T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
2
7
2
9
~
2
7
3
6
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i5
.
1
4
3
9
6
2729
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Perf
o
rma
nce
as
ses
sm
ent
o
f
a
n
opti
miza
tion stra
tegy
pro
po
sed
for po
wer sys
te
m
s
H
a
ro
ld P
uin
,
Cesa
r
H
er
na
nd
ez
Tec
h
n
o
l
o
g
ica
l
F
a
c
u
lt
y
,
Un
i
v
e
rsid
a
d
Distrit
a
l
F
ra
n
c
isc
o
Jo
se
d
e
Ca
l
d
a
s,
Co
l
o
m
b
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
4
,
2
0
1
9
R
ev
is
ed
Ma
y
1
5
,
2
0
2
0
Acc
ep
ted
J
u
n
1
7
,
2
0
2
0
In
t
h
e
p
re
se
n
t
a
rti
c
le,
t
h
e
se
lec
ti
o
n
p
r
o
c
e
ss
o
f
th
e
to
p
o
l
o
g
y
o
f
a
n
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N)
a
s
we
ll
a
s
i
ts
c
o
n
fig
u
ra
ti
o
n
a
re
e
x
p
o
se
d
.
Th
e
AN
N
wa
s
a
d
a
p
ted
t
o
w
o
rk
wi
th
th
e
Ne
wto
n
Ra
p
h
so
n
(NR)
m
e
th
o
d
fo
r
th
e
c
a
l
c
u
latio
n
o
f
p
o
we
r
flo
w
a
n
d
v
o
lt
a
g
e
o
p
ti
m
iz
a
ti
o
n
i
n
th
e
P
Q
n
o
d
e
s
o
f
a
1
0
-
n
o
d
e
p
o
we
r
sy
ste
m
re
p
re
se
n
ted
b
y
t
h
e
IEE
E
1
2
5
0
sta
n
d
a
rd
sy
ste
m
.
Th
e
p
u
r
p
o
se
is
to
a
ss
e
ss
a
n
d
c
o
m
p
a
re
it
s
re
su
lt
s
with
th
e
o
n
e
s
o
b
tain
e
d
b
y
im
p
lem
e
n
ti
n
g
a
n
t
c
o
lo
n
y
a
n
d
g
e
n
e
ti
c
a
lg
o
r
it
h
m
s
i
n
th
e
o
p
ti
m
iz
a
ti
o
n
o
f
th
e
sa
m
e
sy
ste
m
.
As
a
re
su
lt
,
it
is
sta
ted
th
a
t
t
h
e
v
o
lt
a
g
e
s
i
n
a
ll
sy
ste
m
n
o
d
e
s
su
r
p
a
ss
0
,
9
9
p
.
u
.
,
t
h
u
s
re
p
re
se
n
ti
n
g
a
2
0
%
in
c
re
a
se
in
th
e
o
p
ti
m
a
l
sc
e
n
a
rio
,
w
h
e
re
th
e
a
lg
o
rit
h
m
to
o
k
3
0
se
c
o
n
d
s,
o
f
wh
ich
9
se
c
o
n
d
s
we
re
u
se
d
in
th
e
train
i
n
g
a
n
d
v
a
li
d
a
t
io
n
p
r
o
c
e
ss
e
s
o
f
t
h
e
AN
N.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
New
to
n
R
ap
h
s
o
n
Op
tim
izatio
n
Po
wer
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
:
C
esar
Her
n
an
d
ez
,
T
ec
h
n
o
lo
g
ical
Facu
lty
,
Un
iv
er
s
id
ad
Dis
tr
ital Fr
an
cisco
J
o
s
e
d
e
C
ald
as,
C
alle
6
8
D
B
is
A
Su
r
#
4
9
F
–
7
0
,
B
o
g
o
tá
D.
C
.
,
1
1
1
9
4
1
,
C
o
lo
m
b
ia.
E
m
ail:
ca
h
er
n
an
d
ez
s
@
u
d
is
tr
it
al.
ed
u
.
co
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
teg
r
atio
n
o
f
p
o
wer
g
en
er
atio
n
,
tr
an
s
m
is
s
io
n
an
d
d
is
tr
ib
u
tio
n
s
y
s
tem
s
with
th
e
p
r
o
g
r
ess
ev
id
en
ce
d
in
t
h
e
in
f
o
r
m
atio
n
an
d
co
m
m
u
n
icatio
n
tech
n
o
lo
g
ies
(
I
C
T
)
s
ec
to
r
h
as
b
ee
n
e
n
co
m
p
ass
ed
with
in
th
e
d
ev
elo
p
m
en
t
o
f
th
e
c
o
n
ce
p
t
k
n
o
wn
as
s
m
ar
t
g
r
id
s
.
I
t
h
a
s
a
llo
wed
to
u
n
ite
in
a
s
in
g
le
m
an
ag
em
en
t
s
y
s
tem
th
e
ar
ea
s
o
f
p
r
o
tectio
n
co
o
r
d
i
n
atio
n
,
co
n
t
r
o
l,
m
ea
s
u
r
e
an
d
e
co
n
o
m
ic
d
is
p
atch
o
f
an
elec
tr
i
c
n
etwo
r
k
.
I
ts
m
ain
p
u
r
p
o
s
e
is
to
ac
h
iev
e
in
teg
r
at
io
n
th
r
o
u
g
h
th
e
ef
f
icien
t
a
n
d
r
atio
n
al
u
s
e
o
f
en
e
r
g
y
as
well
as
th
e
in
cr
ea
s
e
o
f
r
eliab
ilit
y
,
s
ec
u
r
ity
an
d
f
lex
ib
i
lity
o
f
elec
tr
ic
s
y
s
tem
s
[
1
-
3
]
.
T
h
e
in
h
e
r
en
t
r
esu
lt
o
f
th
e
d
ev
elo
p
m
en
t
o
f
s
m
ar
t
g
r
i
d
s
h
as
b
ee
n
th
e
co
n
s
tan
t
s
ea
r
ch
f
o
r
th
e
im
p
lem
en
tatio
n
o
f
alg
o
r
ith
m
s
th
at
o
p
tim
ize
p
o
wer
s
y
s
tem
s
b
ased
o
n
tech
n
ical
an
d
ec
o
n
o
m
ic
cr
iter
ia
as
well
as
en
er
g
y
q
u
ality
.
I
m
p
r
o
v
em
en
t
p
r
ac
tices
ar
e
also
p
r
o
p
o
s
ed
s
u
ch
as
co
n
tr
o
l
s
y
s
tem
s
to
co
r
r
ec
t
v
o
l
tag
e
u
n
b
alan
ce
s
in
p
o
wer
g
en
er
ati
o
n
u
n
its
em
b
e
d
d
ed
with
in
th
e
n
etwo
r
k
[
4
-
7
]
,
m
u
lti
-
a
g
en
t
s
y
s
tem
s
[
8
-
10
]
to
co
m
p
en
s
ate
th
e
h
i
g
h
v
a
r
iab
i
lity
o
f
th
e
en
e
r
g
y
s
u
p
p
ly
r
e
lated
to
alter
n
ativ
e
s
o
u
r
ce
s
o
f
g
en
e
r
atio
n
,
a
n
d
th
e
f
o
r
ec
ast
o
f
th
e
ef
f
ec
ts
o
f
a
m
ass
iv
e
co
n
n
ec
tio
n
o
f
elec
tr
ic
v
eh
icles
in
th
e
f
u
tu
r
e
[
11
-
13
]
.
Oth
er
p
r
o
p
o
s
als
h
av
e
f
o
cu
s
ed
i
n
th
e
ef
f
ec
ts
o
f
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
in
th
e
p
r
o
jectio
n
o
f
th
e
ec
o
n
o
m
ic
d
is
p
atch
b
ased
o
n
p
r
o
b
a
b
ilit
y
f
u
n
ctio
n
s
d
eliv
er
ed
b
y
th
e
s
tatis
tical
m
eth
o
d
L
atin
Hy
p
er
c
u
b
e
Sam
p
lin
g
[
14
]
.
Ot
h
er
s
tr
ateg
ies
h
a
v
e
f
o
cu
s
ed
o
n
d
e
v
elo
p
in
g
alg
o
r
it
h
m
s
th
at
cr
ea
te
u
s
ag
e
p
r
o
f
iles
o
f
th
e
g
en
er
ato
r
s
lin
k
ed
to
a
n
etwo
r
k
,
ac
co
r
d
i
n
g
to
th
e
co
n
s
u
m
p
tio
n
d
em
a
n
d
[
15,
16
]
.
T
h
e
ca
lcu
latio
n
o
f
th
e
v
o
ltag
e
v
alu
es in
v
o
lv
es so
lv
in
g
a
s
y
s
t
em
o
f
s
im
u
ltan
e
o
u
s
n
o
n
-
lin
ea
r
eq
u
atio
n
s
in
m
o
s
t
ca
s
es.
T
o
ac
h
iev
e
th
i
s
,
th
e
New
to
n
-
R
ap
h
s
o
n
(
NR
)
an
d
Gau
s
s
-
Sied
el
iter
ativ
e
m
e
th
o
d
s
[
4
]
.
