I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
1
9
2
4
~
1
9
3
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
1
9
2
4
-
1
9
3
2
1924
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Nex
t
-
g
eneratio
n
offloa
ding
using
hy
brid dee
p learnin
g
net
wo
rk
for a
da
ptive mo
bi
le edge com
pu
tin
g
P
.
Anus
ha
,
V.
M
a
ry
Am
a
la
B
a
i
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
N
o
o
r
u
l
I
sl
a
m
C
e
n
t
r
e
f
o
r
H
i
g
h
e
r
E
d
u
c
a
t
i
o
n
,
K
a
n
y
a
k
u
mari
,
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
0
,
2
0
2
4
R
ev
is
ed
Sep
1
9
,
2
0
2
4
Acc
ep
ted
Oct
1
,
2
0
2
4
De
p
lo
y
i
n
g
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
tas
k
s
th
a
t
re
q
u
ire
a
lo
t
o
f
c
o
m
p
u
ti
n
g
a
n
d
a
re
ti
m
e
-
se
n
siti
v
e
to
d
istan
t
c
lo
u
d
-
b
a
se
d
d
a
ta
c
e
n
ters
h
a
s
b
e
c
o
m
e
a
p
o
p
u
lar
m
e
th
o
d
o
f
w
o
rk
i
n
g
a
ro
u
n
d
t
h
e
li
m
it
a
ti
o
n
s
o
f
m
o
b
il
e
d
e
v
ice
s
(M
Ds
).
De
e
p
re
in
fo
rc
e
m
e
n
t
lea
rn
in
g
(DRL)
t
e
c
h
n
iq
u
e
s
fo
r
o
ffl
o
a
d
in
g
in
m
o
b
il
e
e
d
g
e
c
o
m
p
u
ti
n
g
(M
EC)
e
n
v
iro
n
m
e
n
ts
stru
g
g
le
to
a
d
a
p
t
to
n
e
w
sit
u
a
ti
o
n
s
d
u
e
t
o
lo
w
sa
m
p
le
e
fficie
n
c
y
fo
r
e
a
c
h
n
e
w
c
o
n
tex
t.
T
o
a
d
d
re
ss
th
e
se
issu
e
s,
a
n
o
v
e
l
c
o
m
p
u
tati
o
n
a
l
o
ffl
o
a
d
i
n
g
in
m
o
b
il
e
e
d
g
e
c
o
m
p
u
t
in
g
(CO
OL
-
M
EC)
a
lg
o
rit
h
m
h
a
s
b
e
e
n
p
r
o
p
o
se
d
th
a
t
c
o
m
b
in
e
s
th
e
b
e
n
e
fit
s
o
f
a
tt
e
n
ti
o
n
m
o
d
u
le
s
a
n
d
b
i
-
d
irec
ti
o
n
a
l
l
o
n
g
s
h
o
rt
-
term
m
e
m
o
ry
.
Th
is
a
lg
o
rit
h
m
imp
r
o
v
e
s
se
rv
e
r
re
so
u
rc
e
u
ti
li
z
a
ti
o
n
b
y
lo
we
rin
g
t
h
e
c
o
st
o
f
a
ss
imilatin
g
p
ro
c
e
ss
in
g
late
n
c
y
,
p
ro
c
e
ss
in
g
e
n
e
rg
y
c
o
n
s
u
m
p
ti
o
n
,
a
n
d
tas
k
th
ro
u
g
h
p
u
t
o
f
late
n
c
y
-
se
n
siti
v
e
tas
k
s.
Th
e
e
x
p
e
rime
n
t'
s
fi
n
d
in
g
s
sh
o
w
th
a
t,
wh
e
n
u
se
d
a
s
i
n
t
e
n
d
e
d
,
th
e
re
c
o
m
m
e
n
d
e
d
COO
L
-
M
EC
a
lg
o
rit
h
m
m
in
imiz
e
s
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
.
Wh
e
n
c
o
m
p
a
re
d
to
t
h
e
c
u
rre
n
t
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
a
tt
e
n
ti
o
n
re
i
n
fo
rc
e
m
e
n
t
lea
rn
in
g
wi
th
a
d
a
p
ti
v
e
re
wa
rd
p
o
li
c
y
(DCA
RL
-
ARP)
a
n
d
DRL
t
e
c
h
n
iq
u
e
s,
th
e
e
n
e
rg
y
c
o
n
s
u
m
p
ti
o
n
o
f
t
h
e
p
r
o
p
o
se
d
COO
L
-
M
EC
is d
e
c
re
a
se
d
b
y
0
.
0
6
%
a
n
d
0
.
0
8
%
,
r
e
s
p
e
c
t
i
v
e
l
y
.
T
h
e
a
v
e
r
a
g
e
t
i
m
e
p
e
r
c
h
a
n
n
e
l
u
t
i
l
i
z
e
d
f
o
r
t
h
e
e
x
e
c
u
t
i
o
n
o
f
t
h
e
p
r
o
p
o
s
e
d
C
O
O
L
-
M
E
C
a
l
s
o
d
e
c
r
e
a
s
e
d
b
y
0
.
0
5
1
%
a
n
d
0
.
0
5
4
%
w
h
e
n
c
o
m
p
a
r
e
d
w
i
t
h
e
x
i
s
t
i
n
g
D
CA
R
L
-
A
R
P
a
n
d
D
R
L
m
e
t
h
o
d
s
r
e
s
p
e
c
t
i
v
e
l
y
.
K
ey
w
o
r
d
s
:
Av
er
ag
e
en
e
r
g
y
c
o
n
s
u
m
p
tio
n
C
o
m
p
u
tatio
n
o
f
f
lo
ad
in
g
Dee
p
lear
n
in
g
Dee
p
r
ein
f
o
r
ce
m
en
t le
ar
n
in
g
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Mo
b
ile
d
ev
ices
Mo
b
ile
ed
g
e
c
o
m
p
u
tin
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
:
P.
An
u
s
h
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
No
o
r
u
l I
s
lam
C
en
tr
e
f
o
r
Hig
h
e
r
E
d
u
ca
tio
n
Ku
m
ar
ac
o
il,
T
h
u
ck
lay
,
Kan
y
a
k
u
m
ar
i,
T
a
m
il Na
d
u
,
6
2
9
1
8
0
,
I
n
d
ia
E
m
ail: m
ail2
m
ea
n
u
8
2
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
ter
n
et
o
f
th
i
n
g
s
(
I
o
T
)
s
m
ar
t m
o
b
ile
d
ev
ice
(
SMD)
is
a
p
o
wer
f
u
l c
o
m
p
u
tin
g
d
ev
ice
t
h
at
en
ab
les
s
m
ar
t
n
etwo
r
k
in
g
[
1
]
,
[
2
]
.
An
em
er
g
in
g
tech
n
o
lo
g
y
ca
lled
th
e
I
o
T
en
ab
les
r
ea
l
o
b
jects,
in
clu
d
in
g
ca
r
s
an
d
h
o
m
e
ap
p
lian
ce
s
,
to
in
ter
ac
t
an
d
ev
en
co
n
v
er
s
e
with
o
n
e
an
o
th
er
[
3
]
–
[
5
]
.
Simu
ltan
eo
u
s
ly
,
SMDs
ar
e
f
r
eq
u
e
n
tly
u
s
ed
to
im
p
lem
e
n
t
ap
p
licatio
n
s
lik
e
v
ir
tu
al
r
ea
lity
an
d
in
ter
ac
tiv
e
o
n
lin
e
g
a
m
in
g
th
at
d
em
a
n
d
s
u
p
er
co
m
p
u
tin
g
ca
p
ac
ity
,
ex
t
r
em
ely
lo
w
laten
cy
,
an
d
p
er
p
etu
al
ac
ce
s
s
r
ig
h
ts
[
6
]
,
[
7
]
.
On
th
e
o
th
er
h
an
d
,
g
iv
en
th
at
SMDs
ar
e
p
o
r
tab
le,
th
eir
s
m
all
s
ize
r
esu
lt
s
in
h
ig
h
er
en
er
g
y
co
n
s
u
m
p
tio
n
,
lo
we
r
p
r
o
ce
s
s
in
g
p
o
wer
,
an
d
s
m
aller
s
to
r
ag
e
ca
p
ac
ity
[
8
]
.
Ma
n
y
ap
p
s
ar
e
e
x
ce
ed
in
g
ly
d
if
f
ic
u
lt
to
d
ep
lo
y
b
ec
au
s
e
o
f
th
is
SMD
co
n
s
tr
ain
t
[
9
]
.
T
o
o
v
er
co
m
e
th
ese
r
estrictio
n
s
,
S
MD
u
s
e
s
a
wir
eless
n
etwo
r
k
to
co
n
n
ec
t to
a
r
em
o
te
clo
u
d
an
d
m
o
v
es
co
m
p
u
tatio
n
al
f
u
n
ctio
n
s
to
t
h
e
clo
u
d
[
1
0
]
.
Ho
we
v
er
,
m
o
s
t
s
izab
le
d
ata
ce
n
te
r
s
h
o
u
s
in
g
clo
u
d
co
m
p
u
tin
g
r
eso
u
r
ce
s
r
em
o
tely
ar
e
s
itu
ated
at
a
co
n
s
id
er
ab
le
d
is
tan
ce
f
r
o
m
th
e
b
u
lk
o
f
clien
ts
[
1
1
]
.
B
ec
au
s
e
o
f
th
is
,
SMD
will tak
e
lo
n
g
er
to
u
n
lo
ad
a
n
d
c
o
n
s
u
m
e
m
o
r
e
en
e
r
g
y
d
u
r
in
g
th
e
p
r
o
ce
s
s
[
1
2
]
.
Mo
b
il
e
ed
g
e
c
o
m
p
u
ti
n
g
,
o
r
M
E
C
,
h
as b
e
en
d
e
v
el
o
p
e
d
as a
r
ec
e
n
t
s
o
lu
ti
o
n
t
o
th
e
p
r
e
v
i
o
u
s
l
y
d
es
cr
ib
e
d
p
r
o
b
l
em
s
.
E
d
g
e
s
e
r
v
e
r
s
,
f
r
e
q
u
en
t
ly
r
ef
e
r
r
ed
t
o
as
c
o
m
p
u
te
n
o
d
es,
a
r
e
d
is
p
er
s
ed
t
h
r
o
u
g
h
o
u
t
th
e
n
et
wo
r
k
w
h
e
n
u
s
i
n
g
ME
C
[
1
3
]
.
E
d
g
e
s
e
r
v
er
s
ar
e
t
h
u
s
s
it
u
a
te
d
c
lo
s
er
t
o
u
s
e
r
s
t
h
a
n
i
n
d
e
p
e
n
d
e
n
t
cl
o
u
d
s
e
r
v
er
s
an
d
ar
e
c
a
p
a
b
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
N
ex
t
-
g
en
era
tio
n
o
fflo
a
d
in
g
u
s
in
g
h
yb
r
id
d
ee
p
lea
r
n
in
g
n
etw
o
r
k
fo
r
…
(
P
.
A
n
u
s
h
a
)
1925
o
f
p
r
o
ce
s
s
in
g
l
ar
g
er
v
o
l
u
m
es
o
f
d
a
ta
t
h
an
S
MD
s
e
r
v
e
r
s
[
1
4
]
.
M
E
C
'
s
f
ea
t
u
r
es
en
a
b
le
i
t
t
o
o
f
f
e
r
c
o
n
s
u
m
er
s
s
er
v
i
ce
s
wit
h
m
i
n
i
m
a
l
en
er
g
y
u
s
e
a
n
d
q
u
ic
k
r
esp
o
n
s
e
ti
m
es
[
1
5
]
.
E
d
g
e
s
e
r
v
e
r
s
ar
e
ty
p
i
ca
l
l
y
in
s
tall
e
d
at
b
ase
s
tati
o
n
s
(
B
S
)
an
d
a
cc
ess
p
o
i
n
t
s
(
AP)
.
Su
b
s
e
q
u
e
n
t
ly
,
SMDs
will
t
r
a
n
s
f
e
r
t
h
e
co
m
p
u
tat
io
n
al
d
u
t
ies
o
r
ass
o
c
iat
ed
d
at
a
to
t
h
e
APs
.
On
ce
a
t t
h
e
A
Ps
,
t
h
e
ed
g
e
s
er
v
e
r
i
n
s
ta
lle
d
o
n
t
h
e
A
p
s
w
ill
h
a
n
d
le
t
h
e
c
o
m
p
u
ta
ti
o
n
al
j
o
b
s
[
1
6
]
.
