I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
3
,
J
u
n
e
2021
,
p
p
.
2211
~
2
2
1
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
11
i
3
.
p
p
2
2
1
1
-
2
2
1
8
2211
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Tra
ff
ic
-
a
w
a
re ad
a
ptive serv
er loa
d
bala
ncing
f
o
r so
f
tw
a
re
defined
net
w
o
rk
s
C.
F
a
ncy
1
,
M
.
P
us
hp
a
la
t
ha
2
1
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Ka
tt
a
n
k
u
lath
u
r
,
In
d
ia
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Ka
tt
a
n
k
u
lath
u
r
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
5
,
2
0
2
0
R
ev
i
s
ed
Sep
1
5
,
2
0
2
0
A
cc
ep
ted
Oct
9
,
2
0
20
S
e
rv
e
rs
in
d
a
ta
c
e
n
ter
n
e
tw
o
rk
s
h
a
n
d
le
h
e
tero
g
e
n
e
o
u
s
b
u
lk
l
o
a
d
s.
L
o
a
d
b
a
lan
c
in
g
,
th
e
re
f
o
re
,
p
lay
s
a
n
im
p
o
rtan
t
ro
le
in
o
p
ti
m
izin
g
n
e
t
w
o
rk
b
a
n
d
w
id
th
a
n
d
m
in
im
izin
g
re
sp
o
n
se
ti
m
e
.
A
c
o
m
p
lete
k
n
o
w
le
d
g
e
o
f
th
e
c
u
rre
n
t
n
e
tw
o
rk
sta
tu
s
is
n
e
e
d
e
d
t
o
p
r
o
v
id
e
a
sta
b
le
lo
a
d
in
t
h
e
n
e
t
w
o
rk
.
T
h
e
p
ro
c
e
ss
o
f
n
e
t
w
o
rk
sta
tu
s
c
a
talo
g
in
a
trad
it
io
n
a
l
n
e
tw
o
rk
n
e
e
d
s
a
d
d
it
io
n
a
l
p
ro
c
e
ss
in
g
w
h
ich
in
c
re
a
se
s
c
o
m
p
lex
it
y
,
w
h
e
re
a
s
,
in
so
f
twa
r
e
d
e
f
in
e
d
n
e
tw
o
rk
in
g
,
th
e
c
o
n
tr
o
l
p
lan
e
m
o
n
it
o
rs
th
e
o
v
e
ra
ll
w
o
rk
in
g
o
f
th
e
n
e
tw
o
rk
c
o
n
ti
n
u
o
u
sly
.
He
n
c
e
it
is
d
e
c
id
e
d
to
p
ro
p
o
se
a
n
e
f
f
i
c
ien
t
lo
a
d
b
a
lan
c
in
g
a
lg
o
rit
h
m
th
a
t
a
d
a
p
ts
S
DN
.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
e
ff
icie
n
t
a
lg
o
rit
h
m
TA
-
A
S
LB
-
tra
ff
ic
-
a
wa
re
a
d
a
p
ti
v
e
se
r
v
e
r
lo
a
d
b
a
la
n
c
in
g
t
o
b
a
la
n
c
e
th
e
f
lo
ws
to
th
e
se
rv
e
rs
in
a
d
a
ta
c
e
n
ter
n
e
tw
o
rk
.
It
w
o
rk
s
b
a
se
d
o
n
tw
o
p
a
ra
m
e
ters
,
re
sid
u
a
l
b
a
n
d
w
id
th
,
a
n
d
se
rv
e
r
c
a
p
a
c
it
y
.
It
d
e
tec
ts
th
e
e
lep
h
a
n
t
f
lo
w
s
a
n
d
f
o
r
w
a
rd
s
th
e
m
to
w
a
rd
s
th
e
o
p
ti
m
a
l
se
rv
e
r
w
h
e
re
it
c
a
n
b
e
p
ro
c
e
ss
e
d
q
u
ick
ly
.
It
h
a
s
b
e
e
n
tes
ted
w
it
h
th
e
M
in
i
n
e
t
sim
u
lato
r
a
n
d
g
a
v
e
c
o
n
sid
e
ra
b
ly
b
e
tt
e
r
re
su
lt
s
c
o
m
p
a
re
d
to
th
e
e
x
isti
n
g
se
rv
e
r
lo
a
d
b
a
lan
c
i
n
g
a
lg
o
rit
h
m
s
in
th
e
f
lo
o
d
li
g
h
t
c
o
n
tro
l
ler.
Af
ter
e
x
p
e
ri
m
e
n
tatio
n
a
n
d
a
n
a
ly
sis,
it
is
u
n
d
e
rsto
o
d
t
h
a
t
th
e
m
e
th
o
d
p
ro
v
id
e
s
c
o
m
p
a
ra
ti
v
e
l
y
b
e
tt
e
r
re
su
lt
s
th
a
n
t
h
e
e
x
isti
n
g
lo
a
d
b
a
lan
c
in
g
a
lg
o
rit
h
m
s.
K
ey
w
o
r
d
s
:
Data
ce
n
ter
n
et
w
o
r
k
s
Flo
o
d
lig
h
t c
o
n
tr
o
ller
SDN
Ser
v
er
lo
ad
b
alan
cin
g
T
h
is
is
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
C.
Fan
c
y
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
SR
M
I
n
s
tit
u
te
o
f
Sc
ien
ce
a
n
d
T
ec
h
n
o
lo
g
y
P
o
th
er
i,
Kan
ch
ee
p
u
r
a
m
,
T
am
i
ln
ad
u
,
603203
-
I
n
d
ia
E
m
ail:
f
an
c
y
c
@
s
r
m
is
t.e
d
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
Data
ce
n
ter
n
et
w
o
r
k
s
(
DC
N)
f
ac
es
d
if
f
er
en
t
t
y
p
es
o
f
w
o
r
k
lo
ad
esp
ec
iall
y
i
n
3
asp
ec
ts
lik
e
b
u
s
i
n
es
s
,
co
n
s
u
m
er
,
an
d
en
ter
tai
n
m
en
t.
DC
Ns
u
s
u
a
ll
y
s
u
p
p
o
r
t
m
u
lt
i
p
le
p
ath
s
b
et
w
ee
n
an
y
e
n
d
h
o
s
ts
.
DC
N
s
s
h
o
u
ld
h
an
d
le
b
o
th
th
e
ca
te
g
o
r
ies
o
f
f
lo
w
s
-
e
lep
h
a
n
t
an
d
m
ice
f
l
o
w
s
[
1
]
.
T
h
e
m
ai
n
ai
m
o
f
l
o
ad
b
alan
cin
g
is
to
i
m
p
r
o
v
e
t
h
e
th
r
o
u
g
h
p
u
t
av
o
id
i
n
g
p
r
o
ce
s
s
i
n
g
d
ela
y
s
i
n
o
p
ti
m
al
p
a
th
s
elec
tio
n
to
b
ala
n
ce
t
h
e
lo
ad
.
T
h
e
v
ar
io
u
s
f
ac
to
r
s
in
f
l
u
en
c
in
g
lo
ad
b
alan
cin
g
i
n
DC
N
i
n
cl
u
d
e
th
e
en
er
g
y
o
f
n
o
d
es,
r
esid
u
al
b
an
d
w
id
th
,
s
ca
lab
ilit
y
o
f
th
e
n
et
w
o
r
k
,
t
y
p
e
s
o
f
f
lo
w
s
.
W
ith
th
e
in
cr
ea
s
i
n
g
n
u
m
b
er
o
f
d
ev
ices
in
t
h
e
n
et
w
o
r
k
,
m
a
n
ag
i
n
g
th
e
n
et
w
o
r
k
tr
a
f
f
ic
is
b
ec
o
m
i
n
g
v
er
y
d
i
f
f
ic
u
lt
[
2
]
.
Av
o
id
in
g
b
u
f
f
er
o
v
er
f
lo
w
s
is
an
o
th
er
m
aj
o
r
co
n
ce
r
n
.
A
ls
o
,
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
n
o
d
e
m
a
y
b
e
ch
o
s
e
n
r
ep
ea
ted
ly
,
w
h
ic
h
lead
s
to
its
q
u
ick
er
d
eg
r
ad
atio
n
.
B
alan
cin
g
th
e
i
n
co
m
i
n
g
lo
ad
am
o
n
g
t
h
e
s
er
v
er
s
i
n
d
ata
ce
n
ter
n
et
w
o
r
k
s
ca
n
b
e
s
ee
n
i
n
v
ar
io
u
s
asp
ec
ts
lik
e
li
n
k
lo
ad
b
alan
cin
g
,
s
er
v
er
lo
ad
b
alan
cin
g
.
Few
o
f
th
e
d
ela
y
-
s
en
s
iti
v
e
ap
p
licatio
n
s
in
c
lu
d
e
r
ea
l
-
ti
m
e
v
id
eo
an
d
v
o
ice.
Dela
y
s
en
s
iti
v
e
ap
p
licatio
n
s
n
ee
d
t
o
m
ain
tain
th
e
Qo
S
p
ar
a
m
et
er
s
also
.
T
h
e
lo
ad
b
alan
cin
g
al
g
o
r
ith
m
m
u
s
t
als
o
i
m
p
r
o
v
is
e
th
e
m
e
tr
ics
s
u
c
h
as
s
ca
lab
ili
t
y
,
r
o
b
u
s
tn
e
s
s
,
e
n
e
r
g
y
e
f
f
icie
n
c
y
,
etc.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
3
,
J
u
n
e
2021
:
2
2
1
1
-
2218
2212
T
h
e
lin
k
u
tili
za
tio
n
v
ar
ies
i
n
t
h
e
D
C
N,
al
s
o
t
h
e
co
n
g
e
s
tio
n
i
n
cr
ea
s
es
i
n
t
h
e
b
o
tto
m
la
y
er
s
.
T
h
e
t
y
p
e
o
f
f
lo
w
i
s
an
o
th
er
m
aj
o
r
co
m
p
o
n
e
n
t
t
h
a
t
v
ar
ies
d
y
n
a
m
icall
y
[
3
,
4
]
.
T
h
er
e
ar
e
t
w
o
p
o
s
s
ib
ilit
ie
s
o
f
f
lo
w
,
i.e
.
m
ice
f
lo
w
an
d
elep
h
an
t
f
lo
w
.
U
s
u
al
l
y
,
t
h
er
e
ar
e
a
lo
t
o
f
m
ice
f
lo
w
s
e.
g
.
h
ello
m
es
s
a
g
es,
m
eta
-
d
at
a
r
eq
u
est
s,
etc.
