I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
,
p
p
.
3
9
5
7
~
3
9
6
6
I
SS
N
: 2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
4
.
pp
3
9
5
7
-
3
9
6
6
3957
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
The qua
lity o
f
dat
a
and the
a
cc
ura
c
y
of energy
gener
a
tion
foreca
st by a
rti
fic
ia
l neural ne
tw
o
r
k
s
B
o
g
da
n K
w
ia
t
k
o
w
s
k
i
1
,
J
a
ce
k
B
a
rt
m
a
n
2
,
Da
m
ia
n M
a
zur
3
1
,2
Co
ll
e
g
e
o
f
Na
tu
ra
l
S
c
ien
c
e
s,
Un
iv
e
rsity
o
f
Rz
e
s
z
o
w
,
P
o
lan
d
3
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Rz
e
sz
o
w
Un
iv
e
r
sity
o
f
T
e
c
h
n
o
lo
g
y
,
P
o
lan
d
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
3
,
2
0
1
9
R
ev
i
s
ed
Ma
r
6
,
2
0
2
0
A
cc
ep
ted
Ma
r
1
5
,
2
0
2
0
T
h
e
p
a
p
e
r
p
re
se
n
ts
th
e
issu
e
s
re
late
d
to
p
re
d
ictin
g
t
h
e
a
m
o
u
n
t
o
f
e
n
e
rg
y
g
e
n
e
ra
ti
o
n
,
in
a
p
a
rti
c
u
lar
w
in
d
p
o
w
e
r
p
lan
t
c
o
m
p
risin
g
f
iv
e
g
e
n
e
ra
to
rs
lo
c
a
ted
in
s
o
u
t
h
-
e
a
ste
rn
P
o
la
n
d
.
T
h
e
lo
c
a
ti
o
n
o
f
w
in
d
p
o
w
e
r
p
lan
t,
th
e
d
istri
b
u
ti
o
n
a
n
d
ty
p
e
o
f
a
p
p
li
e
d
g
e
n
e
ra
to
rs,
a
n
d
to
p
o
g
ra
p
h
ica
l
c
o
n
d
i
ti
o
n
s
w
e
r
e
g
iv
e
n
a
n
d
th
e
c
o
rre
latio
n
b
e
tw
e
e
n
se
lec
ted
w
e
a
th
e
r
p
a
ra
m
e
ters
a
n
d
th
e
v
o
lu
m
e
o
f
e
n
e
rg
y
g
e
n
e
ra
ti
o
n
w
a
s
d
isc
u
ss
e
d
.
T
h
e
p
rim
a
r
y
o
b
jec
ti
v
e
o
f
th
e
p
a
p
e
r
wa
s
to
s
e
lec
t
le
a
rn
in
g
d
a
ta
a
n
d
p
e
rf
o
r
m
f
o
re
c
a
sts
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s.
F
o
r
c
o
m
p
a
riso
n
,
c
o
n
se
rv
a
ti
v
e
f
o
re
c
a
sts
we
re
a
lso
p
re
se
n
ted
.
F
o
re
c
a
sts
re
su
lt
s
o
b
tain
e
d
sh
a
w
th
a
t
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
s
a
re
m
o
re
u
n
iv
e
rsa
l
th
a
n
c
o
n
se
rv
a
ti
v
e
m
e
t
h
o
d
.
Ho
w
e
v
e
r
th
e
ir
f
o
re
c
a
st
a
c
c
u
ra
c
y
o
f
f
o
re
c
a
sts
stro
n
g
ly
d
e
p
e
n
d
s o
n
th
e
se
lec
ti
o
n
o
f
e
x
p
lan
a
to
ry
d
a
ta.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
Fo
r
ec
asti
n
g
P
r
ed
ictio
n
W
in
d
en
er
g
y
g
e
n
er
atio
n
W
in
d
f
ar
m
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
ac
ek
B
ar
tm
a
n
,
C
o
lleg
e
o
f
Na
tu
r
al
Sc
ien
ce
s
,
Un
i
v
er
s
it
y
o
f
R
ze
s
zo
w
,
A
lej
a
T
ad
eu
s
za
R
ej
tan
a
1
6
C
,
3
5
-
3
1
0
R
ze
s
zó
w
,
P
o
lan
d
.
E
m
ail: j
b
ar
t
m
an
@
u
r
.
ed
u
.
p
l
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ical
en
er
g
y
is
o
n
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
s
o
u
r
c
es
o
f
u
s
ab
le
e
n
er
g
y
.
I
ts
g
e
n
er
atio
n
w
as
m
ai
n
l
y
b
ased
o
n
n
at
u
r
al
r
eso
u
r
ce
s
,
s
u
ch
as
ca
r
b
o
n
,
o
il,
g
as,
o
r
r
a
d
io
ac
tiv
e
ele
m
en
t
s
.
Di
m
i
n
is
h
i
n
g
r
eso
u
r
ce
s
o
f
o
il
o
r
g
as,
ar
d
u
o
u
s
e
f
f
ec
ts
f
o
r
th
e
n
at
u
r
al
e
n
v
ir
o
n
m
e
n
t
ca
u
s
ed
b
y
f
o
s
s
il
-
f
u
el
p
o
w
er
s
tatio
n
s
a
n
d
w
a
s
te
f
r
o
m
ato
m
ic
p
o
w
er
s
ta
tio
n
s
led
to
a
g
r
ea
ter
in
ter
est
i
n
r
en
e
w
ab
le
en
er
g
y
s
o
u
r
ce
s
.
R
ec
en
t
y
ea
r
s
h
av
e
s
ee
n
v
er
y
d
y
n
a
m
ic
g
r
o
w
t
h
o
f
b
o
t
h
w
in
d
p
o
w
er
s
tatio
n
a
n
d
s
o
lar
p
o
w
e
r
s
tatio
n
.
T
h
e
g
e
n
er
atio
n
o
f
e
n
er
g
y
i
n
b
o
th
ca
s
e
s
is
h
i
g
h
l
y
c
h
a
n
g
ea
b
le
[
1
-
3
]
,
as
it
d
ir
ec
tl
y
d
ep
en
d
s
o
n
at
m
o
s
p
h
er
ic
co
n
d
itio
n
s
.
T
h
e
s
tab
ilit
y
o
f
e
n
er
g
y
s
y
s
te
m
r
eq
u
ir
es
th
e
b
alan
ce
b
et
w
ee
n
s
u
p
p
l
y
an
d
d
e
m
a
n
d
o
f
elec
tr
ical
en
er
g
y
,
w
h
ic
h
in
tu
r
n
i
n
v
o
l
v
es
est
i
m
a
tin
g
th
e
a
m
o
u
n
t
o
f
e
n
er
g
y
t
h
at
is
t
o
b
e
p
r
o
d
u
ce
d
b
y
r
en
e
w
ab
les
at
a
g
i
v
en
m
o
m
en
t,
t
h
er
ef
o
r
e,
th
e
en
er
g
y
f
o
r
ec
ast
f
r
o
m
b
o
th
s
o
u
r
ce
s
i
s
n
ec
e
s
s
a
r
y
.
H
ig
h
ac
cu
r
ac
y
o
f
w
i
n
d
e
n
er
g
y
f
o
r
ec
ast
s
i
n
cr
ea
s
es
ec
o
n
o
m
ic
b
e
n
ef
i
ts
b
y
r
ed
u
cin
g
en
er
g
y
g
en
er
atio
n
co
s
ts
a
n
d
i
m
p
r
o
v
es t
h
e
s
ec
u
r
it
y
o
f
en
er
g
y
s
y
s
te
m
.
T
h
e
i
s
s
u
e
o
f
p
r
e
d
i
c
t
i
n
g
t
h
e
e
n
e
r
g
y
g
e
n
e
r
a
t
i
o
n
b
y
w
i
n
d
t
u
r
b
i
n
e
s
i
s
b
r
o
a
d
l
y
d
i
s
c
u
s
s
e
d
i
n
t
h
e
l
i
t
e
r
a
t
u
r
e
.
T
h
e
a
u
t
h
o
r
s
a
p
p
l
y
v
a
r
i
o
u
s
f
o
r
e
c
a
s
t
i
n
g
m
e
t
h
o
d
s
,
s
t
a
r
t
i
n
g
f
r
o
m
t
h
e
c
o
n
s
e
r
v
a
t
i
v
e
m
e
t
h
o
d
[
4
,
5
]
,
t
h
r
o
u
g
h
s
t
a
t
i
s
t
i
c
a
l
m
e
t
h
o
d
s
[
5
,
6
]
,
e
c
o
n
o
m
e
t
r
i
c
m
e
t
h
o
d
s
[
4
]
,
p
h
y
s
i
c
a
l
m
o
d
e
l
s
,
p
s
e
u
d
o
-
i
n
t
e
l
l
i
g
e
n
t
m
e
t
h
o
d
s
,
(
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
f
u
z
z
y
l
o
g
i
c
)
[
4
,
7
-
9
]
,
an
d
en
d
in
g
o
n
h
y
b
r
id
m
et
h
o
d
s
[
1
0
-
1
3
]
.
T
h
e
P
r
esen
ted
f
o
r
ec
asts
co
n
ce
r
n
th
e
en
er
g
y
p
r
o
d
u
ce
d
b
y
in
d
i
v
id
u
al
t
u
r
b
in
es
[
4
,
5
,
1
0
]
as
w
ell
as
b
y
w
h
o
le
w
i
n
d
b
u
r
d
e
n
ed
w
i
t
h
s
m
aller
er
r
o
r
m
w
h
e
n
co
m
p
ar
ed
to
th
e
o
n
g
-
ter
m
f
o
r
ec
asts
w
h
ic
h
r
esu
lts
i
n
h
ig
h
er
in
ter
est
o
f
t
h
e
m
.
T
h
e
cu
r
r
en
t
p
ap
er
,
f
o
r
f
o
r
ec
asti
n
g
p
u
r
p
o
s
es
u
s
e
s
f
ee
d
f
o
r
w
ar
d
m
u
ltil
a
y
er
n
et
w
o
r
k
s
co
m
p
ar
in
g
it
s
ac
cu
r
ac
y
w
i
th
th
e
co
n
s
er
v
at
iv
e
(
n
aïv
e)
m
o
d
el.
T
h
e
p
r
esen
ted
i
n
th
e
p
ap
er
h
av
e
a
s
h
o
r
t te
r
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
3
9
5
7
-
3966
3958
2.
DE
SCR
I
P
T
I
O
N
O
F
O
B
J
E
CT
T
h
e
s
tu
d
ies
co
n
ce
r
n
a
w
i
n
d
p
o
w
er
p
lan
t
lo
ca
ted
in
th
e
s
o
u
th
-
ea
s
t
P
o
lan
d
o
n
h
ill
y
lan
d
.
I
ts
to
p
o
g
r
ap
h
y
cr
ea
tes
v
er
y
g
o
o
d
w
i
n
d
co
n
d
itio
n
s
.
I
n
th
e
ea
s
t
-
w
e
s
t
d
ir
ec
tio
n
F
i
g
u
r
e
1
an
d
to
th
e
n
o
r
th
F
ig
u
r
e
2
,
w
it
h
i
n
a
r
ad
iu
s
o
f
1
0
k
m
t
h
er
e
ar
e
n
o
elev
atio
n
s
t
h
at
w
o
u
ld
ex
ce
ed
th
e
ter
r
ain
w
h
er
e
th
e
w
i
n
d
f
ar
m
is
lo
ca
ted
.
Ho
w
e
v
er
,
th
e
o
n
l
y
ele
v
ated
ar
ea
is
lo
ca
ted
in
t
h
e
s
o
u
th
d
ir
ec
tio
n
w
it
h
in
a
r
ad
iu
s
o
f
ar
o
u
n
d
9
.
5
k
m
w
it
h
th
e
h
ills
h
i
g
h
er
o
f
ab
o
u
t
1
5
0
m
F
i
g
u
r
e
2
.
Me
d
iu
m
w
i
n
d
s
p
ee
d
m
ea
s
u
r
ed
i
n
th
e
p
lace
w
h
er
e
th
e
tu
r
b
in
e
s
ar
e
lo
ca
ted
is
7
m
/
s
,
th
at
i
s
w
h
y
t
h
is
ter
r
ain
is
t
h
e
m
o
s
t s
u
itab
le
p
lace
lo
ca
et
to
a
w
in
d
f
ar
m
[
1
4
,
1
5
]
.