A
wid
e
r
an
g
e
o
f
p
r
o
b
lem
s
h
a
v
e
b
ee
n
lear
n
ed
a
n
d
o
p
tim
ized
th
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
d
ee
p
lear
n
in
g
(
DL
)
[
1
7
]
.
Sti
ll,
th
e
m
ajo
r
ity
o
f
DL
tech
n
iq
u
es
n
ee
d
tag
g
e
d
h
is
to
r
ical
d
ata.
Me
an
wh
ile,
a
lar
g
e
q
u
an
tity
o
f
h
u
m
an
lab
o
r
is
n
ee
d
e
d
to
la
b
el
th
e
tr
ain
in
g
d
ata.
R
ein
f
o
r
c
em
en
t
lear
n
in
g
(
R
L
)
o
cc
u
r
s
b
y
in
ter
ac
tio
n
with
ME
C
en
v
ir
o
n
m
en
ts
[
1
8
]
.
C
o
m
p
u
tatio
n
al
o
f
f
lo
ad
in
g
in
m
o
b
ile
ed
g
e
co
m
p
u
tin
g
(
C
OOL
-
ME
C
)
tech
n
iq
u
es
ca
n
b
e
u
s
ed
to
en
ab
le
ef
f
icien
t
task
o
f
f
lo
ad
in
g
,
u
n
m
an
n
ed
ae
r
ial
v
eh
icle
(
UAV
)
co
n
tr
o
l,
a
n
d
r
eso
u
r
ce
allo
ca
tio
n
h
en
ce
r
e
d
u
cin
g
o
v
e
r
all
en
er
g
y
u
s
ag
e.
T
h
e
f
o
llo
win
g
s
u
m
s
u
p
th
is
p
a
p
er
'
s
m
ain
co
n
tr
ib
u
t
io
n
s
:
i)
I
n
itially
th
e
in
p
u
t
task
f
r
o
m
th
e
u
s
er
will
b
e
g
iv
en
t
o
th
e
p
a
r
s
er
th
e
p
a
r
s
er
will
p
ar
s
e
th
e
task
to
th
e
L
o
ca
l
tr
ain
er
an
d
o
f
f
lo
ad
i
n
g
;
ii)
T
h
e
o
f
f
lo
ad
in
g
s
ch
ed
u
ler
u
s
es
d
ee
p
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
f
o
r
p
r
o
v
id
i
n
g
th
e
s
ch
ed
u
le
f
o
r
ex
ec
u
tin
g
th
e
task
;
iii)
T
h
e
o
f
f
lo
ad
in
g
s
ch
ed
u
ler
will
p
r
o
v
id
e
s
ch
ed
u
le
to
th
e
lo
ca
l
ex
e
cu
tio
n
tr
ain
er
will
o
f
f
lo
ad
t
h
e
r
em
o
te
ex
ec
u
tio
n
s
er
v
ice
in
ed
g
e
lev
el
;
a
n
d
iv
)
T
h
e
ef
f
icien
c
y
o
f
t
h
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
i
s
d
em
o
n
s
tr
ated
th
r
o
u
g
h
e
v
alu
atio
n
cr
iter
ia
s
u
ch
as
av
er
ag
e
p
o
wer
co
n
s
u
m
p
tio
n
,
av
e
r
ag
e
d
ata
q
u
eu
e
le
n
g
th
,
a
n
d
p
er
f
o
r
m
an
ce
an
al
y
s
is
.
T
h
e
r
em
ain
in
g
s
ec
tio
n
s
o
f
t
h
e
r
esear
ch
is
ar
r
an
g
e
d
as
f
o
llo
w
s
.
T
h
e
s
ec
tio
n
2
h
o
ld
s
th
e
r
elat
ed
wo
r
k
s
.
Sectio
n
3
h
o
ld
s
th
e
ef
f
ec
tiv
e
t
ask
o
f
f
lo
ad
in
g
s
tr
ateg
y
.
T
h
e
s
i
m
u
latio
n
f
in
d
i
n
g
s
an
d
d
is
cu
s
s
io
n
s
ar
e
d
etailed
in
s
ec
tio
n
4
.
Sectio
n
5
c
o
n
clu
d
es th
e
r
esear
ch
with
f
u
tu
r
e
s
co
p
e
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
Nu
m
er
o
u
s
s
tu
d
ies
h
av
e
d
eleg
ated
th
e
task
s
with
a
r
an
g
e
o
f
tactics
in
r
ec
en
t
y
ea
r
s
.
A
f
ew
o
f
th
e
ex
is
tin
g
ass
ess
m
en
t
m
eth
o
d
s
ar
e
co
v
e
r
ed
i
n
th
e
s
ec
tio
n
th
at
f
o
llo
ws,
alo
n
g
with
s
o
m
e
o
f
th
eir
d
r
aw
b
ac
k
s
.
T
h
ese
ap
p
r
o
ac
h
es
h
av
e
aim
ed
to
im
p
r
o
v
e
e
f
f
icien
cy
,
s
ca
lab
il
ity
,
an
d
ac
cu
r
ac
y
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
.
A
f
ew
o
f
th
e
ex
is
tin
g
ass
ess
m
en
t
m
eth
o
d
s
ar
e
co
v
er
ed
in
th
e
s
ec
tio
n
th
at
f
o
llo
ws,
al
o
n
g
with
s
o
m
e
o
f
th
eir
d
r
awb
ac
k
s
,
an
d
h
ig
h
lig
h
tin
g
th
e
ch
allen
g
es.
Yan
g
[
1
9
]
s
u
g
g
ested
an
o
p
ti
m
izatio
n
p
r
o
b
lem
f
o
r
th
e
wo
r
k
with
th
e
least
av
er
ag
e
co
m
p
letio
n
tim
e
wh
ile
r
eso
u
r
ce
s
ar
e
s
ca
r
ce
.
Simu
latio
n
s
tu
d
ies
ar
e
em
p
lo
y
e
d
to
ev
alu
ate
an
d
co
m
p
ar
e
th
e
ef
f
ec
ts
o
f
d
if
f
e
r
en
t
p
ar
am
eter
s
o
n
task
e
x
ec
u
tio
n
ef
f
icien
cy
.
Simu
latio
n
f
i
n
d
in
g
s
s
h
o
w
th
at
co
m
p
ar
ed
to
e
x
is
tin
g
ap
p
r
o
ac
h
es,
th
e
r
ec
o
m
m
en
d
ed
tech
n
iq
u
e
ca
n
e
f
f
ec
tiv
ely
m
in
im
ize
s
y
s
tem
o
v
er
h
ea
d
an
d
s
h
o
r
te
n
jo
b
e
x
ec
u
ti
o
n
tim
e.
Z
h
an
g
et
a
l.
[
2
0
]
s
u
g
g
ested
th
e
co
m
p
u
tin
g
p
o
wer
an
d
b
atter
y
life
o
f
SMDs
lim
it
th
e
c
o
m
p
u
tatio
n
ally
d
em
an
d
in
g
an
d
d
elay
-
s
en
s
itiv
e
ap
p
licatio
n
s
th
at
ar
e
c
o
n
s
tan
tly
ev
o
l
v
in
g
,
d
esp
ite
b
ei
n
g
s
u
g
g
ested
b
y
n
e
w
co
m
p
u
ter
tech
n
o
lo
g
ies.
T
h
e
e
x
p
er
im
en
tal
r
esu
lts
s
h
o
w
th
at
th
e
d
ee
p
d
eter
m
i
n
is
tic
p
o
licy
g
r
ad
ien
t
(
DDPG
)
-
b
ased
o
f
f
lo
a
d
in
g
tech
n
iq
u
e
ac
h
iev
es
a
lo
n
g
-
ter
m
im
p
r
o
v
em
en
t
o
f
at
least
1
9
%
o
v
er
p
r
ev
i
o
u
s
s
y
s
tem
s
,
wh
ile
s
till
ac
h
iev
in
g
u
ltra
-
lo
w
laten
c
y
,
f
r
eq
u
en
t SMD
s
er
v
er
m
o
v
e
m
en
t,
an
d
e
f
f
icien
t ser
v
er
u
tili
za
tio
n
.
Z
h
an
g
et
a
l.
[
2
1
]
s
u
g
g
ested
a
m
o
b
ile
ap
p
li
ca
tio
n
th
at
p
r
esen
ts
in
ed
g
e
cl
o
u
d
n
etwo
r
k
s
d
u
r
in
g
task
o
f
f
l
o
ad
in
g
a
n
d
r
eso
u
r
ce
allo
ca
tio
n
b
ec
au
s
e
o
f
f
lu
ctu
atin
g
wir
eless
ch
an
n
els,
n
et
wo
r
k
co
n
n
ec
tio
n
wo
r
k
lo
a
d
s
,
an
d
to
m
an
ag
e
u
n
p
r
e
d
ictab
le
r
eso
u
r
ce
av
aila
b
ilit
y
.
T
h
e
o
u
tco
m
es
o
f
th
e
s
im
u
latio
n
co
n
f
ir
m
th
at
th
e
s
u
g
g
ested
r
eso
u
r
ce
s
ch
ed
u
lin
g
an
d
task
o
f
f
lo
ad
in
g
s
tr
ateg
ies o
u
tp
er
f
o
r
m
th
e
b
a
s
elin
e
s
y
s
tem
s
.
E
b
r
ah
im
et
a
l.
[
2
2
]
s
u
g
g
ested
a
d
e
ep
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
(
DR
L
)
b
ased
ap
p
r
o
ac
h
to
e
n
h
an
ce
th
e
ME
C
p
ar
am
eter
o
f
f
lo
ad
i
n
g
p
r
o
ce
d
u
r
e
f
o
r
t
h
e
I
o
T
.
T
h
e
b
est
o
f
f
lo
ad
i
n
g
c
h
o
ice
ca
n
b
e
f
o
u
n
d
u
s
in
g
th
is
tech
n
iq
u
e.
T
h
e
s
im
u
latio
n
'
s
f
in
d
in
g
s
in
d
icate
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
t
p
er
f
o
r
m
s
b
o
th
a
cto
r
-
cr
itic
(
AC
)
an
d
d
ee
p
Q
-
n
etwo
r
k
s
(
DQNs
)
,
in
d
icatin
g
th
at
it
m
ig
h
t
b
e
a
u
s
ef
u
l
to
o
l
f
o
r
lo
we
r
in
g
laten
c
y
a
n
d
en
er
g
y
u
s
ag
e
in
th
e
ME
C
s
y
s
tem
.
Ng
u
y
en
e
t
a
l.
[
2
3
]
s
u
g
g
ested
a
c
o
o
p
er
ativ
e
co
m
p
u
tin
g
ar
ch
itectu
r
e
to
s
h
if
t
o
n
lin
e
co
m
p
u
tatio
n
al
ac
tiv
ities
to
p
ar
k
ed
v
eh
icles
(
PVs
)
in
an
ef
f
icien
t
m
an
n
er
d
u
r
i
n
g
b
u
s
in
ess
h
o
u
r
s
.
W
e
s
u
g
g
est
u
s
in
g
ad
v
an
ce
d
f
ea
tu
r
es
o
f
Ku
b
er
n
etes
-
b
ased
co
n
tain
er
o
r
ch
estra
tio
n
to
en
s
u
r
e
s
er
v
ice
co
n
tin
u
ity
.
Ou
r
p
r
o
p
o
s
ed
co
m
p
u
tin
g
ar
ch
itect
u
r
e
im
p
r
o
v
es
th
e
av
er
a
g
e
wo
r
k
o
f
f
lo
ad
in
g
co
s
t
b
y
at
least
4
0
%
an
d
b
o
o
s
ts
th
e
p
o
ten
tial o
f
ac
ce
p
tin
g
o
n
lin
e
a
s
s
ig
n
m
en
ts
s
ig
n
if
ican
tly
,
ac
co
r
d
in
g
to
ex
ten
s
iv
e
s
im
u
latio
n
r
esu
lts
.
An
u
s
h
a
an
d
B
ai
[
2
4
]
s
u
g
g
ested
a
u
n
iq
u
e
m
eth
o
d
k
n
o
wn
as
d
ee
p
co
n
v
o
l
u
tio
n
al
atten
tio
n
r
ein
f
o
r
ce
m
e
n
t
lear
n
i
n
g
with
ad
ap
tiv
e
r
ewa
r
d
p
o
licy
(
D
C
AR
L
-
A
R
P)
,
wh
ich
co
m
b
in
es
th
e
f
ea
tu
r
e
m
a
p
atten
tio
n
m
ec
h
a
n
is
m
with
d
e
ep
co
n
v
o
lu
tio
n
a
n
d
L
y
ap
u
n
o
v
o
p
tim
izatio
n
.