T
h
e
elep
h
an
t
f
lo
w
ta
k
es
h
u
g
e
r
eso
u
r
ce
s
b
u
t i
t h
ap
p
en
s
n
o
t a
s
f
r
e
q
u
en
t
ly
as
th
e
m
ice
f
lo
w
s
.
A
s
tat
is
tical
r
ep
o
r
t sa
y
s
th
at
th
e
r
ate
o
f
v
id
eo
tr
af
f
ic
i
n
a
DC
N
is
i
n
cr
ea
s
i
n
g
i
n
a
h
ea
v
il
y
.
An
ef
f
icie
n
t
w
a
y
o
f
co
n
tr
o
llin
g
n
et
w
o
r
k
d
ev
ices
is
g
i
v
en
i
n
p
ap
er
[
5
]
.
T
h
e
n
et
w
o
r
k
i
s
p
ar
titi
o
n
ed
in
t
o
v
ar
io
u
s
s
u
b
-
d
o
m
ai
n
s
.
E
ac
h
s
u
b
-
d
o
m
ai
n
h
as
a
n
SDN
en
ab
led
b
o
r
d
er
r
o
u
ter
th
at
h
elp
s
i
n
r
o
u
ti
n
g
to
o
th
er
d
o
m
ai
n
s
.
Her
e
t
h
e
n
e
t
w
o
r
k
m
an
ag
e
m
e
n
t
i
s
ad
ap
tiv
e
.
B
ec
au
s
e,
if
th
e
d
o
m
ain
s
ize
is
lar
g
e,
i
n
ter
-
d
o
m
ai
n
m
an
a
g
e
m
en
t
f
u
n
ctio
n
s
w
er
e
v
er
y
l
ess
co
m
p
ar
ed
to
a
s
m
al
ler
d
o
m
a
in
s
ize.
W
ith
th
i
s
s
ce
n
ar
io
,
ef
f
ec
tiv
e
n
es
s
i
s
ac
h
iev
ed
i
n
t
h
e
s
ca
lab
il
it
y
o
f
b
an
d
w
id
th
allo
ca
tio
n
,
r
o
u
te
d
eter
m
in
at
io
n
b
ased
o
n
cu
r
r
en
t lo
ad
,
an
d
r
ec
o
v
er
y
f
r
o
m
f
a
ilu
r
e
s
.
T
h
e
ch
allen
g
e
s
o
f
w
ir
eless
n
et
w
o
r
k
v
ir
tu
al
izatio
n
[
6
]
ar
e
h
ig
h
l
y
v
ar
y
in
g
tr
af
f
ic,
m
u
ltid
i
m
e
n
s
io
n
al
h
eter
o
g
e
n
eit
y
.
B
esid
es
th
e
s
e
d
r
a
w
b
ac
k
s
,
ef
f
icie
n
c
y
ca
n
b
e
ac
h
iev
ed
in
Qo
S
p
r
o
v
i
s
io
n
i
n
g
,
r
eso
u
r
ce
s
h
ar
i
n
g
,
an
d
v
er
if
ica
tio
n
o
f
n
e
w
tech
n
i
q
u
es
b
ef
o
r
e
it
ca
n
b
e
w
id
el
y
d
ep
lo
y
ed
.
T
h
e
r
eso
u
r
ce
allo
ca
tio
n
in
i
n
ter
v
ir
t
u
al
n
et
w
o
r
k
m
u
s
t
b
e
d
y
n
a
m
ic.
T
h
is
is
d
u
e
to
th
e
c
h
a
n
g
e
s
i
n
s
er
v
ice
r
eq
u
ir
e
m
en
t
s
a
n
d
n
e
w
r
e
q
u
est
s
f
o
r
th
e
v
ir
t
u
al
n
et
w
o
r
k
.
Mu
j
io
n
o
[
7
]
ex
p
lain
s
th
e
is
s
u
es
in
cr
ea
tin
g
a
lo
ad
-
b
alan
ce
d
ag
g
r
e
g
atio
n
tr
ee
f
o
r
a
w
ir
el
ess
s
en
s
o
r
n
et
w
o
r
k
.
H
e
a
n
al
y
ze
d
th
r
ee
r
e
lated
p
r
o
b
lem
s
a
n
d
p
r
o
p
o
s
ed
an
o
p
ti
m
al
s
o
lu
tio
n
.
T
h
e
y
h
a
v
e
p
r
ep
ar
ed
a
tr
af
f
ic
m
atr
i
x
th
at
h
elp
ed
in
a
n
al
y
s
i
n
g
th
e
p
ar
a
m
eter
s
o
f
t
h
e
to
p
o
lo
g
y
.
T
h
e
i
m
p
o
r
tan
t
p
ar
a
m
e
ter
d
is
cu
s
s
ed
in
t
h
eir
m
o
d
el
is
th
e
tr
an
s
m
is
s
io
n
s
u
cc
ess
r
atio
f
o
r
e
v
er
y
l
in
k
i
n
th
e
n
et
w
o
r
k
.
T
h
is
r
atio
d
e
f
i
n
es
th
e
s
u
cc
es
s
f
u
l
d
eliv
er
y
o
f
t
h
e
p
ac
k
et.
An
o
th
e
r
t
w
o
m
etr
ic
s
w
h
ic
h
ar
e
u
s
ed
i
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
in
c
lu
d
e
p
o
ten
tial
lo
ad
an
d
ac
tu
al
lo
ad
.
T
h
e
tech
n
iq
u
es
u
s
ed
to
s
o
lv
e
th
e
id
en
ti
f
ied
p
r
o
b
le
m
ar
e
lin
ea
r
r
elax
atio
n
an
d
r
an
d
o
m
r
o
u
n
d
in
g
.
Up
o
n
an
al
y
s
i
s
,
it is
f
o
u
n
d
th
at
th
e
p
r
o
p
o
s
ed
id
ea
in
cr
ea
s
es th
e
n
et
w
o
r
k
li
f
eti
m
e.
T
h
e
p
ap
er
[
8
]
p
r
o
p
o
s
ed
a
m
y
o
p
ic
alg
o
r
ith
m
th
a
t
u
s
es
t
h
e
co
s
t
o
f
ea
ch
l
in
k
to
d
ec
id
e
th
e
p
ath
.
W
h
e
n
a
f
lo
w
ar
r
iv
es,
it
s
en
d
s
th
r
o
u
g
h
th
e
p
at
h
h
a
v
i
n
g
th
e
m
i
n
i
m
u
m
co
s
t.
T
h
e
y
al
s
o
test
ed
w
it
h
v
ar
y
i
n
g
v
er
s
io
n
s
o
f
m
y
o
p
ic
al
g
o
r
it
h
m
an
d
o
b
tai
n
e
d
b
etter
n
et
w
o
r
k
ef
f
ici
e
n
c
y
.
B
en
lalia
[
9
]
m
ak
e
s
u
s
e
o
f
th
e
g
r
ee
d
y
r
o
u
n
d
-
r
o
b
in
alg
o
r
ith
m
.
T
h
e
ch
allen
g
e
s
o
f
v
e
h
ic
u
lar
ad
h
o
c
n
et
w
o
r
k
s
(
VANE
T
s
)
[
10
]
s
u
ch
as
m
o
b
ilit
y
a
n
d
s
ca
lab
ilit
y
a
f
f
ec
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
r
o
u
ti
n
g
p
r
o
to
co
l.
W
ith
th
e
h
e
lp
o
f
S
DN,
a
s
o
lu
t
io
n
f
o
r
th
e
s
e
is
s
u
es
w
a
s
f
o
u
n
d
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
n
cl
u
d
es
t
h
e
SDN
b
ased
co
n
n
ec
tiv
it
y
a
w
ar
e
g
eo
g
r
ap
h
ical
r
o
u
ti
n
g
p
r
o
to
co
l.
I
n
th
e
s
i
m
u
lat
io
n
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
p
r
o
v
id
ed
an
o
p
tim
ized
r
o
u
tin
g
p
ath
w
h
ile
th
e
f
o
llo
win
g
p
ar
a
m
e
ter
s
ar
e
ev
alu
a
ted
; i)
Dete
r
m
i
n
i
n
g
t
h
e
t
r
af
f
ic
d
e
n
s
it
y
,
ii)
T
r
ac
k
in
g
t
h
e
d
is
tan
ce
,
an
d
iii)
E
s
t
i
m
a
tin
g
t
h
e
lin
k
l
if
e
ti
m
e.
T
h
u
s
,
l
o
ad
b
alan
cin
g
is
an
i
m
p
o
r
tan
t
task
in
an
y
d
ata
ce
n
ter
.
T
h
er
e
w
ill
b
e
m
u
ltip
le
s
er
v
er
s
in
ev
er
y
DC
N,
co
m
p
u
tin
g
co
n
t
in
u
o
u
s
l
y
f
o
r
p
r
o
v
id
in
g
s
ea
m
les
s
c
o
n
n
ec
ti
v
it
y
f
o
r
ap
p
licatio
n
s
s
u
c
h
a
s
W
h
at
s
A
p
p
,
Face
b
o
o
k
,
w
eb
s
ea
r
ch
,
liv
e
p
r
o
g
r
am
s
,
etc.
Hen
ce
it
is
n
ee
d
ed
to
f
o
cu
s
o
n
th
e
s
er
v
er
lo
ad
b
alan
cin
g
alg
o
r
ith
m
s
.
T
h
is
p
ap
er
ai
m
s
to
f
o
c
u
s
o
n
t
h
e
s
er
v
er
lo
ad
b
alan
ci
n
g
i
n
a
h
e
ter
o
g
en
eo
u
s
s
er
v
er
en
v
ir
o
n
m
e
n
t.
I
t
al
s
o
f
o
cu
s
es
o
n
h
o
w
t
h
e
co
n
tr
o
ller
ca
n
ad
ap
tiv
el
y
c
h
o
o
s
e
th
e
alg
o
r
ith
m
s
.
T
h
i
s
ad
ap
tiv
it
y
i
s
in
cl
u
d
ed
to
av
o
id
ad
d
itio
n
al
co
m
p
le
x
it
y
to
t
h
e
lo
ad
b
alan
cin
g
m
o
d
u
le.
T
h
e
p
r
o
p
o
s
ed
p
ap
er
is
d
esig
n
e
d
ac
co
r
d
in
g
to
th
e
f
o
llo
w
in
g
p
r
o
to
co
l
.