T
h
e
p
o
w
er
p
la
n
t
co
m
p
r
i
s
es
5
tu
r
b
in
e
s
t
h
at
ar
e
i
n
s
talled
o
n
1
0
0
-
m
etr
e
m
ast
s
w
h
ic
h
ar
e
l
o
ca
te
d
as
s
h
o
w
n
in
t
h
e
s
c
h
e
m
e
in
Fi
g
u
r
e
3
.
T
h
e
m
as
t
b
ases
ar
e
s
it
u
ated
at
th
e
lev
el
b
et
w
ee
n
3
7
2
an
d
4
0
9
m
.
a.
s
.
l.
w
it
h
t
h
e
d
is
ta
n
ce
f
r
o
m
2
9
0
to
6
5
0
m
b
et
w
ee
n
o
n
e
a
n
o
th
er
F
i
g
u
r
e
3
.
Mo
u
n
ted
w
i
n
d
tu
r
b
in
e
s
R
E
p
o
w
er
MM
9
2
w
it
h
r
ated
p
o
w
er
o
f
2
.
0
5
MW
an
d
r
ated
v
o
l
tag
e
o
f
6
9
0
V
f
o
r
th
e
f
r
eq
u
e
n
c
y
eq
u
al
to
5
0
Hz.
T
o
s
et
th
e
w
h
ee
l
o
f
9
2
.
5
d
iam
eter
in
m
o
tio
n
,
t
h
e
w
i
n
d
n
ee
d
s
to
b
lo
w
at
ab
o
u
t
3
m
/s
.
T
h
e
r
u
n
n
i
n
g
o
f
t
h
e
tu
r
b
in
e
s
to
p
s
w
h
e
n
th
e
w
i
n
d
b
lo
w
s
at
2
4
m
/s
an
d
is
r
ea
ctiv
ated
at
2
2
m
/s
.
I
n
F
ig
u
r
e
4
th
e
t
u
r
b
in
e
o
p
er
ates
at
lo
w
an
d
m
ed
i
u
m
w
i
n
d
s
p
ee
d
.
Fig
u
r
e.
1
.
Far
m
lo
ca
tio
n
in
t
h
e
s
o
u
th
-
n
o
r
th
d
ir
ec
tio
n
Fig
u
r
e
2
.
Far
m
lo
ca
tio
n
i
n
th
e
w
e
s
t
-
ea
s
t d
ir
ec
tio
n
Fig
u
r
e.
3
.
Dis
tr
ib
u
tio
n
o
f
w
i
n
d
tu
r
b
in
es
in
th
e
ar
ea
Fig
u
r
e
4
.
T
h
e
ch
ar
ac
ter
is
tics
o
f
w
i
n
d
tu
r
b
in
e
R
E
p
o
w
er
MM
9
2
3.
F
O
RE
CAS
T
I
N
G
M
E
T
H
O
D
S
T
h
e
p
ap
er
p
r
esen
ts
s
h
o
r
t
-
ter
m
f
o
r
ec
asti
n
g
r
es
u
lts
co
n
d
u
cted
w
it
h
th
e
co
n
s
er
v
ati
v
e
m
et
h
o
d
an
d
u
s
i
n
g
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
s
.
I
n
o
r
d
er
to
f
o
r
ec
ast
w
it
h
t
h
i
s
m
et
h
o
d
,
it
i
s
s
u
f
f
icie
n
t
to
k
n
o
w
t
h
e
h
i
s
to
r
ical
a
m
o
u
n
t
o
f
en
e
r
g
y
g
e
n
er
atio
n
.
T
h
e
n
at
u
r
e
o
f
n
eu
r
al
n
et
w
o
r
k
s
allo
w
s
to
s
elec
t
in
p
u
t
d
ata
(
ex
p
la
n
ati
o
n
s
)
f
o
r
p
r
ed
ictio
n
s
f
r
o
m
a
n
y
ar
ea
.
Ho
w
e
v
er
,
to
o
b
tain
a
s
ati
s
f
ac
to
r
y
e
f
f
ec
t,
t
h
e
f
o
r
ec
ast
a
m
o
u
n
t
(
en
er
g
y
g
e
n
er
atio
n
)
m
u
s
t
d
ep
en
d
o
n
th
e
ex
p
la
n
ato
r
y
v
al
u
es,
th
u
s
th
e
s
elec
t
io
n
o
f
p
r
o
p
er
d
ata
i
s
cr
u
cial.
3
.
1
.
Co
ns
er
v
a
t
iv
e
(
na
iv
e)
m
et
ho
d
T
h
e
co
n
s
er
v
ati
v
e
m
o
d
el
i
s
t
h
e
s
i
m
p
le
s
t
w
a
y
o
f
p
r
ed
ictin
g
w
i
n
d
g
e
n
er
atio
n
.
I
t
d
e
m
an
d
s
t
o
g
en
er
ate
th
e
p
o
w
er
o
f
w
i
n
d
g
e
n
er
atio
n
in
th
e
m
o
m
en
t i
(
o
f
f
o
r
ec
ast
g
en
er
atio
n
)
[
1
6
]
:
+
=
(
1
)
w
h
er
e:
+
:
f
o
r
ec
ast p
o
w
er
:
v
alu
e
o
f
p
o
w
er
in
t
h
e
m
o
m
e
n
t o
f
f
o
r
ec
asti
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Th
e
q
u
a
lity o
f
d
a
ta
a
n
d
t
h
e
a
c
cu
r
a
cy
o
f e
n
erg
y
g
en
era
tio
n
f
o
r
ec
a
s
t b
y
a
r
tifi
cia
l
…
(
B
o
g
d
a
n
K
w
ia
tko
w
s
ki
)
3959
Su
c
h
co
r
r
elatio
n
,
d
esp
ite
its
s
i
m
p
licit
y
,
w
o
r
k
s
v
er
y
w
el
l
w
h
en
p
r
ep
ar
in
g
f
o
r
ec
asts
p
r
ep
ar
ed
in
u
ltra
-
s
h
o
r
t
(
h
o
u
r
l
y
)
ter
m
.
I
t
i
s
ca
u
s
ed
b
y
a
r
elati
v
el
y
co
n
s
er
v
ativ
e
w
i
n
d
.
I
n
ad
d
itio
n
,
t
h
e
w
i
n
d
f
ar
m
w
h
ic
h
co
m
p
r
is
e
s
a
s
u
b
s
tan
tial
n
u
m
b
er
o
f
w
in
d
s
tatio
n
s
o
cc
u
p
ie
s
a
s
u
b
s
ta
n
tial
ar
ea
,
w
h
ic
h
i
s
th
e
r
ea
s
o
n
w
h
y
in
d
iv
id
u
al
u
n
it
s
d
o
n
o
t
r
ea
ct
at
th
e
s
a
m
e
ti
m
e
to
th
e
ch
an
g
e
o
f
w
i
n
d
s
p
ee
d
.
T
h
e
f
o
r
ec
asts
ar
e
u
s
u
al
l
y
co
n
d
u
cted
f
o
r
=
1
an
d
th
e
m
et
h
o
d
h
as t
h
e
f
o
r
m
o
f
n
aï
v
e
m
eth
o
d
.
3
.
2
.
Neura
l net
w
o
rk
s
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
s
(
ANN)
,
b
o
th
in
t
h
e
s
tr
u
c
tu
r
e
a
n
d
o
p
er
atio
n
,
f
o
llo
w
t
h
e
n
er
v
o
u
s
s
y
s
te
m
o
f
liv
i
n
g
cr
ea
t
u
r
e
s
.
I
n
o
r
d
er
to
u
s
e
th
e
m
f
o
r
f
o
r
ec
asts
,
it
is
n
ec
e
s
s
ar
y
to
co
n
d
u
ct
t
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
o
f
ar
tif
icial
n
eu
r
al
n
e
t
w
o
r
k
s
,
th
a
t
ca
n
b
e
co
n
tr
o
lled
o
r
u
n
co
n
tr
o
lled
.
T
h
e
f
o
r
ec
asts
i
n
th
e
p
ap
er
u
s
ed
f
ee
d
f
o
r
w
ar
d
n
e
u
r
al
n
et
w
o
r
k
s
tr
ain
ed
w
it
h
th
e
co
n
t
r
o
lled
m
et
h
o
d
s
.
T
h
en
,
th
e
tr
ai
n
in
g
s
e
t c
an
b
e
d
escr
ib
ed
w
it
h
d
ep
en
d
en
ce
:
=
{
(
=
(
)
,
=
(
)
)
}
=
1
(
2
)
w
h
er
e:
U
:
tr
ain
i
n
g
s
e
t,
N
:
n
u
m
b
er
o
f
o
b
j
ec
ts
in
tr
ain
i
n
g
s
et,
:
i
-
t
h
o
b
j
ec
t o
f
th
e
tr
ain
in
g
s
e
t (
d
escr
ip
tio
n
o
f
th
e
o
b
j
ec
t)
,
:
f
ea
t
u
r
es’
v
ec
to
r
o
f
i
-
th
o
b
j
ec
t (
in
p
u
t v
ec
to
r
f
o
r
A
NN)
,
:
v
ec
to
r
o
f
ANN
’
s
a
n
s
w
er
s
,
:
f
u
n
ctio
n
o
f
q
u
ali
f
icat
io
n
s
.
I
n
ca
s
e
o
f
co
n
tr
o
lled
tr
ai
n
in
g
m
et
h
o
d
s
,
th
e
p
u
r
p
o
s
e
o
f
a
lear
n
er
is
to
f
i
n
d
w
ei
g
h
ts
’
m
atr
i
x
th
at
allo
w
th
e
co
n
v
er
s
io
n
o
f
in
p
u
t
s
i
g
n
al
s
w
h
ic
h
d
escr
ib
e
th
e
o
b
j
ec
t
(
)
,
f
o
r
ex
p
ec
ted
an
s
w
er
s
(
)
.
T
h
u
s
,
ac
co
r
d
in
g
to
th
e
f
o
r
m
u
la
(
2
)
th
e
tr
ain
i
n
g
s
et
U
co
m
p
r
is
e
s
N
o
f
r
ep
r
esen
tin
g
p
air
s
:
n
et
w
o
r
k
in
p
u
t
(
d
es
cr
ib
in
g
t
h
e
o
b
j
ec
t’
s
f
ea
t
u
r
es)
an
d
co
r
r
esp
o
n
d
in
g
a
n
s
w
er
.
Fo
r
n
o
t
tr
iv
ial
ca
s
es
it
i
s
u
s
u
all
y
i
m
p
o
s
s
ib
le
to
f
i
n
d
s
e
p
ar
atin
g
f
u
n
ctio
n
w
h
ic
h
cla
s
s
i
f
ies
o
b
j
ec
ts
in
a
p
r
o
p
er
w
a
y
.
T
h
at
is
w
h
y
,
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
allo
w
s
s
o
m
e
er
r
o
r
to
ler
an
ce
,
s
o
th
at
t
h
e
lear
n
i
n
g
p
r
o
ce
s
s
b
r
in
g
s
b
est r
esu
l
ts
[
1
7
,
1
8
]
.
T
h
e
p
r
o
ce
s
s
o
f
tr
ain
in
g
ar
ti
f
ic
ial
n
e
u
r
al
n
et
w
o
r
k
is
s
to
ch
ast
i
c
s
o
,
to
s
o
m
e
ex
te
n
t,
it
i
s
u
n
p
r
ed
ictab
le.
T
h
is
w
ea
k
n
es
s
is
at
t
h
e
s
a
m
e
ti
m
e
SS
N
’
s
g
r
ea
te
s
t
s
tr
en
g
t
h
-
th
e
f
ea
t
u
r
e
s
a
y
i
n
g
th
a
t
t
h
e
n
et
w
o
r
k
ca
n
s
o
lv
e
p
r
o
b
lem
s
t
h
at
p
eo
p
le
ar
e
u
n
ab
le
to
s
o
lv
e
o
r
w
e
ca
n
n
o
t
d
escr
ib
e
u
s
in
g
class
ic
m
at
h
e
m
atica
l
ap
p
ar
atu
s
.
T
h
e
w
h
o
le
k
n
o
w
led
g
e
o
f
n
e
u
r
al
n
et
w
o
r
k
i
s
s
to
r
ed
in
th
e
w
ei
g
h
ts
o
f
p
ar
ticu
lar
n
eu
r
o
n
s
,
an
d
th
e
tr
ain
in
g
p
r
o
ce
s
s
its
elf
i
s
ab
o
u
t th
e
m
o
d
if
icatio
n
o
f
t
h
e
w
eig
h
t
s
v
al
u
es
ac
co
r
d
in
g
to
a
s
et
alg
o
r
ith
m
[
1
9
,
2
0
]
.
