I
nte
rna
t
io
na
l J
o
urna
l o
f
P
o
wer
E
lect
ro
nics
a
nd
Driv
e
S
y
s
t
em
(
I
J
P
E
DS)
Vo
l.
1
7
,
No
.
2
,
J
u
n
e
20
2
6
,
p
p
.
1440
~
1
4
5
0
I
SS
N:
2
0
8
8
-
8
6
9
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijp
ed
s
.
v
1
7
.
i
2
.
p
p
1
4
4
0
-
1
4
5
0
1440
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
Ada
ptive co
nt
ro
l
o
f
the
v
ir
tual sy
n
chro
no
us g
enerat
o
r by deep
neura
l net
wo
rks f
o
r a wind high
power con
v
ersio
n c
ha
in
Wij
da
ne
E
l
M
a
a
t
a
o
ui,
Abdelo
ua
hed Abo
un
a
da
Te
a
m
o
f
A
u
t
o
m
a
t
i
c
a
n
d
En
e
r
g
y
C
o
n
v
e
r
si
o
n
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
ma
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
,
2
0
2
5
R
ev
is
ed
Ap
r
2
,
2
0
2
6
Acc
ep
ted
Ap
r
23
,
2
0
2
6
Th
e
v
ir
tu
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
ra
t
o
r
(VSG
)
is
c
o
m
m
o
n
l
y
u
se
d
t
o
re
p
ro
d
u
c
e
th
e
in
e
rti
a
l
re
sp
o
n
se
o
f
c
o
n
v
e
n
ti
o
n
a
l
sy
n
c
h
ro
n
o
u
s
m
a
c
h
in
e
s.
Ho
we
v
e
r,
th
e
VSG
c
o
n
tro
l
a
rc
h
it
e
c
tu
re
re
li
e
s
o
n
c
o
n
tro
ll
e
r
c
h
a
i
n
s,
b
e
n
c
h
m
a
rk
tran
sfo
rm
a
ti
o
n
s,
a
n
d
p
a
ra
m
e
ter
se
tt
in
g
s,
i
n
c
lu
d
in
g
v
ir
tu
a
l
i
n
e
rti
a
a
n
d
d
a
m
p
in
g
,
w
h
ich
li
m
it
it
s
flex
i
b
il
it
y
i
n
h
i
g
h
l
y
d
y
n
a
m
ic
e
n
v
ir
o
n
m
e
n
ts.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
s
a
n
i
n
n
o
v
a
ti
v
e
e
n
d
-
to
-
e
n
d
c
o
n
tro
l
a
p
p
r
o
a
c
h
b
a
se
d
o
n
a
n
e
u
ra
l
n
e
two
rk
t
o
fu
l
ly
re
p
lac
e
th
e
c
las
sic
a
l
VS
G
c
o
n
tro
l
stru
c
tu
re
.
T
h
e
n
e
u
ra
l
n
e
two
rk
d
e
v
e
lo
p
e
d
is
trai
n
e
d
to
d
irec
tl
y
g
e
n
e
ra
te
i
n
v
e
rter
c
o
n
tr
o
l
si
g
n
a
l
s
fro
m
re
a
l
-
ti
m
e
e
lec
tri
c
a
l
m
e
a
su
re
m
e
n
ts,
in
c
lu
d
i
n
g
v
o
lt
a
g
e
s
a
n
d
c
u
rre
n
ts,
a
s
we
ll
a
s
a
c
ti
v
e
a
n
d
re
a
c
ti
v
e
p
o
we
r.
A
d
a
tas
e
t
is
g
e
n
e
ra
ted
fro
m
a
d
e
tailed
VSG
m
o
d
e
l
u
n
d
e
r
d
iffere
n
t
o
p
e
ra
ti
n
g
c
o
n
d
it
io
n
s,
a
n
d
th
e
n
a
m
u
lt
il
a
y
e
r
n
e
u
ra
l
n
e
two
rk
is
trai
n
e
d
u
si
n
g
su
p
e
r
v
ise
d
lea
rn
i
n
g
wit
h
M
AT
LAB.
Th
e
re
su
lt
in
g
m
o
d
e
l
is
t
h
e
n
i
n
teg
ra
te
d
in
t
o
a
c
o
m
p
lete
win
d
e
n
e
rg
y
c
o
n
v
e
rsi
o
n
c
h
a
in
sim
u
late
d
in
S
imu
li
n
k
.
Th
e
sim
u
latio
n
re
su
l
ts
d
e
m
o
n
stra
te
th
a
t
c
o
n
tro
l
b
a
se
d
o
n
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
s
e
n
su
re
s
b
e
tt
e
r
fre
q
u
e
n
c
y
a
n
d
v
o
lt
a
g
e
sta
b
il
it
y
,
m
o
re
a
c
c
u
ra
te
trac
k
in
g
o
f
th
e
a
c
ti
v
e
p
o
we
r
i
n
jec
ted
,
a
n
d
a
sig
n
ifi
c
a
n
t
im
p
ro
v
e
m
e
n
t
in
p
o
we
r
q
u
a
li
ty
,
wit
h
to
tal
h
a
rm
o
n
ic
d
isto
rti
o
n
(THD)
re
d
u
c
e
d
to
0
.
0
4
%
,
c
o
m
p
a
r
e
d
to
0
.
5
1
%
f
o
r
c
o
n
v
e
n
ti
o
n
a
l
VS
G
c
o
n
tro
l.
Th
e
se
re
su
lt
s c
o
n
firm t
h
e
p
o
ten
ti
a
l
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
-
b
a
se
d
a
p
p
r
o
a
c
h
e
s
fo
r
th
e
in
telli
g
e
n
t
c
o
n
tr
o
l
o
f
re
n
e
wa
b
le en
e
rg
y
s
y
ste
m
s.
K
ey
w
o
r
d
s
:
Ad
ap
tiv
e
co
n
tr
o
l
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
E
n
d
-
to
-
e
n
d
c
o
n
tr
o
l
I
n
v
er
ter
c
o
n
tr
o
l
Su
p
er
v
is
ed
lear
n
in
g
Vir
tu
al
s
y
n
ch
r
o
n
o
u
s
g
e
n
er
ato
r
W
i
n
d
t
u
r
b
i
n
e
c
o
n
v
e
r
s
i
o
n
s
y
s
t
em
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
:
W
ijd
an
e
E
l
M
aa
tao
u
i
T
ea
m
o
f
Au
t
o
m
atic
an
d
E
n
er
g
y
C
o
n
v
er
s
io
n
,
Facu
lty
o
f
Scie
n
ce
s
an
d
T
ec
h
n
o
lo
g
y
Su
ltan
Mo
u
lay
Sli
m
an
e
Un
iv
e
r
s
ity
B
en
i M
ellal,
Mo
r
o
cc
o
E
m
ail:
wijd
an
e.
elm
aa
tao
u
i@
u
s
m
s
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ex
ten
s
iv
e
in
teg
r
atio
n
o
f
r
en
ewa
b
le
en
er
g
y
s
o
u
r
ce
s
,
p
a
r
ticu
lar
ly
win
d
p
o
wer
,
h
as
tr
an
s
f
o
r
m
ed
m
o
d
er
n
p
o
wer
g
r
id
s
,
with
g
lo
b
al
cu
m
u
lativ
e
win
d
p
o
wer
ca
p
ac
ity
r
ea
ch
i
n
g
a
r
o
u
n
d
1
1
3
6
GW
b
y
th
e
en
d
o
f
2024
[
1
]
.
T
h
ese
g
en
er
ati
o
n
s
o
u
r
ce
s
ar
e
o
f
ten
c
o
n
n
ec
te
d
to
th
e
g
r
id
v
ia
p
er
m
a
n
en
t
m
ag
n
et
s
y
n
ch
r
o
n
o
u
s
g
en
er
ato
r
s
(
PMSGs
)
an
d
p
o
w
er
co
n
v
er
te
r
s
to
en
s
u
r
e
an
in
j
ec
tio
n
th
at
m
ee
ts
th
e
r
eq
u
ir
e
m
en
ts
o
f
th
e
p
o
wer
g
r
id
[
2
]
,
[
3
]
.
I
n
th
is
co
n
tex
t,
th
e
co
n
ce
p
t
o
f
th
e
v
ir
tu
al
s
y
n
ch
r
o
n
o
u
s
g
en
er
ato
r
(
VSG)
h
as
em
er
g
ed
as
an
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
ar
tific
ia
lly
r
ep
r
o
d
u
cin
g
th
e
in
er
tia
o
f
s
y
n
ch
r
o
n
o
u
s
m
ac
h
in
es
b
y
in
j
ec
tin
g
a
ca
lcu
lated
in
er
tial r
esp
o
n
s
e
[
4
]
-
[
6
]
.
T
h
e
class
ic
VSG
s
tr
u
ctu
r
e
is
b
ased
o
n
th
e
s
win
g
eq
u
atio
n
,
co
m
b
in
e
d
with
v
o
ltag
e
an
d
r
ea
ctiv
e
p
o
wer
r
eg
u
latio
n
b
y
Q
-
V
o
r
f
r
eq
u
en
c
y
an
d
ac
tiv
e
p
o
wer
r
e
g
u
latio
n
P
-
f
lo
o
p
s
,
f
o
llo
wed
b
y
s
in
u
s
o
id
al
p
u
ls
e
wid
th
m
o
d
u
latio
n
(
SP
W
M)
[
7
]
.
Alth
o
u
g
h
th
is
ar
c
h
itectu
r
e
is
r
o
b
u
s
t
an
d
b
ased
o
n
estab
lis
h
ed
p
h
y
s
ical
m
o
d
els,
it
h
as
s
ev
er
al
lim
itatio
n
s
,
in
clu
d
in
g
th
e
n
ee
d
f
o
r
ac
cu
r
ate
g
r
i
d
an
d
m
ac
h
in
e
m
o
d
elin
g
,
wh
ich
is
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
A
d
a
p
tive
co
n
tr
o
l o
f th
e
virt
u
a
l
s
yn
ch
r
o
n
o
u
s
g
e
n
era
to
r
b
y
d
e
ep
n
eu
r
a
l n
etw
o
r
ks
…
(
Wij
d
a
n
e
E
l Ma
a
ta
o
u
i
)
1441
ch
allen
g
in
g
in
u
n
s
tab
le
o
r
c
h
a
n
g
in
g
en
v
ir
o
n
m
e
n
ts
[
8
]
.
I
n
ad
d
itio
n
,
th
is
a
p
p
r
o
ac
h
is
s
en
s
itiv
e
to
p
r
o
p
o
r
tio
n
al
-
in
teg
r
al
(
PI)
co
n
t
r
o
ller
t
u
n
in
g
er
r
o
r
s
,
th
e
alig
n
m
en
t
o
f
ab
c/
d
q
Par
k
tr
an
s
f
o
r
m
s
,
an
d
th
e
q
u
ality
o
f
f
r
e
q
u
en
c
y
f
ilter
in
g
[
9
]
.
