Transcript General Background - Network Design

CSC778 - Optical Networking
Rudra Dutta, Fall 2007
General Overview: Static Traffic Network Design
Overview

Static Traffic
–
–
–
–

Variation of traffic over time - no variation
Where and why?
A view of the network
Traffic networks and transport networks
Network Design
–
–
Capacity, flow, provisioning
Design goals
Copyright Rudra Dutta, NCSU, Fall, 2007
2
Network Traffic

What is traffic?
–

That which occupies / is carried by links
Traffic is offered to the network by/at network nodes
–
–
–
Network is made of end nodes, intermediate nodes, and links
All traffic ultimately originated by end-nodes
However, for hierarchical networks, aggregation may occur

In some network paradigms, E2E traffic is recognizable
at all “places” in network
 In others, components within aggregated traffic not
recognizable inside network
 “Forwarding” at L1 versus L3
–
–
Are telephone calls just (very) long packets?
Consider the flexibility / choice of actions afforded to
intermediate stations
Copyright Rudra Dutta, NCSU, Fall, 2007
3
Network View

Because of scalability, hierarchy seems inevitable
 Nature of end-nodes and intermediate nodes vary
 All links are TDM (FDM modeled as separate links)
4
2
1
3
Copyright Rudra Dutta, NCSU, Fall, 2007
4
Traffic Aggregation - Static Traffic


Consider lowest level networks
Assume each station injects traffic steadily
–

Due to aggregation, magnitude increases as traffic
climbs hierarchy
–


But constant nature of traffic remains
Aggregation/dis-aggregation process is straightforward
for intermediate nodes
–

Number of bits injected per time unit is constant for each source
Effectively same as slotted TDM
Therefore static traffic is stable - remains static at higher
levels of hierarchy
Utilization of links / provisioning of capacity is not a
problem / not interesting
–
Capacity, of course, must increase at higher levels
Copyright Rudra Dutta, NCSU, Fall, 2007
5
Bursty Traffic

Traffic is generated intermittently at each end
node
–

Assume (peak) rates are known
Question of capacity and aggregation become
intertwined
–
One approach: pretend each end node is a steady
source at its peak rate, then provision as before

–
Aggregation will be easy
Another approach: provision for average




Do bursts arrive deterministically?
Sometimes link will be busy when traffic arrives to use it
Must store-and-forward, or discard
Question of slotting TDM comes in - work conservation
Copyright Rudra Dutta, NCSU, Fall, 2007
6
A View of Aggregation
1
2
burstiness
4
2
3
1
3
4
4
bandwidth
Copyright Rudra Dutta, NCSU, Fall, 2007
7
“Elastic” Traffic

Read:
–
–
–

“Elastic Traffic Effects on WDM Dynamic Grooming
Algorithms”, R. Lo Cigno, E. Salvadori, Z. Zsoka,
Globecom 2004
Also reference [10] of the above
Need to primarily read the definition and discussion
on “elasticity” of Internet traffic
Briefly:
–
–
–
Source-to-destination traffic flows in the Internet are
not static as generated
Congestion in network will slow down bursts
In response, flow duration will increase
Copyright Rudra Dutta, NCSU, Fall, 2007
8
Empirical Observations

Many sources around the net
–

Not all are equally comprehensive or thorough, use
judgment
CAIDA is a good source
–
Source for this set of data
http://www.caida.org/outreach/isma/9901/slides/gmiller_ISMA99/sld001.htm
Copyright Rudra Dutta, NCSU, Fall, 2007
9
About Loss

Loss may occur on the link
–
–

Loss may occur at intermediate nodes
–
–

Usually very little in guided medium - ignore
Usually handled by L2 transmissions or ignored
Store-and-forward buffers are finite - may overflow
Other mechanism at intermediate node may discard
Does retransmission occur?
–
–
May not be required / desired
If desired,


May be at L2, on link
May be at L4, E2E
Copyright Rudra Dutta, NCSU, Fall, 2007
10
About Delay

