I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
2
8
6
~
1
2
9
9
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
2
8
6
-
1
2
9
9
1286
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Energ
y
-
eff
ici
ent
virtua
l ma
chine
allo
ca
tion usin
g
dire
ctiona
l
a
nd bo
unda
ry
-
a
w
a
re bobca
t
o
ptimi
za
tion
Nida
K
o
us
a
r
G
o
us
e,
G
o
pa
la
K
rish
na
n Cha
nd
ra
s
ek
a
ra
n
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
G
I
TA
M
S
c
h
o
o
l
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
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
Sep
2
2
,
2
0
2
5
R
ev
is
ed
J
an
8
,
2
0
2
6
Acc
ep
ted
J
an
2
5
,
2
0
2
6
Clo
u
d
c
o
m
p
u
ti
n
g
(CC)
h
a
s
g
a
in
e
d
sig
n
if
ica
n
t
trac
ti
o
n
d
u
e
to
i
ts
a
b
il
it
y
t
o
d
e
li
v
e
r
se
rv
ice
s
in
a
sc
a
lab
le
a
n
d
a
d
a
p
tab
le
m
a
n
n
e
r,
c
a
terin
g
to
d
i
v
e
rse
u
se
r
re
q
u
irem
e
n
ts.
Ho
we
v
e
r,
in
v
irt
u
a
li
z
a
ti
o
n
tec
h
n
o
l
o
g
y
,
o
n
e
o
f
th
e
p
rima
ry
c
h
a
ll
e
n
g
e
s
is
m
a
n
a
g
in
g
t
h
e
e
n
e
rg
y
c
o
n
s
u
m
p
ti
o
n
re
q
u
ired
to
m
a
in
ta
in
se
rv
ice
q
u
a
li
t
y
,
a
s
it
d
irec
tl
y
imp
a
c
ts
th
e
o
p
e
ra
ti
o
n
a
l
e
x
p
e
n
se
s
o
f
d
a
ta
c
e
n
ters
.
To
a
d
d
re
ss
th
is
c
h
a
ll
e
n
g
e
,
th
is
re
se
a
rc
h
p
r
o
p
o
se
s
a
d
irec
ti
o
n
a
l
m
o
v
e
m
e
n
t
a
n
d
b
o
u
n
d
a
r
y
-
a
wa
re
stra
teg
y
-
b
a
se
d
b
o
b
c
a
t
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
(DMBABOA
)
fo
r
e
n
e
rg
y
-
e
fficie
n
t
v
ir
tu
a
l
m
a
c
h
in
e
(VM)
a
ll
o
c
a
ti
o
n
a
ime
d
a
t
m
in
imiz
in
g
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
in
c
lo
u
d
e
n
v
iro
n
m
e
n
ts.
Th
e
d
irec
ti
o
n
a
l
se
a
rc
h
a
n
d
b
o
u
n
d
a
ry
-
a
wa
re
c
o
r
re
c
ti
o
n
e
n
h
a
n
c
e
c
o
n
v
e
rg
e
n
c
e
a
n
d
e
n
su
re
fe
a
sib
le
re
so
u
rc
e
d
istri
b
u
ti
o
n
.
Th
i
s
e
n
su
re
s
e
ffe
c
ti
v
e
u
ti
li
z
a
ti
o
n
o
f
r
e
so
u
rc
e
s,
imp
ro
v
e
d
v
irt
u
a
li
z
a
ti
o
n
m
a
n
a
g
e
m
e
n
t,
a
n
d
s
u
b
sta
n
t
ial
e
n
e
rg
y
sa
v
in
g
s.
Th
e
e
x
p
e
rime
n
tal
fin
d
in
g
s
e
sta
b
li
sh
th
a
t
th
e
p
r
o
p
o
se
d
DMBABOA
o
p
ti
m
ize
r
re
a
c
h
e
s
a
m
in
imu
m
e
x
e
c
u
ti
o
n
ti
m
e
o
f
1
3
4
.
4
8
s
wh
e
n
th
e
n
u
m
b
e
r
o
f
VMs
is
e
q
u
a
l
to
1
,
2
0
0
with
2
0
0
u
se
rs,
c
o
m
p
a
re
d
to
e
x
isti
n
g
m
e
th
o
d
s
su
c
h
a
s
th
e
m
e
tah
e
u
risti
c
VM
a
ll
o
c
a
ti
o
n
a
p
p
ro
a
c
h
t
o
p
o
we
r
e
fficie
n
c
y
o
f
s
u
sta
in
a
b
le
c
lo
u
d
e
n
v
ir
o
n
m
e
n
t
(M
V
-
P
E
S
C).
K
ey
w
o
r
d
s
:
B
o
b
ca
t o
p
tim
izatio
n
alg
o
r
ith
m
b
o
u
n
d
ar
y
-
awa
r
e
s
tr
ateg
y
C
lo
u
d
co
m
p
u
tin
g
Dir
ec
tio
n
al
m
o
v
em
e
n
t
E
n
er
g
y
-
ef
f
icien
t v
i
r
tu
al
m
ac
h
in
e
allo
ca
tio
n
Ph
y
s
ical
m
ac
h
in
es
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
:
Nid
a
Ko
u
s
ar
Go
u
s
e
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
GI
T
AM
Sch
o
o
l o
f
T
ec
h
n
o
lo
g
y
B
en
g
alu
r
u
,
I
n
d
ia
E
m
ail: n
k
o
u
s
ar
@
g
itam
.
in
1.
I
NT
RO
D
UCT
I
O
N
C
lo
u
d
co
m
p
u
tin
g
(
C
C
)
h
as
em
er
g
ed
as
a
d
o
m
in
a
n
t
ar
ch
ety
p
e
f
o
r
ef
f
icien
t
d
ata
s
to
r
ag
e
an
d
p
r
o
ce
s
s
in
g
,
o
f
f
er
in
g
e
n
d
-
u
s
e
r
s
o
n
-
d
em
an
d
s
er
v
ices
s
u
p
p
o
r
ted
b
y
v
ir
tu
alize
d
r
eso
u
r
ce
s
[
1
]
.
T
h
r
o
u
g
h
v
ir
tu
aliza
tio
n
,
m
u
ltip
le
v
ir
tu
a
l
m
ac
h
in
es
(
VM
s
)
ca
n
b
e
cr
ea
ted
an
d
ass
ig
n
ed
to
a
p
h
y
s
i
ca
l
m
ac
h
in
e
(
PM)
,
s
ig
n
if
ican
tly
r
e
d
u
cin
g
th
e
c
o
s
t
o
f
ac
q
u
ir
in
g
a
d
d
itio
n
al
s
er
v
er
in
f
r
astru
ctu
r
e
[
2
]
.
V
Ms
p
r
o
v
id
e
b
e
n
ef
its
in
clu
d
in
g
m
o
b
ilit
y
,
ag
ilit
y
,
s
c
alab
ilit
y
,
an
d
elasticity
[
3
]
b
y
v
ir
tu
alizin
g
PM
r
eso
u
r
ce
s
lik
e
s
to
r
ag
e,
C
PU
,
an
d
R
AM
,
an
d
im
p
lem
en
tin
g
u
s
er
task
s
[
4
]
.
T
h
is
m
o
d
el
h
as
tr
a
n
s
f
o
r
m
ed
th
e
d
eliv
er
y
o
f
tech
n
o
lo
g
ical
s
er
v
ices,
en
ab
lin
g
s
er
v
ice
p
r
o
v
id
er
s
to
o
f
f
er
u
s
er
s
a
wid
e
r
a
n
g
e
o
f
f
ac
ilit
ies
[
5
]
.
T
h
ese
s
y
s
tem
s
b
asically
co
n
tain
d
iv
e
r
s
e
ty
p
es
:
in
f
r
astru
ctu
r
e
as
a
s
er
v
ice
(
I
aa
S),
p
latf
o
r
m
as
a
s
er
v
ice
(
PaaS)
,
an
d
s
o
f
twar
e
as
a
s
er
v
ice
(
SaaS)
[
6
]
.
I
n
I
aa
S,
p
r
o
v
id
e
r
s
d
eliv
er
v
ir
tu
alize
d
co
m
p
u
tin
g
r
eso
u
r
ce
s
lik
e
s
er
v
er
s
,
n
etwo
r
k
s
,
an
d
s
to
r
ag
e,
allo
win
g
cu
s
to
m
er
s
to
r
u
n
ap
p
licatio
n
s
o
n
ex
is
tin
g
in
f
r
astru
ctu
r
e
with
o
u
t
p
u
r
ch
as
in
g
h
ar
d
war
e.
PaaS
en
ab
les d
ev
elo
p
e
r
s
to
o
r
g
an
iz
e
an
d
m
ain
tain
ap
p
licatio
n
s
with
o
u
t th
e
n
ee
d
t
o
in
s
tall o
r
o
v
e
r
s
ee
th
e
u
n
d
er
ly
i
n
g
in
f
r
astru
ctu
r
e
[
7
]
,
[
8
]
.
SaaS
p
r
o
v
id
es
s
o
f
twar
e
ac
r
o
s
s
th
e
in
ter
n
et,
en
a
b
lin
g
u
s
er
s
f
o
r
p
er
f
o
r
m
in
g
th
e
d
ev
ice
s
u
s
in
g
a
web
b
r
o
wser
lack
o
f
m
ain
ten
an
ce
o
r
d
ep
l
o
y
m
en
t
r
eq
u
ir
em
e
n
ts
[
9
]
,
[
1
0
]
.
I
n
cl
o
u
d
en
v
ir
o
n
m
en
ts
,
s
er
v
ice
r
eq
u
ests
f
r
o
m
u
s
er
s
a
r
e
h
ig
h
ly
d
y
n
a
m
ic,
m
a
k
in
g
r
es
o
u
r
ce
allo
ca
tio
n
an
o
n
g
o
in
g
c
h
allen
g
e
f
o
r
clo
u
d
s
er
v
ice
p
r
o
v
id
er
s
(
C
SP
s
)
[
1
1
]
.
B
ec
au
s
e
o
f
lim
ited
r
eso
u
r
ce
s
,
C
SP
s
m
u
s
t
m
an
ag
e
allo
ca
tio
n
wh
ile
co
n
s
id
er
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
erg
y
-
efficien
t v
ir
tu
a
l m
a
ch
i
n
e
a
llo
ca
tio
n
u
s
in
g
d
ir
ec
tio
n
a
l a
n
d
b
o
u
n
d
a
r
y
-
a
w
a
r
e
…
(
N
id
a
K
o
u
s
a
r
Go
u
s
e)
1287
m
u
ltip
le
f
ac
to
r
s
s
u
ch
as
s
er
v
ic
e
q
u
ality
,
p
r
icin
g
,
f
ai
r
n
ess
,
p
r
o
f
itab
ilit
y
,
an
d
l
o
ad
b
ala
n
cin
g
[
1
2
]
,
[
1
3
]
.
As
b
o
th
C
SP
s
an
d
co
n
s
u
m
er
s
s
ee
k
to
m
ax
im
ize
th
eir
b
en
ef
its
,
th
is
p
r
o
ce
s
s
b
ec
o
m
es c
o
m
p
lex
[
1
4
]
,
[
1
5
]
.
Po
o
r
r
eso
u
r
ce
m
an
ag
em
en
t
ca
n
lead
to
s
u
b
s
tan
tial
r
eso
u
r
ce
wastag
e,
m
ak
in
g
ef
f
icie
n
t
allo
ca
tio
n
cr
u
cial
f
o
r
en
h
a
n
cin
g
u
tili
za
tio
n
r
ates
an
d
im
p
r
o
v
in
g
p
o
we
r
ef
f
icien
cy
[
1
6
]
.
E
n
er
g
y
-
awa
r
e
VM
allo
ca
tio
n
an
d
m
ig
r
atio
n
p
lay
v
ital
r
o
les
in
b
alan
cin
g
en
er
g
y
c
o
n
s
u
m
p
tio
n
an
d
m
ain
tain
i
n
g
s
er
v
ice
q
u
ality
[
1
7
]
.
Ho
we
v
er
,
ac
h
iev
in
g
b
o
t
h
s
ec
u
r
ity
an
d
en
e
r
g
y
ef
f
icien
c
y
in
C
C
r
em
ain
s
a
s
ig
n
if
ican
t
ch
allen
g
e
[
1
8
]
.
R
ed
u
cin
g
e
n
er
g
y
co
n
s
u
m
p
tio
n
s
u
p
p
o
r
ts
s
u
s
tain
ab
le
c
o
m
p
u
tin
g
an
d
lo
wer
s
t
h
e
o
p
er
atio
n
al
e
x
p
en
s
es
o
f
o
r
g
an
izatio
n
al
d
ata
ce
n
ter
s
[
1
9
]
,
[
2
0
]
.
Sh
ar
m
a
et
a
l.
[
2
1
]
d
ev
el
o
p
ed
a
m
u
ltid
im
en
s
io
n
al
v
ir
tu
al
m
a
ch
in
e
mode
l
(
MD
VM
M)
an
d
a
b
r
an
ch
-
a
n
d
-
p
r
ice
-
ass
is
ted
en
er
g
y
-
ef
f
icien
t
VM
ap
p
r
o
ac
h
at
th
e
d
ata
ce
n
ter
.