T
ak
in
g
i
n
to
co
n
s
id
er
atio
n
t
h
e
k
in
d
o
f
al
g
o
r
ith
m
(
o
f
s
ets)
,
ac
co
r
d
in
g
to
w
h
ic
h
s
y
n
ap
ti
c
w
ei
g
h
ts
m
o
d
i
f
icat
io
n
i
s
p
er
f
o
r
m
ed
i
n
t
h
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
,
a
n
u
m
b
er
o
f
tr
ai
n
in
g
r
u
le
s
ca
n
b
e
d
i
s
ti
n
g
u
i
s
h
ed
.
T
h
e
y
tr
ea
t
ab
o
u
t
th
e
d
ep
en
d
en
ce
s
ac
co
r
d
in
g
to
w
h
ic
h
t
h
e
n
e
u
r
o
n
’
s
w
e
ig
h
t
v
al
u
es
ar
e
m
o
d
i
f
ied
.
So
m
e
o
f
t
h
e
r
u
les
ar
e
r
elate
d
to
th
e
tr
ain
i
n
g
m
o
d
e
with
teac
h
er
,
a
n
d
o
th
er
s
to
tr
ai
n
i
n
g
w
it
h
o
u
t
t
ea
c
h
er
[
1
8
,
2
1
]
.
Neu
r
o
n
o
u
tp
u
t
v
al
u
e
ca
n
b
e
w
r
itte
n
w
it
h
d
ep
en
d
en
c
e:
=
(
∑
=
0
)
=
(
)
(
3
)
w
h
er
e:
=
[
−
1
,
1
,
2
…
]
=
[
0
,
1
,
2
…
]
-
v
ec
to
r
o
f
i
n
p
u
t si
g
n
als
;
=
[
,
1
,
2
…
]
=
[
0
,
1
,
2
…
]
-
v
ec
to
r
o
f
s
y
n
ap
tic
w
eig
h
t
s
;
U
-
n
e
u
r
o
n
d
iap
h
r
ag
m
p
o
ten
t
i
al.
T
h
e
f
o
r
m
u
la
an
a
l
y
s
is
(
3
)
lead
s
to
a
co
n
clu
s
io
n
t
h
at
a
n
ar
tif
i
cial
n
eu
r
o
n
r
ea
li
ze
s
th
e
f
u
n
cti
o
n
o
f
t
w
o
v
ec
to
r
v
ar
iab
les
w
h
ich
co
n
v
er
t
th
e
s
i
g
n
a
l
f
r
o
m
n
-
d
i
m
e
n
s
io
n
al
s
p
ac
e
i
n
to
o
n
e
-
d
i
m
en
s
io
n
al
s
p
ac
e
[
2
2
]
.
T
h
e
tr
an
s
itio
n
f
u
n
ctio
n
d
eter
m
i
n
es
n
eu
r
o
n
’
s
“
b
e
h
av
io
u
r
”
.
Mo
s
t
co
m
m
o
n
l
y
u
s
ed
f
u
n
ct
io
n
s
ar
e:
h
y
p
er
b
o
lic
tan
g
e
n
t,
h
y
p
er
b
o
lic
s
in
e,
a
n
d
lin
ea
r
f
u
n
c
tio
n
.
Ot
h
er
t
y
p
e
s
o
f
f
u
n
ctio
n
s
ar
e
m
o
r
e
r
ar
el
y
u
s
ed
.
4.
I
M
P
ACT O
F
WE
AT
H
E
R
C
O
NDIT
I
O
NS O
N
WI
ND
F
A
RM
O
P
E
RATI
O
N
P
o
w
er
g
e
n
er
ated
b
y
a
w
i
n
d
f
ar
m
is
a
to
tal
p
o
w
er
o
f
i
ts
g
e
n
er
ato
r
s
.
=
∑
=
1
(
4
)
P
o
w
er
o
f
a
n
in
d
i
v
id
u
al
t
u
r
b
in
e
(
)
is
d
ir
ec
tly
d
ep
en
d
an
t o
n
th
e
w
i
n
d
s
tr
en
g
t
h
:
=
(
)
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
3
9
5
7
-
3966
3960
w
h
er
e:
:
w
i
n
d
s
tr
e
n
g
t
h
[
W
]
:
ef
f
icie
n
c
y
o
f
i
-
t
h
t
u
r
b
in
e
W
in
d
s
tr
en
g
th
ca
n
b
e
d
escr
ib
ed
w
it
h
d
ep
en
d
en
ce
[
1
5
]
:
=
1
2
3
(
6
)
w
h
er
e:
:
air
d
en
s
it
y
[
k
g
/
m
2
],
A
:
ar
ea
b
ac
k
ed
-
o
f
f
b
y
th
e
w
h
ee
l
(
cr
o
s
s
-
s
ec
tio
n
o
f
air
s
tr
ea
m
)
,
V
:
w
i
n
d
s
p
ee
d
[
m
/s
]
T
ak
in
g
i
n
to
co
n
s
id
er
atio
n
t
h
at
air
d
en
s
it
y
d
ep
en
d
s
o
n
its
te
m
p
er
atu
r
e,
p
r
ess
u
r
e
an
d
h
u
m
id
it
y
:
=
(
7
)
h
er
e:
:
p
r
ess
u
r
e
[
P
a]
,
M
:
ef
f
ec
tiv
e
air
m
o
lar
m
as
s
[
k
g
/
m
o
l]
,
R
:
g
as c
o
n
s
tan
t [
J
/
m
o
l
*
d
eg
K]
,
T
:
te
m
p
er
atu
r
e
i
n
ab
s
o
lu
te
s
ca
le
[
K]
.
T
h
e
f
o
r
m
u
la
f
o
r
w
i
n
d
f
ar
m
p
o
w
er
is
a
s
f
o
llo
w
s
:
=
∑
(
)
3
2
=
1
(
8
)
Mo
s
t
o
f
te
n
,
a
s
i
n
g
le
f
ar
m
h
as
th
e
s
a
m
e
g
e
n
er
ato
r
s
.
T
h
en
,
=
.
I
t
ca
n
b
e
m
o
s
t
o
f
te
n
as
s
u
m
ed
w
i
t
h
a
s
m
all
er
r
o
r
th
at
air
te
m
p
er
at
u
r
e
an
d
p
r
ess
u
r
e
w
it
h
i
n
th
e
f
a
r
m
ar
e
th
e
s
a
m
e:
=
,
=
.
So
m
e
v
ar
iab
les
m
a
y
o
cc
u
r
in
ca
s
e
i
f
w
i
n
d
s
p
ee
d
.
T
h
e
f
ac
to
r
s
m
en
t
io
n
ed
ab
o
v
e
ar
e
th
e
at
m
o
s
p
h
er
ic
an
d
m
ea
s
u
r
ab
le
f
ac
to
r
s
.
I
t
is
s
ig
n
i
f
ican
t
l
y
m
o
r
e
d
if
f
ic
u
lt
to
d
eter
m
in
e
a
m
o
m
en
tar
y
t
u
r
b
in
e
’
s
ef
f
icie
n
c
y
,
an
d
it
s
ch
an
g
es
d
ir
ec
tl
y
in
f
lu
e
n
ce
t
h
e
g
en
er
ato
r
’
s
c
h
ar
ac
ter
is
tics
,
w
h
ic
h
i
s
th
e
r
ea
s
o
n
w
h
y
its
r
ea
l
p
r
o
ce
s
s
is
d
i
f
f
e
r
en
t
f
r
o
m
t
h
e
id
ea
l
o
n
e
Fi
g
u
r
e
4
.
T
h
e
i
n
f
lu
e
n
ce
o
n
e
f
f
ic
ien
c
y
ca
n
h
a
v
e
m
u
lti
p
le
f
ac
to
r
s
s
u
ch
as
w
i
n
d
g
r
ad
ien
t,
te
m
p
er
atu
r
e
g
r
ad
ien
t,
w
i
n
d
s
p
ee
d
p
r
o
f
ile,
d
is
tu
r
b
an
ce
ca
u
s
ed
b
y
n
e
ig
h
b
o
u
r
in
g
tu
r
b
i
n
es,
ch
a
n
g
es
i
n
w
i
n
d
d
ir
ec
tio
n
,
en
er
g
y
co
n
s
u
m
p
tio
n
o
n
its
o
w
n
n
ee
d
s
.
5.
E
XP
L
A
NATOR
Y
DAT
A
SE
L
E
C
T
I
O
N
F
O
R
AN
N
T
h
e
s
tr
en
g
t
h
o
f
n
e
u
r
al
n
et
w
o
r
k
s
is
ab
o
u
t
a
n
au
to
m
atic
s
ea
r
ch
f
o
r
d
ep
en
d
en
ce
s
b
et
w
ee
n
in
p
u
t
a
n
d
o
u
tp
u
t
d
ata,
as
a
r
es
u
lt
o
f
a
p
r
o
ce
s
s
ca
lled
tr
ain
i
n
g
.
Fo
r
e
f
f
e
ctiv
e
tr
ain
i
n
g
it
is
n
ec
ess
ar
y
t
o
s
elec
t
p
r
o
p
er
in
p
u
t
d
ata
th
at
is
th
e
o
n
es
w
h
ic
h
h
av
e
a
n
i
m
p
ac
t
o
n
o
u
tp
u
t
d
ata
,
in
o
u
r
ca
s
e,
o
n
t
h
e
f
o
r
ec
ast
en
er
g
y
g
en
er
atio
n
.
T
h
e
ex
p
lan
ato
r
y
(
d
eter
m
i
n
an
t
)
f
ea
t
u
r
e
o
f
in
p
u
t
d
ata
a
s
w
el
l
as
i
ts
r
ep
r
ese
n
tati
v
en
e
s
s
ar
e
eq
u
all
y
i
m
p
o
r
tan
t
.
O
w
in
g
to
th
eir
ab
ilit
y
to
lear
n
au
to
m
atica
ll
y
,
ar
tif
icia
l
n
eu
r
al
n
et
w
o
r
k
s
ca
n
f
in
d
i
n
f
o
r
m
a
tio
n
h
id
d
en
in
d
ata
th
at
is
h
ar
d
l
y
ac
ce
s
s
ib
le
f
o
r
o
th
er
m
eth
o
d
s
.
A
s
it
w
as
m
e
n
tio
n
ed
ab
o
v
e,
p
r
o
p
e
r
s
elec
tio
n
o
f
in
p
u
t
d
ata
is
th
e
o
n
l
y
co
n
d
itio
n
.
T
h
e
p
ap
er
[
7
]
p
r
esen
ts
th
e
p
h
y
s
ica
l
in
f
l
u
e
n
ce
an
al
y
s
is
o
f
th
e
w
i
n
d
s
p
ee
d
an
d
d
ir
ec
tio
n
,
air
te
m
p
er
atu
r
e
a
n
d
at
m
o
s
p
h
er
ic
p
r
ess
u
r
e
o
n
th
e
p
o
w
er
g
e
n
er
ated
b
y
t
u
r
b
in
e
s
.
B
ased
o
n
t
h
ese
an
al
y
s
e
s
,
f
o
u
r
f
o
r
ec
ast
m
o
d
el
s
o
f
n
e
u
r
al
n
e
t
w
o
r
k
s
w
er
e
cr
ea
ted
an
d
te
s
te
d
.
T
h
e
co
n
d
u
cted
an
al
y
s
es
s
h
o
w
ed
th
a
t
t
h
e
m
o
d
el
w
h
ic
h
co
n
s
id
er
s
w
i
n
d
s
p
ee
d
an
d
te
m
p
er
at
u
r
e
w
as
m
o
s
t
ac
cu
r
ate.
T
h
e
p
ap
er
[
4
]
s
elec
ts
d
ata
b
ased
o
n
th
e
co
r
r
elatio
n
v
al
u
e
b
et
w
ee
n
p
ar
ticu
lar
f
ac
to
r
s
an
d
en
er
g
y
g
en
er
atio
n
p
er
d
a
y
,
a
n
d
o
n
t
h
e
m
u
t
u
al
co
r
r
elatio
n
b
et
w
ee
n
d
ata.
O
n
t
h
e
b
a
s
is
o
f
t
h
e
co
n
d
u
cted
a
n
al
y
s
e
s
,
t
h
e
au
t
h
o
r
s
s
elec
ted
t
h
e
f
o
llo
w
in
g
e
x
p
lan
ato
r
y
d
ata:
w
i
n
d
s
p
ee
d
f
o
r
e
ca
s
t,
at
m
o
s
p
h
er
ic
p
r
ess
u
r
e
f
o
r
ec
ast,
w
i
n
d
s
p
ee
d
o
n
a
p
r
e
v
io
u
s
d
a
y
,
en
er
g
y
g
e
n
er
atio
n
o
n
a
p
r
ev
io
u
s
d
a
y
,
a
v
er
ag
e
m
o
n
t
h
en
er
g
y
g
e
n
er
atio
n
v
alu
e.