I
n
s
ec
tio
n
2
,
w
e
ex
p
lai
n
t
h
e
i
m
p
o
r
tan
t
s
i
m
ilar
r
esear
ch
asp
ec
ts
,
s
ec
ti
o
n
3
ex
p
lain
s
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
s
ec
tio
n
a
n
d
s
ec
tio
n
4
an
al
y
s
es t
h
e
ex
p
er
i
m
e
n
tatio
n
d
o
n
e
b
y
t
h
e
a
u
th
o
r
s
.
2.
RE
L
AT
E
D
WO
RK
S
A
lo
t
o
f
r
esear
c
h
er
s
h
a
v
e
co
n
t
r
ib
u
ted
to
th
e
s
er
v
er
lo
ad
b
alan
cin
g
r
esear
c
h
.
T
h
e
s
elec
tio
n
o
f
th
e
b
est
r
o
u
tin
g
p
ath
is
al
w
a
y
s
a
n
ex
p
e
n
s
i
v
e
w
o
r
k
in
(
D
C
N)
d
ata
ce
n
ter
n
et
w
o
r
k
s
[
1
1
-
1
3
]
.
T
h
e
m
aj
o
r
p
ar
am
eter
s
to
b
e
co
n
s
id
er
ed
w
h
ile
s
elec
ti
n
g
a
n
o
p
tim
a
l
p
ath
ar
e
s
to
r
ag
e
r
e
s
o
u
r
ce
,
b
an
d
w
id
t
h
co
n
s
u
m
p
tio
n
,
an
d
d
ela
y
i
n
p
ac
k
et
tr
an
s
m
is
s
io
n
.
T
o
i
m
p
r
o
v
e
th
e
clo
u
d
g
a
m
in
g
e
x
p
er
ien
ce
,
t
h
e
h
ier
ar
ch
y
p
r
o
ce
s
s
co
u
ld
b
e
u
s
ed
.
T
h
e
p
r
o
ce
s
s
ass
u
r
ed
b
etter
r
esu
lts
,
o
n
ce
th
e
r
o
u
tin
g
p
at
h
f
o
r
a
g
a
m
e
s
e
s
s
io
n
is
ch
o
s
e
n
b
ased
o
n
th
e
g
a
m
e
t
y
p
e.
DC
N
s
ar
e
m
u
ltil
a
y
er
ed
to
p
o
lo
g
y
.
T
h
e
co
llab
o
r
atio
n
o
f
SDN
b
ased
m
u
ltip
at
h
T
C
P
an
d
s
eg
m
e
n
t
r
o
u
ti
n
g
[
1
4
,
1
5
]
i
m
p
r
o
v
es
t
h
e
ef
f
icien
t
u
s
a
g
e
o
f
m
e
m
o
r
y
r
eso
u
r
ce
s
.
Vir
tu
a
liz
atio
n
s
u
p
p
o
r
ts
th
e
ex
i
s
te
n
ce
o
f
s
ev
er
al
n
e
t
w
o
r
k
s
in
o
n
e
s
u
b
s
tr
ate
n
et
w
o
r
k
.
T
h
is
w
o
r
k
co
u
ld
b
e
d
o
n
e
b
y
a
ce
n
tr
alize
d
co
n
tr
o
ll
er
.
B
y
th
i
s
,
th
e
r
eso
u
r
ce
s
w
h
ic
h
ar
e
u
tili
ze
d
ca
n
b
e
r
ed
u
ce
d
an
d
th
e
s
er
v
ice
to
s
e
v
er
al
clien
ts
ca
n
b
e
in
cr
ea
s
ed
.
T
h
is
m
et
h
o
d
p
r
o
v
id
es a
n
o
n
li
n
e
ap
p
r
o
ac
h
to
s
er
v
e
t
h
e
clo
u
d
clien
t r
eq
u
e
s
ts
.
T
h
e
p
ap
er
[
1
6
]
p
r
o
p
o
s
e
d
a
m
y
o
p
ic
al
g
o
r
ith
m
t
h
at
u
s
es
th
e
co
s
t
o
f
ea
c
h
li
n
k
to
d
ec
id
e
th
e
p
ath
.
W
h
e
n
a
f
lo
w
ar
r
iv
es,
it
s
e
n
d
s
th
r
o
u
g
h
th
e
p
ath
h
a
v
i
n
g
t
h
e
m
i
n
i
m
u
m
co
s
t.
T
h
ey
also
test
ed
w
it
h
v
a
r
y
in
g
v
er
s
io
n
s
o
f
m
y
o
p
ic
alg
o
r
ith
m
a
n
d
o
b
tain
ed
b
etter
n
et
w
o
r
k
ef
f
icie
n
c
y
.
T
h
e
a
u
t
h
o
r
s
i
n
[
1
7
-
1
9
]
m
a
k
e
u
s
e
o
f
t
h
e
g
r
ee
d
y
r
o
u
n
d
-
r
o
b
in
al
g
o
r
ith
m
.
T
h
e
p
r
o
p
o
s
ed
lo
ad
b
alan
cin
g
is
b
ased
o
n
t
h
e
f
lo
w
s
ize.
T
h
e
a
lg
o
r
ith
m
i
s
u
s
ed
o
n
l
y
f
o
r
t
h
e
lo
n
g
f
lo
w
s
,
h
e
n
ce
r
ed
u
c
e
th
e
co
n
tr
o
ller
's
w
o
r
k
l
o
ad
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
a
s
w
itc
h
ca
n
b
e
an
al
y
s
ed
w
it
h
t
h
e
h
elp
o
f
q
u
e
u
in
g
m
o
d
el
s
[
2
0
,
2
1
]
.
T
h
e
ch
allen
g
e
s
o
f
w
ir
eless
n
et
w
o
r
k
v
ir
tu
a
lizatio
n
[
2
2
]
ar
e
h
ig
h
l
y
v
ar
y
i
n
g
tr
af
f
ic,
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
-
8708
Tr
a
ffic
-
a
w
a
r
e
a
d
a
p
tive
s
erver
lo
a
d
b
a
la
n
cin
g
fo
r
s
o
ftw
a
r
e
d
efin
ed
n
etw
o
r
ks
(
C
.
F
a
n
cy
)
2213
m
u
ltid
i
m
en
s
io
n
al
h
eter
o
g
e
n
ei
t
y
.
B
esid
es
t
h
ese
d
r
a
w
b
ac
k
s
,
ef
f
icien
c
y
ca
n
b
e
ac
h
ie
v
ed
in
Qo
S
p
r
o
v
is
io
n
i
n
g
,
r
eso
u
r
ce
s
h
ar
i
n
g
,
a
n
d
v
er
if
ic
atio
n
o
f
n
e
w
tec
h
n
iq
u
es
b
e
f
o
r
e
it
ca
n
b
e
w
id
el
y
d
ep
lo
y
ed
.
T
h
e
r
eso
u
r
ce
allo
ca
tio
n
i
n
i
n
ter
v
ir
t
u
al
n
et
w
o
r
k
m
u
s
t
b
e
d
y
n
a
m
ic.
T
h
i
s
is
d
u
e
to
t
h
e
c
h
an
g
e
s
in
s
er
v
i
ce
r
eq
u
ir
e
m
e
n
ts
a
n
d
n
e
w
r
eq
u
est
s
f
o
r
th
e
v
ir
t
u
al
n
e
t
w
o
r
k
s
.
I
n
th
e
f
lo
o
d
lig
h
t
co
n
tr
o
ller
[
2
3
,
2
4
]
,
th
er
e
ar
e
f
e
w
tr
ad
itio
n
al
lo
ad
b
alan
cin
g
al
g
o
r
ith
m
s
av
ailab
le.
T
h
ey
ar
e
R
R
ap
p
r
o
ac
h
,
w
ei
g
h
t
in
d
u
ce
d
RR
m
e
th
o
d
,
an
d
s
tatis
t
ical
m
et
h
o
d
.
I
n
th
e
w
ei
g
h
ted
r
o
u
n
d
-
r
o
b
in
m
et
h
o
d
,
th
e
p
o
s
s
ib
le
p
ath
s
to
r
ea
ch
th
e
d
esti
n
atio
n
ar
e
f
o
u
n
d
.
T
h
en
b
ased
o
n
th
e
w
e
ig
h
t
s
f
o
r
ea
ch
o
f
th
ese
p
ath
s
,
th
e
o
n
e
h
a
v
in
g
t
h
e
h
i
g
h
est
w
ei
g
h
t
w
ill
b
e
ch
o
s
e
n
.
T
h
e
s
tatis
tical
m
et
h
o
d
is
b
ased
o
n
th
e
r
e
m
ai
n
in
g
b
an
d
w
id
t
h
u
s
ed
.
I
f
th
e
r
e
m
ain
i
n
g
b
a
n
d
w
id
th
o
f
a
n
o
d
e
is
h
i
g
h
er
,
th
e
n
it
w
ill b
e
ch
o
s
e
n
f
o
r
th
e
tr
an
s
m
i
s
s
io
n
.
T
h
e
m
ain
ai
m
o
f
lo
ad
b
alan
c
i
n
g
[
2
5
-
28]
is
to
i
m
p
r
o
v
e
t
h
e
t
h
r
o
u
g
h
p
u
t
av
o
id
i
n
g
p
r
o
ce
s
s
in
g
d
ela
y
s
i
n
o
p
tim
a
l
p
ath
s
elec
tio
n
to
b
ala
n
ce
th
e
lo
ad
.
T
h
e
v
ar
io
u
s
f
ac
t
o
r
s
in
f
l
u
e
n
cin
g
lo
ad
b
alan
cin
g
in
DC
N
in
c
lu
d
e
th
e
en
er
g
y
o
f
n
o
d
es,
r
esid
u
al
b
an
d
w
id
t
h
,
s
ca
lab
ilit
y
o
f
t
h
e
n
et
w
o
r
k
,
t
y
p
es
o
f
f
lo
w
s
.
W
it
h
t
h
e
in
cr
ea
s
i
n
g
n
u
m
b
er
o
f
d
ev
ices
in
t
h
e
n
et
w
o
r
k
,
m
an
ag
i
n
g
th
e
n
e
t
w
o
r
k
tr
af
f
ic
is
b
ec
o
m
i
n
g
v
er
y
d
if
f
ic
u
lt
.
I
n
t
h
is
p
ap
er
,
w
e
h
av
e
d
ev
is
ed
a
tr
af
f
ic
-
a
w
ar
e
s
er
v
er
lo
ad
b
alan
cin
g
t
h
at
w
o
r
k
s
a
d
ap
tiv
el
y
.