Controversial proposition:
–
–

Delay for static traffic / slotted TDM aggregation
–

Small, constant
Delay for bursty traffic / statistical TDM
–

“If delay is not important, capacity is not important”
“If delay is important, capacity must be large OR
aggregation must be slotted OR both”
Large range
Delay for circuits - telephony
–
Very small and constant, operative quantity is
blocking ratio
Copyright Rudra Dutta, NCSU, Fall, 2007
11
Delay for Single Link


Bursty traffic, statistical TDM
Usual M/M/1 assumptions
–


In reality, traffic process is heavier-tailed
D(l, m) = 1 / (m - l)
“Statistical Multiplexing Gain”
Copyright Rudra Dutta, NCSU, Fall, 2007
12
Blocking in Telephony
Average call rate l
 Average holding time t
 Offered traffic load or intensity a = lt

ac / c!
 B(a,c) = -------------------
S ak / k!
Copyright Rudra Dutta, NCSU, Fall, 2007
13
Static Traffic Performance

Give “matrix” of traffic demand components
–
–
–
Static, “always-on”
Usually aggregate
Measured or estimated

Delay - fairly constant for each demand
 Blocking - none; loss - none
–

Except in unusual circumstances
Performance is measured globally
–
–
–
Various objectives
Delay or throughput (global, across all components)
Revenue, fairness, protection, …
Copyright Rudra Dutta, NCSU, Fall, 2007
14
Transport, Demand, Capacity

Traffic Networks and Transport Networks
 Traffic networks: where stochastic demand
picture is operative
–

Transport networks: where traffic demands of
static magnitude are seen to be operative
–
–
–

Short term switching/routing
(Semi-) Permanent
QoS considerations paramount
Demands seen to be injected at transport network
nodes, lower level networks not visible
Links must have capacity to carry traffic
–
But routing can be designed on basis of traffic
Copyright Rudra Dutta, NCSU, Fall, 2007
15
Flows

Multiply defined term
 In this context, the traffic associated with a path
or route
 Sometimes (esp. in Internet context) defined as
source-to-destination traffic
 Routing defines flows, but routing can be in
terms of flows
–
If only s-d is considered, routing can be by flow (s-d)

–
Instead of by destination only
But same s-d traffic can be split up and routed
variously

Requires slotted TDM approach, to “mark” flows
Copyright Rudra Dutta, NCSU, Fall, 2007
16
Summation

L3-switched/routed traffic can be thought of as static at
a high level of network
 At this level, a transport view of network is appropriate,
using slotted TDM
 This approach is indispensable when strong guarantees
must be made w.r.t. delay, variability of delay, and
bandwidth
 Capacity of links becomes important in meeting such
guarantees
 Capacity, routing, and other variables can be thought of
as “control knobs” in the ensuing design problem
Copyright Rudra Dutta, NCSU, Fall, 2007
17
Multi-layer Networks

Generalized protocol
layering can create
complicated networks
–
–

Better thought of as
multiple layers
Each layer satisfies flow
constraints
Generally, demand is
specified in one layer
and capacity in another
–
Must assume some
mapping method possibly constrained
Copyright Rudra Dutta, NCSU, Fall, 2007
Ckt-switched
voice
Private
Line
IP
Networks
CrossConnect
Digital
Transmission
Optics
Media
18
Management Cycle
Near Real-Time
Capacity Mgmt, Netw Engg.
Network Planning
Copyright Rudra Dutta, NCSU, Fall, 2007
19
Design Problems

Capacity Design
–
–

Fair Networking
–
–

Max-min fairness - user fairness
Proportional fairness - mixture of user and network
Topology Design
–
–

Given topology, traffic matrix, (constrained routing), find
minimum links capacities that will work
Utilization maximization
Link installation cost included
Possibly virtual links in multilayer networks
Restoration Design
–
–
Backup paths as well as working paths
Governed by failure criteria
Copyright Rudra Dutta, NCSU, Fall, 2007
20