T
h
e
f
i
n
d
in
g
s
o
f
th
e
ex
p
e
r
im
en
tal
ev
alu
atio
n
s
h
o
w
t
h
at
an
e
f
f
ec
t
iv
e
r
ed
u
ctio
n
o
f
5
0
%
ca
n
b
e
a
ch
iev
ed
in
th
e
av
e
r
ag
e
d
ata
q
u
eu
e
len
g
t
h
an
d
an
ef
f
ec
tiv
e
r
ed
u
ctio
n
o
f
0
.
0
2
%
i
n
th
e
av
er
ag
e
e
x
ec
u
tio
n
e
n
er
g
y
co
n
s
u
m
p
tio
n
.
Gao
et
a
l.
[
2
5
]
s
u
g
g
ested
a
n
o
v
el
tech
n
iq
u
e
th
at
in
te
g
r
ates
th
e
Ma
r
k
o
v
d
ec
is
io
n
p
r
o
b
lem
,
DDPG,
an
d
DR
L
f
o
r
wo
r
k
o
f
f
lo
ad
i
n
g
in
ME
C
.
E
x
p
er
im
en
ts
wer
e
c
o
n
d
u
cted
an
d
th
e
o
u
tco
m
es
s
h
o
w
th
at
,
in
co
m
p
a
r
is
o
n
to
th
e
o
t
h
er
th
r
ee
b
aselin
e
tech
n
iq
u
es,
th
e
r
ec
o
m
m
en
d
e
d
s
tr
ateg
y
ca
n
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
.
B
ec
au
s
e
o
f
its
g
r
ea
t
s
ca
lab
ilit
y
,
ab
ilit
y
to
m
an
ag
e
ex
p
an
s
iv
e
an
d
co
m
p
licated
en
v
ir
o
n
m
en
ts
,
an
d
s
u
itab
ilit
y
f
o
r
p
r
ac
tical
im
p
lem
e
n
tatio
n
,
it
m
ay
b
e
ap
p
lied
to
a
b
r
o
a
d
v
ar
iety
o
f
ta
s
k
o
f
f
lo
ad
i
n
g
an
d
ME
C
ap
p
lic
atio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
9
2
4
-
1
9
3
2
1926
Sev
er
al
d
is
ad
v
an
tag
es
t
o
th
e
jo
b
o
f
f
lo
ad
in
g
s
tr
ateg
ies
m
en
tio
n
ed
ab
o
v
e
in
clu
d
e
h
ig
h
lat
en
cy
,
lo
w
r
eso
u
r
ce
u
tili
za
tio
n
,
en
er
g
y
u
s
e,
an
d
n
etwo
r
k
c
o
n
g
esti
o
n
.
An
in
n
o
v
ativ
e
C
OOl
-
ME
C
ap
p
r
o
ac
h
h
as
b
e
en
p
r
o
p
o
s
ed
an
d
d
escr
ib
ed
to
ad
d
r
ess
th
ese
o
b
s
tacle
s
.
T
h
e
co
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
an
d
ex
i
s
tin
g
m
eth
o
d
s
with
d
em
er
its
an
d
m
er
its
ar
e
s
h
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
ex
is
tin
g
ap
p
r
o
ac
h
with
ad
v
a
n
tag
es
an
d
d
is
ad
v
a
n
tag
es
A
u
t
h
o
r
M
e
t
h
o
d
A
d
v
a
n
t
a
g
e
D
i
sad
v
a
n
t
a
g
e
Y
a
n
g
[
1
9
]
O
p
t
i
mi
z
a
t
i
o
n
p
r
o
b
l
e
m
f
o
r
l
e
a
st
a
v
e
r
a
g
e
c
o
m
p
l
e
t
i
o
n
t
i
me
Th
i
s
a
p
p
r
o
a
c
h
c
a
n
e
f
f
i
c
i
e
n
t
l
y
a
l
l
o
c
a
t
e
c
o
m
p
u
t
i
n
g
t
a
s
k
s
I
n
c
r
e
a
se
d
o
v
e
r
h
e
a
d
i
n
t
a
s
k
a
l
l
o
c
a
t
i
o
n
f
o
r
v
e
h
i
c
l
e
s
Zh
a
n
g
e
t
a
l
.
[
2
0
]
C
o
m
p
u
t
i
n
g
p
o
w
e
r
a
n
d
b
a
t
t
e
r
y
f
o
r
smar
t
m
o
b
i
l
e
d
e
v
i
c
e
s
F
a
st
e
r
p
r
o
c
e
ss
i
n
g
o
f
mu
l
t
i
p
l
e
t
a
s
k
s
I
n
c
r
e
a
se
d
c
o
m
p
l
e
x
i
t
y
Zh
a
n
g
e
t
a
l
.
[
2
1
]
Jo
b
o
f
f
l
o
a
d
i
n
g
i
n
h
y
b
r
i
d
e
d
g
e
-
c
l
o
u
d
n
e
t
w
o
r
k
s
Ef
f
i
c
i
e
n
t
t
a
s
k
o
f
f
l
o
a
d
i
n
g
a
n
d
r
e
s
o
u
r
c
e
sch
e
d
u
l
i
n
g
i
n
h
y
b
r
i
d
e
d
g
e
-
c
l
o
u
d
n
e
t
w
o
r
k
s c
a
n
i
m
p
r
o
v
e
p
e
r
f
o
r
m
a
n
c
e
I
n
c
r
e
a
se
d
n
e
t
w
o
r
k
l
a
t
e
n
c
y
Eb
r
a
h
i
m
e
t
a
l
.
[
2
2
]
O
f
f
l
o
a
d
i
n
g
p
r
o
c
e
d
u
r
e
i
n
M
E
C
b
a
s
e
d
o
n
D
L
R
A
d
a
p
t
t
o
c
o
m
p
l
e
x
,
d
y
n
a
m
i
c
e
n
v
i
r
o
n
m
e
n
t
s f
o
r
e
f
f
i
c
i
e
n
t
r
e
so
u
r
c
e
u
t
i
l
i
z
a
t
i
o
n
I
t
m
a
y
r
e
q
u
i
r
e
l
a
r
g
e
a
m
o
u
n
t
s
o
f
t
r
a
i
n
i
n
g
d
a
t
a
a
n
d
c
o
m
p
u
t
a
t
i
o
n
a
l
r
e
s
o
u
r
c
e
s
f
o
r
UAV
-
a
ssi
st
e
d
M
E
C
N
g
u
y
e
n
e
t
a
l
.
[
2
3
]
C
o
o
p
e
r
a
t
i
v
e
c
o
mp
u
t
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
R
e
d
u
c
i
n
g
t
h
e
w
o
r
k
l
o
a
d
o
n
t
h
e
n
e
t
w
o
r
k
a
n
d
i
mp
r
o
v
i
n
g
e
f
f
i
c
i
e
n
c
y
O
w
n
c
o
m
p
u
t
a
t
i
o
n
a
l
p
o
w
e
r
c
a
n
d
i
sr
u
p
t
t
a
s
k
o
f
f
l
o
a
d
i
n
g
A
n
u
s
h
a
a
n
d
B
a
i
[
2
4
]
D
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
n
d
Ly
a
p
u
n
o
v
o
p
t
i
m
i
z
a
t
i
o
n
Th
i
s
a
p
p
r
o
a
c
h
c
o
m
b
i
n
e
s
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
f
o
r
d
e
c
i
s
i
o
n
-
m
a
k
i
n
g
Th
e
c
o
m
p
l
e
x
n
a
t
u
r
e
o
f
t
h
e
a
p
p
r
o
a
c
h
m
i
g
h
t
l
e
a
d
t
o
h
i
g
h
c
o
m
p
u
t
a
t
i
o
n
a
l
o
v
e
r
h
e
a
d
G
a
o
e
t
a
l
.
[
2
5
]
D
R
L
f
o
r
w
o
r
k
o
f
f
l
o
a
d
i
n
g
i
n
M
E
C
I
t
c
a
n
d
y
n
a
mi
c
a
l
l
y
a
d
a
p
t
t
o
c
h
a
n
g
i
n
g
n
e
t
w
o
r
k
c
o
n
d
i
t
i
o
n
s
c
o
m
p
u
t
a
t
i
o
n
a
l
l
y
e
x
p
e
n
si
v
e
3.
P
RO
P
O
SE
D
CO
M
P
U
T
A
T
I
O
NAL O
F
F
L
O
ADI
NG
I
N
M
O
B
I
L
E
E
DG
E
CO
M
P
U
T
I
NG
T
h
e
s
y
s
t
e
m
r
ec
e
i
v
es
ta
s
k
s
f
r
o
m
u
s
e
r
s
,
w
h
ic
h
c
a
n
b
e
t
r
ai
n
e
d
g
l
o
b
a
l
l
y
o
n
a
d
is
t
a
n
t
s
e
r
v
e
r
o
r
l
o
c
a
l
l
y
o
n
t
h
e
u
s
e
r
'
s
d
e
v
i
c
e
.
W
h
e
t
h
e
r
a
t
as
k
i
s
e
x
e
c
u
t
e
d
l
o
c
a
ll
y
o
n
t
h
e
d
e
v
i
c
e
o
r
r
o
u
t
e
d
t
o
a
c
l
o
u
d
s
e
r
v
e
r
f
o
r
p
r
o
c
e
s
s
i
n
g
i
s
d
e
t
e
r
m
i
n
e
d
b
y
t
h
e
o
f
f
l
o
a
d
s
c
h
e
d
u
l
e
r
.
T
h
i
s
c
h
o
i
ce
t
a
k
es
i
n
t
o
a
c
c
o
u
n
t
v
a
r
i
a
b
l
es
s
u
c
h
as
n
e
tw
o
r
k
l
a
t
e
n
c
y
,
t
as
k
d
i
f
f
i
c
u
l
t
y
,
a
n
d
r
e
s
o
u
r
c
e
a
v
a
i
la
b
i
l
i
t
y
.
V
i
r
t
u
al
m
ac
h
i
n
e
s
a
r
e
u
s
e
d
b
y
t
h
e
cl
o
u
d
s
e
r
v
e
r
to
p
r
o
v
i
d
e
s
e
p
a
r
at
e
e
n
v
i
r
o
n
m
e
n
t
s
f
o
r
t
h
e
e
x
e
c
u
t
i
o
n
o
f
t
a
s
k
s
t
h
at
h
a
v
e
b
e
e
n
o
f
f
lo
a
d
e
d
.
I
n
t
h
e
r
e
a
l
w
o
r
l
d
,
o
f
f
l
o
a
d
i
n
g
c
o
m
p
l
e
x
a
n
d
t
i
m
e
-
s
e
n
s
it
i
v
e
m
o
b
i
l
e
a
p
p
t
as
k
s
t
o
d
i
s
t
a
n
t
c
l
o
u
d
d
a
t
a
c
e
n
te
r
s
is
a
c
o
m
m
o
n
p
r
a
c
t
i
c
e
,
b
u
t
i
t
ca
n
b
e
i
n
e
f
f
i
c
i
e
n
t
d
u
e
t
o
n
e
t
w
o
r
k
l
a
te
n
c
y
.
A
n
e
w
al
g
o
r
i
t
h
m
c
a
l
l
e
d
C
OO
L
-
M
E
C
h
as
b
e
e
n
p
r
o
p
o
s
e
d
t
o
a
d
d
r
e
s
s
t
h
is
b
y
u
s
i
n
g
M
E
C
w
i
t
h
b
e
t
t
e
r
le
a
r
n
i
n
g
t
ec
h
n
i
q
u
e
s
.
T
h
is
c
o
u
l
d
l
e
a
d
t
o
s
i
g
n
i
f
i
c
a
n
t
i
m
p
r
o
v
e
m
e
n
t
s
i
n
b
at
t
e
r
y
l
i
f
e
a
n
d
r
e
s
p
o
n
s
i
v
e
n
e
s
s
f
o
r
m
o
b
i
l
e
a
p
p
s
t
h
at
r
e
l
y
o
n
a
l
o
t
o
f
p
r
o
c
e
s
s
i
n
g
p
o
w
e
r
.
