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
6
,
No
.
4
,
Dec
em
b
er
2
0
2
5
,
p
p
.
2
4
0
0
~
2
4
1
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
6
.
i
4
.
p
p
2
4
0
0
-
2
4
1
0
2400
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
p
e
d
s
.
ia
esco
r
e.
co
m
M
a
chine learning
-
ba
sed ene
rg
y
ma
na
g
ement sys
tem
for elec
tric
v
ehicles wit
h BL
DC mo
tor in
tegra
tion
K
.
S.
R.
Va
ra
P
r
a
s
a
d,
V.
Ush
a
Reddy
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
En
g
i
n
e
e
r
i
n
g
,
S.
V.
U
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Ti
r
u
p
a
t
i
,
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
Ma
y
1
6
,
2
0
2
5
R
ev
is
ed
J
u
l 2
8
,
2
0
2
5
Acc
ep
ted
Sep
2
,
2
0
2
5
Th
is
p
a
p
e
r
p
r
o
p
o
se
s
a
m
a
c
h
in
e
l
e
a
rn
in
g
-
b
a
se
d
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
sy
ste
m
fo
r
e
lec
tri
c
v
e
h
ic
les
with
BL
DC
m
o
to
r
in
te
g
ra
ti
o
n
.
Eff
icie
n
t
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
is
e
ss
e
n
ti
a
l
fo
r
i
m
p
ro
v
i
n
g
t
h
e
p
e
rfo
rm
a
n
c
e
,
ra
n
g
e
,
a
n
d
re
li
a
b
il
it
y
o
f
e
lec
tri
c
v
e
h
icle
s
(EVs),
p
a
rti
c
u
larly
t
h
o
se
p
o
we
re
d
b
y
b
ru
s
h
les
s
DC
(BLDC)
m
o
to
rs.
Trad
it
i
o
n
a
l
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
(EM
S
),
su
c
h
a
s
ru
le
-
b
a
se
d
a
n
d
f
u
z
z
y
l
o
g
ic
c
o
n
tro
ll
e
rs,
o
ften
lac
k
t
h
e
a
d
a
p
tab
il
i
t
y
re
q
u
ired
fo
r
d
y
n
a
m
ic
d
riv
i
n
g
c
o
n
d
i
ti
o
n
s
a
n
d
o
p
ti
m
a
l
e
n
e
rg
y
d
istri
b
u
ti
o
n
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
m
a
c
h
in
e
lea
rn
in
g
(M
L)
-
b
a
se
d
EM
S
fra
m
e
wo
rk
tailo
r
e
d
fo
r
EV
s
e
q
u
ip
p
e
d
with
BLDC
m
o
to
rs,
a
i
m
in
g
to
e
n
h
a
n
c
e
s
y
ste
m
r
e
sp
o
n
si
v
e
n
e
ss
a
n
d
e
n
e
rg
y
e
fficie
n
c
y
.
M
L
a
lg
o
rit
h
m
s
,
in
c
lu
d
in
g
d
e
c
isio
n
tree
s
,
r
a
n
d
o
m
fo
re
sts
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
(
S
VM
s
),
a
n
d
XG
Bo
o
st
,
a
re
train
e
d
o
n
d
i
v
e
rse
d
a
tas
e
ts
th
a
t
re
flec
t
v
a
ry
in
g
lo
a
d
d
e
m
a
n
d
s,
d
ri
v
i
n
g
c
y
c
les
,
a
n
d
b
a
tt
e
ry
sta
te
-
of
-
c
h
a
rg
e
(
S
OC)
lev
e
ls.
T
h
e
p
r
o
p
o
se
d
E
M
S
is
m
o
d
e
led
a
n
d
v
a
li
d
a
ted
i
n
P
y
th
o
n
p
ro
g
ra
m
m
in
g
to
sim
u
late
re
a
li
stic
EV
o
p
e
ra
ti
n
g
sc
e
n
a
rio
s
.
S
imu
latio
n
re
su
lt
s
i
n
d
ica
te
t
h
a
t
t
h
e
M
L
-
b
a
se
d
E
M
S
o
u
tp
e
rfo
rm
s
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
s
b
y
a
c
h
ie
v
in
g
u
p
to
1
5
%
e
n
e
rg
y
sa
v
in
g
s,
re
d
u
c
i
n
g
b
a
tt
e
ry
stre
ss
,
a
n
d
m
a
in
tain
in
g
sm
o
o
th
e
r
S
OC
tra
n
siti
o
n
s.
Th
e
s
e
fin
d
in
g
s
h
ig
h
li
g
h
t
t
h
e
p
o
ten
ti
a
l
o
f
M
L
-
d
riv
e
n
stra
teg
ies
fo
r
c
re
a
ti
n
g
a
d
a
p
ti
v
e
,
in
telli
g
e
n
t
E
M
S
so
lu
ti
o
n
s
in
n
e
x
t
-
g
e
n
e
ra
ti
o
n
BLDC
m
o
t
o
r
-
b
a
se
d
E
Vs
.
K
ey
w
o
r
d
s
:
B
atter
y
m
an
ag
em
en
t
E
lectr
ic
v
eh
icles
E
n
er
g
y
ef
f
icien
cy
E
n
er
g
y
m
an
ag
e
m
en
t sy
s
tem
Ma
ch
in
e
lear
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
:
K.
S.
R
.
Var
a
Pra
s
ad
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
S.
V.
U.
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
T
ir
u
p
ati,
An
d
h
r
a
Pra
d
esh
,
I
n
d
i
a
E
m
ail:
k
s
r
v
ar
am
2
2
0
@
y
ah
o
o
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
ic
v
eh
icles
(
E
Vs)
r
ep
r
esen
t
a
p
iv
o
tal
s
h
if
t
to
war
d
clea
n
er
an
d
m
o
r
e
s
u
s
tain
ab
le
tr
an
s
p
o
r
tatio
n
s
o
lu
tio
n
s
,
d
r
iv
en
b
y
t
h
e
g
lo
b
a
l
im
p
er
ativ
e
to
r
e
d
u
ce
ca
r
b
o
n
em
is
s
io
n
s
,
f
o
s
s
il
f
u
el
d
ep
en
d
e
n
cy
,
an
d
u
r
b
an
air
p
o
llu
tio
n
[
1
]
,
[
2
]
.
Desp
ite
s
ig
n
if
ican
t
ad
v
a
n
ce
m
en
ts
in
b
att
er
y
tech
n
o
lo
g
y
an
d
p
o
wer
el
ec
tr
o
n
ics,
E
Vs
s
till
f
ac
e
k
ey
c
h
allen
g
es
s
u
ch
as
lim
ited
d
r
iv
in
g
r
an
g
e,
p
r
o
l
o
n
g
ed
ch
ar
g
i
n
g
tim
es,
an
d
r
ed
u
ce
d
o
p
er
atio
n
al
ef
f
icien
cy
u
n
d
er
d
y
n
am
ic
co
n
d
itio
n
s
.
T
h
ese
lim
itatio
n
s
u
n
d
er
s
co
r
e
t
h
e
u
r
g
en
t
n
ee
d
f
o
r
in
tellig
en
t
en
er
g
y
m
an
ag
em
en
t
s
tr
ateg
ies
th
at
ca
n
o
p
tim
ize
th
e
u
s
e
o
f
o
n
b
o
ar
d
en
er
g
y
r
eso
u
r
ce
s.
A
t
th
e
co
r
e
o
f
th
is
o
p
tim
izatio
n
lies
th
e
en
er
g
y
m
an
ag
em
en
t
s
y
s
tem
(
E
MS)
,
wh
ich
is
r
esp
o
n
s
ib
le
f
o
r
r
ea
l
-
tim
e
d
ec
is
io
n
-
m
ak
in
g
r
eg
ar
d
in
g
en
er
g
y
allo
ca
tio
n
,
b
atter
y
u
s
ag
e,
an
d
p
o
wer
tr
ain
c
o
n
tr
o
l.
A
well
-
d
esig
n
ed
E
MS
en
s
u
r
es
th
at
en
er
g
y
s
to
r
ed
in
th
e
b
atter
y
is
d
is
tr
ib
u
ted
e
f
f
icien
tly
am
o
n
g
v
a
r
io
u
s
co
m
p
o
n
en
ts
,
s
u
c
h
as
t
h
e
tr
ac
tio
n
m
o
to
r
,
r
eg
en
er
ativ
e
b
r
a
k
in
g
s
y
s
tem
,
an
d
au
x
iliar
y
l
o
ad
s
,
wh
ile
al
s
o
ex
ten
d
in
g
b
atter
y
life
an
d
en
h
an
ci
n
g
v
eh
icle
r
eliab
ilit
y
[
3
]
,
[
4
]
.
His
to
r
ically
,
E
MS
s
tr
ateg
ie
s
h
av
e
r
elied
o
n
r
u
le
-
b
ased
o
r
h
e
u
r
is
tic
alg
o
r
ith
m
s
d
u
e
to
th
eir
s
im
p
licity
an
d
ea
s
e
o
f
im
p
lem
en
tatio
n
.
Ho
wev
er
,
th
ese
m
eth
o
d
s
o
f
ten
lack
ad
a
p
tab
ilit
y
a
n
d
f
ail
to
r
es
p
o
n
d
ef
f
ec
ti
v
ely
t
o
th
e
n
o
n
lin
ea
r
an
d
d
y
n
am
ic
n
atu
r
e
o
f
m
o
d
er
n
E
V
o
p
er
a
tio
n
s
,
esp
ec
ially
in
h
y
b
r
id
a
n
d
p
lu
g
-
in
h
y
b
r
id
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
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
e
n
erg
y
ma
n
a
g
eme
n
t sys
tem
fo
r
elec
tr
ic
ve
h
icles w
ith
…
(
K
.
S
.
R
.
V
a
r
a
P
r
a
s
a
d
)
2401
co
n
f
ig
u
r
atio
n
s
(
HE
Vs
an
d
PHEV
s
)
[
5
]
-
[
7
]
.
I
n
r
ec
en
t
y
ea
r
s
,
m
ac
h
in
e
l
ea
r
n
in
g
(
ML
)
a
n
d
ar
tific
ial
in
tellig
en
ce
(
AI
)
tech
n
iq
u
es
h
av
e
em
er
g
ed
as
r
o
b
u
s
t
alter
n
ativ
es
f
o
r
d
ev
elo
p
in
g
d
ata
-
d
r
iv
en
,
a
d
ap
tiv
e
E
MS
s
o
lu
tio
n
s
.
