I
nte
rna
t
io
na
l J
o
urna
l o
f
Appl
ied P
o
wer
E
ng
i
neer
ing
(
I
J
AP
E
)
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
1
0
3
6
~
1
050
I
SS
N:
2252
-
8
7
9
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijap
e
.
v
1
5
.
i
3
.
pp
1
0
3
6
-
1
0
5
0
1036
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//
ija
p
e.
ia
esco
r
e.
co
m/
Susta
ina
ble e
-
mo
bility wit
h cont
ro
lled charg
ing
sche
me ba
sed
o
n grid energ
y
us
ing
m
a
chine
lea
rn
ing
Arc
ha
na
K
a
da
m
,
Ra
m
esh
M
a
li,
Ree
na
G
un
j
a
n,
Vire
nd
ra
Sh
et
e,
P
ra
deep
M
a
ne
M
I
T
A
r
t
,
D
e
s
i
g
n
a
n
d
Te
c
h
n
o
l
o
g
y
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
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
3
,
2
0
2
5
R
ev
is
ed
Ap
r
6
,
2
0
2
6
Acc
ep
ted
J
u
n
9
,
2
0
2
6
Th
e
e
lec
tri
c
v
e
h
icle
(EV)
p
o
p
u
la
rit
y
h
a
s
tak
e
n
o
ff
a
m
o
n
g
c
o
n
su
m
e
rs,
wh
ich
h
a
s
in
tu
r
n
led
t
o
e
ffo
rts
to
c
re
a
te
a
n
e
fficie
n
t
EV
c
h
a
rg
in
g
in
fr
a
stru
c
tu
re
.
Th
is
p
a
p
e
r
a
d
d
re
ss
e
s
th
is
c
h
a
ll
e
n
g
e
b
y
p
r
o
p
o
sin
g
a
sc
h
e
d
u
led
c
h
a
rg
i
n
g
sc
h
e
m
e
th
a
t
u
se
s
re
a
l
-
ti
m
e
d
a
ta
fro
m
a
g
rid
-
c
o
n
n
e
c
ted
c
h
a
rg
in
g
sta
ti
o
n
a
t
Ba
n
e
r,
P
u
n
e
,
o
p
e
ra
ted
b
y
P
u
n
e
M
a
h
a
n
a
g
a
r
P
a
ri
v
a
h
a
n
M
a
h
a
m
a
n
d
a
l
Lt
d
(
PMPML
)
.
T
h
e
p
r
o
p
o
se
d
s
y
ste
m
m
a
k
e
s
u
se
o
f
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
su
c
h
a
s
th
e
S
t
o
c
h
a
sti
c
d
u
a
l
c
o
o
r
d
i
n
a
te
a
sc
e
n
t
(S
DCA
)
a
n
d
F
a
st
F
o
re
st
(F
F
)
a
lg
o
rit
h
m
,
b
o
t
h
o
f
wh
ich
a
ll
o
w
fo
r
p
re
c
ise
a
n
d
e
fficie
n
t
c
o
m
p
u
tati
o
n
s
to
p
re
d
ict
c
h
a
r
g
in
g
fin
ish
ti
m
e
s
a
n
d
m
a
k
e
o
p
ti
m
a
l
sc
h
e
d
u
li
n
g
d
e
c
isio
n
s.
Th
e
u
se
o
f
th
e
se
a
l
g
o
ri
t
h
m
s
in
c
o
n
ju
n
c
ti
o
n
with
T
o
U
tari
ffs
is
c
o
st
e
ffe
c
ti
v
e
wh
e
n
c
o
m
p
a
re
d
to
flat
ra
te
tariffs.
G
rid
lo
a
d
a
n
a
ly
sis
s
h
o
ws
th
a
t
sc
h
e
d
u
li
n
g
a
c
c
o
rd
i
n
g
to
ti
m
e
lo
we
rs
p
e
a
k
d
e
m
a
n
d
,
e
q
u
a
l
ize
s
lo
a
d
d
istri
b
u
ti
o
n
,
a
n
d
lo
we
rs
o
p
e
ra
ti
n
g
c
o
sts
.
A
q
u
a
n
ti
tativ
e
c
o
m
p
a
riso
n
h
a
s
d
e
m
o
n
stra
ted
b
o
th
g
rid
sta
b
i
li
t
y
a
n
d
e
c
o
n
o
m
ic
e
fficie
n
c
y
g
a
in
s
o
v
e
r
u
n
c
o
n
tro
ll
e
d
c
h
a
rg
i
n
g
.
Th
e
re
su
lt
is
a
n
e
x
trem
e
ly
flex
ib
le
fra
m
e
wo
rk
fo
r
d
iffere
n
t
c
h
a
rg
i
n
g
e
v
e
n
ts
o
r
sta
ti
o
n
s
wh
ich
will
b
e
a
v
iab
le
wa
y
o
f
m
a
n
a
g
in
g
e
n
e
rg
y
i
n
t
h
e
fa
st
-
g
ro
wi
n
g
EV
c
h
a
rg
in
g
n
e
two
r
k
s.
K
ey
w
o
r
d
s
:
Dy
n
am
ic
p
r
icin
g
E
lectr
ic
v
eh
icle
E
n
er
g
y
g
r
id
E
V
c
h
ar
g
in
g
s
ch
ed
u
lin
g
Ma
ch
in
e
l
ea
r
n
in
g
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
:
Ar
ch
an
a
Kad
am
MI
T
Ar
t,
Desig
n
an
d
T
ec
h
n
o
lo
g
y
Un
iv
e
r
s
ity
Pu
n
e,
I
n
d
ia
E
m
ail:
ar
ch
an
a.
k
a
d
am
9
1
1
8
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ic
v
eh
icles
(
E
Vs)
a
r
e
p
r
o
m
is
in
g
b
o
th
i
n
ter
m
s
o
f
en
v
ir
o
n
m
en
tal
a
n
d
ec
o
n
o
m
ic
b
en
ef
its
,
as
well
as
in
cr
ea
s
in
g
av
ailab
ilit
y
an
d
ac
ce
p
tan
ce
.
So
,
th
e
g
o
v
e
r
n
m
en
t
o
f
I
n
d
ia
h
as
lau
n
c
h
ed
s
ev
er
al
in
itiativ
es
an
d
p
o
licies
th
at
aim
to
en
co
u
r
ag
e
th
e
wid
esp
r
ea
d
u
s
e
o
f
E
Vs
an
d
in
s
p
ir
e
a
g
r
ee
n
er
,
s
u
s
tain
ab
le
f
u
tu
r
e
.
Su
c
h
in
itiativ
es
wil
l
f
o
cu
s
o
n
s
p
r
ea
d
in
g
k
n
o
wled
g
e
to
th
e
p
u
b
lic
an
d
cr
ea
tin
g
in
ce
n
ti
v
es
th
r
o
u
g
h
in
f
o
g
r
a
p
h
ics
an
d
f
in
an
cial
ass
is
tan
ce
f
o
r
th
o
s
e
s
ee
k
in
g
E
Vs.
W
e
n
ee
d
to
im
p
r
o
v
e
f
o
r
ec
ast
s
f
o
r
c
h
ar
g
in
g
tim
es
o
f
elec
tr
i
c
v
eh
icles
wh
ich
r
ef
lect
f
ac
to
r
s
s
u
ch
as
th
e
co
s
t
s
av
in
g
s
,
en
a
b
lin
g
u
s
t
o
m
ak
e
a
m
o
r
e
ef
f
icien
t
tr
a
n
s
itio
n
f
r
o
m
g
r
ee
n
en
e
r
g
y
to
cle
an
en
e
r
g
y
in
ter
m
s
o
f
b
o
th
air
q
u
ality
an
d
ca
r
b
o
n
d
io
x
id
e
em
is
s
io
n
s
.
As
th
e
d
em
an
d
f
o
r
E
Vs
in
cr
ea
s
es
an
d
d
em
an
d
r
esp
o
n
s
e
b
ec
o
m
es
m
o
r
e
cr
itical,
ch
ar
g
i
n
g
tim
etab
les
f
o
r
E
Vs
n
ee
d
to
im
p
r
o
v
e
in
o
r
d
er
to
m
ain
tai
n
g
r
id
s
tab
ilit
y
an
d
en
s
u
r
e
o
u
r
s
u
s
tain
ab
le
f
u
tu
r
e
:
i
)
w
e
n
ee
d
to
k
ee
p
o
u
r
ch
ar
g
in
g
tim
es
as
s
h
o
r
t
as
p
o
s
s
ib
le
;
ii
)
im
p
r
o
v
e
th
e
tim
in
g
o
f
ch
a
r
g
in
g
;
iii
)
tr
ac
k
t
h
e
s
tate
o
f
ch
ar
g
e
(
SOC
)
;
an
d
iv
)
o
p
tim
ize
c
h
ar
g
in
g
s
ch
ed
u
les.
Pre
d
ictin
g
th
e
d
em
an
d
f
o
r
elec
tr
icity
[
1
]
,
wh
ich
h
as
b
ee
n
in
v
esti
g
ated
in
n
u
m
er
o
u
s
s
tu
d
ies
o
n
f
in
an
cial
g
o
als.
I
n
th
is
p
ap
e
r
,
we
p
r
o
p
o
s
ed
a
n
elec
tr
ic
v
eh
i
cle
s
ch
ed
u
lin
g
u
s
in
g
tim
e
s
e
n
s
itiv
e
p
r
icin
g
.
T
h
e
p
r
o
p
o
s
e
d
m
u
lti
-
ag
en
t
d
ee
p
n
eu
r
al
n
etwo
r
k
i
n
[
1
]
was
tr
ai
n
ed
f
o
r
im
p
o
r
tan
t
b
atter
y
en
er
g
y
m
a
n
ag
em
en
t
asp
ec
ts
s
u
ch
as
tr
av
el
tim
e,
r
a
n
g
e
u
n
ce
r
tain
ty
,
e
x
p
ec
ted
d
ep
ar
t
u
r
e
tim
e
,
an
d
b
atter
y
s
to
r
ag
e
ca
p
ac
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
S
u
s
ta
in
a
b
le
e
-
mo
b
ilit
y
w
ith
co
n
tr
o
lled
ch
a
r
g
in
g
s
ch
eme
b
a
s
ed
o
n
g
r
id
en
erg
y
u
s
in
g
…
(
A
r
ch
a
n
a
K
a
d
a
m)
1037
I
n
g
en
er
al,
en
er
g
y
ef
f
icien
c
y
,
en
er
g
y
m
an
ag
e
m
en
t,
an
d
co
s
t
r
ed
u
ctio
n
s
tr
ateg
ies
ar
e
em
p
lo
y
ed
[
2
]
.
S
h
o
ws
th
at
th
e
d
ata
o
n
th
e
ti
m
in
g
o
f
c
h
ar
g
i
n
g
,
r
eliab
ilit
y
o
f
p
o
wer
g
r
id
,
an
d
af
f
o
r
d
a
b
ilit
y
o
f
elec
tr
ic
v
e
h
icle
ch
ar
g
in
g
ar
e
v
ar
iab
le
ac
r
o
s
s
lo
ca
tio
n
s
.
