Transcript QoS Guarantee in Wirless Network

Mario Gerla
Current Network Research Projects
• Ad hoc, wireless networks (DARPA, NSF, ONR)
• Wireless, mobile access to Internet (NSF, Intel)
• Internet : QoS Routing and multicasting (CISCO,
NASA, NSF)
• Internet control models: TCP (EPRI,NASA)
• Internet II: high speed traffic models and
measurements (NSF, EPRI)
www.cs.ucla.edu/NRL
Cellular Vs Multihop
Standard Base-Station Cellular Networks
Base
Base
Base
Ad Hoc, Multihop wireless Networks
Challenging problem: multihop routing
•
•
•
•
•
•
mobility
need to scale to large numbers (100’s to 1000's)
unreliable radio channel (fading etc)
limited bandwidth
limited power
need to support multimedia (QoS)
Conventional routing: Distance Vector
0
Routing table at node 5 :
1
Destination Next Hop Distance
0
1
…
2
2
…
3
2
…
3
2
4
5
Conventional wired routing limitations
• Distance Vector (eg, Bellman-Ford, DSDV):
– routing control O/H linearly increasing with net size
– convergence problems (count to infinity); potential loops
CONVENTIONAL ROUTING DOES NOT SCALE TO SIZE AND MOBILITY
Fisheye State Routing
• Routing information is periodically exchanged
with neighbors (as in Distance Vector)
• BUT: Routing update frequency decreases with
distance to destination
– Higher frequency updates within a small radius and lower
frequency updates to remote destinations
– Result: Highly accurate routing information about immediate
neighborhood; progressively less detail for areas further away
Scope of Fisheye
2
8
5
3
1
9
9
4
6
Hop=1
7
13
10
12
11
36
14
21
Hop>2
15
16
17
22
23
20
29
27
25
24
Hop=2
19
18
26
30
35
28
34
32
31
How to deal with remote destination
inaccuracy? Landmark Routing
Landmark
Logical Subnet
Snapshot
LM3
LM1
P
O
J
K
L
D
C
I
H
LM2
LM4
B
A
GloMoSim Simulation Layers
Application
Data Plane
Control Plane
Application Processing
Application Setup
RTP Wrapper
Transport
IP
Network
Link Layer
MAC Layer
Radio
Channel
Transport Wrapper
IP Wrapper
Packet Store/Forward
Packet Store/Forward
Frame Wrapper
Frame Processing
Propagation Model
RCTP
TCP/UDP Control
RSVP
IP/Mobile IP
VC
Handle
Routing
Flow
Control
Routing
Clustering
Ack/Flow Control
RTS/CTS
CS/Radio Setup
Radio Status/Setup
Mobility
Clustering
Ad Hoc, Personal Networking with Bluetooth
headset
PDA
cell phone
storage
palmtop
What Is Bluetooth?
Landline
Cable
Replacement
Data/Voice
Access Points
Personal Ad-hoc
Networks
UCLA Adaptive Speech Experiment
Audio source adapts to QoS feedback
Speech
Recognition
TTS
Sync
Multihop Testbed
Wireless Network
client
server
• Adjustable Parameters
- sampling rate
- packet size
Increase in jitter
Increase in Packet loss
Audio(UDP)
Piggybacked Text Stream(UDP)
Control(TCP)
AdaptatIon Strategy:
network congested
channel noise/interference
• QoS Monitoring:
- packet loss
- jitter
sampling rate is reduced
packet size is reduced
iMASH: Interactive Mobile Application Support for
Heterogeneous clients
CS: R. Bagrodia, M. Gerla, S. Lu, L. Zhang
Medical School: D. Valentino, M. McCoy
Campus Admin: A. Solomon
UCLA
Supported by NSF
Diverse Display Devices
Use of different devices for different components of medical care
Imaging Workstation: high-quality medical imagery and
multimedia patient records
Physician’s PDA: for messaging and scheduling
Mobile Medical Notes: for reviewing and taking medical notes
Medical Workstation: multimedia patient records,
including moderate-resolution images
Hardware & Connectivity
Middleware
Servers
High bandwidth
Intranet
Application
Server
Middleware
Servers
Middleware
Servers
iMASH: Components
• Target application: Mobile physicians
• Middleware infrastructure to support anytime,
anywhere, any-device access to electronic
multimedia data
• Protocols to provide reliable QoS in a mobile,
heterogeneous network
• Simulation/emulation capability to evaluate
scalability of system to many users over large
geographic areas
• Limited evaluation via deployment within UCLA
medical school
QoS Routing and Multicast
in wired nets
• Supported by CISCO and by NASA AMES
• Intradomain environment
• Quality of Service Routing/Multicast for
Real Time traffic (IP telephony,video etc)
• Call Admission Control
• Traffic load balancing
Example of QoS Routing
A
B
Constraints: Delay (D) <= 25, Available Bandwidth (BW) >= 30
Multiple constraints QoS Routing
Given:
- a (real time) connection request with specified QoS
requirements (e.g., Bdw, Delay, Jitter, packet loss, path
reliability etc); examples: IP telephony, video streaming
Find:
- a min cost (typically min hop) path which satisfies such
constraints
- if no feasible path found, reject the connection
2 Hop Path --------------> Fails (Total delay = 55 > 25 and Min. BW = 20 < 30)
3 Hop Path ----------> Succeeds!! (Total delay = 24 < 25, and Min. BW = 90 > 30)
5 Hop Path ----------> Do not consider, although (Total Delay = 16 < 25, Min. BW = 90 > 30)
A
B
Constraints: Delay (D) <= 25, Available Bandwidth (BW) >= 30
We look for feasible path with least number of hops
Benefits of QoS Routing
Without QoS routing:
• must probe path & backtrack; non optimal path, control traffic
and processing OH, latency
With QoS routing:
• optimal route; “focused congestion” avoidance
• more efficient Call Admission Control (at the source)
• more efficient bandwidth allocation (per traffic class)
• resource renegotiation possible
High Speed Networks Performance
Measurement and Analysis
Mario Gerla and Medy Sanadidi
Project Focus
• High speed : backbone links at 2.4 Gbps and
above, as in Abilene and vBNS
• Heterogeneous networks: wired and wireless
• High performance distributed applications:
processor intensive, large data bases, high traffic
volume, low latency
• Application performance : measure the network
performance as perceived by network
applications/users; tune protocols to improve
performance
Example: Urban Simulation
(R. Muntz and B. Jepson)
• Real-time visual simulation for design, urban
planning, emergency response, and education
• Built Virtual Los Angeles model
• Challenge: remote/distributed access through
high speed net
Current Measurement Activities
• TCP performance over wireless Internet access
links (wireless LAN, satellite); wireless, lossy
channel emulator; TCP Westwood
• Characterization of long range dependent traffic
in the Internet; traffic generators
• Measure performance of dataView (3 D rendering
of scientific data): impact of propagation time and
network bottlenecks