
rro
r
(NRMSE
):
n
j
j
j
j
A
P
A
n
v
a
l
u
e
v
a
l
u
e
N
R
M
S
E
1
2
1
.
m
i
n
.
m
a
x
1
(
1
4
)
W
h
er
e
N
-
No
.
o
f
s
a
m
p
le
s
,
A
–
A
ct
u
al
Ou
tp
u
t,
P
-
P
r
ed
icted
Ou
tp
u
t
Fig
u
r
e
15
.
P
er
f
o
r
m
an
ce
An
al
y
s
is
o
f
W
NN
Fig
u
r
e
16
.
R
eg
r
ess
io
n
A
n
a
l
y
s
i
s
o
f
W
NN
7.
CO
NCLU
SI
O
N
T
h
e
s
o
lu
tio
n
o
f
in
te
g
r
atio
n
p
r
o
b
lem
f
o
r
th
e
v
er
y
s
h
o
r
t
ter
m
w
i
n
d
p
o
w
er
f
o
r
ec
asti
n
g
h
as
b
ee
n
ca
r
r
ied
o
u
t b
et
w
ee
n
W
av
elet
B
ased
ANFI
S a
n
d
W
a
v
elet
Ne
u
r
al
Net
w
o
r
k
a
t
d
if
f
er
e
n
t c
ase
s
.
T
h
is
c
o
m
p
ar
is
o
n
lo
o
k
s
a
t
a
d
ee
p
er
p
er
f
o
r
m
a
n
ce
an
al
y
s
is
f
o
cu
s
ed
o
n
ME
,
A
ME
,
MSE
,
R
MSE
,
NR
M
SE
at
d
if
f
er
en
t
h
id
d
en
la
y
er
s
,
in
p
u
t
d
elay
s
an
d
f
ee
d
b
ac
k
d
ela
y
s
o
f
n
et
w
o
r
k
s
.
T
h
e
b
est
r
esu
lts
w
er
e
o
b
tain
ed
in
th
e
ca
s
e
1
o
f
W
av
elet
B
ased
A
N
FIS
co
m
p
a
r
ed
to
o
th
er
m
et
h
o
d
s
.
0
2
4
6
8
10
12
14
16
18
10
-3
10
-2
10
-1
10
0
B
e
s
t
V
a
l
i
d
a
t
i
o
n
P
e
r
f
o
r
m
a
n
c
e
i
s
0
.
0
0
4
7
8
4
3
a
t
e
p
o
c
h
1
3
M
e
a
n
S
q
u
a
r
e
d
E
r
r
o
r
(
m
s
e
)
1
9
E
p
o
c
h
s
T
r
a
i
n
V
a
l
i
d
a
t
i
o
n
T
e
s
t
B
e
s
t
0
0
.
2
0
.
4
0
.
6
0
.
8
0
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
T
a
r
g
e
t
O
u
t
p
u
t
~
=
0
.
9
1
*
T
a
r
g
e
t
+
0
.
0
1
7
T
r
a
i
n
i
n
g
:
R
=
0
.
9
5
8
4
9
D
a
t
a
F
i
t
Y
=
T
0
0
.
2
0
.
4
0
.
6
0
.
8
0
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
T
a
r
g
e
t
O
u
t
p
u
t
~
=
0
.
8
6
*
T
a
r
g
e
t
+
0
.
0
2
3
V
a
l
i
d
a
t
i
o
n
:
R
=
0
.
9
0
6
5
3
D
a
t
a
F
i
t
Y
=
T
0
0
.
2
0
.
4
0
.
6
0
.
8
0
0
.
2
0
.
4
0
.
6
0
.
8
T
a
r
g
e
t
O
u
t
p
u
t
~
=
0
.
9
*
T
a
r
g
e
t
+
0
.
0
0
2
3
T
e
s
t
:
R
=
0
.
9
4
8
3
4
D
a
t
a
F
i
t
Y
=
T
0
0
.
2
0
.
4
0
.
6
0
.
8
0
0
.
2
0
.
4
0
.
6
0
.
8
T
a
r
g
e
t
O
u
t
p
u
t
~
=
0
.
9
1
*
T
a
r
g
e
t
+
0
.