A
r
ea
l
-
tim
e
s
ch
e
d
u
lin
g
m
eth
o
d
[
3
]
is
em
p
lo
y
e
d
to
m
ak
e
d
y
n
am
ic
ad
ju
s
tm
en
ts
to
th
e
in
itial
d
a
y
-
ah
ea
d
p
la
n
to
en
s
u
r
e
th
at
th
e
s
ch
ed
u
lin
g
is
p
r
ec
is
e
a
n
d
g
r
id
s
tab
ilit
y
is
m
ain
tain
ed
.
I
n
teg
r
atin
g
E
Vs
in
to
th
e
p
o
wer
g
r
id
b
r
in
g
s
s
o
m
e
co
m
p
lex
ities
an
d
u
n
ce
r
tai
n
ties
th
at
ca
n
p
o
s
e
ch
allen
g
es
f
o
r
tr
a
d
itio
n
al
s
tab
ilit
y
an
d
r
eliab
ilit
y
ass
ess
m
en
ts
.
T
h
e
s
tatis
tical
p
r
ed
ictio
n
s
ar
e
o
f
te
n
in
c
o
r
r
ec
t,
wh
ich
ca
n
s
ig
n
if
ican
tly
im
p
a
ct
th
e
d
e
p
en
d
a
b
ilit
y
o
f
th
e
d
ay
-
ah
ea
d
p
lan
n
in
g
o
f
ch
ar
g
in
g
p
o
wer
allo
tted
to
ea
ch
E
V.
E
lectr
ic
v
eh
icle
ch
a
r
g
in
g
h
as
b
ee
n
p
r
o
v
e
n
to
b
e
m
o
r
e
r
elia
b
le
an
d
ef
f
icien
t
i
n
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
wh
en
f
ac
to
r
s
s
u
ch
as
ch
ar
g
in
g
s
tatio
n
lo
ca
tio
n
s
,
tr
av
el
d
is
t
an
ce
s
,
an
d
ex
ter
n
al
co
n
d
itio
n
s
,
in
clu
d
in
g
tr
af
f
ic
an
d
wea
th
er
,
ar
e
ta
k
en
in
t
o
ac
co
u
n
t
[
4
]
.
A
d
ee
p
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
(
DR
L
)
m
eth
o
d
o
lo
g
y
was
em
p
lo
y
e
d
to
o
p
tim
ize
d
ec
is
io
n
-
m
ak
in
g
u
n
d
er
th
ese
c
o
m
p
lex
co
n
d
itio
n
s
.
T
h
ese
co
n
d
itio
n
s
ar
e
also
ch
ar
ac
ter
ized
b
y
u
n
ce
r
tain
ty
,
m
ak
in
g
DR
L
s
u
itab
le
f
o
r
h
an
d
lin
g
s
u
ch
s
ce
n
ar
i
o
s
[
5
]
.
I
n
th
e
p
r
e
v
io
u
s
s
tu
d
y
[
6
]
,
t
h
e
im
p
lem
en
tatio
n
was
ca
r
r
ied
o
u
t
in
two
s
u
cc
ess
iv
e
s
tag
es.
I
n
itially
,
an
o
p
tim
al
d
ay
-
ah
ea
d
p
o
wer
s
ch
e
d
u
lin
g
p
lan
at
th
e
g
r
id
c
o
n
n
ec
t
io
n
p
o
i
n
t
(
GC
P)
was
d
ev
elo
p
e
d
,
f
o
llo
wed
b
y
th
e
d
ep
lo
y
m
e
n
t
o
f
a
r
ea
l
-
tim
e
m
o
d
el
p
r
ed
ictiv
e
co
n
tr
o
l
(
MPC
)
ap
p
r
o
ac
h
.
T
h
is
s
tr
ateg
y
u
tili
z
es
th
e
f
lex
ib
ilit
y
o
f
elec
tr
ic
v
eh
icle
ch
ar
g
in
g
s
tatio
n
s
(
E
VC
S)
to
p
r
ec
is
ely
tr
ac
k
th
e
d
is
p
atch
s
ch
ed
u
le
an
d
en
s
u
r
e
r
eliab
le
an
d
r
esp
o
n
s
iv
e
g
r
id
p
er
f
o
r
m
a
n
ce
.
C
ao
et
a
l.
[
7
]
r
ed
ef
in
e
d
t
h
e
o
n
lin
e
o
p
tim
izatio
n
p
r
o
b
lem
an
d
in
t
r
o
d
u
ce
d
two
ac
to
r
-
cr
it
ic
lear
n
in
g
alg
o
r
ith
m
s
s
to
ch
asti
c
co
n
tin
u
o
u
s
ac
to
r
(
SC
A)
an
d
cr
itic
-
as
s
is
ted
lear
n
in
g
with
co
n
tin
u
o
u
s
ac
tio
n
s
(
C
AL
C
)
.
T
h
ese
alg
o
r
ith
m
s
wer
e
d
esig
n
ed
to
en
ab
le
co
n
tin
u
o
u
s
ch
ar
g
in
g
ac
tio
n
s
an
d
im
p
r
o
v
e
ad
ap
tiv
e,
r
ea
l
-
tim
e
d
ec
is
io
n
-
m
ak
in
g
to
ad
d
r
ess
th
e
ch
allen
g
es
p
r
esen
ted
b
y
d
y
n
am
ic
an
d
u
n
ce
r
tain
E
V
c
h
ar
g
in
g
e
n
v
ir
o
n
m
en
ts
.
T
h
is
wo
r
k
esti
m
ated
th
at
E
V
ch
ar
g
in
g
co
s
t
o
f
C
AL
C
was
5
.
5
6
%
h
ig
h
er
th
a
n
th
at
o
f
SC
A
b
u
t
7
.
2
4
%
lo
wer
th
an
th
at
o
f
ad
ap
tiv
e
e
n
er
g
y
m
an
ag
em
en
t
(
AE
M)
.
C
AL
C
d
em
o
n
s
tr
ated
s
ig
n
if
ica
n
tly
h
i
g
h
er
co
m
p
u
tatio
n
al
ef
f
icien
cy
an
d
ac
h
iev
e
d
n
ea
r
-
o
p
tim
al
p
er
f
o
r
m
an
ce
co
m
p
ar
e
d
to
SC
A.
2.
RE
L
AT
E
D
WO
RK
R
ec
en
t
wo
r
k
h
as
s
h
o
wn
th
e
ab
ilit
y
to
ap
p
ly
d
ee
p
lear
n
in
g
(
DL
)
to
c
o
m
p
lex
s
y
s
tem
s
.
Gu
p
ta
et
a
l.
[
6
]
ac
h
ie
v
ed
a
9
9
.
9
7
%
ac
c
u
r
ac
y
in
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
(
I
DS)
u
s
in
g
a
h
y
b
r
id
L
STM
-
s
win
tr
an
s
f
o
r
m
er
a
n
d
tr
an
s
f
er
lear
n
in
g
.
T
h
is
p
er
f
o
r
m
an
ce
is
co
m
p
ar
ab
le
to
th
at
ac
h
iev
ed
with
tr
ad
itio
n
al
DL
m
o
d
els.
I
n
p
o
wer
s
y
s
tem
s
,
r
esear
ch
er
s
ar
e
in
teg
r
atin
g
co
m
p
o
n
en
ts
s
u
ch
as
E
V
to
im
p
r
o
v
e
th
e
g
r
id
.
Pre
v
io
u
s
s
tu
d
ies
[
8
]
a
n
d
[
9
]
in
co
r
p
o
r
at
ed
elec
tr
ic
v
e
h
icles
in
to
d
em
a
n
d
r
esp
o
n
s
e
s
tr
ateg
ies
f
o
r
th
e
d
ay
-
ah
ea
d
p
la
n
n
in
g
in
o
r
d
e
r
to
o
b
tain
n
et
p
r
o
f
it
a
n
d
s
u
r
p
lu
s
p
o
wer
at
t
h
e
ex
p
en
s
e
o
f
g
r
id
lim
itatio
n
s
an
d
ac
tu
a
l
d
ata,
s
u
ch
as
State
o
f
C
h
ar
g
e
(
SOC
)
.
T
h
is
m
o
v
e
to
war
d
o
p
tim
izatio
n
r
ef
lects
t
h
e
g
r
o
win
g
u
s
e
o
f
p
r
ed
ictiv
e
an
aly
tics
;
lin
es
[
9
]
ex
am
in
ed
lin
ea
r
r
eg
r
ess
io
n
f
o
r
en
er
g
y
c
o
n
s
u
m
p
tio
n
,
an
d
a
n
o
th
er
s
tu
d
y
[
1
0
]
ex
am
i
n
ed
m
ac
h
in
e
lear
n
in
g
t
o
o
ls
to
p
lan
f
o
r
c
h
ar
g
in
g
a
n
d
f
o
r
ec
ast
co
s
t
-
ef
f
ec
tiv
e
s
tr
ateg
ies.
P
an
et
a
l.
[
1
0
]
d
escr
ib
ed
th
e
n
o
n
-
co
n
v
ex
n
atu
r
e
o
f
th
is
is
s
u
e
an
d
p
r
o
p
o
s
ed
an
im
p
r
o
v
e
d
h
y
b
r
id
alg
o
r
ith
m
t
h
at
co
m
b
in
es
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
an
d
th
e
g
r
av
itatio
n
al
s
ea
r
ch
alg
o
r
ith
m
(
GSA)
to
m
ak
e
b
etter
th
e
allo
ca
tio
n
o
f
E
V
ch
ar
g
in
g
an
d
d
is
ch
ar
g
in
g
p
o
wer
.
Pan
et
a
l.
[
1
0
]
ex
am
in
ed
m
ac
h
in
e
lear
n
in
g
to
o
ls
th
at
ca
n
p
r
ed
ict
o
p
tim
al
s
o
lu
tio
n
s
f
o
r
co
s
t
-
ef
f
ec
tiv
e
m
o
d
els.
C
h
ar
g
in
g
s
ch
ed
u
lin
g
s
o
lu
tio
n
s
ar
e
m
ad
e
m
o
r
e
e
f
f
ec
tiv
e
th
r
o
u
g
h
th
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
P
h
an
et
a
l.
[
9
]
i
n
v
esti
g
ated
th
e
ap
p
licatio
n
o
f
lin
ea
r
r
eg
r
ess
io
n
an
aly
s
is
f
o
r
f
o
r
ec
asti
n
g
en
er
g
y
co
n
s
u
m
p
tio
n
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
aim
in
g
to
en
h
an
ce
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
s
u
p
p
o
r
t
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
-
m
ak
in
g
in
en
e
r
g
y
m
a
n
ag
em
en
t sy
s
tem
s
.
R
esear
ch
o
n
en
er
g
y
s
y
s
tem
s
o
f
ten
em
p
lo
y
s
m
ac
h
in
e
lear
n
i
n
g
f
o
r
p
r
ed
ictiv
e
an
d
o
p
tim
iz
atio
n
task
s
.
Sp
ec
if
ically
,
th
e
u
tili
ty
o
f
g
en
er
al
m
ac
h
in
e
lear
n
in
g
to
o
ls
f
o
r
f
o
r
ec
asti
n
g
en
e
r
g
y
co
n
s
u
m
p
tio
n
[
9
]
a
n
d
en
h
an
cin
g
th
e
ef
f
ec
tiv
en
ess
o
f
co
s
t
-
ef
f
ec
tiv
e
ch
ar
g
e
s
ch
e
d
u
lin
g
s
o
lu
tio
n
s
[
1
0
]
h
as
b
ee
n
estab
lis
h
ed
.