B
y
lev
er
ag
in
g
h
is
to
r
ical
an
d
r
ea
l
-
tim
e
d
ata,
ML
m
o
d
els
ca
n
p
r
ed
ict
d
r
iv
in
g
b
eh
a
v
io
r
,
b
att
er
y
s
tate
o
f
ch
ar
g
e
(
So
C
)
,
en
er
g
y
d
em
an
d
,
a
n
d
s
y
s
tem
h
ea
lth
,
th
er
eb
y
f
ac
ilit
atin
g
m
o
r
e
ac
cu
r
ate
an
d
r
esp
o
n
s
iv
e
co
n
tr
o
l
s
tr
ateg
ies
[
8
]
.
Su
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
s
u
ch
as
XGBo
o
s
t
[
4
]
,
r
an
d
o
m
f
o
r
est
[
9
]
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
h
av
e
d
em
o
n
s
tr
ated
s
tr
o
n
g
p
er
f
o
r
m
a
n
c
e
in
en
er
g
y
u
s
ag
e
class
if
icatio
n
an
d
an
o
m
al
y
d
etec
tio
n
u
n
d
er
u
n
ce
r
tain
e
n
v
i
r
o
n
m
en
ts
.
Fu
r
th
er
ad
v
a
n
ce
m
en
ts
h
av
e
b
ee
n
ac
h
iev
e
d
th
r
o
u
g
h
d
ee
p
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
(
DR
L
)
,
wh
ich
en
ab
les
E
MS
f
r
am
ewo
r
k
s
to
l
ea
r
n
o
p
tim
al
co
n
tr
o
l p
o
licies b
y
in
ter
ac
tin
g
with
th
e
d
r
i
v
in
g
en
v
ir
o
n
m
en
t.
DR
L
-
b
ased
E
MS
ap
p
r
o
ac
h
es
ca
n
s
im
u
ltan
eo
u
s
ly
b
alan
ce
m
u
ltip
l
e
o
b
jectiv
es
,
s
u
ch
as
en
er
g
y
e
f
f
icien
cy
,
e
m
is
s
io
n
s
r
ed
u
ctio
n
,
a
n
d
u
s
er
co
m
f
o
r
t
,
with
o
u
t
r
eq
u
ir
in
g
ex
p
li
cit
s
y
s
tem
m
o
d
els
[
1
0
]
,
[
1
1
]
.
T
e
ch
n
iq
u
es
lik
e
twin
d
elay
ed
d
ee
p
d
eter
m
i
n
is
tic
p
o
licy
g
r
ad
ien
t
(
T
D3
)
[
1
2
]
,
Q
-
lear
n
in
g
,
an
d
ac
t
o
r
-
cr
itic
m
e
th
o
d
s
h
a
v
e
s
h
o
wn
p
o
ten
tial
in
r
ea
l
-
tim
e
p
o
wer
tr
ain
co
n
tr
o
l
an
d
r
o
u
te
-
awa
r
e
e
n
er
g
y
m
an
a
g
em
en
t
[
1
3
]
,
[
1
4
]
.
A
g
r
o
win
g
t
r
en
d
in
in
tellig
en
t
E
MS
is
th
e
m
o
d
elin
g
o
f
d
r
iv
er
b
eh
av
io
r
an
d
th
e
d
ev
elo
p
m
en
t
o
f
p
er
s
o
n
alize
d
en
er
g
y
s
tr
ateg
ies.
I
n
co
r
p
o
r
atin
g
u
s
er
p
r
o
f
iles
an
d
r
ea
l
-
tim
e
f
ee
d
b
ac
k
allo
ws
E
MS
to
d
y
n
am
ically
ad
j
u
s
t
to
in
d
iv
i
d
u
al
d
r
iv
in
g
s
ty
les,
lo
ad
co
n
d
itio
n
s
,
a
n
d
r
o
u
te
p
r
ef
er
e
n
ce
s
,
lead
in
g
to
en
h
an
ce
d
ef
f
icien
c
y
an
d
d
r
iv
i
n
g
e
x
p
er
ien
ce
[
1
5
]
.
Mo
r
eo
v
er
,
th
e
in
teg
r
atio
n
o
f
r
en
ewa
b
le
en
e
r
g
y
s
o
u
r
ce
s
,
s
m
ar
t
g
r
id
in
f
r
astru
ctu
r
e,
an
d
v
e
h
i
cle
-
to
-
g
r
id
(
V2
G)
s
y
s
tem
s
h
as
in
tr
o
d
u
ce
d
n
ew
lay
er
s
o
f
c
o
m
p
lex
ity
a
n
d
o
p
p
o
r
tu
n
ity
.
E
MSs
m
u
s
t
n
o
w
co
o
r
d
i
n
ate
with
d
is
tr
ib
u
ted
en
er
g
y
r
eso
u
r
ce
s
(
DE
R
s
)
,
b
id
ir
ec
tio
n
al
ch
ar
g
in
g
s
tatio
n
s
,
an
d
d
em
an
d
r
esp
o
n
s
e
p
r
o
g
r
am
s
[
1
6
]
-
[
1
8
]
.
T
o
m
an
ag
e
th
is
,
h
y
b
r
i
d
co
n
t
r
o
l
ap
p
r
o
ac
h
es
in
co
r
p
o
r
atin
g
n
eu
r
al
n
etwo
r
k
s
,
ad
ap
tiv
e
n
eu
r
o
-
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
s
(
ANFI
S),
an
d
m
etah
e
u
r
is
tic
o
p
tim
izatio
n
ar
e
b
ein
g
e
x
p
lo
r
ed
[
1
9
]
-
[
2
1
]
.
R
ec
en
t liter
atu
r
e
r
ev
iews [
2
2
]
-
[
2
4
]
h
ig
h
lig
h
t th
e
ev
o
lu
tio
n
o
f
E
MS
f
r
o
m
s
tatic,
r
u
le
-
b
ased
s
y
s
tem
s
to
h
y
b
r
id
,
AI
-
e
n
ab
led
a
r
ch
itectu
r
es
th
at
in
teg
r
ate
r
ea
l
-
tim
e
o
p
tim
izatio
n
,
p
r
ed
ictiv
e
m
o
d
elin
g
,
a
n
d
e
d
g
e
co
m
p
u
tin
g
.
T
h
e
ad
v
e
n
t
o
f
e
d
g
e
AI
en
a
b
les
lo
w
-
laten
cy
,
d
ec
en
tr
alize
d
E
MS
o
p
er
ati
o
n
,
o
f
f
er
in
g
f
aster
r
esp
o
n
s
e
tim
es
an
d
im
p
r
o
v
ed
d
ata
p
r
iv
ac
y
[
2
5
]
-
[
2
7
]
.
Desp
ite
th
is
p
r
o
g
r
ess
,
s
ev
er
al
r
es
ea
r
ch
g
a
p
s
p
er
s
is
t:
i)
d
ata
s
p
ar
s
ity
an
d
h
eter
o
g
e
n
eity
ac
r
o
s
s
E
V
p
latf
o
r
m
s
,
ii)
h
ig
h
co
m
p
u
tatio
n
al
co
m
p
l
ex
ity
o
f
ad
v
a
n
ce
d
ML
/DR
L
alg
o
r
ith
m
s
,
iii)
l
im
i
ted
in
ter
p
r
etab
ilit
y
o
f
b
lack
-
b
o
x
m
o
d
els
in
s
af
ety
-
c
r
itical
s
y
s
tem
s
,
an
d
i
v
)
l
ac
k
o
f
s
tan
d
ar
d
izatio
n
an
d
r
eg
u
lato
r
y
co
m
p
lian
ce
in
E
MS
d
esig
n
.
T
o
a
d
d
r
ess
th
ese
c
h
a
lle
n
g
es
,
t
h
is
p
ap
e
r
p
r
o
p
o
s
es
a
c
o
m
p
ar
at
iv
e
E
MS
f
r
a
m
ew
o
r
k
l
e
v
e
r
a
g
i
n
g
d
e
cisi
o
n
tr
e
e
,
SV
M,
an
d
XGB
o
o
s
t
c
lass
if
i
er
s
t
r
a
in
e
d
o
n
r
ea
l
-
tim
e
E
V
o
p
e
r
at
io
n
a
l
d
ata
.
T
h
e
f
r
a
m
ew
o
r
k
en
h
an
ce
s
e
n
er
g
y
ef
f
ic
ie
n
c
y
,
s
u
p
p
o
r
ts
p
r
e
d
ictiv
e
lo
ad
m
an
a
g
em
en
t,
a
n
d
f
ac
ilit
ates
f
au
lt
d
iag
n
o
s
is
in
elec
tr
ic
tr
ac
tio
n
s
y
s
tem
s
.
Ad
d
it
io
n
a
ll
y
,
t
h
e
s
t
u
d
y
i
n
t
eg
r
ates
B
L
DC
m
o
to
r
h
ea
lth
m
o
n
ito
r
in
g
,
b
atter
y
s
tate
o
f
h
ea
lth
(
So
H)
esti
m
atio
n
,
an
d
lo
ad
f
o
r
ec
asti
n
g
,
o
f
f
e
r
in
g
a
co
m
p
r
e
h
en
s
iv
e
AI
-
d
r
iv
en
s
o
lu
tio
n
f
o
r
n
ex
t
-
g
en
er
atio
n
E
M
S
in
E
Vs.
2.
E
NE
RG
Y
M
AN
AG
E
M
E
N
T
SYST
E
M
(
E
M
S)
I
N
E
L
E
C
T
RIC V
E
H
I
C
L
E
S (
E
V
S)
2
.
1
.
O
v
er
v
iew
o
f
E
M
S in
E
V
po
wer
t
ra
ins
An
E
V
p
o
wer
tr
ain
co
m
p
r
is
es
s
ev
er
al
k
ey
s
u
b
s
y
s
tem
s
:
th
e
b
atter
y
,
in
v
e
r
ter
,
elec
tr
ic
m
o
to
r
,
a
n
d
a
co
n
tr
o
ller
th
at
g
o
v
e
r
n
s
th
e
en
er
g
y
f
lo
w.
T
h
e
E
MS
f
u
n
ctio
n
s
as
th
e
s
u
p
er
v
is
o
r
y
co
n
tr
o
l
u
n
it
r
esp
o
n
s
ib
le
f
o
r
in
tellig
en
tly
d
is
tr
ib
u
tin
g
p
o
w
er
am
o
n
g
th
ese
c
o
m
p
o
n
en
ts
d
u
r
in
g
d
i
f
f
er
en
t
p
h
ases
o
f
o
p
er
atio
n
,
s
u
ch
as
ac
ce
ler
atio
n
,
cr
u
is
in
g
,
b
r
a
k
in
g
,
an
d
ch
ar
g
in
g
.