T
h
e
an
al
y
s
is
o
f
co
r
r
elatio
n
b
et
w
e
en
ex
p
la
n
ato
r
y
d
ata
an
d
en
er
g
y
g
e
n
er
atio
n
is
also
u
s
ed
in
p
ap
er
s
w
h
ich
ap
p
l
y
to
f
o
r
ec
asti
n
g
b
y
ar
tif
icial
n
eu
r
a
l
n
et
w
o
r
k
s
[
9
]
an
d
o
th
er
f
o
r
ec
asti
n
g
m
et
h
o
d
s
th
a
n
ar
tif
ic
ial
n
e
u
r
al
n
et
w
o
r
k
s
[
5
]
.
5
.
1
.
Wea
t
hers f
a
ct
o
rs
I
n
th
e
p
r
ese
n
t
p
ap
er
,
th
e
s
ele
ctio
n
o
f
e
x
p
lan
ato
r
y
v
ar
iab
les
b
eg
in
s
f
r
o
m
t
h
e
an
al
y
s
is
o
f
co
r
r
elatio
n
b
et
w
ee
n
s
elec
ted
at
m
o
s
p
h
er
ic
f
ac
to
r
s
a
n
d
th
e
e
n
er
g
y
g
e
n
er
atio
n
v
o
l
u
m
e.
T
h
e
s
t
u
d
ies
co
v
er
ed
th
e
w
h
o
le
w
in
d
p
o
w
er
p
lan
t.
T
h
e
an
al
y
s
es i
n
v
o
lv
ed
th
e
f
o
llo
w
i
n
g
ex
ter
n
al
f
ac
to
r
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Th
e
q
u
a
lity o
f
d
a
ta
a
n
d
t
h
e
a
c
cu
r
a
cy
o
f e
n
erg
y
g
en
era
tio
n
f
o
r
ec
a
s
t b
y
a
r
tifi
cia
l
…
(
B
o
g
d
a
n
K
w
ia
tko
w
s
ki
)
3961
-
W
in
d
s
p
ee
d
at
a
h
eig
h
t o
f
1
0
0
m
,
-
W
in
d
s
p
ee
d
at
th
e
h
ei
g
h
t o
f
9
9
m
,
-
W
in
d
s
p
ee
d
at
a
h
eig
h
t o
f
5
0
m
,
-
W
in
d
d
ir
ec
tio
n
at
a
h
eig
h
t o
f
1
0
0
m
,
-
W
in
d
d
ir
ec
tio
n
at
a
h
eig
h
t o
f
5
0
m
,
-
P
r
ec
ip
itatio
n
,
-
A
ir
p
r
ess
u
r
e,
-
E
x
ter
n
al
te
m
p
er
atu
r
e,
-
A
ir
h
u
m
id
it
y
,
T
h
e
v
a
lu
es
o
f
a
c
o
r
r
e
l
a
t
i
o
n
c
o
ef
f
i
ci
en
t
f
o
r
th
e
an
a
ly
s
e
d
f
a
ct
o
r
s
b
e
tw
e
en
2
0
1
4
a
n
d
2
0
1
7
w
e
r
e
s
h
o
w
n
i
n
T
a
b
l
e
1
.
T
h
e
d
ata
an
al
y
s
is
s
h
o
w
s
th
e
s
tr
o
n
g
es
t
d
ep
en
d
en
c
y
o
f
e
n
er
g
y
g
en
er
at
io
n
v
o
l
u
m
e
o
n
t
h
e
w
i
n
d
s
p
ee
d
[
2
3
]
.
T
h
e
co
r
r
elatio
n
w
ith
t
h
e
o
t
h
er
v
ar
iab
les
i
s
s
i
g
n
i
f
ica
n
tl
y
lo
w
er
.
Mo
r
eo
v
er
,
its
v
alu
e
i
n
p
ar
ticu
la
r
y
ea
r
s
g
r
ea
tl
y
v
ar
ies,
th
er
e
f
o
r
e,
it
is
n
ec
es
s
ar
y
to
a
n
al
y
s
e
t
h
e
r
ea
s
o
n
o
f
t
h
e
m
e
n
tio
n
ed
v
ar
i
ab
les
b
ef
o
r
e
a
f
i
n
al
d
ec
is
io
n
ab
o
u
t th
e
s
elec
tio
n
o
f
ex
p
lan
ato
r
y
d
ata
is
m
ad
e.
T
ab
le
1
.
C
o
ef
f
icie
n
t v
al
u
es
o
f
co
r
r
elatio
n
o
f
ex
p
lan
ato
r
y
v
ar
i
ab
les
w
ith
e
n
er
g
y
g
e
n
er
atio
n
v
o
lu
m
e
Ex
p
l
a
n
a
t
o
r
y
v
a
r
i
a
b
l
e
C
o
r
r
e
l
a
t
i
o
n
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
1
0
0
m
0
.
7
8
3
3
0
.
4
7
4
8
0
.
5
5
7
7
0
.
5
8
1
0
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
9
9
m
0
.
7
8
3
3
0
.
4
7
2
3
0
.
5
5
4
3
0
.
5
8
8
1
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
5
0
m
0
.
7
7
8
5
0
.
4
7
7
8
0
.
5
5
8
6
0
.
6
0
0
5
w
i
n
d
d
i
r
e
c
t
i
o
n
a
t
a
h
e
i
g
h
t
o
f
1
0
0
m
0
.
1
6
2
7
0
.
1
8
4
7
0
.
2
9
6
3
-
0
.
0
9
5
1
w
i
n
d
d
i
r
e
c
t
i
o
n
a
t
a
h
e
i
g
h
t
o
f
5
0
m
0
.
1
8
4
8
0
.
2
0
6
3
0
.
3
1
1
8
-
0
.
0
8
3
2
p
r
e
c
i
p
i
t
a
t
i
o
n
0
.
1
3
2
8
0
.
0
6
0
2
0
.
2
1
8
2
-
0
.
0
5
5
2
a
i
r
p
r
e
ssu
r
e
-
0
.
0
3
0
4
0
.
0
5
5
0
0
.
2
2
1
2
0
.
0
0
1
6
e
x
t
e
r
n
a
l
t
e
mp
e
r
a
t
u
r
e
-
0
.
0
3
5
0
-
0
.
0
8
2
3
-
0
.
0
0
1
3
-
0
.
1
9
3
2
a
i
r
h
u
m
i
d
i
t
y
0
.
0
7
0
6
-
0
.
0
0
1
6
0
.
1
6
0
5
0
.
1
5
9
0
Fig
u
r
es
5
an
d
6
s
h
o
w
ed
th
e
d
iag
r
a
m
s
o
f
co
r
r
elatio
n
s
b
et
w
ee
n
w
in
d
s
p
ee
d
an
d
en
er
g
y
g
en
er
atio
n
v
o
lu
m
e.
W
ith
p
er
f
ec
t
tu
r
b
i
n
e
o
p
er
atio
n
an
d
id
ea
l
m
ea
s
u
r
em
en
t
r
esu
lts
,
it
s
h
o
u
ld
b
e
s
i
m
ilar
to
th
e
s
ca
led
(
b
ec
au
s
e
o
f
t
h
e
o
p
er
atio
n
o
f
5
tu
r
b
in
e
s
)
ch
ar
ac
ter
i
s
tics
o
f
th
e
w
i
n
d
t
u
r
b
in
e
Fi
g
u
r
e
4
.
Di
s
tr
ib
u
tio
n
o
f
p
o
in
ts
o
n
l
y
s
u
p
er
f
iciall
y
r
e
s
e
m
b
le
s
t
h
e
m
e
n
tio
n
ed
c
h
ar
ac
ter
is
t
ics.
Dis
p
er
s
io
n
o
f
p
o
i
n
ts
m
a
y
r
e
s
u
l
t
f
r
o
m
t
h
e
c
h
a
n
g
e
s
in
th
e
o
p
er
atio
n
o
f
p
ar
ticu
lar
tu
r
b
in
es.
Ho
w
ev
er
,
th
e
v
er
tica
l
lin
e
s
,
s
h
o
w
n
in
F
i
g
u
r
e
6
,
f
o
r
th
e
w
i
n
d
s
p
ee
d
o
f
0
m
/s
,
2
.
4
m
/s
a
n
d
4
.
6
m
/s
ar
e
h
ar
d
to
j
u
s
ti
f
y
o
t
h
er
w
a
y
t
h
an
a
s
in
co
r
r
ec
t
m
ea
s
u
r
e
m
en
t
o
f
w
in
d
s
p
ee
d
o
r
en
er
g
y
g
e
n
er
atio
n
v
o
lu
m
e.
Si
m
ilar
s
i
tu
atio
n
ca
n
b
e
n
o
ticed
in
d
iag
r
a
m
s
w
i
th
t
h
e
co
r
r
elatio
n
o
f
w
i
n
d
s
p
ee
d
an
d
en
er
g
y
g
e
n
er
atio
n
v
o
lu
m
e
f
o
r
th
e
y
ea
r
s
2
0
1
6
an
d
2
0
1
7
,
b
u
t
th
e
y
ap
p
ea
r
f
o
r
d
if
f
er
e
n
t
s
p
ee
d
in
b
o
th
ca
s
es.
T
h
u
s
,
th
e
d
ata
w
as
clea
r
ed
o
u
t
o
f
v
alu
es
f
o
r
w
h
ich
en
er
g
y
g
en
er
a
tio
n
v
o
l
u
m
es
w
er
e
s
ig
n
i
f
ican
tl
y
to
o
h
i
g
h
f
o
r
p
ar
ticu
lar
w
i
n
d
s
tr
e
n
g
th
.
Af
ter
eli
m
i
n
atio
n
o
f
u
n
d
o
u
b
ted
l
y
in
co
r
r
ec
t
m
ea
s
u
r
e
m
e
n
ts
,
w
in
d
s
p
ee
d
co
r
r
elatio
n
co
ef
f
icie
n
t
s
at
d
if
f
er
en
t
h
ei
g
h
t
s
an
d
its
d
ir
ec
tio
n
w
i
th
e
n
er
g
y
g
en
er
atio
n
v
o
l
u
m
e
c
h
a
n
g
ed
T
ab
le
2
.
T
h
e
an
al
y
s
i
s
o
f
co
ef
f
icie
n
ts
o
f
th
e
co
r
r
elatio
n
b
et
w
ee
n
w
ea
th
er
p
ar
a
m
eter
s
w
it
h
en
er
g
y
g
en
er
atio
n
v
o
lu
m
e
i
n
d
icate
s
h
ig
h
i
n
ter
d
e
p
en
d
en
ce
b
et
w
ee
n
e
n
er
g
y
g
en
er
atio
n
v
o
l
u
m
e
a
n
d
w
i
n
d
s
p
e
ed
.
T
h
e
co
r
r
elatio
n
o
f
th
e
o
th
er
p
ar
a
m
eter
s
w
ith
en
er
g
y
g
e
n
er
atio
n
v
o
lu
m
e
i
s
lo
w
.
I
t
w
a
s
t
h
er
ef
o
r
e
d
ec
id
ed
t
h
at
n
e
u
r
al
n
e
t
w
o
r
k
tr
ain
i
n
g
w
o
u
ld
b
e
co
n
d
u
cted
u
s
in
g
t
w
o
d
if
f
er
en
t e
x
p
lan
a
to
r
y
v
ar
iab
les:
-
W
in
d
s
p
ee
d
at
a
h
eig
h
t o
f
1
0
0
m
;
-
W
in
d
s
p
ee
d
at
a
h
eig
h
t o
f
1
0
0
m
an
d
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t
o
f
5
0
m
.
Fig
u
r
e
5
.
Diag
r
a
m
o
f
co
r
r
elatio
n
b
et
w
ee
n
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t
o
f
at
a
h
ei
g
h
t o
f
1
0
0
m
h
ei
g
h
t
a
n
d
en
er
g
y
g
en
er
atio
n
in
2
0
1
4
0
5
10
15
20
25
0
2
4
6
8
10
W
ind
s
pe
ed
at
a
he
igh
t
of
10
0
m
[
m
/
s
]
En
erg
y
[
M
W
h]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
3
9
5
7
-
3966
3962
Fig
u
r
e
6
.