W
h
il
e
p
ap
er
s
[
1
1
]
,
[
1
2
]
estab
lis
h
th
e
n
ee
d
f
o
r
an
d
ef
f
icac
y
o
f
alg
o
r
i
th
m
ically
s
u
p
er
io
r
o
p
tim
izatio
n
tech
n
iq
u
es in
t
h
e
g
en
er
al
ML
d
o
m
ain
.
I
n
o
r
d
er
t
o
m
ax
im
ize
s
m
ar
t
E
V
ch
ar
g
i
n
g
,
a
n
o
th
e
r
r
esea
r
ch
s
tu
d
y
co
n
s
id
er
e
d
a
d
y
n
a
m
ic
tar
if
f
f
r
am
ewo
r
k
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
,
wh
ic
h
u
s
ed
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
was
d
escr
ib
ed
.
T
h
is
r
esear
ch
ex
am
in
ed
th
e
co
m
b
in
ed
ch
alle
n
g
es o
f
p
r
icin
g
an
d
s
ch
ed
u
lin
g
f
o
r
elec
tr
ic
v
eh
icle
ch
ar
g
i
n
g
f
r
o
m
th
e
v
iewp
o
i
n
t
o
f
a
ch
ar
g
in
g
s
tatio
n
o
p
er
ato
r
[
1
3
]
,
[
1
4
]
.
T
h
e
o
b
jectiv
e
is
to
d
ev
elo
p
p
r
icin
g
alg
o
r
ith
m
s
th
at
en
co
u
r
a
g
e
th
e
p
ar
ticip
atio
n
o
f
elec
tr
ic
v
e
h
icl
e
u
s
er
s
in
th
e
ch
ar
g
in
g
n
etwo
r
k
.
T
h
ese
alg
o
r
ith
m
s
aim
e
d
to
o
p
tim
ize
ch
ar
g
in
g
tim
es p
er
ch
ar
g
e
r
,
en
s
u
r
i
n
g
f
u
ll e
n
er
g
y
d
eliv
er
y
with
in
ea
ch
u
s
er
'
s
av
ailab
le
tim
e
win
d
o
w.
Dee
p
l
ea
r
n
in
g
(
DL
)
m
o
d
els
p
r
o
v
id
e
co
n
s
id
er
ab
le
im
p
r
o
v
e
m
en
ts
in
p
er
f
o
r
m
a
n
ce
f
o
r
in
t
r
icate
task
s
.
No
n
eth
eless
,
th
eir
u
n
clea
r
b
lack
-
b
o
x
c
h
ar
ac
ter
is
tics
r
eq
u
ir
e
in
v
esti
g
atio
n
in
t
o
m
et
h
o
d
s
th
at
p
r
o
m
o
t
e
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
.
C
o
n
s
e
q
u
e
n
t
l
y
,
t
h
e
i
n
t
e
g
r
a
t
i
o
n
o
f
E
x
p
l
a
i
n
a
b
l
e
A
I
(
X
A
I
)
,
a
s
h
i
g
h
l
i
g
h
t
e
d
i
n
r
e
c
e
n
t
s
t
u
d
i
e
s
[
1
5
]
,
[
1
6
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
3
6
-
1
0
5
0
1038
i
s
v
ital
f
o
r
th
e
im
p
o
r
tan
t
s
h
if
t
to
war
d
s
tr
an
s
p
ar
e
n
t
an
d
r
elia
b
le
d
ec
is
io
n
-
m
a
k
in
g
w
h
ich
is
n
ec
ess
ar
y
f
o
r
th
e
ef
f
ec
tiv
e
im
p
lem
en
tatio
n
o
f
clin
ical
o
r
cr
itical
s
y
s
tem
s
.
R
esear
ch
er
s
in
[
2
]
,
[
1
7
]
p
r
o
p
o
s
ed
a
m
eth
o
d
th
at
i
n
clu
d
e
d
th
e
tim
e
o
f
u
s
e
(
T
OU)
p
r
ice‐
b
ase
d
d
em
an
d
r
esp
o
n
s
e
m
o
d
el
a
n
d
d
y
n
am
ic
g
r
id
to
v
eh
icle
(
G2
V
)
c
h
ar
g
e
s
ch
ed
u
lin
g
f
o
r
elec
tr
ic
v
e
h
icle
ag
g
r
eg
at
o
r
(
E
VA
)
th
at
o
p
tim
izes
r
eg
u
latio
n
s
er
v
ices
an
d
ch
ar
g
in
g
co
s
ts
s
im
u
ltan
eo
u
s
ly
.
Pre
v
io
u
s
s
tu
d
y
[
1
8
]
p
r
o
p
o
s
ed
a
p
ea
k
-
s
h
av
in
g
o
p
tim
izatio
n
m
o
d
el
t
o
m
in
im
ize
p
o
wer
g
r
id
lo
s
s
es
th
r
o
u
g
h
p
r
io
r
itized
a
n
d
c
o
o
r
d
i
n
ated
ch
a
r
g
in
g
an
d
d
is
ch
ar
g
in
g
ac
tiv
ities
.
Dev
i
e
t
a
l.
[
1
9
]
f
o
cu
s
o
n
th
e
lin
ea
r
r
eg
r
ess
io
n
d
em
a
n
d
f
o
r
ec
as
t
(
L
R
DF)
th
at
ca
n
b
e
u
s
ed
to
g
e
n
er
ate
m
o
r
e
ac
c
u
r
ate
d
em
an
d
f
o
r
ec
asts
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
a
p
p
r
o
ac
h
es
alo
n
g
with
en
o
u
g
h
h
is
to
r
ical
d
ata
o
n
d
em
an
d
f
o
r
e
ca
s
ts
,
p
r
o
d
u
ct
f
o
r
ec
asts
,
an
d
s
ales p
r
o
jectio
n
s
.
Sh
alev
-
Sh
war
tz
an
d
Z
h
an
g
[
1
1
]
p
r
o
v
i
d
ed
a
th
o
r
o
u
g
h
an
a
ly
s
is
o
f
th
e
s
to
ch
asti
c
d
u
al
co
o
r
d
in
at
e
ascen
t
(
SDC
A)
alg
o
r
ith
m
.
T
h
eir
s
tu
d
y
d
e
m
o
n
s
tr
ated
t
h
at
its
o
p
tim
izatio
n
s
tr
ateg
i
es
p
r
o
v
i
d
ed
s
tr
o
n
g
th
eo
r
etica
l
g
u
a
r
an
tees.
T
h
ese
g
u
ar
an
tees
wer
e
at
p
ar
with
o
r
b
etter
th
a
n
th
o
s
e
o
f
c
o
n
v
e
n
tio
n
al
o
p
tim
izatio
n
tech
n
iq
u
es
.
C
o
n
s
cio
u
s
o
f
th
e
im
p
o
r
ta
n
ce
o
f
alg
o
r
ith
m
ic
ef
f
icien
cy
f
o
r
p
r
ac
tical
u
s
e,
Ya
tes
an
d
I
s
lam
[
2
0
]
d
ev
elo
p
e
d
th
e
Fas
tFo
r
est
alg
o
r
ith
m
.
T
h
e
alg
o
r
ith
m
was
ev
alu
ated
to
ass
es
s
its
p
er
f
o
r
m
an
ce
.
I
t
s
ig
n
if
ican
tly
in
cr
ea
s
ed
th
e
s
p
ee
d
o
f
r
a
n
d
o
m
f
o
r
est p
r
o
c
ess
in
g
with
o
u
t c
o
m
p
r
o
m
is
in
g
p
r
ed
ictio
n
ac
cu
r
a
cy
.
I
n
ter
m
s
o
f
tech
n
o
lo
g
y
,
Far
es
et
a
l.
[
1
6
]
p
r
o
p
o
s
ed
a
m
u
lti
-
p
u
r
p
o
s
e
p
lan
f
o
r
E
V
ch
ar
g
in
g
in
f
r
astru
ctu
r
e
th
at
b
alan
ce
s
en
v
ir
o
n
m
e
n
tal
g
o
als
an
d
g
r
id
d
e
m
an
d
.
T
h
e
p
r
o
p
o
s
ed
s
tr
ateg
y
is
an
o
p
tim
izatio
n
p
lan
f
o
c
u
s
ed
o
n
th
r
ee
g
o
als.
T
h
ese
g
o
als
ar
e
b
o
o
s
tin
g
E
V
ca
p
ac
ity
,
cu
ttin
g
ca
r
b
o
n
d
io
x
id
e
em
is
s
io
n
s
,
an
d
lo
wer
in
g
b
o
th
in
v
estme
n
t a
n
d
o
p
er
atin
g
c
o
s
ts
o
f
th
e
d
e
v
ices
.
T
h
is
p
ap
er
f
o
cu
s
es
o
n
ad
d
r
ess
in
g
th
is
g
ap
b
y
u
tili
zin
g
an
ef
f
icien
t
m
ac
h
in
e
lear
n
in
g
ar
ch
itectu
r
e.
T
h
e
p
r
o
p
o
s
ed
a
r
ch
itectu
r
e
ca
n
im
p
licitly
lear
n
a
n
d
g
e
n
er
al
ize
th
e
co
n
s
tr
ain
ts
n
ee
d
e
d
f
o
r
o
p
tim
al
an
d
g
r
id
-
awa
r
e
ch
ar
g
e
s
ch
e
d
u
lin
g
.
T
h
e
cu
r
r
e
n
t
wo
r
k
aim
s
to
co
n
n
ec
t
ad
v
a
n
ce
d
o
p
tim
izatio
n
p
r
in
ci
p
les
with
a
ch
ar
g
e
s
ch
ed
u
lin
g
f
r
am
ewo
r
k
.
3.
CH
AL
L
E
NG
E
S AN
D
SO
L
UT
I
O
N
S
T
h
e
f
o
llo
win
g
ar
e
t
h
e
ch
a
llen
g
es
to
ac
h
iev
e
s
m
o
o
th
E
V
ch
a
r
g
in
g
d
e
m
an
d
an
d
r
esp
o
n
s
e.
Fig
u
r
e
1
h
ig
h
lig
h
ts
th
e
r
elatio
n
s
h
ip
b
etwe
en
d
em
a
n
d
r
esp
o
n
s
e
in
th
e
elec
tr
ical
g
r
id
a
n
d
o
p
tim
al
E
V
ch
ar
g
in
g
,
an
d
th
e
k
e
y
b
en
ef
its
o
f
o
p
tim
a
l
E
V
ch
a
r
g
in
g
ar
e
in
clu
d
ed
.
I
t
also
s
h
o
ws
th
e
s
o
l
u
tio
n
s
to
th
e
ch
allen
g
e
f
o
r
g
r
id
p
ar
am
eter
m
ain
te
n
an
ce
[
2
1
]
,
[
2
2
]
.
E
V
co
n
s
u
m
e
r
s
f
ac
e
m
an
y
ch
allen
g
es
s
h
o
wn
in
T
ab
le
1
,
wh
ich
also
ex
p
lain
s
m
ac
h
in
e
lear
n
in
g
as
well
as o
th
er
s
o
lu
tio
n
s
f
o
r
co
n
s
u
m
er
s
.