I
n
th
is
s
tu
d
y
,
th
e
E
MS
is
d
esig
n
ed
to
p
r
ed
ict
an
d
m
an
ag
e
p
o
wer
d
is
tr
ib
u
tio
n
s
tr
ateg
ies
u
s
in
g
b
o
th
r
u
le
-
b
ased
lo
g
ic
an
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
o
d
els.
T
h
e
o
b
jectiv
e
is
to
o
p
tim
ize
en
er
g
y
ef
f
icien
c
y
,
m
ain
tain
b
atter
y
h
ea
lth
,
an
d
p
r
o
lo
n
g
v
eh
icle
r
a
n
g
e
u
n
d
er
v
ar
y
in
g
d
r
iv
i
n
g
co
n
d
itio
n
s
.
T
ab
le
1
o
u
tlin
es
th
e
ty
p
ical
b
a
tter
y
s
p
ec
if
icatio
n
s
u
s
ed
in
th
e
d
ataset
s
im
u
latio
n
an
d
m
o
d
e
l
tr
ain
in
g
.
T
h
ese
v
alu
es
ar
e
b
ased
o
n
a
r
ep
r
esen
tativ
e
lith
iu
m
-
io
n
b
atter
y
p
ac
k
s
u
itab
le
f
o
r
m
id
-
r
an
g
e
E
Vs
.
T
ab
le
2
p
r
esen
ts
k
ey
m
o
to
r
p
ar
am
ete
r
s
cr
itical
f
o
r
th
e
E
MS
m
o
d
el,
p
ar
ticu
lar
ly
i
n
ca
p
tu
r
in
g
f
ea
tu
r
es
lik
e
s
p
ee
d
,
ac
ce
ler
atio
n
,
an
d
lo
ad
.
A
4
8
V
,
3
k
W
B
L
DC
m
o
to
r
is
co
n
s
id
er
ed
th
e
p
r
o
p
u
ls
io
n
u
n
it,
d
r
iv
i
n
g
th
e
v
e
h
icle
lo
ad
u
n
d
er
E
MS
s
u
p
er
v
is
io
n
.
T
ab
le
1
.
B
atter
y
p
a
r
am
eter
s
u
s
ed
in
s
im
u
latio
n
P
a
r
a
me
t
e
r
V
a
l
u
e
D
e
scri
p
t
i
o
n
B
a
t
t
e
r
y
t
y
p
e
Li
-
i
o
n
(
N
M
C
)
N
i
c
k
e
l
ma
n
g
a
n
e
se
c
o
b
a
l
t
o
x
i
d
e
N
o
mi
n
a
l
v
o
l
t
a
g
e
3
5
0
V
A
v
e
r
a
g
e
v
o
l
t
a
g
e
u
n
d
e
r
s
t
a
n
d
a
r
d
o
p
e
r
a
t
i
o
n
C
a
p
a
c
i
t
y
1
0
0
A
h
M
a
x
i
m
u
m
c
h
a
r
g
e
s
t
o
r
a
g
e
To
t
a
l
e
n
e
r
g
y
3
5
k
W
h
E
t
ot
a
l
=
V
nom
×
Q
U
sab
l
e
e
n
e
r
g
y
3
1
.
5
k
W
h
~
9
0
%
o
f
t
o
t
a
l
e
n
e
r
g
y
f
o
r
s
a
f
e
o
p
e
r
a
t
i
o
n
S
O
C
r
a
n
g
e
10
–
1
0
0
%
O
p
e
r
a
t
i
o
n
a
l
w
i
n
d
o
w
f
o
r
E
M
S
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.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2400
-
2
4
1
0
2402
T
ab
le
2
.
B
L
DC
m
o
to
r
p
a
r
am
e
ter
s
P
a
r
a
me
t
e
r
V
a
l
u
e
R
a
t
e
d
v
o
l
t
a
g
e
4
8
V
R
a
t
e
d
p
o
w
e
r
3
k
W
R
a
t
e
d
s
p
e
e
d
3
0
0
0
R
P
M
P
e
a
k
t
o
r
q
u
e
10
–
1
5
N
m
B
a
c
k
EM
F
c
o
n
s
t
a
n
t
K
e
0
.
0
8
V
/
r
a
d
/
s
S
t
a
t
o
r
r
e
s
i
st
a
n
c
e
0
.
1
5
–
0
.
2
5
Ω
C
o
o
l
i
n
g
mec
h
a
n
i
sm
N
a
t
u
r
a
l
/
F
a
n
C
o
n
t
r
o
l
st
r
a
t
e
g
y
F
O
C
o
r
6
-
S
t
e
p
2
.
2
.
Rule
-
b
a
s
ed
E
M
S
l
o
g
ic
I
n
th
e
f
i
r
s
t
ap
p
r
o
ac
h
,
a
c
o
n
v
e
n
tio
n
al
r
u
le
-
b
ased
E
MS
is
d
ef
in
ed
u
s
in
g
s
im
p
le
c
o
n
d
itio
n
al
lo
g
ic
b
ased
on
s
tate
o
f
ch
a
r
g
e
(
SOC
)
an
d
l
o
ad
.
T
h
e
lo
g
ic
ca
n
b
e
r
e
p
r
esen
ted
b
y
th
e
f
o
llo
win
g
d
ec
is
io
n
b
o
u
n
d
ar
ies:
−
I
f
SOC
>
0
.
8
an
d
l
o
ad
<
2
0
0
0
W
:
u
s
e
b
atter
y
−
I
f
SOC
<
0
.
3
:
en
ab
le
r
eg
en
e
r
a
tiv
e
b
r
ak
in
g
−
E
ls
e:
u
s
e
an
o
p
tim
ized
en
e
r
g
y
m
ix
T
h
is
ap
p
r
o
ac
h
is
d
eter
m
in
is
tic
an
d
co
m
p
u
tatio
n
ally
ef
f
ici
en
t
,
b
u
t
lack
s
ad
ap
tab
ilit
y
to
d
y
n
am
ic
d
r
i
v
in
g
p
atter
n
s
o
r
u
n
s
ee
n
s
ce
n
ar
io
s
.
2
.
3
.
E
nerg
y
f
l
o
w
a
nd
m
a
na
g
em
ent
ph
a
s
es
in E
V
T
h
e
E
MS
in
ter
ac
ts
with
th
e
E
V
s
u
b
s
y
s
tem
s
ac
r
o
s
s
th
r
ee
m
ajo
r
o
p
e
r
atio
n
al
p
h
ases
:
−
Dis
ch
ar
g
e
ph
ase: Batter
y
p
o
w
er
s
th
e
m
o
to
r
t
h
r
o
u
g
h
t
h
e
in
v
e
r
ter
,
as p
r
esen
ted
in
(
1
).
=
×
(
1
)
−
R
eg
en
er
ativ
e
b
r
ak
i
n
g
p
h
ase: M
o
to
r
ac
ts
as a
g
en
er
ato
r
to
r
e
co
v
er
en
e
r
g
y
,
as p
r
esen
ted
in
(
2
).
=
∫
(
)
.
(
)
2
1
(
2
)
−
C
h
ar
g
in
g
p
h
ase:
B
atter
y
is
r
ec
h
ar
g
ed
v
ia
an
ex
ter
n
al
p
o
wer
s
o
u
r
ce
.
A
s
im
p
lifie
d
b
lo
ck
d
iag
r
am
o
f
th
e
E
V
en
er
g
y
f
lo
w
is
s
h
o
wn
in
Fig
u
r
e
1
,
wh
er
e
e
n
er
g
y
p
ath
s
ar
e
m
o
n
ito
r
ed
a
n
d
g
o
v
e
r
n
ed
b
y
th
e
E
MS
lo
g
ic.
W
h
ile
r
u
le
-
b
ased
E
MS
o
f
f
er
s
ea
s
e
o
f
im
p
lem
en
tatio
n
,
it
ca
n
n
o
t
ad
ap
t
o
r
o
p
tim
ize
u
n
d
er
u
n
ce
r
tain
o
r
v
ar
iab
le
o
p
er
atin
g
c
o
n
d
itio
n
s
.
T
h
is
lim
itatio
n
m
o
tiv
ates
th
e
in
teg
r
atio
n
o
f
d
ata
-
d
r
i
v
en
E
MS
m
o
d
els,
s
u
ch
as
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
,
wh
ich
ca
n
d
y
n
am
ically
lear
n
p
atter
n
s
f
r
o
m
in
p
u
t
f
ea
tu
r
es
lik
e
b
atter
y
SOC
,
lo
ad
(
p
o
wer
d
e
m
an
d
)
,
s
p
ee
d
,
an
d
a
cc
eler
atio
n
.
T
h
ese
f
ea
tu
r
es
ar
e
s
ca
led
an
d
f
ed
in
t
o
ML
m
o
d
e
ls
th
at
class
if
y
th
e
o
p
tim
al
p
o
wer
d
is
tr
ib
u
t
io
n
s
t
r
ateg
y
f
r
o
m
th
e
tr
ain
in
g
d
at
a,
o
f
f
er
in
g
im
p
r
o
v
ed
p
r
ec
is
io
n
a
n
d
a
d
ap
tab
ilit
y
co
m
p
ar
ed
to
s
tatic
r
u
le
s
ets.
Fig
u
r
e
1
.
E
V
e
n
er
g
y
f
lo
w
3.
M
ACH
I
N
E
L
E
AR
NING
-
B
ASE
D
E
N
E
RG
Y
M
A
NAG
E
M
E
N
T
SY
ST
E
M
(
E
M
S)
T
o
o
v
er
c
o
m
e
th
e
lim
itatio
n
s
o
f
co
n
v
e
n
tio
n
al
E
MS
s
tr
ateg
ies
(
r
u
le
-
b
ased
an
d
f
u
zz
y
lo
g
ic)
,
th
is
s
tu
d
y
ex
p
lo
r
es
a
m
ac
h
in
e
lear
n
in
g
(
ML
)
-
d
r
iv
e
n
E
MS
f
o
r
E
Vs
.