T
h
e
NR
m
eth
o
d
co
n
s
is
ts
o
f
an
iter
ativ
e
p
r
o
ce
d
u
r
e
in
w
h
ich
n
o
n
-
lin
ea
r
eq
u
atio
n
s
ar
e
u
s
ed
in
v
o
lv
in
g
v
o
ltag
e
m
ag
n
itu
d
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
7
2
9
-
2736
2730
an
d
an
g
le
v
ar
ia
b
les
as
well
as
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
wer
.
Sin
ce
th
er
e
ar
e
o
n
ly
two
p
o
wer
e
q
u
atio
n
s
,
th
e
o
th
er
two
v
ar
iab
les
m
u
s
t
b
e
ca
lcu
lat
ed
[
8
]
.
I
n
[
9
]
,
th
e
NR
m
eth
o
d
is
u
s
ed
to
ca
lcu
late
p
h
o
to
v
o
ltaic
p
ar
am
eter
s
an
d
ca
r
r
y
o
u
t
t
h
e
m
o
d
ellin
g
p
r
o
c
ess
.
T
h
e
Gau
s
s
-
Seid
el
m
eth
o
d
is
an
iter
ativ
e
m
eth
o
d
in
wh
ich
th
e
n
u
m
b
er
o
f
u
n
k
n
o
wn
v
ar
iab
les
is
eq
u
al
to
th
e
n
u
m
b
er
o
f
e
q
u
atio
n
s
t
o
s
o
lv
e.
I
t
co
n
s
is
ts
o
n
d
esig
n
in
g
a
co
n
v
er
g
in
g
s
u
cc
ess
io
n
ac
co
r
d
in
g
to
a
p
r
e
v
io
u
s
ly
d
ef
in
e
d
cr
iter
ia
[
11
]
,
t
h
e
co
n
v
e
r
g
en
ce
v
alu
es
a
r
e
th
e
s
o
lu
tio
n
o
f
th
e
n
o
d
al
v
o
ltag
es
an
d
p
o
wer
s
o
f
th
e
elec
tr
ic
s
y
s
tem
.
I
n
[
12
]
,
th
e
Ga
u
s
s
-
Seid
el
m
eth
o
d
is
u
s
ed
as
t
h
e
m
ain
s
tr
ateg
y
t
o
ac
ce
ler
ate
th
e
s
o
lu
tio
n
o
f
p
o
wer
f
lo
w
in
a
h
ig
h
-
p
er
f
o
r
m
an
ce
r
ec
o
n
f
ig
u
r
ab
le
c
o
m
p
u
te
r
.
I
t
is
ev
id
en
t
th
at
it
is
th
e
p
r
o
c
ess
to
b
e
o
p
tim
ized
with
in
th
e
s
m
ar
t
g
r
id
th
at
d
eter
m
in
es
th
e
ty
p
e
o
f
alg
o
r
ith
m
to
b
e
im
p
lem
en
ted
,
wh
eth
er
it
is
a
lin
ea
r
s
y
s
tem
o
r
n
o
t.
C
u
r
r
en
tly
,
th
e
alg
o
r
ith
m
s
o
f
th
e
iter
ativ
e
[
17
]
(
New
to
n
m
eth
o
d
[
18
]
,
c
o
n
j
u
g
ated
g
r
ad
ien
t,
i
n
ter
p
o
latio
n
,
etc)
an
d
h
e
u
r
is
tic
ty
p
es
[
19
]
(
ev
o
lu
tio
n
ar
y
alg
o
r
ith
m
s
,
g
en
etic
alg
o
r
ith
m
s
,
Neld
er
Me
ad
,
am
o
n
g
o
th
er
s
)
ar
e
th
e
m
o
s
t
co
m
m
o
n
ly
im
p
lem
e
n
ted
.
Fu
r
th
er
m
o
r
e
,
th
e
r
e
a
r
e
c
o
m
p
u
tatio
n
al
m
o
d
els
th
at
ca
n
b
e
u
s
ed
in
o
p
tim
izatio
n
m
o
d
els
s
u
ch
as
th
e
Ar
tific
ial
Neu
r
al
Net
wo
r
k
s
(
ANN)
,
a
b
io
-
in
s
p
ir
ed
al
g
o
r
ith
m
f
r
o
m
1
9
4
3
th
at
was
r
eleg
ated
to
th
e
b
ac
k
g
r
o
u
n
d
d
u
e
t
o
th
e
co
m
p
u
tatio
n
al
ca
p
ac
ity
th
at
it
r
e
q
u
ir
ed
at
t
h
e
tim
e.
Ho
wev
er
,
with
th
e
u
n
s
to
p
p
a
b
le
d
ev
el
o
p
m
en
t
in
elec
tr
o
n
ics
an
d
s
em
i
-
co
n
d
u
c
to
r
m
ater
ials
an
d
th
e
m
an
u
f
ac
tu
r
e
o
f
in
cr
ea
s
in
g
ly
p
o
wer
f
u
l
p
r
o
ce
s
s
o
r
s
,
th
e
ap
p
licatio
n
o
f
ANN
h
as
r
is
en
.
T
h
ey
ca
n
b
e
class
if
ied
in
to
iter
ativ
e
o
r
h
eu
r
is
tic
m
eth
o
d
s
d
ep
en
d
i
n
g
o
n
t
h
eir
lear
n
in
g
p
r
o
ce
s
s
[
20,
21
]
.
Sin
ce
th
eir
r
ein
tr
o
d
u
ctio
n
as
a
co
m
p
u
tatio
n
al
m
o
d
el,
ANNs
h
av
e
b
ee
n
u
s
ed
to
s
im
u
late
d
if
f
e
r
en
t
ty
p
es
o
f
p
r
o
ce
s
s
es
[
22
-
25
]
,
d
u
e
to
th
eir
s
wif
t
p
r
ed
ic
tio
n
o
f
v
ar
iab
le
s
.
No
n
eth
eless
,
th
eir
u
s
e
as
an
o
p
tim
izatio
n
m
o
d
el
is
n
o
t y
et
ex
ten
d
ed
an
d
n
ee
d
s
s
o
m
e
s
o
r
t o
f
iter
ativ
e
o
r
h
eu
r
is
tic
alg
o
r
ith
m
in
o
r
d
er
to
wo
r
k
.
Hen
ce
,
th
is
ar
ticle
p
r
esen
ts
th
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
o
f
an
ar
tific
ial
n
eu
r
al
n
et
wo
r
k
co
m
b
in
ed
w
ith
t
h
e
New
to
n
R
ap
h
s
o
n
(
NR
)
m
eth
o
d
f
o
r
th
e
ca
lcu
latio
n
o
f
p
o
wer
f
lo
w
a
n
d
t
h
e
o
p
tim
izatio
n
o
f
n
o
d
al
v
o
ltag
es
in
p
o
wer
s
y
s
tem
s
with
n
n
o
d
es
.
T
h
is
is
s
u
b
s
eq
u
en
tly
im
p
lem
en
ted
in
a
1
0
-
n
o
d
e
I
E
E
E
1
2
5
0
s
tan
d
ar
d
ized
p
o
wer
s
y
s
tem
with
th
e
p
u
r
p
o
s
e
o
f
g
u
ar
an
teein
g
v
o
ltag
es
o
v
e
r
0
.
9
8
p
.
u
.
in
all
s
y
s
tem
n
o
d
es.
Fin
ally
,
th
e
p
er
f
o
r
m
an
ce
wi
ll
b
e
ass
es
s
ed
b
y
co
m
p
ar
in
g
th
e
r
esu
lts
o
b
tain
e
d
with
th
e
b
ee
s
war
m
an
d
an
t
co
lo
n
y
alg
o
r
ith
m
s
f
o
r
th
e
s
a
m
e
p
o
wer
s
y
s
tem
.
T
h
is
h
elp
s
to
d
eter
m
in
e
its
p
o
ten
tial
f
o
r
im
p
lem
en
tatio
n
in
s
m
ar
t
g
r
id
s
as
a
n
o
p
tim
izatio
n
m
eth
o
d
b
ased
o
n
th
e
elec
tr
ic
en
er
g
y
cr
iter
ia.
2.
P
RO
P
O
SE
D
AL
G
O
R
I
T
H
M
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
d
e
v
elo
p
ed
in
its
to
tality
in
th
e
MA
T
L
AB
2
0
1
8
b
n
u
m
er
ical
co
m
p
u
tin
g
s
o
f
twar
e.
I
n
itially
,
th
e
e
x
ec
u
ti
o
n
o
f
th
e
NR
m
eth
o
d
is
ca
r
r
ie
d
o
u
t
in
o
r
d
er
to
o
b
tain
t
h
e
m
a
g
n
itu
d
e
a
n
d
an
g
le
o
f
th
e
v
o
ltag
e,
b
ased
o
n
th
e
im
p
ed
an
ce
m
atr
ix
an
d
th
e
ac
tiv
e
an
d
r
ea
ctiv
e
p
o
wer
d
ata.
Usi
n
g
th
e
p
o
wer
f
lo
w
ca
lcu
latio
n
s
,
th
e
alg
o
r
ith
m
ca
n
p
r
o
ce
ed
to
ass
ess
th
e
v
o
ltag
e
in
ea
ch
PQ
n
o
d
e
th
r
o
u
g
h
ANN
to
d
eter
m
in
e
wh
eth
er
th
e
n
o
d
es
ar
e
u
n
d
er
p
o
wer
ed
in
co
m
p
a
r
is
o
n
to
th
e
o
p
tim
al
v
alu
e
u
s
ed
f
o
r
tr
ain
in
g
.