Par
am
eter
s
s
u
ch
as
v
ir
tu
al
in
e
r
tia
J
o
r
d
am
p
in
g
f
ac
to
r
Dp
a
r
e
g
en
er
ally
f
ix
ed
,
wh
ich
r
ed
u
ce
s
t
h
e
s
y
s
tem
'
s
ad
ap
tab
ilit
y
[
1
0
]
.
R
ec
en
tly
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
h
av
e
d
em
o
n
s
tr
ated
th
eir
ef
f
ec
tiv
en
ess
in
m
o
d
elin
g
n
o
n
lin
ea
r
s
y
s
tem
s
,
d
y
n
am
ic
p
r
ed
ictio
n
,
an
d
co
m
m
a
n
d
g
en
er
atio
n
i
n
co
m
p
lex
co
n
t
ex
ts
[
1
1
]
,
[
1
2
]
.
I
n
p
ar
ticu
lar
,
s
ev
er
al
wo
r
k
s
h
av
e
p
r
o
p
o
s
ed
n
eu
r
al
m
o
d
els
to
d
y
n
am
ically
a
d
ju
s
t
VSG
p
ar
am
eter
s
[
1
3
]
o
r
to
r
ep
lace
ce
r
tain
co
n
t
r
o
l
b
lo
ck
s
with
lear
n
e
d
s
u
b
m
o
d
els
[
1
4
]
.
Ho
wev
er
,
f
ew
w
o
r
k
s
g
o
s
o
f
ar
as
to
r
ep
lace
th
e
en
tire
VSG
ar
ch
itectu
r
e
with
a
s
in
g
le
n
e
u
r
al
m
o
d
el,
ca
p
a
b
le
o
f
d
ir
ec
tly
g
en
er
atin
g
in
v
er
ter
co
n
tr
o
l
p
u
ls
es
f
r
o
m
lo
ca
l e
lectr
ical
m
ea
s
u
r
e
m
en
ts
.
I
n
th
is
s
tu
d
y
,
we
p
r
o
p
o
s
e
d
ir
e
ct
en
d
-
to
-
en
d
co
n
tr
o
l u
s
in
g
a
s
u
p
er
v
is
ed
n
eu
r
al
n
etwo
r
k
.
B
y
g
en
er
atin
g
a
d
ataset
v
ia
s
im
u
latio
n
i
n
Si
m
u
lin
k
,
we
tr
ain
a
n
eu
r
al
m
o
d
el
in
MA
T
L
AB
.
T
h
is
m
o
d
el
le
ar
n
s
to
ass
o
ciate
th
e
elec
tr
ical
s
tate
s
o
f
th
e
s
y
s
tem
with
th
e
co
n
tr
o
l p
u
ls
es r
eq
u
ir
e
d
f
o
r
d
ir
ec
t c
u
r
r
en
t
(
DC
)
/alter
n
atin
g
cu
r
r
e
n
t (
AC
)
co
n
v
er
s
io
n
.
T
h
is
m
o
d
el
is
th
e
n
in
teg
r
ate
d
in
to
a
c
o
m
p
lete
win
d
tu
r
b
i
n
e
co
n
v
er
s
io
n
ch
ain
an
d
co
m
p
a
r
ed
wit
h
a
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l sy
s
tem
in
ter
m
s
o
f
s
tab
ilit
y
,
f
r
eq
u
en
cy
r
esp
o
n
s
e,
an
d
h
ar
m
o
n
i
c
d
is
to
r
tio
n
cr
iter
ia.
Un
lik
e
p
r
ev
io
u
s
h
y
b
r
i
d
ANN
-
VSG
ap
p
r
o
ac
h
es
th
at
o
n
ly
r
ep
lace
o
r
tu
n
e
s
p
ec
if
ic
co
n
t
r
o
l
l
o
o
p
s
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
p
er
f
o
r
m
s
a
c
o
m
p
lete
n
eu
r
al
s
u
b
s
titu
tio
n
o
f
th
e
V
SG
s
tr
u
ctu
r
e,
en
a
b
lin
g
a
s
im
p
lifie
d
an
d
ad
a
p
tiv
e
co
n
tr
o
ller
s
u
itab
le
f
o
r
r
ea
l
-
tim
e
an
d
em
b
ed
d
e
d
im
p
lem
en
tati
o
n
.
2.
WI
ND
E
NE
RG
Y
CO
NVE
R
SI
O
N
CH
AIN
Fig
u
r
e
1
illu
s
tr
ates
th
e
win
d
e
n
er
g
y
co
n
v
er
s
io
n
ch
ai
n
,
wh
ic
h
in
clu
d
es
th
e
win
d
tu
r
b
in
e,
th
e
PMSG,
an
d
th
e
th
r
ee
-
p
h
ase
r
ec
tifie
r
.
I
t
also
c
o
n
s
is
ts
o
f
a
c
h
o
p
p
e
r
eq
u
i
p
p
ed
with
m
a
x
im
u
m
p
o
wer
p
o
in
t
tr
ac
k
i
n
g
(
MPPT)
,
o
p
tim
al
t
o
r
q
u
e
alg
o
r
ith
m
co
n
tr
o
l
,
a
n
d
a
DC
b
u
s
.
Ad
d
itio
n
ally
,
t
h
e
s
y
s
tem
in
c
o
r
p
o
r
ates
a
two
-
lev
el
th
r
ee
-
p
h
ase
in
v
er
ter
with
VSG
co
n
tr
o
l,
a
n
L
C
L
f
ilter
,
an
d
th
e
th
r
ee
-
p
h
ase
g
r
id
[
1
5
]
.
Fig
u
r
e
1
.
Diag
r
a
m
o
f
th
e
VSG
co
n
tr
o
l sy
s
tem
in
teg
r
ated
in
to
th
e
win
d
tu
r
b
in
e
co
n
v
er
s
io
n
c
h
ain
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
2
,
J
u
n
e
20
2
6
:
1
4
4
0
-
1450
1442
3.
CL
AS
SI
CA
L
VSG
VSG
co
n
tr
o
l a
im
s
to
r
ep
r
o
d
u
c
e
th
e
d
y
n
am
ic
eq
u
atio
n
s
o
f
a
r
o
tatin
g
s
y
n
ch
r
o
n
o
u
s
m
ac
h
in
e.
3
.
1
.
Virt
ua
l iner
t
ia
equa
t
io
n
Swin
g
'
s
eq
u
atio
n
,
af
ter
ap
p
ly
i
n
g
th
e
f
u
n
d
a
m
en
tal
p
r
i
n
cip
le
o
f
d
y
n
a
m
ics to
a
r
o
tatin
g
m
ass
,
is
as
(
1
)
.
=
∑
=
−
(
1
)
W
h
er
e
J
is
th
e
to
tal
m
o
m
e
n
t
o
f
in
er
tia,
α
m
is
th
e
an
g
u
lar
ac
ce
l
er
atio
n
o
f
th
e
r
o
to
r
,
C
e
is
th
e
elec
tr
ical
to
r
q
u
e,
an
d
C
m
is
th
e
m
ec
h
an
ical
t
o
r
q
u
e.
Dep
en
d
in
g
o
n
th
e
p
o
wer
an
d
d
a
m
p
in
g
ter
m
s
o
f
t
h
e
s
y
n
ch
r
o
n
o
u
s
m
ac
h
i
n
e,
th
e
s
win
g
b
ec
o
m
es
as (
2
)
[
1
5
]
.
d
ω
=
−
−
(
−
re
f
)
(
2
)
W
h
er
e
m
is
th
e
r
o
tatio
n
al
s
p
ee
d
,
P
m
is
th
e
ac
tiv
e
m
ec
h
a
n
ical
p
o
wer
,
P
e
is
th
e
elec
tr
ic
al
p
o
wer
,
D
p
is
t
h
e
d
am
p
in
g
f
ac
to
r
,
an
d
ref
is
th
e
r
ef
er
en
ce
a
n
g
u
la
r
v
elo
city
.
3
.
2
.
Vo
l
t
a
g
e
a
nd
re
a
ct
iv
e
po
wer
co
ntr
o
l
Vo
ltag
e
co
n
tr
o
l
im
p
r
o
v
es
s
tab
ilit
y
an
d
p
r
ev
en
ts
cu
r
r
en
t
s
p
i
k
es.
At
th
e
n
eu
tr
al
p
o
in
t
o
f
t
h
e
in
v
er
ter
,
th
e
v
o
ltag
e
is
g
iv
e
n
b
y
(
1
3
)
[
1
6
]
.
√
2
ℎ
=
(
)
(
√
2
−
√
2
)
(
3
)
W
h
er
e
U
ref
is
th
e
in
v
er
ter
r
ef
e
r
en
ce
v
o
ltag
e,
an
d
U
ph
is
th
e
i
n
v
er
ter
p
h
ase
v
o
ltag
e.
T
h
e
r
el
atio
n
s
h
ip
b
etwe
en
r
ea
ctiv
e
p
o
wer
a
n
d
v
o
ltag
e
is
g
iv
en
(
4
)
.
√
2
(
−
)
=
−
(
4
)
W
h
er
e
D
q
is
th
e
d
r
o
o
p
c
o
ef
f
ic
ien
t
o
f
r
ea
ctiv
e
p
o
wer
an
d
v
o
ltag
e,
Un
is
th
e
o
u
tp
u
t
v
o
ltag
e
,
Q
e
is
th
e
r
ea
ctiv
e
p
o
wer
,
an
d
Q
ref
is
th
e
r
ef
er
e
n
c
e
r
ea
ctiv
e
p
o
wer
.
B
y
in
teg
r
ati
n
g
(
)
=
⁄
,
th
e
(
4
)
b
ec
o
m
es
(
5
)
[
1
5
]
.
√
2
ℎ
=
1
(
−
+
(
√
2
−
√
2
)
)
(
5
)
3
.
3
.
Vo
l
t
a
g
e
a
nd
curr
ent
lo
o
ps
T
o
f
u
r
th
er
im
p
r
o
v
e
v
o
ltag
e
an
d
cu
r
r
en
t
o
u
tp
u
ts
,
two
lo
o
p
s
h
av
e
b
ee
n
ad
d
ed
:
a
n
in
te
r
n
al
c
u
r
r
en
t
lo
o
p
an
d
an
e
x
ter
n
al
v
o
ltag
e
lo
o
p
.
3
.
3
.
1
.
Vo
lt
a
g
e
co
ntr
o
l
T
h
e
DC
cir
cu
it o
f
th
e
i
n
v
er
ter
is
r
ep
r
esen
ted
b
y
(
6
)
[
1
7
]
,
[
1
8
]
.
=
−
(
6
)
v
q
*
is
eq
u
al
to
ze
r
o
,
ass
u
m
in
g
t
h
at
th
e
‘
d
’
ax
is
is
p
ar
allel
to
th
e
AC
m
ain
s
v
o
ltag
e.
[
∗
∗
]
+
[
]
=
(
1
+
)
[
∗
−
∗
−
]
(
7
)
W
ith
i
d
*
an
d
i
q
*
co
r
r
esp
o
n
d
i
n
g
r
esp
ec
tiv
ely
to
t
h
e
co
m
p
o
n
e
n
ts
o
f
th
e
o
u
tp
u
t
cu
r
r
e
n
t
alo
n
g
th
e
d
an
d
q
a
x
es.