Diag
r
a
m
o
f
co
r
r
elatio
n
b
et
w
ee
n
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t o
f
at
a
h
ei
g
h
t o
f
1
0
0
m
h
ei
g
h
t
an
d
en
er
g
y
g
e
n
er
atio
n
i
n
2
0
1
5
T
ab
le
2
.
C
o
ef
f
icie
n
t v
al
u
es o
f
co
r
r
elatio
n
b
et
w
ee
n
e
x
p
lan
a
to
r
y
v
ar
iab
lesa
n
d
en
er
g
y
g
en
er
atio
n
v
o
l
u
m
es
a
f
ter
eli
m
i
n
atio
n
o
f
in
co
r
r
ec
t
m
ea
s
u
r
e
m
e
n
t
Ex
p
l
a
n
a
t
o
r
y
v
a
r
i
a
b
l
e
C
o
r
r
e
l
a
t
i
o
n
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
1
0
0
m
0
.
7
8
3
3
0
.
8
1
7
4
0
.
8
9
0
0
0
.
8
8
3
9
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
9
9
m
0
.
7
8
3
3
0
.
8
2
2
7
0
.
8
8
9
8
0
.
8
8
4
0
w
i
n
d
s
p
e
e
d
a
t
a
h
e
i
g
h
t
o
f
5
0
m
0
.
7
7
8
5
0
.
8
2
7
5
0
.
8
8
9
0
0
.
8
8
2
3
w
i
n
d
d
i
r
e
c
t
i
o
n
a
t
a
h
e
i
g
h
t
o
f
1
0
0
m
0
.
1
6
2
7
0
.
2
3
9
1
0
.
1
4
7
4
0
.
1
3
1
4
w
i
n
d
d
i
r
e
c
t
i
o
n
a
t
a
h
e
i
g
h
t
o
f
5
0
m
0
.
1
8
4
8
0
.
2
9
7
3
0
.
2
2
9
8
0
.
2
0
0
6
6.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
Fo
r
th
e
p
u
r
p
o
s
e
o
f
ev
alu
atio
n
an
d
co
m
p
ar
is
o
n
o
f
th
e
q
u
al
it
y
o
f
co
n
d
u
cted
f
o
r
ec
ast
s
,
th
e
f
o
llo
w
in
g
in
d
ices
w
er
e
in
tr
o
d
u
ce
d
:
-
Me
an
ab
s
o
lu
te
er
r
o
r
:
=
1
∑
|
|
=
1
(
9
)
-
No
r
m
ed
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
=
√
∑
2
=
1
(
1
0
)
-
P
er
ce
n
tag
e
ef
f
ec
ti
v
en
e
s
s
o
f
o
b
tain
in
g
f
o
r
ec
ast
w
it
h
th
e
ac
c
u
r
ac
y
o
f
2
MW
w
h
ic
h
is
20%
o
f
in
s
talled
ca
p
ac
it
y
2
=
co
un
t
(
2
)
∗
100%
,
2
=
{
:
|
|
<
2
}
(
1
1
)
-
P
er
ce
n
tag
e
ef
f
ec
ti
v
en
e
s
s
o
f
o
b
tain
in
g
f
o
r
ec
ast
w
it
h
th
e
ac
c
u
r
ac
y
o
f
1
MW
w
h
ic
h
is
10%
o
f
in
s
talled
ca
p
ac
it
y
1
=
co
un
t
(
1
)
∗
100%
,
1
=
{
:
|
|
<
2
}
(
1
2
)
-
Ma
x
i
m
u
m
f
o
r
ec
ast er
r
o
r
=
min
k
=
1
.
.
n
(
)
(
1
3
)
w
h
er
e:
:
n
u
m
b
er
o
f
f
o
r
ec
ast
s
,
: e
r
r
o
r
o
f
k
-
th
f
o
r
ec
ast,
:
r
ated
f
ar
m
ca
p
ac
it
y
0
5
10
15
20
25
0
2
4
6
8
10
W
i
n
d
s
p
eed
at
a
h
ei
g
h
t
o
f
1
0
0
m
[m
/
s
]
E
n
erg
y
[MW
h
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Th
e
q
u
a
lity o
f
d
a
ta
a
n
d
t
h
e
a
c
cu
r
a
cy
o
f e
n
erg
y
g
en
era
tio
n
f
o
r
ec
a
s
t b
y
a
r
tifi
cia
l
…
(
B
o
g
d
a
n
K
w
ia
tko
w
s
ki
)
3963
6
.
1
.
F
o
re
ca
s
t
s
w
it
h
co
ns
er
v
a
t
iv
e
m
et
ho
d
I
n
th
e
co
n
s
er
v
ati
v
e
m
et
h
o
d
an
ap
p
r
o
ac
h
w
i
th
t
h
e
p
er
s
p
ec
tiv
e
w
as a
p
p
lied
:
-
1
h
-
f
o
r
ec
ast b
ased
o
n
th
e
g
en
e
r
atio
n
an
h
o
u
r
b
ef
o
r
e,
-
6
h
-
f
o
r
ec
ast b
ased
o
n
th
e
g
e
n
er
atio
n
6
h
o
u
r
s
b
ef
o
r
e.
Fig
u
r
e
7
s
h
o
w
ed
f
o
r
ec
ast
r
es
u
lts
f
o
r
th
e
p
er
s
p
ec
ti
v
e
o
f
1
h
.
Ve
r
y
s
h
o
r
t
ti
m
e
p
er
s
p
ec
ti
v
e
m
a
k
e
s
a
v
is
u
al
i
m
p
r
ess
io
n
t
h
at
t
h
e
wav
ef
o
r
m
s
p
r
ac
ti
ca
ll
y
co
in
cid
e
w
it
h
ea
c
h
o
th
er
.
Ho
w
e
v
er
,
th
e
v
alu
e
s
o
f
i
n
d
ices
p
r
esen
ted
in
T
ab
le
3
,
w
h
ic
h
esti
m
ate
f
o
r
ec
ast
ac
c
u
r
ac
y
s
h
o
w
t
h
at
t
h
e
er
r
o
r
is
n
o
t
s
o
s
m
all.
A
tte
n
tio
n
is
b
r
o
u
g
h
t
to
a
lo
w
v
alu
e
o
f
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
an
d
a
r
elativ
el
y
h
ig
h
v
al
u
e
o
f
m
a
x
i
m
u
m
ab
s
o
lu
te
er
r
o
r
(
Ma
x
E
)
.
Fig
u
r
e
8
s
h
o
w
s
t
h
e
f
o
r
ec
ast
r
esu
lt
s
f
o
r
th
e
p
er
s
p
ec
tiv
e
o
f
6
h
an
d
T
ab
le
4
in
clu
d
es
th
e
v
alu
e
s
o
f
in
d
ices
f
o
r
esti
m
ati
n
g
f
o
r
ec
asts
ac
c
u
r
ac
y
.
T
i
m
e
p
e
r
s
p
ec
tiv
e
e
x
te
n
s
io
n
s
i
g
n
i
f
ican
t
l
y
w
o
r
s
e
n
ed
f
o
r
ec
ast
s
ac
cu
r
ac
y
-
m
ea
n
er
r
o
r
in
cr
ea
s
e
d
m
o
r
e
th
a
n
1
0
0
%,
w
h
ile
m
a
x
i
m
u
m
ab
s
o
lu
te
er
r
o
r
r
ea
ch
ed
th
e
v
al
u
e
clo
s
e
to
th
e
r
ated
p
o
w
er
o
f
elec
tr
ic
p
o
w
er
p
lan
t
T
ab
le
4
.
Fig
u
r
e
7
.
P
r
ed
ictio
n
o
f
en
er
g
y
g
en
er
atio
n
w
it
h
co
n
s
er
v
ati
v
e
m
et
h
o
d
in
th
e
p
er
s
p
ec
ti
v
e
o
f
1
h
:
f
o
r
ec
ast
-
in
ter
r
u
p
t lin
e,
r
ea
l g
e
n
er
atio
n
-
co
n
ti
n
u
o
u
s
li
n
e,
f
o
r
ec
ast er
r
o
r
-
d
o
t lin
e
T
ab
le
3
.
Ob
tain
ed
r
esu
lts
o
f
p
r
ed
ictio
n
w
ith
co
n
s
er
v
a
tiv
e
m
e
th
o
d
f
o
r
1
h
ah
ea
d
M
A
E
[
M
W
]
n
R
M
S
E
[
%
]
A
EM
E2
[
%
]
A
EM
E1
[
%
]
M
a
x
E
[
M
W
]
2
0
1
4
0
.
7
4
1
1
.
1
9
2
.
0
7
3
.
9
5
.
7
7
2
0
1
5
0
.
5
7
9
.
4
9
4
.
2
8
2
.
0
8
.
3
1
2
0
1
6
0
.
5
9
1
0
.
0
9
3
.
0
8
1
.
8
7
.
1
1
2
0
1
7
0
.
6
2
1
0
.
1
9
3
.
1
7
9
.
7
7
.
4
8
Fig
u
r
e
8
.
P
r
ed
ictio
n
o
f
en
er
g
y
g
en
er
atio
n
w
it
h
co
n
s
er
v
ati
v
e
m
et
h
o
d
in
th
e
p
er
s
p
ec
ti
v
e
o
f
6
h
:
f
o
r
ec
ast
-
in
ter
r
u
p
t lin
e,
r
ea
l g
e
n
er
atio
n
-
co
n
ti
n
u
o
u
s
lin
e,
f
o
r
ec
ast er
r
o
r
-
d
o
t lin
e
T
ab
le
4
.
Ob
tain
ed
p
r
e
d
ictio
n
r
esu
lt
s
w
it
h
c
o
n
s
er
v
ati
v
e
m
e
th
o
d
f
o
r
6
h
ah
ea
d
M
A
E
[
M
W
]
n
R
M
S
E
[
%
]
A
EM
E2
[
%
]
A
EM
E1
[
%
]
M
a
x
E
[
M
W
]
2
0
1
4
1
.
4
7
2
2
.
2
7
3
.
4
5
5
.
1
9
.
5
9
2
0
1
5
1
.
3
4
2
0
.
3
7
6
.
3
5
7
.
9
9
.
6
6
2
0
1
6
1
.
3
2
2
0
.
5
7
7
.
0
5
9
.
3
9
.
3
6
2
0
1
7
1
.
4
5
2
1
.
4
7
4
.
2
5
4
.
0
9
.
5
2
6
.
2
.
F
o
re
ca
s
t
s
w
i
t
h neura
l net
w
o
rk
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
w
as
co
n
d
u
cted
u
s
i
n
g
t
h
e
d
ata
p
r
esen
ted
i
n
p
.
5
.
T
h
e
tr
ain
ed
n
e
t
w
o
r
k
w
as
u
s
ed
f
o
r
f
o
r
ec
asti
n
g
b
ased
o
n
cu
r
r
en
t
w
ea
t
h
er
,
v
o
l
u
m
e
o
f
e
n
er
g
y
p
r
o
d
u
ce
d
b
y
e
n
er
g
y
w
i
n
d
g
en
er
ato
r
s
.
Data
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
3
9
5
7
-
3966
3964
u
s
ed
f
o
r
t
h
e
tr
ai
n
i
n
g
co
m
e
f
r
o
m
t
h
e
p
er
io
d
0
1
.
0
1
.
2
0
1
4
-
3
1
.
1
2
.
2
0
1
4
,
w
h
ile
test
d
ata
f
r
o
m
t
h
e
p
er
io
d
0
1
.
0
1
.
2
0
1
5
-
3
1
.
1
2
.
2
0
1
7
.
Fo
r
ec
asts
w
er
e
co
n
d
u
cted
f
o
r
th
e
w
h
o
le
y
ea
r
an
d
f
o
r
p
ar
ticu
lar
m
o
n
t
h
s
.
Net
w
o
r
k
tr
ain
ed
w
it
h
d
ata
f
r
o
m
J
a
n
u
ar
y
2
0
1
4
w
as
u
s
ed
f
o
r
f
o
r
ec
asti
n
g
th
e
e
n
er
g
y
g
en
e
r
atio
n
in
J
an
u
ar
y
i
n
th
e
y
ea
r
s
2015
-
2
0
1
7
,
an
d
f
r
o
m
Feb
r
u
ar
y
in
t
h
e
f
o
llo
w
in
g
y
ea
r
s
,
etc.