I
t
ch
ec
k
s
t
h
e
in
co
m
i
n
g
f
lo
w
t
y
p
e
a
n
d
ca
teg
o
r
izes
it
as
s
h
o
r
t
f
lo
w
a
n
d
lo
n
g
f
lo
w
.
Di
f
f
er
en
t
iati
n
g
s
h
o
r
t
f
lo
w
a
n
d
lo
n
g
f
lo
w
s
is
a
s
ep
ar
ate
r
esear
ch
to
p
ic
b
u
t
w
e
h
a
v
e
ta
k
en
f
e
w
r
e
f
er
en
ce
s
f
o
r
d
if
f
er
en
tia
tin
g
t
h
e
f
lo
w
s
t
h
at
h
elp
ed
in
f
o
cu
s
i
n
g
o
n
o
u
r
r
esear
ch
.
T
h
e
p
r
o
p
o
s
ed
lo
a
d
b
alan
cin
g
is
w
o
r
k
i
n
g
b
ased
o
n
t
h
e
f
lo
w
s
ize.
T
h
e
alg
o
r
ith
m
is
u
s
ed
o
n
l
y
f
o
r
th
e
lo
n
g
f
lo
w
s
.
T
h
e
f
ir
s
t
s
tep
is
t
o
d
is
tin
g
u
i
s
h
th
e
in
co
m
i
n
g
f
l
o
w
s
in
to
s
h
o
r
t
an
d
lo
n
g
f
lo
ws
,
t
h
e
n
t
h
e
ad
ap
tiv
e
alg
o
r
ith
m
.
He
n
ce
r
ed
u
cin
g
t
h
e
co
n
tr
o
ller
'
s
co
m
p
u
tatio
n
al
o
v
er
h
ea
d
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
co
n
s
i
s
t
s
o
f
th
r
ee
p
h
ase
s
tr
a
f
f
ic
m
o
n
i
to
r
in
g
p
h
ase,
A
d
ap
ti
v
e
d
ec
is
i
o
n
p
h
ase,
s
er
v
er
s
elec
tio
n
p
h
ase.
I
n
t
h
e
tr
af
f
ic
m
o
n
i
to
r
in
g
p
h
ase
,
t
h
e
co
n
tr
o
ller
m
o
n
i
to
r
s
t
h
e
e
n
tire
to
p
o
lo
g
y
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
ta
k
es
th
r
ee
i
m
p
o
r
ta
n
t
d
etail
s
w
h
ic
h
ar
e
t
h
e
s
ize
o
f
ea
ch
f
lo
w
,
r
e
s
id
u
al
b
an
d
w
id
th
in
a
ll
t
h
e
lin
k
s
to
t
h
e
s
er
v
er
s
,
a
n
d
co
m
p
u
tatio
n
a
l
ca
p
ac
it
y
o
f
all
th
e
a
v
ailab
le
s
er
v
er
s
.
T
h
e
s
ec
o
n
d
p
h
ase
is
t
h
e
A
d
ap
ti
v
e
d
ec
is
io
n
p
h
a
s
e
.
I
f
t
h
e
f
lo
w
s
i
ze
is
les
s
t
h
a
n
a
t
h
r
es
h
o
ld
o
f
1
0
k
B
,
th
en
it
is
d
ec
id
ed
n
o
t
to
u
s
e
a
n
y
co
m
p
le
x
lo
ad
b
alan
cin
g
al
g
o
r
ith
m
,
h
e
n
ce
r
o
u
n
d
-
r
o
b
in
lo
ad
b
alan
ci
n
g
is
r
ec
o
m
m
e
n
d
ed
.
I
f
t
h
e
f
l
o
w
s
ize
ex
ce
ed
s
th
e
th
r
es
h
o
ld
v
alu
e,
t
h
en
t
h
e
T
A
-
ASL
B
m
eth
o
d
w
ill
b
e
f
o
llo
wed
.
T
h
e
f
in
al
p
h
a
s
e
is
th
e
s
er
v
er
s
elec
tio
n
p
h
a
s
e
w
it
h
t
h
e
h
elp
o
f
t
h
e
TA
-
A
S
L
B
m
eth
o
d
.
T
h
e
i
m
p
o
r
tan
t
p
ar
a
m
eter
s
n
ee
d
ed
f
o
r
s
er
v
e
r
lo
ad
b
alan
ci
n
g
in
cl
u
d
e
r
es
id
u
al
b
an
d
w
id
th
a
n
d
s
er
v
er
ca
p
ac
it
y
.
T
h
is
is
id
en
tifie
d
w
i
th
th
e
h
e
lp
o
f
a
liter
atu
r
e
s
u
r
v
e
y
a
m
o
n
g
v
ar
io
u
s
p
ap
er
s
.
I
t
ai
m
s
at
f
in
d
i
n
g
t
h
e
n
o
d
es h
a
v
in
g
a
h
ig
h
er
r
esid
u
al
b
an
d
w
id
t
h
.
T
h
e
alg
o
r
ith
m
is
e
x
p
lain
ed
i
n
F
i
g
u
r
e
1.
Alg
o
ri
t
h
m
1
:
TA
-
A
SL
B
a
lg
o
rit
h
m
T
ra
f
f
ic
m
o
nito
ring
ph
a
s
e:
Data
:
Flo
w
in
t
h
e
S
w
i
tch
e
s
F=
{f
1
,
f
2
,
...
f
n
}
Data
: C
ap
ac
it
y
o
f
all
p
o
s
s
ib
le
lin
k
s
to
r
ea
ch
s
er
v
er
L
=
{L
1
,
L
2
, ... L
n
}
Data
:
C
ap
ac
it
y
o
f
th
e
s
er
v
er
s
i
n
th
e
s
er
v
er
p
o
o
l S
=
{S
1
,
S
2
, ... S
n
}
Ada
ptiv
e
decisi
o
n p
ha
s
e:
b
eg
in
w
h
ile
p
ac
k
et
(
i)
g
en
er
ated
b
y
clie
n
t
s
d
o
f
o
r
ea
ch
f
i
є
F d
o
if
Flo
w
s
ize
(
f
i
)
>
T
h
r
es
h
o
ld
T
s
f
o
llo
w
T
r
af
f
ic
a
w
a
r
e
lo
ad
b
alan
cin
g
else:
f
o
llo
w
R
o
u
n
d
r
o
b
in
lo
ad
b
alan
cin
g
Serv
er
s
elec
t
io
n pha
s
e:
[
α
]
=
m
ax
(L
i
)
f
in
d
th
e
s
er
v
er
s
Si
w
h
ic
h
ar
e
p
r
esen
t in
t
h
i
s
b
est li
n
k
s
β
i
= m
ax
(S
i
)
Op
tim
al
Ser
v
er
=
β
i
Fig
u
r
e
1
.
T
r
af
f
ic
a
w
ar
e
-
ad
ap
tiv
e
s
er
v
er
lo
ad
b
alan
ci
n
g
[
T
A
-
ASL
B
]
m
e
th
o
d
T
h
e
T
AAL
B
m
et
h
o
d
w
o
r
k
s
w
it
h
t
h
e
co
m
b
i
n
atio
n
o
f
t
w
o
p
ar
am
eter
s
,
lin
k
ca
p
ac
it
y
to
w
ar
d
s
t
h
e
s
er
v
er
a
n
d
s
er
v
er
c
h
ar
ac
ter
is
tics
.
I
t
ai
m
s
at
f
i
n
d
in
g
t
h
e
n
o
d
es
h
a
v
i
n
g
a
h
ig
h
er
r
esid
u
al
b
an
d
w
id
t
h
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
3
,
J
u
n
e
2021
:
2
2
1
1
-
2218
2214
r
esid
u
al
b
an
d
w
id
th
o
f
a
li
n
k
i
s
ca
lcu
lated
b
ased
o
n
th
e
lo
ad
th
at
is
cu
r
r
en
tl
y
h
a
n
d
led
b
y
th
e
lin
k
.
T
h
e
lin
k
s
w
h
ic
h
ar
e
ca
r
r
y
i
n
g
a
lo
ad
at
an
y
ti
m
e
w
i
ll
b
e
u
tili
zi
n
g
b
an
d
w
id
th
s
,
s
o
th
e
y
w
ill
b
e
h
a
v
i
n
g
le
s
s
er
r
esid
u
a
l
b
an
d
w
id
t
h
.
T
h
en
,
a
m
o
n
g
t
h
e
m
,
t
h
e
n
o
d
e
s
w
ill
b
e
o
r
d
e
r
ed
in
th
e
d
escen
d
in
g
o
r
d
er
o
f
th
e
s
er
v
er
's
w
ei
g
h
t.
I
t
m
ea
n
s
,
a
n
o
d
e
h
av
in
g
h
i
g
h
er
r
esid
u
al
b
an
d
w
id
t
h
a
n
d
h
ig
h
er
w
e
ig
h
t
th
e
n
.
T
h
u
s
,
i
t
s
h
ar
es
t
h
e
lo
ad
a
m
o
n
g
n
o
d
es
b
ased
o
n
t
w
o
p
ar
a
m
ete
r
s
,
b
an
d
w
id
th
,
a
n
d
w
ei
g
h
t.
T
h
u
s
,
t
h
e
lo
ad
w
il
l
b
e
o
p
ti
m
all
y
s
h
ar
ed
a
m
o
n
g
t
h
e
n
o
d
es
.
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
T
h
e
alg
o
r
ith
m
i
s
i
m
p
le
m
en
ted
w
it
h
th
e
h
elp
o
f
a
M
in
i
n
e
t
s
i
m
u
lato
r
.
Data
ce
n
ter
n
et
w
o
r
k
s
ar
e
u
s
u
all
y
m
ain
tain
ed
b
y
f
o
llo
w
i
n
g
th
e
f
at
-
tr
ee
to
p
o
lo
g
y
s
tr
u
ct
u
r
e.
Hen
ce
f
o
r
th
i
s
tes
tin
g
,
a
f
at
-
tr
ee
to
p
o
lo
g
y
o
f
d
ep
th
3
is
cr
ea
ted
to
d
ep
ict
t
h
e
d
ata
ce
n
ter
n
et
w
o
r
k
.
T
h
e
n
e
t
w
o
r
k
h
a
s
ei
g
h
t
clie
n
t
n
o
d
e
s
te
r
m
ed
f
r
o
m
h
1
to
h8
an
d
s
ev
e
n
d
is
tr
ib
u
t
io
n
la
y
er
s
w
itc
h
e
s
s
1
to
s
7
.