(
C
)
T
h
e
ca
p
ac
itan
ce
o
f
th
e
f
ilt
er
ca
p
ac
ito
r
.
v
d
an
d
v
q
ar
e
th
e
co
m
p
o
n
en
ts
o
f
th
e
o
u
tp
u
t
v
o
ltag
e
alo
n
g
th
e
d
an
d
q
ax
es,
r
esp
ec
tiv
ely
.
v
d
*
an
d
v
q
*
co
r
r
esp
o
n
d
r
esp
ec
tiv
ely
to
t
h
e
co
m
p
o
n
e
n
ts
o
f
th
e
DC
b
u
s
r
ef
er
e
n
ce
v
o
ltag
e
alo
n
g
th
e
d
an
d
q
a
x
es.
3
.
3
.
2
.
Curre
nt
co
ntr
o
l
T
h
e
v
o
ltag
es o
n
th
e
g
r
id
s
id
e
o
f
th
e
p
o
wer
c
o
n
v
e
r
s
io
n
ch
ain
ar
e
ex
p
r
ess
ed
in
ter
m
s
o
f
th
e
p
ar
am
eter
s
o
f
th
e
L
C
L
f
ilter
an
d
th
e
c
o
m
m
o
n
co
u
p
lin
g
p
o
in
t
r
ep
r
esen
ti
n
g
th
e
th
r
ee
-
p
h
ase
in
v
er
ter
as
(
8
)
[
1
7
]
,
[
1
8
]
.
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
A
d
a
p
tive
co
n
tr
o
l o
f th
e
virt
u
a
l
s
yn
ch
r
o
n
o
u
s
g
e
n
era
to
r
b
y
d
e
ep
n
eu
r
a
l n
etw
o
r
ks
…
(
Wij
d
a
n
e
E
l Ma
a
ta
o
u
i
)
1443
{
−
+
=
(
+
)
(
∗
−
)
−
−
=
(
+
)
(
∗
−
)
(
8
)
W
h
er
e
m
d
an
d
m
q
a
r
e
th
e
o
u
tp
u
t
r
ef
er
e
n
ce
v
al
u
es
o
f
th
e
d
an
d
q
a
x
es
o
f
th
e
c
u
r
r
e
n
t
lo
o
p
.
v
d
an
d
v
q
ar
e
th
e
d
-
an
d
q
-
ax
is
v
o
ltag
e
co
m
p
o
n
e
n
ts
o
f
th
e
co
m
m
o
n
co
u
p
lin
g
p
o
in
t,
r
esp
ec
tiv
ely
.
L
g
an
d
R
g
ar
e
th
e
in
d
u
cto
r
an
d
r
esis
to
r
o
f
t
h
e
m
ai
n
s
-
s
id
e
f
ilt
er
,
an
d
ω
is
th
e
an
g
u
lar
f
r
eq
u
en
cy
o
f
t
h
e
m
ai
n
s
v
o
ltag
e
.
A
n
d
i
d
,
i
q
,
i
d
*
,
an
d
i
q
*
in
d
icate
th
e
d
-
an
d
q
-
ax
is
co
m
p
o
n
e
n
ts
o
f
th
e
m
ain
s
-
s
id
e
cu
r
r
en
ts
an
d
th
e
r
ef
e
r
en
ce
o
u
tp
u
t
cu
r
r
e
n
ts
o
f
th
e
v
o
ltag
e
lo
o
p
,
r
esp
ec
tiv
ely
.
3
.
4
.
L
im
it
s
o
f
cla
s
s
ica
l c
o
ntr
o
l
C
o
n
v
en
tio
n
al
VSG
co
n
tr
o
l,
w
h
ile
em
u
latin
g
th
e
b
eh
av
i
o
r
o
f
a
s
y
n
ch
r
o
n
o
u
s
m
ac
h
in
e,
s
u
f
f
er
s
f
r
o
m
s
ev
er
al
m
ajo
r
lim
itatio
n
s
,
m
ak
in
g
it
in
ef
f
ec
tiv
e
in
d
y
n
a
m
ic
en
v
ir
o
n
m
e
n
ts
,
s
u
ch
as
m
icr
o
g
r
id
s
with
h
ig
h
p
en
etr
atio
n
o
f
r
en
ewa
b
le
en
er
g
ies.
I
ts
f
u
n
d
am
en
tal
p
ar
am
et
er
s
(
v
ir
tu
al
in
er
tia
J
an
d
d
a
m
p
in
g
co
ef
f
icien
t
D
p
)
ar
e
g
en
er
ally
f
ix
ed
,
p
r
ev
e
n
tin
g
it
f
r
o
m
a
d
ap
tin
g
to
r
ap
id
v
ar
iatio
n
s
in
th
e
g
r
id
(
lo
ad
c
h
an
g
es,
v
o
ltag
e/f
r
eq
u
en
cy
f
lu
ctu
atio
n
s
)
,
wh
ich
ca
n
lead
to
in
a
d
eq
u
at
e
o
r
u
n
s
tab
le
r
esp
o
n
s
e
[1
9
]
.
T
h
e
s
en
s
itiv
ity
o
f
its
PI
co
n
tr
o
ller
s
r
eq
u
ir
es
f
in
e
-
t
u
n
in
g
,
o
f
ten
h
eu
r
is
tically
,
o
th
er
wis
e
o
v
er
s
h
o
o
t,
o
s
cillatio
n
,
o
r
s
lo
w
r
esp
o
n
s
e
m
ay
o
cc
u
r
,
p
ar
ticu
la
r
ly
d
u
r
i
n
g
n
etwo
r
k
d
is
tu
r
b
an
ce
s
[
20
]
.
I
ts
co
m
p
u
tatio
n
al
co
m
p
lex
ity
,
d
u
e
to
m
u
ltip
le
co
o
r
d
in
ate
tr
an
s
f
o
r
m
atio
n
s
a
n
d
n
ested
co
n
tr
o
l
lo
o
p
s
,
ca
n
a
d
d
to
th
e
r
ea
l
-
tim
e
lo
ad
o
n
em
b
ed
d
ed
p
latf
o
r
m
s
.
I
n
ad
d
itio
n
,
it
lack
s
m
ec
h
an
is
m
s
f
o
r
d
y
n
am
ic
ad
ap
tatio
n
to
s
u
d
d
en
ch
an
g
es
in
th
e
en
v
ir
o
n
m
e
n
t,
s
u
ch
as
g
r
i
d
v
o
ltag
e
v
a
r
iatio
n
s
o
r
lo
a
d
d
is
co
n
n
ec
tio
n
.
Dep
en
d
en
ce
o
n
ac
cu
r
ate
s
y
s
tem
m
o
d
elin
g
also
co
m
p
r
o
m
is
es
p
er
f
o
r
m
a
n
ce
in
th
e
p
r
esen
ce
o
f
u
n
ce
r
tain
ties
o
r
n
o
n
-
lin
ea
r
ities
th
at
ar
e
n
o
t
tak
e
n
in
to
ac
co
u
n
t
[2
1
]
.
Fin
ally
,
c
o
n
v
en
tio
n
al
VSG
co
n
tr
o
l
tak
es
n
o
ad
v
an
tag
e
o
f
h
is
to
r
ical
d
ata
o
r
p
ast
s
y
s
tem
b
eh
av
io
r
,
ac
tin
g
with
o
u
t
p
r
e
d
i
ctiv
e
ca
p
ab
ilit
y
o
r
ad
ap
tiv
e
le
ar
n
in
g
,
u
n
lik
e
m
o
r
e
r
ec
en
t
ap
p
r
o
ac
h
es
b
ased
o
n
ar
tific
ial
in
tellig
en
ce
o
r
ad
a
p
tiv
e
co
n
tr
o
l
[2
2
].
4.
SUPERV
I
S
E
D
N
E
URA
L
N
E
T
WO
RK
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
aim
s
to
r
ep
lace
co
n
v
e
n
tio
n
al
VSG
co
n
tr
o
l
with
a
s
u
p
er
v
is
ed
n
eu
r
a
l
n
etwo
r
k
ca
p
ab
le
o
f
d
ir
ec
tly
g
en
er
atin
g
in
v
er
ter
c
o
n
tr
o
l
s
ig
n
als
f
r
o
m
m
ea
s
u
r
ed
elec
tr
ical
q
u
a
n
titi
es.
T
h
is
m
eth
o
d
o
lo
g
y
r
elies
o
n
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es.
I
t
is
s
tr
u
ctu
r
ed
in
to
th
r
ee
m
ai
n
s
tag
es:
d
ata
g
en
er
atio
n
,
m
o
d
el
tr
ain
in
g
,
an
d
in
teg
r
atio
n
in
to
th
e
co
n
v
er
ter
ch
ai
n
[
2
3
].
4
.
1
.
Da
t
a
s
et
g
ener
a
t
io
n
A
cr
u
cial
s
tep
in
tr
ain
in
g
a
h
ig
h
-
p
e
r
f
o
r
m
an
ce
n
e
u
r
al
n
et
wo
r
k
is
th
e
cr
ea
tio
n
o
f
a
h
i
g
h
-
q
u
ality
tr
ain
in
g
d
ataset.
I
n
o
u
r
ca
s
e,
th
is
tr
ain
in
g
d
ata
is
g
en
er
ated
f
r
o
m
a
VSG
m
o
d
el
s
im
u
lated
in
MA
T
L
AB
/S
im
u
lin
k
[2
4
]
,
[
2
5
]
.
At
ea
c
h
p
o
in
t
i
n
th
e
s
im
u
latio
n
,
th
e
in
p
u
t
v
a
r
iab
les
o
f
th
e
f
u
tu
r
e
n
e
u
r
al
n
etwo
r
k
a
r
e
m
ea
s
u
r
ed
.
T
h
ese
ar
e
th
e
s
y
s
tem
'
s
k
ey
elec
tr
ical
q
u
an
titi
es:
v
o
ltag
es
in
th
e
d
q
f
r
am
e
(
v
d
,
v
q
)
,
s
tato
r
cu
r
r
en
ts
in
th
e
d
q
f
r
am
e
(
i
d
,
i
q
)
,
in
jecte
d
ac
tiv
e
p
o
wer
(
P
e
)
,
a
n
d
in
jecte
d
r
ea
ctiv
e
p
o
wer
(
Q
e
)
.
At
th
e
s
am
e
tim
e,
th
e
co
r
r
esp
o
n
d
i
n
g
o
u
tp
u
t
s
ig
n
als,
wh
ich
s
er
v
e
as
‘
g
r
o
u
n
d
t
r
u
th
’
,
ar
e
c
o
llected
.
T
h
ese
s
ig
n
als
ar
e
th
e
PW
M
p
u
ls
es g
en
er
ated
b
y
th
e
SP
W
M
m
o
d
u
lato
r
o
f
t
h
e
class
ic
VS
G.
4
.
2
.
Neura
l net
wo
r
k
t
r
a
ini
ng
T
r
ain
in
g
th
e
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
in
v
o
lv
es
u
s
in
g
th
e
d
ata
co
llected
b
y
a
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
el.