T
h
is
b
r
an
ch
-
b
ased
VM
ap
p
r
o
ac
h
m
in
im
izes
en
er
g
y
co
n
s
u
m
p
tio
n
a
n
d
r
eso
u
r
ce
wa
s
tag
e
th
r
o
u
g
h
s
elec
tin
g
th
e
id
ea
l
PM
co
u
n
ts
at
th
e
clo
u
d
d
atac
en
ter
.
Ho
wev
er
,
MD
VM
M
s
tr
u
g
g
led
to
ad
ap
t
to
d
y
n
am
ic
o
r
u
n
p
r
ed
ictab
l
e
wo
r
k
lo
ad
s
in
clo
u
d
en
v
i
r
o
n
m
en
ts
,
lead
in
g
to
s
u
b
o
p
tim
al
m
ig
r
atio
n
,
en
h
a
n
c
ed
o
v
er
h
ea
d
,
a
n
d
s
er
v
ice
lev
el
ag
r
ee
m
en
t
(
SLA
)
v
io
latio
n
s
.
Yao
et
a
l.
[
2
2
]
im
p
lem
en
ted
a
lo
ad
-
b
alan
cin
g
m
ec
h
a
n
is
m
-
d
r
iv
en
v
ir
tu
al
m
ac
h
in
e
co
n
s
o
lid
atio
n
(
L
B
VM
C
)
,
tar
g
eted
to
m
in
im
ize
SLA
v
io
latio
n
s
an
d
en
er
g
y
u
tili
za
tio
n
th
r
o
u
g
h
b
alan
ce
d
m
u
ltid
im
en
s
io
n
al
r
eso
u
r
ce
u
tili
za
tio
n
ac
r
o
s
s
PMs.
Ho
wev
er
,
L
B
V
MC
r
eq
u
ir
es
f
r
eq
u
en
t
VM
m
i
g
r
atio
n
s
to
m
ain
tain
b
ala
n
ce
d
r
eso
u
r
ce
u
tili
za
tio
n
ac
r
o
s
s
PM,
wh
ich
lead
s
to
tem
p
o
r
ar
y
s
er
v
ice
d
is
tr
ib
u
tio
n
.
C
ao
et
a
l.
[
2
3
]
i
n
tr
o
d
u
ce
d
a
s
ec
u
r
e
an
d
en
e
r
g
y
-
ef
f
icien
t
VM
allo
ca
tio
n
m
ec
h
an
is
m
to
p
r
ev
e
n
t
co
-
r
esid
en
ce
attac
k
s
an
d
q
u
a
n
tifie
d
th
r
ee
k
ey
f
ac
to
r
s
:
s
ec
u
r
ity
r
is
k
s
d
u
e
to
co
-
r
esid
en
ce
o
f
VM
s
f
r
o
m
d
if
f
er
en
t
u
s
er
s
,
c
o
m
p
r
e
h
en
s
iv
e
en
er
g
y
c
o
n
s
u
m
p
tio
n
,
an
d
w
o
r
k
lo
ad
in
e
q
u
ality
a
m
o
n
g
P
Ms.
Alth
o
u
g
h
th
ese
o
b
jectiv
es
wer
e
m
in
im
ized
s
im
u
ltan
eo
u
s
ly
,
a
r
a
n
d
o
m
n
u
m
b
er
o
f
VM
f
r
o
m
v
ar
io
u
s
u
s
er
s
r
ea
ch
ed
a
clo
u
d
t
h
at
r
eq
u
ir
ed
a
n
o
p
tim
izatio
n
s
o
l
u
tio
n
to
d
y
n
am
ically
r
elate
to
p
r
ev
io
u
s
allo
ca
tio
n
an
d
u
n
k
n
o
wn
allo
ca
tio
n
r
eq
u
ests
.
Ho
wev
er
,
d
ef
en
d
i
n
g
ag
ain
s
t
co
-
r
esid
en
ce
attac
k
s
led
to
u
n
d
er
u
tili
za
tio
n
o
f
p
h
y
s
ical
r
eso
u
r
ce
s
,
th
er
eb
y
r
ed
u
cin
g
en
er
g
y
co
n
s
u
m
p
tio
n
d
u
e
to
th
e
tr
ad
e
-
o
f
f
b
etwe
en
h
ig
h
er
s
ec
u
r
ity
a
n
d
r
eso
u
r
ce
u
tili
za
tio
n
.
Ma
d
ir
ed
d
y
an
d
R
av
in
d
r
an
ath
[
2
4
]
in
tr
o
d
u
ce
d
d
y
n
am
i
c
v
ir
t
u
al
m
ac
h
in
e
r
elo
ca
tio
n
(
DV
MR)
f
o
r
co
n
f
id
en
tial
d
ata
ce
n
ter
s
t
o
u
n
d
er
s
tan
d
v
ir
t
u
aliza
tio
n
an
d
m
i
n
im
ize
en
e
r
g
y
co
n
s
u
m
p
tio
n
in
C
C
.
DVM
R
s
y
s
tem
g
en
e
r
ated
an
ap
p
r
o
ac
h
f
o
r
PM
lo
ad
co
n
d
itio
n
s
b
y
id
en
tify
in
g
o
v
er
lo
a
d
ed
an
d
u
n
d
er
lo
ad
e
d
PMs to
m
an
ag
e
v
ir
tu
aliza
tio
n
an
d
m
in
im
ize
en
er
g
y
c
o
n
s
u
m
p
tio
n
e
f
f
icien
tly
.
H
o
wev
er
,
f
r
eq
u
en
t
VM
r
elo
ca
tio
n
s
in
tr
o
d
u
ce
s
ig
n
if
ican
t
m
ig
r
atio
n
o
v
er
h
ea
d
,
wh
ic
h
r
ed
u
ce
s
ap
p
licatio
n
p
er
f
o
r
m
a
n
ce
an
d
ca
u
s
es
s
er
v
ice
d
is
tr
ib
u
tio
n
s
,
esp
ec
ially
u
n
d
er
h
ig
h
-
l
o
ad
c
o
n
d
itio
n
s
.
Ajm
er
a
an
d
T
ewa
r
i
[
2
5
]
p
r
o
p
o
s
ed
th
e
g
r
ee
n
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
(
GPSO)
ap
p
r
o
a
ch
f
o
r
VM
allo
ca
tio
n
o
n
en
er
g
y
-
ef
f
icien
t
g
r
ee
n
s
y
s
tem
s
.
T
h
ese
s
y
s
tem
s
,
r
ef
er
r
ed
to
as
g
r
ee
n
p
ar
ticl
es,
ar
e
d
esig
n
ed
to
co
n
s
u
m
e
less
p
o
wer
wh
ile
p
er
f
o
r
m
in
g
a
g
lo
b
al
s
ea
r
ch
to
d
eter
m
in
e
an
o
p
tim
al
VM
s
ch
ed
u
lin
g
p
lan
th
at
m
in
im
izes th
e
n
u
m
b
er
o
f
ac
tiv
e
s
er
v
er
s
.
T
h
is
ap
p
r
o
ac
h
e
f
f
ec
t
iv
ely
r
ed
u
ce
s
o
v
e
r
all
p
o
wer
c
o
n
s
u
m
p
tio
n
i
n
d
ata
ce
n
ter
s
wh
ile
m
ain
tain
in
g
SL
A.
Sin
g
h
et
a
l.
[
2
6
]
p
r
esen
ted
th
e
m
etah
eu
r
is
tic
VM
p
lace
m
en
t
f
r
am
ewo
r
k
f
o
r
p
o
wer
ef
f
icien
cy
i
n
a
s
u
s
tain
a
b
le
clo
u
d
en
v
ir
o
n
m
e
n
t
(
MV
-
P
E
SC
)
.
T
h
is
m
eth
o
d
em
p
lo
y
ed
an
ex
ten
d
ed
f
lo
wer
p
o
llin
atio
n
o
p
tim
izatio
n
ap
p
r
o
ac
h
in
co
r
p
o
r
atin
g
th
e
p
r
in
ci
p
les
o
f
th
e
r
an
d
o
m
f
it
ap
p
r
o
ac
h
alo
n
g
with
th
e
s
tan
d
ar
d
f
lo
wer
p
o
llin
atio
n
o
p
tim
izatio
n
tech
n
iq
u
e
.
An
ef
f
icien
cy
o
f
th
e
f
r
am
ewo
r
k
was
v
alid
ated
u
s
in
g
wo
r
k
lo
ad
t
r
ac
es
f
r
o
m
th
e
Go
o
g
le
clu
s
ter
d
ataset
,
d
em
o
n
s
tr
atin
g
o
p
tim
izatio
n
ca
p
ab
ilit
y
in
r
ea
l
-
wo
r
ld
clo
u
d
en
v
ir
o
n
m
en
ts
.
Swain
et
a
l.
[
2
7
]
im
p
lem
e
n
ted
a
r
eso
u
r
ce
-
p
r
ed
ictio
n
-
ass
is
ted
VM
allo
ca
ti
o
n
s
tr
ateg
y
aim
e
d
at
r
ed
u
cin
g
th
e
en
e
r
g
y
c
o
n
s
u
m
p
t
io
n
wh
er
ea
s
im
p
r
o
v
in
g
s
y
s
tem
co
n
s
is
ten
cy
.
T
h
e
k
ey
co
n
tr
i
b
u
tio
n
p
r
esen
t
ed
in
en
h
an
cin
g
a
f
ee
d
-
f
o
r
w
ar
d
n
e
u
r
al
n
etwo
r
k
(
FF
NN)
th
r
o
u
g
h
a
s
elf
-
a
d
a
p
t
i
v
e
d
i
f
f
e
r
e
n
ti
a
l
e
v
o
l
u
t
i
o
n
a
p
p
r
o
a
c
h
t
h
a
t
c
o
m
b
i
n
es
m
u
l
ti
d
i
m
e
n
s
i
o
n
a
l
le
a
r
n
i
n
g
a
n
d
g
l
o
b
a
l
s
ea
r
c
h
c
a
p
a
b
i
l
i
ti
e
s
.
B
y
a
c
c
u
r
a
t
el
y
f
o
r
e
c
a
s
ti
n
g
f
u
t
u
r
e
r
e
s
o
u
r
c
e
d
e
m
a
n
d
s
,
t
h
is
a
p
p
r
o
a
c
h
e
n
a
b
l
es
p
r
o
a
c
t
i
v
e
a
n
d
f
a
u
l
t
-
t
o
l
e
r
a
n
t
VM
m
a
n
a
g
e
m
e
n
t
,
m
i
n
i
m
i
z
es
f
a
i
l
u
r
e
i
m
p
a
c
t
,
a
n
d
e
n
h
an
c
e
s
p
e
r
f
o
r
m
a
n
c
e
.
M
a
h
m
o
o
d
ab
a
d
i
a
n
d
B
a
y
g
i
[
2
8
]
in
tr
o
d
u
ce
d
an
en
er
g
y
-
e
f
f
ec
tiv
e
v
ir
tu
al
m
ac
h
in
e
p
lace
m
e
n
t
(
VM
P)
tech
n
iq
u
e
u
tili
ze
d
th
e
v
ec
to
r
b
in
p
ac
k
in
g
ap
p
r
o
ac
h
to
r
ed
u
ce
en
e
r
g
y
u
s
ag
e
in
d
atac
en
ter
s
.
T
h
eir
wo
r
k
f
o
cu
s
ed
o
n
a
b
in
p
ac
k
in
g
w
ith
lin
ea
r
u
s
ag
e
co
s
t
(
B
PLUC)
m
o
d
el,
wh
ich
d
escr
ib
ed
f
o
r
b
o
th
f
ix
ed
a
n
d
v
a
r
iab
le
o
p
er
atio
n
al
co
s
ts
,
th
er
e
b
y
a
ch
iev
in
g
o
p
tim
ized
r
eso
u
r
ce
allo
ca
tio
n
with
r
ed
u
c
ed
p
o
wer
co
n
s
u
m
p
tio
n
.
Alth
o
u
g
h
CC
en
ab
les
d
y
n
am
ic
r
eso
u
r
ce
s
h
ar
in
g
,
it
also
ex
p
o
s
es
s
y
s
tem
s
to
co
-
r
esid
en
ce
attac
k
s
,
wh
er
e
m
alicio
u
s
VM
s
ex
p
lo
it
s
h
ar
ed
h
ar
d
war
e
with
tar
g
et
VM
s
.
E
x
is
tin
g
s
o
lu
tio
n
s
,
s
u
ch
as
h
y
p
er
v
is
o
r
co
n
tr
o
ls
an
d
s
id
e
-
c
h
an
n
el
d
ef
en
s
es,
a
r
e
o
f
ten
r
e
s
o
u
r
ce
-
in
ten
s
iv
e
o
r
in
f
lex
ib
le.
Prio
r
VM
allo
ca
tio
n
m
eth
o
d
s
lack
ed
r
ea
l
-
tim
e
ad
ap
tab
ilit
y
,
wo
r
k
lo
ad
b
ala
n
cin
g
,
a
n
d
en
e
r
g
y
ef
f
icien
cy
.
Fig
u
r
e
1
illu
s
tr
at
es
th
e
tax
o
n
o
m
y
o
f
ex
is
tin
g
VM
allo
ca
tio
n
s
tr
ateg
ies,
p
r
o
v
id
in
g
a
clea
r
er
s
y
n
th
esis
o
f
th
e
r
elate
d
wo
r
k
s
.