T
h
e
o
b
jectiv
e
is
to
lear
n
o
p
tim
al
p
o
wer
d
is
tr
ib
u
tio
n
s
tr
ateg
ies
f
r
o
m
o
p
er
atio
n
al
d
ata
to
en
h
an
ce
b
atter
y
life
,
i
m
p
r
o
v
e
e
n
er
g
y
ef
f
icien
c
y
,
an
d
s
u
p
p
o
r
t
d
y
n
a
m
ic
d
r
iv
in
g
co
n
d
itio
n
s
.
T
h
e
ML
-
E
MS
s
y
s
tem
is
tr
ain
ed
an
d
e
v
alu
ated
u
s
in
g
lab
eled
d
atasets
o
f
E
V
o
p
er
atio
n
al
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
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
e
n
erg
y
ma
n
a
g
eme
n
t sys
tem
fo
r
elec
tr
ic
ve
h
icles w
ith
…
(
K
.
S
.
R
.
V
a
r
a
P
r
a
s
a
d
)
2403
p
ar
am
eter
s
,
s
u
ch
as
s
p
ee
d
,
ac
ce
ler
atio
n
,
cu
r
r
e
n
t,
v
o
ltag
e
,
a
n
d
SOC
,
to
class
if
y
o
r
p
r
ed
ict
p
o
wer
f
lo
w
co
n
t
r
o
l
ac
tio
n
s
d
u
r
in
g
d
if
f
er
en
t
d
r
iv
e
cy
cles.
Fig
u
r
e
2
illu
s
tr
ates
t
h
e
co
m
p
lete
wo
r
k
f
lo
w
o
f
t
h
e
p
r
o
p
o
s
e
d
e
n
e
r
g
y
m
a
n
a
g
e
m
e
n
t
s
y
s
t
e
m
f
o
r
E
V
s
,
c
o
m
p
a
r
i
n
g
c
o
n
v
e
n
t
i
o
n
al
r
u
l
e
-
b
a
s
e
d
l
o
g
ic
w
it
h
m
a
ch
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
,
f
r
o
m
d
a
t
a
p
r
e
p
r
o
c
e
s
s
i
n
g
t
o
m
o
d
e
l
e
v
a
l
u
a
ti
o
n
a
n
d
d
e
p
l
o
y
m
e
n
t
.
3
.
1
.
Da
t
a
s
et
co
ns
t
ruct
io
n a
n
d f
ea
t
ure
m
a
pp
ing
T
ab
le
3
p
r
esen
ts
th
e
m
ap
p
in
g
o
f
cr
itical
elec
tr
ical
an
d
v
eh
icu
lar
p
ar
am
eter
s
u
s
ed
as
f
ea
tu
r
es
in
th
e
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
ese
i
n
p
u
ts
ar
e
d
ir
e
c
tly
d
er
iv
e
d
f
r
o
m
th
e
s
en
s
o
r
an
d
s
im
u
latio
n
d
ata
o
f
th
e
E
V
s
y
s
tem
.
T
h
e
tar
g
et
lab
el
f
o
r
class
if
icatio
n
in
clu
d
es
E
MS
o
p
er
atio
n
m
o
d
es
s
u
ch
as:
d
is
ch
ar
g
e
(
m
o
to
r
lo
ad
)
,
r
eg
e
n
er
ativ
e
b
r
ak
i
n
g
(
e
n
er
g
y
r
ec
o
v
er
y
)
,
id
le
(
n
o
s
ig
n
i
f
ican
t e
n
er
g
y
f
lo
w)
,
an
d
ch
ar
g
in
g
(
ex
ter
n
al
p
o
we
r
s
o
u
r
ce
)
.
T
h
e
(
3
)
-
(
6
)
ar
e
u
s
ed
to
d
er
iv
e
c
o
m
p
u
ted
f
ea
tu
r
es:
−
E
lectr
ical
p
o
wer
as p
r
esen
ted
i
n
(
3
)
.
=
∗
1000
(
3
)
−
State
o
f
ch
ar
g
e
esti
m
atio
n
b
ased
o
n
c
o
u
lo
m
b
co
u
n
tin
g
as p
r
esen
ted
in
(
4
).
(
)
=
(
0
)
−
1
∫
(
)
0
(
4
)
−
Mo
to
r
to
r
q
u
e
esti
m
atio
n
as p
r
esen
ted
in
(
5
)
.
=
60
∗
2
∗
(
5
)
W
h
er
e:
P
elec
: E
lectr
ical
p
o
wer
(
W
)
,
N:
Mo
to
r
s
p
ee
d
in
R
PM
.
Fig
u
r
e
2
.
B
lo
ck
d
ia
g
r
am
o
f
a
n
ML
-
b
ased
en
er
g
y
m
a
n
ag
em
e
n
t sy
s
tem
f
o
r
elec
tr
ic
v
e
h
icles
T
ab
le
3
.
Featu
r
e
m
ap
p
in
g
f
o
r
ML
-
EMS
F
e
a
t
u
r
e
n
a
me
D
e
scri
p
t
i
o
n
U
n
i
t
s
V
o
l
t
a
g
e
Te
r
mi
n
a
l
v
o
l
t
a
g
e
o
f
t
h
e
b
a
t
t
e
r
y
V
o
l
t
s (V
)
C
u
r
r
e
n
t
I
n
st
a
n
t
a
n
e
o
u
s
b
a
t
t
e
r
y
c
u
r
r
e
n
t
A
mp
e
r
e
s
(
A
)
P
o
w
e
r
I
n
st
a
n
t
a
n
e
o
u
s
e
l
e
c
t
r
i
c
a
l
p
o
w
e
r
(
V
×
I
/
1
0
0
0
)
kW
S
p
e
e
d
R
o
t
a
t
i
o
n
a
l
sp
e
e
d
o
f
B
LD
C
mo
t
o
r
R
P
M
S
O
C
B
a
t
t
e
r
y
s
t
a
t
e
o
f
c
h
a
r
g
e
%
To
r
q
u
e
To
r
q
u
e
d
e
ma
n
d
e
d
f
r
o
m t
h
e
m
o
t
o
r
Nm
A
c
c
e
l
e
r
a
t
i
o
n
R
a
t
e
o
f
c
h
a
n
g
e
o
f
v
e
h
i
c
l
e
s
p
e
e
d
m/
s²
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.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2400
-
2
4
1
0
2404
3
.
2
.
M
o
del
dev
elo
pm
ent
a
nd
s
up
er
v
is
e
d lea
rning
a
pp
ro
a
ch
I
n
th
is
s
tu
d
y
,
t
h
e
d
ev
el
o
p
m
en
t
o
f
in
tellig
en
t
E
MS
lo
g
ic
f
o
r
E
Vs
is
f
o
r
m
u
lated
as
a
s
u
p
er
v
is
ed
m
u
lti
-
class
clas
s
if
icatio
n
p
r
o
b
lem
.
T
h
e
o
b
jectiv
e
is
to
p
r
ed
ict
th
e
E
MS
o
p
er
atio
n
m
o
d
e
—
s
u
ch
as
ch
ar
g
in
g
,
d
is
ch
ar
g
in
g
,
r
e
g
en
er
ativ
e
b
r
a
k
in
g
,
o
r
id
le
,
b
ased
o
n
r
ea
l
-
ti
m
e
f
ea
tu
r
es
d
er
iv
ed
f
r
o
m
th
e
p
o
wer
tr
ain
.
T
h
ese
f
ea
tu
r
es in
clu
d
e:
−
State
o
f
ch
ar
g
e
(
SOC
)
–
(
%)
−
B
atter
y
vo
ltag
e
(
V)
a
n
d
c
u
r
r
en
t (
A)
−
Mo
to
r
s
p
e
ed
(
R
PM)
an
d
to
r
q
u
e
(
Nm
)
−
Acc
eler
atio
n
(
m
/s
²)
an
d
v
eh
icl
e
s
p
ee
d
(
k
m
/
h
)
−
T
h
r
o
ttle
po
s
itio
n
(
%)
an
d
b
r
ak
in
g
in
ten
s
ity
−
L
o
ad
p
o
wer
d
em
a
n
d
(
Kw)
T
h
e
co
r
r
esp
o
n
d
in
g
o
u
tp
u
t
la
b
el
(
tar
g
et)
d
en
o
tes
th
e
E
M
S
m
o
d
e,
wh
ich
is
p
r
ed
icted
b
ased
o
n
th
e
ab
o
v
e
f
ea
tu
r
es u
s
in
g
th
e
f
o
llo
win
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els:
i)
Dec
is
io
n
t
r
ee
(
DT
)
c
lass
if
ier
T
h
e
d
ec
is
io
n
tr
ee
class
if
ier
i
s
a
h
ier
ar
ch
ical
m
o
d
el
th
at
r
ec
u
r
s
iv
ely
p
ar
titi
o
n
s
th
e
f
ea
tu
r
e
s
p
ac
e
in
to
d
ec
is
io
n
r
eg
io
n
s
b
ased
o
n
th
r
esh
o
ld
s
p
lits
,
as
s
h
o
wn
in
Fig
u
r
e
3
.
I
t
is
co
n
s
tr
u
cte
d
u
s
in
g
cr
iter
ia
s
u
ch
as
Gin
i
im
p
u
r
ity
o
r
en
tr
o
p
y
t
o
m
ax
im
i
ze
class
p
u
r
ity
at
ea
ch
n
o
d
e,
a
s
p
r
esen
ted
in
(
6
)
.
A
t e
a
ch
s
p
lit:
Gin
i(
D)
=
1
−
∑
2
=
1
(
6
)
W
h
er
e
p
i
is
th
e
p
r
o
p
o
r
tio
n
o
f
c
lass
i in
s
u
b
s
et
D.
−
C
ap
tu
r
es r
u
le
-
b
ased
h
e
u
r
is
tics
th
at
ar
e
co
m
m
o
n
in
class
ical
E
MS
s
y
s
tem
s
.
−
I
n
ter
p
r
etab
le
s
tr
u
ctu
r
e
allo
ws
tr
ac
in
g
b
ac
k
d
ec
is
io
n
lo
g
ic
(
e.
g
.
,
“I
f
SOC
<
2
0
%
an
d
to
r
q
u
e
d
em
an
d
is
h
ig
h
,
e
n
ter
id
le
o
r
p
o
wer
-
s
av
in
g
m
o
d
e”
)
.