T
h
e
M
E
C
h
o
s
t'
s
n
et
w
o
r
k
,
s
t
o
r
a
g
e
,
a
n
d
p
r
o
c
e
s
s
i
n
g
r
es
o
u
r
c
e
s
a
r
e
p
r
o
v
i
d
e
d
b
y
t
h
e
v
i
r
t
u
al
i
z
ati
o
n
i
n
f
r
a
s
t
r
u
ct
u
r
e
a
n
d
M
E
C
p
la
t
f
o
r
m
c
o
m
b
i
n
e
d
.
W
h
a
t
is
p
r
o
v
i
d
e
d
b
y
t
h
e
M
E
C
p
l
a
t
f
o
r
m
i
s
e
d
g
e
s
e
r
v
i
c
e
s
i
n
a
d
d
i
t
i
o
n
t
o
t
r
a
f
f
i
c
m
a
n
a
g
e
m
e
n
t
,
w
h
i
c
h
i
n
c
l
u
d
e
s
d
o
m
a
i
n
n
a
m
e
p
r
o
c
e
s
s
i
n
g
a
n
d
t
r
a
f
f
i
c
r
u
l
e
c
o
n
t
r
o
l
.
T
h
e
g
l
o
b
a
l
t
r
a
i
n
i
n
g
s
e
r
v
i
c
e
,
l
o
c
a
l
t
r
a
i
n
e
r
,
o
f
f
l
o
a
d
s
c
h
e
d
u
l
e
r
,
a
n
al
y
z
e
r
,
a
n
d
r
e
m
o
t
e
e
x
e
c
u
t
i
o
n
s
e
r
v
i
c
e
a
r
e
t
h
e
f
i
v
e
p
r
i
m
a
r
y
C
O
O
L
-
ME
C
m
o
d
u
l
e
s
.
T
h
e
M
E
C
s
y
s
t
e
m
a
l
l
o
w
s
f
o
r
t
h
e
a
u
t
o
n
o
m
o
u
s
d
e
p
l
o
y
m
e
n
t
o
f
e
a
c
h
o
f
t
h
e
s
e
m
o
d
u
l
es
a
t
t
h
e
u
s
e
r
a
n
d
d
e
v
i
c
e
l
e
v
e
l
s
.
T
h
e
a
r
c
h
i
t
e
ctu
r
e
o
f
t
h
e
r
e
m
o
t
e
c
l
o
u
d
s
e
r
v
e
r
f
o
r
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
i
s
d
e
p
i
ct
e
d
i
n
F
i
g
u
r
e
1
.
3
.
1
.
User
lev
el
T
h
e
p
a
r
s
er
'
s
jo
b
is
to
tr
a
n
s
late
u
s
er
task
s
in
t
o
u
s
er
-
lev
el
d
i
r
ec
ted
ac
y
clic
g
r
a
p
h
s
(
DAGs
)
.
Usi
n
g
a
lo
ca
l
tr
an
s
p
o
r
t
d
ev
ice,
th
e
tr
ai
n
er
u
s
es
th
e
an
aly
ze
d
DAG
as
tr
ain
in
g
d
ata,
d
o
wn
lo
a
d
in
g
an
d
lo
ad
in
g
p
o
licy
n
etwo
r
k
p
ar
am
eter
s
to
an
d
f
r
o
m
th
e
ME
C
s
er
v
e
r
.
T
h
is
k
in
d
o
f
tr
ain
in
g
is
ca
lled
“
in
n
er
lo
o
p
”
tr
ain
i
n
g
.
T
h
e
o
f
f
lo
ad
i
n
g
s
ch
ed
u
ler
will
u
s
e
th
e
tr
ain
ed
p
o
licy
n
etwo
r
k
to
in
f
er
wh
eth
er
to
o
f
f
lo
ad
a
ta
s
k
b
ased
o
n
p
o
licy
n
etwo
r
k
in
f
e
r
en
ce
.
T
h
e
l
o
ca
l
ex
ec
u
to
r
will
f
in
is
h
th
e
lo
ca
lly
s
ch
ed
u
led
task
s
o
n
ce
th
e
D
AG
h
as
d
eter
m
in
ed
o
n
all
o
f
its
ac
tio
n
s
,
an
d
th
e
M
E
C
h
o
s
t w
ill g
et
th
e
o
f
f
lo
ad
e
d
jo
b
s
.
3
.
2
.
O
f
f
lo
a
din
g
s
cheduler
I
n
th
e
p
r
o
p
o
s
ed
s
tu
d
y
,
th
e
m
o
d
el
is
u
tili
ze
d
to
d
ec
id
e
wh
e
n
to
o
f
f
lo
ad
jo
b
s
in
co
n
ju
n
ctio
n
with
th
e
DR
L
m
o
d
el.
T
h
e
m
o
d
el
is
in
ten
d
ed
to
s
im
u
late
a
m
u
lti
-
ter
m
in
al,
m
u
lti
-
ed
g
e
n
etwo
r
k
.
=
{
1
,
2
.
.
.
}
in
d
icate
s
th
at
th
er
e
ar
e
a
n
u
m
b
er
o
f
ter
m
in
al
la
y
er
d
e
v
ices.
T
ask
an
d
co
m
p
u
tatio
n
q
u
eu
es a
r
e
p
r
esen
t o
n
ev
er
y
ter
m
in
al
d
e
v
ice,
also
k
n
o
w
n
as
m
o
b
ile
d
ev
ices
(
MD
)
.
T
h
e
co
m
p
u
tatio
n
q
u
e
u
e
h
a
n
d
les
ac
tiv
ities
th
at
ar
e
p
er
f
o
r
m
ed
l
o
ca
lly
,
wh
e
r
ea
s
t
h
e
task
q
u
eu
e
h
o
ld
s
jo
b
s
th
at
n
ee
d
to
b
e
o
f
f
lo
ad
e
d
.
An
ad
d
itio
n
al
s
et
o
f
ed
g
e
lay
er
s
er
v
er
s
is
d
en
o
ted
by
=
{
1
,
2
.
.
.
}
.
E
ac
h
ed
g
e
s
er
v
er
h
as
m
u
ltip
le
co
m
p
u
tatio
n
q
u
eu
es
th
at
ca
n
b
e
u
s
ed
to
p
ar
allelize
th
e
co
m
p
u
t
atio
n
o
f
task
s
th
at
ar
e
o
f
f
lo
a
d
ed
f
r
o
m
MD
s
.
As
d
ep
icted
in
Fig
u
r
e
2
,
th
e
ed
g
e
s
y
s
tem
is
ca
p
ab
le
o
f
p
r
o
ce
s
s
in
g
d
ata
f
r
o
m
MD
s
an
d
s
to
r
in
g
t
h
e
p
r
o
ce
s
s
ed
r
ec
o
r
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
N
ex
t
-
g
en
era
tio
n
o
fflo
a
d
in
g
u
s
in
g
h
yb
r
id
d
ee
p
lea
r
n
in
g
n
etw
o
r
k
fo
r
…
(
P
.
A
n
u
s
h
a
)
1927
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
f
o
r
th
e
p
r
o
p
o
s
ed
C
OOL
-
MEC
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
f
o
r
task
o
f
f
lo
a
d
in
g
3
.
2
.
1
.
Dee
p
co
nv
o
lutio
n
L
ST
M
a
t
t
ent
io
n r
einf
o
rc
em
ent
l
ea
rning
Dee
p
co
n
v
o
lu
tio
n
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
atten
ti
o
n
r
ei
n
f
o
r
ce
m
en
t
lear
n
in
g
r
e
war
d
-
b
ased
lear
n
in
g
f
o
r
c
o
m
p
le
x
task
s
.
Dee
p
co
n
v
o
lu
tio
n
L
STM
atte
n
tio
n
r
ein
f
o
r
ce
m
en
t
lear
n
i
n
g
is
an
ap
p
r
o
ac
h
t
h
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
9
2
4
-
1
9
3
2
1928
tack
les
s
eq
u
en
tial
d
ec
is
io
n
-
m
ak
in
g
b
y
c
o
m
b
in
i
n
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
l
o
n
g
-
te
r
m
m
em
o
r
y
,
an
d
s
elec
tiv
e
f
o
cu
s
f
o
r
b
etter
p
e
r
f
o
r
m
an
ce
.
Usi
n
g
L
STM
,
th
e
f
ea
tu
r
e
in
f
o
r
m
atio
n
lear
n
ed
b
elo
n
g
s
to
u
p
c
o
m
in
g
task
ca
n
b
e
f
o
r
ec
asted
.
T
h
e
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
d
ec
is
io
n
m
o
d
el,
wh
i
ch
is
in
ten
d
ed
to
cr
ea
te
an
o
f
f
l
o
ad
in
g
s
tr
ateg
y
f
o
r
th
e
an
ticip
ated
task
,
is
th
en
f
e
d
th
is
p
r
o
jecte
d
d
ata.
T
h
e
d
ec
i
s
io
n
to
o
f
f
lo
ad
th
e
jo
b
is
m
ad
e
im
m
ed
iately
wh
e
n
th
e
ac
tu
al
task
is
d
eliv
er
ed
,
p
r
o
v
id
ed
th
at
th
e
d
if
f
er
en
ce
b
et
wee
n
th
e
ac
tu
al
an
d
an
ticip
at
ed
task
s
is
wi
th
in
a
r
ea
s
o
n
ab
le
r
an
g
e.
W
h
en
a
n
er
r
o
r
b
e
y
o
n
d
th
e
p
er
m
itted
r
a
n
g
e,
th
e
ac
tu
al
wo
r
k
em
p
l
o
y
s
th
e
d
ec
is
io
n
m
o
d
el
to
d
eter
m
in
e
th
e
o
u
tco
m
e
.
B
y
u
s
in
g
task
in
f
o
r
m
atio
n
p
r
e
d
ictio
n
,
it
is
p
o
s
s
ib
le
to
p
r
e
d
ict
th
e
co
m
p
u
tatio
n
n
o
d
e
th
at
t
h
e
task
is
aim
in
g
at,
wh
ich
h
elp
s
to
m
in
i
m
ize
th
e
r
esp
o
n
s
e
an
d
waitin
g
d
elay
s
th
at
th
e
task
en
c
o
u
n
ter
s
in
th
e
s
y
s
tem
.
(
)
=
(
∗
[
ℎ
(
−
1
)
,
]
+
)
(
1
)
(
)
=
(
∗
[
ℎ
(
−
1
)
,
]
+
)
(
2
)
(
)
=
ℎ
(
∗
[
ℎ
(
−
1
)
,
]
+
(
3
)
(
)
=
0
∗
(
−
1
)
+
∗
(
4
)
(
)
=
(
∗
)
[
ℎ
(
−
1
)
,
]
+
(
5
)
(
ℎ
)
ℎ
=
∗
ℎ
(
)
(
6
)
T
h
e
s
ig
n
if
ican
t
o
f
t
h
is
p
r
o
p
o
s
ed
m
o
d
el
is
as
f
o
llo
ws,
in
ch
a
n
n
el
atten
tio
n
m
ec
h
an
is
m
in
c
o
r
p
o
r
ati
n
g
b
id
ir
ec
tio
n
al
L
STM
wh
ich
is
th
e
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
.
W
h
en
u
s
in
g
a
b
id
ir
ec
tio
n
al
L
STM
,
in
p
u
t
is
p
r
o
v
id
e
d
in
b
o
th
lef
t
-
to
-
r
ig
h
t
an
d
r
ig
h
t
-
to
-
lef
t
d
ir
ec
tio
n
s
.
H
er
e,
ev
er
y
co
m
p
o
n
e
n
t
o
f
a
n
i
n
p
u
t
s
eq
u
e
n
ce
h
as
in
f
o
r
m
atio
n
f
r
o
m
b
o
th
t
h
e
p
a
s
t
an
d
p
r
esen
t.
I
n
c
o
r
p
o
r
atin
g
d
is
tr
ib
u
ted
co
n
ce
p
t
in
o
b
jecti
v
e
v
alu
es
o
f
b
i
n
ar
y
o
f
f
lo
ad
i
n
g
m
o
d
es
(
m
u
ltip
le
s
u
b
s
et
p
ar
allel
m
o
d
e
wh
ich
r
e
s
u
lted
in
f
ast
a
n
d
o
p
tim
al
r
e
s
o
u
r
ce
allo
ca
tio
n
)
.
B
ased
o
n
th
r
esh
o
ld
v
alu
es
t
h
e
o
b
jectiv
e
v
alu
es
g
et
p
ar
ti
tio
n
an
d
th
er
eb
y
o
p
tim
al
r
eso
u
r
ce
allo
ca
tio
n
is
ac
h
iev
ed
.