I
t
aim
s
to
f
o
r
m
a
d
ir
ec
t
n
o
n
-
lin
ea
r
m
ap
p
in
g
b
etwe
en
in
p
u
ts
an
d
o
u
tp
u
ts
,
in
th
is
ca
s
e,
th
e
s
ix
m
ea
s
u
r
ed
elec
tr
ical
q
u
an
titi
es
an
d
th
e
PW
M
p
u
ls
e
s
ig
n
als.
T
h
e
n
eu
r
al
n
etwo
r
k
u
s
ed
in
th
is
s
tu
d
y
is
th
e
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P),
wh
ich
is
r
ep
r
esen
ted
b
y
a
f
ee
d
f
o
r
wa
r
d
ar
c
h
itectu
r
e
wid
ely
u
s
ed
f
o
r
r
e
g
r
ess
io
n
an
d
class
if
icatio
n
task
s
[2
6
]
,
[
2
7
]
.
T
h
e
ar
ch
itectu
r
e
o
f
th
e
ML
P is
s
h
o
wn
in
F
ig
u
r
e
2
.
No
n
-
lin
ea
r
ity
is
in
tr
o
d
u
ce
d
b
y
ap
p
ly
i
n
g
an
ac
tiv
atio
n
f
u
n
ctio
n
[2
8
]
to
th
e
weig
h
ted
s
u
m
s
o
f
th
e
in
p
u
ts
o
f
ea
ch
n
eu
r
o
n
i
n
th
e
h
id
d
en
lay
er
s
an
d
th
e
o
u
t
p
u
t
lay
er
.
T
h
e
n
etwo
r
k
is
tr
ain
e
d
u
s
in
g
th
e
‘
f
itn
et’
f
u
n
ctio
n
in
MA
T
L
AB
.
T
h
is
f
u
n
ctio
n
is
u
s
ed
to
co
n
f
ig
u
r
e
an
d
tr
ain
a
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
f
o
r
r
eg
r
ess
io
n
task
s
.
T
h
e
L
ev
en
b
e
r
g
-
Ma
r
q
u
ar
d
t a
lg
o
r
ith
m
[2
9
]
is
g
en
er
ally
u
s
ed
f
o
r
th
is
f
u
n
cti
o
n
.
I
t c
o
m
b
i
n
es th
e
f
ast
co
n
v
e
r
g
en
ce
n
ea
r
th
e
m
in
im
u
m
o
f
t
h
e
Gau
s
s
-
New
to
n
m
eth
o
d
an
d
th
e
r
o
b
u
s
tn
ess
f
ar
f
r
o
m
th
e
m
in
i
m
u
m
o
f
g
r
a
d
ien
t d
escen
t,
f
o
r
im
p
r
o
v
ed
n
o
n
lin
ea
r
o
p
tim
izatio
n
.
T
h
e
tr
ain
in
g
s
tep
s
ar
e
s
h
o
w
n
in
F
ig
u
r
e
3
,
with
th
e
in
itializatio
n
o
f
th
e
co
n
n
ec
tio
n
c
o
ef
f
icien
ts
b
etwe
en
n
eu
r
o
n
s
(
weig
h
ts
)
an
d
th
e
v
alu
es
ad
d
ed
to
th
e
wei
g
h
ted
s
u
m
o
f
in
p
u
ts
(
b
ias)
[
30
]
.
T
h
is
is
a
cr
u
cial
s
tep
in
en
ab
lin
g
th
e
n
etwo
r
k
to
lear
n
d
if
f
er
e
n
t
f
ea
tu
r
es.
N
ex
t,
f
o
r
war
d
p
r
o
p
ag
atio
n
is
u
s
ed
to
tr
an
s
m
it
th
e
in
p
u
t
d
ata
th
r
o
u
g
h
th
e
n
etwo
r
k
lay
er
s
.
Ap
p
licatio
n
o
f
a
n
ac
tiv
atio
n
f
u
n
ctio
n
to
th
e
weig
h
ted
s
u
m
o
f
in
p
u
ts
p
r
o
d
u
ce
s
th
e
n
eu
r
al
o
u
tp
u
ts
[3
1
]
.
T
h
e
er
r
o
r
ca
lc
u
latio
n
is
a
co
m
p
a
r
is
o
n
b
etwe
en
t
h
e
o
u
tp
u
t
g
en
e
r
ated
b
y
th
e
n
eu
r
al
n
etwo
r
k
an
d
th
e
o
u
tp
u
t
o
f
th
e
‘
g
r
o
u
n
d
-
t
r
u
th
’
VSG
m
o
d
el
[3
2
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
2
,
J
u
n
e
20
2
6
:
1
4
4
0
-
1450
1444
I
n
th
is
ca
s
e,
to
q
u
a
n
tify
th
e
d
i
f
f
er
en
ce
b
etwe
en
p
r
e
d
icted
an
d
ac
tu
al
o
u
tp
u
t,
a
co
s
t
f
u
n
ctio
n
s
u
ch
as
th
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
is
ca
lcu
lated
.
T
h
e
ca
lcu
lated
er
r
o
r
is
p
r
o
p
ag
ated
f
r
o
m
th
e
o
u
tp
u
t
la
y
er
to
th
e
in
p
u
t
lay
er
th
r
o
u
g
h
th
e
n
e
u
r
al
n
etwo
r
k
.
T
h
e
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
m
i
n
im
izes
th
e
co
s
t
f
u
n
ctio
n
b
y
ca
lcu
latin
g
th
e
g
r
ad
ie
n
ts
o
f
th
is
f
u
n
ctio
n
to
ea
c
h
weig
h
t
an
d
b
ias
o
f
th
e
n
etwo
r
k
,
in
d
icatin
g
th
e
n
ec
ess
ar
y
ad
ju
s
tm
en
ts
.
T
h
is
alg
o
r
ith
m
is
ca
lled
b
ac
k
p
r
o
p
ag
atio
n
[3
3
]
,
an
d
it
ca
lcu
la
tes
th
e
g
r
ad
ien
ts
o
f
th
e
co
s
t
f
u
n
ctio
n
co
n
ce
r
n
in
g
ea
ch
weig
h
t
an
d
b
ias
in
th
e
n
etwo
r
k
,
in
d
icatin
g
th
e
n
ec
ess
ar
y
ad
ju
s
tm
en
ts
.
Af
ter
war
d
s
,
an
u
p
d
ate
is
ap
p
lied
to
f
in
d
th
e
weig
h
ts
an
d
b
ia
s
es
th
at
en
ab
le
m
o
r
e
ac
c
u
r
ate
p
r
ed
ictio
n
o
f
PW
M
p
u
ls
es
[3
4
]
.
On
ce
th
e
e
r
r
o
r
r
ea
c
h
es
a
1
0
-
6
t
h
r
esh
o
ld
,
o
r
p
er
f
o
r
m
a
n
ce
n
o
l
o
n
g
er
im
p
r
o
v
es
o
n
a
s
ep
ar
ate
v
alid
atio
n
s
et,
th
e
r
ep
etitio
n
p
r
o
ce
s
s
o
n
t
h
e
‘
ep
o
ch
’
tr
ain
in
g
d
ata
s
et
is
s
to
p
p
ed
.
T
o
p
r
ev
e
n
t
o
v
e
r
f
itti
n
g
,
it
is
n
ec
ess
ar
y
to
u
s
e
a
v
alid
atio
n
s
et.
T
h
is
o
cc
u
r
s
wh
en
th
e
m
o
d
el
lo
s
es
its
ab
ilit
y
to
g
en
er
alize
to
u
n
s
ee
n
d
ata,
ev
en
if
it
lear
n
s
th
e
tr
ain
in
g
d
ata
to
o
well
.
Fig
u
r
e
2
.
MLP
ar
c
h
itectu
r
e
Fig
u
r
e
3
.
Su
p
er
v
is
ed
tr
ain
i
n
g
p
r
o
ce
s
s
f
o
r
a
n
eu
r
al
n
etwo
r
k
,
in
clu
d
in
g
f
o
r
war
d
p
r
o
p
ag
ati
o
n
,
er
r
o
r
ca
lc
u
latio
n
,
b
ac
k
p
r
o
p
ag
atio
n
,
an
d
weig
h
t
u
p
d
atin
g
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
A
d
a
p
tive
co
n
tr
o
l o
f th
e
virt
u
a
l
s
yn
ch
r
o
n
o
u
s
g
e
n
era
to
r
b
y
d
e
ep
n
eu
r
a
l n
etw
o
r
ks
…
(
Wij
d
a
n
e
E
l Ma
a
ta
o
u
i
)
1445
4
.
3
.
Neura
l
m
o
del int
eg
ra
t
i
o
n
On
ce
tr
ain
ed
an
d
v
alid
ated
,
th
e
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
is
in
teg
r
ated
i
n
to
t
h
e
wi
n
d
e
n
er
g
y
co
n
v
er
s
io
n
ch
ain
to
r
ep
lace
c
o
n
v
en
tio
n
al
VSG
co
n
tr
o
l
,
as
s
h
o
wn
in
F
ig
u
r
e
4
.
T
h
is
‘
e
n
d
-
to
-
en
d
’
ap
p
r
o
ac
h
co
n
s
is
ts
o
f
g
en
e
r
atin
g
PW
M
p
u
ls
es
f
r
o
m
elec
tr
ical
r
atin
g
s
m
ea
s
u
r
ed
in
r
ea
l
tim
e,
u
s
in
g
th
e
n
etwo
r
k
'
s
lear
n
in
g
ca
p
ab
ilit
ies
[3
5
]
.
T
h
is
in
teg
r
at
io
n
o
f
f
er
s
s
ev
er
al
s
ig
n
if
ican
t
ad
v
an
tag
es,
s
u
ch
as
s
im
p
lific
atio
n
o
f
t
h
e
co
n
t
r
o
l
s
tr
u
ctu
r
e,
as
th
e
n
e
u
r
al
n
etw
o
r
k
r
e
p
lace
s
a
co
m
p
le
x
s
et
o
f
co
n
t
r
o
ller
s
,
tr
an
s
f
o
r
m
atio
n
s
,
an
d
m
o
d
u
latio
n
m
o
d
u
l
es,
w
h
ic
h
ca
n
r
ed
u
ce
t
h
e
c
o
m
p
u
ta
ti
o
n
al
l
o
a
d
a
n
d
c
o
m
p
lex
it
y
o
f
i
m
p
le
m
e
n
t
ati
o
n
o
n
e
m
b
e
d
d
ed
p
la
tf
o
r
m
s
,
o
n
ce
th
e
m
o
d
el
h
as
b
ee
n
tr
ai
n
ed
[2
2
]
,
[
3
6
]
.
I
n
cr
ea
s
ed
ad
a
p
tab
ilit
y
an
d
r
o
b
u
s
tn
ess
,
h
av
in
g
b
ee
n
tr
ain
e
d
o
n
a
v
ar
iety
o
f
s
ce
n
ar
io
s
,
th
e
n
eu
r
al
n
etwo
r
k
ca
n
i
n
tr
in
s
ically
ad
ap
t
to
n
etwo
r
k
v
a
r
iatio
n
s
an
d
d
is
tu
r
b
an
ce
s
,
with
o
u
t r
eq
u
i
r
in
g
m
a
n
u
al
ad
j
u
s
tm
en
ts
o
r
ex
p
licit a
d
ap
tatio
n
m
ec
h
an
is
m
s
f
o
r
ea
c
h
p
ar
am
et
er
[3
7
]
.