T
h
u
s
,
a
ca
p
ac
itiv
e
r
ea
ctan
ce
o
f
0
.
1
p
.
u
.
is
i
n
jecte
d
if
th
e
ass
ess
ed
n
o
d
e
d
o
es
n
o
t
co
m
p
ly
with
th
is
o
p
tim
izatio
n
p
a
r
am
eter
.
W
h
en
th
e
ANN
co
m
p
letes
th
e
ass
e
s
s
m
en
t
o
f
all
p
o
w
er
s
y
s
tem
n
o
d
es,
th
e
alg
o
r
ith
m
ex
ec
u
tes
th
e
NR
m
eth
o
d
with
th
e
p
u
r
p
o
s
e
o
f
d
eter
m
in
in
g
t
h
e
n
ew
v
o
ltag
es
in
th
e
s
y
s
tem
,
wh
ich
ar
e
o
n
ce
a
g
ain
ass
ess
ed
b
y
th
e
ANN.
T
h
e
p
r
o
ce
s
s
is
co
n
clu
d
ed
wh
e
n
it
is
estab
lis
h
ed
t
h
at
all
th
e
PQ
n
o
d
al
v
o
ltag
es
a
r
e
eq
u
al
o
r
ab
o
v
e
t
h
e
o
p
tim
al
r
ef
er
en
ce
v
alu
e.
I
n
th
is
m
an
n
er
,
t
h
e
NR
an
d
ANN
m
eth
o
d
s
en
ab
le
th
e
o
p
tim
izatio
n
o
f
th
e
p
o
wer
s
y
s
tem
,
b
y
g
iv
i
n
g
th
e
u
s
er
a
f
in
al
r
e
p
o
r
t
in
.
x
ls
x
f
o
r
m
at
with
t
h
e
o
p
tim
ized
v
alu
es
o
f
v
o
ltag
e
m
ag
n
itu
d
e
an
d
an
g
le
f
o
r
ea
ch
n
o
d
e
as
well
as
th
e
ca
lcu
latio
n
o
f
g
e
n
er
ated
ac
tiv
e
-
r
ea
ctiv
e
p
o
wer
an
d
th
e
d
em
an
d
.
T
h
e
u
s
er
is
in
f
o
r
m
ed
o
n
th
e
v
al
u
e
o
f
th
e
ca
p
ac
itiv
e
co
r
r
ec
tio
n
r
e
q
u
ir
ed
b
y
ea
c
h
n
o
d
e
t
o
elev
at
e
th
e
v
o
ltag
e
to
o
p
tim
al
v
alu
e
s
.
Fig
u
r
e
1
s
h
o
ws
th
e
f
lo
w
d
iag
r
am
o
f
th
e
d
e
v
elo
p
ed
alg
o
r
ith
m
.
T
h
e
n
eu
r
al
n
etwo
r
k
p
r
o
p
o
s
ed
in
th
e
alg
o
r
ith
was
d
ev
elo
p
ed
b
y
im
p
lem
en
tin
g
th
e
b
ase
co
d
es
o
f
th
e
MA
T
L
AB
f
itn
et
f
u
n
ctio
n
,
estab
lis
h
in
g
a
s
tr
u
ctu
r
e
o
f
th
r
ee
lay
er
s
:
in
p
u
t
lay
er
,
h
id
d
en
la
y
er
an
d
o
u
t
p
u
t
lay
er
.
T
h
is
is
illu
s
tr
ated
in
Fig
u
r
e
2
a
n
d
th
e
c
o
m
p
o
n
en
ts
ar
e
ex
p
lain
ed
in
th
is
s
ec
tio
n
.
2
.
1
.
I
np
ut
v
a
ria
bles
I
t
is
th
e
in
f
o
r
m
atio
n
g
iv
en
to
t
h
e
n
eu
r
al
n
etwo
r
k
,
f
o
r
t
h
e
tr
a
n
in
g
p
h
ase
as
well
as
th
e
v
ali
d
atio
n
an
d
test
in
g
p
h
ases
.
I
n
th
is
s
p
ec
if
ic
ca
s
e,
th
e
n
o
d
al
v
o
ltag
e
in
p
.
u
.
m
ay
v
ar
y
f
r
o
m
0
to
1
.
T
h
e
u
s
er
is
in
f
o
r
m
ed
o
n
th
e
v
alu
e
o
f
th
e
ca
p
ac
itiv
e
co
r
r
ec
tio
n
r
eq
u
i
r
ed
b
y
ea
ch
n
o
d
e
to
elev
ate
th
e
v
o
ltag
e
to
o
p
tim
al
v
alu
es.
Fig
u
r
e
1
s
h
o
ws th
e
f
lo
w
d
iag
r
am
o
f
t
h
e
d
ev
elo
p
e
d
alg
o
r
ith
m
.
2.
2
.
L
a
y
er
s
T
h
e
m
o
d
el
h
as
th
r
ee
ty
p
es
o
f
lay
er
s
:
in
p
u
t
lay
er
,
h
id
d
en
lay
er
an
d
o
u
tp
u
t
lay
er
.
T
h
e
in
p
u
t
lay
er
h
as
o
n
e
n
eu
r
o
n
,
wh
ich
in
d
iv
id
u
ally
r
ec
eiv
es
th
e
i
n
f
o
r
m
atio
n
o
f
t
h
e
v
o
ltag
e
in
ea
ch
n
o
d
e.
T
h
e
h
id
d
en
lay
er
h
as
3
0
n
eu
r
o
n
s
,
wh
ich
is
a
n
u
m
b
er
d
eter
m
in
ed
b
y
co
n
s
id
er
in
g
th
at
th
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
p
r
e
s
en
t
in
th
is
la
y
er
is
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
P
erfo
r
ma
n
ce
a
s
s
ess
men
t o
f a
n
o
p
timiz
a
tio
n
s
tr
a
teg
y
p
r
o
p
o
s
e
d
fo
r
p
o
w
er sys
tems
(
Ha
r
o
ld
P
u
in
)
2731
p
r
o
p
o
r
tio
n
al
to
th
e
ac
cu
r
ac
y
o
f
th
e
n
eu
r
al
n
etwo
r
k
r
eg
a
r
d
in
g
t
h
e
class
if
icatio
n
o
f
d
ata
b
u
t
it
i
s
also
p
r
o
p
o
r
tio
n
al
to
th
e
tim
e
r
eq
u
ir
e
d
to
p
e
r
f
o
r
m
s
u
ch
task
.
I
n
ter
m
s
o
f
th
e
c
o
n
n
ec
tio
n
s
,
ea
c
h
n
eu
r
o
n
in
th
i
s
lay
er
is
co
n
n
ec
ted
with
a
n
eu
r
o
n
o
f
th
e
in
p
u
t
la
y
er
d
ep
en
d
in
g
o
h
th
e
weig
h
ts
o
f
th
e
co
n
n
ec
tio
n
s
.
I
t
is
im
p
o
r
tan
t
to
clar
if
y
th
at
th
er
e
m
ay
b
e
m
o
r
e
th
an
o
n
e
h
i
d
d
en
lay
er
.
T
h
e
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
o
f
a
n
e
u
r
al
n
etwo
r
k
is
d
ir
ec
tly
r
elate
d
with
h
o
w
ea
s
y
it
is
to
class
if
y
th
e
d
esire
d
o
u
tp
u
t
ac
co
r
d
i
n
g
to
th
e
i
n
p
u
t.
Fig
u
r
e
3
s
h
o
ws
th
e
o
u
t
p
u
t
v
s
in
p
u
t
d
iag
r
am
with
ty
p
ical
v
alu
es
o
f
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
o
f
a
p
o
wer
s
y
s
tem
.
Acc
o
r
d
in
g
to
th
e
d
iag
r
am
,
f
o
r
in
p
u
t
v
ar
iab
les
with
v
alu
es
b
elo
w
0
.
9
,
th
e
n
eu
r
al
n
etwo
r
k
ca
n
g
e
n
er
ate
an
o
u
tp
u
t
o
f
0
.
Fo
r
i
n
p
u
t
v
ar
iab
les
o
v
er
0
.
9
,
th
e
n
eu
r
al
n
etwo
r
k
m
u
s
t
g
en
er
ate
an
o
u
tp
u
t
o
f
0
.
1
.
T
h
is
allo
ws
th
e
p
er
f
ec
t
d
iv
is
io
n
o
f
th
e
d
ata
th
r
o
u
g
h
a
lin
ea
r
cu
r
v
e
.
I
n
ca
s
e
th
e
o
u
tp
u
t
s
tates
ca
n
n
o
t
b
e
lin
ea
r
l
y
s
ep
ar
ated
,
th
e
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
m
u
s
t
k
ee
p
in
cr
ea
s
in
g
.
T
h
e
o
u
tp
u
t
lay
er
h
as
o
n
e
n
e
u
r
o
n
,
co
r
r
esp
o
n
d
i
n
g
to
th
e
n
u
m
b
er
o
f
o
u
tp
u
t
v
ar
iab
les
with
a
m
in
im
u
m
o
f
2
s
tates.