T
h
e
cr
u
cial
n
o
tes
o
f
th
is
r
esear
ch
ar
e:
an
in
n
o
v
ativ
e
en
er
g
y
-
ef
f
icien
t
an
d
co
n
s
is
ten
t
VM
allo
ca
tio
n
ap
p
r
o
ac
h
n
am
ed
d
ir
ec
tio
n
al
m
o
v
em
en
t
an
d
b
o
u
n
d
a
r
y
-
awa
r
e
s
tr
ateg
y
-
b
ased
b
o
b
ca
t
o
p
ti
m
izatio
n
alg
o
r
ith
m
(
DM
B
AB
OA)
is
p
r
o
p
o
s
ed
f
o
r
clo
u
d
en
v
ir
o
n
m
en
ts
,
en
s
u
r
in
g
o
p
tim
al
p
lace
m
en
t
o
n
en
er
g
y
-
ef
f
icien
t
an
d
co
n
s
is
ten
t
PMs.
T
o
en
s
u
r
e
lo
a
d
b
alan
ce
o
f
d
esti
n
atio
n
PMs
later
to
VM
allo
ca
tio
n
,
th
is
s
tu
d
y
d
esig
n
s
a
VM
allo
ca
tio
n
ap
p
r
o
ac
h
in
ter
m
s
o
f
r
eso
u
r
ce
f
itn
ess
an
d
VM
lo
ad
r
elatio
n
s
h
ip
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
a
p
p
r
o
ac
h
is
v
alid
ated
th
r
o
u
g
h
s
im
u
latio
n
u
s
in
g
th
e
C
lo
u
d
Sim
to
o
lk
it
b
y
co
n
s
id
er
i
n
g
d
i
f
f
er
en
t
p
er
f
o
r
m
an
ce
m
etr
ics.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
2
8
6
-
1
2
9
9
1288
T
h
is
p
ap
er
is
f
o
r
m
atted
as
tr
a
ils
:
s
ec
tio
n
2
s
p
ec
if
ies
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
.
Sectio
n
3
s
ig
n
if
ies
th
e
VM
allo
ca
tio
n
u
s
in
g
t
h
e
b
o
b
ca
t
o
p
tim
izatio
n
alg
o
r
i
th
m
(
B
OA)
.
Sectio
n
4
s
h
o
ws
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
.
Sectio
n
5
g
iv
es th
e
co
n
clu
s
io
n
.
Fig
u
r
e
1
.
T
a
x
o
n
o
m
y
o
f
ex
is
tin
g
VM
allo
ca
tio
n
s
tr
ateg
ies
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
p
r
o
p
o
s
ed
s
ec
u
r
e
VM
allo
ca
tio
n
s
tr
ateg
y
in
d
etail.
I
t
b
eg
i
n
s
with
an
o
v
er
v
iew
o
f
th
e
s
y
s
tem
m
o
d
el
,
d
escr
ib
in
g
t
h
e
co
r
e
c
o
m
p
o
n
e
n
ts
an
d
in
ter
ac
tio
n
s
with
in
th
e
CC
en
v
ir
o
n
m
en
t.
Nex
t,
th
e
co
n
ce
p
t
o
f
e
n
er
g
y
ef
f
icien
cy
is
f
o
r
m
u
lated
as
an
o
p
tim
izatio
n
p
r
o
b
lem
,
d
ef
i
n
in
g
th
e
o
b
jectiv
es
an
d
co
n
s
tr
ain
ts
g
o
v
er
n
i
n
g
th
e
allo
ca
tio
n
p
r
o
ce
s
s
.
Fin
ally
,
th
e
ap
p
licatio
n
o
f
th
e
DM
B
AB
OA
is
p
r
esen
ted
to
ef
f
icien
tly
s
o
lv
e
th
e
f
o
r
m
u
lated
p
r
o
b
lem
w
h
ile
en
s
u
r
in
g
b
o
th
s
ec
u
r
ity
an
d
o
p
tim
al
r
e
s
o
u
r
ce
u
tili
za
tio
n
.
Fig
u
r
e
2
o
u
tlin
es
a
n
o
v
er
all
s
y
s
tem
ar
ch
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
,
r
e
p
r
esen
tin
g
th
e
k
ey
co
m
p
o
n
e
n
ts
f
o
r
en
er
g
y
-
ef
f
icien
t V
M
allo
ca
tio
n
.
Fig
u
r
e
2
.
Ov
e
r
all
s
y
s
tem
ar
ch
i
tectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
2
.
1
.
Sy
s
t
e
m
mo
del
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
m
o
d
el
is
d
esig
n
ed
f
o
r
an
I
aa
S
en
v
ir
o
n
m
en
t,
wh
e
r
e
a
d
ata
ce
n
ter
ty
p
ically
co
m
p
r
is
es
ap
p
licatio
n
co
n
tr
o
l
ler
s
,
clo
u
d
ad
m
in
is
tr
ato
r
s
,
an
d
lo
ca
l
ad
m
in
is
tr
ato
r
s
.
I
n
th
i
s
ar
ch
itectu
r
e,
an
ap
p
licatio
n
co
n
tr
o
ller
m
a
n
ag
es
in
co
m
in
g
u
s
er
r
eq
u
ests
u
s
in
g
b
u
ilt
-
in
s
o
f
twar
e.
A
c
lo
u
d
ad
m
in
is
tr
ato
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
erg
y
-
efficien
t v
ir
tu
a
l m
a
ch
i
n
e
a
llo
ca
tio
n
u
s
in
g
d
ir
ec
tio
n
a
l a
n
d
b
o
u
n
d
a
r
y
-
a
w
a
r
e
…
(
N
id
a
K
o
u
s
a
r
Go
u
s
e)
1289
o
v
er
s
ee
s
clo
u
d
s
er
v
ices
at
th
e
ap
p
licatio
n
p
r
o
g
r
am
m
in
g
in
te
r
f
ac
e
(
API
)
le
v
el,
en
s
u
r
in
g
th
at
u
s
er
r
eq
u
ests
ar
e
d
ir
ec
ted
to
th
e
a
p
p
r
o
p
r
iate
ap
p
licatio
n
.
At
th
e
p
h
y
s
ical
in
f
r
astru
ctu
r
e
lev
el,
a
lo
ca
l
a
d
m
in
is
tr
ato
r
h
an
d
les
th
e
in
ter
n
al
r
eso
u
r
ce
s
o
f
PMs,
ass
ig
n
s
VM
s
to
en
d
u
s
er
s
,
an
d
e
x
ec
u
tes
th
eir
task
s
.
As
a
p
r
o
g
r
am
s
u
p
er
v
is
o
r
,
th
e
lo
ca
l
ad
m
in
is
tr
ato
r
d
eter
m
in
e
s
wh
eth
er
a
n
ew
VM
r
eq
u
es
t
ca
n
b
e
f
u
lf
illed
wh
ile
a
d
h
e
r
in
g
to
q
u
ality
o
f
s
er
v
ic
e
(
Qo
S)
r
eq
u
ir
em
en
ts
.
T
h
e
clo
u
d
m
an
a
g
er
u
tili
ze
s
in
f
o
r
m
atio
n
f
r
o
m
th
e
lo
ca
l
m
an
ag
er
to
co
o
r
d
in
ate
an
d
m
a
n
ag
e
VM
m
ig
r
atio
n
b
etwe
en
p
h
y
s
ical
h
o
s
ts
.
T
h
is
in
clu
d
es
d
ec
id
in
g
wh
eth
er
to
r
el
o
ca
te
a
VM
,
e
n
ab
le
v
ir
tu
aliza
tio
n
f
ea
tu
r
es,
o
r
u
s
e
s
to
r
ag
e
d
r
iv
es
f
o
r
VM
o
p
er
atio
n
s
.
T
h
e
lo
ca
l
m
an
ag
er
is
r
esp
o
n
s
ib
le
f
o
r
co
n
tin
u
o
u
s
m
ain
ten
an
ce
o
f
e
ac
h
VM
o
n
e
v
er
y
h
o
s
t
an
d
m
a
n
ag
es
th
e
allo
ca
tio
n
o
f
p
h
y
s
ical
r
eso
u
r
ce
s
am
o
n
g
th
em
.
Her
e,
th
e
B
OA
is
in
tr
o
d
u
ce
d
f
o
r
ac
h
iev
in
g
th
e
en
er
g
y
-
ef
f
icien
t
a
n
d
s
ec
u
r
e
VM
allo
ca
tio
n
.
T
h
e
m
o
d
el
r
e
p
r
esen
ts
a
v
ir
tu
al
d
ata
ce
n
ter
co
n
tain
in
g
m
u
ltip
le
clo
u
d
clien
ts
co
n
s
is
tin
g
o
f
N
p
h
y
s
ical
n
o
d
es
an
d
a
n
ass
o
ciate
d
lis
t
o
f
PMs,
ex
p
r
ess
ed
as:
=
{
1
,
2
,
…
,
}
.
E
ac
h
PM
is
h
o
m
o
g
e
n
eo
u
s
an
d
co
n
s
is
ts
o
f
VM
s
,
r
ep
r
esen
ted
as:
=
{
1
,
2
,
…
,
}
.
VM
s
ar
e
d
y
n
am
ically
a
llo
ca
ted
to
m
in
im
ize
en
er
g
y
co
n
s
u
m
p
tio
n
,
an
d
th
ei
r
r
eso
u
r
ce
d
em
a
n
d
s
f
lu
ctu
ate
,
p
ar
ticu
lar
ly
in
ter
m
s
o
f
C
PU
u
tili
za
tio
n
.
E
ac
h
VM
ca
n
b
e
ass
ig
n
ed
a
m
ax
im
u
m
C
PU
ca
p
ab
ilit
y
,
d
en
o
ted
as
.
Giv
en
th
at
ea
ch
PM
h
as
C
PU
ca
p
ac
ity
,
VM
co
u
n
ts
,
wh
ich
ar
e
h
o
s
ted
o
n
a
s
in
g
le
PM
is
d
eter
m
in
ed
b
y
t
h
e
r
atio
/
.
As
th
ese
VM
s
ca
n
ex
ec
u
te
a
wid
e
r
an
g
e
o
f
a
p
p
l
icatio
n
s
with
d
is
tin
ct
b
eh
av
io
r
s
,
th
e
y
m
ay
v
ar
y
s
ig
n
if
ican
tly
in
f
u
n
ctio
n
a
n
d
o
f
te
n
r
u
n
co
n
cu
r
r
e
n
tly
.
B
ased
o
n
r
ea
l
-
tim
e
w
o
r
k
lo
a
d
d
em
an
d
s
,
VM
s
ca
n
b
e
d
y
n
am
ically
ac
tiv
ated
o
r
d
ea
ctiv
ate
d
o
n
a
PM,
en
ab
lin
g
ef
f
icien
t
u
tili
za
tio
n
o
f
th
e
p
h
y
s
ical
s
y
s
tem
’
s
r
eso
u
r
ce
s
.
E
ac
h
VM
ca
n
o
p
er
ate
d
if
f
er
en
t
o
p
e
r
atin
g
s
y
s
tem
s
an
d
ap
p
licatio
n
s
s
im
u
ltan
eo
u
s
ly
o
n
th
e
s
am
e
PM,
en
s
u
r
in
g
f
lex
ib
ilit
y
an
d
ef
f
ic
ien
t
r
eso
u
r
ce
u
s
ag
e
f
o
r
clo
u
d
u
s
er
s
.
Ser
v
ices
ar
e
p
r
o
v
id
ed
th
r
o
u
g
h
ap
p
licati
o
n
s
d
is
tr
ib
u
ted
ac
r
o
s
s
s
ev
er
al
VM
s
with
in
th
e
u
n
d
er
ly
i
n
g
clo
u
d
in
f
r
astru
ct
u
r
e.
Giv
en
th
e
h
ig
h
ly
v
ar
iab
le
n
atu
r
e
o
f
wo
r
k
lo
ad
s
,
th
e
r
eso
u
r
ce
r
eq
u
ir
em
e
n
ts
o
f
ea
ch
VM
ca
n
d
if
f
er
s
ig
n
if
ica
n
tly
;
th
er
ef
o
r
e,
VM
s
m
ay
m
i
g
r
ate
ac
r
o
s
s
PMs
to
o
p
tim
ize
r
eso
u
r
ce
u
tili
za
tio
n
,
r
ed
u
ce
r
ed
u
n
d
an
c
y
,
an
d
r
elea
s
e
u
n
u
s
ed
ca
p
ac
ity
.
C
o
n
s
eq
u
e
n
tly
,
PMs
ca
n
b
e
tu
r
n
e
d
o
f
f
o
r
m
o
v
e
d
to
an
id
l
e
s
tate
to
r
ed
u
ce
p
o
wer
co
n
s
u
m
p
tio
n
.
2
.
2
.
E
nerg
y
ef
f
iciency
mo
del
Mo
s
t
co
n
tem
p
o
r
ar
y
m
ain
f
r
a
m
es
ar
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
d
y
n
am
ic
v
o
ltag
e
an
d
f
r
eq
u
e
n
cy
s
ca
lin
g
(
DVFS)
ad
v
an
ce
m
en
t,
wh
ic
h
en
ab
les
r
ea
l
-
tim
e
ad
ju
s
tm
en
t
o
f
o
p
er
atin
g
f
r
eq
u
e
n
cy
to
r
ed
u
ce
e
n
er
g
y
co
n
s
u
m
p
tio
n
.
