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
s
(
I
J
P
E
DS)
Vo
l.
1
6
,
No
.
1
,
Ma
r
ch
20
2
5
,
p
p
.
5
3
8
~
5
4
5
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
1
6
.i
1
.
p
p
5
3
8
-
545
538
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
Co
mpa
ra
tive a
na
ly
sis
of wind
sp
ee
d predic
tion:
enh
a
ncing
a
ccuracy
using
P
CA and li
nea
r re
g
ress
io
n vs
.
G
P
R,
SVR,
a
nd RNN
So
m
a
s
un
da
ra
m
Dee
pa
1
,
J
a
y
a
nthi A
rum
ug
a
m
2
,
Ra
g
ura
m
a
n P
urus
ho
t
ha
m
a
n
3
,
D.
N
a
g
eswa
ri
4
,
L
.
Ra
j
a
s
ek
ha
ra
B
a
bu
5
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
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
V
e
l
a
mm
a
l
En
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
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
&
En
g
i
n
e
e
r
i
n
g
-
(
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
)
,
M
a
d
a
n
a
p
a
l
l
e
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
&
S
c
i
e
n
c
e
,
M
a
d
a
n
a
p
a
l
l
e
,
I
n
d
i
a
4
D
e
p
a
r
t
m
e
n
t
o
f
S
c
i
e
n
c
e
a
n
d
H
u
m
a
n
i
t
i
e
s
(
G
e
n
e
r
a
l
E
n
g
i
n
e
e
r
i
n
g
-
EE
E)
,
R
.
M
.
K
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
T
h
i
r
u
v
a
l
l
u
r
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
o
n
e
r
u
L
a
k
sh
m
a
i
a
h
E
d
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
V
a
d
d
e
sw
a
r
a
m
,
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
J
u
l 1
0
,
2
0
2
4
R
ev
is
ed
Oct
9
,
2
0
2
4
Acc
ep
ted
Oct
2
3
,
2
0
2
4
F
o
r
p
o
we
r
sy
ste
m
s
with
sig
n
ifi
c
a
n
t
win
d
p
o
we
r
in
teg
ra
ti
o
n
to
o
p
e
ra
te
in
a
n
e
fficie
n
t
a
n
d
d
e
p
e
n
d
a
b
le
m
a
n
n
e
r,
win
d
sp
e
e
d
p
re
d
icti
o
n
a
c
c
u
ra
c
y
is
c
ru
c
ial.
F
a
c
to
rs
su
c
h
a
s
tem
p
e
ra
tu
re
,
h
u
m
id
it
y
,
a
ir
p
re
ss
u
re
,
a
n
d
win
d
in
te
n
sity
h
e
a
v
il
y
in
f
lu
e
n
c
e
wi
n
d
sp
e
e
d
,
a
d
d
in
g
c
o
m
p
lex
it
y
to
th
e
p
re
d
icti
o
n
p
ro
c
e
ss
.
Th
is
p
a
p
e
r
i
n
tro
d
u
c
e
s
a
m
e
th
o
d
fo
r
wi
n
d
sp
e
e
d
fo
re
c
a
stin
g
t
h
a
t
u
ti
li
z
e
s
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
sis
(P
CA)
to
re
d
u
c
e
d
ime
n
si
o
n
a
li
t
y
a
n
d
li
n
e
a
r
re
g
re
ss
io
n
f
o
r
t
h
e
p
re
d
icti
o
n
m
o
d
e
l.
P
CA
is
e
m
p
l
o
y
e
d
to
id
e
n
ti
fy
k
e
y
fe
a
tu
re
s
fro
m
t
h
e
e
x
ten
siv
e
m
e
teo
ro
lo
g
ica
l
d
a
ta,
w
h
ich
a
re
su
b
se
q
u
e
n
tl
y
u
se
d
a
s
in
p
u
ts
f
o
r
t
h
e
Li
n
e
a
r
Re
g
re
ss
io
n
m
o
d
e
l
to
e
stim
a
te
win
d
s
p
e
e
d
.
T
h
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
is
tes
ted
u
si
n
g
p
u
b
li
c
l
y
a
v
a
il
a
b
le
m
e
teo
ro
l
o
g
ica
l
d
a
ta,
fo
c
u
sin
g
o
n
v
a
riab
les
su
c
h
a
s
tem
p
e
ra
tu
re
,
a
ir
p
re
ss
u
re
,
a
n
d
h
u
m
id
i
ty
.
P
o
p
u
lar
m
o
d
e
ls
li
k
e
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
rk
s
(RNN
),
su
p
p
o
rt
v
e
c
t
o
r
re
g
re
ss
io
n
(S
VR),
a
n
d
G
a
u
ss
ia
n
p
r
o
c
e
ss
re
g
re
ss
io
n
(G
P
R)
a
re
u
se
d
to
c
o
m
p
a
re
it
s
p
e
rfo
rm
a
n
c
e
.
Ev
a
lu
a
t
io
n
m
e
tri
c
s
su
c
h
a
s
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
a
n
d
R²
a
re
u
se
d
to
m
e
a
su
re
e
ffe
c
ti
v
e
n
e
ss
.
Re
su
lt
s
sh
o
w
th
a
t
th
e
P
CA
c
o
m
b
in
e
d
wit
h
Li
n
e
a
r
Re
g
re
ss
io
n
m
o
d
e
l
y
iel
d
s
m
o
re
a
c
c
u
ra
te
p
re
d
ictio
n
s,
wi
th
a
n
RM
S
E
o
f
9
4
.
1
1
a
n
d
R²
o
f
0
.
9
7
5
5
,
su
r
p
a
ss
in
g
th
e
G
P
R,
S
VR,
a
n
d
RNN
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
E
n
er
g
y
m
an
ag
e
m
en
t
Ma
ch
in
e
lear
n
in
g
Per
f
o
r
m
an
ce
m
etr
ics
R
eg
r
ess
io
n
m
o
d
el
R
en
ewa
b
le
en
er
g
y
W
in
d
s
y
s
tem
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
:
So
m
asu
n
d
ar
am
Dee
p
a
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,
I
n
d
ia
E
m
ail:
d
ee
_
s
o
m
s
1
2
3
@
y
ah
o
o
.
co
.
in
1.
I
NT
RO
D
UCT
I
O
N
W
in
d
p
o
wer
h
as
b
ec
o
m
e
a
c
r
u
cial
s
o
u
r
ce
o
f
r
en
ewa
b
le
e
n
er
g
y
,
ex
p
e
r
ien
cin
g
s
ig
n
if
ica
n
t
g
r
o
wth
wo
r
ld
wid
e.
B
y
2
0
1
8
,
g
lo
b
al
in
s
talled
win
d
p
o
wer
ca
p
ac
ity
h
ad
r
ea
ch
ed
5
9
2
GW
,
with
ex
p
ec
tatio
n
s
to
s
u
r
p
ass
8
0
0
GW
b
y
2
0
2
1
[1
]
-
[
5
]
.
A
k
ey
ch
allen
g
e
f
o
r
win
d
en
er
g
y
p
r
o
d
u
ctio
n
is
th
e
v
ar
iab
ilit
y
a
n
d
u
n
p
r
ed
ictab
ilit
y
o
f
win
d
s
p
ee
d
,
wh
ich
d
ir
ec
tl
y
im
p
ac
ts
th
e
ef
f
icien
c
y
an
d
in
teg
r
atio
n
o
f
win
d
en
er
g
y
in
to
p
o
we
r
g
r
id
s
.
Acc
u
r
ate
win
d
s
p
ee
d
f
o
r
ec
asti
n
g
is
ess
en
tial
f
o
r
o
p
tim
izin
g
p
o
wer
s
y
s
tem
s
,
m
ain
tain
in
g
g
r
id
s
tab
ilit
y
,
an
d
m
ax
im
izin
g
th
e
ec
o
n
o
m
ic
b
en
ef
its
o
f
win
d
en
er
g
y
[6
]
-
[
8
]
.
Ho
wev
er
,
th
e
u
n
p
r
ed
ictab
le
n
atu
r
e
o
f
win
d
s
p
ee
d
m
ak
es r
eliab
le
f
o
r
ec
asti
n
g
a
c
o
m
p
lex
task
,
r
eq
u
ir
in
g
ad
v
an
c
ed
m
eth
o
d
s
to
en
s
u
r
e
ac
c
u
r
ac
y
[9
]
,
[
1
0
]
.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f wi
n
d
s
p
ee
d
p
r
ed
ictio
n
:
e
n
h
a
n
cin
g
a
cc
u
r
a
cy
u
s
in
g
P
C
A
…
(
S
o
ma
s
u
n
d
a
r
a
m
Dee
p
a
)
539
Sev
er
al
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
d
ev
elo
p
ed
,
ea
c
h
with
its
ad
v
an
tag
es
an
d
lim
itatio
n
s
.
