Examples of Traffic

Содержание

Слайд 2

Video

Video Traffic (High Definition)
30 frames per second
Frame format: 1920x1080 pixels
24 bits

Video Video Traffic (High Definition) 30 frames per second Frame format: 1920x1080
per pixel
Required rate: 1.5 Gbps
Required storage: 1 TB per hour
Video uses compression algorithm to reduce bitrate

ECE 466

Слайд 3

MPEG compression

I frames: intra-coded
P frames: predictive
B frames: bi-directional
Group of Pictures

MPEG compression I frames: intra-coded P frames: predictive B frames: bi-directional Group
(GOP): IBBPBBPBB

ECE 466

Слайд 4

Example: Harry Potter

30 minutes of Harry Potter movie with HD encoding
Codec: H.264

Example: Harry Potter 30 minutes of Harry Potter movie with HD encoding
SVC
Resolution: 1920x1088
Frames per second: 24 fps
GOP: IBBBPBBBPBBBPBBB
Frame size (Bytes):
Avgerage: 28,534
Minimum: 109
Maximum: 287,576
Mean Frame Bit Rate (Mbps): 5.48
Peak Frame Bit Rate (Mbps): 55.21

ECE 466

Слайд 5

Harry Potter: 30 minutes

ECE 466

Harry Potter: 30 minutes ECE 466

Слайд 6

Harry Potter: 20 seconds

ECE 466

Harry Potter: 20 seconds ECE 466

Слайд 7

Harry Potter

ECE 466

Distribution of packet sizes

Distribution of time gap between packets

Harry Potter ECE 466 Distribution of packet sizes Distribution of time gap between packets

Слайд 8

Voice

Standard (Pulse Code Modulation) voice encoding:
8000 samples per second (8 kHz)
8 bits

Voice Standard (Pulse Code Modulation) voice encoding: 8000 samples per second (8
per sample
Bit rate: 64 kbps
Better quality with higher sampling rate and larger samples
CD encoding:
44 kHz sampling rate
16 bits per sample
2 channels
Bit rate: 1.4 Mbps
Packet voice collects multiple samples in once packet
Modern voice encoding schemes also use compression and silent suppression

ECE 466

Слайд 9

Skype Voice Call: 6 minutes

ECE 466

SVOPC encoding, one direction of 2-way call

Dark

Skype Voice Call: 6 minutes ECE 466 SVOPC encoding, one direction of
blue: UDP traffic
Light blue: TCP traffic

Слайд 10

Skype Voice Call: 2 seconds

ECE 466

Skype Voice Call: 2 seconds ECE 466

Слайд 11

Skype (UDP traffic only)

ECE 466

Distribution of packet sizes

Distribution of time gap between

Skype (UDP traffic only) ECE 466 Distribution of packet sizes Distribution of time gap between packets
packets

Слайд 12

Internet Traffic: 10 Gbps link

Data measured from a backbone link of a

Internet Traffic: 10 Gbps link Data measured from a backbone link of
Tier-1 Internet Service provider
Link measured: Chicago – Seattle
Link rate: 10 Gbps (10 Gigabit Ethernet)
Data measures total (aggregate) traffic of all transmissions on the network
Data shown is 1 second:
~430,000 packets packet transmissions
Average rate: ~3 Gbps
Avg. packet size: 868 Bytes
Min. packet size: 44 Bytes
Max. packet size: 1504 Bytes

ECE 466

Слайд 13

Internet Traffic: 10 Gbps link

ECE 466

One data point is the traffic in

Internet Traffic: 10 Gbps link ECE 466 One data point is the traffic in one millisecond
one millisecond

Слайд 14

Internet Traffic

ECE 466

Packet arrivals in a 2μs snapshot:

Internet Traffic ECE 466 Packet arrivals in a 2μs snapshot:

Слайд 15

Internet Traffic: 10 Gbps link

ECE 466

Distribution of packet sizes

Distribution of time gap

Internet Traffic: 10 Gbps link ECE 466 Distribution of packet sizes Distribution
between packets

Слайд 16

Data Traffic: “Bellcore Traces”

Data measured on an Ethernet network at Bellcore Labs

Data Traffic: “Bellcore Traces” Data measured on an Ethernet network at Bellcore
with 10Mbps
Data measures total (aggregate) traffic of all transmissions on the network
Measurements from 1989
One of the first systematic analyses of network measurements