I
t
ca
n
h
a
n
d
le
n
o
n
-
lin
ea
r
ities
an
d
m
o
d
el
u
n
ce
r
tain
ties
th
at
co
n
v
en
tio
n
al
co
n
tr
o
ller
s
s
tr
u
g
g
le
to
ad
d
r
ess
[3
8
]
.
W
ith
im
p
r
o
v
ed
d
y
n
am
ic
r
esp
o
n
s
iv
en
ess
,
th
e
n
eu
r
al
n
etwo
r
k
'
s
ab
ilit
y
to
p
r
o
ce
s
s
in
f
o
r
m
atio
n
in
p
ar
allel
an
d
g
en
er
ate
d
ir
ec
t
co
m
m
an
d
s
ca
n
p
o
te
n
tially
lead
to
f
aster
r
esp
o
n
s
e
tim
es
an
d
b
etter
t
r
an
s
ien
t
s
y
s
tem
p
er
f
o
r
m
a
n
ce
[3
9
]
.
I
n
teg
r
atio
n
o
f
th
e
n
e
u
r
al
m
o
d
el
in
Simu
lin
k
en
ab
les
r
ig
o
r
o
u
s
v
alid
atio
n
o
f
its
p
er
f
o
r
m
an
ce
i
n
a
co
m
p
lete
s
y
s
tem
en
v
ir
o
n
m
en
t
b
y
d
ir
ec
tly
co
m
p
ar
in
g
its
b
eh
a
v
io
r
with
t
h
at
o
f
co
n
v
en
tio
n
a
l
VSG
co
n
tr
o
l.
Fig
u
r
e
4
.
I
n
teg
r
atio
n
o
f
th
e
tr
a
in
ed
n
eu
r
al
n
etwo
r
k
in
th
e
e
n
e
r
g
y
co
n
v
er
s
io
n
ch
ain
,
r
ep
lacin
g
th
e
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
n
eu
r
al
n
etwo
r
k
co
n
tr
o
l
was
ev
a
lu
ated
an
d
co
m
p
ar
e
d
with
t
h
at
o
f
th
e
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l
th
r
o
u
g
h
s
im
u
latio
n
s
in
MA
T
L
A
B
/Si
m
u
lin
k
.
Fig
u
r
e
5
s
h
o
ws
th
e
r
ap
id
a
n
d
s
tab
le
co
n
v
er
g
en
ce
o
f
th
e
n
eu
r
al
n
e
two
r
k
.
Af
te
r
ap
p
r
o
x
im
ately
2
0
0
iter
atio
n
s
,
th
e
MSE
d
ec
r
e
ases
s
ig
n
if
ican
tly
,
d
em
o
n
s
tr
atin
g
ef
f
ec
tiv
e
lear
n
in
g
.
T
h
e
c
u
r
v
es
ass
o
ciate
d
with
th
e
t
r
ain
in
g
,
v
alid
atio
n
,
a
n
d
test
s
ets
r
em
ain
p
ar
allel,
in
d
icatin
g
g
e
n
er
aliza
tio
n
with
o
u
t
o
v
e
r
f
itti
n
g
.
T
h
e
s
tab
ilit
y
,
r
o
b
u
s
tn
ess
,
an
d
ac
cu
r
ac
y
o
f
th
e
tr
ai
n
ed
n
etwo
r
k
d
e
m
o
n
s
tr
ate
its
r
elev
an
ce
as a
n
alter
n
ativ
e
to
co
n
v
e
n
tio
n
al
VSG
co
n
tr
o
l
.
Fig
u
r
e
6
s
h
o
ws
a
co
m
p
ar
is
o
n
b
etwe
en
two
co
n
tr
o
l
s
tr
ateg
ie
s
:
Fig
u
r
e
6
(
a)
co
n
v
en
tio
n
al
V
SG
co
n
tr
o
l
an
d
Fig
u
r
e
6
(
b
)
n
e
u
r
al
n
etwo
r
k
-
b
ased
co
n
tr
o
l.
I
n
th
e
ca
s
e
o
f
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l,
r
elativ
ely
lar
g
e
o
s
cillatio
n
s
ar
o
u
n
d
th
e
n
o
m
i
n
al
f
r
eq
u
en
cy
o
f
5
0
Hz
ca
n
b
e
o
b
s
er
v
ed
.
T
h
is
b
eh
a
v
io
r
i
s
d
u
e
to
f
ix
ed
-
g
ain
co
n
tr
o
ller
s
,
wh
o
s
e
p
e
r
f
o
r
m
an
c
e
is
s
en
s
itiv
e
to
in
itial p
ar
am
eter
s
an
d
n
etwo
r
k
co
n
d
itio
n
s
.
I
n
co
n
tr
ast,
th
er
e
is
a
s
ig
n
if
ican
t
r
ed
u
ctio
n
in
t
h
e
am
p
litu
d
e
o
f
o
s
cillatio
n
s
,
as
well
as
a
s
h
o
r
ter
s
tab
ilizatio
n
tim
e
f
o
r
n
e
u
r
al
n
etwo
r
k
-
b
ased
c
o
n
tr
o
l.
T
h
is
s
tr
ateg
y
m
ak
es
it
p
o
s
s
ib
le
to
g
en
er
ate
m
o
r
e
ap
p
r
o
p
r
iate
co
n
tr
o
l
p
u
ls
es
in
r
ea
l
tim
e,
with
o
u
t
ex
p
licit
d
ep
en
d
en
ce
o
n
r
ig
id
s
y
s
tem
m
o
d
elin
g
.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
e
v
alu
e
o
f
th
e
p
r
o
p
o
s
ed
en
d
-
to
-
e
n
d
ap
p
r
o
ac
h
to
r
ep
lace
co
n
v
en
ti
o
n
al
co
n
tr
o
ll
er
s
in
VSG
s
,
wh
ile
im
p
r
o
v
in
g
s
y
s
tem
s
tab
ilit
y
an
d
r
esp
o
n
s
e
tim
e
.
C
hoppe
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
2
,
J
u
n
e
20
2
6
:
1
4
4
0
-
1450
1446
Fig
u
r
e
5
.
Neu
r
al
n
etwo
r
k
p
er
f
o
r
m
an
ce
(
a)
(
b
)
Fig
u
r
e
6
.
Sy
s
tem
f
r
e
q
u
en
c
y
w
ith
(
a)
co
n
v
en
tio
n
al
VSG
co
n
t
r
o
l a
n
d
(
b
)
n
eu
r
al
n
etwo
r
k
c
o
n
tr
o
l
Fig
u
r
e
7
co
m
p
ar
es
th
e
ac
tiv
e
p
o
wer
in
jecte
d
b
y
th
e
s
y
s
te
m
with
Fig
u
r
e
7
(
a)
c
o
n
v
e
n
tio
n
al
VSG
co
n
tr
o
l a
n
d
Fig
u
r
e
7
(
b
)
n
eu
r
al
n
etwo
r
k
-
b
ased
co
n
tr
o
l.
I
n
b
o
t
h
Fig
u
r
es,
th
e
p
o
wer
g
en
e
r
ally
f
o
llo
ws th
e
5
MW
s
etp
o
in
t.
Fo
r
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l,
it
ca
n
b
e
s
ee
n
th
at
t
h
e
ac
tiv
e
p
o
wer
in
jecte
d
s
h
o
ws
m
o
r
e
p
r
o
n
o
u
n
ce
d
f
lu
ctu
atio
n
s
ar
o
u
n
d
th
e
s
etp
o
i
n
t
d
u
e
to
th
e
lim
itatio
n
s
o
f
PI
co
n
tr
o
ller
s
.
Ho
wev
er
,
it
ca
n
b
e
s
ee
n
th
at
n
eu
r
al
co
n
tr
o
l p
r
o
v
id
es b
etter
r
eg
u
lat
io
n
.
Oscill
atio
n
s
ar
o
u
n
d
th
e
s
etp
o
in
t a
r
e
s
ig
n
if
ican
tly
r
ed
u
ce
d
.
T
h
is
co
m
p
ar
is
o
n
s
h
o
ws th
at
n
eu
r
al
co
n
tr
o
l is m
o
r
e
s
tab
le
an
d
r
o
b
u
s
t,
wh
ich
i
m
p
r
o
v
es r
e
n
ewa
b
le
en
e
r
g
y
p
r
o
d
u
ctio
n
.
Fig
u
r
e
8
co
m
p
a
r
es
th
e
o
u
tp
u
t
cu
r
r
en
t
q
u
ality
f
o
r
th
e
two
co
n
tr
o
l
s
tr
ateg
ies
v
ia
a
tim
e
an
d
f
r
eq
u
en
c
y
an
aly
s
is
.
Fig
u
r
e
8
(
a
)
co
n
v
en
t
io
n
al
VSG
co
n
tr
o
l
h
as
a
h
ig
h
er
T
HD
o
f
0
.
5
1
%,
with
h
ar
m
o
n
ic
co
m
p
o
n
en
ts
v
is
ib
le
in
th
e
Fo
u
r
ier
s
p
ec
tr
u
m
.
I
n
co
n
tr
ast,
Fig
u
r
e
8
(
b
)
th
e
n
eu
r
al
co
n
tr
o
l
h
as
a
s
in
u
s
o
id
a
l
o
u
tp
u
t
s
ig
n
al,
with
a
v
er
y
lo
w
T
HD
o
f
0
.
0
4
%.
T
h
is
p
er
f
o
r
m
an
ce
i
n
d
icate
s
th
e
r
em
ar
k
ab
le
a
b
ilit
y
o
f
th
e
n
eu
r
al
n
etwo
r
k
to
g
en
er
ate
ap
p
r
o
p
r
iate
co
n
tr
o
l sig
n
als,
m
in
im
izin
g
d
is
to
r
tio
n
.
T
h
is
co
m
p
ar
is
o
n
d
em
o
n
s
tr
ates
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
n
eu
r
al
n
etwo
r
k
in
im
p
r
o
v
in
g
o
u
t
p
u
t
cu
r
r
en
t
q
u
ality
a
n
d
r
ed
u
ci
n
g
h
ar
m
o
n
i
cs
wh
ile
co
m
p
ly
in
g
with
g
r
id
co
n
n
ec
tio
n
co
n
d
itio
n
s
.
T
ab
le
1
s
h
o
ws
th
e
g
e
n
er
al
p
ar
am
eter
s
o
f
th
e
s
y
s
tem
,
in
clu
d
in
g
a
n
o
m
i
n
al
f
r
eq
u
e
n
cy
o
f
5
0
Hz,
wh
ich
co
r
r
esp
o
n
d
s
to
th
e
s
tan
d
ar
d
f
r
eq
u
e
n
cy
o
f
elec
tr
ical
n
etwo
r
k
s
.
