2. Performance Evaluation Cycle
System under
Evaluation Use evaluation results
Performance in system
measures
System Model
Relate results to
- Environment System Model
- System
Evaluation Model
-Input (e.g.traces) Derive
-System model Performance Measures
-Evaluation method - Compute
-Analytical - Simulate
-Simulation - Measure
-Experimental
2
3. Example: Influence of network congestion on video
quality
• Streaming video transmitted through a
congested network
• Packets of the video get lost due to buffer
overflow
• What is the influence of the packet loss on the
video quality
3
4. Performance Evaluation Cycle: System Under
Evaluation
System under
Evaluation Use evaluation results
Performance in system
measures
System Model
Relate results to
- Environment System Model
- System
Evaluation Model
-Input (e.g.traces) Derive
-System model Performance Measures
-Evaluation method - Compute
-Analytical - Simulate
-Simulation - Measure
-Experimental
4
5. System under Evaluation / Performance measures
Performance measures
Network: packet loss, number of consecutive packets
lost, number of admitted streams
Content: type of packet lost, synchronization
User perception
Congested
network
(Buffer
Video overflow)
server End User
5
6. Performance Evaluation Cycle: System Model
System under
Evaluation Use evaluation results
Performance in system
measures
System Model
Relate results to
- Environment System Model
- System
Evaluation Model
-Input (e.g.traces) Derive
-System model Performance Measures
-Evaluation method - Compute
-Analytical - Simulate
-Simulation - Measure
-Experimental
6
7. System Model
Congestion can be modelled by
- Background traffic
- Variable service time in router
Background
traffic
Tagged
video source
Packet loss
7
8. Performance Evaluation Cycle: Evaluation model and
determine performance measures
System under
Evaluation Use evaluation results
Performance in system
measures
System Model
Relate results to
- Environment System Model
- System
Evaluation Model
-Input (e.g.traces) Derive
-System model Performance Measures
-Evaluation method - Compute
-Analytical - Simulate
-Simulation - Measure
-Experimental
8
9. Analytical Approach
Frame size trace - bond
250000
I-frames I h1,
e
1/ 1
B B P B B P B B P B B
B-frames
m
N I
P-frames
a 200000 1
r
f 1/ N h1,
N I
2
/ 150000 h2,
1/ 1
s
t
i 100000 N I
B B P B B P B B P B B 2
b
1/ N h1,
50000 N
i h1,
I hL,L
1/
0
0 10000 20000
frame number
30000 40000
N I
1 B B P B B P B B P B B L
1/ N
N
.
. approximate
B<∞
process
packet loss
superposition
probability 9
of X sources
10. s
e
c
Use of results: Admission Control
r
u
o
s
1e-4 admission boundary, buffer = 100 packets
x 60
i Theoretical results
r Experimental results
e 50
t
s
a 40
f
o
30
r
e
b 20
m
u
n 10
0
0 5 10 15 20 25 30 35 40 45
number of bond sources
10
12. Performance Evaluation Cycle: Interpretation of results
System under
Evaluation Use evaluation results
Performance in system
measures
System Model
Relate results to
- Environment System Model
- System
Evaluation Model
-Input (e.g.traces) Derive
-System model Performance Measures
-Evaluation method - Compute
-Analytical - Simulate
-Simulation - Measure
-Experimental
12
13. Use performance evaluation results
Use the IBBT competences to suggest improvements
Examples:
Network groups:
intelligent buffer management schemes (e.g. using
thresholds)
Congestion control mechanisms (e.g. explicit
congestion notification)
Define efficient admission control algorithms
Video groups:
Codecs using feedback
use layered video coding schemes
13
14. Use of Performance Evaluation Competence
Application and
Content
Network
Protocols
Layer L2 – L4
Physical Layer
14
15. Application and Content
Layer System Measures
Application content distribution responsiveness, scalability,
web access stability
parallel file
processing
Video and audio analysis of different coding efficiency,
Content codecs, error error resilience and
resilience concealment, error types and
mechanisms, … frequencies, synchronization
Traffic Analysis video, (aggregated) burstiness,
applications, web peak bitrate,
traffic average bitrate, mobility
15
16. Networks Protocols L2 – L4
Layer System Measures
Protocol scheduling mechanism, responsiveness,
performance MAC protocol, routing scalability, stability,
evaluation protocol, auto-configuration functionality,
protocol throughput
protocol test testing of HGW,
suites modem/mux interaction
Advanced and protocols for mesh, ad hoc scalability,
large scale and wireless sensor robustness, reliability,
experimental networks throughput
testbeds (fixed
and wireless)
16
17. Physical Layer
Layer System Measures
Signal propagation WiMAX Signal propagation
Body Area Networks characteristics
17
18. Generic Test and Measurement Equipment
Use of advanced test equipment:
E.g. Spirent-Smartbits, Spirent-
Avalanche, Agilent-NX2, Opticom-
Opera, Tracespan, Fluke-Optiview, …
18