Ph
y
s
ical
m
o
d
els,
s
u
ch
as
n
u
m
er
ical
wea
th
er
p
r
ed
ictio
n
(
NW
P),
u
tili
ze
co
m
p
lex
m
ath
em
atica
l
eq
u
atio
n
s
to
s
im
u
late
atm
o
s
p
h
er
ic
d
y
n
am
i
cs
an
d
p
r
e
d
ict
win
d
p
atter
n
s
.
W
h
ile
th
ese
m
o
d
els
ca
n
p
r
o
v
id
e
h
ig
h
ac
cu
r
ac
y
,
th
ey
d
e
m
an
d
s
ig
n
if
ican
t
c
o
m
p
u
tatio
n
al
r
eso
u
r
ce
s
an
d
h
ig
h
-
q
u
ality
d
ata,
m
ak
in
g
th
em
less
s
u
itab
le
f
o
r
s
h
o
r
t
-
ter
m
o
r
r
ea
l
-
tim
e
p
r
e
d
ictio
n
s
.
Ad
d
itio
n
ally
,
NW
P
m
o
d
els
m
ay
p
er
f
o
r
m
p
o
o
r
ly
in
ar
ea
s
with
u
n
p
r
ed
ictab
le
wea
th
er
p
atter
n
s
[
1
1
]
-
[
1
4
]
.
On
th
e
o
th
e
r
h
a
n
d
,
s
tatis
tical
m
eth
o
d
s
,
in
cl
u
d
in
g
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e
o
r
AR
I
MA
,
Kalm
an
f
ilter
s
,
an
d
Gau
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
(
GPR
)
,
u
s
e
h
is
to
r
ical
d
ata
to
m
ak
e
s
h
o
r
t
-
ter
m
f
o
r
ec
asts
ef
f
icien
tly
.
Ho
wev
er
,
t
h
ey
o
f
ten
s
tr
u
g
g
le
to
m
o
d
el
n
o
n
lin
ea
r
r
el
atio
n
s
h
ip
s
b
etwe
en
v
ar
iab
les,
wh
ich
lim
its
th
eir
lo
n
g
-
ter
m
f
o
r
ec
asti
n
g
ca
p
ab
ilit
ies
[
1
5
]
-
[
1
7
]
.
Ma
ch
in
e
lear
n
in
g
a
p
p
r
o
ac
h
es,
s
u
ch
as
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
,
b
ac
k
p
r
o
p
ag
at
io
n
n
eu
r
a
l
n
etwo
r
k
s
(
B
PNNs
)
,
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs),
h
av
e
g
ain
ed
p
o
p
u
lar
ity
f
o
r
p
r
e
d
ictin
g
win
d
s
p
ee
d
d
u
e
to
th
eir
ca
p
ac
ity
to
lear
n
co
m
p
licated
,
n
o
n
lin
ea
r
c
o
r
r
e
latio
n
s
f
r
o
m
h
u
g
e
d
atasets
[
1
8
]
-
[
2
1
]
.
R
NNs,
in
p
ar
ticu
lar
,
h
av
e
d
e
m
o
n
s
tr
ate
d
ef
f
ec
tiv
en
ess
in
id
en
tify
in
g
tem
p
o
r
al
d
ep
e
n
d
en
cies
in
win
d
d
ata,
h
en
ce
en
h
an
cin
g
f
o
r
ec
ast
ac
cu
r
ac
y
.
Ho
wev
er
,
th
ese
m
o
d
els
ar
e
s
o
m
etim
es
r
eg
ar
d
e
d
as
"b
lack
b
o
x
es,"
p
r
o
v
i
d
in
g
litt
le
in
ter
p
r
etab
ilit
y
in
to
h
o
w
p
ar
ticu
lar
m
eteo
r
o
lo
g
ical
co
n
d
itio
n
s
in
f
lu
e
n
ce
win
d
s
p
ee
d
.
Fu
r
th
e
r
m
o
r
e,
m
ac
h
in
e
lear
n
in
g
m
o
d
els
r
eq
u
ir
e
s
ig
n
if
ican
t
co
m
p
u
tatio
n
a
l
r
eso
u
r
ce
s
an
d
h
u
g
e
d
atasets
,
wh
ich
m
ig
h
t
b
e
d
if
f
icu
lt f
o
r
r
ea
l
-
tim
e
o
r
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
ap
p
licatio
n
s
.
T
o
o
v
er
c
o
m
e
th
ese
is
s
u
es,
a
h
y
b
r
id
win
d
s
p
ee
d
p
r
ed
icti
o
n
m
eth
o
d
u
s
in
g
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
an
d
lin
ea
r
r
eg
r
ess
io
n
is
p
r
esen
ted
.
PC
A
r
ed
u
ce
s
th
e
d
im
en
s
io
n
ality
o
f
m
et
eo
r
o
lo
g
ical
d
ata
b
y
elim
in
atin
g
r
ed
u
n
d
an
t
f
ea
tu
r
e
s
,
f
o
cu
s
in
g
o
n
th
e
m
o
s
t
cr
iti
ca
l
f
ac
to
r
s
in
f
lu
en
cin
g
win
d
s
p
ee
d
.
Usi
n
g
th
is
s
tr
ea
m
lin
ed
d
ataset,
lin
ea
r
r
eg
r
ess
io
n
ef
f
icien
tly
p
r
ed
icts
wi
n
d
s
p
ee
d
wh
ile
m
ain
tain
in
g
a
cc
u
r
ac
y
[
2
2
]
,
[
2
3
]
.
T
h
is
ap
p
r
o
ac
h
is
co
m
p
u
tatio
n
ally
ef
f
icien
t,
in
ter
p
r
etab
le,
a
n
d
ca
p
ab
le
o
f
m
an
a
g
in
g
m
u
lt
ico
llin
ea
r
ity
in
th
e
in
p
u
t
d
ata.
C
o
m
p
ar
ed
to
m
o
r
e
co
m
p
lex
m
o
d
els
lik
e
GPR
,
s
u
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
(
SVR
)
,
an
d
R
NN,
th
e
PC
A
-
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
o
f
f
er
s
a
b
ala
n
ce
d
s
o
lu
tio
n
,
co
m
b
in
in
g
e
f
f
icien
cy
,
ac
cu
r
ac
y
,
an
d
in
ter
p
r
etab
ilit
y
,
m
ak
in
g
it a
p
r
ac
tical
ch
o
ice
f
o
r
win
d
s
p
ee
d
f
o
r
ec
asti
n
g
.
2.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
s
u
g
g
ested
win
d
s
p
ee
d
p
r
e
d
ictio
n
ap
p
r
o
ac
h
is
d
iv
id
e
d
in
t
o
f
o
u
r
m
ajo
r
s
tag
es:
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
u
s
i
n
g
PC
A,
win
d
s
p
ee
d
p
r
e
d
ictio
n
u
s
in
g
a
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el,
an
d
m
o
d
el
ev
alu
atio
n
.
Fig
u
r
e
1
d
ep
icts
th
e
o
v
er
all
p
r
o
ce
d
u
r
e,
wh
ile
ea
c
h
s
tag
e
is
d
is
cu
s
s
ed
in
d
etail
b
elo
w.
2
.
1
.
Da
t
a
pre
-
pro
ce
s
s
ing
-
Data
co
llectio
n
an
d
d
ata
n
o
r
m
aliza
tio
n
:
T
h
e
d
ataset
co
n
s
is
ts
o
f
h
is
to
r
i
ca
l
m
eteo
r
o
lo
g
ical
d
ata,
in
clu
d
in
g
air
p
r
ess
u
r
e,
h
u
m
id
ity
,
te
m
p
er
atu
r
e
an
d
win
d
s
p
ee
d
.
T
h
ese
f
ac
t
o
r
s
s
ig
n
if
ican
tly
in
f
lu
en
ce
win
d
s
p
ee
d
,
m
ak
in
g
th
em
cr
itical
f
o
r
ac
cu
r
ate
win
d
s
p
ee
d
p
r
ed
ictio
n
.