2.
3
.
Weig
hts
W
eig
h
ts
ar
e
co
ef
f
icien
ts
th
at
alter
th
e
in
p
u
t
v
alu
e
o
f
n
e
u
r
o
n
s
,
s
tar
tin
g
f
r
o
m
th
e
h
i
d
d
en
lay
er
,
co
n
s
id
er
in
g
th
e
p
e
r
io
d
icity
i
n
wh
ich
a
s
p
ec
if
ic
i
n
p
u
t
v
alu
e
i
s
tr
an
s
m
itted
co
m
p
ar
e
d
to
a
d
esire
d
o
u
tp
u
t
v
alu
e.
T
h
is
s
tr
en
g
th
en
s
th
e
co
n
n
ec
tio
n
with
th
e
tr
an
s
m
itted
n
e
u
r
o
n
at
th
e
ex
p
en
s
e
o
f
th
e
co
n
n
ec
tio
n
with
o
th
er
n
eu
r
o
n
s
.
Hen
ce
,
weig
h
ts
also
h
av
e
th
e
f
u
n
ctio
n
n
ality
o
f
in
te
r
co
n
n
ec
tin
g
n
eu
r
o
n
s
in
d
if
f
er
e
n
t la
y
er
s
.
De
v
e
l
o
p
o
f
p
o
w
e
r
f
l
o
w
a
n
a
l
y
s
i
s
w
i
t
h
N
R
RN
A
t
r
a
in
in
g
p
r
o
c
e
s
s
w
it
h
7
0
0
0
t
y
p
e
v
a
lu
e
s
RN
A
v
a
l
i
d
a
t
i
o
n
p
o
r
c
e
s
s
w
i
t
h
1
5
0
0
t
y
p
e
v
a
lu
e
s
R
N
A
t
e
s
t
p
r
o
c
e
s
s
w
it
h
1
5
0
0
t
y
p
e
v
a
lu
e
s
P
Q
n
o
d
e
s
in
d
iv
id
u
a
l
R
N
A
e
v
a
lu
a
t
io
n
P
o
w
e
r
e
le
c
t
r
ic
s
y
s
t
e
m
in
it
ia
l
d
a
t
a
r
e
a
d
in
g
fr
o
m
.
x
ls
x
fi
le
T
h
e
n
o
d
e
h
a
v
e
u
n
d
e
r
v
o
lt
a
g
e
?
NO
G
e
n
e
r
a
t
io
n
o
f
t
h
e
.
x
ls
x
r
e
p
o
r
t
fi
le
Y
E
S
I
n
d
iv
i
d
u
a
lly
in
y
e
c
t
io
n
o
f
r
e
a
c
t
iv
e
c
o
m
p
e
n
s
a
t
io
n
in
t
h
e
a
ll
P
Q
n
o
d
e
s
o
f
t
h
e
s
y
s
t
e
m
w
it
h
u
n
d
e
r
v
o
lt
a
g
e
N
R
a
lg
o
r
it
m
e
j
e
c
u
t
io
n
Fig
u
r
e
1.
Flo
w
d
ia
g
r
am
o
f
th
e
d
ev
elo
p
e
d
alg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
7
2
9
-
2736
2732
a
2
.
1
a
2
.
2
a
2
.
3
a
2
.
30
a
3
.
1
a
1
.
1
I
n
p
u
t
l
a
y
er
Hi
d
d
en
l
a
y
e
r
O
u
t
p
u
t
l
a
y
er
N
o
d
es
N
o
d
es
N
o
d
es
W
e
i
g
t
h
W
e
i
g
t
h
I
n
p
u
t
s
v
a
r
ia
b
le
s
O
u
t
p
u
t
v
a
r
ia
b
le
s
Fig
u
r
e
2
.
Stru
ctu
r
e
o
f
th
e
n
e
u
r
al
n
etwo
r
k
im
p
lem
e
n
ted
in
th
e
o
p
tim
zz
atio
n
alg
o
r
ith
m
Fig
u
r
e
3
.
Data
class
if
icatio
n
in
a
s
in
g
le
lay
er
n
eu
r
al
n
etwo
r
k
2.
4
.
O
utput
v
a
ria
bles
I
n
(
1
)
is
th
e
o
u
t
p
u
t
o
f
o
n
e
n
eu
r
o
n
in
th
e
in
p
u
t
la
y
er
.
I
n
(
2
)
is
t
h
e
m
ath
em
atica
l
m
o
d
el
f
o
r
th
e
o
u
tp
u
t
o
f
a
n
eu
r
al
n
etwo
r
k
an
d
it r
e
p
r
esen
ts
all
p
o
s
s
ib
le
co
m
b
i
n
atio
n
s
o
f
th
e
co
n
n
ec
tio
n
s
b
etwe
en
th
e
d
if
f
er
e
n
t la
y
er
s
o
f
a
n
eu
r
al
n
etwo
r
k
f
r
o
m
th
e
h
id
d
en
lay
er
u
p
to
t
h
e
o
u
tp
u
t la
y
e
r
.
Fo
r
t
h
e
ANN
d
is
cu
s
s
ed
in
th
is
p
ap
er
,
th
e
o
u
t
p
u
t
v
ar
iab
le
h
as two
s
tates: 0
o
r
0
.
1
.
=
(
1
)
Fo
r
k
=
1
,
i >
0
,
wh
er
e
a
is
th
e
n
eu
r
o
n
o
u
tp
u
t a
n
d
x
is
th
e
i
n
p
u
t v
ar
iab
le.
(
)
=
(
∑
(
−
1
)
−
1
=
1
∗
(
−
1
)
)
(
2
)
f
o
r
k
>
1
,
i
>
0
a
n
d
j
>
0
,
wh
er
e
a
is
th
e
n
e
u
r
o
n
o
u
tp
u
t,
w
ar
e
th
e
weig
h
ts
o
f
th
e
n
eu
r
al
co
n
n
ec
tio
n
s
an
d
f
(
x
)
is
th
e
lim
ited
f
u
n
ctio
n
.
Af
ter
estab
lis
h
in
g
th
e
to
p
o
l
o
g
y
o
f
th
e
ANN
d
escr
ib
ed
i
n
th
is
ar
ticle,
Fig
u
r
e
4
p
r
esen
ts
t
h
e
ty
p
ical
r
esu
lts
o
f
th
e
tr
ain
in
g
,
v
alid
at
io
n
an
d
test
in
g
p
h
ases
,
u
s
in
g
7
0
0
0
,
1
5
0
0
an
d
1
5
0
0
t
y
p
ical
d
ata
r
esp
ec
tiv
ely
.
T
h
e
s
y
s
tem
im
p
lem
en
ts
th
e
B
ay
esian
r
eg
u
lar
izatio
n
f
u
n
ct
io
n
as
a
tr
ain
in
g
f
u
n
ctio
n
.
I
n
o
r
d
er
t
o
ass
ess
it
s
p
er
f
o
r
m
an
ce
,
th
e
g
eo
m
etr
ic
m
ea
n
r
o
o
t
is
u
s
ed
.
A
to
tal
o
f
5
8
iter
atio
n
s
wer
e
ca
r
r
ied
o
u
t
to
tr
ain
th
e
n
etwo
r
k
.
T
h
e
tr
ain
in
g
,
v
alid
atio
n
an
d
te
s
tin
g
p
r
o
ce
s
s
es
wer
e
s
to
p
p
ed
b
ec
au
s
e
th
e
ANN
attain
ed
th
e
ex
p
ec
ted
m
i
n
im
u
m
g
r
ad
ien
t in
8
s
ec
o
n
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
P
erfo
r
ma
n
ce
a
s
s
ess
men
t o
f a
n
o
p
timiz
a
tio
n
s
tr
a
teg
y
p
r
o
p
o
s
e
d
fo
r
p
o
w
er sys
tems
(
Ha
r
o
ld
P
u
in
)
2733
Fig
u
r
e
4
.
T
y
p
ical
d
ata
in
th
e
tr
ain
in
g
,
v
alid
atio
n
an
d
test
in
g
p
r
o
ce
s
s
es o
f
th
e
im
p
lem
e
n
ted
ANN
3.
RE
SU
L
T
S
T
h
e
s
c
h
e
m
a
t
i
c
o
f
t
h
e
s
y
s
t
e
m
to
b
e
o
p
t
i
m
i
z
e
d
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
5
.
I
t
i
s
c
o
m
p
r
i
s
e
d
o
f
1
0
n
o
d
e
s
,
f
r
o
m
w
h
i
c
h
tw
o
n
o
d
e
s
h
a
v
e
a
P
V
t
y
p
e
,
o
n
e
n
o
d
e
h
as
a
s
la
c
k
t
y
p
e
a
n
d
s
e
v
e
n
n
o
d
e
s
h
a
v
e
a
PQ
t
y
p
e
.
T
h
e
o
t
h
e
r
c
h
a
r
a
c
t
e
r
is
t
i
cs
a
n
d
v
a
r
i
a
b
l
es
o
f
t
h
e
el
e
c
t
r
ic
s
y
s
t
e
m
a
r
e
p
r
e
s
en
t
e
d
i
n
T
a
b
l
e
s
1
a
n
d
2
,
r
e
s
p
ec
t
i
v
e
l
y
.