ECE 466

Слайд 17

Data Traffic: 100 seconds

ECE 466

One data point is the traffic in 100

Data Traffic: 100 seconds ECE 466 One data point is the traffic in 100 milliseconds
milliseconds

Слайд 18

Packet arrivals: 200 milliseconds

ECE 466

Packet arrivals: 200 milliseconds ECE 466

Слайд 19

Bellcore traces

ECE 466

Distribution of packet sizes

Distribution of time gap between packets

Bellcore traces ECE 466 Distribution of packet sizes Distribution of time gap between packets

Слайд 20

Some background on Lab 1

Some background on Lab 1

Слайд 21

ECE 466

“Typical network traffic is not well described by Poisson model”

Lab 1

Lab

ECE 466 “Typical network traffic is not well described by Poisson model”
1 is about comparing a simple model for network traffic (Poisson traffic) with actual network traffic (LAN traffic, video traffic)
Lab 1 retraces one fo the most fundamental insights of networking research ever:

Слайд 22

ECE 466

Poisson

In a Poisson process with rate λ, the number of events

ECE 466 Poisson In a Poisson process with rate λ, the number
in a time interval (t, t+τ ], denoted by N(t+τ) – N(t), is given by
In a Poisson process with rate λ, the time between events follows an exponential distribution:

Слайд 23

ECE 466

In the Past…

Before there were packet networks there was the circuit-switched

ECE 466 In the Past… Before there were packet networks there was
telephone network
Traffic modeling of telephone networks was the basis for initial network models
Assumed Poisson arrival process of new calls
Assumed Poisson call duration

Source: Prof. P. Barford (edited)

Слайд 24

ECE 466

… until early 1990’s

Traffic modeling of packet networks also used Poisson
Assumed

ECE 466 … until early 1990’s Traffic modeling of packet networks also
Poisson arrival process for packets
Assumed Exponential distribution for traffic

Source: Prof. P. Barford (edited)

Слайд 25

ECE 466

The measurement study that changed everything

Bellcore Traces: In 1989, researchers at

ECE 466 The measurement study that changed everything Bellcore Traces: In 1989,
(Leland and Wilson) begin taking high resolution traffic traces at Bellcore
Ethernet traffic from a large research lab
100 μ sec time stamps
Packet length, status, 60 bytes of data
Mostly IP traffic (a little NFS)
Four data sets over three year period
Over 100 million packets in traces
Traces considered representative of normal use

Source: Prof. C. Williamson

The data in part 3 of Lab 1 is a subset of the actual measurements.

Слайд 26

ECE 466

That Changed Everything…..

Extract from abstract

Results were published in 1993
“On the Self-Similar

ECE 466 That Changed Everything….. Extract from abstract Results were published in
Nature of Ethernet Traffic” Will E. Leland, Walter Willinger, Daniel V. Wilson, Murad S. Taqqu
“We demonstrate that Ethernet local area network (LAN) traffic is statistically self-similar, that none of the commonly used traffic models is able to capture this fractal behavior, that such behavior has serious implications for the design, control, and analysis of high-speed…”

Source: Prof. V. Mishra, Columbia U. (edited)

Слайд 27

ECE 466

Fractals

Source: Prof. P. Barford, U. Wisconsin

ECE 466 Fractals Source: Prof. P. Barford, U. Wisconsin

Слайд 29

ECE 466

Traffic at different time scales (Bellcore traces)

bursty

still bursty

Source: Prof. P. Barford

ECE 466 Traffic at different time scales (Bellcore traces) bursty still bursty
(edited)

Слайд 30

ECE 466

Source: Prof. V. Mishra, Columbia U.

ECE 466 Source: Prof. V. Mishra, Columbia U.

Слайд 31

ECE 466

What is the observation?

A Poisson process
When observed on a

ECE 466 What is the observation? A Poisson process When observed on
fine time scale will appear bursty
When aggregated on a coarse time scale will flatten (smooth) to white noise
A Self-Similar (fractal) process
When aggregated over wide range of time scales will maintain its bursty characteristic

Source: Prof. C. Williamson

Слайд 32

ECE 466

Why do we care?
For traffic with the same average, the probability

ECE 466 Why do we care? For traffic with the same average,
of a buffer overflow of self-similar traffic is much higher than with Poisson traffic
Costs of buffers (memory) are 1/3 the cost of a high-speed router !
When aggregating traffic from multiple sources, self-similar traffic becomes burstier, while Poisson traffic becomes smoother
Имя файла: Examples-of-Traffic.pptx
Количество просмотров: 157
Количество скачиваний: 0