Sin
ce
C
PU
u
tili
za
tio
n
ty
p
ically
r
ef
lects
wo
r
k
l
o
ad
in
te
n
s
ity
,
th
e
p
o
wer
u
s
ag
e
o
f
a
PM
is
lar
g
ely
af
f
ec
ted
b
y
its
C
PU
lo
ad
.
DVFS
i
s
b
r
o
ad
ly
ad
o
p
ted
as
an
ef
f
ec
tiv
e
m
ec
h
a
n
is
m
to
b
alan
ce
s
y
s
tem
p
er
f
o
r
m
an
ce
an
d
en
er
g
y
c
o
n
s
u
m
p
tio
n
.
B
y
a
d
ju
s
tin
g
th
e
p
r
o
ce
s
s
o
r
’
s
o
p
er
atin
g
f
r
eq
u
e
n
cy
an
d
v
o
ltag
e
,
DVFS
in
f
lu
en
ce
s
o
v
er
all
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
as
lo
wer
f
r
eq
u
en
ci
es
m
ay
e
x
ten
d
ex
ec
u
tio
n
tim
e
d
esp
ite
r
e
d
u
cin
g
p
o
wer
.
An
ef
f
icien
t
DVFS
-
b
ased
s
ch
ed
u
lin
g
s
tr
ateg
y
aim
s
to
m
in
im
ize
to
tal
en
er
g
y
co
n
s
u
m
p
tio
n
wh
il
e
s
atis
f
y
in
g
Qo
S
r
eq
u
ir
em
en
ts
s
u
ch
as
ex
ec
u
tio
n
d
ea
d
lin
es.
D
VFS
allo
ws
th
e
p
r
o
ce
s
s
o
r
to
o
p
er
ate
at
d
if
f
e
r
en
t
v
o
ltag
e
-
f
r
e
q
u
en
c
y
c
o
m
b
in
atio
n
s
d
u
r
i
n
g
ac
tiv
e
an
d
id
le
co
m
m
u
n
icatio
n
p
er
i
o
d
s
,
co
n
tr
ib
u
tin
g
to
o
p
tim
ized
p
o
wer
u
s
ag
e.
Pro
ce
s
s
o
r
allo
ca
tio
n
s
tr
ateg
ies
g
en
er
ally
ass
ig
n
clu
s
ter
s
to
in
d
iv
id
u
al
p
r
o
ce
s
s
in
g
u
n
its
(
PU
s
)
.
A
s
u
m
o
f
p
o
wer
u
tili
ze
d
th
r
o
u
g
h
P
M
d
ep
en
d
s
o
n
s
ev
er
al
co
m
p
o
n
en
ts
,
i
n
clu
d
in
g
n
etwo
r
k
,
C
PU,
s
to
r
ag
e
,
an
d
m
em
o
r
y
(
R
AM
)
u
tili
za
tio
n
.
P
r
io
r
s
tu
d
ies
h
a
v
e
s
h
o
wn
a
s
tr
o
n
g
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
C
PU
u
s
ag
e
an
d
to
tal
en
er
g
y
c
o
n
s
u
m
p
tio
n
in
s
er
v
er
s
.
Fo
r
in
s
tan
ce
,
th
e
p
r
o
c
ess
o
r
is
th
e
d
o
m
in
an
t
co
n
tr
i
b
u
to
r
to
h
o
s
t
p
o
wer
co
n
s
u
m
p
tio
n
,
in
d
icatin
g
th
at
C
PU
u
ti
lizatio
n
is
d
ir
ec
tly
l
in
k
ed
to
th
e
p
o
wer
d
r
aw.
Acc
o
r
d
in
g
ly
,
th
e
p
o
wer
m
o
d
el
o
f
a
s
er
v
er
ca
n
b
e
e
x
p
r
e
s
s
ed
as a
f
u
n
ctio
n
o
f
C
PU u
s
ag
e,
r
ep
r
esen
ted
m
ath
em
atica
ll
y
in
(
1
)
.
=
(
−
)
×
+
(
1
)
Her
e
m
ea
n
s
av
e
r
ag
e
p
o
wer
i
n
an
in
d
o
len
t
s
tate,
d
en
o
tes
th
e
av
er
ag
e
p
o
wer
at
f
u
ll
u
tili
za
tio
n
,
an
d
r
ep
r
esen
ts
th
e
r
eso
u
r
ce
co
n
s
u
m
p
tio
n
o
f
th
e
h
o
s
t
in
th
e
cu
r
r
en
t
p
o
wer
s
tate.
T
h
e
to
tal
en
er
g
y
u
s
ag
e
f
o
r
h
o
s
t
s
is
esti
m
ated
as (
2
)
.
∑
=
∑
[
×
(
(
−
)
×
∑
(
×
)
+
=
1
)
]
=
1
=
1
(
2
)
W
h
er
e
R
is
th
e
s
et
o
f
VM
p
r
o
ce
s
s
o
r
s
,
s
p
ec
if
ies
th
e
o
p
er
at
io
n
u
p
d
ate
o
f
th
e
PM
with
r
e
s
p
ec
t
to
0
an
d
1
,
d
en
o
tes
th
e
task
o
f
VM
to
PM.
E
v
en
wh
en
a
PM
is
i
d
le
(
i.e
.
,
0
%
u
tili
za
tio
n
)
,
it
s
till
co
n
s
u
m
es
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
its
p
o
wer
.
L
et
α
r
ep
r
esen
t
th
e
p
r
o
p
o
r
tio
n
o
f
p
o
we
r
co
n
s
u
m
e
d
b
y
P
M
in
th
e
id
le
s
tate
r
elativ
e
to
wh
en
it
is
f
u
lly
u
tili
ze
d
an
d
r
ep
r
esen
t
th
e
p
o
wer
u
tili
za
tio
n
at
th
e
cu
r
r
en
t
o
p
er
atin
g
lev
el.
T
h
e
to
tal
p
o
wer
co
n
s
u
m
p
tio
n
o
f
is
d
ef
in
ed
as (
3
)
.
W
h
er
e
d
en
o
tes th
e
p
o
wer
co
n
s
u
m
p
tio
n
o
f
.
=
×
+
(
1
−
)
×
×
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
2
8
6
-
1
2
9
9
1290
2
.
3
.
Securit
y
qu
a
ntif
ica
t
io
n
I
n
p
ar
ticu
lar
,
ass
u
m
e
a
co
m
p
ar
ab
le
d
is
tr
ib
u
tio
n
o
f
m
alic
io
u
s
u
s
er
s
.
T
h
e
s
ec
u
r
ity
q
u
a
n
tific
atio
n
co
n
s
id
er
s
th
e
lik
elih
o
o
d
o
f
m
alicio
u
s
VM
s
b
ein
g
co
-
lo
ca
ted
with
leg
itima
te
u
s
er
s
,
wh
ic
h
d
ir
ec
tly
in
f
lu
en
ce
s
s
y
s
tem
v
u
ln
er
ab
ilit
y
.
T
h
is
s
tu
d
y
m
o
d
els
th
e
p
r
o
b
a
b
ilit
y
o
f
m
alicio
u
s
VM
s
b
ein
g
co
-
lo
ca
ted
with
leg
itima
te
u
s
er
s
,
th
er
eb
y
ca
p
tu
r
in
g
p
o
te
n
tial secu
r
ity
r
is
k
s
,
as f
o
r
m
u
lat
ed
in
(
4
)
.
=
×
∑
(
−
−
1
)
=
1
∗
(
−
1
)
(
4
)
W
h
er
e
r
ep
r
esen
ts
th
e
ev
alu
at
ed
m
alicio
u
s
u
s
er
p
er
ce
n
ta
g
e,
an
d
an
d
d
en
o
te
th
e
n
u
m
b
e
r
o
f
PMs
an
d
u
s
er
s
,
r
esp
ec
tiv
ely
.
−
is
a
c
o
u
n
t o
f
co
-
lo
ca
te
d
u
s
er
s
at
.
T
h
is
s
tu
d
y
ass
u
m
es
th
at
a
PM
with
o
n
l
y
o
n
e
u
s
er
is
s
ec
u
r
e.
No
tab
l
y
,
a
PM
h
o
s
tin
g
a
s
in
g
le
u
s
er
is
co
n
s
id
er
ed
s
ec
u
r
e,
as n
o
co
-
l
o
ca
tio
n
ex
is
ts
to
en
ab
le
m
alicio
u
s
in
ter
ac
tio
n
s
.
3.
VIRT
UAL
M
ACH
I
NE
A
L
L
O
CATI
O
N
U
SI
NG
B
O
B
CA
T
O
P
T
I
M
I
Z
A
T
I
O
N
A
L
G
O
RIT
H
M
I
n
th
e
d
esig
n
o
f
th
e
B
OA,
th
e
p
o
p
u
latio
n
u
p
d
ate
m
ec
h
an
is
m
with
in
th
e
s
o
lu
tio
n
s
p
ac
e
is
e
n
co
u
r
a
g
ed
th
r
o
u
g
h
n
at
u
r
al
h
u
n
tin
g
s
tr
ateg
ies
o
f
wild
b
o
b
ca
ts
.
I
n
th
is
m
ec
h
an
is
m
,
a
b
o
b
ca
t
i
n
itially
tr
ails
a
lo
ca
tio
n
o
f
p
r
ey
an
d
tr
av
els
to
war
d
s
it.
Su
b
s
eq
u
en
tly
,
it
tr
a
p
s
an
d
attac
k
s
a
p
r
ey
at
an
o
p
p
o
r
tu
n
e
m
o
m
en
t
an
d
ev
e
n
tu
ally
ca
tch
es th
e
p
r
ey
later
to
h
u
r
tlin
g
p
r
o
ce
d
u
r
e.
T
h
e
u
p
d
ated
s
tag
es o
f
th
e
B
OA
ar
e
d
escr
ib
ed
.
3
.
1
.
I
nitia
liza
t
io
n
B
OA
is
a
p
o
p
u
latio
n
-
d
r
iv
e
n
o
p
tim
izatio
n
ap
p
r
o
ac
h
wh
ich
iter
ativ
ely
ex
p
lo
r
es
th
e
s
o
lu
t
io
n
s
p
ac
e,
lev
er
ag
in
g
th
e
co
llectiv
e
s
ea
r
c
h
ca
p
ab
ilit
y
o
f
its
ag
en
ts
to
ef
f
ec
tiv
ely
s
o
lv
e
o
p
tim
izatio
n
p
r
o
b
lem
s
.
B
ased
o
n
th
e
d
esig
n
in
s
p
ir
atio
n
o
f
th
e
B
OA,
th
e
s
o
lu
tio
n
s
p
ac
e
is
an
alo
g
o
u
s
to
th
e
n
atu
r
al
h
ab
itat
o
f
b
o
b
ca
ts
,
an
d
th
e
p
o
s
itio
n
o
f
ea
ch
b
o
b
ca
t
with
i
n
th
is
h
ab
itat
r
ep
r
esen
ts
a
lo
ca
tio
n
o
f
a
B
OA
m
em
b
er
in
th
e
s
o
lu
tio
n
s
p
ac
e.
T
h
u
s
,
in
th
e
B
OA,
ea
ch
b
o
b
c
at
in
th
e
p
o
p
u
latio
n
r
ep
r
esen
ts
a
p
o
ten
tial
s
o
l
u
tio
n
with
in
t
h
e
p
r
o
b
lem
-
s
o
lv
i
n
g
s
p
ac
e,
wh
er
e
its
p
o
s
itio
n
co
r
r
esp
o
n
d
s
to
s
p
ec
if
ic
v
alu
es
ass
ig
n
ed
t
o
th
e
d
ec
is
io
n
v
a
r
iab
le
s
.
Ma
th
em
atica
lly
,
th
e
b
o
b
ca
t
p
o
s
itio
n
ca
n
b
e
e
x
p
r
ess
ed
as
a
v
ec
to
r
,
in
th
at,
ev
er
y
co
n
s
titu
en
t
d
en
o
tes
th
e
tar
g
et
co
m
p
o
n
e
n
t.
C
o
llectiv
ely
,
all
b
o
b
ca
ts
co
n
s
t
itu
te
an
alg
o
r
ith
m
’
s
p
o
p
u
latio
n
,
d
en
o
ted
as
a
m
atr
ix
,
as
r
ep
r
esen
ted
in
(
5
)
.
T
h
e
in
itial p
o
s
itio
n
o
f
ea
ch
b
o
b
ca
t
is
ar
b
itra
r
ily
g
en
er
ate
d
in
th
e
s
o
lu
tio
n
s
p
ac
e
u
s
in
g
(
6
)
.
=
[
1
⋮
⋮
]
×
=
[
1
,
1
…
1
,
…
1
,
⋮
⋱
⋮
⋱
⋮
,
⋮
,
1
…
⋱
…
,
⋮
,
…
⋱
…
,
⋮
,
]
×
(
5
)
,
=
+
.
(
−
)
(
6
)
W
h
er
e
d
en
o
tes
th
e
p
o
p
u
latio
n
m
atr
ix
o
f
th
e
B
OA,
d
en
o
te
s
th
e
an
in
d
iv
i
d
u
al
s
o
lu
tio
n
,
a
n
d
,
d
en
o
tes
th
e
th
d
im
en
s
io
n
in
th
e
s
o
lu
tio
n
ar
ea
.
d
en
o
tes
b
o
b
ca
t
co
u
n
ts
,
s
p
ec
if
ies
th
e
co
u
n
t
o
f
tar
g
et
co
m
p
o
n
en
ts
,
an
d
is
an
ar
b
itra
r
y
co
u
n
t
in
t
h
e
r
an
g
e
[
0
,
1
]
.
an
d
co
r
r
esp
o
n
d
to
th
e
u
p
p
e
r
an
d
lo
wer
b
o
u
n
d
a
r
ies
o
f
th
e
th
d
im
en
s
io
n
,
in
d
iv
id
u
all
y
.