T
h
e
k
i
n
d
o
f
p
r
o
b
lem
a
n
d
t
h
e
s
tr
u
ctu
r
e
o
f
d
ata
i
n
d
icate
t
h
at
s
t
u
d
ies
s
h
o
u
ld
b
e
g
i
n
t
h
e
s
elec
tio
n
o
f
SNN
ar
c
h
itect
u
r
e
f
r
o
m
m
u
ltil
a
y
er
f
ee
d
f
o
r
w
ar
d
n
et
w
o
r
k
s
.
T
h
e
liter
atu
r
e,
i
n
ca
s
e
o
f
f
ee
d
f
o
r
w
ar
d
n
et
w
o
r
k
s
,
in
d
icate
s
t
h
at
a
n
et
w
o
r
k
co
m
p
r
i
s
i
n
g
3
la
y
er
s
:
in
p
u
t,
h
id
d
en
an
d
o
u
tp
u
t,
i
s
ab
le
to
s
o
lv
e
e
v
er
y
p
r
o
b
lem
.
A
r
e
m
ain
in
g
p
r
o
b
lem
to
s
o
l
v
e
is
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
p
ar
ticu
lar
lev
el
s
.
I
n
ca
s
e
o
f
i
n
p
u
t
an
d
o
u
tp
u
t
la
y
er
s
th
e
an
s
w
er
s
ar
e
o
b
v
io
u
s
:
-
T
h
e
am
o
u
n
t
o
f
n
e
u
r
o
n
s
i
n
t
h
e
in
p
u
t
la
y
er
m
u
s
t
b
e
eq
u
al
to
th
e
len
g
t
h
o
f
i
n
p
u
t
v
ec
to
r
-
in
o
u
r
ca
s
e,
it
w
i
ll
b
e
1
n
eu
r
o
n
,
w
h
e
n
th
e
tr
ain
i
n
g
is
p
er
f
o
r
m
ed
b
ased
o
n
l
y
o
n
th
e
s
p
ee
d
at
a
h
eig
h
t
o
f
1
0
0
m
o
r
2
n
eu
r
o
n
s
,
w
h
e
n
th
e
tr
ain
in
g
u
s
es t
h
e
s
p
ee
d
at
th
e
h
ei
g
h
ts
o
f
1
0
0
m
a
n
d
5
0
m
.
-
T
h
e
am
o
u
n
t
o
f
n
e
u
r
o
n
s
in
th
e
o
u
tp
u
t
la
y
er
m
u
s
t
b
e
eq
u
al
to
th
e
a
m
o
u
n
t
o
f
f
o
r
ec
ast
v
a
l
u
es
-
i
n
o
u
r
ca
s
e,
it th
e
a
m
o
u
n
t o
f
g
en
er
ated
en
e
r
g
y
,
s
o
1
n
e
u
r
o
n
is
s
u
f
f
icien
t.
Dete
r
m
i
n
i
n
g
th
e
le
n
g
t
h
o
f
h
id
d
en
la
y
er
,
i
n
t
u
r
n
,
i
s
n
o
t
s
o
o
b
v
io
u
s
.
A
l
th
o
u
g
h
t
h
er
e
ar
e
s
o
m
e
d
ep
en
d
en
cies
u
s
ed
f
o
r
t
h
is
p
u
r
p
o
s
e
b
u
t
th
e
liter
at
u
r
e
i
n
d
icate
s
t
h
at
ca
lc
u
lated
v
al
u
es
s
h
o
u
ld
b
e
tr
ea
ted
a
s
m
i
n
i
m
u
m
v
al
u
es
,
a
n
d
th
e
s
el
ec
tio
n
s
h
o
u
ld
b
e
p
er
f
o
r
m
ed
b
y
tr
ial
a
n
d
er
r
o
r
.
I
n
th
e
d
is
c
u
s
s
ed
ca
s
e,
t
h
e
te
s
ts
w
er
e
co
n
d
u
cted
f
o
r
t
h
e
h
id
d
en
la
y
er
co
m
p
r
is
i
n
g
2
,
3
,
4
an
d
5
n
e
u
r
o
n
s
.
I
t
s
h
o
u
ld
b
e
e
m
p
h
a
s
is
ed
t
h
at
a
n
ex
ce
s
s
iv
e
i
n
cr
ea
s
e
i
n
len
g
t
h
o
f
h
id
d
en
la
y
er
m
a
y
lead
to
a
n
o
v
er
tr
ain
i
n
g
w
h
ic
h
r
e
s
u
l
ts
in
v
er
y
g
o
o
d
tr
ain
in
g
r
esu
lt
s
an
d
a
s
i
g
n
i
f
ica
n
t d
r
o
p
in
p
er
f
o
r
m
a
n
ce
o
f
n
et
w
o
r
k
w
it
h
th
e
d
ata
an
a
l
y
s
is
o
u
ts
id
e
t
h
e
tr
ain
i
n
g
s
e
t.
A
cc
o
r
d
in
g
to
t
h
e
ass
u
m
p
tio
n
s
o
f
f
ee
d
f
o
r
w
ar
d
n
et
w
o
r
k
ar
ch
itect
u
r
e,
all
n
e
u
r
o
n
s
i
n
a
l
a
y
er
h
a
v
e
th
e
s
a
m
e
tr
an
s
it
io
n
f
u
n
c
tio
n
.
I
t
w
as
d
ec
id
ed
th
at
in
th
e
in
p
u
t
an
d
o
u
tp
u
t
la
y
er
s
a
lin
ea
r
f
u
n
ctio
n
w
o
u
ld
b
e
u
s
ed
,
an
d
in
t
h
e
h
id
d
en
la
y
e
r
,
tan
g
en
t
cu
r
v
e
f
u
n
ctio
n
.
T
h
e
tr
ain
ed
n
et
w
o
r
k
w
ith
L
e
v
en
b
er
g
a
-
Ma
r
q
u
r
d
ta
m
et
h
o
d
.
Net
w
o
r
k
tr
ai
n
i
n
g
a
n
d
test
s
w
er
e
ca
r
r
ied
o
u
t
in
t
h
e
Ma
tlab
e
nv
.
,
eq
u
ip
p
ed
w
ith
th
e
to
o
lb
o
x
Ne
u
r
al
Net
w
o
r
k
s
t
h
at
o
f
f
er
s
a
w
id
e
r
an
g
e
o
f
ar
ch
itect
u
r
es a
n
d
p
r
o
ce
d
u
r
es u
s
ed
f
o
r
tr
ain
i
n
g
t
h
e
A
N
N
[
2
4
,
2
5
]
.
Vis
u
a
ll
y
,
s
i
m
i
lar
r
esu
lts
w
er
e
o
b
tain
ed
f
o
r
th
e
an
n
u
al
f
o
r
ec
ast,
in
b
o
th
an
al
y
s
ed
ca
s
es
-
f
o
r
ec
ast
s
b
ased
o
n
w
i
n
d
s
p
ee
d
at
a
h
ei
g
h
t
o
f
1
0
0
m
an
d
f
o
r
ec
asts
b
ase
d
o
n
w
i
n
d
s
p
ee
d
at
o
f
1
0
0
m
a
n
d
5
0
m
a
s
s
h
o
w
n
i
n
Fig
u
r
es
9
a
n
d
1
0
.
T
ested
ac
cu
r
ac
y
co
e
f
f
icie
n
ts
h
av
e
s
i
m
ilar
v
al
u
es
a
s
s
h
o
w
n
i
n
T
a
b
le
s
5
an
d
6
.
Me
a
n
ab
s
o
lu
te
er
r
o
r
f
o
r
th
e
f
ir
s
t
ca
s
e
is
0
.
7
2
MW,
w
h
ile
f
o
r
th
e
s
ec
o
n
d
o
n
e
0
.
7
6
MW
.
A
llo
w
i
n
g
f
o
r
ec
ast
d
ev
iat
io
n
f
r
o
m
r
ea
l
v
al
u
es
o
f
2
0
%,
th
e
n
et
w
o
r
k
e
f
f
ec
ti
v
en
e
s
s
is
9
3
.
7
%
f
o
r
th
e
f
ir
s
t
ca
s
e
a
n
d
9
2
.
2
%
f
o
r
th
e
s
ec
o
n
d
ca
s
e.
W
ith
f
o
r
ec
ast
d
ev
iatio
n
o
f
1
0
%,
it
is
7
2
.
7
%
an
d
7
2
%,
r
esp
e
ctiv
el
y
.
Ob
tain
ed
v
al
u
es
ar
e
c
o
m
p
ar
ab
le,
b
u
t
a
b
it
b
etter
f
o
r
th
e
f
o
r
ec
asts
t
h
at
u
s
e
o
n
l
y
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t
o
f
1
0
0
m
.
Fig
u
r
e
9
.
An
n
u
al
f
o
r
ec
ast o
f
e
n
er
g
y
g
e
n
er
atio
n
r
ea
lized
b
y
A
N
N
b
ased
o
n
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t
o
f
1
0
0
m
,
f
o
r
ec
ast
-
i
n
ter
r
u
p
t li
n
e,
r
ea
l g
en
er
atio
n
-
c
co
n
ti
n
u
o
u
s
lin
e,
f
o
r
ec
ast er
r
o
r
-
d
o
t lin
e
Fig
u
r
e
1
0
.
A
n
n
u
al
en
er
g
y
r
ea
l
ized
b
y
A
NN
b
ased
o
n
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t o
f
1
0
0
m
a
n
d
5
0
m
,
f
o
r
ec
ast
-
in
ter
r
u
p
t lin
e,
r
ea
l g
e
n
er
atio
n
-
c
o
n
ti
n
u
o
u
s
lin
e,
f
o
r
ec
ast er
r
o
r
-
d
o
t lin
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Th
e
q
u
a
lity o
f
d
a
ta
a
n
d
t
h
e
a
c
cu
r
a
cy
o
f e
n
erg
y
g
en
era
tio
n
f
o
r
ec
a
s
t b
y
a
r
tifi
cia
l
…
(
B
o
g
d
a
n
K
w
ia
tko
w
s
ki
)
3965
T
ab
le
5
.
Ob
tain
ed
d
ata
o
f
SS
N
p
r
ed
ictio
n
,
tr
ain
in
g
w
it
h
d
ata
f
r
o
m
2
0
1
2
,
w
i
n
d
o
n
l
y
at
a
h
ei
g
h
t o
f
1
0
0
m
,
3
n
eu
r
o
n
s
M
A
E
[
M
W
]
n
R
M
S
E
[
%
]
A
EM
E2
[
%
]
A
EM
E1
[
%
]
M
a
x
E
[
M
W
]
2
0
1
5
0
.
7
0
1
0
.
8
9
2
.
8
7
6
.
7
6
.
2
6
2
0
1
6
0
.
7
7
1
0
.
6
9
4
.
9
6
7
.
0
4
.
8
3
2
0
1
7
0
.
7
0
1
0
.
2
9
3
.
4
7
4
.
5
7
.
4
7
T
ab
le
6
Ob
tain
ed
d
ata
o
f
SS
N
p
r
ed
ictio
n
,
tr
ain
in
g
w
it
h
d
ata
f
r
o
m
2
0
1
3
,
w
i
n
d
at
a
h
ei
g
h
t
o
f
1
0
0
m
an
d
5
0
m
,
4
n
e
u
r
o
n
s
.
M
A
E
[
M
W
]
n
R
M
S
E
[
%
]
A
EM
E2
[
%
]
A
EM
E1
[
%
]
M
a
x
E
[
M
W
]
2
0
1
5
0
.
6
8
1
0
.
2
9
3
.
7
7
6
.
8
5
.
8
9
2
0
1
6
0
.
7
6
1
0
.
4
9
3
.
3
6
8
.
9
5
.
1
6
2
0
1
7
0
.
8
3
1
2
.
2
8
9
.
5
7
0
.
4
7
.
2
9
I
n
ca
s
e
o
f
m
o
n
th
l
y
f
o
r
ec
asts
,
d
u
e
to
cy
cl
ical
ch
ar
ac
ter
o
f
at
m
o
s
p
h
er
ic
co
n
d
itio
n
s
,
d
ata
ca
n
b
e
m
o
r
e
co
h
er
en
t
w
h
ic
h
s
h
o
u
ld
r
es
u
lt
in
g
r
ea
ter
ac
c
u
r
ac
y
o
f
p
r
ed
ictio
n
.
T
h
e
o
b
tain
ed
f
o
r
ec
asts
r
esu
lt
s
p
r
o
v
e
t
h
e
s
e
ass
u
m
p
ti
o
n
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
11
.
A
ll
ac
cu
r
ac
y
p
r
ed
ictio
n
in
d
ices
i
m
p
r
o
v
ed
T
a
b
le
7
.