T
o
en
s
u
r
e
t
h
at
all
f
ea
tu
r
es
ar
e
o
n
a
co
m
p
ar
ab
le
s
ca
le,
th
e
d
ata
is
n
o
r
m
alize
d
u
s
in
g
th
e
Min
Ma
x
Scaler
,
wh
ich
tr
an
s
f
o
r
m
s
ea
ch
f
ea
tu
r
e
in
to
th
e
r
an
g
e
[
0
,
1
]
.
No
r
m
aliza
tio
n
h
elp
s
t
h
e
m
o
d
el
lear
n
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
v
ar
i
ab
les
b
y
p
r
e
v
en
tin
g
f
ea
tu
r
es
with
b
r
o
a
d
er
r
an
g
es
f
r
o
m
c
o
n
tr
o
llin
g
th
e
lear
n
in
g
p
r
o
ce
s
s
[
2
4
]
,
[
2
5
]
.
T
h
is
is
h
o
w
th
e
n
o
r
m
aliza
tio
n
is
ca
r
r
ied
o
u
t
,
as in
(
1
)
.
Xn
o
r
m
=
X
−
X
m
i
n
X
m
ax
−
X
m
i
n
(
1
)
W
h
er
e
X
is
th
e
o
r
ig
in
al
d
ata,
Xm
in
an
d
Xm
ax
ar
e
th
e
m
in
i
m
u
m
an
d
m
ax
im
u
m
v
alu
es o
f
X
,
r
esp
ec
tiv
ely
.
2
.
2
.
Dim
ens
io
na
lity
re
du
ct
io
n
-
PC
A
T
h
e
n
o
r
m
alize
d
m
eteo
r
o
lo
g
ic
al
d
ata'
s
d
im
en
s
io
n
ality
is
d
ec
r
ea
s
ed
b
y
th
e
u
s
e
o
f
PC
A.
PC
A
r
em
o
v
es
u
n
n
ec
ess
ar
y
in
f
o
r
m
atio
n
f
r
o
m
th
e
o
r
ig
in
al
d
ata
wh
ile
p
r
eser
v
in
g
th
e
m
ajo
r
ity
o
f
its
v
ar
iatio
n
b
y
co
n
v
er
tin
g
it
in
to
a
s
et
o
f
u
n
co
r
r
elate
d
p
r
i
n
cip
al
co
m
p
o
n
en
ts
.
T
h
is
s
tep
r
e
d
u
ce
s
th
e
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
o
f
th
e
m
o
d
el
wh
ile
p
r
eser
v
in
g
ess
en
tial in
f
o
r
m
atio
n
f
o
r
win
d
s
p
ee
d
p
r
e
d
ic
tio
n
.
T
h
e
tr
a
n
s
f
o
r
m
atio
n
is
d
ef
in
ed
as
in
(
2
)
:
Z
=X
norm
.W
(
2)
T
h
e
m
ajo
r
co
m
p
o
n
e
n
t
m
atr
ix
is
Z
,
th
e
n
o
r
m
alize
d
d
ata
m
a
tr
ix
is
Xn
o
r
m
,
an
d
th
e
ei
g
en
v
ec
to
r
m
atr
ix
is
W
.
T
h
e
n
u
m
b
er
o
f
p
r
in
cip
le
c
o
m
p
o
n
e
n
ts
p
r
eser
v
ed
is
d
eter
m
in
ed
b
y
t
h
e
to
tal
ex
p
lain
e
d
v
ar
ian
ce
.
T
y
p
ically
,
co
m
p
o
n
en
ts
ac
co
u
n
tin
g
f
o
r
9
5
%
o
f
th
e
to
tal
v
ar
ian
ce
ar
e
ch
o
s
en
to
s
tr
ik
e
a
b
alan
ce
b
etwe
en
d
im
en
s
io
n
ality
r
ed
u
ctio
n
a
n
d
in
f
o
r
m
atio
n
r
ete
n
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
6
,
No
.
1
,
Ma
r
c
h
20
2
5
:
538
-
545
540
2
.
3
.
Wind
s
peed
pre
dict
io
n
-
L
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
T
h
e
r
e
d
u
ce
d
f
ea
tu
r
e
s
et
o
b
tain
ed
f
r
o
m
PC
A
is
u
s
ed
as
in
p
u
t
f
o
r
th
e
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el.
L
in
ea
r
r
eg
r
ess
io
n
estab
lis
h
es
a
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
th
e
p
r
in
cip
al
co
m
p
o
n
en
ts
an
d
th
e
win
d
s
p
ee
d
,
wh
ich
is
ex
p
r
ess
ed
b
y
t
h
e
(
3
)
:
y
=
0
+
∑
=
1
(
3
)
w
h
er
e
y
is
th
e
p
r
ed
icted
win
d
s
p
ee
d
Z
i
ar
e
th
e
p
r
in
ci
p
al
co
m
p
o
n
e
n
ts
,
an
d
β
i
ar
e
th
e
r
eg
r
e
s
s
io
n
co
ef
f
icien
ts
.
2
.
4
.
M
o
del
ev
a
lua
t
io
n
T
h
e
d
ataset
is
s
p
lit
7
5
-
2
5
,
with
7
5
%
u
tili
ze
d
f
o
r
m
o
d
e
l
tr
ain
in
g
a
n
d
2
5
%
f
o
r
test
in
g
.
C
r
o
s
s
-
v
alid
atio
n
m
eth
o
d
s
s
u
ch
as
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
ar
e
u
s
ed
to
ev
alu
ate
m
o
d
el
r
o
b
u
s
tn
ess
an
d
r
ed
u
ce
o
v
er
f
itti
n
g
.
Me
tr
ics
lik
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(M
SE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
e
r
r
o
r
(
MA
E
)
,
an
d
R
²
a
r
e
u
s
ed
to
ass
ess
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
i
n
clu
d
in
g
p
r
e
d
ictio
n
ac
cu
r
ac
y
an
d
f
it.
MSE
m
ea
s
u
r
es
th
e
av
er
ag
e
o
f
s
q
u
ar
ed
e
r
r
o
r
s
,
wh
er
ea
s
R
²
ev
alu
ates
th
e
m
o
d
el'
s
ab
ilit
y
to
ex
p
lain
v
ar
ian
ce
in
d
ata.
T
h
e
f
o
llo
win
g
m
ea
s
u
r
es
ex
am
i
n
e
th
e
ef
f
ec
tiv
en
ess
o
f
r
eg
r
ess
io
n
m
o
d
els,
an
d
th
e
f
o
llo
win
g
m
etr
ics
wer
e
u
s
ed
to
ev
alu
ate
p
er
f
o
r
m
an
c
e.
Fig
u
r
e
1
d
ep
icts
th
e
b
lo
ck
d
i
ag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
win
d
s
p
ee
d
p
r
ed
icti
o
n
p
r
o
ce
s
s
en
tails
g
ath
er
in
g
h
is
to
r
ical
m
eteo
r
o
lo
g
ical
d
ata
(
tem
p
er
atu
r
e,
h
u
m
id
ity
,
air
p
r
ess
u
r
e,
a
n
d
win
d
s
p
ee
d
)
an
d
n
o
r
m
alizin
g
it
with
Min
Ma
x
S
ca
ler
to
ass
u
r
e
f
ea
tu
r
e
c
o
m
p
ar
ab
ilit
y
.
T
h
e
d
ata
is
th
en
d
i
v
id
ed
in
to
tr
ain
in
g
a
n
d
test
s
ets.
PC
A
is
u
s
ed
to
r
e
d
u
ce
d
im
en
s
io
n
ality
b
y
r
etai
n
in
g
t
h
e
m
o
s
t
im
p
o
r
tan
t
f
ea
t
u
r
es
an
d
r
em
o
v
in
g
r
ed
u
n
d
an
t
in
f
o
r
m
atio
n
.
A
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
is
tr
ain
ed
o
n
th
e
PC
A
-
tr
an
s
f
o
r
m
ed
f
ea
tu
r
es
to
f
o
r
ec
ast
win
d
s
p
ee
d
.
T
h
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
o
n
th
e
test
in
g
s
et
is
ass
ess
ed
u
s
in
g
th
e
R
MSE
an
d
R
-
s
q
u
ar
ed
m
et
r
ics.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
p
r
o
p
o
s
ed
m
eth
o
d
2
.
5
.
Co
m
pa
riso
n wit
h
o
t
her
m
et
ho
ds
T
o
ass
ess
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
PC
A
-
lin
ea
r
r
eg
r
ess
io
n
ap
p
r
o
ac
h
,
it
is
co
m
p
ar
ed
with
s
ev
er
al
wid
ely
ad
o
p
ted
win
d
s
p
ee
d
p
r
e
d
ictio
n
m
eth
o
d
s
,
s
u
ch
as GPR
,
SV
R
,
an
d
R
NN
.