Fig
u
r
e
1
.
Dem
a
n
d
r
esp
o
n
s
e
o
f
E
V
T
ab
le
1
.
C
h
allen
g
es
f
o
r
s
m
o
o
t
h
d
em
an
d
r
esp
o
n
s
e
C
h
a
l
l
e
n
g
e
S
o
l
u
t
i
o
n
S
e
c
u
r
i
t
y
r
i
s
k
s
B
l
o
c
k
c
h
a
i
n
a
n
d
e
n
c
r
y
p
t
e
d
c
o
m
mu
n
i
c
a
t
i
o
n
p
r
o
t
o
c
o
l
s
I
n
d
i
v
i
d
u
a
l
a
g
r
e
e
m
e
n
t
En
t
i
c
e
me
n
t
s
a
n
d
c
o
st
sa
v
i
n
g
s f
o
r
o
f
f
-
p
e
a
k
c
h
a
r
g
i
n
g
G
r
i
d
f
l
u
c
t
u
a
t
i
o
n
s
R
e
a
l
-
t
i
me
mo
n
i
t
o
r
i
n
g
a
n
d
smar
t
c
h
a
r
g
i
n
g
a
l
t
e
r
a
t
i
o
n
s
P
e
a
k
l
o
a
d
d
e
m
a
n
d
AI
-
b
a
se
d
d
y
n
a
mi
c
p
r
i
c
i
n
g
a
n
d
d
e
m
a
n
d
r
e
s
p
o
n
s
e
4.
SM
AR
T
E
V
CH
ARG
I
NG
S
CH
E
DU
L
I
NG
T
h
e
s
ch
ed
u
lin
g
o
f
s
m
ar
t
ch
ar
g
in
g
ef
f
ec
tiv
ely
in
teg
r
ates
au
to
m
atio
n
f
o
r
elec
tr
ic
v
eh
icles
with
s
o
p
h
is
ticated
co
m
m
u
n
icatio
n
m
eth
o
d
s
an
d
in
tellig
en
t
m
an
a
g
em
en
t
s
y
s
tem
s
.
T
h
is
co
llab
o
r
atio
n
en
h
an
ce
s
th
e
ef
f
icien
cy
an
d
e
f
f
ec
tiv
en
ess
o
f
ch
ar
g
in
g
elec
tr
ic
v
eh
icles.
T
h
e
p
r
im
ar
y
g
o
al
is
to
lo
wer
ex
p
en
s
es
an
d
en
h
an
c
e
en
er
g
y
e
f
f
icien
cy
with
in
th
e
g
r
id
[
2
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
S
u
s
ta
in
a
b
le
e
-
mo
b
ilit
y
w
ith
co
n
tr
o
lled
ch
a
r
g
in
g
s
ch
eme
b
a
s
ed
o
n
g
r
id
en
erg
y
u
s
in
g
…
(
A
r
ch
a
n
a
K
a
d
a
m)
1039
5.
SYST
E
M
ARCH
I
T
E
CT
U
R
E
I
n
th
is
s
tu
d
y
,
th
e
f
o
cu
s
was
o
n
an
ar
tific
ial
in
tellig
en
ce
d
r
i
v
en
e
n
er
g
y
m
an
a
g
em
en
t
s
y
s
tem
,
wh
ich
'
s
r
ea
lly
im
p
o
r
tan
t
to
th
e
o
v
er
all
s
y
s
tem
p
lan
.
T
h
e
ar
tific
ial
in
t
ellig
en
ce
d
r
iv
en
en
er
g
y
m
an
a
g
em
en
t
s
y
s
tem
is
a
p
ar
t
o
f
th
is
p
r
o
ject
[
2
3
]
.
T
h
e
AI
-
d
r
iv
en
en
er
g
y
m
an
a
g
em
en
t
s
y
s
tem
AI
DM
S
s
y
s
tem
,
s
h
o
wn
in
Fig
u
r
e
2
,
u
s
es
m
ath
to
f
o
r
ec
ast
e
n
er
g
y
lo
a
d
s
an
d
a
d
ju
s
t
h
o
w
m
u
c
h
p
o
wer
is
u
s
ed
t
o
ch
a
r
g
e
f
r
o
m
th
e
g
r
i
d
.
I
t
aim
s
to
o
p
tim
ize
en
er
g
y
u
s
e.
Or
d
e
r
ed
d
ata
wa
s
d
etec
ted
.
T
h
e
d
ata
h
elp
ed
t
r
an
s
f
er
an
d
id
e
n
tify
lo
a
d
s
.
T
h
e
d
y
n
am
ic
p
r
icin
g
m
o
d
el
m
a
n
ag
ed
tr
an
s
m
is
s
io
n
,
d
is
tr
ib
u
tio
n
,
an
d
u
tili
za
tio
n
.
T
h
is
h
ap
p
e
n
ed
at
c
h
ar
g
in
g
p
o
in
ts
.
T
h
ese
p
o
i
n
ts
wer
e
av
ailab
le
at
th
e
co
r
r
esp
o
n
d
in
g
ch
a
r
g
in
g
s
tatio
n
.
Ultim
ately
,
t
h
e
AI
DM
S,
th
e
lin
ea
r
r
eg
r
ess
io
n
alg
o
r
ith
m
f
o
r
en
e
r
g
y
m
an
ag
em
e
n
t
co
u
l
d
b
e
a
ch
ea
p
e
r
o
p
tio
n
,
s
im
ilar
to
th
e
g
r
id
.
T
h
er
e
we
r
e
s
o
m
e
p
r
o
b
lem
s
th
o
u
g
h
.
Fig
u
r
e
2
.
AI
-
b
ased
en
e
r
g
y
s
y
s
tem
ar
ch
itectu
r
e
o
f
E
V
6.
E
L
E
C
T
RIC V
E
H
I
C
L
E
CH
ARG
I
NG
T
AR
I
F
F
T
h
e
p
r
icin
g
m
o
d
els
f
o
r
elec
tr
i
c
v
eh
icle
ch
a
r
g
in
g
is
elec
tr
ic
v
eh
icle
ch
ar
g
in
g
p
r
ices
ar
e
also
af
f
ec
ted
b
y
h
o
w
p
o
wer
ev
er
y
o
n
e
else
i
s
u
s
in
g
at
th
e
s
am
e
tim
e.
T
h
ese
th
in
g
s
th
at
d
ec
id
e
th
e
co
s
t
in
clu
d
e
h
o
w
p
o
wer
th
e
elec
tr
ic
v
eh
icle
u
s
es,
h
o
w
f
ast
it
ch
ar
g
es
an
d
h
o
w
lo
n
g
it
is
p
lu
g
g
ed
in
[
2
1
]
.
As
elec
tr
ic
v
eh
icles
h
av
e
b
ec
o
m
e
m
o
r
e
p
o
p
u
lar
in
th
e
p
ast
d
ec
ad
e,
u
tili
ties
h
av
e
h
a
d
to
r
eth
in
k
th
eir
ap
p
r
o
ac
h
t
o
m
an
ag
in
g
en
e
r
g
y
d
em
an
d
.
B
y
co
n
tr
o
llin
g
e
n
er
g
y
-
co
n
s
u
m
in
g
d
e
v
ices
an
d
d
ev
ices
th
at
co
n
s
u
m
e
m
o
r
e
e
n
er
g
y
,
u
tili
ties
ca
n
m
an
ag
e
en
e
r
g
y
d
em
an
d
m
o
r
e
ef
f
ec
tiv
ely
[
2
1
]
,
[
2
2
]
.
7.
M
ACH
I
N
E
L
E
AR
NING
T
O
O
L
S
Ma
ch
in
e
lear
n
in
g
to
o
ls
u
tili
ze
v
ar
io
u
s
tech
n
iq
u
es
f
o
r
b
u
ild
i
n
g
an
d
d
ep
l
o
y
in
g
m
o
d
els
th
at
lear
n
f
r
o
m
d
ata.
Var
io
u
s
m
ac
h
in
e
lea
r
n
i
n
g
m
o
d
els
wer
e
u
s
ed
,
s
u
ch
as
L
in
ea
r
r
eg
r
ess
io
n
,
s
to
ch
as
tic
d
u
al
co
o
r
d
in
ate
ascen
t
(
SDC
A
)
an
d
Fas
t
Fo
r
es
t
(
FF
)
m
ac
h
in
e
lear
n
in
g
m
o
d
el
to
o
p
tim
ize
th
e
en
er
g
y
d
is
tr
ib
u
tio
n
an
d
c
h
ar
g
in
g
s
ch
ed
u
les o
f
E
Vs.
7
.
1
.
L
inea
r
re
g
re
s
s
io
n
T
h
e
v
alu
e
o
f
a
v
ar
ia
b
le
is
p
r
ed
icted
u
s
in
g
lin
ea
r
r
eg
r
ess
io
n
an
aly
s
is
b
y
r
ef
er
en
ce
to
its
v
alu
e.
T
h
e
d
ep
en
d
e
n
t
v
ar
iab
le
is
th
e
o
n
e
y
o
u
wis
h
to
p
r
ed
ict.
I
n
r
e
g
r
ess
io
n
an
aly
s
is
,
th
e
in
d
ep
en
d
en
t
v
ar
iab
le(
s
)
ar
e
th
e
p
r
ed
icto
r
s
u
s
ed
to
m
o
d
el
an
d
f
o
r
ec
ast
th
e
v
alu
e
o
f
th
e
d
ep
e
n
d
en
t
v
ar
ia
b
le.
T
h
e
an
aly
s
is
wo
r
k
s
b
y
esti
m
atin
g
th
e
eq
u
atio
n
'
s
co
ef
f
icien
ts
,
wh
ich
q
u
an
tif
y
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
in
d
ep
en
d
en
t
v
ar
i
ab
le(
s
)
an
d
th
e
b
est
p
r
ed
icted
v
alu
e
o
f
th
e
d
ep
en
d
en
t
v
ar
ia
b
le
[
1
1
]
.
L
i
n
ea
r
r
e
g
r
ess
io
n
f
its
a
s
tr
aig
h
t
lin
e
t
o
th
e
d
is
cr
ep
a
n
cies
b
etwe
en
ex
p
ec
ted
an
d
ac
t
u
al
o
u
tp
u
t v
alu
es o
r
t
o
r
ea
lize
t
h
e
b
est
-
f
it lin
e
f
o
r
a
s
et
o
f
c
o
r
r
esp
o
n
d
in
g
n
u
m
b
er
s
.
7
.
2
.
L
inea
r
re
g
re
s
s
io
n f
o
r
e
nerg
y
g
rid
L
in
ea
r
r
eg
r
ess
io
n
f
its
a
s
tr
aig
h
t
lin
e
to
th
e
d
is
cr
ep
a
n
cies
b
etwe
en
ex
p
ec
ted
an
d
ac
tu
al
o
u
tp
u
t
v
alu
es
o
r
t
o
r
ea
lize
th
e
b
est
-
f
it
lin
e
f
o
r
a
s
et
o
f
co
r
r
esp
o
n
d
i
n
g
n
u
m
b
er
s
[
1
0
]
.