T
h
e
ex
p
er
i
m
en
tatio
n
i
s
d
o
n
e
in
v
ir
tu
al
h
av
in
g
Ub
u
n
t
u
1
4
.
1
0
o
p
er
atin
g
s
y
s
te
m
.
T
h
e
n
et
w
o
r
k
is
ass
u
m
ed
to
h
av
e
h
eter
o
g
en
eo
u
s
s
er
v
er
s
.
T
h
e
to
p
o
lo
g
y
is
d
ep
icted
in
th
e
b
elo
w
d
iag
r
a
m
m
e
n
tio
n
ed
in
F
ig
u
r
e
2
.
Fig
u
r
e
2
.
DC
N
s
a
m
p
le
to
p
o
lo
g
y
i
n
Mi
n
i
n
et
Her
e
th
e
ass
u
m
p
tio
n
is
h
o
s
t
1
an
d
h
o
s
t
8
ar
e
clien
ts
.
Ho
s
ts
2
,
3
,
4
,
5,
6,
7
is
d
ef
in
ed
as
s
er
v
er
s
.
Ser
v
er
s
ar
e
ass
u
m
ed
to
h
a
v
e
d
if
f
er
en
t
p
r
o
ce
s
s
in
g
ca
p
ab
ilit
ie
s
s
u
c
h
a
s
2
0
co
r
e,
1
6
co
r
e,
8
co
r
e,
an
d
d
u
al
-
co
r
e.
Nu
m
er
o
u
s
tr
ials
ar
e
m
ad
e
o
n
a
f
at
-
tr
ee
to
p
o
lo
g
y
,
u
s
in
g
th
e
ex
is
tin
g
lo
ad
b
alan
c
in
g
m
e
th
o
d
s
i
n
f
lo
o
d
lig
h
t
co
n
tr
o
ller
an
d
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
tr
af
f
ic
a
w
ar
e
-
ad
ap
t
iv
e
s
er
v
er
lo
ad
b
alan
cin
g
[TA
-
A
S
L
B
]
m
et
h
o
d
.
Af
ter
th
e
v
ar
io
u
s
ex
p
er
i
m
en
ta
t
io
n
,
th
e
co
n
cl
u
s
io
n
is
d
er
iv
ed
.
T
h
e
av
er
ag
e
w
a
iti
n
g
ti
m
e
i
n
t
h
e
q
u
eu
e
o
f
a
s
er
v
er
is
d
ef
i
n
ed
as th
e
f
o
r
m
u
la
in
(
1
)
.
(
1
)
Her
e,
th
e
v
ar
iab
le
w
t
r
e
f
er
s
to
th
e
w
ait
in
g
ti
m
e
o
f
f
lo
w
in
t
h
e
q
u
eu
e,
r
r
ef
er
s
to
th
e
u
til
izat
io
n
r
ate,
u
r
ef
er
s
to
th
e
u
tili
za
tio
n
r
ate.
T
h
e
n
u
m
b
er
o
f
e
n
tr
ies i
n
t
h
e
q
u
eu
e
ca
n
b
e
d
e
f
in
ed
b
y
t
h
e
f
o
l
lo
w
i
n
g
(
2
)
.
(
2)
I
n
th
e
ab
o
v
e
eq
u
at
io
n
,
n
q
r
ef
er
s
to
t
h
e
av
er
a
g
e
co
u
n
t
o
f
f
lo
ws p
r
esen
t
in
th
e
q
u
e
u
e,
r
r
ef
er
s
to
th
e
r
ate
at
w
h
ic
h
th
e
f
lo
w
i
s
b
ee
n
u
tili
ze
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
-
8708
Tr
a
ffic
-
a
w
a
r
e
a
d
a
p
tive
s
erver
lo
a
d
b
a
la
n
cin
g
fo
r
s
o
ftw
a
r
e
d
efin
ed
n
etw
o
r
ks
(
C
.
F
a
n
cy
)
2215
T
h
er
e
is
an
o
th
er
i
m
p
o
r
tan
t
p
ar
t
o
f
th
e
alg
o
r
ith
m
,
w
h
ic
h
is
th
e
f
lo
w
clas
s
i
f
icatio
n
.
Fo
r
th
is
ex
p
er
i
m
e
n
t,
th
er
e
i
s
a
co
n
s
ta
n
t
th
r
es
h
o
ld
d
ef
in
ed
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
i
n
co
m
i
n
g
f
lo
w
s
.
A
p
r
ed
ef
i
n
ed
v
al
u
e
o
f
1
0
Mb
p
s
is
b
ee
n
s
et.
I
f
t
h
e
f
lo
w
co
m
es
w
it
h
a
s
ize
ab
o
v
e
t
h
is
v
a
lu
e,
s
h
o
u
ld
b
e
tr
ea
t
ed
b
y
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
n
d
th
e
y
ar
e
ca
lled
as
th
e
elep
h
a
n
t
f
lo
w
s
.
T
h
e
i
n
c
o
m
in
g
f
lo
w
s
b
elo
w
t
h
i
s
v
alu
e
w
i
ll
b
e
ter
m
ed
a
s
m
ice
f
lo
w
s
a
n
d
th
e
y
ca
n
b
e
s
e
n
t
to
s
er
v
er
s
i
n
r
o
u
n
d
-
r
o
b
in
f
a
s
h
io
n
f
o
r
p
r
o
ce
s
s
in
g
.
R
o
u
n
d
R
o
b
in
m
e
th
o
d
ai
m
s
at
allo
ttin
g
f
lo
w
r
eq
u
e
s
ts
to
ea
ch
o
f
t
h
e
s
er
v
er
s
o
n
e
b
y
o
n
e.
T
h
e
to
p
o
lo
g
y
is
tr
ied
u
n
d
er
v
ar
io
u
s
w
o
r
k
i
n
g
co
n
d
itio
n
s
s
u
ch
as
T
C
P
p
ac
k
et
s
tr
a
n
s
m
is
s
io
n
,
U
DP
p
ac
k
ets
tr
a
n
s
m
is
s
io
n
.
W
it
h
t
h
at,
it
is
p
o
s
s
ib
le
to
m
ea
s
u
r
e
t
h
e
p
ar
a
m
eter
s
s
u
c
h
a
s
th
r
o
u
g
h
p
u
t,
p
ac
k
e
t
lo
s
s
,
j
itter
,
r
esp
o
n
s
e
ti
m
e
(
laten
c
y
)
,
etc.
Fig
u
r
es
3
an
d
4
ar
e
w
o
r
k
in
g
ex
a
m
p
le
s
f
o
r
th
e
UD
P
an
d
T
C
P
p
ac
k
et
tr
an
s
m
is
s
io
n
s
d
o
n
e.
T
h
u
s
,
t
h
e
ab
o
v
e
f
i
g
u
r
e
tel
ls
clea
r
l
y
t
h
at
th
e
Mi
n
i
n
et
e
m
u
la
to
r
p
r
o
v
id
es
T
C
P
p
ac
k
ets
an
d
its
f
ea
t
u
r
es.
I
t
i
n
cl
u
d
es
t
h
e
w
i
n
d
o
w
s
ize,
t
h
e
p
o
r
t
n
u
m
b
er
i
n
w
h
ic
h
it
is
lis
te
n
i
n
g
,
th
e
th
r
o
u
g
h
p
u
t
v
al
u
e,
a
n
d
th
e
ti
m
e
s
er
ies.
Fig
u
r
e
3
.
Sa
m
p
le
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
a
f
ter
g
e
n
er
atin
g
T
C
P
p
ac
k
ets
Fig
u
r
e
4
.
Sa
m
p
le
p
er
f
o
r
m
a
n
ce
ev
alu
at
io
n
a
f
ter
g
e
n
er
atin
g
UD
P
p
ac
k
ets
T
h
e
ab
o
v
e
f
i
g
u
r
e
is
a
s
cr
ee
n
s
h
o
t
o
b
tain
ed
d
u
r
i
n
g
o
u
r
e
x
p
e
r
i
m
en
tatio
n
o
n
t
h
e
s
i
m
u
la
ted
to
p
o
lo
g
y
.
T
h
e
ip
er
f
is
a
n
e
f
f
icien
t
to
o
l
t
o
ex
p
lo
r
e
th
e
e
v
al
u
atio
n
p
ar
a
m
eter
s
o
f
t
h
e
g
i
v
en
n
et
w
o
r
k
.
I
t
ev
en
d
ep
icts
t
h
e
v
ar
io
u
s
a
n
al
y
s
e
s
s
u
m
m
ar
y
r
el
a
ted
to
th
e
p
ac
k
et
tr
an
s
m
i
s
s
io
n
.
4
.
1
.
T
hro
ug
hp
ut
T
h
r
o
u
g
h
p
u
t
r
ef
er
s
to
th
e
r
ate
o
f
s
u
cc
es
s
f
u
l
d
ata
tr
an
s
m
i
tte
d
b
etw
ee
n
a
s
o
u
r
ce
an
d
a
d
esti
n
a
tio
n
.
B
an
d
w
id
t
h
i
s
d
ef
i
n
ed
as
t
h
e
a
m
o
u
n
t
o
f
p
o
s
s
ib
le
d
ata
th
at
ca
n
b
e
tr
a
n
s
m
it
ted
i
n
a
li
n
k
.
Fo
r
t
h
is
ex
p
er
i
m
e
n
tatio
n
,
tr
af
f
ic
is
g
e
n
er
ated
b
et
w
ee
n
h
o
s
t
1
an
d
h
o
s
t
7
.
Ho
s
t
1
is
th
e
clie
n
t
a
n
d
h
o
s
t
8
is
d
ef
i
n
ed
as
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
3
,
J
u
n
e
2021
:
2
2
1
1
-
2218
2216
s
er
v
er
in
o
u
r
ex
p
er
i
m
e
n
t.
T
h
e
th
r
o
u
g
h
p
u
t
o
f
t
h
e
ab
o
v
e
-
m
e
n
ti
o
n
ed
alg
o
r
ith
m
s
i
s
n
o
ted
f
o
r
t
h
e
g
i
v
e
n
to
p
o
lo
g
y
.
T
h
e
ip
er
f
co
m
m
an
d
is
u
s
ed
to
o
b
tain
th
e
th
r
o
u
g
h
p
u
t.
T
C
P
p
ac
k
ets
ar
e
s
en
t
ca
r
r
y
i
n
g
1
0
2
4
b
y
te
s
.
T
h
e
ex
p
er
i
m
e
n
t
is
r
ep
ea
ted
w
it
h
a
v
ar
y
i
n
g
n
u
m
b
er
o
f
p
ar
allel
r
e
q
u
ests
s
u
c
h
as
1
0
0
,
2
0
0
,
3
0
0
,
4
0
0
,
an
d
5
0
0
.