As
d
is
cu
s
s
ed
ea
r
lier
,
a
lo
ca
tio
n
o
f
ev
er
y
b
o
b
ca
t
d
en
o
tes
an
in
d
iv
i
d
u
al
p
r
o
b
lem
-
s
o
lv
in
g
,
ac
co
r
d
in
g
t
o
th
at
an
aim
v
alu
e
is
ev
alu
at
ed
.
T
h
e
v
alu
es
o
f
th
is
f
u
n
ctio
n
co
r
r
esp
o
n
d
in
g
to
th
ese
s
o
lu
tio
n
s
ar
e
ex
p
r
ess
ed
a
s
a
v
ec
to
r
,
as sh
o
wn
in
(
7
)
.
=
[
1
⋮
⋮
]
×
=
[
(
1
)
⋮
(
)
⋮
(
)
]
×
(
7
)
W
h
er
e
d
en
o
tes
a
v
ec
t
o
r
o
f
th
e
esti
m
ated
aim
v
alu
e
,
an
d
d
en
o
tes
aim
v
alu
e
co
r
r
esp
o
n
d
in
g
to
th
b
o
b
ca
t
.
r
ep
r
esen
ts
th
e
g
r
o
u
p
o
f
all
ca
n
d
id
ate
s
o
lu
tio
n
s
.
An
aim
v
al
u
e
(
)
ev
alu
ates
ev
er
y
s
o
lu
tio
n
.
C
o
llectiv
ely
,
th
ese
ev
alu
atio
n
s
f
o
r
m
th
e
m
at
r
ix
,
wh
ich
h
o
ld
s
f
itn
ess
v
alu
e
s
o
f
all
ca
n
d
id
ate
s
o
lu
tio
n
s
ac
r
o
s
s
o
b
jectiv
es.
3
.
2
.
E
x
plo
ra
t
i
o
n:
t
ra
c
k
ing
a
nd
m
o
v
ing
t
o
wa
rds
prey
I
n
an
in
itial
s
tag
e
o
f
th
e
B
O
A,
a
lo
ca
tio
n
o
f
p
o
p
u
latio
n
m
em
b
er
s
in
a
s
o
lu
tio
n
s
p
ac
e
is
u
p
d
ated
ac
co
r
d
in
g
to
b
o
b
ca
t
’
s
tr
ac
k
in
g
an
d
m
o
v
em
en
t
t
o
war
d
p
r
e
y
at
th
e
tim
e
o
f
h
u
n
tin
g
.
C
ap
tu
r
in
g
th
e
bobc
at’
s
m
o
v
em
en
t
to
war
d
its
p
r
ey
r
e
s
u
lts
in
g
r
ea
ter
m
o
d
if
icatio
n
in
lo
ca
tio
n
s
o
f
p
o
p
u
latio
n
m
e
m
b
er
s
in
a
s
o
lu
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
erg
y
-
efficien
t v
ir
tu
a
l m
a
ch
i
n
e
a
llo
ca
tio
n
u
s
in
g
d
ir
ec
tio
n
a
l a
n
d
b
o
u
n
d
a
r
y
-
a
w
a
r
e
…
(
N
id
a
K
o
u
s
a
r
Go
u
s
e)
1291
s
p
ac
e
an
d
en
h
an
ce
s
th
e
ex
p
lo
r
atio
n
ca
p
a
b
ilit
y
o
f
t
h
e
B
OA
w
ith
r
esp
ec
t
t
o
m
ai
n
tain
in
g
a
g
l
o
b
al
s
ea
r
ch
.
I
n
t
h
e
B
OA
d
ep
lo
y
m
en
t,
f
o
r
e
v
er
y
b
o
b
ca
t,
th
e
o
th
er
p
o
p
u
latio
n
m
em
b
er
’
s
lo
c
atio
n
s
with
s
u
p
er
io
r
aim
v
alu
e
ar
e
id
en
tifie
d
as p
r
ey
p
o
s
itio
n
s
.
A
n
in
d
iv
id
u
al
p
r
e
y
g
r
o
u
p
f
o
r
ev
er
y
b
o
b
ca
t is id
en
tifie
d
th
r
o
u
g
h
(
8
)
.
=
{
:
<
≠
1
}
,
ℎ
=
1
,
2
,
…
,
∈
{
1
,
2
,
…
,
}
(
8
)
W
h
er
e
r
ep
r
esen
ts
th
e
g
r
o
u
p
o
f
in
d
iv
id
u
al
p
r
ey
p
o
s
itio
n
s
f
o
r
th
e
th
b
o
b
ca
t,
d
en
o
tes
a
p
o
p
u
latio
n
m
em
b
er
th
r
o
u
g
h
th
e
o
p
tim
al
aim
v
alu
e
in
ac
co
r
d
an
ce
with
th
b
o
b
ca
t
,
an
d
d
en
o
tes
th
e
aim
v
alu
e.
I
n
th
e
B
OA,
ev
er
y
b
o
b
ca
t
ar
b
itra
r
ily
ch
o
o
s
es
th
e
id
en
tifie
d
p
r
ey
item
s
an
d
in
itiates
an
attac
k
.
Acc
o
r
d
in
g
t
o
th
e
m
o
d
eled
m
o
v
em
en
t
o
f
th
e
b
o
b
ca
t
to
war
d
th
e
p
r
ey
,
a
n
ew
p
o
s
itio
n
is
esti
m
ated
f
o
r
ev
er
y
B
OA
in
d
iv
id
u
al
th
r
o
u
g
h
(
9
)
.
I
f
an
u
n
k
n
o
w
n
l
o
ca
tio
n
attain
s
a
n
en
h
an
ce
d
aim
v
alu
e,
it
ex
c
h
an
g
es
a
p
r
io
r
lo
ca
tio
n
o
f
th
e
r
esp
ec
tiv
e
m
em
b
er
,
as d
ef
in
ed
in
(
1
0
)
.
,
1
=
,
+
(
1
−
2
,
)
.
(
,
−
,
.
,
)
(
9
)
=
{
,
1
,
,
1
≤
,
(
1
0
)
W
h
er
e
,
d
en
o
tes
th
e
p
r
e
y
s
elec
ted
b
y
th
b
o
b
ca
t
in
th
d
im
en
s
io
n
,
an
d
,
1
d
en
o
tes
th
e
n
e
w
lo
ca
tio
n
esti
m
ated
f
o
r
th
e
th
b
o
b
ca
t
in
th
d
im
en
s
io
n
of
t
h
e
ex
p
lo
r
atio
n
s
tag
e
o
f
th
e
p
r
o
p
o
s
ed
B
OA.
,
r
ep
r
esen
ts
a
r
an
d
o
m
n
u
m
b
er
in
a
r
an
g
e
b
et
wee
n
0
an
d
1
,
a
n
d
,
r
ef
er
s
to
a
n
u
m
b
er
r
an
d
o
m
ly
c
h
o
s
en
as
ei
th
er
o
n
e
o
r
two
.
3
.
3
.
E
x
plo
it
a
t
io
n:
cha
s
ing
t
o
ca
t
ch
prey
I
n
th
is
s
tag
e,
p
o
s
itio
n
s
o
f
p
o
p
u
latio
n
m
em
b
er
s
in
a
s
o
lu
ti
o
n
s
p
ac
e
ar
e
r
e
o
r
g
a
n
ized
wit
h
r
esp
ec
t
to
s
im
u
lated
ch
ase
am
o
n
g
b
o
b
ca
t
an
d
its
p
r
ey
at
t
h
e
tim
e
o
f
h
u
n
tin
g
.
T
h
is
ch
ase
o
cc
u
r
s
n
ea
r
th
e
p
r
ey
’
s
lo
ca
tio
n
an
d
ev
e
n
tu
ally
r
esu
lts
in
th
e
ca
p
tu
r
e
o
f
th
e
p
r
ey
.
T
h
e
m
o
d
eled
m
o
v
em
en
t
o
f
b
o
b
ca
ts
d
u
r
in
g
th
is
p
h
ase
in
tr
o
d
u
ce
s
s
m
all,
lo
ca
lized
c
h
an
g
es
to
th
e
p
o
s
itio
n
s
o
f
in
d
iv
id
u
als
in
th
e
p
o
p
u
latio
n
,
t
h
u
s
en
h
an
cin
g
th
e
ex
p
lo
itatio
n
ca
p
a
b
ilit
y
o
f
th
e
B
OA
an
d
im
p
r
o
v
in
g
its
lo
ca
l
s
ea
r
ch
p
er
f
o
r
m
an
ce
.
An
u
n
k
n
o
wn
lo
ca
tio
n
f
o
r
ea
ch
B
OA
m
em
b
er
is
esti
m
ated
clo
s
e
to
th
e
p
r
ey
’s
lo
ca
tio
n
u
s
in
g
(
1
1
)
,
b
ased
o
n
th
e
m
o
d
eled
p
o
s
itio
n
al
ad
ju
s
tm
en
ts
d
u
r
in
g
th
e
ch
ase
.
I
f
t
h
is
u
p
d
ate
d
p
o
s
itio
n
attain
s
an
o
p
tim
al
f
u
n
ctio
n
v
alu
e,
it
r
e
p
lace
s
th
e
p
r
ev
io
u
s
r
esp
ec
tiv
e
in
d
iv
id
u
al
,
as d
ef
in
ed
i
n
(
1
2
)
.
,
2
=
,
+
1
−
2
,
1
+
×
,
(
1
1
)
=
{
,
2
,
,
2
≤
,
(
1
2
)
W
h
e
r
e
,
2
d
e
n
o
t
e
s
a
n
u
n
k
n
o
w
n
l
o
c
a
t
i
o
n
e
s
t
i
m
a
t
e
d
f
o
r
t
h
e
t
h
b
o
b
c
a
t
w
i
t
h
r
e
s
p
e
ct
t
o
t
h
e
e
x
p
l
o
i
t
a
t
i
o
n
s
t
a
g
e
o
f
B
O
A
.
T
h
e
c
o
n
v
e
n
t
i
o
n
a
l
B
OA
u
s
e
s
s
t
o
c
h
as
t
ic
s
ea
r
c
h
m
e
c
h
a
n
is
m
s
t
o
s
i
m
u
l
a
t
e
t
h
e
h
u
n
t
i
n
g
b
e
h
a
v
i
o
r
o
f
b
o
b
c
a
t
s
;
h
o
w
e
v
e
r
,
s
u
c
h
r
a
n
d
o
m
n
e
s
s
c
an
l
e
a
d
t
o
i
n
e
f
f
i
c
i
e
n
t
e
x
p
l
o
r
a
t
i
o
n
o
f
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
o
r
c
o
n
s
tr
a
i
n
e
d
p
r
o
b
l
e
m
s
.
T
o
a
d
d
r
e
s
s
t
h
i
s
li
m
i
ta
t
i
o
n
,
tw
o
d
i
f
f
e
r
e
n
t
s
t
r
at
e
g
i
es
a
r
e
a
p
p
l
ie
d
i
n
th
e
B
O
A
,
d
i
s
c
u
s
s
e
d
i
n
d
e
t
a
il
a
s
f
o
l
l
o
w
s
.
3
.
4
.
Dire
ct
io
na
l
m
o
v
em
ent
a
nd
bo
un
da
ry
a
wa
re
s
t
ra
t
e
g
y
T
o
en
h
an
ce
p
r
ec
is
io
n
,
co
n
v
er
g
en
ce
s
p
ee
d
,
an
d
b
o
u
n
d
ar
y
h
a
n
d
lin
g
,
th
is
r
esear
ch
i
n
teg
r
ates
a
d
ir
ec
tio
n
al
m
o
v
em
en
t
s
tr
ateg
y
g
u
id
e
d
b
y
th
e
lo
ca
tio
n
o
f
th
e
p
r
ey
a
n
d
ap
p
lies
b
o
u
n
d
ar
y
-
aw
ar
e
ad
ju
s
tm
en
ts
to
en
s
u
r
e
f
ea
s
ib
le
s
o
lu
tio
n
s
.
T
h
i
s
ap
p
r
o
ac
h
d
r
aws
in
s
p
ir
atio
n
f
r
o
m
th
e
p
r
ey
-
p
r
e
d
ato
r
in
ter
ac
tio
n
o
p
er
at
o
r
in
th
e
zo
o
lo
g
ical
s
ea
r
ch
o
p
tim
izati
o
n
(
Z
SO)
[
2
9
]
m
o
d
el
wh
ile
m
ain
tain
in
g
th
e
s
o
litar
y
n
atu
r
e
o
f
th
e
b
o
b
ca
t.
T
h
e
en
h
an
ce
d
B
OA
co
m
b
in
es
a
d
ir
ec
tio
n
al
m
o
v
em
e
n
t
m
ec
h
an
is
m
with
a
b
o
u
n
d
ar
y
-
awa
r
e
ad
ju
s
tm
en
t
s
tr
ateg
y
in
s
p
ir
ed
b
y
Z
SO.