T
h
e
ac
tiv
e
p
o
wer
in
jecte
d
is
s
et
at
5
M
W
,
wh
ich
r
ep
r
esen
ts
a
r
ea
lis
tic
s
ca
le
f
o
r
a
n
i
n
d
u
s
tr
i
al
wi
n
d
c
o
n
v
er
s
i
o
n
ap
p
l
ic
ati
o
n
.
T
h
e
r
e
ac
ti
v
e
p
o
we
r
is
z
er
o
,
r
ef
l
ec
ti
n
g
o
p
e
r
at
i
o
n
at
a
u
n
it
y
p
o
w
er
f
ac
to
r
.
T
h
e
h
ig
h
s
witch
in
g
f
r
e
q
u
en
cy
o
f
1
0
k
Hz
e
n
s
u
r
es f
in
e
m
o
d
u
latio
n
an
d
g
o
o
d
o
u
tp
u
t s
ig
n
al
q
u
ality
.
T
ab
le
2
d
etails
th
e
p
ar
am
eter
s
o
f
th
e
o
u
tp
u
t
f
ilter
,
wh
ic
h
p
lay
s
a
k
e
y
r
o
le
in
s
m
o
o
th
i
n
g
th
e
s
ig
n
als
o
u
tp
u
t
b
y
t
h
e
in
v
er
ter
a
n
d
lim
itin
g
th
e
h
a
r
m
o
n
ics
in
jecte
d
i
n
to
th
e
g
r
id
.
T
h
e
h
ig
h
v
alu
es
o
f
th
e
r
esis
to
r
s
an
d
in
d
u
cto
r
s
o
n
th
e
in
v
er
ter
s
id
e
r
ef
lect
a
p
r
o
n
o
u
n
ce
d
f
ilter
in
g
s
tr
ateg
y
to
d
am
p
en
h
i
g
h
-
f
r
eq
u
en
cy
d
is
tu
r
b
a
n
ce
s
.
On
th
e
g
r
id
s
id
e,
t
h
e
lo
wer
r
e
s
is
to
r
an
d
in
d
u
cto
r
v
al
u
es
ar
e
in
ten
d
ed
to
m
ain
tain
t
h
e
c
o
u
p
lin
g
d
y
n
am
ics
with
th
e
f
ast
g
r
id
.
T
h
e
f
ilter
'
s
ca
p
ac
itan
ce
,
co
m
b
i
n
ed
with
th
e
d
a
m
p
in
g
r
esis
to
r
,
en
s
u
r
es
ef
f
ec
tiv
e
p
ass
iv
e
f
ilter
in
g
an
d
h
elp
s
r
e
d
u
ce
h
ar
m
o
n
ic
d
is
to
r
tio
n
.
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
A
d
a
p
tive
co
n
tr
o
l o
f th
e
virt
u
a
l
s
yn
ch
r
o
n
o
u
s
g
e
n
era
to
r
b
y
d
e
ep
n
eu
r
a
l n
etw
o
r
ks
…
(
Wij
d
a
n
e
E
l Ma
a
ta
o
u
i
)
1447
(
a)
(
b
)
Fig
u
r
e
7
.
Activ
e
p
o
wer
o
f
th
e
s
y
s
tem
with
(
a)
co
n
v
e
n
tio
n
al
VSG
co
n
tr
o
l a
n
d
(
b
)
n
eu
r
al
n
e
two
r
k
co
n
tr
o
l
(
a)
(
b
)
Fig
u
r
e
8
.
T
o
tal
h
ar
m
o
n
ic
d
is
to
r
tio
n
with
(
a)
c
o
n
v
e
n
tio
n
al
VS
G
co
n
tr
o
l a
n
d
(
b
)
n
e
u
r
al
n
etw
o
r
k
co
n
tr
o
l
T
ab
le
1
.
Sy
s
tem
p
ar
a
m
eter
s
P
a
r
a
me
t
e
r
s
S
y
mb
o
l
V
a
l
u
e
F
r
e
q
u
e
n
c
y
f
5
0
H
z
A
c
t
i
v
e
p
o
w
e
r
P
5
M
W
R
e
a
c
t
i
v
e
p
o
w
e
r
Q
0
V
A
S
w
i
t
c
h
i
n
g
f
r
e
q
u
e
n
c
y
f
sw
1
0
k
H
z
T
ab
le
2
.
Fil
ter
p
ar
am
eter
s
P
a
r
a
me
t
e
r
s
S
y
mb
o
l
V
a
l
u
e
I
n
v
e
r
t
e
r
s
i
d
e
r
e
si
s
t
o
r
Ri
4
3
7
3
.
0
3
Ω
I
n
v
e
r
t
e
r
s
i
d
e
i
n
d
u
c
t
o
r
Li
0
.
0
3
3
H
G
r
i
d
s
i
d
e
r
e
s
i
st
o
r
Rg
1
7
4
.
9
3
Ω
G
r
i
d
s
i
d
e
i
n
d
u
c
t
o
r
Lg
5
.
6
7
6
µ
H
D
a
mp
i
n
g
r
e
s
i
st
o
r
RC
2
1
7
.
9
7
Ω
C
a
p
a
c
i
t
y
C
8
.
5
4
4
mF
T
ab
le
3
s
u
m
m
ar
izes
th
e
p
a
r
a
m
eter
s
o
f
th
e
PI
co
n
tr
o
ller
s
u
s
ed
in
th
e
v
ar
io
u
s
c
o
n
tr
o
l
lo
o
p
s
,
cu
r
r
e
n
t
v
o
ltag
e,
an
d
o
p
tim
al
to
r
q
u
e.
T
h
e
k
p
an
d
k
i
g
ain
s
f
o
r
v
o
ltag
e
co
n
tr
o
l
a
r
e
lo
w,
wh
ich
is
ty
p
ical
f
o
r
s
y
s
tem
s
with
lo
n
g
tim
e
co
n
s
tan
ts
.
T
h
e
g
ain
s
f
o
r
cu
r
r
e
n
t
co
n
tr
o
l
ar
e
h
i
g
h
er
to
e
n
ab
le
a
r
ap
i
d
r
esp
o
n
s
e
to
lo
a
d
v
ar
iatio
n
s
.
T
h
e
p
ar
a
m
eter
s
f
o
r
o
p
tim
al
to
r
q
u
e
c
o
n
tr
o
l
s
tr
ik
e
a
g
o
o
d
b
alan
ce
b
etwe
en
r
esp
o
n
s
iv
en
ess
an
d
s
tab
ilit
y
in
m
ac
h
in
e
co
n
tr
o
l,
e
n
s
u
r
in
g
th
e
ef
f
icien
t tr
an
s
f
e
r
o
f
m
ec
h
an
ical
en
er
g
y
to
elec
tr
i
ca
l e
n
er
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
6
9
4
I
n
t J Po
w
E
lec
&
Dr
i Sy
s
t
,
Vo
l.
1
7
,
No
.
2
,
J
u
n
e
20
2
6
:
1
4
4
0
-
1450
1448
T
ab
le
3
.
C
o
n
tr
o
ller
s
’
p
ar
am
ete
r
s
P
a
r
a
me
t
e
r
s
S
y
mb
o
l
V
a
l
u
e
V
o
l
t
a
g
e
c
o
n
t
r
o
l
kp
0
.
0
0
4
5
8
7
ki
0
.
0
0
2
2
C
u
r
r
e
n
t
c
o
n
t
r
o
l
kp
1
.
7
4
9
3
ki
0
.
0
0
0
0
0
5
6
7
6
O
p
t
i
mal
t
o
r
q
u
e
c
o
n
t
r
o
l
kp
0
.
0
0
2
1
1
ki
0
.
0
0
4
4
8
6.
CO
NCLU
SI
O
N
T
h
is
ar
ticle
p
r
o
p
o
s
es
a
n
ew
a
p
p
r
o
ac
h
th
at
in
v
o
lv
es
r
ep
lacin
g
th
e
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l
with
an
en
d
-
to
-
e
n
d
n
e
u
r
al
n
etwo
r
k
.
T
h
is
co
n
tr
o
l
is
b
ased
o
n
a
s
u
p
er
v
is
ed
lear
n
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
k
ca
p
ab
le
o
f
g
en
er
atin
g
th
e
in
v
er
ter
co
n
tr
o
l
p
u
ls
es,
v
o
ltag
es,
cu
r
r
en
ts
,
an
d
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
wer
.
T
h
e
s
im
u
latio
n
r
esu
lts
d
em
o
n
s
tr
ated
th
e
s
tab
i
lity
o
f
f
r
e
q
u
en
c
y
an
d
ac
tiv
e
p
o
wer
,
as
well
as
a
r
ed
u
ctio
n
in
T
HD
to
0
.
0
4
%
co
m
p
ar
ed
to
0
.
5
1
%
f
o
r
c
o
n
v
e
n
tio
n
al
VSG
co
n
tr
o
l.
I
n
ad
d
iti
o
n
,
t
h
e
v
e
r
y
lo
w
MSE
s
h
o
we
d
a
g
e
n
er
aliza
tio
n
o
f
th
e
n
eu
r
al
n
etwo
r
k
.
T
h
ese
f
in
d
in
g
s
p
r
o
v
e
t
h
e
r
o
b
u
s
tn
ess
an
d
f
lex
ib
ilit
y
o
f
n
e
u
r
al
n
etwo
r
k
-
b
ased
co
n
tr
o
l
in
th
e
f
ac
e
o
f
t
h
e
lim
itatio
n
s
o
f
co
n
v
en
tio
n
al
VSG
co
n
tr
o
l.
T
h
is
ap
p
r
o
ac
h
en
ab
les
win
d
en
er
g
y
c
o
n
v
er
s
io
n
s
y
s
tem
s
to
b
etter
m
ee
t g
r
id
co
n
n
ec
tio
n
r
eq
u
ir
em
e
n
ts
in
ter
m
s
o
f
s
tab
il
ity
an
d
p
o
wer
q
u
ality
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
t
h
an
k
th
e
a
n
o
n
y
m
o
u
s
r
e
v
iewe
r
s
f
o
r
th
eir
h
el
p
f
u
l
an
d
co
n
s
tr
u
ctiv
e
co
m
m
en
ts
th
at
wo
u
ld
g
r
ea
tly
co
n
tr
ib
u
te
to
im
p
r
o
v
in
g
th
e
f
i
n
al
v
er
s
io
n
o
f
th
e
p
ap
e
r
.
T
h
e
y
wo
u
ld
also
lik
e
to
th
an
k
th
e
E
d
ito
r
s
f
o
r
th
eir
g
en
er
o
u
s
co
m
m
e
n
ts
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
e
d
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
W
ijd
an
e
E
l M
aa
tao
u
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
b
d
e
l
o
u
a
h
e
d
A
b
o
u
n
a
d
a
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
g
en
er
ated
d
u
r
in
g
an
d
/o
r
a
n
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t
s
tu
d
y
a
r
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
G
l
o
b
a
l
W
i
n
d
E
n
e
r
g
y
C
o
u
n
c
i
l
,
“
W
i
n
d
i
n
d
u
s
t
r
y
i
n
st
a
l
l
s
r
e
c
o
r
d
c
a
p
a
c
i
t
y
i
n
2
0
2
4
d
e
sp
i
t
e
p
o
l
i
c
y
i
n
st
a
b
i
l
i
t
y
,
”
G
W
EC
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
g
w
e
c
.
n
e
t
/
g
w
e
c
-
n
e
w
s
/
w
i
n
d
-
i
n
d
u
st
r
y
-
i
n
st
a
l
l
s
-
r
e
c
o
r
d
-
c
a
p
a
c
i
t
y
-
in
-
2
0
2
4
-
d
e
s
p
i
t
e
-
p
o
l
i
c
y
-
i
n
s
t
a
b
i
l
i
t
y
.