I
n
T
a
b
l
e
1,
t
h
e
f
i
r
s
t
t
w
o
c
o
l
u
m
n
s
r
e
p
r
es
en
t
t
h
e
i
n
t
e
r
c
o
n
n
e
c
t
i
o
n
o
f
t
h
e
s
y
s
te
m
n
o
d
e
s
,
t
h
e
e
l
e
c
t
r
ic
c
h
a
r
a
c
t
e
r
is
t
i
cs
o
f
t
h
e
s
e
c
o
n
n
e
c
t
i
o
n
s
a
r
e
es
t
a
b
li
s
h
e
d
f
r
o
m
t
h
e
t
h
i
r
d
t
o
t
h
e
f
i
f
t
h
c
o
l
u
m
n
.
I
n
T
a
b
l
e
2
,
t
h
e
f
i
r
s
t
tw
o
c
o
l
u
m
n
s
r
e
p
r
e
s
e
n
t
t
h
e
n
u
m
b
e
r
o
f
t
h
e
n
o
d
e
a
n
d
i
ts
t
y
p
e
.
T
h
e
t
h
i
r
d
c
o
l
u
m
n
u
p
t
o
t
h
e
s
e
v
e
n
t
h
c
o
l
u
m
n
s
h
o
w
t
h
e
v
a
lu
e
s
o
f
t
h
e
g
e
n
e
r
a
t
e
d
a
c
t
i
v
e
/
r
e
ac
t
i
v
e
p
o
w
e
r
,
t
h
e
d
e
m
a
n
d
e
d
a
c
t
i
v
e
/
r
e
ac
t
i
v
e
p
o
we
r
a
n
d
t
h
e
v
o
l
t
a
g
e
m
a
g
n
i
t
u
d
e
i
n
e
a
c
h
n
o
d
e
.
T
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
n
e
u
r
a
l
n
e
t
w
o
r
k
d
u
r
i
n
g
t
h
e
t
r
a
i
n
i
n
g
,
v
a
l
i
d
a
t
i
o
n
a
n
d
t
es
t
i
n
g
p
h
a
s
e
s
f
o
r
t
h
e
o
p
t
i
m
i
z
a
ti
o
n
p
r
o
c
e
s
s
o
f
t
h
is
s
p
e
c
i
f
i
c
s
y
s
t
em
i
s
p
r
e
s
e
n
t
e
d
i
n
Fi
g
u
r
e
6
.
T
h
e
p
r
e
l
i
m
i
n
a
r
y
r
e
s
u
lt
o
f
t
h
e
n
o
d
a
l
v
o
l
t
a
g
e
a
f
t
e
r
o
p
t
i
m
i
z
a
ti
o
n
a
n
d
t
h
e
t
o
t
a
l
c
o
m
p
u
t
a
t
i
o
n
t
i
m
e
(
A
N
N
t
r
a
i
n
i
n
g
t
im
e
p
l
u
s
o
p
t
i
m
iz
a
t
i
o
n
ti
m
e
)
a
r
e
s
h
o
w
n
i
n
F
i
g
u
r
e
7
.
Fig
u
r
e
5
.
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
7
2
9
-
2736
2734
T
ab
le
1
.
C
h
ar
ac
ter
is
tics
o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
N
st
a
r
t
N
f
i
n
i
sh
R
X
B
sh
/
2
1
2
0
.
0
8
3
7
9
0
.
1
7
7
2
0
.
0
0
0
4
7
1
6
0
.
1
0
8
9
0
.
2
3
0
4
0
.
0
0
0
6
1
2
3
0
.
1
8
4
3
0
.
3
9
0
0
0
.
0
0
1
0
2
5
0
.
1
5
0
8
0
.
3
1
9
1
0
0
0
0
8
5
2
6
0
.
1
6
7
5
0
.
3
5
4
5
0
.
0
0
0
9
4
3
4
0
.
2
3
4
6
0
.
4
9
6
3
0
.
0
0
1
3
3
5
0
.
2
0
9
4
0
.
4
4
3
2
0
.
0
0
1
1
5
4
0
.
1
8
4
3
0
.
3
9
0
0
0
.
0
0
1
0
4
10
0
.
1
6
7
5
0
.
3
5
4
5
0
.
0
0
0
9
4
6
7
0
.
1
2
5
6
0
.
2
6
5
9
0
.
0
0
0
7
1
7
8
0
.
1
0
0
5
0
.
2
1
2
7
0
.
0
0
0
5
6
7
9
0
.
0
6
7
0
0
.
1
4
1
8
0
.
0
0
0
3
7
9
8
0
.
1
3
4
0
0
.
2
8
3
6
0
.
0
0
0
7
5
8
10
0
.
1
0
8
9
0
.
2
3
0
4
0
.
0
0
0
6
1
T
ab
le
2
.
Kn
o
wn
s
y
s
tem
v
ar
iab
les o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
N
o
d
e
Ty
p
e
P
g
e
n
Q
g
e
n
P
d
e
m
Q
d
e
m
V
mag
1
S
l
a
c
k
0
.
7
0
0
0
1
2
PQ
0
0
0
.
15
0
.
2
0
.
9
4
3
3
3
PQ
0
0
0
.
15
0
.
2
0
.
8
9
3
9
4
PQ
0
0
0
.
15
0
.
2
0
.
8
6
6
6
5
PV
0
0
0
.
15
0
.
2
1
6
PQ
0
0
0
.
15
0
.
2
0
.
9
3
5
3
7
PQ
0
0
0
.
15
0
.
2
0
.
9
3
3
5
8
PQ
0
0
0
.
15
0
.
2
0
.
8
9
4
3
9
PV
0
.
5
0
0
0
1
10
PQ
0
0
0
.
15
0
.
2
0
.
8
3
7
3
Fig
u
r
e
6
.
T
r
ain
in
g
,
v
alid
aito
n
an
d
test
in
g
o
f
th
e
ANN
u
s
ed
i
n
th
e
o
p
tim
izatio
n
o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
Fig
u
r
e
1
.
Pre
lim
in
ar
y
r
esu
lts
o
f
th
e
n
o
d
al
v
o
ltag
es a
n
d
to
tal
e
x
ec
u
tio
n
tim
e
o
f
th
e
o
p
tim
izat
io
n
alg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
P
erfo
r
ma
n
ce
a
s
s
ess
men
t o
f a
n
o
p
timiz
a
tio
n
s
tr
a
teg
y
p
r
o
p
o
s
e
d
fo
r
p
o
w
er sys
tems
(
Ha
r
o
ld
P
u
in
)
2735
4.
C
O
M
P
ARA
T
I
V
E
A
S
SE
SS
M
E
N
T
Fig
u
r
e
7
s
h
o
ws
th
e
r
ep
o
r
t
g
en
er
ated
b
y
th
e
alg
o
r
ith
m
in
wh
ich
th
e
o
p
tim
izatio
n
r
esu
lts
ca
n
b
e
th
o
r
o
u
g
h
ly
d
etailed
f
o
r
th
e
1
0
-
n
o
d
e
I
E
E
E
1
2
5
0
s
tan
d
ar
d
p
o
wer
s
y
s
tem
.
I
n
T
ab
le
3
,
th
e
n
o
d
e
ty
p
e
is
c
o
d
ed
in
th
e
s
ec
o
n
d
co
lu
m
n
,
with
1
f
o
r
Slack
,
2
f
o
r
PV
an
d
3
f
o
r
PQ.
T
ab
le
4
p
r
esen
ts
th
e
r
esu
lts
o
f
th
e
n
o
d
al
v
o
ltag
e
m
ag
n
itu
d
es
o
b
tain
ed
with
t
h
e
g
en
etic
alg
o
r
ith
m
(
GA)
a
n
d
t
h
e
an
t
c
o
lo
n
y
o
p
tim
izatio
n
(
AC
O)
.
T
ab
le
5
s
h
o
ws
th
e
o
p
tim
izatio
n
p
er
ce
n
ta
g
e
o
f
th
e
v
o
ltag
e
m
ag
n
itu
d
e
f
o
r
e
ac
h
n
o
d
e
o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
.
E
ac
h
c
o
lu
m
n
r
e
p
r
esen
ts
o
n
e
o
f
th
e
a
lg
o
r
ith
m
s
d
is
cu
s
s
ed
in
th
is
s
ec
tio
n
.
T
ab
le
3
.
R
ep
o
r
t
o
f
th
e
o
p
tim
iz
atio
n
r
esu
lts
f
o
r
I
E
E
E
1
2
5
0
B
u
s
i
Ty
p
e
n
o
d
e
P
g
e
n
Q
g
e
n
P
d
e
m
Q
d
e
m
V
mag
V
a
n
g
1
1
0
.
7
7
9
-
0
.
28
0
0
1
0
2
3
0
0
.
2
0
.
15
0
.
2
0
.
9
9
2
-
5
.
96
3
3
0
0
.
3
0
.
15
0
.
2
1
.
0
0
2
-
1
1
2
6
4
3
0
0
.
3
0
.
15
0
.
2
1
.
0
0
8
-
12
.
58
5
2
0
0
0
.
15
0
.