T
h
e
f
u
n
ctio
n
s
o
f
th
e
in
t
r
o
d
u
ce
d
s
tr
ateg
y
ar
e
e
x
p
lain
ed
as f
o
llo
w
s
:
i)
Dir
ec
tio
n
al
v
ec
to
r
-
b
ased
m
o
v
em
en
t:
ea
ch
b
o
b
ca
t
(
s
o
lu
ti
o
n
)
in
tellig
en
tly
m
o
v
es
to
war
d
p
r
o
m
is
in
g
r
eg
io
n
s
u
s
in
g
a
d
ap
tiv
e
d
ir
ec
t
io
n
al
v
ec
to
r
s
ca
lcu
lated
r
elat
iv
e
to
b
etter
-
p
e
r
f
o
r
m
in
g
s
o
lu
tio
n
s
(
p
r
ey
)
.
Ass
u
m
e
th
e
f
o
llo
win
g
m
ath
e
m
atica
l
m
o
d
elin
g
:
lo
ca
tio
n
o
f
b
o
b
ca
t
∈
;
lo
ca
tio
n
o
f
c
h
o
s
en
p
r
e
y
∗
∈
;
co
n
s
is
ten
tly
d
is
p
er
s
ed
r
an
d
o
m
n
u
m
b
e
r
~
(
0
,
1
)
;
cu
r
r
e
n
t
iter
atio
n
;
m
ax
im
u
m
n
u
m
b
er
o
f
iter
atio
n
s
;
d
ir
ec
tio
n
al
v
ec
to
r
f
r
o
m
b
o
b
ca
t
to
p
r
e
y
⃗
⃗
;
an
d
ex
p
lo
r
atio
n
co
n
tr
o
l
p
ar
am
eter
.
T
h
e
d
ir
ec
tio
n
al
v
ec
to
r
an
d
p
o
s
itio
n
u
p
d
ate
o
f
th
e
b
o
b
ca
t
a
r
e
d
ef
in
ed
as (
1
3
)
an
d
(
1
4
)
.
⃗
⃗
=
∗
−
(
1
3
)
+
1
=
+
.
.
⃗
⃗
(
1
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
2
8
6
-
1
2
9
9
1292
W
h
e
r
e
=
(
1
−
)
.
T
h
is
e
n
s
u
r
es
b
r
o
a
d
er
ex
p
l
o
r
at
io
n
i
n
e
ar
lie
r
it
e
r
at
io
n
s
a
n
d
m
o
r
e
f
o
c
u
s
e
d
m
o
v
e
m
e
n
t
in
l
at
er
o
n
es
.
T
h
e
s
t
r
a
te
g
y
e
m
p
h
asiz
es
m
o
v
e
m
e
n
t
t
o
wa
r
d
p
r
o
m
is
i
n
g
s
o
l
u
ti
o
n
s
,
r
es
u
lt
i
n
g
i
n
o
p
ti
m
al
o
u
tc
o
m
es
.
T
h
is
d
y
n
am
ic
a
p
p
r
o
a
ch
h
el
p
s
t
h
e
al
g
o
r
it
h
m
a
v
o
i
d
p
r
e
m
at
u
r
e
c
o
n
v
er
g
en
ce
a
n
d
i
n
c
r
ea
s
es
th
e
lik
eli
h
o
o
d
o
f
i
d
e
n
ti
f
y
i
n
g
g
l
o
b
a
l
o
p
tim
a.
ii)
B
o
u
n
d
ar
y
-
awa
r
e
ad
j
u
s
tm
en
t:
s
o
lu
tio
n
s
ar
e
d
y
n
am
ically
ad
ju
s
ted
to
s
tay
with
in
th
e
le
g
al
b
o
u
n
d
s
o
f
s
er
v
er
ca
p
ac
ities
(
C
PU
an
d
m
em
o
r
y
)
,
en
s
u
r
in
g
f
ea
s
ib
ilit
y
a
n
d
p
r
ev
en
tin
g
r
an
d
o
m
r
esets
o
r
clip
p
in
g
.
T
h
e
b
o
u
n
d
ar
y
-
awa
r
e
ad
ju
s
tm
en
t
m
ec
h
an
is
m
co
r
r
ec
t
s
s
o
lu
tio
n
s
th
at
v
io
late
p
r
o
b
lem
co
n
s
tr
ain
ts
s
u
ch
as
C
PU
o
r
m
em
o
r
y
ca
p
ac
ity
in
clo
u
d
e
n
v
ir
o
n
m
en
ts
.
T
h
e
b
o
u
n
d
ar
y
-
a
war
e
ad
ju
s
tm
en
t is ca
lcu
lated
u
s
in
g
(
1
5
)
.
,
+
1
=
{
+
.
(
−
)
,
,
+
1
<
+
.
(
−
)
,
,
+
1
>
,
+
1
,
ℎ
(
15)
T
h
is
en
s
u
r
es
t
h
at
n
o
s
o
l
u
ti
o
n
e
x
c
ee
d
s
th
e
p
r
o
b
le
m
’
s
f
ea
s
ib
le
s
p
a
ce
.
iii)
Ad
ap
tiv
e
ex
p
lo
r
atio
n
co
ef
f
icien
t
(
α
)
:
th
e
c
o
ef
f
icien
t
d
y
n
a
m
ically
d
ec
r
ea
s
es
o
v
e
r
iter
ati
o
n
s
,
en
ab
lin
g
b
r
o
ad
ea
r
ly
e
x
p
lo
r
atio
n
a
n
d
r
e
f
in
ed
ex
p
lo
itatio
n
i
n
later
s
tag
es.
Alg
o
r
ith
m
1
p
r
esen
ts
th
e
p
s
eu
d
o
co
d
e
f
o
r
th
e
DM
B
AB
OA
ap
p
r
o
ac
h
f
o
r
b
etter
r
e
p
r
o
d
u
cib
ilit
y
.
B
ec
au
s
e
en
g
in
ee
r
in
g
p
r
o
b
lem
s
in
v
o
lv
e
co
n
s
tr
ain
ts
,
th
e
ac
tu
al
m
etah
eu
r
is
tic
ap
p
r
o
ac
h
B
OA
d
o
es
n
o
t
h
an
d
le
th
e
o
p
tim
izatio
n
is
s
u
es.
T
h
er
ef
o
r
e
,
th
is
s
tu
d
y
p
r
ep
ar
e
s
all
m
etah
eu
r
is
tic
ap
p
r
o
ac
h
es
u
s
in
g
a
s
tatic
p
en
alty
f
u
n
ctio
n
.
T
h
e
f
itn
ess
f
u
n
ct
io
n
co
n
s
id
er
s
en
er
g
y
c
o
n
s
u
m
p
ti
o
n
an
d
is
d
ef
in
ed
in
(
1
6
)
.
(
)
=
(
)
+
.
∑
(
(
0
,
(
)
)
)
=
1
(
1
6
)
W
h
er
e
(
.
)
d
en
o
tes
f
itn
ess
f
u
n
ctio
n
,
(
.
)
an
d
(
.
)
d
en
o
te
o
b
jectiv
e
an
d
r
estrictio
n
f
u
n
ctio
n
s
,
in
d
iv
id
u
ally
,
a
n
d
is
a
co
n
s
ta
n
t
s
et.
T
h
is
d
y
n
am
ic
ad
ju
s
tm
en
t
p
r
ev
en
ts
p
r
em
atu
r
e
co
n
v
e
r
g
en
ce
wh
ile
m
ain
tain
in
g
th
e
b
alan
ce
b
etwe
en
g
lo
b
al
a
n
d
lo
ca
l
s
ea
r
ch
.
B
y
in
teg
r
atin
g
th
is
s
tr
ateg
y
,
t
h
e
alg
o
r
ith
m
n
atu
r
ally
a
d
ap
ts
to
th
e
o
p
tim
i
za
tio
n
p
r
o
ce
s
s
an
d
en
s
u
r
es
r
o
b
u
s
t
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
d
if
f
e
r
en
t
p
r
o
b
lem
s
ca
les an
d
co
m
p
lex
ities
.
Alg
o
r
ith
m
1
.
Ps
eu
d
o
co
d
e
o
f
t
h
e
DM
B
AB
O
A
ap
p
r
o
ac
h
BEGIN
1. Initialize system parameters:
-
Population size
(
)
-
Maximum iterations
(
)
-
Lower and upper bounds (LB, UB) for server resources (CPU, Memory)
-
Adaptive exploration coefficient
∈
[
1
,
0
]
-
VM and host configuration data (CPU, Memory, Security Level)
2. Initialize population of bobcats:
For each bobcat
=
1
Randomly initialize position X_i within bounds
[
,
]
Evaluate fitness (
)
using:
(
)
=
1
∗
(
1
/
(
)
)
+
2
∗
(
(
)
)
+
3
∗
(
(
)
)
3. Identify best solution:
∗
=
(
(
)
)
over all
4. Iteration loop (for t = 1 to {Max}_{Iter}):
Update
=
0
∗
(
1
−
/
)
// Gradually reduce exploration
For each bobcat i in population:
-
Select prey (X^
\
ast) from better individuals (elitism
-
based selection)
-
Compute directional vector:
=
∗
−
Update position with directional movement:
=
+
∗
(
)
∗
-
Apply boundary
-
aware adjustment:
For each dimension j:
[
]
<
[
]
[
]
=
[
]
+
(
)
∗
(
[
]
−
[
]
)
Else
[
]
>
[
]
[
]
=
[
]
−
(
)
∗
(
[
]
−
[
]
)
-
Evaluate new fitness:
(
)
=
1
∗
(
1
/
(
)
)
+
2
∗
(
(
)
)
+
3
∗
(
(
)
)
-
Update
(
)
>
(
)
-
Update global best:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
erg
y
-
efficien
t v
ir
tu
a
l m
a
ch
i
n
e
a
llo
ca
tio
n
u
s
in
g
d
ir
ec
tio
n
a
l a
n
d
b
o
u
n
d
a
r
y
-
a
w
a
r
e
…
(
N
id
a
K
o
u
s
a
r
Go
u
s
e)
1293
If any
(
)
>
(
∗
)
,
∗
=
5. END LOOP
∗
6. Output
∗
as the optimal VM allocation.
7. Evaluate results:
En
er
gy
Co
ns
um
pt
io
n
(k
Wh
),
Ma
ke
sp
an
(s
),
Ex
ec
ut
io
n
Ti
me
(s
),
SL
A
Vi
ol
at
io
n
R
at
e
(%
),
La
te
nc
y
(ms), and Fitness Convergence over iterations
END
W
h
er
e
th
e
p
ar
am
ete
r
co
n
tr
o
l
s
th
e
ex
p
lo
r
atio
n
-
to
-
e
x
p
lo
itati
o
n
b
alan
ce
;
r
is
a
u
n
if
o
r
m
r
a
n
d
o
m
f
ac
to
r
t
h
at
p
r
o
m
o
tes
d
i
v
er
s
if
icatio
n
,
a
n
d
th
e
f
itn
ess
f
u
n
ctio
n
in
teg
r
ates
b
o
th
e
n
er
g
y
co
n
s
u
m
p
tio
n
f
r
o
m
th
e
DVFS
-
b
ased
m
o
d
elin
g
an
d
co
-
r
esid
en
ce
s
e
cu
r
ity
m
etr
ics.
So
lu
tio
n
s
v
io
latin
g
C
PU
o
r
m
em
o
r
y
lim
its
a
r
e
co
r
r
ec
ted
b
ef
o
r
e
ev
alu
atio
n
to
en
s
u
r
e
f
ea
s
ib
ilit
y
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
f
lo
wch
ar
t
o
f
th
e
p
r
o
p
o
s
ed
DM
B
AB
OA
ap
p
r
o
ac
h
f
o
r
en
er
g
y
-
ef
f
icien
t V
M
allo
ca
tio
n
,
wh
ich
in
v
o
lv
es b
o
th
ex
p
lo
r
atio
n
an
d
e
x
p
lo
itatio
n
p
h
ases
.
Fig
u
r
e
3
.
Flo
wch
ar
t
o
f
p
r
o
p
o
s
ed
DM
B
AB
O
A
ap
p
r
o
ac
h
f
o
r
en
er
g
y
-
ef
f
icien
t V
M
allo
ca
tio
n
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
s
eq
u
en
ce
o
f
im
p
lem
en
tatio
n
was
p
er
f
o
r
m
ed
f
o
r
v
alid
ati
n
g
th
e
p
er
f
o
r
m
a
n
ce
an
d
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
co
n
tain
er
s
ch
ed
u
lin
g
f
r
am
ewo
r
k
.
T
h
e
m
o
d
el
im
p
lem
en
tatio
n
was
p
er
f
o
r
m
e
d
u
s
in
g
Py
th
o
n
3
.
3
o
n
a
s
y
s
tem
co
n
f
i
g
u
r
e
d
u
s
in
g
I
n
tel
C
o
r
e
i5
C
PU
an
d
6
G
B
R
AM
u
n
d
er
W
in
d
o
ws
1
0
OS.
I
n
th
is
s
tu
d
y
,
a
s
y
n
th
etic
wo
r
k
lo
ad
was
g
en
er
ated
u
s
in
g
th
e
C
lo
u
d
Sim
s
im
u
latio
n
to
o
lk
it
to
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
en
er
g
y
-
ef
f
icien
t
,
s
ec
u
r
ity
-
awa
r
e
VM
-
allo
ca
tio
n
a
lg
o
r
ith
m
.
