You are on page 1of 43

1

Optical Packet Switching


Techniques
Walter Picco
MS Thesis Defense December 2001

Fabio Neri, Marco Ajmone Marsan
Telecommunication Networks Group
http://www.tlc-networks.polito.it/
2
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
3
The need of optics
Future network requirements:
High bandwidth capacity
Flexibility, robustness
Power supply and equipment footprint
reduction

Optics offers a good evolution perspective
4
Optical framework today
Point to point communications
Circuit switching with packet switching
electronic control
why ?
Optical packet switching:
no optical memories
slow optical switches
5
Optical packet switching
Bandwidth is not a problem

Network cost is in the commutation

New protocols and architectures needed


New tools to measure performance
New design techniques
more
6
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
7
Goals
New optical network simulator
Topology Simulation Performance
8
Goals
New analysis and design method for optical
networks

Resources Analysis Topology
9
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
10
Transmitting data
Wavelength Division Multiplexing: the huge
bandwidth of an optical fiber is divided in many
channels (colors)




Each channel occupies a
different frequency slot
11
Storing data
Optical RAM is not available yet
Fiber Delay Lines (FDLs) are used instead
FDLs
Forward usage Feedback usage
FDL
12
Processing data
Electronics limits the speed in data
forwarding
Optical 3R regeneration (and wavelength
conversion) is now possible



Physical layer is not a matter of concern
All-optical solutions are currently at the study
3R

1

2

13
Switching data
Tomorrow (a
possibility): Micro
Electro Mechanical
Systems
Today: Semiconductor Optical Amplifiers
14
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
15
Fixed routing
implementation


Not good for WDM
The starting simulator: CLASS
Simulator of ATM networks
Topology independent


Adaptable tool
} fiber
channel
16
CLASS modifications
Dynamic routing strategy



Each WDM channel must be listed in the
network description file

Maximum flexibility in the network description
} fiber
channel
17
SIMON node architecture
n n
1 1
n-1 n-1
SWITCH
CONTROL
UNIT
3R
3R
3R
3R
3R
3R
3R
3R
3R
1 1
2 2
m m
18
Time division
Slotted network:
t
t
t
C
1
C
2
C
3
t
0
timeslot
P 1
P 2
t
1
19
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
20
Designing WDM networks
Given:
Network topology and the traffic matrix
Find:
Number of WDM channels on each link
Optimizing:
Network throughput
Meeting a cost constraint:
Network cost

commutation
Fixed number
of ports for all
the switches
21
The optimization problem
Mathematical statement:
Find minimum (maximum) of a non-linear
function in the discrete domain, meeting
some constraints

NP-complete problem

Only heuristic solutions are possible
22
Proposed approach
1) Find:

P
tot
: packet loss probability of the whole
network
n
i
: number of WDM channels on link i

2) Elaborate a heuristic solution to find the
minimum of P
tot
( )
M tot
n n f P
1
=
23
Link model
Classical queueing theory: M/M/L/k queue






server WDM channel
buffer slot FDL
k
1
2
L
servers
buffer
more
24
Node model
Input
fibers
Output
fibers
25
FDLs cant be modeled as a simple buffer
discrete storage time
noise addition at each recirculation




All the FDLs of a node are shared among the
different queues
Model limitations
channel
FDL
A

B

A + =
<
t t t
SNR SNR
A B
A B
26
Network model
The packet loss probability (P
f
) of a flow is:


The packet loss probability (P
tot
) of the whole
network results:
First step completed
e
e

=
F f
f
F f
f f
tot
t
P t
P
( )
M tot
n n f P
1
=
e
=
f
L i
i
f
P P 1 1
27
Cost constraint:
(channel ports + FDLs ports) = constant
optimum balance optimum solution
Searching the minimum
Network connectivity
(number of channel
ports)
Storage capacity
(number of FDLs)
Level
28
Heuristic approach
Starting topology: maximum connected




Iteration steps:
the current topology is perturbed
if the perturbed topology has a lower P
tot

the topology is modified
Highest possible level
29
Heuristic approach
Topology perturbation:
all the links are analyzed
the link that modified gives the lower P
tot
is
memorized
cancelled
added
30
Overview
Introduction and motivations
Goals of the thesis
State-of-the-art and enabling technologies
SIMON: an optical network simulator
Optical networks design
Obtained results
31
General backbone: topology
Node
User
1 2
3 4
5
6 7
8
9
10 11
12
32
General backbone: throughput
0 2 4 6 8 10 12 14 16 18
0.85
0.9
0.95
1
Total network load [Gbps]
F
r
a
c
t
i
o
n

o
f

p
a
c
k
e
t
s

s
u
c
c
e
s
s
f
u
l
l
y

t
r
a
n
s
f
e
r
r
e
d

1
2
3
4
M/M/L/k (4 MR)
M/M/L/k ( MR)
33
General backbone: delay
0 2 4 6 8 10 12 14 16 18
0
1
2
3
4
5
6
7
8
9
P
a
c
k
e
t
s

n
e
t

d
e
l
a
y

1
2
3
4
M/M/L/k (4 MR)
M/M/L/k ( MR)
Total network load [Gbps]
34
USA backbone: topology
28
27
26
25
24
23
22
21
20
19
18 15
16 11
10
12
13
17
14 9
8
5
6
7
3
4 2
1
35
USA backbone: throughput
0 5 10 15 20 25 30 35 40
0.86
0.88
0.9
0.92
0.94
0.96
0.98
1
1
2
3
M/M/L/k (4 MR)
M/M/L/k ( MR)
Total network load [Gbps]
F
r
a
c
t
i
o
n

o
f

p
a
c
k
e
t
s

s
u
c
c
e
s
s
f
u
l
l
y

t
r
a
n
s
f
e
r
r
e
d

more
36
Conclusions
Two key elements:

A new tool capable to simulate the next
generation optical networks

A new optimization target in the optical
networks design giving good results
more
37
E S
38
Optical Burst Switching
Packets are assembled in the network edge,
forming bursts
Advantages:
More efficient exploitation of the bandwidth
Possibility to implement Service
Differentiation
Disadvantages:
More complicated network structure
More complicated forwarding process
continue
39
Link model
Packet loss probability P on the link:
link capacity
o link traffic load
offered load [Erlangs],

o
=
( )

=
(

+ +
=
(

+
=

=
+

1 if 1
! !
1 if
1
1
!
1
1
0
1
1
0
1
0
r k
L i
r
r
r
i
L
L
i
i
L
i
k i

t
continue
L
r

=
40
Japan backbone: topology
1
2 3
4
5
6
7
8
9 10
11
41
Japan backbone: throughput
0 5 10 15 20 25 30
0.9
0.91
0.92
0.93
0.94
0.95
0.96
0.97
0.98
0.99
1
1
2
3
M/M/L/k (4 MR)
M/M/L/k ( MR)
Total network load [Gbps]
F
r
a
c
t
i
o
n

o
f

p
a
c
k
e
t
s

s
u
c
c
e
s
s
f
u
l
l
y

t
r
a
n
s
f
e
r
r
e
d

continue
42
Future work
Simulator:
Support for different architectures
FDLs of variable length

Heuristic approach:
More detailed model for FDLs


continue
43
End of presentation

You might also like