−
L
o
w
co
m
p
u
tatio
n
al
co
s
t e
n
ab
l
es r
ea
l
-
tim
e
em
b
ed
d
e
d
d
e
p
lo
y
m
en
t in
o
n
b
o
ar
d
E
V
co
n
tr
o
l u
n
its
.
ii)
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
T
h
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
is
a
d
is
cr
im
in
ativ
e
class
if
ier
th
at
f
in
d
s
an
o
p
tim
al
h
y
p
er
p
lan
e
with
m
ax
im
u
m
m
ar
g
in
s
ep
ar
atin
g
d
if
f
er
en
t
class
es
in
a
tr
an
s
f
o
r
m
ed
f
ea
tu
r
e
s
p
ac
e.
A
r
a
d
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
k
er
n
el
is
u
s
ed
to
h
an
d
le
n
o
n
-
lin
ea
r
s
ep
ar
a
b
ilit
y
.
Giv
en
tr
ain
in
g
v
ec
to
r
s
x
i
∈
R
n
,
la
b
els
y
i
∈
{1
,
.
.
.
,
K},
SVM
s
o
lv
es,
as p
r
esen
ted
in
(
7
).
1
2
‖
‖
2
+
.
.
(
∅
(
)
+
)
≥
1
−
(
7
)
W
h
er
e
ϕ
(
x
i
)
is
th
e
k
e
r
n
el
m
a
p
p
in
g
.
−
R
o
b
u
s
t
to
o
u
tlier
s
an
d
g
en
e
r
alize
s
well
o
n
h
ig
h
-
d
im
en
s
io
n
al,
n
o
n
lin
ea
r
E
MS
f
ea
t
u
r
e
s
ets
as
s
h
o
wn
in
Fig
u
r
e
4
.
−
Par
ticu
lar
ly
ef
f
ec
tiv
e
in
s
ce
n
ar
io
s
with
o
v
er
lap
p
in
g
class
d
is
tr
ib
u
tio
n
s
(
e.
g
.
,
p
ar
tial
b
r
a
k
in
g
with
lo
w
r
eg
en
er
ativ
e
o
u
tp
u
t v
s
lo
w
-
lo
a
d
d
is
ch
ar
g
in
g
)
.
−
Su
itab
le
f
o
r
r
ea
l
-
tim
e
class
if
icatio
n
with
p
r
e
-
tr
ai
n
ed
,
k
er
n
el
-
o
p
tim
iz
ed
m
o
d
els.
iii)
XGBo
o
s
t c
las
s
if
ier
XGBo
o
s
t
(
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
)
is
an
en
s
em
b
le
-
b
ase
d
class
if
ier
th
at
b
u
ild
s
s
eq
u
en
tial
wea
k
lear
n
er
s
(
d
ec
is
io
n
tr
ee
s
)
to
m
i
n
im
ize
a
r
eg
u
lar
ized
lo
s
s
f
u
n
c
tio
n
u
s
in
g
g
r
ad
ien
t
d
escen
t
o
p
tim
izatio
n
.
I
t
ex
ce
ls
in
b
o
th
ac
c
u
r
ac
y
a
n
d
c
o
m
p
u
tat
io
n
al
ef
f
icien
cy
.
T
h
e
m
o
d
el
p
r
ed
icts
,
as p
r
esen
ted
in
(
8
)
.
̂
=
∑
(
)
,
=
1
∈
(
8
)
W
h
er
e
ea
ch
f
m
is
a
r
eg
r
ess
io
n
tr
ee
a
n
d
F
is
th
e
f
u
n
ctio
n
al
s
p
ac
e.
T
h
e
lo
s
s
f
u
n
ctio
n
in
clu
d
es
a
r
e
g
u
lar
izatio
n
ter
m
,
as p
r
esen
ted
in
(
9
)
an
d
(
1
0
)
.
=
∑
(
,
̂
)
+
∑
(
)
(
9
)
(
)
=
+
1
2
‖
‖
2
(
1
0
)
−
Au
to
m
atica
lly
ca
p
tu
r
es c
o
m
p
l
ex
f
ea
tu
r
e
in
te
r
ac
tio
n
s
an
d
n
o
n
-
lin
ea
r
d
e
p
en
d
e
n
cies a
m
o
n
g
SOC
,
s
p
ee
d
,
an
d
p
o
wer
d
em
a
n
d
a
s
s
h
o
wn
in
Fig
u
r
e
5
.
−
Han
d
les f
ea
tu
r
e
s
p
ar
s
ity
,
n
o
is
e,
an
d
m
is
s
in
g
d
ata
with
o
u
t p
r
e
p
r
o
ce
s
s
in
g
p
en
alties.
−
I
d
ea
l f
o
r
lar
g
e
-
s
ca
le,
h
i
g
h
-
d
im
en
s
io
n
al
E
MS
d
atasets
an
d
s
u
p
p
o
r
ts
in
cr
e
m
e
n
tal
u
p
d
ates (
o
n
lin
e
lear
n
in
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
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
e
n
erg
y
ma
n
a
g
eme
n
t sys
tem
fo
r
elec
tr
ic
ve
h
icles w
ith
…
(
K
.
S
.
R
.
V
a
r
a
P
r
a
s
a
d
)
2405
Fig
u
r
e
3
.
Dec
is
io
n
tr
ee
f
lo
w
ch
ar
t
Fig
u
r
e
4
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
f
lo
w
ch
ar
t
Fig
u
r
e
5
.
XGBo
o
s
t
f
lo
w
ch
ar
t
3
.
3
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
o
f
t
hree
m
et
ho
ds
f
o
r
E
M
S in EVs
All
th
r
ee
m
o
d
els
o
f
f
er
u
n
iq
u
e
ca
p
ab
ilit
ies
f
o
r
d
ev
elo
p
in
g
a
d
ata
-
d
r
iv
e
n
E
MS
lo
g
ic,
as
m
en
tio
n
ed
in
T
ab
le
4
.
W
h
ile
d
ec
is
io
n
tr
ee
s
alig
n
clo
s
ely
with
tr
ad
itio
n
al
co
n
tr
o
l
lo
g
ic,
SVM
an
d
XGBo
o
s
t
p
r
o
v
id
e
th
e
f
lex
ib
ilit
y
an
d
ad
ap
ta
b
ilit
y
n
e
ed
ed
f
o
r
c
o
m
p
lex
,
d
y
n
a
m
ic
E
V
o
p
er
atio
n
.
T
h
ese
m
o
d
els
co
llectiv
ely
f
o
r
m
th
e
b
asis
f
o
r
ev
alu
atin
g
ML
-
b
ased
E
MS
s
tr
ateg
ies ag
ain
s
t c
o
n
v
en
tio
n
al
r
u
le
-
an
d
f
u
zz
y
-
b
ased
co
u
n
ter
p
a
r
ts
in
r
ea
l
d
r
iv
in
g
c
o
n
d
itio
n
s
.
XGBo
o
s
t
o
u
tp
er
f
o
r
m
e
d
o
th
e
r
m
o
d
els
in
ter
m
s
o
f
o
v
e
r
all
ac
cu
r
ac
y
an
d
class
-
s
p
ec
if
ic
r
ec
a
ll,
m
ak
in
g
it
h
ig
h
ly
e
f
f
ec
tiv
e
f
o
r
r
ea
l
-
tim
e
E
MS
d
ec
is
io
n
s
,
as
m
en
tio
n
e
d
in
T
a
b
le
5
.
Dec
is
io
n
tr
ee
s
al
s
o
p
er
f
o
r
m
ed
well
b
u
t
ex
h
i
b
ited
m
in
o
r
o
v
er
f
itti
n
g
.
SVM
y
ield
ed
co
m
p
etitiv
e
r
esu
lts
b
u
t
r
eq
u
ir
ed
f
ea
t
u
r
e
s
ca
lin
g
an
d
h
ig
h
er
co
m
p
u
tatio
n
.
−
Ad
ap
tiv
e
co
n
tr
o
l:
Un
lik
e
r
u
le
-
b
ased
lo
g
ic,
ML
m
o
d
els
d
y
n
a
m
ically
lear
n
co
n
tr
o
l
s
tr
ateg
ie
s
u
n
d
er
v
ar
y
i
n
g
lo
ad
s
an
d
b
atter
y
s
tates.
−
E
n
er
g
y
e
f
f
icien
cy
:
B
etter
class
if
icatio
n
o
f
b
r
ak
in
g
an
d
d
is
ch
ar
g
e
p
h
ases
lead
s
to
o
p
tim
ized
r
eg
en
er
ativ
e
en
er
g
y
ca
p
tu
r
e
a
n
d
r
e
d
u
ce
d
th
er
m
al
s
tr
ess
.
−
Scalab
ilit
y
:
T
h
e
ML
-
b
ased
E
MS
ca
n
g
en
er
alize
ac
r
o
s
s
d
if
f
er
en
t
b
atter
y
co
n
f
ig
u
r
atio
n
s
an
d
d
r
i
v
in
g
p
r
o
f
iles
with
r
etr
ain
in
g
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
an
d
s
u
itab
ilit
y
f
o
r
E
MS
in
E
Vs
M
o
d
e
l
K
e
y
s
t
r
e
n
g
t
h
I
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
C
o
m
p
u
t
a
t
i
o
n
a
l
d
e
m
a
n
d
S
u
i
t
a
b
i
l
i
t
y
f
o
r
r
e
a
l
-
t
i
me
E
M
S
D
e
c
i
s
i
o
n
t
r
e
e
Lo
g
i
c
a
l
& r
u
l
e
-
b
a
s
e
d
m
o
d
e
l
i
n
g
H
i
g
h
Lo
w
H
i
g
h
S
V
M
R
o
b
u
st
t
o
o
v
e
r
l
a
p
a
n
d
n
o
i
s
e
M
e
d
i
u
m
M
o
d
e
r
a
t
e
M
e
d
i
u
m
X
G
B
o
o
st
H
i
g
h
a
c
c
u
r
a
c
y
&
g
e
n
e
r
a
l
i
z
a
t
i
o
n
Lo
w
H
i
g
h
M
e
d
i
u
m (
o
f
f
l
i
n
e
o
r
e
d
g
e
-
a
i
d
e
d
)
T
ab
le
5
.
Sam
p
le
class
if
icatio
n
r
ep
o
r
t
(
XGBo
o
s
t
c
lass
if
ier
)
C
l
a
s
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
D
i
sch
a
r
g
e
0
.
9
5
0
.
9
4
0
.
9
4
R
e
g
e
n
e
r
a
t
i
v
e
br
a
k
i
n
g
0
.
9
2
0
.
9
1
0
.
9
1
I
d
l
e
0
.
8
9
0
.
9
3
0
.
9
1
C
h
a
r
g
i
n
g
0
.
9
6
0
.