-
Gau
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
(
GPR
)
:
GP
R
is
a
p
r
o
b
ab
ilis
tic
m
o
d
el
th
at
p
r
o
v
id
es
a
f
le
x
ib
le,
n
o
n
-
lin
ea
r
r
eg
r
ess
io
n
ap
p
r
o
ac
h
b
ased
o
n
Gau
s
s
ian
d
is
tr
ib
u
tio
n
s
.
I
t is k
n
o
wn
f
o
r
its
ab
ilit
y
to
q
u
a
n
tify
u
n
ce
r
tain
ty
in
p
r
ed
ictio
n
s
b
u
t c
an
b
e
co
m
p
u
t
atio
n
ally
in
ten
s
iv
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f wi
n
d
s
p
ee
d
p
r
ed
ictio
n
:
e
n
h
a
n
cin
g
a
cc
u
r
a
cy
u
s
in
g
P
C
A
…
(
S
o
ma
s
u
n
d
a
r
a
m
Dee
p
a
)
541
-
Su
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
S
VR
)
:
SV
R
co
n
s
tr
u
cts
a
h
y
p
er
p
lan
e
in
a
h
ig
h
-
d
im
en
s
io
n
al
s
p
ac
e
to
m
o
d
el
th
e
r
elatio
n
s
h
ip
b
etwe
en
in
p
u
t
f
ea
tu
r
es
an
d
win
d
s
p
ee
d
.
I
t
is
ef
f
ec
tiv
e
in
ca
p
tu
r
i
n
g
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
b
u
t r
e
q
u
ir
es c
ar
e
f
u
l tu
n
in
g
o
f
h
y
p
er
p
ar
a
m
eter
s
.
-
R
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NN)
:
R
ec
u
r
r
en
t
n
eu
r
al
n
et
wo
r
k
s
(
R
NNs),
p
ar
ticu
lar
ly
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
m
o
d
els,
ar
e
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
tim
e
-
s
er
ies
p
r
ed
ictio
n
d
u
e
to
th
eir
ca
p
a
b
ilit
y
to
lear
n
an
d
r
etain
tem
p
o
r
al
p
atter
n
s
with
in
s
eq
u
en
tial
d
ata.
Ho
we
v
er
,
th
ey
ca
n
b
e
r
eso
u
r
ce
-
in
te
n
s
iv
e
an
d
o
f
te
n
r
eq
u
ir
e
s
u
b
s
tan
tial
d
atasets
to
ac
h
iev
e
o
p
tim
al
p
e
r
f
o
r
m
an
ce
to
ac
h
iev
e
a
f
air
co
m
p
a
r
is
o
n
,
a
ll
ap
p
r
o
ac
h
es'
p
er
f
o
r
m
an
ce
is
test
ed
with
t
h
e
s
am
e
d
ataset
a
n
d
m
etr
ics
(
R
MSE
an
d
R
²)
.
T
h
e
f
in
d
i
n
g
s
s
h
o
w
t
h
at
th
e
PC
A
-
lin
ea
r
r
eg
r
ess
io
n
s
tr
ateg
y
s
u
r
p
ass
es
th
e
o
th
er
m
eth
o
d
s
in
ter
m
s
o
f
b
o
t
h
ac
cu
r
ac
y
a
n
d
co
m
p
u
tin
g
ec
o
n
o
m
y
,
esp
ec
ially
wh
en
d
ea
lin
g
with
h
ig
h
-
d
im
en
s
io
n
al
m
eteo
r
o
lo
g
ical
d
ata
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lts
f
r
o
m
th
e
lin
ea
r
r
e
g
r
ess
io
n
m
o
d
el,
in
cl
u
d
in
g
p
r
e
d
icted
an
d
ac
tu
al
ac
tiv
e
p
o
we
r
v
alu
es
f
o
r
b
o
th
th
e
t
r
ain
in
g
a
n
d
test
in
g
d
ata,
ar
e
v
is
u
alize
d
i
n
th
e
p
lo
t
is
s
h
o
wn
in
F
ig
u
r
e
2
.
T
r
ai
n
in
g
d
ata:
th
e
ac
tu
al
ac
tiv
e
p
o
wer
(
s
h
o
w
n
in
b
l
u
e)
an
d
p
r
e
d
icted
ac
tiv
e
p
o
wer
(
o
r
an
g
e)
a
r
e
p
lo
tted
o
v
er
tim
e.
T
h
e
m
o
d
el
f
its
th
e
tr
ain
in
g
d
ata
well,
in
d
icatin
g
th
at
t
h
e
r
e
g
r
ess
io
n
m
o
d
el
h
as
lear
n
ed
th
e
u
n
d
er
ly
in
g
r
el
atio
n
s
h
ip
b
etwe
en
m
eteo
r
o
lo
g
ical
f
ea
tu
r
es
an
d
t
h
e
tar
g
et
v
ar
iab
le.
T
esti
n
g
d
a
ta
th
e
ac
tu
al
ac
tiv
e
p
o
wer
(
g
r
ee
n
)
an
d
p
r
e
d
icted
ac
tiv
e
p
o
wer
(
r
e
d
)
ar
e
p
lo
tt
ed
f
o
r
th
e
test
in
g
p
e
r
io
d
.
T
h
e
p
r
ed
ictio
n
s
clo
s
ely
f
o
llo
w
th
e
ac
tu
al
d
ata,
d
em
o
n
s
tr
atin
g
t
h
e
m
o
d
el'
s
ab
il
ity
to
g
en
er
alize
t
o
n
ew,
u
n
s
ee
n
d
ata.
Fig
u
r
e
2
.
S
h
o
ws th
e
ac
tiv
e
p
o
wer
p
r
ed
ictio
n
f
o
r
tr
ain
in
g
a
n
d
test
in
g
d
ata
T
h
e
u
p
d
ated
co
d
e
in
clu
d
es
v
is
u
aliza
tio
n
s
f
o
r
ac
tiv
e
p
o
wer
p
r
ed
ictio
n
,
e
n
h
an
ci
n
g
u
n
d
er
s
t
an
d
in
g
o
f
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
Fig
u
r
e
3
s
h
o
ws
b
o
th
ac
tu
al
an
d
p
r
ed
i
cted
ac
tiv
e
p
o
wer
v
alu
es
f
o
r
tr
ain
in
g
an
d
test
in
g
d
ata,
with
co
n
f
id
e
n
ce
in
ter
v
al
s
in
d
icate
d
b
y
s
h
ad
ed
ar
ea
s
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
d
is
tr
ib
u
tio
n
o
f
r
esid
u
als,
co
m
p
ar
in
g
tr
ain
in
g
a
n
d
test
in
g
r
esid
u
als
with
Ker
n
el
d
en
s
ity
esti
m
atio
n
o
r
KDE
.
T
h
ese
p
lo
ts
p
r
o
v
id
e
in
s
ig
h
ts
in
to
p
r
e
d
ictio
n
ac
c
u
r
ac
y
an
d
t
h
e
r
esid
u
als'
d
is
tr
ib
u
tio
n
,
h
ig
h
lig
h
tin
g
th
e
m
o
d
el'
s
r
eliab
ilit
y
an
d
ar
ea
s
wh
er
e
it
m
ig
h
t
b
e
im
p
r
o
v
ed
.
I
n
th
is
s
t
u
d
y
,
we
in
v
esti
g
ated
th
e
p
er
f
o
r
m
an
ce
o
f
f
o
u
r
d
is
tin
ct
ap
p
r
o
ac
h
es
f
o
r
p
r
ed
ictin
g
win
d
s
p
ee
d
:
PC
A
+
l
in
ea
r
r
eg
r
ess
io
n
,
GPR
,
SV
R
,
an
d
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
.
T
h
e
t
r
ain
in
g
an
d
test
in
g
d
atasets
wer
e
co
m
p
ar
e
d
u
s
in
g
th
e
p
e
r
f
o
r
m
an
ce
m
ea
s
u
r
es
R
MSE
an
d
co
e
f
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
²)
.
T
h
e
f
in
d
in
g
s
ar
e
s
u
m
m
ar
ized
in
T
a
b
le
1
.
Fig
u
r
e
5
d
is
p
lay
s
a
c
o
m
p
ar
is
o
n
o
f
d
if
f
er
en
t a
lg
o
r
ith
m
s
.
T
ab
le
1
.