T
h
e
v
al
u
e
o
f
C
(
d
ep
en
d
e
n
t
v
ar
iab
le)
f
r
o
m
P
(
in
d
ep
en
d
en
t v
a
r
iab
le)
is
esti
m
ated
b
y
(
1
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
3
6
-
1
0
5
0
1040
=
+
(
1
)
As p
er
th
e
co
r
r
esp
o
n
d
e
n
ce
,
th
e
lin
e
eq
u
atio
n
M
is
r
ep
r
esen
t
ed
b
y
(
2
)
.
=
∑
(
−
՟
)
(
−
՟
)
∑
(
−
՟
)
2
(
2
)
I
n
th
is
way
,
th
e
v
alu
e
o
f
M
in
th
e
l
in
ea
r
r
eg
r
ess
io
n
m
eth
o
d
is
ca
lcu
lated
to
f
in
d
th
e
b
est
f
it
lin
e.
I
n
(
2
)
,
ch
ar
g
i
n
g
p
r
ice
is
r
ep
r
esen
ted
as
C
,
C
՟
is
m
ea
n
o
f
C
.
On
a
s
im
ilar
n
o
te,
P
r
ep
r
esen
ts
c
h
a
r
g
in
g
p
o
wer
,
P
՟
is
th
e
m
ea
n
o
f
P.
T
o
av
o
id
n
u
llifica
tio
n
o
f
er
r
o
r
d
if
f
er
en
ce
b
etwe
en
th
e
ac
tu
al
an
d
p
r
ed
icted
v
alu
es,
th
e
s
u
m
o
f
s
q
u
ar
e
ac
tu
al
ch
ar
g
in
g
p
r
ice
m
in
u
s
m
ea
n
ch
a
r
g
in
g
p
r
ice
is
u
s
ed
.
T
h
en
D
is
to
b
e
esti
m
ated
b
y
p
u
ttin
g
m
ea
n
v
alu
es o
f
P a
n
d
C
in
(
3
)
.
՟
=
՟
+
(
3
)
I
n
l
in
ea
r
r
eg
r
ess
io
n
,
R
2
r
ep
r
e
s
en
ts
h
o
w
th
e
lin
e
p
r
ed
icts
th
e
ac
tu
al
p
o
i
n
ts
to
h
a
v
e
a
b
etter
en
er
g
y
m
o
d
el
to
m
i
n
im
ize
r
esid
u
al
er
r
o
r
.
R
2
is
ca
lcu
lated
as
(
4
)
an
d
(
5
)
.
2
=
1
−
(
)
(
)
(
4
)
2
=
1
−
∑
(
−
̂
)
2
∑
(
−
՟
)
2
(
5)
W
h
er
e
Pi is
th
e
a
ctu
al
v
alu
e
a
n
d
P h
at
is
th
e
p
r
ed
icted
v
al
u
e
.
T
h
is
s
tatis
tica
l
m
o
d
el
is
ca
s
t
-
o
f
f
to
p
r
e
d
ict
f
o
r
t
h
co
m
in
g
co
n
s
eq
u
en
ce
s
with
m
in
im
u
m
m
ea
n
s
q
u
ar
e
er
r
o
r
[
1
0
]
.
So
lin
ea
r
r
eg
r
ess
io
n
is
an
ad
m
ir
a
b
le
p
o
s
s
ib
ilit
y
f
o
r
esti
m
atin
g
en
e
r
g
y
p
er
f
o
r
m
an
ce
in
elec
tr
ic
v
eh
icle
ch
ar
g
i
n
g
s
tatio
n
s
an
d
elec
tr
icity
g
r
id
s
u
n
d
e
r
(
6
)
.
∑
=
0
(
6
)
W
h
er
e
is
th
e
elec
tr
icity
p
r
ice
at
tim
e
;
is
th
e
ch
ar
g
in
g
p
o
wer
at
tim
e
;
Δ
t
is
th
e
tim
e
in
ter
v
al
;
an
d
T
is
th
e
to
tal
tim
e
h
o
r
izo
n
.
Su
b
ject
to
co
n
s
tr
ain
ts
as (
7
)
an
d
(
8
)
.
≤
≥
(
7
)
∑
=
0
=
(
8
)
W
h
er
e
is
th
e
r
eq
u
ir
e
d
ch
ar
g
in
g
en
er
g
y
f
o
r
an
E
V.
T
h
e
er
r
o
r
m
etr
ics
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
MA
E
)
,
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
q
u
an
tif
y
th
e
m
ag
n
itu
d
e
o
f
p
r
ed
ictio
n
er
r
o
r
s
an
d
ar
e
d
e
f
in
ed
in
th
e
o
r
ig
in
al
u
n
its
o
f
th
e
tar
g
et
v
ar
iab
le
to
tal
ch
ar
g
in
g
tim
e
in
m
in
u
tes.
E
r
r
o
r
m
etr
ics
h
av
e
b
ee
n
ev
alu
ated
u
s
in
g
(9
)
to
(
1
1
)
,
r
esp
ec
tiv
ely
.
=
1
∑
|
−
̂
|
=
1
(
9
)
W
h
er
e
|
Pi
−
P̂
i
|
is
t
h
e
ab
s
o
lu
te
er
r
o
r
f
o
r
a
s
in
g
le
o
b
s
er
v
atio
n
.
=
1
∑
|
−
̂
|
2
=
1
(
1
0
)
W
h
er
e
|
Pi
−
P̂
i
|
2
is
t
h
e
s
q
u
ar
ed
er
r
o
r
f
o
r
a
s
in
g
le
o
b
s
er
v
atio
n
.
=
√
1
∑
|
−
̂
|
2
=
1
(
1
1
)
T
h
is
m
o
d
el,
p
a
r
ticu
lar
ly
in
la
r
g
e
-
s
ca
le
g
r
id
o
p
er
atio
n
s
,
ca
n
a
ls
o
b
e
r
u
m
m
a
g
e
-
s
ale
p
r
ice
o
p
t
im
izatio
n
an
d
g
r
id
lo
ad
b
alan
cin
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
S
u
s
ta
in
a
b
le
e
-
mo
b
ilit
y
w
ith
co
n
tr
o
lled
ch
a
r
g
in
g
s
ch
eme
b
a
s
ed
o
n
g
r
id
en
erg
y
u
s
in
g
…
(
A
r
ch
a
n
a
K
a
d
a
m)
1041
7
.
3
.
St
o
cha
s
t
ic
du
a
l c
o
o
rdina
t
e
a
s
ce
nt
SDC
A
i
s
g
en
er
ally
u
s
ed
f
o
r
o
p
tim
izin
g
p
e
n
alize
d
lin
ea
r
m
o
d
els,
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
,
lo
g
is
tic
r
eg
r
ess
io
n
f
r
am
ewo
r
k
s
,
an
d
co
n
v
e
n
tio
n
al
lin
ea
r
r
eg
r
ess
io
n
f
r
am
ewo
r
k
s
.
SDC
A
d
if
f
er
s
f
r
o
m
tr
ad
itio
n
al
g
r
ad
ien
t
o
p
tim
izatio
n
m
eth
o
d
s
b
y
p
er
f
o
r
m
in
g
u
p
d
ates
in
th
e
d
u
al
s
p
ac
e
an
d
alter
in
g
o
n
ly
o
n
e
co
o
r
d
in
ate
,
m
ea
n
in
g
th
e
d
u
al
v
ar
iab
le
f
o
r
an
in
d
i
v
id
u
al
tr
ain
in
g
d
ata
p
o
i
n
t
d
u
r
i
n
g
ea
ch
s
te
p
.
T
h
e
o
p
tim
izatio
n
alg
o
r
ith
m
s
s
u
ch
as
s
to
ch
asti
c
g
r
ad
ie
n
t
d
escen
t
(
SGD)
[
1
1
]
d
ir
ec
tly
o
p
tim
ize
t
h
e
p
r
im
al
lo
s
s
f
u
n
ctio
n
wh
ile
SDC
A
o
p
tim
izes
th
e
d
u
al
p
r
o
b
lem
.
SDC
A
wo
r
k
s
with
d
u
al
v
ar
iab
les
an
d
d
u
al
o
b
jectiv
e
f
u
n
ctio
n
to
s
o
lv
e
th
e
p
r
o
b
lem
.
T
o
s
o
lv
e
th
e
o
r
ig
in
al
p
r
im
al
o
p
tim
izatio
n
p
r
o
b
lem
f
o
cu
s
ed
o
n
f
in
d
in
g
t
h
e
o
p
tim
al
m
o
d
e
l
weig
h
ts
,
SDC
A
r
ef
o
r
m
u
lates
it
in
to
an
eq
u
iv
ale
n
t
d
u
al
p
r
o
b
lem
,
w
h
ich
it
th
en
a
d
d
r
ess
es.
SDC
A
p
er
f
o
r
m
s
iter
ativ
e
u
p
d
ates
to
th
e
d
u
al
v
ar
ia
b
les
with
n
ew
v
ar
iab
les
f
r
o
m
tr
a
n
s
f
o
r
m
in
g
th
e
p
r
o
b
lem
to
th
e
d
u
al
d
o
m
ain
.
T
h
e
ap
p
r
o
ac
h
m
o
d
if
ies
ea
ch
d
u
al
v
ar
iab
le
in
d
iv
id
u
ally
r
ath
er
th
an
u
p
d
atin
g
all
at
o
n
ce
,
wh
ic
h
is
r
ef
er
r
ed
t
o
as
co
o
r
d
in
ate
ascen
t.
'
Sto
ch
asti
c'
m
ea
n
s
th
at
th
e
alg
o
r
ith
m
a
d
ju
s
ts
th
e
d
u
al
v
a
r
iab
les
b
as
ed
o
n
a
r
an
d
o
m
ly
s
elec
ted
tr
ain
in
g
ex
am
p
le
at
ea
ch
iter
atio
n
.
T
h
e
g
o
al
o
f
SDC
A
i
s
to
o
p
tim
ize
th
e
d
u
al
o
b
jectiv
e
f
u
n
ctio
n
,
wh
ich
is
clo
s
ely
l
in
k
ed
to
th
e
p
r
im
al
lo
s
s
f
u
n
ctio
n
,
an
d
d
u
e
to
th
eir
s
tr
o
n
g
d
u
ality
,
m
ax
im
izin
g
th
e
d
u
al
o
b
jectiv
e
ef
f
ec
tiv
ely
m
in
im
ize
s
th
e
p
r
im
al
lo
s
s
[
2
4
]
,
[
2
5
]
.
7
.
4
.
F
a
s
t
F
o
re
s
t
(
F
F
)
As
p
ar
t
o
f
th
e
en
s
em
b
le
lea
r
n
in
g
p
r
o
ce
s
s
,
FF
co
n
s
tr
u
cts
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
an
d
g
en
er
ates
p
r
ed
ictio
n
s
eith
er
b
y
av
er
ag
i
n
g
th
e
o
u
tc
o
m
es
f
o
r
r
e
g
r
ess
io
n
task
s
o
r
b
y
em
p
lo
y
in
g
m
ajo
r
ity
v
o
tin
g
f
o
r
class
if
icatio
n
task
s
.
T
h
is
ap
p
r
o
ac
h
aim
s
to
h
a
r
n
ess
th
e
s
tr
en
g
th
s
o
f
v
ar
i
o
u
s
d
ec
is
io
n
tr
ee
s
,
e
n
h
an
cin
g
b
o
th
ac
c
u
r
ac
y
an
d
r
esil
ien
ce
wh
ile
s
teer
in
g
clea
r
o
f
o
v
e
r
-
f
i
ttin
g
[
2
5
]
,
[
2
6
]
.