9
5
0
.
9
5
4.
RE
SU
L
T
S & D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
a
d
etailed
an
aly
s
is
o
f
th
e
m
ac
h
in
e
lear
n
in
g
-
b
ased
en
er
g
y
m
an
ag
em
e
n
t
s
y
s
t
em
f
o
r
elec
tr
ic
v
eh
icles
(
E
Vs),
f
o
cu
s
in
g
o
n
m
o
d
el
p
er
f
o
r
m
an
ce
,
s
y
s
tem
b
eh
a
v
io
r
u
n
d
er
d
y
n
a
m
ic
co
n
d
itio
n
s
,
an
d
th
e
ef
f
ec
tiv
en
ess
o
f
in
tellig
en
t
p
h
ase
class
if
icatio
n
.
T
h
e
r
esu
lts
co
m
p
ar
is
o
n
m
en
tio
n
ed
in
T
ab
le
6
clea
r
ly
s
h
o
ws
th
at
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
o
u
tp
er
f
o
r
m
th
e
c
o
n
v
e
n
tio
n
al
r
u
le
-
b
ased
E
MS.
Am
o
n
g
th
e
test
ed
m
o
d
els,
XGBo
o
s
t
ac
h
iev
es
th
e
h
ig
h
est
F1
sc
o
r
e
(
0
.
8
9
)
,
in
d
icatin
g
a
r
o
b
u
s
t
an
d
well
-
b
alan
ce
d
p
r
ed
ictio
n
ca
p
ab
ilit
y
.
C
o
m
p
ar
ed
to
p
r
io
r
wo
r
k
as
r
ep
o
r
ted
in
cited
p
a
p
er
s
,
o
u
r
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
es
a
p
er
f
o
r
m
an
ce
g
ain
o
f
~5
%,
d
em
o
n
s
tr
atin
g
th
e
b
e
n
ef
it o
f
in
co
r
p
o
r
atin
g
ad
v
a
n
ce
d
e
n
s
em
b
le
tech
n
iq
u
es.
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.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2400
-
2
4
1
0
2406
4
.
1
.
F
e
a
t
ure
co
rr
ela
t
io
n a
na
ly
s
is
Fig
u
r
e
6
s
h
o
ws
th
e
f
ea
t
u
r
e
c
o
r
r
elatio
n
h
ea
tm
ap
,
illu
s
tr
atin
g
th
e
r
elatio
n
s
h
ip
s
am
o
n
g
t
h
e
k
ey
in
p
u
t
v
ar
iab
les:
b
atter
y
SOC
,
v
eh
icle
s
p
ee
d
,
ac
ce
ler
atio
n
,
an
d
elec
tr
ical
lo
ad
.
T
h
e
h
ea
tm
ap
r
ev
ea
ls
th
at
SO
C
h
as
a
m
o
d
er
ate
n
eg
ativ
e
c
o
r
r
elatio
n
with
ac
ce
ler
atio
n
an
d
lo
ad
,
in
d
icat
in
g
th
at
h
ig
h
er
p
o
we
r
d
em
an
d
s
ten
d
to
d
ep
lete
th
e
b
atter
y
m
o
r
e
q
u
ic
k
ly
.
S
p
e
e
d
a
n
d
a
c
c
e
l
e
r
a
t
i
o
n
e
x
h
i
b
i
t
a
s
t
r
o
n
g
p
o
s
i
t
i
v
e
c
o
r
r
e
l
a
tio
n
,
c
o
n
s
i
s
t
e
n
t
w
i
t
h
r
e
a
l
-
w
o
r
l
d
d
r
i
v
i
n
g
d
y
n
a
m
i
c
s
.
T
h
e
s
e
i
n
s
i
g
h
t
s
j
u
s
ti
f
y
t
h
e
s
e
l
e
c
t
i
o
n
o
f
f
e
a
t
u
r
es
u
s
e
d
i
n
m
o
d
e
l
t
r
a
i
n
i
n
g
a
n
d
e
m
p
h
a
s
i
z
e
t
h
e
i
m
p
o
r
t
a
n
c
e
o
f
u
s
i
n
g
c
o
r
r
e
l
a
te
d
i
n
p
u
t
v
a
r
i
a
b
l
es
to
e
n
h
a
n
c
e
c
l
a
s
s
i
f
ic
a
t
i
o
n
a
c
c
u
r
ac
y
.
T
ab
le
6
.
C
o
m
p
a
r
ativ
e
ev
alu
ati
o
n
o
f
m
ac
h
in
e
lea
r
n
in
g
m
o
d
el
s
an
d
co
n
v
en
tio
n
al
E
MS
M
e
t
h
o
d
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
s
c
o
r
e
N
o
t
e
s
R
u
l
e
-
b
a
se
d
EM
S
0
.
7
2
0
.
7
0
0
.
6
8
0
.
6
9
B
a
se
l
i
n
e
D
e
c
i
s
i
o
n
t
r
e
e
0
.
8
5
0
.
8
4
0
.
8
3
0
.
8
3
I
n
t
e
r
p
r
e
t
a
b
l
e
S
V
M
(
R
B
F
K
e
r
n
e
l
)
0
.
8
8
0
.
8
7
0
.
8
6
0
.
8
6
N
o
n
l
i
n
e
a
r
p
a
t
t
e
r
n
s
X
G
B
o
o
st
0
.
9
1
0
.
9
0
0
.
8
9
0
.
8
9
B
e
st
m
o
d
e
l
W
a
n
g
e
t
a
l
.
[
1
3
]
0
.
8
6
0
.
8
5
0
.
8
4
0
.
8
5
S
u
p
e
r
v
i
se
d
M
L
EM
S
f
o
r
H
EV
s
D
e
v
i
e
t
a
l
.
[
1
8
]
0
.
8
9
0
.
8
8
0
.
8
7
0
.
8
7
X
G
B
o
o
st
mo
d
e
l
f
o
r
EV
E
M
S
Y
e
p
t
h
o
e
t
a
l
.
[
1
9
]
0
.
8
7
0
.
8
5
0
.
8
5
0
.
8
5
M
L
m
o
d
e
l
c
o
m
p
a
r
i
so
n
Est
r
a
d
a
e
t
a
l
.
[
1
5
]
0
.
8
3
0
.
8
2
0
.
8
0
0
.
8
1
RL
-
b
a
se
d
E
M
S
s
t
r
a
t
e
g
y
Li
u
a
n
d
Z
h
a
n
g
[
2
]
0
.
8
8
0
.
8
6
0
.
8
5
0
.
8
6
ML
-
E
d
g
e
E
M
S
o
p
t
i
mi
z
a
t
i
o
n
Fig
u
r
e
6
.
Featu
r
e
co
r
r
elatio
n
h
ea
tm
ap
4
.
2
.
M
o
del
perf
o
rma
nce
ev
a
lua
t
io
n
Fig
u
r
e
7
co
m
p
a
r
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
f
o
u
r
ML
m
o
d
els
,
d
ec
is
io
n
tr
ee
,
r
a
n
d
o
m
f
o
r
e
s
t,
SVM,
an
d
XGBo
o
s
t
—
u
s
in
g
s
tan
d
ar
d
m
etr
ics:
a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F1
s
co
r
e.
T
h
e
XGBo
o
s
t
m
o
d
el
o
u
tp
er
f
o
r
m
s
th
e
o
th
er
s
,
ac
h
ie
v
in
g
th
e
h
ig
h
est
F1
sc
o
r
e
(
0
.
9
8
)
,
in
d
icatin
g
s
u
p
e
r
io
r
o
v
er
all
p
er
f
o
r
m
an
ce
i
n
class
if
y
in
g
en
er
g
y
f
lo
w
p
h
as
es.
W
h
ile
th
e
d
ec
is
io
n
tr
ee
a
nd
r
an
d
o
m
f
o
r
est
m
o
d
els
also
ac
h
iev
ed
p
er
f
ec
t
s
co
r
es
d
u
r
in
g
tr
ain
i
n
g
,
th
eir
p
o
ten
tial
f
o
r
o
v
er
f
itti
n
g
is
a
co
n
ce
r
n
.
T
h
e
SVM
m
o
d
el,
al
th
o
u
g
h
s
lig
h
tly
less
ac
cu
r
ate
(
F1
Sco
r
e:
0
.
9
3
)
,
d
e
m
o
n
s
tr
ated
r
o
b
u
s
tn
ess
in
h
an
d
lin
g
co
m
p
lex
,
n
o
n
lin
ea
r
b
o
u
n
d
ar
ies
in
th
e
d
ata.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
e
v
iab
ilit
y
o
f
XGBo
o
s
t
f
o
r
r
ea
l
-
tim
e
E
MS
d
ep
lo
y
m
en
t
d
u
e
to
its
b
alan
ce
o
f
ac
cu
r
ac
y
an
d
g
e
n
er
aliza
tio
n
.
4
.
3
.
SO
C
beha
v
io
r
a
na
ly
s
is
Fig
u
r
e
8
p
r
esen
ts
a
c
o
m
p
a
r
is
o
n
o
f
th
e
b
atter
y
SOC
v
s
.
tim
e
f
o
r
co
n
v
en
tio
n
al
an
d
ML
-
b
ased
E
MS.
T
h
e
ML
-
b
ased
E
MS,
p
ar
ticu
lar
ly
with
XGBo
o
s
t,
s
h
o
ws
a
s
m
o
o
th
er
an
d
m
o
r
e
c
o
n
tr
o
lled
SOC
p
r
o
f
ile,
in
d
icatin
g
ef
f
icien
t
p
o
wer
all
o
ca
tio
n
ac
r
o
s
s
v
ar
io
u
s
d
r
iv
in
g
p
h
ases
.
T
h
e
co
n
v
en
tio
n
al
E
MS
s
h
o
ws
f
r
eq
u
en
t
f
lu
ctu
atio
n
s
an
d
r
ap
id
SOC
d
r
o
p
s
,
esp
ec
ially
d
u
r
in
g
h
ig
h
a
cc
eler
atio
n
o
r
l
o
ad
p
e
r
io
d
s
.
T
h
is
er
r
atic
b
eh
av
io
r
ca
n
lead
to
in
cr
ea
s
ed
b
atter
y
wea
r
an
d
r
ed
u
ce
d
d
r
iv
in
g
r
a
n
g
e.
I
n
co
n
tr
ast,
th
e
ML
-
b
ased
E
MS
d
em
o
n
s
tr
ates
in
tellig
en
t p
h
ase
s
witch
in
g
,
all
o
win
g
f
o
r
en
er
g
y
r
e
g
en
er
atio
n
an
d
m
o
r
e
s
tab
le
SOC
m
ain
ten
an
ce
.