Sh
o
ws th
e
c
o
m
p
ar
is
o
n
o
f
d
if
f
er
e
n
t a
lg
o
r
ith
m
M
e
t
h
o
d
R
M
S
E
(
Tr
a
i
n
i
n
g
S
e
t
)
R
² (Tr
a
i
n
i
n
g
S
e
t
)
R
M
S
E
(
Te
s
t
i
n
g
S
e
t
)
R
² (Tes
t
i
n
g
S
e
t
)
P
C
A
+
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
9
5
.
5
9
0
.
9
7
4
5
9
4
.
1
1
0
.
9
7
5
5
G
a
u
ss
i
a
n
p
r
o
c
e
ss re
g
r
e
ss
i
o
n
(
G
P
R
)
9
6
.
6
5
0
.
9
7
3
0
9
6
.
4
0
0
.
9
7
3
9
S
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
(
S
V
R
)
9
4
.
5
2
0
.
9
6
8
1
9
9
.
0
2
0
.
9
6
9
2
R
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
(
R
N
N
)
9
4
.
8
7
0
.
9
7
5
4
9
2
.
1
2
0
.
9
7
5
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
6
,
No
.
1
,
Ma
r
c
h
20
2
5
:
538
-
545
542
Fig
u
r
e
3
.
S
h
o
ws th
e
ac
tu
al
p
o
wer
p
r
ed
ictio
n
with
co
n
f
i
d
en
c
e
lev
el
Fig
u
r
e
4
.
S
h
o
ws th
e
d
is
tr
ib
u
tio
n
o
f
r
esid
u
als
-
PC
A
+
lin
ea
r
r
eg
r
ess
io
n
:
T
h
e
co
m
b
in
e
d
m
eth
o
d
o
f
PC
A
an
d
lin
ea
r
r
eg
r
ess
io
n
d
em
o
n
s
tr
ated
s
u
p
er
io
r
o
v
er
all
p
e
r
f
o
r
m
an
ce
,
with
an
R
MSE
o
f
9
5
.
5
9
o
n
t
h
e
tr
ain
in
g
d
ata
an
d
9
4
.
1
1
o
n
th
e
test
d
ata.
Ad
d
itio
n
ally
,
th
e
R
²
v
alu
es
wer
e
0
.
9
7
4
5
f
o
r
tr
ai
n
in
g
a
n
d
0
.
9
7
5
5
f
o
r
test
in
g
,
in
d
icatin
g
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
an
d
s
tr
o
n
g
g
en
e
r
aliza
tio
n
to
n
ew
d
ata.
T
h
e
in
teg
r
atio
n
o
f
PC
A
ef
f
ec
tiv
ely
r
ed
u
ce
d
i
n
p
u
t
d
im
en
s
io
n
ality
,
en
h
an
ci
n
g
b
o
th
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
co
m
p
u
tatio
n
al
e
f
f
icien
cy
.
-
GPR
GPR
p
er
f
o
r
m
ed
r
ea
s
o
n
ab
ly
well,
y
ield
in
g
an
R
MSE
o
f
9
6
.
6
5
f
o
r
tr
ain
in
g
an
d
9
6
.
4
0
f
o
r
test
in
g
,
alo
n
g
with
R
²
v
alu
es
o
f
0
.
9
7
3
0
an
d
0
.
9
7
3
9
,
r
esp
ec
tiv
ely
.
W
h
ile
GP
R
d
is
p
lay
ed
s
o
lid
p
r
ed
ictiv
e
ab
ilit
y
,
its
ac
cu
r
ac
y
f
ell
s
lig
h
tly
s
h
o
r
t
o
f
th
e
PC
A
+
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el.
T
h
e
m
ar
g
in
ally
h
i
g
h
er
R
MSE
v
alu
es
s
u
g
g
est th
at
GPR
m
ay
n
o
t c
ap
tu
r
e
d
ata
in
tr
icac
ies as e
f
f
ec
tiv
ely
.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f wi
n
d
s
p
ee
d
p
r
ed
ictio
n
:
e
n
h
a
n
cin
g
a
cc
u
r
a
cy
u
s
in
g
P
C
A
…
(
S
o
ma
s
u
n
d
a
r
a
m
Dee
p
a
)
543
-
SVR
Am
o
n
g
th
e
test
ed
m
eth
o
d
s
,
SVR
h
ad
th
e
lo
we
s
t
p
er
f
o
r
m
an
ce
,
with
an
R
MSE
o
f
9
4
.
5
2
f
o
r
th
e
tr
ain
in
g
s
et
an
d
9
9
.
0
2
f
o
r
t
h
e
test
in
g
s
et.
T
h
e
R
²
v
alu
es
wer
e
0
.
9
6
8
1
f
o
r
t
r
ain
in
g
an
d
0
.
9
6
9
2
f
o
r
test
in
g
.
Desp
ite
th
e
lo
w
tr
ai
n
in
g
R
MSE
,
th
e
s
ig
n
if
ican
t
i
n
cr
ea
s
e
in
t
est
er
r
o
r
p
o
in
ts
t
o
o
v
er
f
itti
n
g
,
in
d
icatin
g
th
at
SVR
m
ay
s
tr
u
g
g
le
with
g
en
er
aliza
ti
o
n
in
th
is
win
d
s
p
ee
d
p
r
e
d
ictio
n
task
.
-
R
NN
R
NN
also
ac
h
iev
ed
s
tr
o
n
g
r
e
s
u
lts
,
with
an
R
MSE
o
f
9
4
.
8
7
o
n
th
e
tr
ain
in
g
s
et
a
n
d
9
2
.
1
2
o
n
t
h
e
test
in
g
s
et.
T
h
e
R
²
v
alu
es
we
r
e
0
.
9
7
5
4
an
d
0
.
9
7
5
2
,
r
esp
ec
tiv
ely
.
T
h
ese
v
alu
es
ar
e
clo
s
e
to
th
o
s
e
o
f
PC
A
+
lin
ea
r
r
eg
r
ess
io
n
,
s
u
g
g
esti
n
g
th
at
R
NN
is
h
ig
h
ly
co
m
p
etitiv
e
f
o
r
win
d
s
p
ee
d
p
r
ed
ictio
n
.
I
ts
s
lig
h
tly
lo
we
r
R
MSE
o
n
th
e
test
s
et
im
p
lies
t
h
at
R
NN
m
ay
ca
p
tu
r
e
ce
r
tain
p
atter
n
s
m
o
r
e
e
f
f
ec
tiv
ely
.
I
n
s
u
m
m
a
r
y
,
t
h
e
co
m
p
ar
is
o
n
o
f
t
h
ese
m
eth
o
d
s
h
ig
h
lig
h
ts
PC
A
+
lin
ea
r
r
e
g
r
ess
io
n
as
th
e
b
est
p
er
f
o
r
m
er
in
ter
m
s
o
f
b
o
th
ac
cu
r
ac
y
an
d
er
r
o
r
m
in
im
izatio
n
.
W
h
ile
GPR
an
d
R
NN
al
s
o
s
h
o
wed
co
m
p
etitiv
e
r
esu
lts
,
SVR
lag
g
ed
b
eh
in
d
,
p
r
im
ar
ily
d
u
e
t
o
o
v
er
f
itti
n
g
is
s
u
es.
Ov
er
all,
PC
A
+
lin
ea
r
r
e
g
r
ess
io
n
em
er
g
es
as
a
r
eliab
le
an
d
ef
f
icien
t
s
o
lu
tio
n
f
o
r
h
a
n
d
lin
g
h
ig
h
-
d
im
en
s
i
o
n
al
m
eteo
r
o
lo
g
ical
d
ata
an
d
d
eliv
er
in
g
ac
cu
r
ate
win
d
s
p
ee
d
f
o
r
ec
asts
.
Fig
u
r
e
5
.
s
h
o
ws th
e
c
o
m
p
ar
is
o
n
o
f
d
if
f
er
e
n
t a
lg
o
r
ith
m
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
h
o
wca
s
es
th
e
ef
f
ec
tiv
en
ess
o
f
co
m
b
in
in
g
PC
A
with
lin
ea
r
r
eg
r
ess
io
n
f
o
r
win
d
s
p
ee
d
p
r
ed
ictio
n
.
PC
A’
s
d
im
en
s
io
n
a
lity
r
ed
u
ctio
n
an
d
f
ea
tu
r
e
s
ele
ctio
n
v
ia
SelectKBes
t
r
esu
lted
in
a
m
o
d
el
with
an
R
MSE
o
f
9
4
.
1
1
an
d
an
R
²
o
f
0
.