W
ith
Fas
t
Fo
r
est,
y
o
u
ca
n
p
r
ed
ict
h
o
w
m
u
ch
e
n
er
g
y
an
elec
tr
ic
ca
r
will
u
s
e,
an
aly
ze
u
s
er
b
eh
av
io
r
,
an
d
p
r
ed
ict
en
e
r
g
y
l
o
ad
n
ee
d
s
f
o
r
y
o
u
r
b
u
ild
in
g
.
8.
M
E
T
H
O
D
T
h
e
p
o
we
r
g
r
i
d
'
s
co
n
d
itio
n
is
co
n
s
tan
tly
c
h
an
g
in
g
,
with
ea
ch
m
o
m
e
n
t
s
h
o
win
g
a
d
if
f
er
e
n
t
s
tate
o
f
th
e
tr
en
d
.
C
u
r
r
en
t
m
eth
o
d
s
f
o
cu
s
o
n
ly
o
n
th
e
cu
r
r
en
t
s
tate
o
f
th
e
p
o
wer
s
y
s
tem
,
wh
ich
h
el
p
s
ex
p
lain
h
o
w
th
e
g
r
id
is
o
p
er
atin
g
.
T
h
e
o
p
tim
i
za
tio
n
m
o
d
el
e
n
h
an
ce
s
en
e
r
g
y
d
is
tr
ib
u
tio
n
ef
f
icien
cy
a
n
d
id
en
tifie
s
o
p
tim
al
ch
ar
g
in
g
tim
es
f
o
r
elec
tr
ic
v
e
h
icles.
I
n
a
f
lo
wch
ar
t
r
e
p
r
esen
ted
in
Fig
u
r
e
3
,
it
is
s
h
o
wn
th
at
tr
ain
in
g
a
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
in
v
o
l
v
es
id
en
tify
in
g
th
e
o
p
tim
al
lin
e
th
a
t
r
ed
u
ce
s
th
e
d
is
cr
ep
an
cy
b
etwe
en
p
r
ed
icted
an
d
ac
tu
al
v
alu
es,
in
o
r
d
er
to
f
ac
ilit
ate
f
u
tu
r
e
p
r
ed
ictio
n
s
.
Fig
u
r
e
3
.
Flo
wch
ar
t
f
o
r
i
n
teg
r
ated
o
p
tim
izatio
n
a
n
d
r
e
g
r
ess
io
n
m
o
d
el
Data
f
r
o
m
g
r
i
d
s
an
d
elec
tr
ic
v
eh
icles
ar
e
c
o
llected
,
i
n
clu
d
i
n
g
m
et
r
ics
s
u
ch
as
s
y
s
tem
lo
a
d
,
v
o
ltag
e,
ch
ar
g
in
g
p
er
f
o
r
m
a
n
ce
,
a
n
d
e
n
er
g
y
s
to
r
ag
e
ca
p
ac
ity
.
Data
p
r
ep
ar
atio
n
is
f
o
llo
we
d
b
y
p
r
elim
in
ar
y
m
o
d
elin
g
m
eth
o
d
s
s
u
ch
as
FF
an
d
SDC
A
th
at
im
p
r
o
v
e
p
r
e
d
ictio
n
ac
c
u
r
ac
y
.
E
Vs
ar
e
g
iv
en
an
esti
m
ate
o
f
th
e
c
h
ar
g
i
n
g
tim
e
an
d
a
p
er
ce
n
tag
e
o
f
th
e
g
r
id
’
s
ch
a
r
g
e
lo
ad
.
T
h
ese
r
esu
lts
ar
e
im
p
o
r
tan
t
in
u
n
d
e
r
s
tan
d
in
g
th
e
im
p
ac
t
o
f
E
Vs
to
th
e
g
r
id
o
v
er
tim
e,
p
a
r
ticu
lar
ly
in
ter
m
s
o
f
lo
a
d
m
an
ag
em
en
t
an
d
p
ea
k
d
em
an
d
.
T
h
e
m
o
d
el
p
r
o
v
i
d
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
3
6
-
1
0
5
0
1042
r
ea
l
-
tim
e
an
d
p
r
e
d
ictiv
e
in
s
ig
h
ts
in
to
ch
ar
g
in
g
a
n
d
g
r
i
d
s
tr
ess
,
as
well
as
m
ak
in
g
p
lan
n
in
g
,
in
f
r
astru
ctu
r
e,
a
n
d
p
o
licy
d
ec
is
io
n
s
to
m
ak
e
th
e
p
o
wer
g
r
id
m
o
r
e
ef
f
icien
t
an
d
r
esil
ien
t.
W
e
ch
o
s
e
lin
ea
r
r
eg
r
ess
io
n
,
s
to
ch
asti
c
d
u
al
co
o
r
d
in
ate
ascen
t,
an
d
FF
m
o
d
els
b
ec
au
s
e
th
ey
o
f
f
er
a
g
o
o
d
b
ase
to
test
o
u
r
id
ea
.
lin
ea
r
r
eg
r
ess
io
n
is
s
im
p
le
to
u
n
d
er
s
tan
d
a
n
d
will
h
elp
u
s
s
ee
h
o
w
m
u
c
h
b
etter
th
e
p
er
f
o
r
m
an
ce
g
ets
w
h
en
we
s
witch
to
m
o
r
e
co
m
p
lex
m
o
d
els.
SDC
A
was
ch
o
s
en
d
u
e
to
its
ex
em
p
lar
y
p
er
f
o
r
m
an
ce
in
o
p
t
im
izatio
n
an
d
h
ig
h
-
ca
p
ac
ity
tr
ain
in
g
f
o
r
d
ea
lin
g
with
th
e
lar
g
e
d
atas
ets
o
f
m
o
d
er
n
g
r
i
d
m
o
n
ito
r
in
g
.
An
ac
cu
r
ate
esti
m
atio
n
o
f
th
e
m
a
x
im
u
m
p
er
f
o
r
m
an
ce
ce
ilin
g
ac
h
iev
a
b
le
b
y
lin
ea
r
class
if
ier
s
wh
en
u
tili
zin
g
ad
v
an
ce
d
,
co
m
p
u
tatio
n
ally
ef
f
icien
t
o
p
tim
izatio
n
m
eth
o
d
s
.
T
h
e
FF
is
a
h
ig
h
p
er
f
o
r
m
in
g
en
s
em
b
le
lear
n
in
g
m
o
d
el
with
h
i
g
h
ac
cu
r
ac
y
.
B
ased
o
n
th
e
ac
cu
r
ac
y
ac
h
iev
ed
,
th
e
m
o
d
el
will
co
r
r
ec
tly
ex
p
lain
wh
y
th
e
p
er
f
o
r
m
a
n
ce
g
ain
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
u
p
er
io
r
to
t
h
e
m
o
s
t e
f
f
icien
t
m
eth
o
d
s
.
9.
RE
SU
L
T
S AN
A
L
YS
I
S B
Y
SDCA
AND
F
A
ST
F
O
R
E
ST
Usi
n
g
SDC
A
an
d
Fas
t
Fo
r
est
,
th
e
r
esu
lt
was
a
p
r
ef
er
en
ce
f
o
r
p
o
la
r
ized
ch
ar
g
in
g
b
ased
o
n
th
r
ee
-
m
o
n
th
co
n
v
en
tio
n
s
o
f
b
an
er
P
MPM
L
ch
ar
g
in
g
s
tatio
n
s
.
T
h
e
w
o
r
k
em
p
lo
y
ed
SDC
A
an
d
FF
to
b
etter
p
r
e
d
ict
ch
ar
g
in
g
tim
es
o
f
elec
tr
ic
v
e
h
icles
b
y
lo
o
k
in
g
at
en
er
g
y
u
s
e,
g
r
id
p
er
f
o
r
m
an
ce
,
an
d
p
ast
ch
ar
g
in
g
p
atter
n
s
.
C
h
ar
g
es we
r
e
m
o
r
e
e
f
f
icien
tly
s
ch
ed
u
led
an
d
p
ea
k
lo
ad
im
p
ac
t w
as d
ec
r
ea
s
ed
.
9
.
1
.
St
o
cha
s
t
ic
du
a
l c
o
o
rdina
t
e
a
s
ce
nt
ma
chine le
a
rning
m
o
del
I
t
ad
d
r
ess
es
th
is
d
ilem
m
a
b
y
f
o
cu
s
in
g
o
n
th
e
p
r
o
b
lem
its
elf
.
As
we
s
h
o
w
in
[
1
2
]
,
SDC
A
h
as
a
b
etter
lin
ea
r
co
n
v
e
r
g
en
ce
r
ate
f
o
r
s
m
o
o
th
lo
s
s
f
u
n
ctio
n
s
th
an
S
GD.
I
n
ad
d
itio
n
,
SDC
A
is
b
etter
th
an
SGD
f
o
r
n
o
n
s
m
o
o
t
h
lo
s
s
f
u
n
ctio
n
s
s
u
ch
as
SVMs.
W
e
n
o
w
co
n
s
id
e
r
th
e
lo
n
g
-
ter
m
ef
f
ec
ts
o
f
SDC
A
o
n
co
n
tin
u
o
u
s
lo
s
s
f
u
n
ctio
n
s
d
esp
ite
t
h
e
ch
a
llen
g
es
o
f
d
ata
d
is
tr
ib
u
tio
n
.
S
DC
A
is
s
u
p
er
io
r
to
SGD
at
t
r
ain
in
g
a
m
o
d
el
o
f
co
n
tin
u
o
u
s
lo
s
s
es [
1
1
]
.
T
h
e
SDC
A
m
o
d
el
is
tr
ain
ed
to
p
r
ed
ict
p
ea
k
c
h
ar
g
in
g
tim
es
f
o
r
elec
tr
ic
b
u
s
es
at
B
an
e
r
ch
ar
g
in
g
d
ep
o
t.
T
h
e
q
u
ic
k
an
d
ef
f
icien
t
p
r
o
ce
s
s
in
g
o
f
la
r
g
e
d
atasets
f
r
o
m
b
an
er
c
h
ar
g
in
g
s
tatio
n
s
is
u
s
ed
f
o
r
en
e
r
g
y
g
r
id
s
en
h
an
ce
m
e
n
t,
en
er
g
y
d
i
s
tr
ib
u
tio
n
,
r
ed
u
cti
o
n
o
f
c
o
s
ts
,
an
d
g
r
id
p
er
f
o
r
m
an
ce
b
o
o
s
tin
g
.
SDC
A
alg
o
r
ith
m
was
ex
p
lo
ited
to
o
p
tim
ize
ch
ar
g
in
g
tim
e
esti
m
atio
n
.
T
h
e
g
r
ap
h
s
h
o
wn
in
F
ig
u
r
e
4
r
e
p
r
esen
ts
ch
ar
g
er
v
s
p
r
ed
icted
ch
ar
g
in
g
c
o
m
p
l
etio
n
tim
e.
T
h
is
ev
alu
atio
n
is
co
n
d
u
cted
o
n
B
an
er
(
Pu
n
e)
ch
a
r
g
in
g
s
tatio
n
d
ataset’
s
a
p
ar
ticu
lar
.