T
h
e
a
m
o
u
n
t
o
f
tim
e
allo
ca
ted
f
o
r
o
f
f
lo
ad
in
g
th
e
task
an
d
to
u
tili
ze
th
e
r
eso
u
r
ce
s
is
ef
f
ec
tiv
ely
d
eter
m
in
ed
b
y
th
e
o
p
tim
al
p
ar
am
eter
.
T
h
e
o
p
tim
al
p
ar
a
m
eter
s
elec
tio
n
is
b
ased
o
n
d
u
al
b
in
a
r
y
s
ea
r
c
h
alg
o
r
ith
m
.
So
m
e
tim
e
it
m
ay
tak
e
lo
t
o
f
iter
atio
n
s
d
ep
en
d
s
o
n
th
e
s
ize
o
f
th
e
ac
tiv
e
q
u
eu
e
len
g
th
.
Hen
ce
in
th
is
r
esear
ch
in
s
tead
o
f
ap
p
ly
i
n
g
b
in
ar
y
s
ea
r
c
h
co
n
ce
p
t
,
a
q
u
eu
e
len
g
th
b
ased
eith
er
s
ea
r
c
h
len
g
th
is
d
iv
id
ed
b
y
eith
er
two
o
r
th
r
ee
.
Als
o
,
u
p
p
er
b
o
u
n
d
(
UB
)
co
n
s
id
er
e
d
to
b
e
s
u
f
f
icien
tly
lar
g
e
v
alu
e
an
d
lo
wer
b
o
u
n
d
(
L
B
)
to
b
e
0
.
Her
e
th
e
m
i
d
v
al
u
e
is
d
eter
m
in
ed
b
y
th
e
f
o
llo
w
in
g
co
n
ce
p
t:
(
−
)
/
>
0
.
65
ℎ
−
=
(
(
)
–
(
)
)
/
3
−
=
(
(
)
–
(
)
)
/
2
No
r
m
ally
all
th
e
task
f
r
o
m
t
h
e
q
u
eu
e
is
tr
an
s
f
er
r
e
d
f
o
r
th
e
f
u
r
th
er
p
r
o
ce
s
s
if
it
is
n
o
t
em
p
ty
.
I
n
t
h
is
m
o
d
u
le,
ea
ch
av
ailab
le
task
in
th
e
q
u
e
u
e
is
d
iv
id
ed
b
y
its
m
ax
im
u
m
v
alu
e
to
attain
as
th
e
co
n
tr
ib
u
t
io
n
weig
h
t.
T
h
at
is
m
u
ltip
lied
by
t
h
e
ac
tu
al
d
ata
o
f
th
e
q
u
e
u
e
an
d
tr
an
s
f
o
r
m
ed
to
f
in
d
th
e
o
p
tim
al
s
o
lu
tio
n
.
3
.
3
.
E
dg
e
lev
el
T
h
e
ME
C
p
latf
o
r
m
g
ain
s
n
ew
ca
p
ab
ilit
ies
with
th
e
ad
d
itio
n
o
f
g
lo
b
al
tr
ain
in
g
s
er
v
ices
an
d
r
em
o
te
ex
ec
u
tio
n
s
er
v
ices
m
o
d
u
l
es.
T
h
e
en
tire
in
f
r
astru
ctu
r
e
tr
ain
i
n
g
p
r
o
ce
d
u
r
e
is
ca
r
r
ie
d
o
u
t
d
i
g
itally
o
n
th
e
ME
C
s
er
v
er
,
an
d
th
e
g
lo
b
al
tr
ain
in
g
s
er
v
ice
m
an
ag
es
th
e
tr
an
s
m
is
s
io
n
an
d
r
ec
eiv
in
g
o
f
p
o
licy
n
etwo
r
k
p
ar
am
eter
s
to
an
d
f
r
o
m
th
e
e
n
d
u
s
er
(
E
U)
.
T
h
is
ty
p
e
o
f
tr
ain
in
g
is
r
ef
e
r
r
ed
to
as
“
o
u
ts
id
e
th
e
b
o
x
”
tr
ai
n
in
g
.
T
ask
s
th
at
a
r
e
o
f
f
lo
ad
e
d
f
r
o
m
th
e
u
s
er
e
n
v
ir
o
n
m
en
t
ar
e
m
an
ag
e
d
b
y
th
e
r
em
o
te
ex
ec
u
tio
n
s
er
v
ice,
wh
ic
h
also
ass
ig
n
s
th
em
to
r
elev
an
t v
i
r
tu
al
m
ac
h
in
es a
n
d
r
etu
r
n
s
th
e
r
esu
lts
to
th
e
u
s
er
en
v
ir
o
n
m
en
t.
3
.
4
.
Re
m
o
t
e
le
v
el
R
em
o
te
clo
u
d
s
er
v
er
s
p
r
o
v
id
e
s
ca
lab
le,
o
n
-
d
em
an
d
r
eso
u
r
ce
s
th
at
ar
e
ac
ce
s
s
ib
le
o
v
er
t
h
e
in
ter
n
et,
r
em
o
te
clo
u
d
s
er
v
e
r
s
ar
e
r
ev
o
lu
tio
n
izin
g
co
m
p
u
tin
g
.
B
y
u
s
in
g
th
em
,
b
u
s
in
ess
es
ca
n
s
av
e
a
co
n
s
id
er
ab
le
am
o
u
n
t
o
f
m
o
n
e
y
a
n
d
im
p
r
o
v
e
o
p
er
atio
n
al
ef
f
icien
c
y
b
y
n
o
t
h
a
v
in
g
to
m
a
n
ag
e
an
d
in
v
est
in
p
h
y
s
ical
in
f
r
astru
ctu
r
e.
T
h
ese
s
er
v
e
r
s
e
n
ab
le
co
m
p
an
ies
to
p
r
o
ce
s
s
m
ass
iv
e
am
o
u
n
ts
o
f
d
ata,
q
u
ick
l
y
r
o
ll
o
u
t
ap
p
s
,
an
d
en
ab
le
s
m
o
o
th
team
wo
r
k
b
et
wee
n
g
eo
g
r
a
p
h
ically
s
ca
tter
ed
wo
r
k
er
s
.
All
th
in
g
s
co
n
s
id
er
ed
,
d
is
tan
t
clo
u
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
N
ex
t
-
g
en
era
tio
n
o
fflo
a
d
in
g
u
s
in
g
h
yb
r
id
d
ee
p
lea
r
n
in
g
n
etw
o
r
k
fo
r
…
(
P
.
A
n
u
s
h
a
)
1929
s
er
v
er
s
ar
e
a
v
ital
c
o
m
p
o
n
en
t
o
f
co
n
te
m
p
o
r
a
r
y
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
(
I
T
)
i
n
f
r
as
tr
u
ctu
r
e,
allo
win
g
co
m
p
an
ies to
co
m
p
ete
an
d
d
e
v
elo
p
in
a
co
n
s
tan
tly
ch
a
n
g
in
g
d
ig
ital m
ar
k
et.
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
m
eth
o
d
’
s
ex
p
er
im
en
tal
r
esu
l
ts
ar
e
an
aly
ze
d
in
t
h
is
s
ec
tio
n
.
T
h
e
s
im
u
latio
n
r
esu
lts
in
th
is
s
ec
tio
n
s
h
o
w
h
o
w
s
u
cc
ess
f
u
l
th
e
r
ec
o
m
m
e
n
d
ed
C
OOL
-
ME
C
ap
p
r
o
ac
h
is
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
im
p
lem
en
t
ed
u
s
in
g
th
e
NS2
s
im
u
lato
r
.
T
h
e
ex
p
er
im
en
tal
an
aly
s
is
u
tili
ze
d
to
ev
alu
ate
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
b
ased
m
eth
o
d
is
p
r
esen
ted
in
t
h
e
ac
c
o
m
p
an
y
in
g
T
a
b
le
2
.
T
h
e
s
u
g
g
ested
C
OOL
-
ME
C
m
eth
o
d
p
e
r
f
o
r
m
an
ce
is
co
m
p
ar
ed
with
ex
is
tin
g
DR
L
an
d
DC
AR
L
-
AR
P
r
eg
ar
d
in
g
av
er
a
g
e
p
o
wer
co
n
s
u
m
p
tio
n
,
av
er
a
g
e
d
ata
q
u
eu
e
len
g
th
,
an
d
p
er
f
o
r
m
an
ce
a
n
aly
s
is
.
T
ab
le
2
.
E
n
v
ir
o
n
m
en
tal
s
etu
p
P
a
r
a
me
t
e
r
S
e
t
t
i
n
g
O
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
A
d
a
m
B
a
t
c
h
si
z
e
2
5
6
S
a
mp
l
e
s
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
R
e
c
t
i
f
i
e
d
l
i
n
e
a
r
u
n
i
t
(
R
e
LU
)
S
mo
o
t
h
i
n
g
c
o
e
f
f
i
c
i
e
n
t
0
.
0
0
5
U
p
d
a
t
e
i
n
t
e
r
v
a
l
1
G
r
a
d
i
e
n
t
u
p
d
a
t
e
st
e
p
1
Le
a
r
n
i
n
g
r
a
t
e
3.
10
−
4
D
i
sco
u
n
t
f
a
c
t
o
r
0
.
9
9
9
R
e
p
l
a
y
mem
o
r
y
b
u
f
f
e
r
s
i
z
e
1
0
6
4
.
1
.
Dis
cus
s
io
n
T
h
e
wo
r
k
o
f
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
is
d
is
cu
s
s
ed
in
th
is
s
ec
tio
n
.
T
h
e
C
OOL
-
ME
C
o
f
f
lo
ad
i
n
g
s
ch
ed
u
le
r
is
p
r
o
p
o
s
ed
to
b
e
s
en
t
r
em
o
tely
to
a
r
e
m
o
te
clo
u
d
s
er
v
e
r
o
r
at
th
e
ed
g
e
lev
el
u
s
in
g
a
DL
f
r
am
ewo
r
k
.
I
n
co
m
p
a
r
is
o
n
to
ex
is
tin
g
ap
p
r
o
ac
h
es
s
u
ch
as
DR
L
an
d
DC
AR
L
-
A
R
P,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
is
ass
es
s
ed
r
eg
ar
d
in
g
a
v
er
ag
e
en
er
g
y
co
n
s
u
m
p
tio
n
,
av
er
ag
e
d
ata
q
u
eu
e
len
g
th
,
av
er
a
g
e
tim
e
p
er
ch
an
n
el,
av
er
ag
e
ac
cu
r
ac
y
,
an
d
DL
-
b
ased
p
er
f
o
r
m
an
ce
an
aly
s
is
.
T
h
e
DR
L
ap
p
r
o
ac
h
y
ield
s
av
er
a
g
e
d
ata
q
u
eu
e
len
g
th
s
o
f
6
0
.
6
9
,
3
2
.
3
2
,
an
d
2
0
.
7
8
f
o
r
DC
AR
L
-
AR
P,
C
OOL
-
ME
C
r
esp
ec
tiv
ely
.
I
n
th
is
co
m
p
ar
is
o
n
,
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
ac
h
i
ev
es
a
s
h
o
r
ter
a
v
er
ag
e
m
ea
n
d
ata
q
u
eu
e
len
g
th
o
f
2
0
.
7
8
th
an
o
th
er
ex
is
tin
g
a
p
p
r
o
ac
h
es
wh
ich
is
d
ep
icted
i
n
Fig
u
r
e
3
.
I
n
Fig
u
r
e
4
,
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
o
b
tain
s
less
en
er
g
y
co
n
s
u
m
p
tio
n
u
p
to
0
.
0
1
3
,
c
o
m
p
ar
ed
to
th
e
ex
is
tin
g
ap
p
r
o
ac
h
es
s
u
ch
as
D
R
L
o
f
0
.
0
8
,
an
d
DC
AR
L
-
AR
P
o
f
0
.
0
6
r
esp
ec
tiv
el
y
.
Fig
u
r
es
5
an
d
6
d
e
p
ict
th
e
tr
ain
in
g
ac
cu
r
ac
y
an
d
lo
s
s
o
f
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
e
wo
r
k
.
T
h
e
tr
ain
in
g
lo
s
s
o
f
th
e
C
OOL
-
ME
C
f
r
am
ewo
r
k
is
0
.
1
3
,
wh
ich
is
less
th
an
th
at
o
f
th
e
cu
r
r
en
t
DR
L
an
d
DC
AR
L
-
AR
P
m
o
d
els,
wh
ich
r
ea
ch
tr
ain
in
g
lo
s
s
e
s
o
f
0
.
3
1
an
d
0
.