0
1
4
A
l
l
:
R
=
0
.
9
5
4
1
8
D
a
t
a
F
i
t
Y
=
T
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
P
o
w
er
E
lectr
o
n
&
Dr
i
S
y
s
t
I
SS
N:
2088
-
8
694
V
ery
-
S
h
o
r
t Term
W
in
d
P
o
w
er F
o
r
ec
a
s
tin
g
th
r
o
u
g
h
…
(
M.
N
a
n
d
a
n
a
Jy
o
th
i
)
405
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
w
o
r
k
w
as
s
u
p
p
o
r
ted
b
y
t
h
e
Go
v
t.
o
f
I
n
d
ia,
M
in
i
s
tr
y
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
Dep
ar
t
m
en
t
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
u
n
d
er
W
o
m
e
n
Scien
tis
t
Sc
h
e
m
e
(
W
OS
-
A
)
o
r
d
er
n
u
m
b
er
SR
/W
OS
-
A/E
T
-
1
3
9
/2
0
1
6
.
T
h
e
au
t
h
o
r
s
w
o
u
ld
li
k
e
to
t
h
a
n
k
N.
M.
S
w
a
m
y
f
o
r
h
e
lp
in
g
r
ea
l
ti
m
e
S
C
A
D
A
o
f
w
i
n
d
p
o
w
er
g
e
n
er
atio
n
d
ata
at
No
r
th
I
n
d
ia.
RE
F
E
R
E
NC
E
S
[1
]
S
o
m
a
n
,
S
.
S
,
Zare
i
p
o
u
r,
H;
M
a
l
ik
.
O,;
M
a
n
d
a
l
.
P
,
A
re
v
ie
w
o
f
w
in
d
p
o
w
e
r
a
n
d
w
in
d
sp
e
e
d
f
o
re
c
a
stin
g
m
e
th
o
d
s w
it
h
d
if
fe
re
n
t
ti
m
e
h
o
rizo
n
s,
N
o
rth
Ame
ric
a
n
Po
we
r
S
y
mp
o
si
u
m (
NAP
S
)
,
2
0
1
0
,
1
-
8
.
[2
]
Y
-
K W
u
,
a
n
d
J
-
S
Ho
n
g
,
“
A
li
tera
tu
re
re
v
ie
w
o
f
w
in
d
f
o
re
c
a
stin
g
te
c
h
n
o
l
o
g
y
in
th
e
w
o
rld
,
”
IEE
E
P
o
we
r T
e
c
h
2
0
0
7
,
504
-
5
0
9
.
[3
]
M
.
L
e
i,
L
.
S
h
i
y
a
n
,
J.
Ch
u
a
n
w
e
n
,
L
iu
Ho
n
g
li
n
g
a
n
d
Z.
Ya
n
,
”
A
re
v
ie
w
o
n
th
e
f
o
re
c
a
stin
g
o
f
w
in
d
sp
e
e
d
a
n
d
g
e
n
e
ra
ted
p
o
w
e
r,
“
Ren
e
wa
b
le a
n
d
S
u
sta
i
n
a
b
le E
n
e
rg
y
Rev
iews
,
1
3
,
2
0
0
9
,
9
1
5
-
9
2
0
.
[4
]
A
.
Co
sta
,
A
.
Cre
sp
o
,
J.
Na
v
a
rro
,
G
.
L
izc
a
n
o
,
H.
M
a
d
se
n
,
E
.
F
e
it
o
sa
,
A
re
v
i
e
w
o
n
th
e
y
o
u
n
g
h
ist
o
ry
o
f
th
e
w
in
d
p
o
w
e
r
sh
o
rt
-
term
p
re
d
ictio
n
,
Ren
e
w.
S
u
st
a
in
.
En
e
rg
y
Re
v
.
1
2
(
6
),
2
0
0
8
,
1
7
2
5
–
1
7
4
4
.
[5
]
M
.
L
e
i,
L
.
S
h
iy
a
n
,
J.
Ch
u
a
n
w
e
n
,
L
.
Ho
n
g
li
n
g
,
Z.
Ya
n
,
A
re
v
iew
o
n
th
e
f
o
re
c
a
stin
g
o
f
w
in
d
sp
e
e
d
a
n
d
g
e
n
e
ra
ted
p
o
w
e
r,
Ren
e
w.