T
h
e
i
m
p
o
r
tan
t
th
i
n
g
is
th
at
m
ax
i
m
u
m
f
o
r
ec
ast
er
r
o
r
d
ec
r
ea
s
ed
to
th
e
v
alu
e
o
f
ab
o
u
t
3
.
8
5
M
W
w
h
ic
h
is
t
h
e
v
a
lu
e
b
elo
w
4
0
%
o
f
r
ated
p
o
w
er
o
f
elec
tr
ic
p
o
w
er
p
lan
t
.
T
h
e
r
esu
lts
f
r
o
m
Feb
r
u
ar
y
2
0
1
5
w
en
t
p
ar
ticu
lar
l
y
w
ell
-
m
ea
n
ab
s
o
l
u
te
er
r
o
r
w
a
s
0
.
3
4
MW
,
r
o
o
t
m
ea
n
s
q
u
a
r
e
er
r
o
r
w
as
5
.
4
%
an
d
9
2
.
8
%
o
f
f
o
r
ec
ast
s
d
id
n
o
t
d
if
f
er
o
f
m
o
r
e
t
h
a
n
1
0
%
f
r
o
m
r
ea
l v
alu
e
s
.
Fig
u
r
e
1
1
.
E
n
er
g
y
g
en
er
atio
n
f
o
r
ec
ast (
Feb
r
u
ar
y
)
r
ea
lized
b
y
A
NN
b
ased
o
n
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t o
f
1
0
0
m
,
m
o
n
th
l
y
i
n
ter
r
u
p
t li
n
e,
r
ea
l g
en
er
atio
n
–
c
o
n
ti
n
u
o
u
s
li
n
e,
f
o
r
ec
ast er
r
o
r
–
d
o
t lin
e
T
ab
le
7
Ob
tain
ed
r
esu
lts
o
f
m
o
n
th
l
y
(
Feb
r
u
ar
y
)
p
r
ed
ictio
n
o
f
SS
N
tr
ain
i
n
g
w
i
th
d
ata
f
r
o
m
2
0
1
4
,
w
i
n
d
o
n
l
y
at
a
h
ei
g
h
t o
f
1
0
0
m
,
3
n
eu
r
o
n
s
M
A
E
[
M
W
]
n
R
M
S
E
[
%
]
A
EM
E2
[
%
]
A
EM
E1
[
%
]
M
a
x
E
[
M
W
]
2
0
1
5
0
.
3
4
5
.
4
9
9
.
1
9
2
.
8
3
.
8
0
2
0
1
6
0
.
6
0
8
.
6
9
5
.
7
7
8
.
6
3
.
8
5
2
0
1
7
0
.
5
8
8
.
6
9
5
.
6
7
8
.
6
3
.
8
8
7.
CO
NCLU
SI
O
N
T
h
e
p
ap
er
d
is
cu
s
s
ed
4
m
o
d
els
:
co
n
s
er
v
ati
v
e
w
i
th
1
h
p
er
s
p
e
ctiv
e,
co
n
s
er
v
at
iv
e
w
it
h
6
h
p
e
r
s
p
ec
tiv
e,
n
eu
r
al
n
et
w
o
r
k
t
h
at
u
s
ed
w
i
n
d
s
p
ee
d
at
a
h
ei
g
h
t
o
f
1
0
0
m
,
n
e
u
r
al
n
et
w
o
r
k
th
at
u
s
ed
w
in
d
s
p
ee
d
at
a
h
ei
g
h
t
o
f
1
0
0
m
a
n
d
5
0
m
.
T
h
e
h
i
g
h
est
ac
cu
r
ac
y
w
as
o
b
tain
ed
f
o
r
n
e
u
r
al
n
et
w
o
r
k
th
a
t
u
s
ed
w
i
n
d
s
p
ee
d
at
a
h
eig
h
t
o
f
1
0
0
m
w
it
h
m
o
n
t
h
l
y
f
o
r
ec
ast
s
.
T
h
e
s
tu
d
ies
p
r
o
v
ed
k
n
o
w
n
f
r
o
m
li
ter
a
tu
r
e
p
h
e
n
o
m
e
n
o
n
t
h
at
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
s
ca
n
b
e
e
f
f
ec
ti
v
e
l
y
u
s
ed
i
n
ta
s
k
s
o
f
f
o
r
ec
asti
n
g
en
er
g
y
g
en
er
atio
n
.
T
h
e
co
m
p
ar
is
o
n
o
f
f
o
r
ec
asts
r
esu
lt
s
o
b
tain
ed
u
s
in
g
SS
N
with
co
n
s
er
v
ati
v
e
m
et
h
o
d
in
d
ic
ates
t
h
at
n
et
w
o
r
k
s
ar
e
m
o
r
e
u
n
i
v
er
s
al.
Fo
r
ec
as
t
ac
cu
r
ac
y
o
f
co
n
s
er
v
at
iv
e
m
et
h
o
d
d
ec
r
ea
s
es a
lo
n
g
w
ith
t
h
e
e
x
ten
s
io
n
o
f
t
i
m
e
p
er
s
p
ec
tiv
e.
Fo
r
ec
ast
ac
cu
r
ac
y
o
f
f
o
r
ec
ast
s
w
it
h
ar
tific
ial
n
e
u
r
al
n
et
w
o
r
k
s
s
tr
o
n
g
l
y
d
ep
en
d
s
o
n
th
e
s
e
lectio
n
o
f
ex
p
lan
ato
r
y
d
ata.
I
n
th
e
a
n
al
y
s
ed
ca
s
e,
t
h
e
i
n
f
lu
e
n
ce
o
f
9
d
if
f
er
e
n
t
d
ata
w
er
e
test
ed
-
it
t
u
r
n
ed
o
u
t
t
h
at
o
n
l
y
w
i
n
d
s
p
ee
d
h
as
a
r
ea
l
im
p
ac
t
o
n
en
er
g
y
g
e
n
er
atio
n
v
o
lu
m
e.
Of
co
u
r
s
e,
it
d
o
es
n
o
t
m
ea
n
t
h
at
o
th
er
th
a
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
3
9
5
7
-
3966
3966
an
al
y
s
ed
d
ata
f
ail
to
in
f
l
u
en
ce
th
e
f
o
r
ec
ast
v
al
u
e.
A
t
t
h
e
s
a
m
e
ti
m
e,
it
ca
n
n
o
t
b
e
eli
m
in
a
t
ed
th
at
b
y
d
if
f
er
en
t
in
p
u
t d
ata
co
d
in
g
,
th
eir
co
r
r
elatio
n
w
it
h
en
er
g
y
p
r
o
d
u
ctio
n
w
il
l i
m
p
r
o
v
e.
T
h
e
q
u
alit
y
o
f
e
x
p
la
n
ato
r
y
d
ata
(
m
ea
s
u
r
e
m
e
n
t
s
)
is
v
er
y
cr
u
cial
f
o
r
th
e
f
o
r
ec
ast
ac
c
u
r
ac
y
.
I
n
ca
s
e
o
f
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
s
,
m
en
d
ac
io
u
s
d
ata
ag
g
r
av
a
te
th
e
tr
ain
in
g
a
n
d
,
r
eg
ar
d
less
o
f
p
r
ed
ictio
n
m
eth
o
d
,
d
is
en
ab
le
co
r
r
ec
t
f
o
r
ec
asts
ev
alu
a
tio
n
.
I
n
ca
s
e
o
f
A
N
N,
r
ed
u
cin
g
t
h
e
r
a
n
g
e
o
f
d
ata
t
o
o
n
e
m
o
n
t
h
h
ad
a
p
o
s
itiv
e
i
m
p
ac
t
o
n
th
e
f
o
r
ec
ast
ac
c
u
r
ac
y
.
T
r
ain
i
n
g
p
er
f
o
r
m
ed
f
o
r
d
ata
f
r
o
m
th
e
w
h
o
le
y
ea
r
a
n
d
,
n
e
x
t,
f
o
r
ec
asti
n
g
th
e
g
e
n
er
atio
n
f
o
r
th
e
w
h
o
le
y
ea
r
g
i
v
es
w
o
r
s
e
r
e
s
u
lt
s
t
h
a
n
tr
ain
in
g
w
i
th
d
ata
f
r
o
m
o
n
e
m
o
n
th
a
n
d
f
o
r
ec
asti
n
g
f
o
r
th
e
s
a
m
e
m
o
n
th
in
f
o
llo
w
i
n
g
y
ea
r
s
.
T
h
e
ch
an
g
es
i
n
t
h
e
t
u
r
b
in
e
o
p
er
atio
n
r
esu
lti
n
g
f
r
o
m
w
ea
t
h
er
an
d
o
p
er
atin
g
co
n
d
it
i
o
n
s
i
n
h
ib
it
th
e
n
e
u
r
al
n
e
t
w
o
r
k
tr
ain
in
g
p
r
o
ce
s
s
,
as
it
s
ee
m
s
th
at
th
e
y
co
u
ld
b
e
p
ar
tly
id
e
n
ti
f
ied
b
y
in
tr
o
d
u
cin
g
ad
d
itio
n
al
ex
p
la
n
ato
r
y
v
ar
iab
les.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
.
S
a
k
th
i
,
e
t
a
l
.
,
"
W
in
d
In
teg
ra
ted
T
h
e
r
m
a
l
Un
it
Co
m
m
it
m
e
n
t
S
o
lu
ti
o
n
u
si
n
g
G
re
y
W
o
lf
Op
ti
m
ize
r,
"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E
)
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
2
3
0
9
-
2
3
2
0
,
2
0
1
7
.
[2
]
D.
S
o
b
c
z
y
ń
sk
i,
"
S
i
m
u
latio
n
stu
d
y
o
f
s
m
a
ll
iso
late
d
p
o
w
e
r
e
le
c
tro
n
ic
c
o
n
v
e
rters
f
o
r
P
V
s
y
ste
m
,
"
2
0
1
6
Pr
o
g
re
ss
in
Ap
p
li
e
d
El
e
c
trica
l
En
g
in
e
e
rin
g
(
PA
EE
)
,
K
o
sc
ielisk
o
-
Zak
o
p
a
n
e
,
p
p
.
1
-
6
,
2
0
1
6
.
[3
]
I
.
M
.
W
a
r
t
a
n
a
,
e
t
a
l
.
,
"
O
p
t
i
m
a
l
I
n
t
e
g
r
a
t
i
o
n
o
f
t
h
e
R
e
n
e
w
a
b
l
e
E
n
e
r
g
y
t
o
t
h
e
G
r
i
d
b
y
C
o
n
s
i
d
e
r
i
n
g
S
m
a
l
l
S
i
g
n
a
l
S
t
a
b
i
l
i
t
y
C
o
n
s
t
r
a
i
n
t
,
"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E
)
,
v
o
l
.
7
,
n
o
.
5
,
p
p
.
2
3
2
9
-
2337
,
2
0
1
7
.
[4
]
D.
Ba
c
z
y
ń
sk
i
a
n
d
P
.
P
io
tr
o
w
sk
i,
"
P
ro
g
n
o
z
o
w
a
n
ie
d
o
b
o
w
e
j
p
ro
d
u
k
c
ji
e
n
e
rg
ii
e
lek
tr
y
c
z
n
e
j
p
rz
e
z
tu
rb
in
ę
w
iatro
w
ą
z
h
o
ry
z
o
n
tem
1
d
o
b
y
,
"
Prze
g
lą
d
El
e
k
tro
tec
h
n
icz
n
y
,
v
o
l.
9
0
,
n
o
.
9
,
p
p
.
1
1
3
-
1
1
7
,
2
0
1
4
.
[5
]
T
.
Ho
ss
a
,
W
.
S
o
k
o
ło
w
sk
a
,
K.,
F
a
b
isz
a
n
d
A
.
,
F
il
ip
o
w
sk
a
,
"
P
ro
g
n
o
z
o
w
a
n
ie
g
e
n
e
ra
c
ji
w
iatro
we
j
z
wy
k
o
rz
y
sta
n
ie
m
m
e
to
d
lo
k
a
ln
y
c
h
i
re
g
re
sji
n
ielin
i
o
w
e
j,
"
Ryn
e
k
e
n
e
rg
ii
,
v
o
l.
1
1
1
,
n
o
.
2
,
p
p
.
6
1
-
6
8
,
2
0
1
4
.
[6
]
G
.
S
i
d
e
ra
to
s
a
n
d
N.D.
Ha
tzia
rg
y
rio
u
,
"
A
n
A
d
v
a
n
c
e
d
S
tatisti
c
a
l
M
e
t
h
o
d
f
o
r
W
in
d
P
o
w
e
r
F
o
re
c
a
stin
g
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Po
we
r
S
y
ste
ms
,
v
o
l.