T
h
e
b
elo
w
is
a
s
a
m
p
le
s
cr
ee
n
s
h
o
t
th
at
d
ep
icts
o
u
r
e
x
p
er
i
m
e
n
ts
.
T
h
e
r
esu
lts
ar
e
d
ep
icted
as
a
g
r
ap
h
th
a
t
is
g
i
v
en
b
elo
w
F
i
g
u
r
e
5
.
Fig
u
r
e
5
.
T
h
r
o
u
g
h
p
u
t r
es
u
lt a
n
al
y
s
i
s
B
y
th
e
r
e
s
u
lt
s
,
it
i
s
i
n
f
er
r
ed
th
at
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
is
g
i
v
in
g
h
i
g
h
er
t
h
r
o
u
g
h
p
u
t
co
m
p
ar
ed
to
th
e
tr
ad
itio
n
al
al
g
o
r
ith
m
s.
W
h
e
n
n
u
m
b
er
o
f
p
ac
k
et
s
i
n
cr
ea
s
e,
th
eir
th
r
o
u
g
h
p
u
t
d
ec
r
ea
s
es.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
s
a
m
o
n
g
t
h
e
o
th
er
ex
is
t
in
g
lo
ad
b
alan
cin
g
al
g
o
r
ith
m
s
.
4
.
1
.
1
.
L
a
t
ency
L
ate
n
c
y
i
s
d
ef
i
n
ed
as t
h
e
ti
m
e
tak
en
f
o
r
th
e
d
ata
to
g
e
t tr
an
s
m
itted
f
r
o
m
s
o
u
r
ce
to
d
esti
n
ati
o
n
an
d
th
e
r
ec
eiv
er
p
r
o
ce
s
s
in
g
it.
I
t
ca
n
also
b
e
ca
lled
as
r
o
u
n
d
-
tr
ip
ti
m
e.
T
h
e
laten
c
y
o
f
t
h
e
tr
a
d
itio
n
al
,
as
w
ell
as
alg
o
r
ith
m
s
,
is
n
o
ted
f
o
r
t
h
e
g
iv
en
to
p
o
lo
g
y
.
T
h
e
e
x
p
er
i
m
e
n
t
i
s
r
ep
ea
ted
w
it
h
a
v
ar
y
i
n
g
n
u
m
b
er
o
f
p
ac
k
ets
s
u
c
h
as
1
0
0
,
2
0
0
,
3
0
0
,
4
0
0
,
an
d
5
0
0
.
T
h
is
is
o
b
tain
ed
w
it
h
th
e
h
elp
o
f
th
e
p
in
g
co
m
m
a
n
d
.
B
y
th
e
r
es
u
lt
s
,
it
is
in
f
er
r
ed
th
at
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
s
h
o
w
i
n
g
less
er
d
ela
y
t
h
an
th
e
e
x
is
t
in
g
m
e
th
o
d
s
.
T
h
e
r
esu
lt
s
ar
e
d
ep
icted
as a
g
r
ap
h
th
a
t
is
g
iv
e
n
as F
ig
u
r
e
6
.
Fig
u
r
e
6
.
L
aten
c
y
r
es
u
lt a
n
al
y
s
is
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
E
NH
A
NCEM
E
NT
S
T
h
e
f
o
cu
s
o
f
th
i
s
p
ap
er
is
t
o
p
er
f
o
r
m
an
ef
f
icie
n
t
s
er
v
e
r
lo
ad
b
alan
cin
g
.
T
h
e
p
r
o
p
o
s
ed
n
o
v
e
l
alg
o
r
ith
m
p
r
o
v
id
ed
an
o
p
ti
m
al
s
er
v
er
s
elec
t
io
n
w
h
en
e
v
er
lo
n
g
f
lo
w
s
ar
r
iv
e.
T
h
e
ex
p
er
i
m
en
tatio
n
wa
s
d
o
n
e
to
u
n
d
er
s
ta
n
d
th
e
i
m
p
o
r
ta
n
ce
o
f
th
e
lo
ad
r
eg
u
latin
g
p
r
o
ce
s
s
in
d
ata
ce
n
ter
s
.
T
h
e
f
ir
s
t
s
tep
w
a
s
to
id
en
tify
th
e
p
ar
am
eter
s
th
at
in
f
l
u
e
n
ce
th
e
d
elay
i
n
d
ata
tr
an
s
m
is
s
io
n
.
Nex
t,
th
e
t
y
p
e
o
f
f
lo
w
s
i
s
b
ee
n
co
n
s
id
er
ed
,
b
ec
au
s
e
th
er
e
ca
n
b
e
s
h
o
r
t
-
li
v
ed
f
lo
ws
an
d
lo
n
g
-
li
v
ed
f
lo
w
s
in
th
e
DC
N
s
.
B
ased
o
n
t
h
e
v
ar
io
u
s
t
y
p
es
o
f
f
lo
w
s
i.e
.
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
-
8708
Tr
a
ffic
-
a
w
a
r
e
a
d
a
p
tive
s
erver
lo
a
d
b
a
la
n
cin
g
fo
r
s
o
ftw
a
r
e
d
efin
ed
n
etw
o
r
ks
(
C
.
F
a
n
cy
)
2217
v
id
eo
tr
af
f
ic,
m
es
s
a
g
e
,
o
r
im
ag
e
tr
an
s
f
er
,
th
e
d
ela
y
in
d
at
a
tr
an
s
m
is
s
io
n
w
il
l
v
ar
y
.
I
t
is
o
b
s
er
v
ed
f
r
o
m
t
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
n
o
d
es
an
d
th
e
in
f
l
u
en
ce
o
f
a
n
o
d
e
in
th
e
p
ath
to
d
esti
n
atio
n
p
la
y
s
a
m
aj
o
r
r
o
le
in
th
e
ef
f
icien
t
lo
ad
b
alan
cin
g
o
f
f
lo
w
s
i
n
an
SDN
e
n
v
ir
o
n
m
e
n
t.
Hen
ce
th
e
ad
ap
tiv
e
lo
ad
b
alan
cin
g
s
c
h
e
m
e
is
v
er
y
g
o
o
d
in
r
ed
u
ci
n
g
t
h
e
d
ela
y
a
n
d
i
m
p
r
o
v
i
n
g
t
h
e
t
h
r
o
u
g
h
p
u
t
o
f
t
h
e
n
e
t
w
o
r
k
.
A
l
s
o
,
th
e
ad
ap
tiv
e
n
atu
r
e
o
f
t
h
e
alg
o
r
ith
m
h
elp
s
th
e
co
n
tr
o
ller
to
av
o
id
co
m
p
u
tatio
n
al
co
m
p
l
ex
it
y
in
ca
s
e
o
f
s
h
o
r
t f
lo
w
s
.
I
n
t
h
e
f
u
t
u
r
e,
t
h
is
s
er
v
er
s
el
ec
tio
n
p
r
o
ce
s
s
ca
n
b
e
m
ad
e
as
a
n
i
n
telli
g
e
n
t
ap
p
licatio
n
w
o
r
k
i
n
g
s
ep
ar
atel
y
o
n
to
p
o
f
t
h
e
ce
n
tr
alize
d
co
n
tr
o
ller
.
B
ec
au
s
e
to
p
r
o
p
o
s
e
th
e
s
er
v
er
s
e
lectio
n
a
ctiv
itie
s
q
u
ic
k
l
y
an
d
also
to
o
v
er
co
m
e
a
n
y
f
ail
u
r
e,
t
h
e
n
e
u
r
al
n
et
w
o
r
k
a
s
p
ec
t
p
r
o
p
o
s
es
o
p
tim
al
an
d
s
u
b
o
p
tim
al
s
o
l
u
tio
n
s
.
T
h
is
m
ak
e
s
t
h
e
n
e
u
r
al
n
et
w
o
r
k
s
o
lu
tio
n
as
a
b
etter
o
p
tio
n
f
o
r
th
e
f
u
t
u
r
e.
A
n
o
t
h
er
asp
e
ct
is
in
t
h
e
f
lo
w
class
i
f
icatio
n
.
I
n
th
i
s
p
ap
er
,
we
h
a
v
e
u
s
ed
it
a
s
a
s
tatic
w
a
y
to
s
p
lit
t
h
e
f
lo
w
s
.
W
e
h
a
v
e
p
l
an
n
ed
to
in
cl
u
d
e
a
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
,
to
s
p
lit th
e
i
n
co
m
i
n
g
f
lo
w
s
in
t
o
a
f
iv
e
-
s
ca
le
m
eter
.
T
h
is
ca
n
b
e
u
s
ed
to
ar
r
iv
e
at
a
d
etailin
g
o
f
f
lo
w
s
an
d
it
co
u
ld
h
elp
in
th
e
g
e
n
er
ic
p
r
io
r
it
y
ass
i
g
n
m
e
n
t.
A
l
s
o
,
d
y
n
a
m
ici
t
y
in
t
h
r
es
h
o
ld
s
etti
n
g
co
u
ld
b
e
ar
r
iv
ed
b
ased
o
n
th
e
cu
r
r
en
t
s
it
u
atio
n
i
n
t
h
e
n
et
wo
r
k
.
W
ith
t
h
i
s
,
a
p
r
ec
is
e
m
o
d
el
th
at
ca
n
g
e
n
er
ate
th
at
f
o
c
u
s
o
n
th
e
c
u
r
r
en
t
s
tate
o
f
th
e
m
ac
h
in
e
s
lik
e,
n
u
m
b
e
r
o
f
f
lo
w
s
c
u
r
r
en
tl
y
w
aiti
n
g
t
o
b
e
p
r
o
ce
s
s
ed
,
th
e
n
u
m
b
er
o
f
f
lo
w
s
h
a
n
d
led
alr
ea
d
y
,
t
h
e
s
er
v
er
ca
p
ac
it
y
,
th
e
r
esid
u
al
b
an
d
w
id
th
i
n
th
e
li
n
k
s
co
n
n
ec
ti
n
g
to
th
e
s
er
v
er
s
,
t
h
e
q
u
e
u
e
le
n
g
t
h
,
ar
r
iv
al
r
ate,
etc.
Fo
c
u
s
o
n
t
h
ese
c
o
u
ld
,
ev
e
n
m
o
r
e,
i
m
p
r
o
v
is
e
th
e
ef
f
icie
n
c
y
o
f
t
h
e
cu
r
r
en
t lo
ad
b
alan
cin
g
s
y
s
te
m
s
.