[
A
c
c
e
sse
d
:
A
p
r
.
1
,
2
0
2
6
]
.
[
2
]
V
.
V
.
Y
a
d
a
v
a
n
d
S
.
B
a
l
a
su
b
r
a
m
a
n
i
y
a
n
,
“
S
y
n
c
h
r
o
n
i
z
a
t
i
o
n
s
t
a
b
i
l
i
t
y
a
n
d
c
o
n
t
r
o
l
s
t
r
a
t
e
g
i
e
s
f
o
r
P
M
S
G
-
b
a
se
d
w
i
n
d
e
n
e
r
g
y
s
y
st
e
ms
u
n
d
e
r
g
r
i
d
f
a
u
l
t
c
o
n
d
i
t
i
o
n
s,
”
E
n
e
r
g
y
R
e
p
o
rt
s
,
v
o
l
.
1
3
,
p
p
.
6
1
4
8
–
6
1
6
0
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
5
.
0
5
.
0
5
2
.
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
A
d
a
p
tive
co
n
tr
o
l o
f th
e
virt
u
a
l
s
yn
ch
r
o
n
o
u
s
g
e
n
era
to
r
b
y
d
e
ep
n
eu
r
a
l n
etw
o
r
ks
…
(
Wij
d
a
n
e
E
l Ma
a
ta
o
u
i
)
1449
[
3
]
Y
.
Zh
e
n
g
,
Y
.
X
u
,
Y
.
Y
a
n
g
,
L.
H
u
a
,
a
n
d
Y
.
Y
a
n
g
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
a
d
a
p
t
i
v
e
v
i
r
t
u
a
l
sy
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
b
a
sed
o
n
i
m
p
r
o
v
e
d
a
c
t
i
v
e
p
o
w
e
r
l
o
o
p
i
n
p
h
o
t
o
v
o
l
t
a
i
c
st
o
r
a
g
e
s
y
s
t
e
ms
,
”
Fr
o
n
t
i
e
rs
i
n
E
n
e
r
g
y
R
e
se
a
rc
h
,
v
o
l
.
1
2
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
e
n
r
g
.
2
0
2
4
.
1
4
6
8
6
2
9
.
[
4
]
C
.
L
u
a
n
d
X
.
Z
h
u
a
n
,
“
A
d
a
p
t
i
v
e
c
o
n
t
r
o
l
f
o
r
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
p
a
r
a
me
t
e
r
s
b
a
se
d
o
n
s
o
f
t
a
c
t
o
r
c
r
i
t
i
c
,
”
S
e
n
so
rs
,
v
o
l
.
2
4
,
n
o
.
7
,
p
.
2
0
3
5
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
0
7
2
0
3
5
.
[
5
]
T.
S
h
i
,
J.
S
u
n
,
X
.
H
a
n
,
a
n
d
C
.
T
a
n
g
,
“
R
e
s
e
a
r
c
h
o
n
a
d
a
p
t
i
v
e
o
p
t
i
ma
l
c
o
n
t
r
o
l
st
r
a
t
e
g
y
o
f
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
i
n
e
r
t
i
a
a
n
d
d
a
m
p
i
n
g
p
a
r
a
m
e
t
e
r
s,”
I
ET P
o
w
e
r
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
1
2
1
–
1
3
3
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
4
9
/
p
e
l
2
.
1
2
6
2
0
.
[
6
]
L.
Y
a
n
g
,
X
.
Z
h
u
,
Y
.
Li
,
X
.
C
h
e
n
,
B
.
H
u
a
n
g
,
a
n
d
Z.
X
u
,
“
V
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
c
o
n
t
r
o
l
s
t
r
a
t
e
g
y
a
n
d
i
n
e
r
t
i
a
a
n
a
l
y
si
s
o
f
l
a
r
g
e
-
s
c
a
l
e
e
n
e
r
g
y
st
o
r
a
g
e
,
”
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
P
o
w
e
r
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
9
,
n
o
.
2
,
p
p
.
1
9
0
–
1
9
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
9
7
8
1
/
j
.
i
ss
n
.
1
6
7
3
-
9
1
4
0
.
2
0
2
4
.
0
2
.
0
2
1
.
[
7
]
M
.
Y
a
n
g
,
L.
Z
h
a
n
g
,
X
.
S
o
n
g
,
W
.
K
a
n
g
,
a
n
d
Z
.
K
a
n
g
,
“
A
t
r
a
n
si
e
n
t
c
o
n
t
r
o
l
s
t
r
a
t
e
g
y
f
o
r
g
r
i
d
-
f
o
r
mi
n
g
p
h
o
t
o
v
o
l
t
a
i
c
s
y
st
e
ms
b
a
se
d
o
n
d
y
n
a
mi
c
v
i
r
t
u
a
l
i
m
p
e
d
a
n
c
e
a
n
d
R
B
F
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
4
,
n
o
.
4
,
p
.
7
8
5
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
4
0
4
0
7
8
5
.
[
8
]
O
.
B
a
b
a
y
o
mi
,
Y
.
Li
,
Z
.
Z
h
a
n
g
,
a
n
d
K
.
-
B
.
P
a
r
k
,
“
A
d
v
a
n
c
e
d
c
o
n
t
r
o
l
o
f
g
r
i
d
-
c
o
n
n
e
c
t
e
d
mi
c
r
o
g
r
i
d
s:
c
h
a
l
l
e
n
g
e
s,
a
d
v
a
n
c
e
s,
a
n
d
t
r
e
n
d
s
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
P
o
w
e
r
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
4
0
,
n
o
.
6
,
p
p
.
7
6
8
1
–
7
7
0
8
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TPE
L.
2
0
2
5
.
3
5
2
6
2
4
6
.
[
9
]
J.
H
a
n
,
X
.
F
e
n
g
,
H
.
Z
h
a
o
,
P
.
H
u
,
a
n
d
C
.
H
e
,
“
A
d
a
p
t
i
v
e
V
S
G
c
o
n
t
r
o
l
s
t
r
a
t
e
g
y
c
o
n
s
i
d
e
r
i
n
g
e
n
e
r
g
y
s
t
o
r
a
g
e
S
O
C
c
o
n
st
r
a
i
n
t
s,
”
Fro
n
t
i
e
rs
i
n
E
n
e
r
g
y
Re
s
e
a
rc
h
,
v
o
l
.
1
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
e
n
r
g
.
2
0
2
3
.
1
2
7
8
6
4
8
.
[
1
0
]
F
.
W
a
n
g
,
L.
Zh
a
n
g
,
X
.
F
e
n
g
,
a
n
d
H
.
G
u
o
,
“
A
n
a
d
a
p
t
i
v
e
c
o
n
t
r
o
l
s
t
r
a
t
e
g
y
f
o
r
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
,
”
I
E
E
E
T
ra
n
sa
c
t
i
o
n
s
o
n
I
n
d
u
st
r
y
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
4
,
n
o
.
5
,
p
p
.
5
1
2
4
–
5
1
3
3
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
A
.
2
0
1
8
.
2
8
5
9
3
8
4
.
[
1
1
]
Y
.
Le
C
u
n
,
Y
.
B
e
n
g
i
o
,
a
n
d
G
.
H
i
n
t
o
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
,
”
N
a
t
u
re
,
v
o
l
.
5
2
1
,
n
o
.
7
5
5
3
,
p
p
.
4
3
6
–
4
4
4
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
3
8
/
n
a
t
u
r
e
1
4
5
3
9
.
[
1
2
]
I
.
S
.
M
o
h
a
me
d
,
S
.
R
o
v
e
t
t
a
,
T
.
D
.
D
o
,
T.
D
r
a
g
i
c
e
v
i
c
,
a
n
d
A
.
A
.
Z.
D
i
a
b
,
“
A
n
e
u
r
a
l
-
n
e
t
w
o
r
k
-
b
a
se
d
m
o
d
e
l
p
r
e
d
i
c
t
i
v
e
c
o
n
t
r
o
l
o
f
t
h
r
e
e
-
p
h
a
s
e
i
n
v
e
r
t
e
r
w
i
t
h
a
n
o
u
t
p
u
t
LC
F
i
l
t
e
r
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
2
4
7
3
7
–
1
2
4
7
4
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
8
2
2
0
.
[
1
3
]
Q
.
H
u
e
t
a
l
.
,
“
G
r
i
d
-
f
o
r
m
i
n
g
i
n
v
e
r
t
e
r
e
n
a
b
l
e
d
v
i
r
t
u
a
l
p
o
w
e
r
p
l
a
n
t
s
w
i
t
h
i
n
e
r
t
i
a
su
p
p
o
r
t
c
a
p
a
b
i
l
i
t
y
,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
S
m
a
rt
G
ri
d
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
4
1
3
4
–
4
1
4
3
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TSG
.
2
0
2
2
.
3
1
4
1
4
1
4
.
[
1
4
]
Y
.
W
a
n
g
a
n
d
R
.
-
J.
W
a
i
,
“
A
d
a
p
t
i
v
e
f
u
z
z
y
-
n
e
u
r
a
l
-
n
e
t
w
o
r
k
p
o
w
e
r
d
e
c
o
u
p
l
i
n
g
s
t
r
a
t
e
g
y
f
o
r
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
i
n
mi
c
r
o
-
g
r
i
d
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
Po
w
e
r
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
3
7
,
n
o
.
4
,
p
p
.
3
8
7
8
–
3
8
9
1
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TPE
L.
2
0
2
1
.
3
1
2
0
5
1
9
.
[
1
5
]
W
.
El
M
a
a
t
a
o
u
i
,
S
.
El
D
a
o
u
d
i
,
A
.
A
b
o
u
n
a
d
a
,
a
n
d
M
.
M
a
b
r
o
u
k
i
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
a
n
d
si
n
u
s
o
i
d
a
l
p
u
l
se
w
i
d
t
h
mo
d
u
l
a
t
i
o
n
i
n
a
w
i
n
d
h
i
g
h
p
o
w
e
r
c
o
n
v
e
r
s
i
o
n
c
h
a
i
n
,
”
Arc
h
i
v
e
s o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
7
3
,
n
o
.
4
,
p
p
.
9
6
1
–
9
7
6
,
2
0
2
4
,
d
o
i
:
1
0
.
2
4
4
2
5
/
a
e
e
.
2
0
2
4
.
1
5
2
1
0
5
.
[
1
6
]
J.
Li
u
,
F
.
R
a
f
i
,
J.
L
u
,
a
n
d
M
.
J.