9
7
5
5
o
n
th
e
test
in
g
s
et,
o
u
t
p
er
f
o
r
m
in
g
GPR
,
SVR
,
an
d
R
NN
in
b
o
th
ac
c
u
r
ac
y
an
d
co
m
p
u
tatio
n
al
ef
f
icie
n
cy
.
T
h
e
m
o
d
el'
s
p
r
ac
tical
im
p
licatio
n
s
in
clu
d
e
im
p
r
o
v
ed
win
d
en
er
g
y
i
n
teg
r
atio
n
an
d
o
p
er
atio
n
al
p
lan
n
in
g
.
Ho
wev
er
,
lim
itatio
n
s
s
u
ch
as
r
eli
an
ce
o
n
h
is
to
r
ical
d
ata
an
d
ch
allen
g
es
with
r
ea
l
-
tim
e
ad
ap
tatio
n
ar
e
n
o
ted
.
F
u
tu
r
e
r
esear
ch
s
h
o
u
ld
ex
p
lo
r
e
in
co
r
p
o
r
atin
g
ad
d
itio
n
al
v
ar
iab
les,
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es,
an
d
r
ea
l
-
tim
e
ap
p
licatio
n
a
d
ap
tatio
n
s
.
T
h
is
ap
p
r
o
ac
h
ad
v
an
ce
s
win
d
s
p
ee
d
f
o
r
ec
asti
n
g
,
b
e
n
ef
itin
g
e
n
er
g
y
p
r
o
v
id
e
r
s
an
d
p
o
licy
m
ak
e
r
s
in
o
p
tim
izin
g
win
d
p
o
wer
s
y
s
tem
s
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
L.
M
a
h
m
o
o
d
,
A
.
M
.
S
h
a
k
i
r
,
a
n
d
B
.
A
.
N
u
m
a
n
,
“
D
e
si
g
n
a
n
d
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s
o
f
st
a
n
d
-
a
l
o
n
e
P
V
s
y
st
e
m
a
t
a
l
-
n
a
h
r
a
i
n
u
n
i
v
e
r
si
t
y
,
B
a
g
h
d
a
d
,
I
r
a
q
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Po
w
e
r E
l
e
c
t
r
o
n
i
c
s a
n
d
D
ri
v
e
S
y
st
e
m
s
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
9
2
1
–
9
3
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s
.
v
1
1
.
i
2
.
p
p
9
2
1
-
9
3
0
.
[
2
]
G
.
N
g
u
y
e
n
e
t
a
l
.
,
“
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
D
e
e
p
Le
a
r
n
i
n
g
f
r
a
mew
o
r
k
s
a
n
d
l
i
b
r
a
r
i
e
s
f
o
r
l
a
r
g
e
-
s
c
a
l
e
d
a
t
a
m
i
n
i
n
g
:
a
s
u
r
v
e
y
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
2
,
n
o
.
1
,
p
p
.
7
7
–
1
2
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
018
-
0
9
6
7
9
-
z.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
6
,
No
.
1
,
Ma
r
c
h
20
2
5
:
538
-
545
544
[
3
]
S
.
D
e
e
p
a
,
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
p
r
e
d
i
c
t
i
n
g
s
y
s
t
e
m
p
r
o
d
u
c
t
i
o
n
i
n
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
Po
w
e
r
El
e
c
t
r
o
n
i
c
s
a
n
d
D
r
i
v
e
S
y
st
e
m
s
,
v
o
l
.
15
,
n
o
.
3
,
p
p
.
1
9
2
5
–
1
9
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s.
v
1
5
.
i
3
.
p
p
1
9
2
5
-
1
9
3
3
.
[
4
]
R
.
V
i
n
a
y
a
k
u
mar,
M
.
A
l
a
z
a
b
,
K
.
P
.
S
o
man
,
P
.
P
o
o
r
n
a
c
h
a
n
d
r
a
n
,
A
.
A
l
-
N
e
mr
a
t
,
a
n
d
S
.
V
e
n
k
a
t
r
a
m
a
n
,
“
D
e
e
p
L
e
a
r
n
i
n
g
Ap
p
r
o
a
c
h
f
o
r
I
n
t
e
l
l
i
g
e
n
t
I
n
t
r
u
s
i
o
n
D
e
t
e
c
t
i
o
n
S
y
s
t
e
m
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
1
5
2
5
–
4
1
5
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
5
3
3
4
.
[
5
]
R
.
A
y
o
p
e
t
a
l
.
,
“
T
h
e
p
e
r
f
o
r
ma
n
c
e
s
o
f
p
a
r
t
i
a
l
s
h
a
d
i
n
g
a
d
j
u
st
e
r
f
o
r
i
m
p
r
o
v
i
n
g
p
h
o
t
o
v
o
l
t
a
i
c
e
m
u
l
a
t
o
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Po
w
e
r
El
e
c
t
r
o
n
i
c
s
a
n
d
D
r
i
v
e
S
y
st
e
m
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
5
2
8
–
5
3
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s
.
v
1
3
.
i
1
.
p
p
5
2
8
-
536
.
[
6
]
N
.
P
r
i
y
a
d
a
r
sh
i
,
S
.
P
a
d
ma
n
a
b
a
n
,
M
.
S
.
B
h
a
s
k
a
r
,
F
.
B
l
a
a
b
j
e
r
g
,
a
n
d
J.
B
.
H
o
l
m‐
N
i
e
l
s
e
n
,
“
A
n
i
m
p
r
o
v
e
d
h
y
b
r
i
d
P
V
‐
w
i
n
d
p
o
w
e
r
sy
st
e
m
w
i
t
h
M
P
P
T
f
o
r
w
a
t
e
r
p
u
mp
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
T
r
a
n
sa
c
t
i
o
n
s
o
n
E
l
e
c
t
r
i
c
a
l
En
e
rg
y
S
y
st
e
m
s
,
v
o
l
.
3
0
,
n
o
.
2
,
p
.
e
1
2
2
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
2
0
5
0
-
7
0
3
8
.
1
2
2
1
0
.
[
7
]
V
.
M
a
h
e
sw
a
r
i
,
e
t
a
l
.
,
“
Th
e
o
r
e
t
i
c
a
l
a
n
d
s
i
mu
l
a
t
i
o
n
a
n
a
l
y
s
i
s
o
f
f
i
r
s
t
g
e
n
e
r
a
t
i
o
n
D
C
-
D
C
c
o
n
v
e
r
t
e
r
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
28
,
n
o
.
1
9
,
p
p
.
7
2
–
78
,
2
0
1
9
.
[
8
]
S
.
D
e
e
p
a
,
N.
A
n
i
p
r
i
y
a
,
&
R
.
S
u
b
b
u
l
a
k
sh
my
,
"
D
e
s
i
g
n
o
f
c
o
n
t
r
o
l
l
e
r
s
f
o
r
c
o
n
t
i
n
u
o
u
s
st
i
r
r
e
d
t
a
n
k
r
e
a
c
t
o
r
"
.
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Po
w
e
r
El
e
c
t
r
o
n
i
c
s
a
n
d
D
r
i
v
e
S
y
st
e
m
s
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
576
–
5
8
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s.
v
5
.
i
4
.
p
p
5
7
6
-
5
8
2
.
[
9
]
E.
H
.
M
.
N
d
i
a
y
e
,
A
.
N
d
i
a
y
e
,
M
.
F
a
y
e
,
a
n
d
S
.
G
u
e
y
e
,
“
I
n
t
e
l
l
i
g
e
n
t
c
o
n
t
r
o
l
o
f
a
p
h
o
t
o
v
o
l
t
a
i
c
g
e
n
e
r
a
t
o
r
f
o
r
c
h
a
r
g
i
n
g
a
n
d
d
i
sc
h
a
r
g
i
n
g
b
a
t
t
e
r
y
u
si
n
g
a
d
a
p
t
i
v
e
n
e
u
r
o
-
f
u
z
z
y
i
n
f
e
r
e
n
c
e
s
y
st
e
m,"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
P
h
o
t
o
E
n
e
rg
y
,
v
o
l
.
2
0
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
6
4
9
8
6
8
.
[
1
0
]
Y
.
E
.
G
a
r
c
í
a
-
V
e
r
a
,
R
.
D
u
f
o
-
Ló
p
e
z
,
a
n
d
J.
L.
B
e
r
n
a
l
-
A
g
u
st
í
n
,
“
O
p
t
i
mi
z
a
t
i
o
n
o
f
i
s
o
l
a
t
e
d
h
y
b
r
i
d
mi
c
r
o
g
r
i
d
s
w
i
t
h
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
b
a
s
e
d
o
n
d
i
f
f
e
r
e
n
t
b
a
t
t
e
r
y
m
o
d
e
l
s a
n
d
t
e
c
h
n
o
l
o
g
i
e
s,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
5
8
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
0
3
0
5
8
1
.