RE
F
E
R
E
NC
E
S
[1
]
K.
Ra
m
a
n
a
a
n
d
M
.
P
o
n
n
a
v
a
ik
k
o
,
“
A
W
S
Q:
a
n
a
p
p
ro
x
ima
ted
we
b
se
rv
e
r
q
u
e
u
in
g
a
lg
o
rit
h
m
f
o
r
h
e
tero
g
e
n
e
o
u
s
w
e
b
se
r
v
e
r
c
lu
ste
r
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
),
v
o
l.
9
,
n
o
.
3
,
p
p
.
2
0
8
3
-
2
0
9
3
,
Ju
n
.
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i3
.
p
p
2
0
8
3
-
2
0
9
3
.
[2
]
K.S
.
Qa
d
d
o
u
m
,
“
El
a
stic
n
e
u
ra
l
n
e
tw
o
rk
m
e
th
o
d
f
o
r
lo
a
d
p
re
d
ictio
n
in
c
lo
u
d
c
o
m
p
u
ti
n
g
g
rid
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
of
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
1
2
0
1
-
1
2
0
8
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i2
.
p
p
1
2
0
1
-
1
2
0
8
.
[3
]
T.
E
m
a
d
A
li
,
A
.
H.
M
o
ra
d
,
M
.
A
.
A
b
d
a
la
.,
“
L
o
a
d
Ba
lan
c
e
in
Da
t
a
Ce
n
ter S
DN
Ne
t
w
o
rk
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
5
,
p
p
.
3
0
8
6
-
3
0
9
2
,
O
c
t.
2
0
1
8
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
8
i5
.
p
p
3
0
8
4
-
3
0
9
1
.
[4
]
M.
T
a
ra
h
o
m
i
a
n
d
M
.
Iz
a
d
i,
“
A
h
y
b
rid
a
lg
o
rit
h
m
to
re
d
u
c
e
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
m
a
n
a
g
e
m
e
n
t
in
c
lo
u
d
d
a
ta
c
e
n
ters
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
),
v
o
l.
9
,
n
o
.
1
,
p
p
.
5
5
4
-
5
6
1
,
F
e
b
.
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i1
.
p
p
5
5
4
-
5
6
1
.
[5
]
D.
Ha
rtan
ti
,
“
Op
ti
m
iza
ti
o
n
o
f
sm
a
rt
traff
ic
li
g
h
ts
to
p
re
v
e
n
t
traff
ic
c
o
n
g
e
stio
n
u
sin
g
f
u
z
z
y
lo
g
ic
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
m
p
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
320
-
3
2
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A
.
v
1
7
i1
.
1
0
1
2
9
.
[6
]
N.
Zh
a
n
g
,
“
S
o
f
twa
re
-
De
f
in
e
d
Ne
tw
o
rk
in
g
En
a
b
led
W
irele
ss
Ne
t
w
o
rk
V
irt
u
a
li
z
a
ti
o
n
:
Ch
a
l
len
g
e
s
a
n
d
S
o
lu
ti
o
n
s
,
”
IEE
E
Ne
two
rk
,
v
o
l
.
3
1
,
n
o
.
5
,
p
p
.
4
2
-
4
9
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/M
NET
.
2
0
1
7
.
1
6
0
0
2
4
8
.
[7
]
M
u
ji
o
n
o
S
.
,
“
L
o
a
d
b
a
lan
c
i
n
g
c
lu
ste
rin
g
o
n
m
o
o
d
le
L
M
S
to
o
v
e
rc
o
m
e
p
e
rf
o
r
m
a
n
c
e
issu
e
o
f
e
-
le
a
rn
in
g
sy
ste
m
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
t
i
o
n
Co
m
p
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
1
3
1
-
1
3
8
,
F
e
b
.
2
0
1
9
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A
.
v
1
7
i
1
.
1
0
2
8
4
.
[8
]
M.
S
h
a
f
iee
a
n
d
J.
G
h
a
d
e
ri,
“
A
S
im
p
le
Co
n
g
e
stio
n
-
Aw
a
re
A
l
g
o
rit
h
m
f
o
r
L
o
a
d
Ba
lan
c
in
g
in
Da
tac
e
n
ter
Ne
tw
o
rk
s
,
”
IEE
E/
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
tw
o
rk
in
g
,
v
o
l.
2
5
,
n
o
.
6
,
p
p
.
3
6
7
0
-
3
6
8
2
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/T
NET
.
2
0
1
7
.
2
7
5
1
2
5
1
.
[9
]
Z.
Be
n
lalia
,
“
Co
m
p
a
rin
g
lo
a
d
b
a
l
a
n
c
in
g
a
lg
o
rit
h
m
s
f
o
r
w
e
b
a
p
p
li
c
a
ti
o
n
i
n
c
lo
u
d
e
n
v
iro
n
m
e
n
t
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
7
,
n
o
.
2
,
p
p
.
1
1
0
4
-
1
1
0
8
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
7
.
i
2
.
p
p
1
1
0
4
-
1
1
0
8
.
[1
0
]
D.K.N.
V
e
n
k
a
tram
a
n
a
,
S
.
B.
S
rik
a
n
taia
h
,
J.
M
o
o
d
a
b
i
d
ri
,
“
S
CG
RP
:
S
DN
-
e
n
a
b
led
c
o
n
n
e
c
ti
v
it
y
-
a
w
a
r
e
g
e
o
g
r
a
p
h
ica
l
ro
u
ti
n
g
p
r
o
to
c
o
l
o
f
V
A
NET
s
f
o
r
th
e
u
r
b
a
n
e
n
v
ir
o
n
m
e
n
t,
”
IET
J
o
u
rn
a
l,
v
o
l
.
6
,
n
o
.
5
,
p
p
.
1
0
2
-
1
1
1
,
2
0
1
7
,
d
o
i:
h
tt
p
s:/
/d
o
i
.
o
rg
/1
0
.
1
0
4
9
/i
e
t
-
n
e
t.
2
0
1
6
.
0
1
1
7
.
[1
1
]
C.
C.
Ch
u
a
n
g
Ya
-
Ju
Y
u
,
a
n
d
A
i
-
Ch
u
n
P
a
n
g
,
“
F
lo
w
-
Aw
a
r
e
Ro
u
ti
n
g
a
n
d
F
o
rw
a
rd
in
g
f
o
r
S
DN
S
c
a
lab
il
it
y
in
W
irele
ss
Da
ta
Ce
n
ters
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
two
rk
a
n
d
S
e
rv
ice
M
a
n
a
g
e
me
n
t,
v
o
l.
1
5
,
n
o
.
4
,
p
p
.
1
6
7
6
-
1
6
9
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/T
NSM
.
2
0
1
8
.
2
8
6
5
1
6
6
.
[1
2
]
J.
P
a
n
g
G
a
o
c
h
a
o
X
u
,
a
n
d
X
iao
d
o
n
g
F
u
,
“
S
DN
-
Ba
se
d
Da
ta
C
e
n
ter
Ne
t
w
o
rk
in
g
w
it
h
Co
ll
a
b
o
ra
ti
o
n
o
f
M
u
lt
ip
a
t
h
T
CP
a
n
d
S
e
g
m
e
n
t
Ro
u
ti
n
g
,
”
IEE
E
Acc
e
ss
,
v
o
l
.
5,
p
p
.
9
7
6
4
-
9
7
7
3
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
7
.
2
7
0
0
8
6
7
.
[1
3
]
Q.
Qin
,
e
t
a
l.
,
“
S
DN
Co
n
tr
o
ll
e
r
P
lac
e
m
e
n
t
W
it
h
De
la
y
-
Ov
e
rh
e
a
d
Ba
lan
c
in
g
in
W
irele
ss
Ed
g
e
Ne
tw
o
rk
s
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
On
Ne
two
rk
A
n
d
S
e
rv
ice
M
a
n
a
g
e
me
n
t,
v
o
l
.
1
5
,
n
o
.
4
,
p
p
.
1
4
4
6
-
1
4
5
9
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/T
NSM
.
2
0
1
8
.
2
8
7
6
0
6
4
.
[1
4
]
S.
Zh
a
n
g
,
e
t
a
l.
,
“
O
n
li
n
e
L
o
a
d
Ba
lan
c
in
g
f
o
r
Distrib
u
ted
C
o
n
tr
o
l
P
l
a
n
e
in
S
o
f
tw
a
re
-
D
e
f
in
e
d
D
a
ta
Ce
n
ter
Ne
tw
o
rk
,
”
IEE
E
Acc
e
ss
,
v
o
l
.
6
,
p
p
.
1
8
1
8
4
–
1
8
1
9
1
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
8
.
2
8
2
0
1
4
8
.
[1
5
]
M.
Am
iri
,
e
t
a
l.
,
“
S
DN
-
En
a
b
led
Ga
m
e
-
Aw
a
re
Ro
u
ti
n
g
f
o
r
Clo
u
d
G
a
m
in
g
Da
tac
e
n
ter
Ne
t
w
o
rk
,
”
IEE
E
Acc
e
ss
,
v
o
l.
5
,
p
p
.
1
8
6
3
3
–
1
8
6
4
5
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
7
.
2
7
5
2
6
4
3
.
[1
6
]
J.
Zh
a
n
g
,
e
t
a
l.
,
“
L
o
a
d
Ba
lan
c
in
g
in
Da
ta
Ce
n
ter
Ne
t
w
o
rk
s:
A
S
u
rv
e
y
,
”
IEE
E
Co
mm
u
n
ica
ti
o
n
s
S
u
rv
e
y
s
&
T
u
to
ri
a
ls,
v
o
l.
2
0
,
n
o
.
3
,
p
p
.
2
3
2
4
-
2
3
5
2
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/COM
S
T
.
2
0
1
8
.
2
8
1
6
0
4
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
3
,
J
u
n
e
2021
:
2
2
1
1
-
2218
2218
[1
7
]
Yo
u
-
Ch
i
u
n
W
a
n
g
,
a
n
d
S
ian
g
-
Y
u
Yo
u
,
“
A
n
Eff
icie
n
t
Ro
u
te
M
a
n
a
g
e
m
e
n
t
F
ra
m
e
w
o
rk
f
o
r
L
o
a
d
Ba
lan
c
e
a
n
d
Ov
e
rh
e
a
d
Re
d
u
c
ti
o
n
in
S
DN
-
Ba
se
d
Da
ta
C
e
n
ter
Ne
t
w
o
rk
s
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Ne
two
rk
a
n
d
S
e
rv
ice
M
a
n
a
g
e
me
n
t,
v
o
l.