H
o
ssa
i
n
,
“
N
e
u
t
r
a
l
c
u
r
r
e
n
t
c
o
m
p
e
n
sa
t
i
o
n
i
n
a
V
S
G
-
b
a
s
e
d
t
h
r
e
e
-
p
h
a
se
f
o
u
r
-
w
i
r
e
m
i
c
r
o
g
r
i
d
s
y
st
e
m,
”
i
n
2
0
1
8
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
En
v
i
r
o
n
m
e
n
t
a
n
d
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
2
0
1
8
I
EEE
I
n
d
u
st
r
i
a
l
a
n
d
C
o
m
m
e
rc
i
a
l
Po
w
e
r
S
y
s
t
e
m
s
Eu
ro
p
e
(
EEEI
C
/
I
&C
PS
Eu
r
o
p
e
)
,
Ju
n
.
2
0
1
8
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
E
EEI
C
.
2
0
1
8
.
8
4
9
4
4
8
8
.
[
1
7
]
W
.
E
l
M
a
a
t
a
o
u
i
,
S
.
El
D
a
o
u
d
i
,
L
.
L
a
z
r
a
k
,
a
n
d
M
.
M
a
b
r
o
u
k
i
,
“
I
mp
r
o
v
e
d
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
g
r
i
d
si
d
e
p
o
w
e
r
c
o
n
v
e
r
si
o
n
c
h
a
i
n
b
y
a
d
o
p
t
i
n
g
m
u
l
t
i
l
e
v
e
l
i
n
v
e
r
t
e
r
t
o
p
o
l
o
g
i
e
s
w
i
t
h
a
n
o
p
t
i
mi
z
e
d
LC
L
f
i
l
t
e
r
,
”
i
n
D
i
g
i
t
a
l
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
5
5
,
S
.
M
o
t
a
h
h
i
r
a
n
d
B
.
B
o
ss
o
u
f
i
,
Ed
s
.
,
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
N
e
t
w
o
r
k
s
a
n
d
S
y
s
t
e
ms,
v
o
l
.
4
5
5
.
,
C
h
a
m
:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
2
,
p
p
.
5
0
7
–
5
1
5
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
0
2
4
4
7
-
4
_
5
2
.
[
1
8
]
W
.
El
M
a
a
t
a
o
u
i
,
S
.
El
D
a
o
u
d
i
,
L
.
La
z
r
a
k
,
a
n
d
M
.
M
a
b
r
o
u
k
i
,
“
M
i
n
i
m
i
z
e
d
t
o
t
a
l
h
a
r
m
o
n
i
c
d
i
st
o
r
t
i
o
n
o
f
a
mu
l
t
i
-
l
e
v
e
l
i
n
v
e
r
t
e
r
o
f
a
w
i
n
d
p
o
w
e
r
c
o
n
v
e
r
s
i
o
n
c
h
a
i
n
s
y
n
c
h
r
o
n
i
z
e
d
t
o
t
h
e
g
r
i
d
-
LC
L
f
i
l
t
e
r
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
t
h
i
r
d
h
a
r
mo
n
i
c
c
a
n
c
e
l
l
a
t
i
o
n
,
”
ELEC
T,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
2
7
–
4
0
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
5
1
5
2
/
e
l
e
c
t
r
i
c
a
.
2
0
2
1
.
2
1
0
8
6
.
[1
9
]
Z.
Li
n
g
,
Y
.
L
i
u
,
Z.
W
a
n
g
,
a
n
d
J.
Y
i
n
,
“
A
d
a
p
t
i
v
e
i
n
e
r
t
i
a
a
n
d
d
a
m
p
i
n
g
o
f
g
r
i
d
‐
c
o
n
n
e
c
t
e
d
i
n
v
e
r
t
e
r
w
i
t
h
i
m
p
r
o
v
e
d
V
S
G
c
o
n
t
r
o
l
,
”
I
ET
Po
w
e
r
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
6
,
n
o
.
1
6
,
p
p
.
2
7
6
9
–
2
7
8
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
4
9
/
p
e
l
2
.
1
2
6
0
0
.
[
20
]
M
.
A
.
S
h
o
b
u
g
,
F
.
Y
a
n
g
,
a
n
d
J
.
L
u
,
“
S
t
a
b
i
l
i
t
y
i
m
p
r
o
v
e
m
e
n
t
o
f
m
i
c
r
o
g
r
i
d
s
u
n
d
e
r
d
y
n
a
m
i
c
l
o
a
d
c
o
n
d
i
t
i
o
n
s
:
A
n
e
w
a
d
a
p
t
i
v
e
v
i
r
t
u
a
l
sy
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
b
a
s
e
d
v
i
r
t
u
a
l
i
n
e
r
t
i
a
c
o
n
t
r
o
l
a
p
p
r
o
a
c
h
,
”
Re
s
u
l
t
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
5
,
p
.
1
0
4
5
5
6
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
5
.
1
0
4
5
5
6
.
[2
1
]
H
.
G
r
o
v
e
r
,
S
.
S
h
a
r
ma
,
A
.
V
e
r
ma
,
M
.
J.
H
o
ss
a
i
n
,
a
n
d
I
.
K
a
mw
a
,
“
A
d
a
p
t
i
v
e
p
a
r
a
me
t
e
r
t
u
n
i
n
g
s
t
r
a
t
e
g
y
o
f
V
S
G
-
b
a
se
d
i
sl
a
n
d
e
d
mi
c
r
o
g
r
i
d
u
n
d
e
r
u
n
c
e
r
t
a
i
n
t
i
e
s
,
”
El
e
c
t
r
i
c
P
o
w
e
r
S
y
s
t
e
m
s
Re
se
a
rc
h
,
v
o
l
.
2
3
5
,
p
.
1
1
0
8
5
4
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
p
sr
.
2
0
2
4
.
1
1
0
8
5
4
.
[2
2
]
X
.
D
i
n
g
a
n
d
J.
C
a
o
,
“
D
e
e
p
a
n
d
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
i
n
v
i
r
t
u
a
l
s
y
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,”
E
n
e
rg
i
e
s
,
v
o
l
.
1
7
,
n
o
.
1
1
,
p
.
2
6
2
0
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
7
1
1
2
6
2
0
.
[2
3
]
Y
.
L
i
e
t
a
l
.
,
“
D
a
t
a
-
d
r
i
v
e
n
o
p
t
i
m
a
l
c
o
n
t
r
o
l
s
t
r
a
t
e
g
y
f
o
r
v
i
r
t
u
a
l
sy
n
c
h
r
o
n
o
u
s
g
e
n
e
r
a
t
o
r
v
i
a
d
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
Mo
d
e
r
n
Po
w
e
r
S
y
st
e
m
s
a
n
d
C
l
e
a
n
E
n
e
r
g
y
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
9
1
9
–
9
2
9
,
2
0
2
1
,
d
o
i
:
1
0
.
3
5
8
3
3
/
M
P
C
E.
2
0
2
0
.
0
0
0
2
6
7
.
[2
4
]
Y
.
L
u
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
sy
n
t
h
e
t
i
c
d
a
t
a
g
e
n
e
r
a
t
i
o
n
:
A
r
e
v
i
e
w
,
”
a
rX
i
v
p
re
p
ri
n
t
a
r
X
i
v
:
2
3
0
2
.
0
4
0
6
2
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
3
0
2
.
0
4
0
6
2
.
[2
5
]
C
.
R
.
S
t
i
c
h
t
a
n
d
S
.
A
.
B
u
k
o
w
s
k
i
,
P
o
w
e
r
syst
e
m
w
a
v
e
f
o
rm
d
a
t
a
s
e
t
s
f
o
r
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
,
I
d
a
h
o
N
a
t
i
o
n
a
l
La
b
o
r
a
t
o
r
y
,
I
d
a
h
o
F
a
l
l
s,
I
D
,
U
S
A
,
R
e
p
.
I
N
L/
R
P
T
-
23
-
7
6
0
2
9
-
R
e
v
0
0
0
,
2
0
2
4
.
[2
6
]
J.
C
a
r
mi
c
h
a
e
l
a
n
d
Y
.
Li
a
o
,
“
B
a
y
e
s
i
a
n
o
p
t
i
m
i
z
a
t
i
o
n
o
f
m
u
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
mo
d
e
l
s
f
o
r
p
o
w
e
r
d
i
st
r
i
b
u
t
i
o
n
sy
s
t
e
m
st
a
t
e
e
st
i
mat
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Em
e
r
g
i
n
g
El
e
c
t
ri
c
P
o
w
e
r
S
y
s
t
e
m
s
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
4
9
5
–
5
0
7
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
5
1
5
/
i
j
e
e
p
s
-
2
0
2
2
-
0
3
2
8
.
[2
7
]
M
.
Q
i
a
o
,
Y
.
L
i
a
n
g
,
A
.
T
a
v
a
r
e
s,
a
n
d
X
.
S
h
i
,
“
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
n
e
t
w
o
r
k
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
c
h
a
o
t
i
c
t
i
me
seri
e
s
m
o
d
e
l
i
n
g
,”
En
t
r
o
p
y
,
v
o
l
.
2
5
,
n
o
.
7
,
p
.
9
7
3
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
5
0
7
0
9
7
3
.
[2
8
]
I
.
K
h
a
l
f
a
o
u
i
-
H
a
ssa
n
i
a
n
d
S
.
K
e
ss
e
l
h
e
i
m,
“
P
o
l
y
n
o
m
i
a
l
,
t
r
i
g
o
n
o
met
r
i
c
,
a
n
d
t
r
o
p
i
c
a
l
a
c
t
i
v
a
t
i
o
n
s,
”
a
r
Xi
v
p
re
p
r
i
n
t
a
r
X
i
v
:
2
5
0
2
.
0
1
2
4
7
,
M
a
r
.
2
0
2
6
.
[2
9
]
J.
J.
M
o
r
é
,
“
T
h
e
Le
v
e
n
b
e
r
g
-
M
a
r
q
u
a
r
d
t
a
l
g
o
r
i
t
h
m:
I
mp
l
e
me
n
t
a
t
i
o
n
a
n
d
t
h
e
o
r
y
,
”
1
9
7
8
,
p
p
.
1
0
5
–
1
1
6
.
d
o
i
:
1
0
.
1
0
0
7
/
B
F
b
0
0
6
7
7
0
0
.
[
30
]
M
.
V
.
N
a
r
k
h
e
d
e
,
P
.
P
.
B
a
r
t
a
k
k
e
,
a
n
d
M
.
S
.
S
u
t
a
o
n
e
,
“
A
r
e
v
i
e
w
o
n
w
e
i
g
h
t
i
n
i
t
i
a
l
i
z
a
t
i
o
n
s
t
r
a
t
e
g
i
e
s
f
o
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
Ar
t
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
5
,
n
o
.
1
,
p
p
.
2
9
1
–
3
2
2
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
2
1
-
1
0
0
3
3
-
z.
[3
1
]
S
.
R
.
D
u
b
e
y
,
S
.
K
.
S
i
n
g
h
,
a
n
d
B
.
B
.
C
h
a
u
d
h
u
r
i
,
“
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s i
n
d
e
e
p
l
e
a
r
n
i
n
g
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
a
n
d
b
e
n
c
h
mark
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
5
0
3
,
p
p
.
9
2
–
1
0
8
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
2
.
0
6
.
1
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.