T
h
e
wo
r
k
l
o
ad
was
d
esig
n
ed
to
m
im
i
c
r
ea
l
-
wo
r
ld
clo
u
d
en
v
ir
o
n
m
en
t
s
with
th
e
f
o
llo
win
g
c
h
ar
ac
ter
i
s
tics
.
−
T
as
k
s
iz
e:
ea
c
h
tas
k
was
ass
i
g
n
e
d
a
r
an
d
o
m
in
s
tr
u
cti
o
n
le
n
g
t
h
u
n
if
o
r
m
l
y
d
is
tr
i
b
u
t
ed
f
r
o
m
1
,
0
0
0
t
o
1
0
,
0
0
0
m
ill
io
n
i
n
s
t
r
u
cti
o
n
s
(
M
I
)
,
r
e
p
r
ese
n
ti
n
g
d
i
v
e
r
s
e
c
o
m
p
u
tat
io
n
a
l c
o
m
p
le
x
it
ies
.
−
Data
s
i
ze
:
in
p
u
t
a
n
d
o
u
t
p
u
t
d
at
a
s
i
ze
s
f
o
r
t
h
e
t
as
k
s
v
ar
i
e
d
b
et
wee
n
1
0
MB
a
n
d
5
0
0
MB,
r
e
f
l
ec
ti
n
g
a
r
a
n
g
e
o
f
c
lo
u
d
-
s
e
r
v
ic
e
d
e
m
a
n
d
s
.
−
T
as
k
ar
r
i
v
a
l
p
at
te
r
n
:
a
P
o
is
s
o
n
d
is
t
r
i
b
u
ti
o
n
w
as
u
s
e
d
t
o
s
im
u
l
ate
t
ask
-
a
r
r
i
v
al
ti
m
es
,
ca
p
t
u
r
i
n
g
t
h
e
s
to
c
h
asti
c
an
d
b
u
r
s
t
y
n
at
u
r
e
o
f
r
ea
l
-
w
o
r
l
d
u
s
e
r
r
e
q
u
ests
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
2
8
6
-
1
2
9
9
1294
−
Sim
u
la
ti
o
n
s
c
ale
:
e
x
p
e
r
i
m
e
n
ts
wer
e
co
n
d
u
ct
ed
wi
th
w
o
r
k
l
o
a
d
s
r
a
n
g
i
n
g
f
r
o
m
1
0
t
o
1
,
0
0
0
ta
s
k
s
s
ch
ed
u
l
e
d
ac
r
o
s
s
a
s
i
m
u
lat
e
d
i
n
f
r
ast
r
u
ct
u
r
e
c
o
m
p
r
is
i
n
g
1
0
d
ata
c
e
n
te
r
s
an
d
1
5
VM
s.
−
Sy
n
t
h
et
ic
n
at
u
r
e:
alt
h
o
u
g
h
r
e
al
-
wo
r
l
d
d
atas
ets
we
r
e
u
s
e
d
,
th
e
s
y
n
th
eti
c
w
o
r
k
l
o
a
d
ac
cu
r
atel
y
ca
p
t
u
r
e
d
r
e
alis
t
ic
v
ar
ia
b
il
it
y
i
n
tas
k
a
r
r
i
v
al
,
s
iz
e,
a
n
d
r
es
o
u
r
ce
d
e
m
a
n
d
s
.
T
h
i
s
s
i
m
u
l
a
t
i
o
n
s
e
t
u
p
e
n
s
u
r
ed
a
c
o
n
t
r
o
l
l
e
d
y
e
t
r
e
a
l
i
s
t
i
c
e
n
v
i
r
o
n
m
e
n
t
f
o
r
e
v
a
l
u
a
t
i
n
g
t
h
e
e
n
e
r
g
y
e
f
f
i
c
i
e
n
c
y
o
f
t
h
e
p
r
o
p
o
s
e
d
o
p
t
im
i
z
a
t
i
o
n
a
l
g
o
r
it
h
m
,
s
e
c
u
r
it
y
-
aw
a
r
e
p
l
a
c
e
m
e
n
t
c
a
p
a
b
i
li
t
y
,
a
n
d
c
o
n
s
t
r
a
i
n
t
-
h
a
n
d
l
i
n
g
p
e
r
f
o
r
m
a
n
c
e
.
T
a
b
l
e
1
l
i
s
t
s
t
h
e
k
e
y
c
o
n
f
i
g
u
r
a
t
i
o
n
s
o
f
V
M
u
s
e
d
i
n
s
i
m
u
l
a
t
i
o
n
s
s
u
c
h
a
s
e
x
p
e
r
i
m
e
n
t
a
l
c
o
n
s
t
r
a
i
n
ts
,
s
i
z
e
,
a
n
d
r
e
s
o
u
r
c
e
l
i
m
i
t
s
.
T
h
e
p
r
o
c
e
s
s
i
n
g
V
M
d
y
n
a
m
i
ca
l
l
y
ad
j
u
s
ts
a
c
c
o
r
d
i
n
g
t
o
a
p
p
l
i
c
at
i
o
n
-
r
e
q
u
e
s
t
d
e
m
a
n
d
s
.
C
l
o
u
d
s
v
a
r
y
r
a
n
d
o
m
l
y
f
r
o
m
l
o
w
e
s
t
t
o
h
i
g
h
e
s
t
b
a
s
e
d
o
n
d
e
m
a
n
d
a
n
d
a
r
e
a
r
r
a
n
g
e
d
a
s
c
o
n
s
i
s
t
e
n
t
l
y
d
i
s
t
r
i
b
u
t
e
d
v
a
r
i
a
b
l
e
s
t
h
at
s
i
m
u
l
a
t
e
i
n
d
e
p
e
n
d
e
n
t
c
h
a
n
g
e
s
i
n
v
a
r
i
o
u
s
p
r
o
g
r
a
m
a
p
p
l
i
c
a
t
i
o
n
s
.
M
o
r
e
o
v
e
r
,
V
M
c
h
a
n
g
e
s
d
u
r
i
n
g
t
h
e
e
x
p
e
r
i
m
e
n
t
o
c
c
u
r
i
n
t
e
r
m
it
t
e
n
tly
a
t
a
f
i
x
e
d
6
0
s
t
i
m
e
i
n
t
e
r
v
a
l
.
T
ab
le
1
.
Key
c
o
n
f
i
g
u
r
atio
n
o
f
VM
s
u
s
ed
in
s
im
u
latio
n
s
,
in
clu
d
in
g
e
x
p
er
im
e
n
tal
co
n
s
tr
ain
t
s
,
s
ize,
an
d
r
eso
u
r
ce
lim
its
P
a
r
a
me
t
e
r
s
D
e
f
a
u
l
t
v
a
l
u
e
M
I
P
S
2
0
0
0
B
a
n
d
w
i
d
t
h
1
G
B
S
i
z
e
o
f
V
M
2
.
5
G
B
P
r
o
c
e
ss
i
n
g
e
l
e
me
n
t
2
U
t
i
l
i
z
a
t
i
o
n
o
f
C
P
U
0
%
t
o
1
0
0
%
4
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
is
s
ec
tio
n
s
ig
n
if
ies
an
an
al
y
s
is
o
f
th
e
s
im
u
latio
n
f
i
n
d
in
g
s
f
o
r
esti
m
atin
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
DM
B
AB
OA.
A
co
m
p
ar
ativ
e
an
aly
s
is
o
f
f
o
u
r
s
ch
e
d
u
lin
g
alg
o
r
ith
m
s
was c
o
n
d
u
cte
d
to
d
eter
m
i
n
e
th
e
s
ig
n
if
ican
ce
o
f
th
e
p
r
o
p
o
s
e
d
ap
p
r
o
ac
h
.
T
h
e
DM
B
AB
OA
ap
p
r
o
ac
h
was
c
o
m
p
ar
e
d
with
t
h
e
co
y
o
te
o
p
tim
izatio
n
alg
o
r
ith
m
(
C
OA)
,
f
o
x
o
p
tim
izatio
n
alg
o
r
ith
m
(
FOA)
,
g
r
ey
w
o
lf
o
p
tim
izatio
n
alg
o
r
ith
m
(
GOA)
,
an
d
co
n
v
en
tio
n
al
B
OA.
T
ab
le
2
p
r
esen
ts
th
e
p
er
f
o
r
m
a
n
ce
an
aly
s
is
o
f
en
er
g
y
c
o
n
s
u
m
p
tio
n
f
o
r
1
0
0
-
1
,
0
0
0
task
s
ac
r
o
s
s
th
e
f
iv
e
s
ch
ed
u
lin
g
al
g
o
r
ith
m
s
.
T
h
e
p
r
o
p
o
s
ed
DM
B
AB
OA
ex
h
ib
its
th
e
lo
west
en
er
g
y
c
o
n
s
u
m
p
tio
n
in
ea
ch
s
ce
n
a
r
io
,
o
u
tp
er
f
o
r
m
in
g
C
OA,
FOA,
GOA,
an
d
co
n
v
en
tio
n
al
B
OA.
T
h
is
im
p
r
o
v
em
en
t
r
esu
lts
f
r
o
m
its
d
ir
ec
tio
n
al
m
o
v
em
en
t
a
n
d
b
o
u
n
d
ar
y
-
aw
ar
e
m
ec
h
an
is
m
s
,
wh
ich
r
ed
u
ce
th
e
n
u
m
b
e
r
o
f
ac
tiv
e
PMs
b
y
ef
f
ec
tiv
ely
co
n
s
o
lid
atin
g
VM
s
.
As
th
e
task
co
u
n
t
in
cr
ea
s
es,
en
er
g
y
co
n
s
u
m
p
tio
n
n
atu
r
ally
in
cr
ea
s
es;
h
o
wev
er
,
DM
B
A
B
OA
m
an
ag
es
th
is
in
cr
ea
s
e
m
o
r
e
ef
f
icien
tly
.
Fo
r
e
x
am
p
le,
f
o
r
1
,
0
0
0
task
s
,
DM
B
AB
OA
co
n
s
u
m
es
2
,
7
3
2
.
9
9
KW
h
,
wh
er
ea
s
C
OA
co
n
s
u
m
es
3
,
6
2
1
.
3
5
KW
h
.
T
h
e
s
ig
n
if
ican
t
e
n
er
g
y
s
av
i
n
g
s
h
ig
h
lig
h
t
th
e
ef
f
ec
tiv
en
ess
o
f
th
is
m
et
h
o
d
f
o
r
p
o
wer
-
awa
r
e
VM
p
lace
m
en
t
,
co
n
tr
ib
u
t
in
g
to
b
o
th
c
o
s
t
r
ed
u
ctio
n
an
d
en
v
ir
o
n
m
en
tal
s
u
s
tain
ab
ilit
y
in
d
atac
en
ter
s
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
en
e
r
g
y
c
o
n
s
u
m
p
tio
n
(
Kwh
)
ac
r
o
s
s
n
u
m
b
e
r
o
f
task
s
co
m
p
ar
in
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
with
e
x
is
tin
g
m
eth
o
d
s
N
u
mb
e
r
o
f
t
a
sk
s
C
O
A
F
O
A
GOA
B
O
A
P
r
o
p
o
se
d
D
M
B
A
B
O
A
1
0
0
5
8
8
.
7
6
5
4
3
.
2
7
5
1
6
.
4
3
4
8
7
.
3
2
4
4
1
.
8
8
3
0
0
1
3
8
7
.
4
1
1
2
9
2
.
1
5
1
2
1
6
.
5
2
1
1
4
0
.
7
9
1
0
5
6
.
7
2
5
0
0
2
1
8
3
.
9
2
2
0
2
4
.
1
8
1
9
1
2
.
6
3
1
7
9
6
.
5
4
1
6
4
8
.
3
8
7
0
0
2
9
2
6
.
1
7
2
7
2
4
.
5
5
2
5
7
8
.
9
2
2
4
1
2
.
1
7
2
2
1
6
.
4
7
1
,
0
0
0
3
6
2
1
.
3
5
3
3
6
5
.
9
1
3
1
8
4
.
4
7
2
9
7
3
.
9
3
2
7
3
2
.
9
9
Fig
u
r
e
4
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
an
aly
s
is
o
f
th
e
m
a
k
esp
an
f
o
r
task
lo
a
d
s
r
an
g
in
g
f
r
o
m
1
0
0
to
1
,
0
0
0
.
T
h
e
m
ak
esp
a
n
r
ef
e
r
s
to
th
e
to
tal
tim
e
r
eq
u
ir
e
d
to
c
o
m
p
lete
all
s
ch
ed
u
led
task
s
.
T
h
e
g
r
a
p
h
d
em
o
n
s
tr
ates
th
at
DM
B
A
B
OA
co
n
s
is
ten
tly
ac
h
iev
ed
th
e
l
o
west
m
ak
esp
an
v
al
u
es
ac
r
o
s
s
all
task
s
izes.
T
h
is
r
ed
u
ctio
n
in
d
icate
s
ef
f
icien
t
u
tili
z
atio
n
o
f
co
m
p
u
tin
g
r
eso
u
r
ce
s
an
d
m
in
im
i
ze
d
s
ch
ed
u
lin
g
d
ela
y
s
.