S
u
sta
i
n
.
E
n
e
rg
y
R
e
v
.
1
3
(4
)
,
2
0
0
9
,
9
1
5
–
9
2
0
.
[6
]
J.P
.
S
.
Ca
tala
o
,
H.M
.
I.
P
o
u
sin
h
o
,
V
.
M
.
F
.
M
e
n
d
e
s,
S
h
o
rt
-
term
w
in
d
p
o
w
e
r
f
o
re
c
a
stin
g
in
P
o
rt
u
g
a
l
b
y
n
e
u
ra
l
n
e
t
w
o
rk
s a
n
d
w
a
v
e
let
tran
s
f
o
rm
,
Ren
e
w.
En
e
rg
y
3
6
,
2
0
1
1
,
1
2
4
5
–
1
2
5
1
.
[7
]
R.
Blo
n
b
o
u
,
V
e
ry
sh
o
rt
-
term
w
in
d
p
o
w
e
r
f
o
re
c
a
stin
g
w
it
h
n
e
u
ra
l
n
e
tw
o
rk
s
a
n
d
a
d
a
p
ti
v
e
Ba
y
e
sia
n
le
a
rn
in
g
,
Ren
e
w
.
En
e
rg
y
3
6
,
2
0
1
1
,
1
1
8
–
1
1
2
4
.
[8
]
G
.
L
i,
J.
S
h
i,
J.Y.
Z
h
o
u
,
Ba
y
e
si
a
n
a
d
a
p
ti
v
e
c
o
m
b
in
a
ti
o
n
o
f
sh
o
rt
-
term
w
in
d
sp
e
e
d
f
o
re
c
a
sts
f
ro
m
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
ls,
Ren
e
w.
En
e
rg
y
3
6
,
2
0
1
1
,
3
5
2
–
3
5
9
.
[9
]
Ch
i
-
Hu
a
n
g
L
u
,
2
0
1
1
W
a
v
e
let
F
u
z
z
y
Ne
u
ra
l
Ne
tw
o
rk
s
f
o
r
Id
e
n
ti
f
ica
ti
o
n
a
n
d
P
re
d
ictiv
e
Co
n
tr
o
l
o
f
D
y
n
a
m
ic
S
y
st
e
m
s,
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
i
n
d
u
stri
a
l
e
lec
tro
n
ics
,
5
8
,
2
0
1
1
,
3
0
4
6
-
3
0
5
9
.
[1
0
]
N.M
.
P
in
d
o
riy
a
,
S
.
N.
S
in
g
h
,
a
n
d
S
.
K.
S
in
g
h
,
“
A
n
a
d
a
p
ti
v
e
w
a
v
e
l
e
t
n
e
u
ra
l
n
e
tw
o
rk
-
b
a
se
d
e
n
e
r
g
y
p
rice
f
o
re
c
a
stin
g
in
e
lec
tri
c
it
y
m
a
r
k
e
ts,”
IEE
E
T
ra
n
s.
Po
we
r
S
y
st.
,
2
3
,
2
0
0
8
,
1
4
2
3
-
1
4
3
2
.
[1
1
]
Bh
a
sk
a
r.
K.,
S
in
g
h
.
S
.
N.
,
“
AW
NN
-
A
s
siste
d
W
in
d
P
o
w
e
r
F
o
r
e
c
a
stin
g
Us
in
g
F
e
e
d
-
F
o
rw
a
rd
Ne
u
ra
l
Ne
tw
o
rk
”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
u
sta
i
n
a
b
l
e
En
e
rg
y
,
3
,
2
0
1
2
,
3
0
6
-
3
1
5
.
[1
2
]
J.
Zh
a
n
g
,
G
.
G
.
W
a
lt
e
r,
Y.
M
iao
,
a
n
d
W
.
N.
W
.
L
e
e
,
“
Wav
e
l
e
t
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
f
u
n
c
ti
o
n
lea
rn
in
g
,
”
IEE
E
T
ra
n
s
.
S
ig
n
a
l
Pro
c
e
ss
.
,
4
3
,
1
9
9
5
,
1
4
8
5
-
1
4
9
7
.