Fig
u
r
e
4
.
C
h
ar
g
in
g
tim
e
o
p
tim
izatio
n
p
er
ch
a
r
g
er
f
r
o
m
SDC
A
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
S
u
s
ta
in
a
b
le
e
-
mo
b
ilit
y
w
ith
co
n
tr
o
lled
ch
a
r
g
in
g
s
ch
eme
b
a
s
ed
o
n
g
r
id
en
erg
y
u
s
in
g
…
(
A
r
ch
a
n
a
K
a
d
a
m)
1043
T
ab
le
2
(
s
ee
Ap
p
en
d
ix
)
r
e
p
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
an
aly
s
is
o
f
th
e
SDC
A
m
o
d
el,
in
wh
ich
th
e
ex
p
er
im
en
ted
v
alu
es
o
f
R
-
s
q
u
ar
ed
,
MSE
,
MA
E
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
a
r
e
p
r
e
s
en
ted
.
T
h
e
m
o
d
e
l
d
eliv
er
s
en
h
an
ce
d
p
r
ed
ictiv
e
ac
cu
r
ac
y
in
co
m
p
a
r
is
o
n
to
lin
ea
r
m
o
d
els.
T
h
is
im
p
r
o
v
em
en
t
is
o
b
s
er
v
ed
wh
en
th
e
m
o
d
el
is
ap
p
lied
to
r
ea
l
-
w
o
r
ld
d
ata.
9
.
2
.
F
a
s
t
F
o
re
s
t
m
a
chine le
a
rning
m
o
del
T
h
e
FF
alg
o
r
ith
m
also
tack
les
th
e
o
p
tim
izatio
n
ch
allen
g
e
b
y
co
n
ce
n
tr
atin
g
o
n
ti
m
e
s
er
ies
f
o
r
ec
asti
n
g
.
T
h
e
FF
m
o
d
el,
a
n
en
s
em
b
le
r
eg
r
ess
io
n
tech
n
i
q
u
e
b
ased
o
n
g
r
a
d
ien
t
-
b
o
o
s
ted
d
ec
is
io
n
tr
ee
s
,
is
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
m
an
ag
in
g
n
o
n
-
lin
ea
r
an
d
in
tr
icat
e
d
atasets
,
r
en
d
er
in
g
it
s
u
itab
le
f
o
r
p
r
ed
ictin
g
elec
tr
ic
v
eh
icle
ch
ar
g
in
g
d
u
r
at
io
n
[
1
4
]
,
[
1
6
]
,
[
2
5
]
.
Fig
u
r
e
5
s
h
o
ws
th
e
ch
ar
g
in
g
tim
e
o
p
tim
izatio
n
p
er
c
h
ar
g
e
r
f
o
r
th
e
FF
m
o
d
el
o
v
e
r
th
e
s
am
e
ch
ar
g
in
g
s
tatio
n
d
ataset.
T
ab
le
3
(
s
ee
Ap
p
en
d
ix
)
r
ep
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
an
aly
s
is
o
f
th
e
FF
m
etr
ic.
T
h
e
ca
lcu
lat
ed
v
alu
es
in
clu
d
e
R
-
s
q
u
ar
ed
,
MSE
,
MA
E
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
.
T
h
ese
m
etr
ics
wer
e
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
FF
m
o
d
el.
Fig
u
r
e
5
.
C
h
ar
g
in
g
tim
e
o
p
tim
izatio
n
p
er
ch
a
r
g
er
f
o
r
FF
m
o
d
el
10.
CO
M
P
ARI
SO
N
O
F
P
RICI
NG
M
O
DE
L
AND
CH
ARG
I
NG
T
I
M
E
E
S
T
I
M
A
T
I
O
N
T
o
im
p
r
o
v
e
s
ch
ed
u
le
d
c
h
ar
g
in
g
,
th
is
w
o
r
k
tak
es
in
to
ac
c
o
u
n
t
t
h
e
c
o
m
p
ar
ativ
e
co
s
t
b
en
ef
its
b
y
an
aly
zin
g
th
e
en
e
r
g
y
p
er
f
o
r
m
an
ce
o
f
th
e
en
e
r
g
y
g
r
id
.
I
t
als
o
im
p
lem
en
ts
th
e
SDC
A
an
d
FF
alg
o
r
ith
m
s
f
o
r
an
elec
tr
ic
b
u
s
ch
ar
g
in
g
s
tatio
n
.
T
h
ese
alg
o
r
ith
m
s
ar
e
u
s
ed
f
o
r
b
atter
y
ch
ar
g
in
g
tim
e
f
o
r
ec
asti
n
g
[
2
6
]
,
[
2
7
]
.
Fig
u
r
e
6
illu
s
tr
ates
th
e
co
m
p
a
r
ativ
e
r
esu
lts
o
f
f
lat
r
ate
tar
if
f
o
p
tim
izatio
n
p
er
c
h
ar
g
e
r
o
v
e
r
tim
e
f
o
r
th
e
SDC
A
an
d
FF
m
o
d
els,
d
em
o
n
s
tr
atin
g
th
at
th
e
FF
a
lg
o
r
ith
m
y
ield
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
,
th
er
e
b
y
estab
lis
h
in
g
it
as
a
m
o
r
e
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
.
I
f
m
o
d
el
ac
cu
r
ately
p
r
ed
icts
th
e
to
tal
en
er
g
y
r
eq
u
ir
e
d
(
P̂
r
eq
)
an
d
wh
en
it
will
b
e
co
n
s
u
m
ed
,
it
ca
n
s
elec
t
th
e
m
o
s
t
f
av
o
r
a
b
le
tar
if
f
.
Hig
h
ac
cu
r
ac
y
e
n
s
u
r
es
y
o
u
d
o
n
'
t
o
v
er
-
co
m
m
it
to
ex
p
e
n
s
iv
e
tar
if
f
s
o
r
u
n
d
er
-
u
tili
ze
c
h
ea
p
o
n
es.
T
h
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
els’
p
r
ed
i
ctio
n
s
h
as
r
esu
lted
in
a
h
ig
h
lev
el
o
f
ec
o
n
o
m
ic
b
en
ef
it,
wh
ich
h
as
b
ee
n
e
x
p
lo
ited
b
y
o
u
r
o
p
tim
izatio
n
en
g
in
e.
E
s
p
ec
ially
im
p
r
ess
iv
e
was
th
e
h
ig
h
R
2
v
alu
es
an
d
lo
w
e
r
r
o
r
m
etr
ics
(
MA
E
/R
MSE
)
in
T
ab
les
3
an
d
4
,
wh
ich
p
r
o
v
ed
to
b
e
cr
u
cial
in
th
e
o
p
er
ati
o
n
o
f
th
e
PMPML
ch
ar
g
in
g
s
tatio
n
.
T
h
e
h
ig
h
ac
c
u
r
ac
y
o
f
th
e
m
o
d
els’
p
r
e
d
ictio
n
s
ab
o
u
t
th
e
tim
in
g
o
f
th
e
c
h
ar
g
e
s
ig
n
if
ican
tly
r
ed
u
ce
s
th
e
tar
if
f
as
ch
ar
g
in
g
s
ess
io
n
s
ar
e
cu
t
f
r
o
m
p
ea
k
T
im
e
-
of
-
Use
(
T
o
U)
p
e
r
io
d
s
to
ch
ea
p
er
o
f
f
-
p
ea
k
o
n
es,
r
esu
ltin
g
in
th
e
s
u
b
s
tan
tial
r
ed
u
cti
o
n
i
n
co
s
t
o
f
ch
ar
g
in
g
s
h
o
wn
in
th
e
ch
ar
g
in
g
c
o
s
t c
o
m
p
ar
is
o
n
g
r
ap
h
.
T
ab
le
4
c
o
m
p
ar
es
t
h
e
er
r
o
r
m
etr
ics,
in
clu
d
in
g
R
-
s
q
u
ar
ed
,
MSE
,
MA
E
,
an
d
R
MSE
,
f
o
r
th
e
tw
o
alg
o
r
ith
m
s
.
A
v
alu
e
b
etwe
en
0
.
6
an
d
0
.
8
in
d
icate
s
a
g
o
o
d
m
o
d
el
f
it.
A
v
alu
e
n
ea
r
1
.
0
in
d
icate
s
an
id
ea
l
f
it,
m
ea
n
in
g
th
at
t
h
e
m
o
d
el
ca
p
tu
r
es th
e
v
ar
iab
ilit
y
o
f
t
h
e
r
esp
o
n
s
e
v
ar
iab
le
ar
o
u
n
d
its
m
ea
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
0
3
6
-
1
0
5
0
1044
Fig
u
r
e
6
.
C
o
m
p
a
r
is
o
n
o
f
tar
if
f
f
o
r
SDC
A
an
d
FF
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
e
v
alu
ati
o
n
m
atr
ix
u
s
in
g
SDC
A
an
d
FF
P
a
r
a
me
t
e
r
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
D
C
4
D
C
4
D
C
5
D
C
5
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
1
0
2
6
1
0
2
6
9
0
9
9
0
9
R
-
sq
u
a
r
e
d
0
.
6
7
5
6
0
.
6
7
7
8
0
.
7
0
4
1
0
.
6
9
4
9
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
5
3
4
.
1
8
5
3
0
.
5
5
5
4
.
0
5
5
7
1
.
1
9
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
6
.
2
1
1
4
.
6
1
4
.
3
1
4
.
8
3
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
3
.
1
1
2
3
.
0
3
2
3
.
5
4
2
3
.
9
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
23
23
26
26
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
2
4
7
2
4
7
2
5
8
2
5
8
R
-
sq
u
a
r
e
d
0
.
7
5
5
2
0
.
7
3
9
7
0
.
5
3
6
7
0
.
6
5
0
8
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
5
3
6
.
2
9
5
7
0
.
2
1
2
2
2
.
8
9
2
1
.
5
2
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
7
.
8
7
1
8
.
2
7
2
6
.
1
5
2
2
.
2
3
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
3
.
1
6
2
3
.
8
8
3
4
.
9
7
3
0
.
3
6
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
22
22
18
18
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
2
2
9
2
2
9
2
1
1
2
1
1
R
-
sq
u
a
r
e
d
0
.
6
4
8
4
0
.
6
8
0
8
0
.
7
3
7
2
0
.
7
2
2
9
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
7
6
2
.
4
3
6
9
2
.
1
7
8
9
4
.
4
8
9
4
3
.
0
1
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
6
.
6
6
1
5
.
6
7
2
2
.
2
3
2
3
.
9
4
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
7
.
6
1
2
6
.
3
1
2
9
.
9
1
3
0
.
7
1
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
27
27
25
25
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
2
5
9
2
5
9
2
6
9
2
6
9
R
-
sq
u
a
r
e
d
0
.
7
1
7
6
0
.
7
2
0
3
0
.
5
9
7
8
0
.
6
3
4
8
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
8
4
2
.
9
6
8
3
4
.
7
1
1
6
6
.
5
1
1
0
5
8
.
9
6
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
5
.
7
3
1
7
.
0
2
2
2
.
8
4
2
0
.
7
8
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
9
.
0
3
2
8
.
8
9
3
4
.
1
5
3
2
.