2
1
-
10
.
99
6
3
0
0
.
3
0
.
15
0
.
2
1
-
4
.
369
7
3
0
0
.
3
0
.
15
0
.
2
1
.
0
0
2
-
5
.
194
8
3
0
0
.
3
0
.
15
0
.
2
1
.
0
0
4
-
7
.
374
9
2
0
,
5
0
0
0
1
-
2
.
583
10
3
0
0
.
3
0
.
15
0
.
2
1
0
0
9
-
10
.
9
9
6
T
ab
le
4
.
R
esu
lts
in
n
o
d
al
v
o
lta
g
e
m
ag
n
itu
d
es
f
o
r
g
a
an
d
ac
o
N
o
d
e
GA
A
C
O
1
1
1
2
0
.
9
9
8
4
0
.
9
5
6
6
3
0
.
9
9
6
3
0
.
9
1
0
9
4
0
.
9
9
7
2
0
.
9
0
3
8
5
1
1
6
0
.
9
9
5
7
0
.
9
7
2
2
7
0
.
9
9
5
7
0
.
9
7
3
5
8
0
.
9
9
4
7
0
.
9
5
1
3
9
1
1
10
0
.
9
9
5
5
0
.
9
0
7
5
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
th
e
p
e
r
ce
n
tag
es o
f
n
o
d
al
v
o
ltag
e
in
cr
ea
s
e
N
o
d
e
GA
A
C
O
ANN
1
0%
0%
0%
2
5
.
8
4
%
1
.
4
%
5
.
1
6
%
3
11
.
4
5
%
1
.
9
%
12
.
0
9
%
4
15
.
0
7
%
4
.
2
9
%
16
.
3
1
%
5
0%
0%
0%
6
6
.
4
5
%
3
.
9
4
%
6
.
9
1
%
7
6
.
5
5
%
4
.
2
8
%
7
.
3
3
%
8
11
.
2
2
%
6
.
3
7
%
12
.
2
6
%
9
0%
0%
0%
10
18
.
8
9
%
8
.
3
8
%
20
.
5%
5.
A
NALY
SI
S O
F
T
H
E
RE
SU
L
T
S
Fig
u
r
es
4
an
d
6
ex
h
ib
it
th
e
tr
ain
in
g
,
v
alid
ati
o
n
an
d
test
in
g
p
r
o
ce
s
s
o
f
th
e
n
eu
r
al
n
et
wo
r
k
.
I
t
is
co
n
clu
d
e
d
th
at
th
e
tim
e
lap
s
es
an
d
iter
atio
n
s
o
f
co
n
v
er
g
e
n
ce
ar
e
s
im
ilar
u
n
d
er
d
if
f
e
r
en
t
p
er
f
o
r
m
an
ce
s
ce
n
ar
io
s
.
T
h
is
in
d
icate
s
th
at
th
e
s
ize
o
f
th
e
p
o
wer
s
y
s
tem
to
b
e
o
p
ti
m
ized
d
o
es
n
o
t
in
f
l
u
en
ce
th
e
tim
e
an
d
q
u
ality
o
f
th
e
ANN
in
d
etec
tin
g
s
u
b
v
o
ltag
es
in
t
h
e
s
y
s
tem
n
o
d
es.
Go
i
n
g
b
ac
k
to
Fig
u
r
es
4
an
d
6
,
it
ca
n
b
e
d
eter
m
in
e
d
th
at
th
e
ty
p
ical
p
ar
am
eter
s
f
o
r
wh
ich
th
e
tr
ain
in
g
p
r
o
ce
s
s
is
s
to
p
p
ed
a
r
e
tied
to
th
e
m
in
im
u
m
lear
n
in
g
g
r
a
d
ien
t
o
f
th
e
n
eu
r
al
n
etwo
r
k
a
n
d
its
p
er
f
o
r
m
an
ce
.
T
h
is
m
ea
n
s
th
a
t
th
e
tr
ain
ed
n
eu
r
al
n
etwo
r
k
g
u
ar
an
tees
a
a
h
i
g
h
ac
cu
r
ac
y
in
t
h
e
p
r
ed
ictio
n
o
f
v
alu
es
d
ep
en
d
in
g
o
n
th
e
in
p
u
t
v
ar
ia
b
le.
T
h
is
is
h
ig
h
lig
h
t
ed
b
y
th
e
f
ac
t
th
at
th
e
o
u
tp
u
t
h
as
two
s
tates
o
n
ly
d
is
tan
ce
d
b
y
a
0
.
0
1
.
I
n
ca
s
e
t
h
at
th
e
n
e
u
r
al
n
etwo
r
k
is
h
alted
af
ter
c
o
m
p
letin
g
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
iter
atio
n
s
,
it
is
r
ec
o
m
m
en
d
e
d
t
o
ap
p
l
y
o
n
ce
ag
ain
th
e
lea
r
n
in
g
p
r
o
ce
s
s
s
in
ce
th
e
n
etwo
r
k
m
ay
n
o
t su
cc
ess
f
u
lly
p
r
ed
ict
th
e
ex
p
ec
te
d
o
u
t
p
u
t v
alu
es.
T
ab
le
3
s
h
o
wca
s
es th
e
r
ep
o
r
t
o
f
th
e
al
g
o
r
ith
m
af
ter
t
h
e
o
p
tim
izatio
n
p
r
o
ce
s
s
o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
.
T
h
is
tab
le
also
s
h
o
ws
th
at,
ev
e
n
if
th
e
t
o
tal
n
o
n
-
ca
p
ac
itiv
e
r
ea
ctiv
e
p
o
wer
s
p
er
n
o
d
e
d
o
n
o
t
ex
ce
ed
th
e
ac
tiv
e
p
o
wer
s
,
th
ey
ar
e
s
ig
n
if
ican
t
en
o
u
g
h
to
af
f
ec
t
th
e
p
o
wer
f
ac
to
r
ass
o
ciate
d
to
th
e
n
o
d
e.
T
h
is
is
tr
u
e
n
o
t
o
n
ly
f
o
r
th
e
ANN
alg
o
r
itih
m
b
u
t
also
f
o
r
th
e
o
th
er
alg
o
r
ith
m
s
.
I
t
is
r
ec
o
m
m
en
d
ed
to
co
n
s
id
er
th
is
p
ar
am
eter
s
f
o
r
f
u
tu
r
e
v
er
s
io
n
s
o
f
th
e
alg
o
r
ith
m
s
.
Fu
r
th
er
m
o
r
e
,
T
ab
le
3
r
ev
ea
ls
th
at
th
e
r
ea
ctiv
e
p
o
wer
in
th
e
PV
n
o
d
es
o
r
th
e
n
o
d
es
co
n
n
ec
ted
to
a
g
en
e
r
ato
r
is
in
cr
ea
s
ed
in
o
r
d
er
to
c
o
m
p
en
s
ate
th
e
ca
p
ac
itiv
e
r
ea
c
tiv
e
p
o
wer
in
jecte
d
to
th
e
s
y
s
tem
b
y
th
e
ANN.
T
h
is
r
esu
lts
in
a
n
o
r
m
al
b
eh
av
i
o
r
co
n
s
id
er
in
g
th
at
th
ese
n
o
d
e
s
m
u
s
t
r
em
ain
with
a
v
o
ltag
e
e
q
u
al
to
1
p
.
u
.
T
h
e
r
e
s
u
lts
o
f
th
e
o
p
tim
izatio
n
o
f
th
e
I
E
E
E
1
2
5
0
p
o
wer
s
y
s
tem
e
x
h
i
b
ited
b
y
th
e
g
e
n
etic
alg
o
r
ith
m
an
d
th
e
ANN
ar
e
f
air
ly
c
o
m
p
etitiv
e.
T
h
e
m
in
i
m
u
m
d
if
f
er
e
n
ce
is
0
.
4
6
%
in
th
e
s
ix
th
n
o
d
e
an
d
th
e
m
ax
im
u
m
d
if
f
er
e
n
ce
is
1
.
2
6
%
in
th
e
last
n
o
d
e.
I
t
is
s
u
g
g
ested
to
ass
ess
th
e
o
p
tim
izatio
n
tim
e
to
f
in
d
an
ar
g
u
a
b
le
d
if
f
e
r
en
ce
.
6.
CO
NCLU
SI
O
NS
T
h
e
to
p
o
lo
g
y
o
f
th
e
im
p
lem
e
n
ted
ANN
in
t
h
e
o
p
tim
izatio
n
alg
o
r
ith
m
h
as
s
h
o
w
n
a
s
tab
le
b
eh
av
i
o
u
r
in
ter
m
s
o
f
th
e
p
a
r
am
eter
s
u
s
ed
f
o
r
tr
ai
n
in
g
,
v
alid
atio
n
an
d
test
in
g
,
g
u
ar
an
teein
g
ac
c
u
r
ac
y
an
d
s
wif
tn
ess
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
7
2
9
-
2736
2736
m
o
s
t
ca
s
es.