[
1
1
]
Y
.
W
u
e
t
a
l
.
,
“
La
r
g
e
s
c
a
l
e
i
n
c
r
e
m
e
n
t
a
l
l
e
a
r
n
i
n
g
,
”
in
2
0
1
9
I
E
EE/
C
V
F
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
(
C
VPR)
,
v
o
l
.
2
0
1
9
-
Ju
n
e
,
2
0
1
9
,
p
p
.
3
7
4
–
3
8
2
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
9
.
0
0
0
4
6
.
[
1
2
]
A
.
M
o
s
a
v
i
,
S
.
S
h
a
msh
i
r
b
a
n
d
,
E
.
S
a
l
w
a
n
a
,
K
.
w
i
n
g
C
h
a
u
,
a
n
d
J.
H
.
M
.
T
a
h
,
“
P
r
e
d
i
c
t
i
o
n
o
f
m
u
l
t
i
-
i
n
p
u
t
s
b
u
b
b
l
e
c
o
l
u
m
n
r
e
a
c
t
o
r
u
si
n
g
a
n
o
v
e
l
h
y
b
r
i
d
m
o
d
e
l
o
f
c
o
mp
u
t
a
t
i
o
n
a
l
f
l
u
i
d
d
y
n
a
mi
c
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
E
n
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Fl
u
i
d
M
e
c
h
a
n
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
4
8
2
–
4
9
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
1
9
9
4
2
0
6
0
.
2
0
1
9
.
1
6
1
3
4
4
8
.
[
1
3
]
W
a
n
g
,
Z
.
,
L
i
u
,
K
.
,
L
i
,
J.
,
Z
h
u
,
Y
.
,
&
Zh
a
n
g
,
Y
.,
"
V
a
r
i
o
u
s
F
r
a
m
e
w
o
r
k
s
a
n
d
Li
b
r
a
r
i
e
s
o
f
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
a
n
d
D
e
e
p
Le
a
r
n
i
n
g
:
A
S
u
r
v
e
y
,"
Arc
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
1
,
p
p
.
1
-
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
8
3
1
-
0
1
8
-
0
9
3
1
2
-
w
.
[
1
4
]
K
r
i
z
h
e
v
s
k
y
,
A
.
,
S
u
t
sk
e
v
e
r
,
I
.
,
&
H
i
n
t
o
n
,
G
.
E.
,
"
I
mag
e
N
e
t
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
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
s
,"
C
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
h
e
A
C
M
,
v
o
l
.
60
,
n
o
.
6
,
p
p
.
84
–
90
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
0
6
5
3
8
6
.
[
1
5
]
J.
R
.
S
a
u
r
a
,
B
.
R
.
H
e
r
r
a
e
z
,
a
n
d
A
.
R
e
y
e
s
-
M
e
n
e
n
d
e
z
,
“
C
o
m
p
a
r
i
n
g
a
t
r
a
d
i
t
i
o
n
a
l
a
p
p
r
o
a
c
h
f
o
r
f
i
n
a
n
c
i
a
l
b
r
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
a
n
a
l
y
si
s
w
i
t
h
a
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s t
e
c
h
n
i
q
u
e
,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
7
,
p
p
.
3
7
1
0
0
–
3
7
1
0
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ES
S
.
2
0
1
9
.
2
9
0
5
3
0
1
.
[
1
6
]
D
e
e
p
a
,
S
.
,
P
r
a
b
a
,
S
.
,
D
e
e
p
a
l
a
k
s
h
mi
,
V
.
,
Ja
y
a
p
r
a
k
a
sh
,
L
.
,
&
M
a
n
i
m
u
r
u
g
a
n
,
M
.
,
"
A
f
u
z
z
y
G
A
b
a
s
e
d
S
TA
TC
O
M
f
o
r
p
o
w
e
r
q
u
a
l
i
t
y
i
mp
r
o
v
e
me
n
t
,
"
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
P
o
w
e
r
El
e
c
t
ro
n
i
c
s
a
n
d
D
ri
v
e
S
y
st
e
m
s
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
483
–
4
9
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s
.
v
8
.
i
1
.
p
p
4
8
3
-
491
.
[
1
7
]
A
w
a
st
h
i
,
A
.
,
S
h
u
k
l
a
,
A
.
K
.
,
M
u
r
a
l
i
M
a
n
o
h
a
r
,
S
.
R
.
,
D
o
n
d
a
r
i
y
a
,
C
.
,
S
h
u
k
l
a
,
K
.
N
.
,
P
o
r
w
a
l
,
D
.
,
&
R
i
c
h
h
a
r
i
y
a
,
G
.
,
"
R
e
v
i
e
w
o
n
su
n
t
r
a
c
k
i
n
g
t
e
c
h
n
o
l
o
g
y
i
n
s
o
l
a
r
P
V
sy
st
e
m.
En
e
r
g
y
R
e
p
o
r
t
s
,"
E
n
e
rg
y
Re
p
o
rt
s
,
v
o
l
.
6
,
p
p
.
3
9
2
-
4
0
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
0
.
0
2
.
0
0
4
.
[
1
8
]
AL
-
R
o
u
sa
n
,
N
.
,
M
a
t
I
sa,
N
.
A
.
,
&
M
a
t
D
e
sa
,
M
.
K
.
,
"
Ef
f
i
c
i
e
n
t
s
i
n
g
l
e
a
n
d
d
u
a
l
a
x
i
s
s
o
l
a
r
t
r
a
c
k
i
n
g
sy
s
t
e
m
c
o
n
t
r
o
l
l
e
r
s
b
a
s
e
d
o
n
a
d
a
p
t
i
v
e
n
e
u
r
a
l
f
u
z
z
y
i
n
f
e
r
e
n
c
e
s
y
st
e
m
,
"
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rs
i
t
y
-
En
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s
,
v
o
l
.
32
,
n
o
.
7
,
p
p
.
4
5
9
–
469
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
e
s.
2
0
2
0
.
0
4
.
0
0
4
.
[
1
9
]
M
.
K
h
a
r
r
i
c
h
e
t
a
l
.
,
“
O
p
t
i
ma
l
d
e
si
g
n
o
f
a
n
i
s
o
l
a
t
e
d
h
y
b
r
i
d
m
i
c
r
o
g
r
i
d
f
o
r
e
n
h
a
n
c
e
d
d
e
p
l
o
y
me
n
t
o
f
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
s
o
u
r
c
e
s
i
n
S
a
u
d
i
A
r
a
b
i
a
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
3
,
n
o
.
9
,
p
.
4
7
0
8
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
3
0
9
4
7
0
8
.
[
2
0
]
Jo
se
A
.
C
a
r
b
a
l
l
o
,
Ja
v
i
e
r
B
o
n
i
l
l
a
,
L
i
d
i
a
R
o
c
a
,
M
a
n
u
e
l
B
e
r
e
n
g
u
e
l
,
"
N
e
w
l
o
w
-
c
o
st
s
o
l
a
r
t
r
a
c
k
i
n
g
s
y
st
e
m
b
a
s
e
d
o
n
o
p
e
n
so
u
r
c
e
h
a
r
d
w
a
r
e
f
o
r
e
d
u
c
a
t
i
o
n
a
l
p
u
r
p
o
s
e
s
,
"
S
o
l
a
r E
n
e
rg
y
,
v
o
l
.
1
7
4
,
,
8
2
6
-
8
3
6
,
2
0
1
8
.
[
2
1
]
Jo
se
A
.
C
a
r
b
a
l
l
o
,
J
a
v
i
e
r
B
o
n
i
l
l
a
,
M
a
n
u
e
l
B
e
r
e
n
g
u
e
l
,
Jes
ú
s
F
e
r
n
á
n
d
e
z
-
R
e
c
h
e
,
G
i
n
é
s
G
a
r
c
í
a
,
"
N
e
w
a
p
p
r
o
a
c
h
f
o
r
s
o
l
a
r
t
r
a
c
k
i
n
g
sy
st
e
ms
b
a
s
e
d
o
n
c
o
mp
u
t
e
r
v
i
s
i
o
n
,
l
o
w
c
o
s
t
h
a
r
d
w
a
r
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
"
Re
n
e
w
a
b
l
e
E
n
e
r
g
y
,
v
ol
.
1
3
3
,
p
p
.