5
4
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
21
21
7
7
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
2
3
4
2
3
4
1
3
7
1
3
7
R
-
sq
u
a
r
e
d
0
.
7
9
2
6
0
.
7
7
4
2
0
.
7
9
8
9
0
.
7
9
4
1
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
6
5
8
.
5
4
7
1
7
.
1
4
7
6
.
7
6
4
8
8
.
1
5
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
7
.
1
4
1
7
.
2
8
1
6
.
2
8
1
7
.
4
4
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
5
.
6
6
2
6
.
7
8
2
1
.
8
3
2
2
.
0
9
S
D
C
A
F
a
st
F
o
r
e
s
t
S
D
C
A
F
a
st
F
o
r
e
s
t
C
h
a
r
g
e
r
n
a
me
:
13
13
12
12
M
o
d
e
l
e
v
a
l
u
a
t
i
o
n
d
a
t
a
s
i
z
e
2
0
6
2
0
6
1
8
6
1
8
6
R
-
sq
u
a
r
e
d
0
.
8
5
4
9
0
.
8
4
8
3
0
.
7
7
3
9
0
.
7
3
7
2
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
4
2
9
.
0
3
4
4
8
.
7
8
6
8
9
.
3
8
8
0
1
.
3
6
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
1
5
.
4
9
1
5
.
6
4
1
8
.
5
9
2
0
.
1
2
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
2
0
.
7
1
2
1
.
1
8
2
6
.
2
6
2
8
.
3
1
11.
CO
NCLU
SI
O
N
Ma
ch
in
e
lear
n
i
n
g
’
s
p
r
ed
icti
v
e
ab
ilit
ies
also
h
elp
e
d
i
m
p
r
o
v
e
E
V
c
h
ar
g
i
n
g
s
tati
o
n
e
n
er
g
y
m
an
ag
em
en
t.
T
h
e
two
m
ain
p
r
ed
ictio
n
alg
o
r
ith
m
s
test
ed
,
SDC
A
an
d
FF
,
p
er
f
o
r
m
ed
well
wh
en
d
ea
lin
g
with
r
ea
l
-
wo
r
ld
d
ata.
B
o
th
m
o
d
els
p
r
o
d
u
ce
d
R
2
v
alu
es
o
f
o
v
er
0
.
7
0
o
n
ch
ar
g
er
s
th
at
ar
e
h
i
g
h
ly
u
tili
ze
d
.
T
h
is
p
er
f
o
r
m
an
ce
in
d
icate
s
th
at
th
e
m
o
d
el
ca
n
p
r
ed
ict
m
o
r
e
ac
cu
r
ately
in
s
ce
n
ar
io
s
with
h
ig
h
u
s
ag
e.
On
all
test
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
S
u
s
ta
in
a
b
le
e
-
mo
b
ilit
y
w
ith
co
n
tr
o
lled
ch
a
r
g
in
g
s
ch
eme
b
a
s
ed
o
n
g
r
id
en
erg
y
u
s
in
g
…
(
A
r
ch
a
n
a
K
a
d
a
m)
1045
ch
ar
g
er
s
,
th
e
Fas
t
Fo
r
est
alg
o
r
ith
m
p
e
r
f
o
r
m
ed
s
lig
h
tly
b
e
tter
in
r
ed
u
cin
g
er
r
o
r
s
.
I
t
d
e
cr
ea
s
ed
th
e
m
ed
ia
n
R
MSE
b
y
ab
o
u
t
3
%
to
SDC
A,
p
r
o
v
id
i
n
g
a
n
a
r
r
o
wer
er
r
o
r
m
ar
g
in
f
o
r
p
ea
k
s
h
av
in
g
.
T
h
e
h
ig
h
ac
c
u
r
ac
y
o
f
th
ese
m
o
d
els
in
f
o
r
ec
asti
n
g
ch
ar
g
in
g
d
u
r
atio
n
s
h
elp
ed
p
lan
a
cc
o
r
d
in
g
l
y
to
s
h
if
t
f
r
o
m
ex
p
e
n
s
iv
e
T
im
e
-
of
-
Use
(
T
o
U
)
p
ea
k
tim
es
to
ch
ea
p
er
o
f
f
-
p
ea
k
tim
es,
ac
h
iev
in
g
b
o
t
h
co
s
t
an
d
lo
ad
eq
u
aliza
tio
n
.
T
h
e
co
m
b
in
atio
n
o
f
th
ese
s
ch
ed
u
lin
g
alg
o
r
ith
m
s
with
lin
ea
r
r
eg
r
ess
io
n
g
r
ea
tly
im
p
r
o
v
es
en
er
g
y
p
er
f
o
r
m
a
n
ce
an
aly
s
is
o
f
E
V
g
r
id
s
.
B
ec
au
s
e
r
eg
r
ess
io
n
m
o
d
els
ar
e
ab
le
to
p
r
e
v
en
t
u
n
p
r
ed
ictab
le
s
p
ik
es
in
lo
ad
,
g
r
id
s
tab
ilit
y
ca
n
b
e
m
ain
tain
ed
d
esp
ite
th
e
d
y
n
a
m
is
m
cr
ea
ted
b
y
E
V
i
n
teg
r
atio
n
.
T
h
e
cu
r
r
en
t
m
o
d
el
r
elies
s
o
lely
o
n
ch
ar
g
i
n
g
s
tatio
n
d
ata.
I
t
d
o
es
n
o
t
f
ac
to
r
in
an
y
ex
te
r
n
al
f
ac
to
r
s
th
at
co
u
ld
af
f
ec
t a
v
ailab
ilit
y
o
f
v
eh
icles su
ch
as r
ea
l
-
tim
e
d
e
lay
s
in
p
u
b
lic
tr
an
s
it o
r
m
icr
o
-
wea
th
er
ev
en
ts
at
a
lo
ca
l
lev
el.
I
t
also
r
elies
ex
clu
s
iv
ely
o
n
DC
f
ast
ch
ar
g
in
g
,
b
u
t
p
er
f
o
r
m
an
ce
m
ay
v
a
r
y
to
A
C
L
ev
el
2
ch
ar
g
in
g
n
etwo
r
k
s
with
d
if
f
e
r
en
t u
s
es.
Fu
tu
r
e
wo
r
k
will
f
o
c
u
s
o
n
cr
e
atin
g
a
m
u
lti
-
ch
ar
g
er
ag
g
r
eg
at
io
n
s
y
s
tem
(
MCAS)
to
b
etter
co
o
r
d
in
at
e
h
o
w
elec
tr
icity
u
s
e
is
m
a
n
ag
e
d
at
s
ev
e
r
al
PMPML
ch
a
r
g
in
g
s
tatio
n
s
ac
r
o
s
s
d
if
f
er
en
t
r
eg
i
o
n
s
.
T
o
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
c
h
ar
g
i
n
g
d
em
a
n
d
p
r
ed
ictio
n
,
ex
ter
n
al
d
ata
s
o
u
r
ce
s
will
b
e
in
teg
r
ated
.
T
h
ese
s
o
u
r
ce
s
in
clu
d
e
tr
af
f
ic
in
f
o
r
m
atio
n
a
n
d
m
icr
o
-
wea
th
er
d
ata
to
m
a
k
e
th
e
s
ch
e
d
u
lin
g
e
n
g
in
e
m
o
r
e
r
o
b
u
s
t.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
ar
e
v
er
y
g
r
atef
u
l
to
MI
T
ADT
Un
iv
e
r
s
ity
f
o
r
th
e
r
esear
ch
f
ac
ilit
ies,
f
ac
ilit
ies,
an
d
s
u
p
p
o
r
t
th
at
m
ad
e
th
is
s
tu
d
y
p
o
s
s
ib
le.
W
e
th
an
k
o
u
r
ac
ad
em
ic
ad
v
is
o
r
s
an
d
r
esear
ch
co
llab
o
r
ato
r
s
f
o
r
th
ei
r
g
u
id
an
ce
an
d
in
s
ig
h
tf
u
l
co
m
m
en
ts
,
alo
n
g
with
th
e
tech
n
ic
al
f
ee
d
b
ac
k
th
at
m
ad
e
th
is
p
r
o
ject
s
u
cc
ess
f
u
l.
T
h
e
wo
r
k
o
n
ca
lcu
latin
g
th
e
c
h
a
r
g
in
g
tim
es
o
f
elec
tr
ic
v
eh
ic
les
with
in
th
e
e
n
er
g
y
p
er
f
o
r
m
an
ce
an
al
y
s
is
o
f
elec
tr
icity
g
r
id
h
as
b
ee
n
s
ig
n
if
ican
tly
ass
is
ted
b
y
a
s
tim
u
latin
g
an
d
in
tellectu
ally
s
tim
u
latin
g
en
v
ir
o
n
m
en
t.
W
e
th
an
k
th
e
PMPML
B
an
e
r
C
h
ar
g
in
g
Statio
n
f
o
r
p
r
o
v
i
d
in
g
th
e
d
ata
in
th
is
r
esear
c
h
s
tu
d
y
.
T
h
is
d
ata
ass
is
ted
u
s
in
d
ev
elo
p
i
n
g
a
n
d
v
alid
atin
g
o
u
r
m
o
d
els,
im
p
r
o
v
in
g
th
e
u
s
ef
u
ln
ess
o
f
th
e
f
i
n
d
i
n
g
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
Ar
ch
an
a
Kad
am
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
am
esh
Ma
li
✓
✓
✓
✓
✓
✓
✓
✓
R
ee
n
a
Gu
n
jan
✓
✓
✓
✓
✓
✓
Vir
en
d
r
a
Sh
ete
✓
✓
✓
✓
✓
✓
Pra
d
ee
p
Ma
n
e
✓
✓
✓
✓
✓
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
No
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
et
u
tili
ze
d
f
o
r
r
esear
ch
is
s
o
u
r
ce
d
f
r
o
m
th
e
PM
PML
B
an
er
E
lectr
ic
B
u
s
Dep
o
t
in
Pu
n
e,
I
n
d
ia.
T
h
e
d
ata
c
o
llected
f
o
r
th
is
s
tu
d
y
en
co
m
p
ass
ed
a
s
ix
-
m
o
n
th
p
er
io
d
f
r
o
m
Ma
y
1
,
2
0
2
3
to
Octo
b
er
3
1
,
2
0
2
3
.
T
h
is
d
ata
s
et
co
m
p
r
is
ed
ap
p
r
o
x
im
ately
3
,
7
0
0
u
n
iq
u
e
ch
ar
g
in
g
e
v
en
ts
co
llected
f
r
o
m
DC
f
ast
ch
ar
g
er
s
an
d
AC
c
h
ar
g
er
s
.
T
h
e
in
p
u
t
f
ea
tu
r
es
u
s
ed
f
o
r
m
o
d
elin
g
in
c
lu
d
ed
:
c
h
a
r
g
er
I
D,
d
ay
o
f
wee
k
,
tim
e
o
f
d
ay
,
th
e
in
itial
s
tate
o
f
ch
ar
g
e
%S
O
C
,
th
e
f
in
al
%S
OC
.
T
h
e
tar
g
et
v
ar
iab
le
f
o
r
p
r
e
d
ictio
n
was
th
e
ch
ar
g
in
g
d
u
r
atio
n
in
Evaluation Warning : The document was created with Spire.PDF for Python.