2
,
r
esp
ec
tiv
ely
.
I
n
Fig
u
r
e
7
,
t
h
e
av
er
a
g
e
tim
e
p
e
r
ch
a
n
n
e
l
f
o
r
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
is
co
m
p
ar
ed
.
wh
er
e
th
e
o
f
f
lo
a
d
in
g
p
r
o
ce
s
s
with
th
e
DR
L
m
eth
o
d
is
ad
d
ed
to
th
e
p
r
o
p
o
s
ed
m
u
lti
-
o
b
jectiv
e
o
p
tim
al
s
ch
ed
u
lin
g
alg
o
r
ith
m
is
also
ev
alu
ated
wi
th
th
e
h
el
p
o
f
a
wo
r
k
f
lo
w
s
im
u
lato
r
with
d
if
f
er
en
t
k
in
d
s
o
f
o
b
jectiv
es
as
well
as
d
if
f
er
en
t
o
f
f
lo
ad
in
g
ty
p
es
o
f
alg
o
r
ith
m
s
.
T
h
e
DL
-
b
ased
p
er
f
o
r
m
a
n
ce
an
aly
s
is
o
f
th
e
ex
is
tin
g
m
eth
o
d
s
s
u
ch
as
c
o
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
,
p
r
o
b
ab
ilis
tic
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
PR
NN)
,
b
id
ir
ec
tio
n
al
g
ated
r
ec
u
r
r
e
n
t
u
n
it
with
C
NN
(
B
i
-
GR
U
-
C
NN)
an
d
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
f
r
am
ewo
r
k
is
p
r
esen
ted
in
Fig
u
r
e
8
.
T
h
e
m
a
x
im
u
m
ac
cu
r
a
cy
attain
ed
b
y
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
is
9
9
.
2
7
%
,
wh
ile
th
e
ex
is
tin
g
C
NN,
s
im
p
le
lo
g
is
tics
,
an
d
d
ee
p
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
DR
NN)
m
o
d
els
o
b
tain
9
8
.
4
%,
9
7
.
2
%,
an
d
9
6
.
5
%.
T
h
e
ef
f
ec
ti
v
en
ess
o
f
m
em
o
r
izin
g
u
s
in
g
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
5
1
.
5
%
an
d
5
2
.
7
%
h
ig
h
er
th
an
th
at
o
f
e
x
is
tin
g
ap
p
r
o
ac
h
es.
Fin
ally
,
th
e
ex
p
e
r
im
en
tal
f
in
d
in
g
s
s
h
o
w
th
at,
w
h
en
u
s
ed
as
in
ten
d
ed
,
t
h
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
alg
o
r
ith
m
m
in
im
izes
en
er
g
y
c
o
n
s
u
m
p
tio
n
,
co
n
tain
s
s
h
o
r
t
d
ata
q
u
eu
e
len
g
th
,
o
b
tain
s
less
tim
e
p
er
ch
an
n
el,
an
d
ac
h
i
ev
es b
etter
ac
cu
r
ac
y
in
ad
a
p
tiv
e
m
o
b
ile
e
d
g
e
co
m
p
u
tin
g
.
4
.
2
.
P
er
f
o
r
m
a
nce
co
m
pa
riso
n
T
h
e
e
f
f
i
c
a
c
y
o
f
t
h
e
s
u
g
g
es
t
e
d
f
r
a
m
e
w
o
r
k
i
s
c
o
n
t
r
as
t
e
d
wi
t
h
D
R
L
a
n
d
DC
AR
L
-
A
R
P
b
y
a
n
a
l
y
z
i
n
g
t
h
e
a
v
e
r
a
g
e
d
a
t
a
q
u
e
u
e
l
e
n
g
t
h
,
av
e
r
a
g
e
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
,
a
v
e
r
a
g
e
a
c
c
u
r
a
c
y
,
a
n
d
a
v
e
r
a
g
e
t
i
m
e
p
e
r
c
h
a
n
n
e
l
.
F
i
g
u
r
e
3
i
l
l
u
s
t
r
at
e
s
t
h
e
c
o
m
p
u
t
a
t
i
o
n
o
f
t
a
s
k
p
e
r
f
o
r
m
a
n
c
e
a
t
v
a
r
i
o
u
s
t
i
m
e
i
n
t
e
r
v
a
ls
f
o
r
e
v
e
r
y
t
a
s
k
i
n
t
h
e
t
a
s
k
q
u
e
u
e
.
T
h
e
p
r
o
p
o
s
e
d
C
O
O
L
-
M
E
C
f
r
a
m
e
w
o
r
k
,
h
o
w
e
v
e
r
,
a
r
e
2
0
.
7
8
t
i
m
e
s
s
h
o
r
t
e
r
t
h
a
n
t
h
e
D
C
AR
L
-
AR
P
a
n
d
D
R
L
,
a
v
e
r
a
g
e
d
a
t
a
q
u
e
u
e
l
e
n
g
th
o
f
3
2
.
3
2
a
n
d
6
0
.
6
9
.
A
s
s
u
m
e
a
n
e
d
g
e
n
o
d
e
h
a
s
N
t
a
s
k
d
a
t
a
q
u
e
u
e
s
.
E
v
e
r
y
q
u
e
u
e
i
s
ass
i
g
n
e
d
t
o
a
ta
s
k
s
t
o
r
e
a
c
c
o
r
d
i
n
g
t
o
t
h
e
p
a
r
t
i
c
u
la
r
t
y
p
es
o
f
ap
p
l
i
c
a
t
i
o
n
s
it
r
e
c
ei
v
e
s
f
r
o
m
v
a
r
i
o
u
s
m
o
b
i
l
e
n
o
d
e
s
.
P
y
t
h
o
n
is
u
s
e
d
t
o
c
o
n
s
t
r
u
c
t
C
OO
L
-
M
E
C
wi
t
h
Ke
r
a
s
;
it
h
as
a
m
e
m
o
r
y
c
a
p
a
c
i
t
y
o
f
1
0
2
4
a
n
d
a
t
r
a
i
n
i
n
g
b
a
t
c
h
s
i
ze
o
f
1
2
8
.
O
n
e
i
s
s
el
e
c
t
e
d
as
t
h
e
in
t
e
r
v
a
l
f
r
a
m
e
.
I
ts
l
e
a
r
n
i
n
g
r
a
t
e
i
s
0
.
0
1
f
o
r
t
h
e
A
d
a
m
o
p
t
i
m
iz
e
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
9
2
4
-
1
9
3
2
1930
C
o
m
p
ar
in
g
th
e
s
u
g
g
ested
C
OOL
-
ME
C
in
Fig
u
r
e
4
t
o
t
h
e
cu
r
r
e
n
t
DR
L
an
d
DC
AR
L
-
AR
P,
o
u
r
m
eth
o
d
r
ed
u
ce
s
C
OOL
-
ME
C
b
y
u
p
to
0
.
0
1
3
,
DC
AR
L
-
AR
P
b
y
u
p
to
0
.
0
6
,
an
d
DR
L
b
y
u
p
to
0
.
0
8
,
as
ca
n
b
e
s
ee
n
.
I
t
also
wo
r
k
s
ef
f
ec
tiv
ely
at
an
y
tim
e
o
f
d
a
y
.
T
h
e
s
u
g
g
ested
m
eth
o
d
'
s
tr
ain
in
g
lo
s
s
a
n
aly
s
is
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
DC
AR
L
-
AR
P
ap
p
r
o
ac
h
h
as
a
tr
ain
in
g
lo
s
s
o
f
0
.
2
in
co
m
p
ar
is
o
n
t
o
th
e
DR
L
tr
ain
in
g
lo
s
s
(
0
.
3
1
)
,
wh
ile
o
u
r
p
r
o
p
o
s
ed
C
OOL
-
ME
C
h
as
a
lo
wer
tr
ain
in
g
lo
s
s
o
f
0
.
1
3
.
I
n
a
d
d
itio
n
,
th
e
s
u
g
g
ested
th
e
C
OOL
-
ME
C
tech
n
iq
u
e
r
ed
u
c
es
th
e
en
tr
o
p
y
lo
s
s
wh
ile
th
e
n
etwo
r
k
is
tr
ain
ed
u
s
in
g
d
ata
s
am
p
les.
Du
r
atio
n
o
f
ea
ch
ch
an
n
el
o
n
a
v
er
ag
e.
I
n
co
m
p
a
r
is
o
n
to
DC
AR
L
-
AR
P
(
0
.
0
5
1
)
a
n
d
DR
L
(
0
.
0
5
4
)
,
th
e
am
o
u
n
t
o
f
Fig
u
r
e
6
u
tili
ze
d
f
o
r
ex
ec
u
tio
n
is
lik
ewise
lo
wer
f
o
r
C
OOL
-
ME
C
(
0
.
0
4
3
)
.
T
h
e
s
u
g
g
ested
m
o
d
el'
s
tr
ain
in
g
tim
e
an
d
ac
cu
r
ac
y
ar
e
im
p
r
o
v
e
d
b
y
u
s
in
g
th
e
p
r
ed
ic
tiv
e
ca
p
ab
ilit
ies
o
f
L
STM
.
T
h
e
s
u
g
g
ested
alg
o
r
ith
m
m
in
i
m
izes
th
e
o
f
f
lo
a
d
in
g
d
ec
is
io
n
laten
cy
f
o
r
jo
b
s
th
at
p
r
ee
m
p
tiv
ely
in
d
icate
th
e
b
est
o
f
f
lo
ad
in
g
ch
o
ices
d
u
r
i
n
g
ac
t
u
al
in
f
er
en
ce
.
I
t
is
im
p
o
r
tan
t
t
o
k
e
ep
i
n
m
in
d
t
h
at
s
im
u
latio
n
a
p
p
r
o
ac
h
es
f
o
r
m
th
e
b
asis
o
f
th
e
e
x
p
er
im
en
tal
r
esu
lts
o
f
th
is
s
tr
ateg
y
in
th
is
s
tu
d
y
.
Fig
u
r
e
3
.
Av
e
r
ag
e
en
er
g
y
co
n
s
u
m
p
tio
n
Fig
u
r
e
4
.
Av
e
r
ag
e
d
ata
q
u
e
u
e
len
g
th
Fig
u
r
e
5
.
T
r
ain
in
g
l
o
s
s
Fig
u
r
e
6
.
Acc
u
r
ac
y
tr
ain
i
n
g
T
h
e
av
er
ag
e
en
e
r
g
y
co
n
s
u
m
p
t
io
n
,
av
er
ag
e
tr
ain
i
n
g
lo
s
s
,
av
er
ag
e
tim
e
p
er
ch
an
n
el,
a
n
d
av
er
ag
e
d
ata
q
u
eu
e
len
g
th
all
s
h
o
w
h
o
w
s
u
cc
ess
f
u
l
an
d
ef
f
icien
t
th
e
s
u
g
g
ested
C
OOL
-
MEC
m
eth
o
d
is
.
T
h
is
o
f
f
lo
ad
in
g
p
r
o
ce
s
s
with
DR
L
m
eth
o
d
is
ad
d
ed
with
th
e
p
r
o
p
o
s
ed
m
u
lt
i
o
b
jectiv
e
o
p
tim
al
s
ch
ed
u
lin
g
alg
o
r
ith
m
is
also
ev
alu
ated
with
th
e
h
elp
o
f
wo
r
k
f
lo
w
s
im
u
lato
r
with
d
if
f
er
e
n
t
k
in
d
s
o
f
o
b
jectiv
es
as
well
a
s
d
if
f
er
en
t
k
in
d
s
o
f
o
f
f
lo
ad
i
n
g
alg
o
r
ith
m
s
.
Av
er
a
g
e
tim
e
p
er
ch
a
n
n
el
is
s
h
o
wn
in
Fig
u
r
e
7
.
An
an
aly
tical
co
m
p
ar
is
o
n
o
f
e
x
is
tin
g
C
NN,
PR
N
N,
an
d
B
i
-
GR
U
-
C
N
N
tech
n
iq
u
es with
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
m
eth
o
d
is
s
h
o
w
n
in
Fig
u
r
e
8
.
T
h
e
m
a
x
im
u
m
ac
cu
r
ac
y
attain
ed
b
y
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
is
9
9
.
2
7
%,
wh
ile
th
e
ex
is
tin
g
C
NN,
s
im
p
le
lo
g
is
tic
s
,
an
d
DR
NN
m
o
d
els
o
b
tain
9
8
.
4
%
,
9
7
.
2
%,
a
n
d
9
6
.
5
%
r
esp
ec
tiv
ely
.