1
1
5
8
-
1
1
6
6
,
2
0
1
9
.
[
2
2
]
R
e
d
d
y
,
S
.
R.
,
"
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
m
o
d
e
l
i
n
g
i
r
r
e
g
u
l
a
r
r
e
g
i
o
n
s
w
i
t
h
m
u
l
t
i
p
l
e
o
w
n
e
r
s
i
n
w
i
n
d
f
a
r
m
l
a
y
o
u
t
d
e
s
i
g
n
,"
En
e
rg
y
,
v
o
l
.
2
2
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
0
.
1
1
9
6
9
1
.
[
2
3
]
M
.
S
e
e
g
e
r
,
"
G
a
u
ss
i
a
n
p
r
o
c
e
sses
f
o
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
N
e
u
ra
l
S
y
st
e
m
s
,
v
o
l
.
14
,
n
o
.
2
,
p
p
.
69
–
106
,
2
0
0
4
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
1
2
9
0
6
5
7
0
4
0
0
1
8
9
9
.
[
2
4
]
L.
D
h
a
n
e
s
h
,
e
t
a
l
.
,
“
En
h
a
n
c
e
d
a
n
d
En
e
r
g
y
-
Ef
f
i
c
i
e
n
t
P
r
o
g
r
a
m
S
c
h
e
d
u
l
i
n
g
f
o
r
H
e
t
e
r
o
g
e
n
e
o
u
s
M
u
l
t
i
-
C
o
r
e
P
r
o
c
e
ss
o
r
s
S
y
s
t
e
m
,
”
L
e
c
t
u
re
N
o
t
e
s
in
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
6
5
,
p
p
.
7
3
7
–
747
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
15
-
5
2
6
2
-
5
_
5
5
.
[
2
5
]
M
.
A
q
i
b
,
R
.
M
e
h
m
o
o
d
,
A
.
A
l
z
a
h
r
a
n
i
,
I
.
K
a
t
i
b
,
A
.
A
l
b
e
s
h
r
i
,
a
n
d
S
.
M
.
A
l
t
o
w
a
i
j
r
i
,
"
S
mart
e
r
Tr
a
f
f
i
c
P
r
e
d
i
c
t
i
o
n
U
s
i
n
g
B
i
g
D
a
t
a
,
I
n
-
M
e
m
o
r
y
C
o
m
p
u
t
i
n
g
,
D
e
e
p
L
e
a
r
n
i
n
g
a
n
d
G
P
U
s
,
"
S
e
n
s
o
rs
,
v
o
l
.
1
9
,
n
o
.
9
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
9
2
2
0
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
o
m
a
sun
d
a
r
a
m
De
e
p
a
re
c
e
iv
e
d
h
e
r
B.
E.
fro
m
K.
S
.
R
C
o
ll
e
g
e
o
f
Tec
h
n
o
lo
g
y
,
a
ffil
iate
d
to
P
e
ri
y
a
r
Un
i
v
e
rsity
,
in
2
0
0
3
,
M
.
E
fro
m
A
n
n
a
m
a
lai
Un
i
v
e
rsity
in
2
0
0
5
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
.
D
.
d
e
g
re
e
fo
r
m
S
a
th
y
a
b
a
m
a
u
n
iv
e
rsity
i
n
2
0
1
3
.
P
re
se
n
tl
y
,
sh
e
is
wo
rk
in
g
a
s
a
p
ro
fe
s
so
r
in
th
e
De
p
a
rtme
n
t
o
f
EE
E
a
t
P
a
n
ima
lar
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
,
Ch
e
n
n
a
i.
S
h
e
h
a
s
p
u
b
li
sh
e
d
a
m
o
re
t
h
a
n
3
0
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
jo
u
r
n
a
ls
.
He
r
a
re
a
o
f
in
tere
st
is
p
o
we
r
sy
ste
m
,
o
p
ti
m
isa
ti
o
n
tec
h
n
iq
u
e
.
S
h
e
h
a
s
m
o
re
th
a
n
1
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
field
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
e
_
so
m
s1
2
3
@
y
a
h
o
o
.
c
o
.
in
.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f wi
n
d
s
p
ee
d
p
r
ed
ictio
n
:
e
n
h
a
n
cin
g
a
cc
u
r
a
cy
u
s
in
g
P
C
A
…
(
S
o
ma
s
u
n
d
a
r
a
m
Dee
p
a
)
545
J
a
y
a
n
t
h
i
Ar
u
m
u
g
a
m
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
a
t
Ve
lam
m
a
l
En
g
i
n
e
e
rin
g
Co
l
leg
e
,
Ch
e
n
n
a
i,
In
d
ia.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
m
in
i
n
g
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
jay
a
n
th
iaru
m
u
g
a
m
k
@g
m
a
il
.
c
o
m
.
Ra
g
u
r
a
m
a
n
Pu
r
u
sh
o
th
a
m
a
n
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
CS
E
(
a
rti
ficia
l
in
telli
g
e
n
c
e
),
M
a
d
a
n
a
p
a
ll
e
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
&
S
c
ien
c
e
,
An
g
a
ll
u
,
M
a
d
a
n
a
p
a
ll
e
,
An
d
h
ra
P
ra
d
e
sh
.
His
a
re
a
o
f
i
n
tere
st
in
c
lu
d
e
s
th
e
o
r
y
o
f
c
o
m
p
u
tati
o
n
,
d
e
sig
n
a
n
d
a
n
a
ly
sis
o
f
a
lg
o
rit
h
m
s,
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
d
a
ta
sc
ien
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
u
v
a
ra
g
u
.
p
t@g
m
a
il
.
c
o
m
.
D.
N
a
g
e
s
wa
r
i
a
s
sis
ta
n
t
p
r
o
fe
ss
o
r
a
t
R
.
M
.
K.
C
o
l
le
g
e
o
f
E
n
g
i
n
e
e
ri
n
g
a
n
d
Tec
h
n
o
l
o
g
y
,
h
o
l
d
s
a
P
h
.
D
.
in
E
l
e
c
tr
ica
l
a
n
d
E
lec
t
r
o
n
ic
s
E
n
g
i
n
e
e
r
in
g
f
r
o
m
A
n
n
a
U
n
i
v
e
rs
it
y
(2
0
2
2
)
a
n
d
a
n
M
.
E
.
i
n
P
o
w
e
r
E
lec
tr
o
n
i
c
s
a
n
d
D
ri
v
e
s
f
r
o
m
R
.
M
.
K
.
E
n
g
i
n
e
e
r
i
n
g
C
o
ll
e
g
e
,
w
h
e
re
sh
e
r
e
c
e
i
v
e
d
t
h
e
Un
i
v
e
rsi
t
y
G
o
l
d
M
e
d
a
l
.
S
h
e
h
a
s
p
u
b
l
is
h
e
d
o
v
e
r
1
8
p
a
p
e
rs
,
is
a
m
e
m
b
e
r
o
f
fo
u
r
p
r
o
f
e
ss
i
o
n
a
l
s
o
c
ie
ti
e
s,
a
n
d
h
e
r
re
se
a
rc
h
fo
c
u
se
s
o
n
o
p
t
im
iz
a
ti
o
n
tec
h
n
i
q
u
e
s,
a
rt
if
ic
ial
in
te
ll
i
g
e
n
c
e
,
a
n
d
sm
a
r
t
g
ri
d
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
n
a
g
e
sw
a
ri@
rm
k
c
e
t.
a
c
.
i
n
.
L
.
Ra
ja
se
k
h
a
r
a
B
a
b
u
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
K
o
n
e
ru
Lak
s
h
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
(KL
EF
),
A
n
d
h
ra
P
ra
d
e
sh
.
He
h
o
l
d
s
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
i
e
n
c
e
fro
m
Bh
a
ra
th
id
a
sa
n
Un
iv
e
rsity
a
n
d
h
a
s
e
x
p
e
rti
se
in
m
e
d
ica
l
d
a
ta
m
in
i
n
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
b
io
i
n
fo
rm
a
ti
c
s.
Wi
th
n
u
m
e
ro
u
s
p
u
b
li
c
a
ti
o
n
s
a
n
d
a
wa
rd
s,
h
is
re
se
a
rc
h
sp
a
n
s
in
m
a
c
h
in
e
lea
rn
i
n
g
,
b
i
g
d
a
ta,
a
n
d
o
n
to
lo
g
y
d
e
v
e
lo
p
m
e
n
t
.
H
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
ra
jas
e
k
h
a
rl
in
g
ise
tt
y
@k
l
u
n
i
v
e
rsity
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.