[1
3
]
M
a
d
a
su
Ha
n
m
a
n
d
lu
,
Bh
a
v
e
sh
Ku
m
a
r
Ch
a
u
h
a
n
,
L
o
a
d
f
o
re
c
a
stin
g
u
sin
g
h
y
b
rid
m
o
d
e
ls,
IEE
E
T
ra
n
sa
c
ti
o
n
o
f
p
o
we
r
sy
ste
m
,
2
6
,
2
0
1
1
,
2
0
-
2
9
.
[1
4
]
R.
H.
A
b
i
y
e
v
a
n
d
O.
Ka
y
n
a
k
,
“
F
u
z
z
y
w
a
v
e
let
n
e
u
ra
l
n
e
t
w
o
rk
s
f
o
r
id
e
n
ti
f
ica
ti
o
n
a
n
d
c
o
n
tr
o
l
o
f
d
y
n
a
m
ic
p
lan
ts
—
A
n
o
v
e
l
stru
c
tu
re
a
n
d
a
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
”
IEE
E
T
ra
n
s.
I
n
d
.
El
e
c
tro
n
.
,
v
o
l
.
5
5
,
2
0
0
8
,
3
1
3
3
–
3
1
4
0
.
[1
5
]
Ed
u
a
rd
o
M
a
rt
in
M
o
ra
u
d
,
“
W
a
v
e
l
e
t
Ne
tw
o
rk
s”
A
re
p
o
rt,
2
0
0
9
.
[1
6
]
I.
Da
u
b
e
c
h
ies
,
“
T
h
e
w
a
v
e
let
tran
sf
o
r
m
,
ti
m
e
-
f
re
q
u
e
n
c
y
lo
c
a
li
z
a
ti
o
n
a
n
d
sig
n
a
l
a
n
a
ly
sis,”
IEE
E
T
ra
n
s.
In
f.
T
h
e
o
ry
,
3
6
,
1
9
9
0
,
9
6
1
-
1
0
0
5
.
[1
7
]
S
.
G
.
M
a
ll
a
t,
“
A
th
e
o
r
y
f
o
r
m
u
lt
ires
o
l
u
ti
o
n
sig
n
a
l
d
e
c
o
m
p
o
siti
o
n
:
T
h
e
w
a
v
e
let
re
p
re
s
e
n
tatio
n
,
”
IEE
E
T
ra
n
s
.
Pa
tt
e
rn
A
n
a
l.
M
a
c
h
.
In
tell
.
,
1
1
,
1
9
8
9
,
6
7
4
-
6
9
3
.
[1
8
]
D.
P
a
rc
iv
a
l
a
n
d
A
.
W
a
ld
e
n
,
W
a
v
e
let
M
e
th
o
d
s
f
o
r
T
i
m
e
S
e
ries
A
n
a
l
y
sis.
Ca
m
b
rid
g
e
,
U.K.:
Ca
m
b
ri
d
g
e
Un
iv
.
P
re
ss
,
2
0
0
0
.
[1
9
]
M
.
Na
n
d
a
n
a
Jy
o
th
i,
Dr.
P
.
V.
Ra
m
a
n
a
Ra
.
V
e
r
y
-
sh
o
rt
ter
m
w
in
d
p
o
w
e
r
f
o
re
c
a
stin
g
th
ro
u
g
h
a
d
a
p
ti
v
e
w
a
v
e
let
n
e
u
ra
l
n
e
tw
o
rk
.
Bien
n
ial
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
P
o
w
e
r
a
n
d
En
e
rg
y
t
o
w
a
rd
s S
u
sta
in
a
b
le E
n
e
rg
y
(P
ES
T
S
E)
2
0
1
6
,
2
n
d
IEE
E
Co
n
f
e
re
n
c
e
2
0
1
6
.
[2
0
]
M
.
Na
n
d
a
n
a
Jy
o
th
i,
V
.
Di
n
a
k
a
r,
N.S
.
S
Ra
v
i
T
e
ja,
Na
rx
b
a
s
e
d
w
in
d
p
o
w
e
r
f
o
re
c
a
stin
g
m
o
d
e
l,
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ju
ly
2
0
1
5
,
p
p
.
2
0
~
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.