A
n
eu
r
al
n
etwo
r
k
th
at
ad
o
p
ts
a
n
u
m
b
e
r
o
f
in
p
u
t
s
eq
u
al
to
th
e
n
u
m
b
er
n
o
d
es
i
n
th
e
p
o
wer
s
y
s
tem
to
b
e
o
p
tim
ized
is
n
o
t v
iab
le
s
in
ce
it wo
u
ld
r
eq
u
ir
e
a
lar
g
e
a
m
o
u
n
t o
f
d
ata
to
ass
u
r
e
a
co
r
r
ec
t tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
co
r
r
esp
o
n
d
in
g
co
m
p
u
tin
g
p
o
wer
wo
u
l
d
n
ee
d
to
s
u
r
p
ass
th
e
ca
p
ac
ity
o
f
an
av
er
a
g
e
co
m
p
u
te
r
.
I
t
is
r
ec
o
m
m
en
d
ed
to
in
clu
d
e
t
h
e
p
o
wer
f
ac
to
r
as
an
o
p
tim
izatio
n
p
ar
am
eter
k
ee
p
in
g
in
m
i
n
d
t
h
a
t
o
p
tim
izatio
n
m
u
s
t
b
e
b
ased
o
n
t
h
e
p
r
in
cip
le
o
f
e
n
er
g
y
q
u
ality
.
T
h
e
o
p
tim
izatio
n
r
esu
lts
o
b
tain
e
d
with
b
o
th
t
h
e
g
en
etic
alg
o
r
ith
m
an
d
th
e
im
p
lem
en
ted
ANN
ar
e
s
im
ilar
.
RE
F
E
R
E
NC
E
S
[1
]
Be
rrío
L,
Zu
l
u
a
g
a
C.
,
“
Co
n
c
e
p
t
s,
sta
n
d
a
rd
s
a
n
d
c
o
m
m
u
n
ica
ti
o
n
tec
h
n
o
l
o
g
ies
in
sm
a
rt
g
rid
,”
2
0
1
2
I
EE
E
4
t
h
Co
lo
mb
ia
n
W
o
rk
sh
o
p
o
n
Circ
u
it
s a
n
d
S
y
ste
ms
,
CW
CAS
2
0
1
2
-
Co
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
s
,
2
0
1
2
.
[2
]
He
ro
n
J
.
W
.
,
Jia
n
g
J
.
,
S
u
n
H
.
,
G
e
z
e
rli
s
V
.
,
D
o
u
k
o
g
lo
u
T.
,
“
De
m
a
n
d
-
Re
sp
o
n
se
R
o
u
n
d
-
Tri
p
Late
n
c
y
o
f
Io
T
S
m
a
rtG
rid
Ne
two
rk
To
p
o
lo
g
ies
,”
IEE
E
Acc
e
ss
,
v
o
l
.
6
,
p
p
.
2
2
9
3
0
-
3
7
,
2
0
1
8
.
[3
]
P
e
n
g
F
.
Z
.
,
Li
Y
.
W
.
,
T
o
lb
e
rt
L
.
M.
,
“
Co
n
tr
o
l
a
n
d
p
ro
tec
ti
o
n
o
f
p
o
we
r
e
lec
tro
n
ics
i
n
terfa
c
e
d
d
istr
i
b
u
ted
g
e
n
e
ra
ti
o
n
sy
ste
m
s in
a
c
u
sto
m
e
r
-
d
ri
v
e
n
m
ic
ro
g
ri
d
,
”
Co
n
fer
e
n
c
e
:
Po
we
r &
En
e
rg
y
S
o
c
iety
Ge
n
e
ra
l
M
e
e
ti
n
g
,
2
0
0
9
.
[4
]
Ka
ti
ra
e
i
F
.
,
Ira
v
a
n
i
R
.
,
Ha
tzia
rg
y
rio
u
N
.
,
Dim
e
a
s
A.
,
“
M
icro
g
r
id
s
m
a
n
a
g
e
m
e
n
t
,”
IEE
E
Po
we
r
E
n
e
rg
y
M
a
g
.,
v
o
l.
6
,
n
o
.
3
,
p
p
.
54
-
65
,
2
0
0
8
.
[5
]
Zh
a
n
g
H
.
,
Nie
Y
.
,
Ch
e
n
g
J
.
,
Leu
n
g
V
.
C
.
M
.
,
Na
ll
a
n
a
th
a
n
A.
,
“
S
e
n
sin
g
Ti
m
e
Op
ti
m
iza
ti
o
n
a
n
d
P
o
we
r
Co
n
tr
o
l
f
o
r
En
e
rg
y
Eff
icie
n
t
Co
g
n
it
iv
e
S
m
a
ll
Ce
ll
with
Im
p
e
rfe
c
t
Hy
b
ri
d
S
p
e
c
tru
m
S
e
n
sin
g
,”
IE
EE
T
r
a
n
sa
c
ti
o
n
s
o
n
W
ire
les
s
Co
mm
u
n
ica
ti
o
n
s
,
v
o
l
.
16
,
n
o
.
2
,
p
p
.
7
3
0
-
43
,
2
0
1
7
.
[6
]
Ka
ra
b
o
g
a
D
.
,
Ba
stu
r
k
B.
,
“
Art
if
icia
l
Be
e
Co
lo
n
y
(ABC)
Op
t
imiz
a
ti
o
n
Alg
o
rit
h
m
fo
r
S
o
lv
in
g
Co
n
stra
in
e
d
Op
ti
m
iza
ti
o
n
P
ro
b
lem
s
,”
In
ter
n
a
t
io
n
a
l
F
u
zz
y
S
y
ste
ms
Asso
c
ia
ti
o
n
W
o
rld
Co
n
g
re
ss
,
2
0
0
7
.
[7
]
Jo
rd
e
h
i
A
.
R
.
,
Ja
sn
i
J.
,
“
Ap
p
r
o
a
c
h
e
s
fo
r
F
ACTS
o
p
ti
m
iza
ti
o
n
p
r
o
b
lem
in
p
o
we
r
sy
ste
m
s
,”
2
0
1
2
IEE
E
In
ter
n
a
t
io
n
a
l
Po
we
r E
n
g
in
e
e
rin
g
a
n
d
Op
ti
miz
a
ti
o
n
Co
n
fer
e
n
c
e
M
e
la
k
a
,
M
a
lay
si
a
,
2
0
1
2
.
[8
]
Zh
a
o
B
.
,
X
u
e
M
.
,
Z
h
a
n
g
X
.
,
W
a
n
g
C
.
,
Z
h
a
o
J.
,
“
An
M
AS
b
a
se
d
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
sy
ste
m
fo
r
a
sta
n
d
-
a
lo
n
e
m
icro
g
rid
a
t
h
i
g
h
a
l
ti
tu
d
e
,”
Ap
p
l
En
e
rg
y
,
v
o
l.
1
4
3
,
p
p
.
2
5
1
-
61
,
2
0
1
5
.
[9
]
Ch
e
n
C
.
,
D
u
a
n
S.
,
“
M
icr
o
g
ri
d
e
c
o
n
o
m
ic
o
p
e
ra
ti
o
n
c
o
n
sid
e
ri
n
g
p
lu
g
-
in
h
y
b
r
id
e
lec
tri
c
v
e
h
icle
s
in
te
g
ra
ti
o
n
,”
J
.
M
o
d
.
Po
we
r
.
S
y
st
.
Cle
a
n
.
En
e
rg
y
.
,
v
o
l.
3
,
n
o
.
2
,
p
p
.
2
2
1
-
31
,
2
0
1
5
.
[1
0
]
Rizk
Y
.
,
Aw
a
d
M
.
,
T
u
n
ste
l
E
.
W.
,
“
De
c
isio
n
M
a
k
i
n
g
in
M
u
lt
i
-
Ag
e
n
t
S
y
ste
m
s:
A
S
u
rv
e
y
,”
6
th
In
ter
n
a
ti
o
o
n
a
l
Co
n
fer
e
n
c
e
,
M
E
S
AS
2
0
1
9
P
a
ler
m
o
,
Italy
,
2
0
1
9
.
[1
1
]
M
a
z
id
i
M
.
,
Zak
a
riaz
a
d
e
h
A
.
,
Ja
d
i
d
S
.
,
S
ia
n
o
P
.
,
“
In
teg
ra
ted
sc
h
e
d
u
l
in
g
o
f
re
n
e
wa
b
le
g
e
n
e
ra
ti
o
n
a
n
d
d
e
m
a
n
d
re
sp
o
n
se
p
ro
g
ra
m
s in
a
m
icro
g
r
id
,
”
E
n
e
rg
y
Co
n
v
e
rs
io
n
a
n
d
M
a
n
a
g
e
me
n
t
,
v
o
l.
8
6
,
p
p
.
1
1
1
8
-
2
7
,
2
0
1
4
.
[1
2
]
El
sie
d
M
.
,
Ou
k
a
o
u
r
A
.
,
G
u
a
lo
u
s
H
.
,
Ha
ss
a
n
R.
,
“
E
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
a
n
d
o
p
ti
m
iza
ti
o
n
in
m
icro
g
rid
sy
ste
m
b
a
se
d
o
n
g
re
e
n
e
n
e
rg
y
,”
En
e
r
g
y
,
v
o
l.
84
,
p
p
.
1
3
9
-
51
,
2
0
1
5
.
[1
3
]
M
wa
silu
F
.
,
Ju
st
o
J
.
J
.
,
Kim
E
.
K
.
,
Do
T
.
D
.