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
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
e
n
erg
y
ma
n
a
g
eme
n
t sys
tem
fo
r
elec
tr
ic
ve
h
icles w
ith
…
(
K
.
S
.
R
.
V
a
r
a
P
r
a
s
a
d
)
2407
Fig
u
r
e
7
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
Fig
u
r
e
8
.
SOC
v
s
.
tim
e
co
m
p
a
r
is
o
n
4
.
4
.
Dec
is
io
n t
re
e
co
nfusi
o
n m
a
t
rix
Fig
u
r
e
9
illu
s
tr
ates
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
h
e
d
ec
is
io
n
tr
ee
m
o
d
el.
All
en
er
g
y
f
l
o
w
p
h
ases
,
d
is
ch
ar
g
e,
r
eg
en
e
r
atio
n
,
an
d
ch
ar
g
in
g
,
wer
e
co
r
r
ec
tly
class
if
ied
with
o
u
t
an
y
m
is
clas
s
if
i
ca
tio
n
s
.
W
h
ile
th
i
s
s
u
g
g
ests
a
h
ig
h
ly
ac
cu
r
ate
m
o
d
el,
s
u
ch
p
er
f
ec
t
class
if
icati
o
n
o
n
tr
ain
in
g
/tes
t
d
ata
m
ay
in
d
icate
o
v
er
f
itti
n
g
,
wh
er
e
th
e
m
o
d
el
m
em
o
r
izes
r
ath
er
th
an
g
en
er
alize
s
p
atte
r
n
s
.
T
h
is
lim
itatio
n
r
ein
f
o
r
ce
s
th
e
ad
v
an
tag
e
o
f
en
s
em
b
le
m
o
d
els lik
e
XGBo
o
s
t th
at
o
f
f
er
b
etter
g
en
er
aliza
ti
o
n
u
n
d
er
u
n
s
ee
n
d
r
iv
in
g
c
o
n
d
i
tio
n
s
.
4
.
5
.
Vehicle
s
peed
a
nd
a
cc
eler
a
t
io
n t
re
nd
s
Fig
u
r
e
1
0
d
is
p
lay
s
t
h
e
tim
e
-
s
er
ies
p
lo
t
o
f
v
e
h
icle
s
p
ee
d
an
d
ac
ce
ler
atio
n
d
u
r
in
g
s
im
u
lati
o
n
.
Sh
a
r
p
ch
an
g
es
in
ac
ce
ler
ati
o
n
co
r
r
es
p
o
n
d
to
tr
a
n
s
itio
n
s
b
etwe
en
d
i
f
f
er
en
t
e
n
er
g
y
f
lo
w
p
h
ases
,
s
u
ch
as
m
o
v
i
n
g
f
r
o
m
d
is
ch
ar
g
e
to
r
e
g
en
er
atio
n
d
u
r
in
g
d
ec
eler
atio
n
.
T
h
ese
v
ar
iat
io
n
s
u
n
d
er
s
co
r
e
th
e
n
ee
d
f
o
r
a
r
esp
o
n
s
iv
e
E
MS
th
at
ca
n
ad
ju
s
t
in
r
ea
l
tim
e.
T
h
e
ML
-
b
ased
E
MS
d
em
o
n
s
tr
a
ted
tim
ely
class
if
icatio
n
an
d
c
o
n
tr
o
l
d
u
r
in
g
th
ese
tr
an
s
itio
n
s
,
co
n
tr
ib
u
tin
g
to
s
m
o
o
th
er
v
eh
icle
d
y
n
am
ics an
d
i
m
p
r
o
v
e
d
en
e
r
g
y
e
f
f
icien
cy
.
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.
16
,
No
.
4
,
Dec
em
b
er
20
25
:
2400
-
2
4
1
0
2408
Fig
u
r
e
9
.
C
o
n
f
u
s
io
n
m
at
r
i
x
-
d
e
cisi
o
n
tr
ee
Fig
u
r
e
1
0
.
Sp
ee
d
an
d
ac
ce
ler
a
tio
n
o
v
er
tim
e
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
im
p
lem
en
tatio
n
o
f
a
m
ac
h
in
e
l
ea
r
n
in
g
-
b
ased
E
MS
f
o
r
E
Vs,
u
s
in
g
r
ea
l
-
wo
r
ld
elec
tr
ical
p
ar
a
m
eter
s
to
class
if
y
en
er
g
y
o
p
er
atio
n
m
o
d
es.
T
h
e
co
r
e
o
b
jectiv
e
was
to
en
h
a
n
ce
d
ec
is
io
n
-
m
ak
in
g
in
E
V
p
r
o
p
u
ls
io
n
s
y
s
tem
s
th
r
o
u
g
h
i
n
tellig
en
t
m
o
d
el
-
b
ased
class
if
icatio
n
o
f
m
o
to
r
c
o
n
d
itio
n
s
,
ch
ar
g
in
g
,
d
is
ch
ar
g
in
g
,
an
d
r
e
g
en
er
ativ
e
b
r
ak
i
n
g
b
y
lev
er
ag
in
g
in
p
u
t
f
ea
t
u
r
es
s
u
ch
as
b
at
ter
y
s
tate
-
of
-
c
h
ar
g
e
SOC
,
cu
r
r
en
t,
v
o
ltag
e,
p
o
wer
,
an
d
m
o
t
o
r
s
p
ee
d
.
T
h
r
ee
s
u
p
er
v
is
ed
lear
n
in
g
class
if
ier
s
,
d
ec
is
io
n
tr
ee
(
DT
)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
,
an
d
XGBo
o
s
t
,
wer
e
d
ev
elo
p
ed
an
d
ev
al
u
ated
o
n
th
e
s
a
m
e
d
ataset
to
ass
e
s
s
th
eir
p
er
f
o
r
m
an
ce
.
Am
o
n
g
th
e
m
o
d
els,
XGBo
o
s
t
o
u
tp
er
f
o
r
m
ed
o
th
e
r
s
with
an
ac
cu
r
ac
y
o
f
9
9
.
4
%,
p
r
ec
is
io
n
o
f
9
9
.
3
%,
r
ec
all
o
f
9
9
.
5
%,
an
d
F1
-
s
co
r
e
o
f
9
9
.
4
%,
as
r
ef
le
cted
in
its
co
n
f
u
s
io
n
m
atr
ix
s
h
o
win
g
n
ea
r
-
p
e
r
f
ec
t
class
s
ep
ar
atio
n
.
T
h
e
SVM
cla
s
s
if
ier
s
h
o
wed
h
ig
h
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
with
an
ac
cu
r
a
cy
o
f
9
7
.
5
%,
wh
ile
th
e
d
ec
is
io
n
tr
ee
ac
h
ie
v
ed
9
6
.
2
%
ac
cu
r
ac
y
b
u
t
was
m
o
r
e
p
r
o
n
e
to
o
v
er
f
itti
n
g
in
c
o
m
p
lex
b
o
u
n
d
ar
y
ca
s
es.
T
h
e
tr
ain
ed
m
o
d
els
u
s
ed
in
p
u
t
f
ea
t
u
r
es
ex
tr
ac
ted
f
r
o
m
r
ea
l
-
tim
e
E
MS
lo
g
s
,
s
u
ch
as
v
o
ltag
e
(
3
5
0
–
4
0
0
V)
,
cu
r
r
en
t
(
5
0
–
300
A)
,
m
o
to
r
to
r
q
u
e
(
1
0
–
15
Nm
)
,
an
d
s
tate
o
f
c
h
ar
g
e
(
1
0
–
1
0
0
%)
to
p
r
ed
ict
en
er
g
y
f
lo
w
c
o
n
d
itio
n
s
.
T
h
is
f
ea
t
u
r
e
-
r
ic
h
d
ataset
im
p
r
o
v
ed
t
h
e
lear
n
in
g
q
u
ality
an
d
m
o
d
el
r
o
b
u
s
tn
ess
,
esp
ec
ially
f
o
r
XGBo
o
s
t,
d
u
e
to
its
r
eg
u
lar
ized
b
o
o
s
tin
g
ap
p
r
o
ac
h
an
d
h
a
n
d
lin
g
o
f
n
o
n
lin
ea
r
f
ea
tu
r
e
in
ter
ac
tio
n
s
.
I
n
c
o
n
clu
s
io
n
,
m
ac
h
in
e
lear
n
in
g
m
o
d
els
,
p
ar
ticu
lar
ly
XGBo
o
s
t
,
p
r
esen
t
a
p
r
o
m
is
in
g
s
o
lu
tio
n
f
o
r
r
ea
l
-
tim
e,
in
tellig
en
t
E
MS
d
ec
is
io
n
-
m
ak
in
g
in
E
Vs,
lead
in
g
t
o
im
p
r
o
v
e
d
en
er
g
y
ef
f
icien
c
y
,
ex
te
n
d
ed
b
atter
y
life
,
an
d
s
m
o
o
th
e
r
v
eh
icle
o
p
er
atio
n
ac
r
o
s
s
d
iv
er
s
e
d
r
iv
in
g
co
n
d
itio
n
s
.
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
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
e
n
erg
y
ma
n
a
g
eme
n
t sys
tem
fo
r
elec
tr
ic
ve
h
icles w
ith
…
(
K
.
S
.
R
.
V
a
r
a
P
r
a
s
a
d
)
2409
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
s
,
g
r
an
ts
,
o
r
o
th
e
r
s
u
p
p
o
r
t
wer
e
r
ec
eiv
ed
d
u
r
in
g
th
e
p
r
e
p
ar
atio
n
o
f
th
is
m
an
u
s
cr
ip
t.
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,
a
nd
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
K
.
S
.
R
.
Var
a
Pra
s
ad
✓
✓
✓
✓
✓
✓
✓
✓
✓
V
.
Ush
a
R
ed
d
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
ata
av
ailab
ilit
y
is
n
o
t
ap
p
licab
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
al
y
z
ed
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
X
.
Q
i
,
G
.
W
u
,
K
.
B
o
r
i
b
o
o
n
s
o
ms
i
n
,
M
.
J
.
B
a
r
t
h
,
a
n
d
J
.