1
5
,
n
o
.
4
,
p
p
.
1
4
2
2
–
1
4
3
4
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/T
NSM
.
2
0
1
8
.
2
8
7
2
0
5
4
.
[1
8
]
K.
A
lh
a
z
m
i
A
b
d
a
ll
a
h
S
h
a
m
i,
a
n
d
A
h
m
e
d
Re
f
a
e
y
.
“
Op
ti
m
iz
e
d
P
r
o
v
isio
n
i
n
g
o
f
S
DN
-
e
n
a
b
led
V
irt
u
a
l
Ne
tw
o
rk
s
in
G
e
o
-
d
istri
b
u
ted
C
lo
u
d
C
o
m
p
u
ti
n
g
Da
tac
e
n
ters
,
”
J
o
u
rn
a
l
o
f
C
o
mm
u
n
ic
a
ti
o
n
s
a
n
d
Ne
two
rk
s,
v
o
l.
1
9
,
n
o
.
4
,
p
p
.
4
0
2
–
4
1
5
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/
JCN
.
2
0
1
7
.
0
0
0
0
6
4
.
[1
9
]
P
.
R.
Iy
e
r,
e
t
a
l.
,
“
A
d
a
p
ti
v
e
re
a
l
ti
m
e
tra
ff
ic
p
re
d
ictio
n
u
sin
g
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
1
0
7
-
1
1
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai.
v
8
.
i2
.
p
p
1
0
7
-
1
1
9
.
[2
0
]
J.
Zh
a
n
g
e
t
a
l.
,
“
L
o
a
d
Ba
lan
c
in
g
in
Da
ta
Ce
n
ter
Ne
t
w
o
rk
s:
A
S
u
rv
e
y
,
”
IEE
E
Co
mm
u
n
ica
ti
o
n
s
S
u
rv
e
y
s
&
T
u
to
ria
ls
,
v
o
l.
2
0
,
n
o
.
3
,
p
p
.
2
3
2
4
–
2
3
5
2
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/CO
M
S
T
.
2
0
1
8
.
2
8
1
6
0
4
2
.
[2
1
]
C.
Jitt
a
w
iri
y
a
n
u
k
o
o
n
,
“
Ev
a
lu
a
ti
o
n
o
f
lo
a
d
b
a
lan
c
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
Erl
a
n
g
c
o
n
c
u
rre
n
t
a
p
p
li
c
a
ti
o
n
i
n
c
l
o
u
d
s
y
ste
m
s
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
1
7
9
5
-
1
8
0
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NI
KA
.
v
1
8
i4
.
1
3
1
5
0
.
[2
2
]
H.
T
u
ss
y
a
d
iah
,
Rid
h
a
M
.
N
.
,
a
n
d
Da
n
u
D
.
S
.,
“
Distrib
u
ted
g
a
tew
a
y
-
b
a
se
d
lo
a
d
b
a
lan
c
in
g
in
s
o
f
t
w
a
r
e
d
e
f
in
e
d
n
e
tw
o
rk
,
”
T
EL
KOM
NIKA
T
e
le
c
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ti
n
g
,
El
e
c
tr
o
n
ics
a
n
d
Co
n
tro
l,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
2
3
5
2
-
2
3
6
1
,
Oc
t
.
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A
.
v
1
8
i5
.
1
4
8
5
1
.
[2
3
]
X.
Y
u
Ho
n
g
Xu
,
a
n
d
H
u
a
x
i
G
u
,
“
T
h
o
r:
A
S
e
rv
e
r
-
le
v
e
l
H
y
b
rid
S
w
it
c
h
in
g
Da
ta
Ce
n
ter
Ne
tw
o
rk
w
it
h
He
tero
g
e
n
e
o
u
s
T
o
p
o
lo
g
ies
,
”
ACM
T
UR
-
C
’
1
7
,
p
p
.
1
-
10
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
4
5
/
3
0
6
3
9
5
5
.
3
0
6
3
9
9
2
.
[2
4
]
D.
S
u
n
,
e
t
a
l.
,
“
D
y
n
a
m
ic
T
r
a
ff
i
c
S
c
h
e
d
u
l
in
g
a
n
d
Co
n
g
e
stio
n
Co
n
t
ro
l
a
c
ro
ss
Da
ta
Ce
n
ters
Ba
se
d
o
n
S
DN
,
”
Fu
tu
re
In
ter
n
e
t,
v
o
l.
1
0
,
n
o
.
7
,
2
0
1
8
,
d
o
i:
1
0
.
3
3
9
0
/f
i1
0
0
7
0
0
6
4
.
[2
5
]
X
i
Hu
a
n
g
,
e
t
a
l.
,
“
Dy
n
a
m
ic
s
w
it
c
h
-
c
o
n
tro
ll
e
r
a
ss
o
c
iatio
n
a
n
d
c
o
n
tro
l
d
e
v
o
lu
t
io
n
f
o
r
S
DN
sy
ste
m
s
,
”
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ica
t
io
n
s (
ICC),
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/ICC.
2
0
1
7
.
7
9
9
7
4
2
7
.
[2
6
]
W
.
P
ra
k
a
sh
a
n
d
De
e
p
a
lak
sh
m
i
P
.
,
“
DServ
-
L
B:
D
y
n
a
m
ic
s
e
rv
e
r
lo
a
d
b
a
lan
c
in
g
a
lg
o
rit
h
m
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mm
u
n
ica
ti
o
n
S
y
ste
ms
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
2
/
d
a
c
.
3
8
4
0
.
[2
7
]
M
.
A
ll
a
’
A
n
z
y
a
n
d
M
.
Oth
m
a
n
,
“
L
o
a
d
b
a
lan
c
in
g
a
n
d
se
rv
e
r
c
o
n
so
li
d
a
ti
o
n
in
c
l
o
u
d
c
o
m
p
u
ti
n
g
e
n
v
iro
n
m
e
n
ts:
A
m
e
ta
-
stu
d
y
,
”
IEE
E
Acc
e
ss
,
Dig
it
a
l
Ob
jec
t
Id
e
n
ti
fi
e
r,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/A
CCES
S
.
2
0
1
9
.
2
9
4
4
4
2
0
.
[2
8
]
V
.
P
riy
a
,
e
t
a
l.
,
“
Re
so
u
rc
e
s
c
h
e
d
u
li
n
g
a
lg
o
rit
h
m
w
it
h
lo
a
d
b
a
lan
c
in
g
f
o
r
c
lo
u
d
se
rv
ice
p
ro
v
isio
n
in
g
,”
Ap
p
li
e
d
so
f
t
c
o
mp
u
ti
n
g
,
El
se
v
ier
,
v
o
l
7
6
,
p
p
.
41
6
-
4
2
4
,
2
0
1
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
C.
Fa
n
c
y
is
c
u
rre
n
tl
y
p
u
rsu
in
g
Do
c
to
ra
l
re
se
a
rc
h
in
th
e
Co
m
p
u
ter
S
c
ien
c
e
En
g
in
e
e
rin
g
d
e
p
a
rtm
e
n
t,
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ka
tt
a
n
k
u
lath
u
r.
S
h
e
is
a
lso
a
T
e
a
c
h
in
g
f
a
c
u
lt
y
in
th
e
sa
m
e
u
n
iv
e
rsit
y
.
He
r
re
se
a
rc
h
f
i
e
ld
is
S
o
f
twa
re
De
f
in
e
d
Ne
t
w
o
rk
in
g
.
S
h
e
h
a
d
a
c
c
o
m
p
li
sh
e
d
UG
a
n
d
P
G
c
o
u
rse
s
in
th
e
y
e
a
rs
2
0
0
9
a
n
d
2
0
1
1
re
sp
e
c
ti
v
e
l
y
.
S
h
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
w
it
h
o
th
e
r
re
se
a
rc
h
a
sp
e
c
ts
su
c
h
a
s
Cr
y
p
to
g
ra
p
h
y
,
T
CP
/IP
se
rv
ice
s,
a
n
d
th
e
In
tern
e
t
o
f
T
h
in
g
s.
M
.
Pu
sh
p
a
la
t
h
a
is
w
o
rk
in
g
in
S
RM
In
sti
tu
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ka
tt
a
n
k
u
lath
u
r.
S
h
e
h
o
l
d
s
th
e
P
r
o
f
e
ss
o
r
d
e
sig
n
a
ti
o
n
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
d
e
p
a
rtm
e
n
t.
S
h
e
h
a
d
c
o
m
p
lete
d
U
G
a
n
d
P
G
c
o
u
rse
s
in
th
e
y
e
a
rs
1
9
9
4
a
n
d
2
0
0
1
re
sp
e
c
ti
v
e
l
y
.
S
h
e
c
o
m
p
lete
d
Do
c
to
ra
l
re
se
a
rc
h
in
th
e
Co
m
p
u
ter
S
c
ien
c
e
En
g
in
e
e
rin
g
d
o
m
a
in
,
in
th
e
y
e
a
r
2
0
1
4
.
He
r
a
re
a
o
f
in
tere
sts
in
c
lu
d
e
S
o
f
tw
a
r
e
De
f
in
e
d
Da
ta
C
e
n
ter
Ne
t
w
o
rk
s,
M
id
d
lew
a
re
se
rv
ice
s,
a
n
d
W
irele
s
s
Ne
t
w
o
rk
s,
In
tern
e
t
o
f
T
h
in
g
s,
5
G
a
n
d
f
u
tu
re
n
e
tw
o
rk
s.
S
h
e
h
a
s
se
v
e
ra
l
p
u
b
li
c
a
ti
o
n
s
i
n
re
p
u
ted
jo
u
rn
a
ls.
S
h
e
h
a
d
p
re
se
n
ted
p
a
p
e
rs
i
n
v
a
rio
u
s
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s.
S
h
e
is
c
u
rre
n
tl
y
g
u
id
i
n
g
re
se
a
rc
h
s
c
h
o
lars
in
v
a
rio
u
s
d
o
m
a
in
s.
S
h
e
is
a
p
ro
f
e
ss
io
n
a
l
m
e
m
b
e
r
o
f
v
a
rio
u
s
re
p
u
ted
sta
n
d
a
rd
b
o
d
ies
su
c
h
a
s A
CM
e
tc.
S
h
e
h
a
s g
u
id
e
d
se
v
e
ra
l
UG
a
n
d
P
G
lev
e
l
stu
d
e
n
t
p
r
o
jec
ts.
Evaluation Warning : The document was created with Spire.PDF for Python.