,
Ju
n
g
J
.
W.
,
“
El
e
c
tri
c
v
e
h
icle
s
a
n
d
sm
a
rt
g
rid
in
tera
c
ti
o
n
:
A
re
v
iew
o
n
v
e
h
icle
t
o
g
rid
a
n
d
re
n
e
wa
b
le
e
n
e
rg
y
s
o
u
rc
e
s
in
teg
ra
ti
o
n
,”
Re
n
e
wa
b
le
a
n
d
S
u
st
a
in
a
b
le
En
e
rg
y
Re
v
iews
,
v
o
l.
34
,
p
p
.
5
0
1
-
16
,
2
0
1
4
.
[1
4
]
Co
rc
h
e
ro
C
.
,
Nu
n
e
z
-
De
l
-
To
ro
C
.
,
P
a
ra
d
e
ll
P
.
,
De
l
-
Ro
sa
ri
o
-
Ca
laf
G
.
,
“
In
teg
ra
ti
n
g
a
n
c
il
lary
se
rv
ice
s
fro
m
d
e
m
a
n
d
sid
e
m
a
n
a
g
e
m
e
n
t
a
n
d
d
istri
b
u
te
d
g
e
n
e
ra
ti
o
n
:
A
n
o
p
ti
m
a
l
m
o
d
e
l
,”
2
0
1
8
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ma
rt
En
e
rg
y
S
y
ste
ms
a
n
d
T
e
c
h
n
o
lo
g
ies
,
S
ES
T
2
0
1
8
-
Pro
c
e
e
d
in
g
s.
I
n
stit
u
te o
f
E
lec
trica
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rs
In
c
.
;
2
0
1
8
.
[1
5
]
Ya
n
g
B
.
,
Li
J
.
,
Ha
n
Q
.
,
He
T
.
,
Ch
e
n
C
.
,
G
u
a
n
X.
,
“
Distrib
u
ted
C
o
n
tro
l
fo
r
Ch
a
rg
i
n
g
M
u
l
ti
p
le E
lec
tri
c
Ve
h
icle
s with
Ov
e
rlo
a
d
L
imitatio
n
,”
IEE
E
T
ra
n
s P
a
ra
ll
e
l
Distri
b
S
y
st.
,
v
o
l.
27
,
n
o
.
12
,
p
p
.
3
4
4
1
-
54
,
2
0
1
6
.
[1
6
]
Xu
H
.
,
Hu
a
n
g
H
.
,
Kh
a
li
d
R
.
S
.
,
Yu
H.
,
“
Distrib
u
ted
m
a
c
h
in
e
lea
r
n
in
g
b
a
se
d
sm
a
rt
-
g
rid
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
with
o
c
c
u
p
a
n
t
c
o
g
n
it
i
o
n
,”
2
0
1
6
IEE
E
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ma
r
t
Gr
id
Co
mm
u
n
ica
ti
o
n
s
,
2
0
1
6
.
[1
7
]
Ca
rre
n
o
F
ra
n
c
o
E
.
,
T
o
ro
Oc
a
m
p
o
E
.
,
Esc
o
b
a
r
Zu
l
u
a
g
a
A.
,
Op
t
imiz
a
c
ió
n
De
S
istem
a
s
Li
n
e
a
les
Us
a
n
d
o
M
é
to
d
o
s
De
P
u
n
t
o
I
n
terio
r
,”
S
c
i
T
e
c
h
,
v
o
l.
1
,
n
o
.
24
,
p
p
.
43
-
8
,
2
0
0
4
.
[1
8
]
An
a
u
t
D
.
O
.
,
d
i
M
a
u
r
o
G
.
F
.
,
M
e
sc
h
in
o
G
.
,
S
u
á
re
z
J
.
A.
,
“
Op
ti
m
iza
c
ió
n
d
e
Re
d
e
s E
léc
tri
c
a
s M
e
d
ian
t
e
la Ap
li
c
a
c
ió
n
d
e
Alg
o
r
it
m
o
s
G
e
n
é
ti
c
o
s
,”
In
f
tec
n
o
l
ó
g
ic
a
,
v
o
l.
20
,
n
o
.
4
,
p
p
.
1
3
7
-
4
8
,
2
0
0
9
.
[1
9
]
M
o
re
n
o
L
.
F
.
,
Día
z
F
.
J
.
,
P
e
ñ
a
G
.
E
.
,
Ri
v
e
ra
J
.
C.
,
“
An
á
li
sis
c
o
m
p
a
r
a
ti
v
o
e
n
tre
d
o
s
a
lg
o
rit
m
o
s
h
e
u
r
ísti
c
o
s
p
a
ra
re
so
l
v
e
r
e
l
p
ro
b
lem
a
d
e
p
lan
e
a
c
ió
n
d
e
tar
e
a
s
c
o
n
re
stricc
ió
n
d
e
re
c
u
rso
s
(
RCP
S
P
)
,”
Dy
n
a
(
M
e
d
e
ll
i
n
,
Co
l
o
mb
ia
)
,
v
o
l.
74
,
n
o
.
1
5
1
,
p
p
.
1
7
1
-
83
,
2
0
0
7
.
[2
0
]
Ap
ril
ia
E
.
,
M
e
n
g
K
.
,
Al
Ho
sa
n
i
M
.
,
Zein
e
l
d
in
H
.
H
.
,
Do
n
g
Z
.
Y.
,
“
Un
ifi
e
d
P
o
we
r
F
l
o
w
Alg
o
rit
h
m
fo
r
S
tan
d
a
lo
n
e
AC/DC Hy
b
ri
d
M
icro
g
ri
d
s
,”
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
S
ma
rt Gri
d
,
v
o
l.
10
,
n
o
.
1
,
p
p
.
6
3
9
-
49
,
2
0
1
9
.
[2
1
]
Ili
y
a
S
.
,
G
o
o
d
y
e
r
E
.
,
G
o
w
J
.
,
S
h
e
ll
J
.
,
G
o
n
g
o
ra
M
.
,
“
Ap
p
li
c
a
ti
o
n
o
f
Artifi
c
ial
Ne
u
ra
l
Ne
two
rk
a
n
d
S
u
p
p
o
rt
Ve
c
to
r
Re
g
re
ss
io
n
i
n
Co
g
n
it
iv
e
Ra
d
io
Ne
two
rk
s
f
o
r
RF
P
o
we
r
P
re
d
icti
o
n
U
sin
g
Co
m
p
a
c
t
Diffe
re
n
ti
a
l
E
v
o
lu
ti
o
n
Alg
o
rit
h
m
,”
2
0
1
5
Fe
d
e
ra
ted
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
(Fed
CS
IS
)
,
2
0
1
5
.
[2
2
]
Álv
a
re
z
D
.
,
H
u
rtad
o
G
ó
m
e
z
J.
,
“
Op
tmiz
a
c
ió
n
b
a
sa
d
a
e
n
c
o
n
f
iab
il
i
d
a
d
p
o
r
m
e
d
i
o
d
e
re
d
e
s
n
e
u
r
o
n
a
l
e
s
y
a
l
g
o
ri
tmo
s
e
v
o
lu
ti
v
o
s
,”
M
é
t
o
d
o
s n
u
mé
ric
o
s p
a
ra
c
á
lcu
l
o
y
d
ise
ñ
o
e
n
In
g
Rev
In
t.
,
v
o
l.
18
,
n
o
.
4
,
p
p
.
5
7
3
-
94
,
2
0
0
2
.
[2
3
]
Be
a
le
M
.
H
.
,
Ha
g
a
n
M
.
T
.
,
De
m
u
th
H
.
B
.,
“
Dy
n
a
m
ic
Ne
u
ra
l
Ne
two
rk
s.
Ne
u
ra
l
Ne
two
r
k
T
o
o
l
b
o
x
(T
M
)
Us
e
r’s
G
u
id
e
,”
Na
ti
c
k
,
M
A:
T
h
e
M
a
th
W
o
rk
s,
I
n
c
.
;
2
0
1
8
.
[2
4
]
Ab
b
a
s
N
.
,
Na
ss
e
r
Y
.
,
A
h
m
a
d
K
.
E
l.
,
“
Re
c
e
n
t
a
d
v
a
n
c
e
s
o
n
a
rti
ficia
l
i
n
telli
x
g
e
n
c
e
a
n
d
lea
rn
in
g
tec
h
n
iq
u
e
s
in
c
o
g
n
it
iv
e
ra
d
io
n
e
two
rk
s
,”
EURA
S
IP
J
o
u
r
n
a
l
o
n
W
ire
les
s Co
mm
u
n
ic
a
ti
o
n
s a
n
d
Ne
tw
o
rk
in
g
,
v
o
l.
1
,
p
p
.
1
-
20
,
2
0
1
5
.
[
2
5
]
V
e
i
t
c
h
D
.
,
“
W
a
v
e
l
e
t
N
e
u
r
a
l
N
e
t
w
o
r
k
s
a
n
d
t
h
e
i
r
a
p
p
l
i
c
a
t
i
o
n
i
n
t
h
e
s
t
u
d
y
o
f
d
y
n
a
m
i
c
a
l
s
y
s
t
e
m
s
,”
U
n
i
v
e
r
s
i
t
y
o
f
Y
o
r
k
,
2
0
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.