I
n
ter
m
s
o
f
r
ec
o
l
lectio
n
,
th
e
s
u
g
g
ested
m
eth
o
d
p
er
f
o
r
m
s
9
.
4
8
%,
5
.
1
5
%,
an
d
5
2
.
7
%
b
etter
th
a
n
th
e
cu
r
r
e
n
t a
p
p
r
o
ac
h
es.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
h
as
a
m
ax
im
u
m
F
-
m
ea
s
u
r
e
o
f
9
7
.
4
%,
wh
ic
h
is
g
r
ea
te
r
th
an
th
e
m
ax
im
u
m
F
-
m
ea
s
u
r
e
o
f
th
e
ex
is
tin
g
m
eth
o
d
s
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
u
tp
er
f
o
r
m
s
ex
is
tin
g
m
eth
o
d
s
,
ac
co
r
d
in
g
t
o
th
is
co
m
p
ar
is
o
n
.
T
h
e
lim
itatio
n
o
f
th
e
C
OOL
-
ME
C
ap
p
r
o
ac
h
r
eq
u
ir
e
h
ig
h
p
o
wer
.
T
h
is
lim
itatio
n
will b
e
co
n
s
id
er
ed
a
s
a
f
u
tu
r
e
wo
r
k
f
o
r
ex
ten
d
in
g
o
u
r
C
OOL
-
ME
C
s
y
s
tem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
N
ex
t
-
g
en
era
tio
n
o
fflo
a
d
in
g
u
s
in
g
h
yb
r
id
d
ee
p
lea
r
n
in
g
n
etw
o
r
k
fo
r
…
(
P
.
A
n
u
s
h
a
)
1931
Fig
u
r
e
7
.
Av
e
r
ag
e
tim
e
p
er
ch
an
n
el
Fig
u
r
e
8
.
C
o
m
p
a
r
is
o
n
g
r
ap
h
f
o
r
s
u
g
g
ested
a
n
d
ex
is
tin
g
tech
n
iq
u
e
5.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
er
,
a
n
o
v
el
C
OOL
-
ME
C
tech
n
iq
u
e
h
as
b
ee
n
p
r
o
p
o
s
ed
to
o
p
tim
ize
th
e
d
is
tr
i
b
u
tio
n
o
f
task
s
.
T
h
er
e
ar
e
th
r
ee
lev
els
in
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
wh
ich
ar
e
th
e
d
e
v
ice,
r
em
o
te,
an
d
u
s
er
.
I
n
itially
,
th
e
in
p
u
t
task
f
r
o
m
th
e
u
s
e
r
w
ill
b
e
g
iv
en
to
t
h
e
p
ar
s
er
th
e
p
ar
s
er
will
p
ar
s
e
th
e
task
to
th
e
L
o
ca
l
tr
ain
er
a
n
d
o
f
f
lo
ad
i
n
g
.
T
h
e
o
f
f
lo
ad
in
g
s
ch
ed
u
ler
u
s
es
d
ee
p
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
t
o
p
r
o
v
id
e
t
h
e
s
ch
ed
u
le
f
o
r
ex
ec
u
tin
g
th
e
task
.
T
h
e
o
f
f
l
o
ad
in
g
s
ch
e
d
u
ler
will
p
r
o
v
id
e
a
s
ch
ed
u
le
to
th
e
l
o
ca
l
ex
ec
u
tio
n
tr
ai
n
e
r
will
o
f
f
lo
a
d
th
e
r
em
o
te
ex
ec
u
tio
n
s
er
v
ice
at
th
e
ed
g
e
lev
el.
E
v
alu
atio
n
cr
iter
ia
lik
e
av
er
ag
e
d
ata
q
u
eu
e
len
g
th
,
av
er
ag
e
en
e
r
g
y
u
s
ag
e,
p
er
f
o
r
m
a
n
ce
a
n
aly
s
is
,
an
d
p
e
r
f
o
r
m
an
ce
an
aly
s
is
h
av
e
b
ee
n
u
s
ed
to
s
h
o
w
h
o
w
s
u
cc
ess
f
u
l
th
e
p
r
o
p
o
s
e
d
C
OOL
-
ME
C
.
T
h
e
en
er
g
y
co
n
s
u
m
p
tio
n
o
f
t
h
e
C
OOL
-
ME
C
ap
p
r
o
ac
h
is
0
.
0
6
% a
n
d
0
.
0
8
% less
th
an
th
at
o
f
th
e
cu
r
r
en
t
DC
AR
L
-
AR
P
an
d
DR
L
s
y
s
tem
s
,
r
esp
ec
tiv
ely
.
W
h
en
co
m
p
ar
in
g
th
e
p
r
o
p
o
s
ed
C
OOL
-
ME
C
to
th
e
cu
r
r
en
t
DC
AR
L
-
AR
P
an
d
DR
L
tech
n
iq
u
es,
th
e
a
v
er
ag
e
tim
e
p
er
c
h
an
n
el
u
tili
ze
d
f
o
r
e
x
ec
u
tio
n
d
r
o
p
p
ed
b
y
0
.
0
5
1
%
an
d
0
.
0
5
4
%,
r
esp
ec
tiv
ely
.
Fu
tu
r
e
r
esear
ch
en
d
ea
v
o
r
s
will
en
tail
tr
an
s
itio
n
in
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
to
r
ea
l
-
wo
r
ld
ex
p
er
im
e
n
tatio
n
.
O
u
r
f
u
tu
r
e
wo
r
k
is
in
p
r
o
g
r
ess
t
o
id
en
tif
y
a
n
d
o
p
tim
ize
p
ar
am
eter
s
f
o
r
ex
p
e
d
itin
g
co
n
tr
o
l
ac
tio
n
s
in
s
ce
n
ar
io
s
in
v
o
lv
in
g
p
ar
tial
o
f
f
lo
a
d
in
g
,
p
av
in
g
th
e
way
f
o
r
m
o
r
e
ef
f
icien
t
an
d
r
esp
o
n
s
iv
e
s
y
s
tem
s
.
C
OOL
-
ME
C
ac
h
iev
es
lo
wer
en
er
g
y
co
n
s
u
m
p
tio
n
,
ex
p
lo
r
e
if
f
u
r
th
er
r
ed
u
ctio
n
s
ar
e
p
o
s
s
ib
le.
T
h
is
co
u
ld
in
v
o
lv
e
in
v
esti
g
atin
g
d
y
n
am
ic
v
o
ltag
e
a
n
d
f
r
eq
u
e
n
cy
s
ca
lin
g
tech
n
iq
u
es f
o
r
th
e
ME
C
s
er
v
er
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
to
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
an
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
RE
F
E
R
E
NC
E
S
[
1
]
E.
M
u
st
a
f
a
e
t
a
l
.
,
“
Jo
i
n
t
w
i
r
e
l
e
ss
p
o
w
e
r
t
r
a
n
sf
e
r
a
n
d
t
a
sk
o
f
f
l
o
a
d
i
n
g
i
n
mo
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
:
a
s
u
r
v
e
y
,
”
C
l
u
st
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
2
4
2
9
–
2
4
4
8
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
8
6
-
0
2
1
-
0
3
3
7
6
-
3.
[
2
]
J.
B
h
a
r
a
t
h
i
M
a
d
a
v
a
r
a
p
u
,
H
.
I
sl
a
m,
A
.
A
p
p
a
t
h
u
r
a
i
,
G
.
A
.
S
a
f
d
a
r
,
N
.
M
u
t
h
u
k
u
m
a
r
a
n
,
a
n
d
J
.
G
n
a
n
a
ma
l
a
r
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
e
n
e
r
g
y
h
a
r
v
e
st
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
smar
t
h
o
me
I
o
T
a
c
c
e
l
e
r
a
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
7
3
6
6
7
–
7
3
6
7
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
9
7
6
6
4
.
[
3
]
M
.
A
m
a
n
u
l
l
a
k
h
a
n
,
M
.
U
s
h
a
,
a
n
d
S
.
R
a
mes
h
,
“
I
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
a
r
c
h
i
t
e
c
t
u
r
e
(
I
D
A
)
i
n
I
o
T
-
b
a
s
e
d
se
c
u
r
i
t
y
s
y
st
e
m,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
En
g
i
n
e
e
ri
n
g
O
p
t
i
m
i
z
a
t
i
o
n
(
I
J
C
EO
)
,
v
o
l
.
1
,
n
o
.
1
.
[
4
]
S
.
Za
f
a
r
,
N
.
I
f
t
e
k
h
a
r
,
A
.
Y
a
d
a
v
,
A
.
A
h
i
l
a
n
,
S
.
N
.
K
u
mar,
a
n
d
A
.
Je
y
a
m
,
“
A
n
I
o
T
m
e
t
h
o
d
f
o
r
t
e
l
e
me
d
i
c
i
n
e
:
Lo
ss
l
e
ss
me
d
i
c
a
l
i
ma
g
e
c
o
mp
r
e
ssi
o
n
u
si
n
g
l
o
c
a
l
a
d
a
p
t
i
v
e
b
l
o
c
k
s
,
”
I
EEE
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
2
2
,
n
o
.
1
5
,
p
p
.
1
5
3
4
5
–
1
5
3
5
2
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
8
4
4
2
3
.
[
5
]
R
.
R
.
S
a
t
h
i
y
a
,
S
.
R
a
j
a
k
u
mar,
a
n
d
J
.
S
a
t
h
i
a
m
o
o
r
t
h
y
,
“
S
e
c
u
r
e
b
l
o
c
k
c
h
a
i
n
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
a
t
a
t
r
a
n
sm
i
ssi
o
n
i
n
I
o
T
-
e
n
a
b
l
e
d
h
e
a
l
t
h
c
a
r
e
sy
st
e
m,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
En
g
i
n
e
e
ri
n
g
O
p
t
i
m
i
z
a
t
i
o
n
(
I
J
C
EO
)
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
5
–
2
3
,
2
0
2
3
.
[
6
]
Z.
W
a
n
g
,
P
.
L
i
,
S
.
S
h
e
n
,
a
n
d
K
.
Y
a
n
g
,
“
Ta
s
k
o
f
f
l
o
a
d
i
n
g
sc
h
e
d
u
l
i
n
g
i
n
mo
b
i
l
e
e
d
g
e
c
o
mp
u
t
i
n
g
n
e
t
w
o
r
k
s
,
”
P
ro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
8
4
,
p
p
.
3
2
2
–
3
2
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
1
.
0
3
.
0
4
1
.
[
7
]
R
.
K
.
W
a
l
t
e
r
s,
E
.
M
.
G
a
l
e
,
J.
B
a
r
n
o
u
d
,
D
.
R
.
G
l
o
w
a
c
k
i
,
a
n
d
A
.
J.
M
u
l
h
o
l
l
a
n
d
,
“
T
h
e
e
m
e
r
g
i
n
g
p
o
t
e
n
t
i
a
l
o
f
i
n
t
e
r
a
c
t
i
v
e
v
i
r
t
u
a
l
r
e
a
l
i
t
y
i
n
d
r
u
g
d
i
sc
o
v
e
r
y
,
”
Ex
p
e
rt
O
p
i
n
i
o
n
o
n
D
r
u
g
D
i
s
c
o
v
e
r
y
,
v
o
l
.
1
7
,
n
o
.
7
,
p
p
.
6
8
5
–
6
9
8
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
4
6
0
4
4
1
.
2
0
2
2
.
2
0
7
9
6
3
2
.
[
8
]
M
.
Z
h
a
o
e
t
a
l
.
,
“
E
n
e
r
g
y
-
a
w
a
r
e
t
a
sk
o
f
f
l
o
a
d
i
n
g
a
n
d
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
f
o
r
t
i
m
e
-
se
n
si
t
i
v
e
ser
v
i
c
e
s
i
n
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
sy
st
e
ms,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
0
,
n
o
.
1
0
,
p
p
.
1
0
9
2
5
–
1
0
9
4
0
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T
.
2
0
2
1
.
3
1
0
8
5
0
8
.
[
9
]
S
.
Y
a
n
g
,
G
.
L
e
e
,
a
n
d
L
.
H
u
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
d
y
n
a
mi
c
c
o
m
p
u
t
a
t
i
o
n
t
a
s
k
o
f
f
l
o
a
d
i
n
g
f
o
r
m
o
b
i
l
e
e
d
g
e
c
o
mp
u
t
i
n
g
n
e
t
w
o
r
k
s,”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
1
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
1
4
0
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
9
2
4
-
1
9
3
2
1932
[
1
0
]
M
.
T
a
n
g
a
n
d
V
.