2
2
,
n
o
.
1
,
p
p
.
2
5
8
-
2
6
5
,
2
0
0
7
.
[7
]
Z.
Ha
n
z
e
lk
a
,
M
.
Du
tk
a
a
n
d
B.
Ś
w
iąte
k
,
"
P
ro
g
n
o
z
o
w
a
n
ie
il
o
śc
i
g
e
n
e
ro
w
a
n
e
j
e
n
e
rg
ii
e
lek
tr
y
c
z
n
e
j
p
r
z
e
z
e
lek
tro
w
n
ie
w
iatro
w
e
z
wy
k
o
rz
y
sta
n
ie
m
sie
c
i
n
e
u
ro
n
o
w
y
c
h
,
"
L
e
o
n
a
rd
o
E
n
e
rg
y
,
p
p
.
1
-
9
,
2
0
1
6
.
[8
]
W
.
Y
.
C
h
a
n
g
,
"
C
o
m
p
a
r
is
o
n
o
f
T
h
r
e
e
S
h
o
r
t
T
e
rm
W
i
n
d
P
o
w
e
r
F
o
r
e
c
a
s
t
i
n
g
,
"
A
d
v
a
n
c
e
d
M
a
t
e
r
i
a
l
s
R
e
se
a
r
c
h
,
v
o
l
.
684
,
p
p
.
6
7
1
-
6
7
5
,
2
0
1
3
.
[9
]
Y.
Ho
n
g
,
T
.
Yu
a
n
d
Ch
.
L
iu
,
"
Ho
u
r
-
A
h
e
a
d
W
in
d
S
p
e
e
d
a
n
d
P
o
w
e
r
F
o
re
c
a
stin
g
Us
in
g
E
m
p
iri
c
a
l
M
o
d
e
De
c
o
m
p
o
siti
o
n
,
"
En
e
rg
ies
,
v
o
l.
6
,
n
o
.
1
2
,
p
p
.
6
1
3
7
-
6
1
5
2
,
2
0
1
3
.
[1
0
]
W
.
Y.
Ch
a
n
g
,
"
S
h
o
rt
-
T
e
r
m
W
in
d
P
o
w
e
r
F
o
re
c
a
stin
g
Us
in
g
th
e
En
h
a
n
c
e
d
P
a
r
ti
c
le
S
w
a
r
m
Op
ti
m
iz
a
ti
o
n
Ba
se
d
H
y
b
rid
M
e
th
o
d
,
"
En
e
rg
ies
,
v
o
l
.
6
,
n
o
.
9
,
p
p
.
4
8
7
9
-
4
8
9
6
,
2
0
1
3
.
[1
1
]
J.
S
h
i
,
J.
M
.
G
u
o
a
n
d
S
.
T
.
Zh
e
n
g
,
"
Ev
a
lu
a
ti
o
n
o
f
H
y
b
rid
F
o
re
c
a
stin
g
A
p
p
ro
a
c
h
e
s
f
o
r
W
in
d
S
p
e
e
d
a
n
d
P
o
w
e
r
G
e
n
e
r
a
ti
o
n
T
im
e
S
e
ries
,
"
Ren
e
wa
b
le a
n
d
S
u
st
a
in
a
b
le E
n
e
rg
y
Rev
ie
ws
,
v
o
l.
1
6
,
n
o
.
5
,
p
p
.
3
4
7
1
-
3
4
8
0
,
2
0
1
2
.
[1
2
]
J.
W
a
n
g
,
e
t
a
l
,
"
Hy
b
rid
f
o
re
c
a
stin
g
m
o
d
e
l
-
b
a
se
d
d
a
ta
m
in
in
g
a
n
d
g
e
n
e
ti
c
a
lg
o
rit
h
m
-
a
d
a
p
ti
v
e
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
isa
ti
o
n
:
a
c
a
se
s
tu
d
y
o
f
w
in
d
sp
e
e
d
ti
m
e
se
rie
s,"
IET
Ren
e
wa
b
le
P
o
we
r
Ge
n
e
ra
ti
o
n
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
2
8
7
-
2
9
8
,
2
0
1
6
.
[1
3
]
Z
.
G
o
m
o
l
k
a
,
E
.
D
u
d
e
k
-
D
y
d
u
c
h
a
n
d
Y
.
K
o
n
d
r
a
t
e
n
k
o
,
"
F
r
o
m
h
o
m
o
g
e
n
e
o
u
s
n
e
t
w
o
r
k
t
o
n
e
u
r
a
l
n
e
t
s
w
i
t
h
f
r
a
c
t
i
o
n
a
l
d
e
r
i
v
a
t
i
v
e
m
e
c
h
a
n
i
s
m
,
"
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
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
S
o
f
t
C
o
m
p
u
t
i
n
g
-
I
C
A
I
S
C
,
v
o
l
.
1
0
2
4
5
,
p
p
.
5
2
-
63
,
2
0
1
7
.
[1
4
]
T
.
Dh
e
rt,
T
.
A
sh
u
ri
a
n
d
J.
M
a
rti
n
s,
"
A
e
ro
d
y
n
a
m
ic
sh
a
p
e
o
p
ti
m
iza
ti
o
n
o
f
w
in
d
tu
rb
in
e
b
lad
e
s
u
si
n
g
a
Re
y
n
o
ld
s
-
a
v
e
ra
g
e
d
Na
v
ier
-
S
to
k
e
s
m
o
d
e
l
a
n
d
a
n
a
d
jo
i
n
t
m
e
th
o
d
,
"
W
in
d
E
n
e
rg
y
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
9
0
9
–
9
2
6
,
2
0
1
6
.
[1
5
]
A
.
B
a
d
a
w
i,
N.
F
.
H
a
sb
u
ll
a
h
a
,
S
.
Yu
so
f
f
,
S
.
Kh
a
n
,
A
.
H
a
sh
i
m
,
A
.
Zy
o
u
d
,
M
.
El
a
m
a
ss
ie,
"
Ev
a
lu
a
ti
o
n
o
f
w
in
d
p
o
w
e
r
f
o
r
e
lec
tri
c
a
l
e
n
e
r
g
y
g
e
n
e
ra
ti
o
n
in
th
e
m
e
d
it
e
rra
n
e
a
n
c
o
a
st
o
f
P
a
les
ti
n
e
f
o
r
1
4
y
e
a
rs,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
2
2
1
2
-
2
2
1
9
,
2
0
1
9
[1
6
]
G
.
K.
V
e
n
a
y
a
g
a
m
o
o
rth
y
,
e
t
a
l
.
,
"
On
e
S
tep
A
h
e
a
d
.
S
h
o
rt
-
T
e
r
m
W
i
n
d
P
o
w
e
r
F
o
re
c
a
stin
g
a
n
d
I
n
telli
g
e
n
t
P
re
d
ictiv
e
C
o
n
tr
o
l
Ba
se
d
o
n
Da
ta A
n
a
ly
ti
c
s,"
IEE
E
Po
we
r a
n
d
En
e
rg
y
M
a
g
a
z
in
e
,
v
o
l.
1
0
,
n
o
.
5
,
p
p
.
7
0
-
7
8
,
2
0
1
2
.
[1
7
]
A
.
A
.
M
o
g
h
a
d
d
a
m
a
n
d
A
.
R.
S
e
i
f
i,
"
S
tu
d
y
o
f
f
o
re
c
a
stin
g
re
n
e
w
a
b
le
e
n
e
rg
ies
in
s
m
a
rt
g
rid
s
u
sin
g
li
n
e
a
r
p
re
d
ictio
v
e
f
il
ters
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s,"
IET
Ren
e
wa
b
le P
o
we
r Ge
n
e
ra
ti
o
n
,
v
o
l.
5
,
n
o
.
6
,
p
p
.
4
7
0
-
4
8
0
,
2
0
1
1
.
[1
8
]
Z.
G
o
m
ó
łk
a
,
e
t
a
l
.
,
"
I
m
p
ro
v
e
m
e
n
t
o
f
Im
a
g
e
P
ro
c
e
ss
in
g
b
y
Us
in
g
Ho
m
o
g
e
n
e
u
s
Ne
u
ra
l
N
e
t
w
o
rk
s
w
it
h
F
ra
c
ti
o
n
a
l
De
riv
a
ti
v
e
s T
h
e
o
re
m
,
"
Dy
n
a
mic
a
l
S
y
ste
ms
,
Diff
e
re
n
ti
a
l
Eq
u
a
ti
o
n
s
a
n
d
Ap
p
lca
t
io
n
s
,
v
o
l
.
3
1
,
p
p
.
5
0
5
-
514
,
2
0
1
1
.
[1
9
]
D.
O.
He
b
b
,
"
T
h
e
o
rg
a
n
iza
ti
o
n
o
f
b
e
h
a
v
io
r,
"
Psy
c
h
o
l
o
g
y
Pre
ss
;
1
e
d
it
io
n
,
1
9
4
9
.
[2
0
]
N.K.
S
in
g
h
,
A
.
K.
S
in
g
h
a
b
d
M
.
T
rip
a
th
y
,
"
S
e
lec
ti
o
n
o
f
h
id
d
e
n
lay
e
r
n
e
u
ro
n
s
a
n
d
b
e
st
train
i
n
g
m
e
th
o
d
f
o
r
F
F
NN
in
a
p
p
li
c
a
ti
o
n
o
f
lo
n
g
term
lo
a
d
f
o
re
c
a
stin
g
,
"
J
o
u
r
n
a
l
o
f
E
lec
trica
l
En
g
in
e
e
rin
g
,
v
o
l.
6
3
,
n
o
.
3
,
p
p
.
1
5
3
-
1
6
1
,
2
0
1
2
.
[2
1
]
J
.
B
a
r
t
m
a
n
,
"
R
e
g
u
ł
a
P
I
D
u
c
z
e
n
i
a
s
z
t
u
c
z
n
y
c
h
n
e
u
r
o
n
ó
w
,
"
M
e
t
o
d
y
I
n
f
o
r
m
a
t
y
k
i
S
t
o
s
o
w
a
n
e
j
,
v
o
l
.
20,
n
o
.
3
,
p
p
.
5
-
19
,
2
0
0
9
.
[2
2
]
A
.
Biele
c
k
i,
"
M
a
th
e
m
a
ti
c
a
l
m
o
d
e
l
o
f
a
rc
h
it
e
c
tu
re
a
n
d
lea
rn
in
g
p
ro
c
e
ss
e
s
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,
"
T
a
sk
q
u
a
rte
rly
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
9
3
–
1
1
4
,
2
0
0
3
.
[2
3
]
W
.
M
a
lsk
a
a
n
d
D.
M
a
z
u
r,
"
A
n
a
l
iza
w
p
ł
y
w
u
p
rę
d
k
o
śc
i
w
iatru
n
a
g
e
n
e
ra
c
ję
m
o
c
y
n
a
p
rz
y
k
ład
z
ie
f
a
r
m
y
w
iatro
w
e
j,
"
Prze
g
lą
d
El
e
k
tro
tec
h
n
icz
n
y
,
v
o
l.
1
,
n
o
.
4
,
p
p
.
5
6
-
5
9
,
2
0
1
7
.
[2
4
]
J.
Ba
rt
m
a
n
,
Z.
,
G
o
m
ó
łk
a
a
n
d
B.
Tw
a
ró
g
,
"
A
NN
tr
a
in
in
g
-
th
e
a
n
a
ly
sis
o
f
th
e
se
lec
ted
p
r
o
c
e
d
u
re
s
in
M
a
tl
a
b
e
n
v
iro
n
m
e
n
t,
"
Co
mp
u
t
in
g
i
n
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
8
8
-
1
0
1
,
2
0
1
5
.
[2
5
]
S
.
B.
A
.
Ka
m
a
ru
d
d
in
,
N.
A
.
M
.
G
h
a
n
i,
H.
A
.
Ra
h
i
m
a
n
d
I.
M
u
sirin
,
"
Kill
e
r
w
h
a
le
-
b
a
c
k
p
ro
p
a
g
a
ti
o
n
(KW
-
BP
)
a
lg
o
rit
h
m
f
o
r
a
c
c
u
ra
c
y
i
m
p
ro
v
e
m
e
n
t
o
f
n
e
u
ra
l
n
e
tw
o
rk
f
o
re
c
a
sti
n
g
m
o
d
e
ls
o
n
e
n
e
rg
y
e
ff
icie
n
t
d
a
t
a
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
IJ
A
-
AI)
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
2
7
0
-
2
7
7
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.