T
h
e
s
teep
in
cr
ea
s
e
in
m
ak
esp
an
f
o
r
tr
a
d
itio
n
al
m
et
h
o
d
s
(
s
u
ch
as
C
OA
an
d
FOA)
h
ig
h
lig
h
ts
th
eir
lim
itatio
n
s
in
h
an
d
lin
g
lar
g
e
wo
r
k
lo
ad
s
.
Me
an
wh
ile,
DM
B
AB
OA
m
ain
tain
s
lo
w
o
v
er
h
ea
d
ev
e
n
u
n
d
er
p
r
ess
u
r
e,
r
ef
lectin
g
s
u
p
er
io
r
d
y
n
am
ic
s
ch
ed
u
lin
g
an
d
lo
ad
-
b
alan
cin
g
ca
p
ab
ilit
ies.
T
h
is
p
er
f
o
r
m
a
n
ce
en
h
an
ce
m
en
t
en
s
u
r
es
f
aster
r
esp
o
n
s
e
an
d
im
p
r
o
v
ed
Qo
S in
r
ea
l
-
tim
e
clo
u
d
e
n
v
ir
o
n
m
en
ts
.
T
ab
le
3
p
r
esen
ts
th
e
p
e
r
f
o
r
m
a
n
ce
an
aly
s
is
o
f
th
e
av
er
a
g
e
ex
ec
u
tio
n
tim
e
ac
r
o
s
s
d
if
f
er
e
n
t
task
s
u
s
in
g
th
e
f
iv
e
alg
o
r
ith
m
s
.
E
x
ec
u
tio
n
tim
e
is
cr
itical
f
o
r
d
eter
m
in
in
g
clo
u
d
s
y
s
tem
r
esp
o
n
s
iv
en
es
s
.
T
h
e
DM
B
A
B
OA
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
o
th
er
s
,
ac
h
iev
in
g
th
e
lo
west
ex
ec
u
tio
n
tim
es
ac
r
o
s
s
all
task
s
iz
es
f
r
o
m
2
3
.
0
2
s
at
1
0
0
task
s
to
1
4
2
.
6
7
s
at
1
,
0
0
0
task
s
.
T
h
is
ef
f
icien
cy
is
attr
ib
u
ted
to
its
in
tellig
en
t
s
ch
ed
u
li
n
g
m
ec
h
a
n
is
m
th
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
erg
y
-
efficien
t v
ir
tu
a
l m
a
ch
i
n
e
a
llo
ca
tio
n
u
s
in
g
d
ir
ec
tio
n
a
l a
n
d
b
o
u
n
d
a
r
y
-
a
w
a
r
e
…
(
N
id
a
K
o
u
s
a
r
Go
u
s
e)
1295
p
r
io
r
itizes
f
aster
VM
allo
ca
tio
n
an
d
r
eso
u
r
ce
av
ailab
ilit
y
.
T
h
e
tab
le
also
s
h
o
ws
th
at
as
th
e
co
u
n
t
task
s
en
h
an
ce
s
,
a
g
ap
b
etwe
en
DM
B
AB
OA
an
d
th
e
o
th
er
alg
o
r
it
h
m
s
b
ec
o
m
es
m
o
r
e
p
r
o
n
o
u
n
c
ed
.
T
h
is
h
ig
h
lig
h
ts
th
e
s
ca
lab
ilit
y
an
d
ab
ilit
y
to
m
ain
tain
p
er
f
o
r
m
a
n
ce
u
n
d
er
h
ea
v
y
lo
ad
s
.
T
h
e
r
ed
u
ce
d
e
x
ec
u
tio
n
tim
e
also
co
n
tr
ib
u
ted
to
th
e
e
n
h
an
ce
d
u
s
er
s
atis
f
ac
tio
n
an
d
o
v
er
all
s
y
s
tem
th
r
o
u
g
h
p
u
t.
Fig
u
r
e
5
p
r
esen
ts
a
g
r
a
p
h
ical
r
ep
r
esen
tatio
n
o
f
th
e
SLA
v
i
o
latio
n
r
ate
v
er
s
u
s
th
e
n
u
m
b
e
r
o
f
task
s
,
em
p
h
asizin
g
th
e
im
p
r
o
v
ed
r
el
iab
ilit
y
ac
h
iev
ed
u
s
in
g
DM
B
AB
OA.
T
h
e
f
ig
u
r
e
illu
s
tr
ate
s
th
e
SLA
v
io
latio
n
r
ate
u
n
d
er
i
n
cr
ea
s
in
g
task
lo
ad
s
,
wh
er
e
a
n
SLA
v
io
latio
n
o
cc
u
r
s
wh
en
task
s
ar
e
n
o
t
c
o
m
p
leted
with
in
a
s
tip
u
lated
r
esp
o
n
s
e
o
r
e
x
ec
u
t
io
n
tim
e.
DM
B
AB
OA
m
ain
t
ain
ed
th
e
lo
west
SLA
v
io
latio
n
r
ate
am
o
n
g
all
alg
o
r
ith
m
s
test
ed
,
r
ef
lectin
g
its
ef
f
icien
t
an
d
ad
ap
tiv
e
r
eso
u
r
ce
-
m
a
n
ag
em
en
t
s
tr
ateg
y
.
W
ith
tr
ad
itio
n
al
alg
o
r
ith
m
s
,
v
io
latio
n
s
in
cr
e
ase
s
ig
n
if
ican
tly
as
wo
r
k
lo
ad
in
cr
ea
s
es,
in
d
icatin
g
p
o
o
r
s
ca
lab
ilit
y
an
d
u
n
p
r
e
d
ictab
le
task
h
an
d
lin
g
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
e
n
s
u
r
e
s
b
alan
ce
d
lo
ad
d
is
tr
ib
u
tio
n
an
d
s
tr
ateg
ic
VM
p
lace
m
en
t,
r
e
d
u
cin
g
laten
cy
a
n
d
m
is
s
ed
d
ea
d
lin
es.
T
h
is
co
n
s
is
ten
cy
in
SLA
ad
h
e
r
en
ce
m
ak
es
DM
B
AB
O
A
h
ig
h
ly
s
u
itab
le
f
o
r
s
er
v
ice
-
c
r
itical
an
d
tim
e
-
s
en
s
itiv
e
clo
u
d
a
p
p
licatio
n
s
.
T
a
b
le
4
p
r
ese
n
ts
th
e
p
e
r
f
o
r
m
a
n
c
e
a
n
al
y
s
is
o
f
t
h
e
lat
en
c
y
ac
r
o
s
s
d
if
f
e
r
en
t
tas
k
c
o
u
n
ts
,
c
o
m
p
a
r
i
n
g
t
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
wit
h
ex
is
ti
n
g
m
et
h
o
d
s
.
T
h
e
r
es
u
lts
s
h
o
w
t
h
at
DM
B
AB
OA
ac
h
i
e
v
es
t
h
e
lo
w
est
l
ate
n
cy
in
all
wo
r
k
lo
a
d
s
,
r
a
n
g
i
n
g
f
r
o
m
2
9
.
1
7
m
s
at
1
0
0
t
ask
s
to
1
0
5
.
2
8
m
s
a
t
1
,
0
0
0
t
ask
s
.
L
at
en
c
y
r
ep
r
e
s
en
ts
th
e
ti
m
e
d
e
la
y
b
et
we
en
a
u
s
er
’
s
r
eq
u
est
an
d
th
e
s
y
s
te
m
’
s
r
es
p
o
n
s
e.
L
o
w
er
lat
e
n
c
y
v
a
lu
es
in
d
i
ca
t
e
f
as
te
r
a
n
d
m
o
r
e
r
eli
a
b
le
s
er
v
i
ce
p
r
o
v
is
io
n
.
T
h
e
o
th
e
r
al
g
o
r
i
th
m
s
ex
h
i
b
i
t
a
s
h
ar
p
e
r
in
cr
ea
s
e
in
la
te
n
c
y
as
tas
k
c
o
u
n
t
r
i
s
es
,
d
e
m
o
n
s
tr
ati
n
g
p
o
o
r
ad
a
p
ta
b
i
lit
y
an
d
b
o
tt
le
n
ec
k
s
i
n
co
m
m
u
n
i
ca
t
io
n
a
n
d
co
m
p
u
tati
o
n
.
I
n
c
o
n
tr
ast
,
t
h
e
p
r
o
p
o
s
e
d
m
e
th
o
d
ef
f
e
cti
v
e
ly
r
e
d
u
ce
s
q
u
e
u
e
t
im
e
a
n
d
e
n
s
u
r
es
b
e
tte
r
tas
k
-
to
-
r
es
o
u
r
ce
m
a
p
p
i
n
g
.
Di
r
e
cti
o
n
al
-
a
n
d
b
o
u
n
d
a
r
y
-
awa
r
e
s
tr
a
te
g
ies
c
o
n
tr
i
b
u
t
e
s
i
g
n
if
i
ca
n
tly
t
o
r
e
d
u
ci
n
g
p
r
o
c
ess
i
n
g
d
el
ay
s
a
n
d
i
m
p
r
o
v
i
n
g
r
es
p
o
n
s
e
e
f
f
ic
ie
n
c
y
,
wh
ic
h
a
r
e
cr
u
c
ial
f
o
r
in
te
r
a
cti
v
e
a
n
d
r
ea
l
-
tim
e
cl
o
u
d
s
e
r
v
ic
es.
Fig
u
r
e
4
.
Ma
k
esp
a
n
(
s
)
ac
r
o
s
s
th
e
n
u
m
b
er
o
f
task
s
,
co
m
p
ar
in
g
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
with
t
h
e
ex
is
tin
g
m
eth
o
d
s
Fig
u
r
e
5
.
SLA
v
io
latio
n
r
ate
v
er
s
u
s
n
u
m
b
er
o
f
task
s
,
em
p
h
asizin
g
im
p
r
o
v
ed
r
eliab
ilit
y
ac
h
iev
ed
u
s
in
g
DM
B
AB
OA
T
ab
le
3
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
av
e
r
ag
e
ex
ec
u
tio
n
tim
e(
s
)
ac
r
o
s
s
d
if
f
er
en
t ta
s
k
s
f
o
r
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
with
ex
is
tin
g
m
eth
o
d
s
N
u
mb
e
r
o
f
t
a
sk
s
C
O
A
F
O
A
GOA
B
O
A
P
r
o
p
o
se
d
D
M
B
A
B
O
A
1
0
0
3
0
.
2
1
2
8
.
4
7
2
6
.
8
9
2
5
.
1
4
2
3
.
0
2
3
0
0
7
3
.
6
5
6
9
.
8
4
6
4
.
1
5
5
8
.
9
3
5
4
.
2
6
5
0
0
1
1
8
.
3
6
1
1
0
.
2
7
1
0
2
.
8
6
9
5
.
4
1
8
7
.
6
5
7
0
0
1
6
0
.
4
8
1
4
9
.
1
6
1
3
7
.
9
4
1
2
6
.
0
3
1
1
5
.
4
2
1
0
0
0
1
9
8
.
9
2
1
8
3
.
5
7
1
7
0
.
4
2
1
5
6
.
7
8
1
4
2
.
6
7
T
a
b
l
e
4
.
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
is
o
f
l
a
t
e
n
c
y
(
m
s
)
a
c
r
o
s
s
d
i
f
f
e
r
e
n
t
t
a
s
k
s
f
o
r
p
r
o
p
o
s
e
d
m
e
t
h
o
d
w
i
th
e
x
i
s
t
i
n
g
m
et
h
o
d
s
N
u
mb
e
r
o
f
t
a
sk
s
C
O
A
F
O
A
GOA
B
O
A
P
r
o
p
o
se
d
D
M
B
A
B
O
A
1
0
0
3
8
.
5
4
3
6
.
1
7
3
4
.
2
6
3
2
.
4
5
2
9
.
1
7
3
0
0
6
4
.
2
8
6
0
.
9
2
5
6
.
1
4
5
2
.
4
7
4
8
.
3
6
5
0
0
9
1
.
4
3
8
5
.
1
6
7
8
.
7
2
7
3
.
2
8
6
7
.
4
9
7
0
0
1
1
5
.
8
9
1
0
8
.
3
6
1
0
0
.
2
7
9
4
.
3
8
8
6
.
4
5
1
,
0
0
0
1
4
2
.
3
6
1
3
3
.
2
9
1
2
3
.
1
6
1
1
5
.
3
4
1
0
5
.
2
8
T
ab
le
5
p
r
esen
ts
th
e
co
n
v
e
r
g
e
n
ce
b
eh
a
v
io
r
o
f
th
e
o
p
tim
izatio
n
ap
p
r
o
ac
h
es
b
y
tr
ac
k
in
g
th
eir
f
itn
ess
v
alu
es
o
v
er
5
0
iter
atio
n
s
.
D
MBAB
OA
ex
h
ib
ited
r
ap
id
an
d
m
o
s
t
r
eliab
le
co
n
v
er
g
en
c
e,
ac
co
m
p
lis
h
in
g
a
f
itn
ess
v
alu
e
o
f
0
.
9
7
,
wh
e
r
ea
s
th
e
o
th
er
s
co
n
v
er
g
ed
m
o
r
e
s
lo
wly
an
d
to
lo
wer
v
alu
es.
T
h
is
in
d
icate
s
th
at
DM
B
A
B
OA
q
u
ick
ly
id
en
tifie
s
n
ea
r
-
o
p
tim
al
s
o
lu
tio
n
s
with
f
ewe
r
iter
atio
n
s
,
th
er
eb
y
im
p
r
o
v
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.