G
o
n
d
e
r
,
“
D
a
t
a
-
d
r
i
v
e
n
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
–
b
a
s
e
d
r
e
a
l
-
t
i
me
e
n
e
r
g
y
man
a
g
e
me
n
t
s
y
st
e
m
f
o
r
p
l
u
g
-
i
n
h
y
b
r
i
d
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
s
,”
T
r
a
n
sp
o
r
t
a
t
i
o
n
R
e
se
a
rc
h
R
e
c
o
rd
:
J
o
u
r
n
a
l
o
f
t
h
e
T
ra
n
sp
o
rt
a
t
i
o
n
Re
se
a
rc
h
Bo
a
r
d
,
v
o
l
.
2
5
7
2
,
n
o
.
1
,
p
p
.
1
–
8
,
Ja
n
.
2
0
1
6
,
d
o
i
:
1
0
.
3
1
4
1
/
2
5
7
2
-
01
.
[
2
]
H
.
Zh
a
n
g
,
H
.
Li
,
Y
.
H
u
,
K
.
T
.
V
e
n
k
a
t
e
sw
a
r
a
R
a
o
,
C
.
(
C
h
a
r
l
e
s)
X
u
,
a
n
d
S
.
Y
a
n
g
,
“
A
d
v
a
n
c
e
s
i
n
p
r
o
d
u
c
t
i
o
n
o
f
b
i
o
-
b
a
se
d
e
s
t
e
r
f
u
e
l
s
w
i
t
h
h
e
t
e
r
o
g
e
n
e
o
u
s
b
i
f
u
n
c
t
i
o
n
a
l
c
a
t
a
l
y
s
t
s,”
R
e
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
r
g
y
R
e
v
i
e
w
s
,
v
o
l
.
1
1
4
,
p
.
1
0
9
2
9
6
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.
2
0
1
9
.
1
0
9
2
9
6
.
[
3
]
K
.
V
i
n
i
d
a
a
n
d
M
.
C
h
a
c
k
o
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
s
p
e
e
d
c
o
n
t
r
o
l
o
f
se
n
s
o
r
l
e
ss
b
r
u
s
h
l
e
ss
D
C
m
o
t
o
r
d
r
i
v
e
u
s
i
n
g
H
-
i
n
f
i
n
i
t
y
c
o
n
t
r
o
l
l
e
r
w
i
t
h
o
p
t
i
mi
z
e
d
w
e
i
g
h
t
f
i
l
t
e
r
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
P
o
w
e
r
El
e
c
t
ro
n
i
c
s
a
n
d
D
ri
v
e
S
y
s
t
e
m
s
(
I
J
PED
S
)
,
v
o
l
.
1
2
,
n
o
.
3
,
p
.
1
3
7
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
e
d
s.
v
1
2
.
i
3
.
p
p
1
3
7
9
-
1
3
8
9
.
[
4
]
Y
.
L
i
m,
S
.
B
a
e
,
a
n
d
J
.
M
o
o
n
,
“
O
p
t
i
ma
l
c
o
n
t
r
o
l
sc
h
e
me
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
c
h
a
r
g
i
n
g
u
s
i
n
g
c
o
mb
i
n
e
d
m
o
d
e
l
o
f
X
G
B
o
o
s
t
a
n
d
c
u
m
u
l
a
t
i
v
e
p
r
o
s
p
e
c
t
t
h
e
o
r
y
,”
En
e
rg
i
e
s
,
v
o
l
.
1
7
,
n
o
.
2
4
,
p
.
6
4
5
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
7
2
4
6
4
5
7
.
[
5
]
K
.
K
u
mar,
V
.
L.
D
e
v
i
,
A
.
P
r
a
sa
d
,
H
.
R
.
G
a
l
i
,
a
n
d
R
.
T
i
w
a
r
i
,
“
A
n
a
l
y
si
s
o
f
a
f
u
e
l
c
e
l
l
-
f
e
d
B
LD
C
m
o
t
o
r
d
r
i
v
e
w
i
t
h
a
d
o
u
b
l
e
b
o
o
s
t
c
o
n
v
e
r
t
e
r
f
o
r
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
a
p
p
l
i
c
a
t
i
o
n
,
”
i
n
S
m
a
rt
G
ri
d
s
f
o
r
R
e
n
e
w
a
b
l
e
En
e
r
g
y
S
y
s
t
e
m
s,
El
e
c
t
ri
c
V
e
h
i
c
l
e
s
a
n
d
E
n
e
rg
y
S
t
o
r
a
g
e
S
y
s
t
e
m
s,
C
R
C
Pre
ss
,
2
0
2
2
,
p
p
.
5
9
–
7
5
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
3
1
1
1
9
5
-
4.
[
6
]
M
.
H
.
M
u
n
e
e
r
a
n
d
V
.
A
.
H
a
se
e
n
a
,
“
A
n
M
L
-
B
a
s
e
d
F
l
e
e
t
M
a
n
a
g
e
me
n
t
S
y
s
t
e
m
f
o
r
El
e
c
t
r
i
c
V
e
h
i
c
l
e
s,”
i
n
1
0
T
H
S
AE
I
n
d
i
a
I
n
t
e
r
n
a
t
i
o
n
a
l
M
o
b
i
l
i
t
y
C
o
n
f
e
re
n
c
e
,
O
c
t
.
2
0
2
2
.
d
o
i
:
1
0
.
4
2
7
1
/
2
0
2
2
-
28
-
0
3
0
0
.
[
7
]
R
.
T
i
w
a
r
i
,
K
.
K
u
mar,
V
.
L
.
D
e
v
i
,
S
.
V
.
S
u
r
j
i
t
h
S
u
r
y
a
,
a
n
d
N
.
R
.
A
t
y
a
m,
“
Ev
a
l
u
a
t
i
o
n
o
f
t
h
e
M
P
P
T
f
o
r
t
h
e
w
i
n
d
e
n
e
r
g
y
c
o
n
v
e
r
si
o
n
sy
st
e
m’
s
p
e
r
f
o
r
m
a
n
c
e
u
s
i
n
g
A
N
N
a
n
d
A
N
F
I
S
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
2
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
,
C
o
m
p
u
t
i
n
g
a
n
d
I
n
d
u
s
t
ry
4
.
0
,
C
2
I
4
2
0
2
2
,
p
p
.
1
–
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
C
2
I
4
5
6
8
7
6
.
2
0
2
2
.
1
0
0
5
1
4
2
9
.
[
8
]
Y
.
I
.
M
.
Al
-
M
a
sh
h
a
d
a
n
y
,
A
.
K
h
u
d
h
a
i
r
A
b
b
a
s,
a
n
d
S
.
S
a
a
d
o
o
n
A
l
g
b
u
r
i
,
“
M
o
d
e
l
i
n
g
a
n
d
a
n
a
l
y
s
i
s
o
f
b
r
u
s
h
l
e
ss
D
C
m
o
t
o
r
sy
s
t
e
m
b
a
s
e
d
o
n
i
n
t
e
l
l
i
g
e
n
t
c
o
n
t
r
o
l
l
e
r
s,”
B
u
l
l
e
t
i
n
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
6
,
p
p
.
2
9
9
5
–
3
0
0
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
1
i
6
.
4
3
6
5
.
[
9
]
J.
C
h
e
n
,
H
.
S
h
u
,
X
.
T
a
n
g
,
T.
Li
u
,
a
n
d
W
.
W
a
n
g
,
“
D
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
-
b
a
se
d
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
c
o
n
t
r
o
l
o
f
h
y
b
r
i
d
p
o
w
e
r
sy
st
e
m
c
o
mb
i
n
e
d
w
i
t
h
r
o
a
d
r
e
c
o
g
n
i
t
i
o
n
u
n
d
e
r
t
i
me
-
v
a
r
y
i
n
g
e
n
v
i
r
o
n
men
t
,
”
E
n
e
r
g
y
,
v
o
l
.
2
3
9
,
p
.
1
2
2
1
2
3
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
1
.
1
2
2
1
2
3
.
[
1
0
]
X
.
D
a
n
g
,
Y
.
S
h
i
,
a
n
d
H
.
P
e
n
g
,
“
T
o
r
q
u
e
–
f
l
u
x
l
i
n
k
a
g
e
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
a
d
a
p
t
i
v
e
i
n
v
e
r
si
o
n
c
o
n
t
r
o
l
o
f
t
o
r
q
u
e
f
o
r
sw
i
t
c
h
e
d
r
e
l
u
c
t
a
n
c
e
mo
t
o
r
,
”
I
ET
El
e
c
t
ri
c
P
o
w
e
r A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
9
,
p
p
.
1
6
1
2
–
1
6
2
3
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
e
p
a
.
2
0
2
0
.
0
1
0
5
.
[
1
1
]
C
.
L
e
i
,
“
N
e
w
e
n
e
r
g
y
v
e
h
i
c
l
e
b
a
t
t
e
r
y
st
a
t
e
o
f
c
h
a
r
g
e
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
X
G
B
o
o
st
a
l
g
o
r
i
t
h
m
a
n
d
R
F
f
u
si
o
n
,
”
E
n
e
r
g
y
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
7
,
n
o
.
1
,
p
.
1
1
5
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
1
6
2
-
0
2
4
-
0
0
4
2
4
-
1.
[
1
2
]
X
.
Ta
n
g
e
t
a
l
.
,
“
R
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
-
b
a
s
e
d
e
n
e
r
g
y
ma
n
a
g
e
me
n
t
f
o
r
h
y
b
r
i
d
p
o
w
e
r
s
y
s
t
e
ms
:
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
su
r
v
e
y
,
r
e
v
i
e
w
,
a
n
d
p
e
r
s
p
e
c
t
i
v
e
s
,
”
C
h
i
n
e
s
e
J
o
u
r
n
a
l
o
f
Me
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
7
,
n
o
.
1
,
p
.
4
3
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
0
0
3
3
-
0
2
4
-
0
1
0
2
6
-
4.
[
1
3
]
K
.
W
a
n
g
,
R
.
Y
a
n
g
,
Y
.
Z
h
o
u
,
W
.
H
u
a
n
g
,
a
n
d
S
.
Z
h
a
n
g
,
“
D
e
si
g
n
a
n
d
i
m
p
r
o
v
e
m
e
n
t
o
f
S
D
3
-
b
a
se
d
e
n
e
r
g
y
ma
n
a
g
e
men
t
st
r
a
t
e
g
y
f
o
r
a
h
y
b
r
i
d
e
l
e
c
t
r
i
c
u
r
b
a
n
b
u
s
,
”
En
e
r
g
i
e
s
,
v
o
l
.
1
5
,
n
o
.
1
6
,
p
.
5
8
7
8
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
1
6
5
8
7
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.