W
.
S
.
W
o
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
f
o
r
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
sy
st
e
ms,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
1
,
n
o
.
6
,
p
p
.
1
9
8
5
–
1
9
9
7
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
C
.
2
0
2
0
.
3
0
3
6
8
7
1
.
[
1
1
]
Y
.
Q
i
a
n
,
J
.
X
u
,
S
.
Z
h
u
,
W
.
X
u
,
L.
F
a
n
,
a
n
d
G
.
K
.
K
a
r
a
g
i
a
n
n
i
d
i
s,
“
L
e
a
r
n
i
n
g
t
o
o
p
t
i
mi
z
e
r
e
so
u
r
c
e
a
ss
i
g
n
m
e
n
t
f
o
r
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
mo
b
i
l
e
e
d
g
e
c
o
mp
u
t
i
n
g
,
”
I
E
EE
C
o
m
m
u
n
i
c
a
t
i
o
n
s
L
e
t
t
e
rs
,
v
o
l
.
2
6
,
n
o
.
6
,
p
p
.
1
3
0
3
–
1
3
0
7
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
L
C
O
M
M
.
2
0
2
2
.
3
1
5
9
7
4
2
.
[
1
2
]
C
.
S
u
n
e
t
a
l
.
,
“
Ta
s
k
o
f
f
l
o
a
d
i
n
g
f
o
r
e
n
d
-
e
d
g
e
-
c
l
o
u
d
o
r
c
h
e
st
r
a
t
e
d
c
o
mp
u
t
i
n
g
i
n
mo
b
i
l
e
n
e
t
w
o
r
k
s
,
”
I
n
2
0
2
0
I
EE
E
W
i
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
i
n
g
C
o
n
f
e
re
n
c
e
(
W
C
N
C
)
,
2
0
2
0
,
p
p
.
1
-
6,
d
o
i
:
1
0
.
1
1
0
9
/
W
C
N
C
4
5
6
6
3
.
2
0
2
0
.
9
1
2
0
4
9
6
.
[
1
3
]
A
.
N
a
o
u
r
i
,
H
.
W
u
,
N
.
A
.
N
o
u
r
i
,
S
.
D
h
e
l
i
m,
a
n
d
H
.
N
i
n
g
,
“
A
n
o
v
e
l
f
r
a
m
e
w
o
r
k
f
o
r
m
o
b
i
l
e
-
e
d
g
e
c
o
mp
u
t
i
n
g
b
y
o
p
t
i
m
i
z
i
n
g
t
a
sk
o
f
f
l
o
a
d
i
n
g
,
”
I
E
EE
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
J
o
u
rn
a
l
,
v
o
l
.
8
,
n
o
.
1
6
,
p
p
.
1
3
0
6
5
–
1
3
0
7
6
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
1
.
3
0
6
4
2
2
5
.
[
1
4
]
G
.
Q
u
,
H
.
W
u
,
R
.
Li
,
a
n
d
P
.
J
i
a
o
,
“
D
M
R
O
:
A
d
e
e
p
m
e
t
a
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
t
a
s
k
o
f
f
l
o
a
d
i
n
g
f
r
a
mew
o
r
k
f
o
r
e
d
g
e
-
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
N
e
t
w
o
rk
a
n
d
S
e
r
v
i
c
e
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
3
4
4
8
–
3
4
5
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
M
.
2
0
2
1
.
3
0
8
7
2
5
8
.
[
1
5
]
Z.
Y
u
,
X
.
X
u
,
a
n
d
W
.
Z
h
o
u
,
“
Ta
s
k
o
f
f
l
o
a
d
i
n
g
a
n
d
r
e
so
u
r
c
e
a
l
l
o
c
a
t
i
o
n
st
r
a
t
e
g
y
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
mo
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
1
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
4
2
7
2
1
9
.
[
1
6
]
Z.
H
.
A
b
b
a
s
e
t
a
l
.
,
“
C
o
m
p
u
t
a
t
i
o
n
a
l
o
f
f
l
o
a
d
i
n
g
i
n
mo
b
i
l
e
e
d
g
e
w
i
t
h
c
o
m
p
r
e
h
e
n
si
v
e
a
n
d
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
c
o
st
f
u
n
c
t
i
o
n
:
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
1
0
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
1
0
3
5
2
3
.
[
1
7
]
L.
A
l
e
,
N
.
Z
h
a
n
g
,
X
.
F
a
n
g
,
X
.
C
h
e
n
,
S
.
W
u
,
a
n
d
L.
L
i
,
“
D
e
l
a
y
-
a
w
a
r
e
a
n
d
e
n
e
r
g
y
-
e
f
f
i
c
i
e
n
t
c
o
m
p
u
t
a
t
i
o
n
o
f
f
l
o
a
d
i
n
g
i
n
m
o
b
i
l
e
-
e
d
g
e
c
o
m
p
u
t
i
n
g
u
s
i
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
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
g
n
i
t
i
v
e
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
N
e
t
w
o
r
k
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
8
8
1
–
8
9
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
C
N
.
2
0
2
1
.
3
0
6
6
6
1
9
.
[
1
8
]
X
.
C
h
e
n
g
,
J.
Li
u
,
a
n
d
Z.
J
i
n
,
“
Ef
f
i
c
i
e
n
t
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
c
o
m
p
u
t
a
t
i
o
n
a
l
o
f
f
l
o
a
d
i
n
g
i
n
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
n
e
t
w
o
r
k
s,”
Wi
re
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
2
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
9
7
6
1
4
1
.
[
1
9
]
S
.
Y
a
n
g
,
“
A
t
a
sk
o
f
f
l
o
a
d
i
n
g
s
o
l
u
t
i
o
n
f
o
r
i
n
t
e
r
n
e
t
o
f
v
e
h
i
c
l
e
s
u
s
i
n
g
c
o
m
b
i
n
a
t
i
o
n
a
u
c
t
i
o
n
ma
t
c
h
i
n
g
m
o
d
e
l
b
a
se
d
o
n
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
5
3
2
6
1
–
5
3
2
7
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
8
0
5
6
7
.
[
2
0
]
H
.
Z
h
a
n
g
,
Y
.
Y
a
n
g
,
X
.
H
u
a
n
g
,
C
.
F
a
n
g
,
a
n
d
P
.
Z
h
a
n
g
,
“
U
l
t
r
a
-
l
o
w
l
a
t
e
n
c
y
mu
l
t
i
-
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
m
o
b
i
l
e
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
3
2
5
6
9
–
3
2
5
8
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
6
1
1
0
5
.
[
2
1
]
Q
.
Zh
a
n
g
,
L
.
G
u
i
,
S
.
Z
h
u
,
a
n
d
X
.
La
n
g
,
“
Ta
s
k
o
f
f
l
o
a
d
i
n
g
a
n
d
r
e
so
u
r
c
e
sc
h
e
d
u
l
i
n
g
i
n
h
y
b
r
i
d
e
d
g
e
-
c
l
o
u
d
n
e
t
w
o
r
k
s
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
8
5
3
5
0
–
8
5
3
6
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
8
8
1
2
4
.
[
2
2
]
M
.
A
.
Eb
r
a
h
i
m,
G
.
A
.
E
b
r
a
h
i
m
,
H
.
K
.
M
o
h
a
me
d
,
a
n
d
S
.
O
.
A
b
d
e
l
l
a
t
i
f
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
m
u
l
t
i
-
U
A
V
a
i
d
e
d
m
o
b
i
l
e
e
d
g
e
c
o
mp
u
t
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
0
1
7
1
6
–
1
0
1
7
3
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
0
8
5
8
4
.
[
2
3
]
K
.
N
g
u
y
e
n
,
S
.
D
r
e
w
,
C
.
H
u
a
n
g
,
a
n
d
J.
Zh
o
u
,
“
P
a
r
k
e
d
v
e
h
i
c
l
e
s
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
4
1
5
9
2
–
4
1
6
0
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
6
7
6
4
1
.
[
2
4
]
P
.
A
n
u
s
h
a
a
n
d
V
.
M
.
A
.
B
a
i
,
“
O
n
l
i
n
e
c
o
m
p
u
t
a
t
i
o
n
o
f
f
l
o
a
d
i
n
g
v
i
a
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
f
e
a
t
u
r
e
m
a
p
a
t
t
e
n
t
i
o
n
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
a
n
d
a
d
a
p
t
i
v
e
r
e
w
a
r
d
i
n
g
p
o
l
i
c
y
,
”
Wi
re
l
e
ss N
e
t
w
o
rks
,
v
o
l
.
2
9
,
n
o
.
8
,
p
p
.
3
7
6
9
–
3
7
7
9
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
2
7
6
-
0
2
3
-
0
3
4
3
7
-
y.
[
2
5
]
X
.
G
a
o
,
M
.
C
.
A
n
g
,
a
n
d
S
.
A
.
A
l
t
h
u
b
i
t
i
,
“
D
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
a
n
d
M
a
r
k
o
v
d
e
c
i
s
i
o
n
p
r
o
b
l
e
m fo
r
t
a
s
k
o
f
f
l
o
a
d
i
n
g
i
n
m
o
b
i
l
e
e
d
g
e
c
o
mp
u
t
i
n
g
,
”
J
o
u
r
n
a
l
o
f
G
ri
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
1
,
n
o
.
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
2
3
-
0
2
3
-
0
9
7
0
8
-
4.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
P.
Anu
sha
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
to
wa
r
d
s
h
e
r
P
h
.
D.
d
e
g
re
e
a
t
th
e
No
o
ru
l
Isla
m
Ce
n
tre
fo
r
Hig
h
e
r
E
d
u
c
a
ti
o
n
.
S
h
e
o
b
tai
n
e
d
h
e
r
BCA
a
n
d
M
CA
fro
m
M
a
n
o
n
m
a
n
iam
S
u
n
d
a
ra
n
a
r
Un
iv
e
rsit
y
wit
h
a
fo
c
u
s
o
n
c
o
m
p
u
ter
n
e
tw
o
rk
s.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
p
e
rfo
rm
a
n
c
e
o
p
ti
m
iza
ti
o
n
i
n
wire
les
s
a
n
d
m
o
b
il
e
n
e
two
rk
s,
a
p
p
li
e
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
il
2
m
e
a
n
u
8
2
@g
m
a
il
.
c
o
m
.
V.
Ma
r
y
Am
a
l
a
Ba
i
h
a
d
h
e
r
B.
E
.
fr
o
m
In
stit
u
te
o
f
R
o
a
d
a
n
d
Tran
sp
o
rt
Tec
h
n
o
l
o
g
y
,
Er
o
d
e
a
n
d
M
.
E
fro
m
No
o
ru
l
Isla
m
Co
l
leg
e
o
f
E
n
g
in
e
e
rin
g
,
Ku
m
a
ra
c
o
il
a
n
d
P
h
D
fr
o
m
An
n
a
U
n
iv
e
rsit
y
o
f
T
e
c
h
n
o
l
o
g
y
,
Ti
ru
n
e
lv
e
li
.
S
h
e
h
a
s
e
x
p
e
rien
c
e
s
o
f
wo
r
k
in
g
in
v
a
rio
u
s
E
n
g
in
e
e
rin
g
c
o
ll
e
g
e
s
sin
c
e
1
9
9
9
.
S
h
e
h
a
s
se
v
e
ra
l
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
h
a
d
a
tt
e
n
d
e
d
n
u
m
b
e
r
o
f
se
m
in
a
rs,
wo
r
k
sh
o
p
s
,
c
o
n
fe
re
n
c
e
s
a
n
d
fa
c
u
lt
y
d
e
v
e
l
o
p
m
e
n
t
p
r
o
g
ra
m
s
.
S
h
e
h
a
s
a
lso
o
rg
a
n
ize
d
w
o
rk
s
h
o
p
s
a
n
d
sy
m
p
o
siu
m
s.
C
u
rre
n
tl
y
sh
e
is
wo
rk
in
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
No
o
r
u
l
Isla
m
Ce
n
tre
fo
r
Hig
h
e
r
E
d
u
c
a
ti
o
n
.
S
h
e
is
a
re
c
o
g
n
ize
d
s
u
p
e
rv
is
o
r
f
o
r
g
u
id
in
g
P
h
.
D
.
stu
d
e
n
ts.
Cu
rre
n
t
ly
6
sc
h
o
lars
a
re
p
u
rsu
in
g
re
se
a
rc
h
u
n
d
e
r
h
e
r
su
p
e
rv
isi
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
ry
a
m
a
lab
a
i@n
iu
n
iv
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.