Design of a Mobile TV Testbed - network systems lab @ sfu
Download
Report
Transcript Design of a Mobile TV Testbed - network systems lab @ sfu
Designing an Efficient and Extensible
Mobile TV Testbed
Cheng-Hsin Hsu
Simon Fraser University, Canada
joint work with Mohamed Hefeeda,
Yi Liu, and Cong Ly
Mobile TV Service
Broadcast mass-market programs to subscribers
Mobile devices have stringent energy budgets
Devices receive a data burst and turn off receiving
circuits until the next burst called time slicing
2
Mobile TV Networks
Content
Providers
Streaming
Server
Network Operators
Base Station
Multiplexer
Modulator/
Amplifier
(IP Encapsulator)
Camera
IP Networks
ASI Networks
Program feeds are IP streams from streaming
servers or cameras
Multiple TV programs are multiplexed AND time
sliced by a multiplexer into a MPEG-2 TS stream
The MPEG-2 TS stream is modulated, amplified,
and broadcast to mobile devices
3
Problem Statement
Design a mobile TV base station for academic
prototyping and cost-efficient small- to mediumsize deployments
platform to analyze: energy consumption,
channel switching delay, no. broadcast
programs, and perceived streaming quality
10-20 TV channels with a commodity PC or
low-end server
4
Current Solutions (1/2)
Commercial Base Stations
expensive, e.g., a single EXPWAY FastESG
server costs 75k USD [Sarri09]
a complete base station costs even more
Need a more cost-efficient
base station!
5
Current Solutions (2/2)
Python
Sources
For PSISI
VLC
Server
MPEG
TS Packets
Python
Compiler
Data
Aggregator
x20?
Time
Slicer
Pcap
Null Packet
Replacer
TS
Tdt
Updater
w/PSISI
Dtplay
Correct PSISI
Open-Source Base Station [FATCAPS]
too many disk I/O’s
does not scale well
too many utilities with no admin interface
Need a better design!
6
Design Goals
[G1] Higher efficiency and scalability
avoid disk I/O’s and memcpys
[G2] Utilization of multi-core processors
pipelined structure to allow parallelism
[G3] Integrated software solution
centralized admin interface
[G4] Better extensibility
future supports for other networks such as
MediaFLO, WiMAX, and MBMS
7
Design Decisions (1/3)
[D1] Use Burst as the unit of time slicing,
encapsulation, and transmission.
Burst is self-contained with IP payloads and
headers/trailers of all protocols
No disk I/O’s for intermediate data
No memcpys for IP payloads
8
Design Decisions (2/3)
[D2] Divide the base station into three indep.
Phases, which are connected by two priority queue
pipelined and parallelism
Request
Queue
Empty
Burst
Time
Slicing
Thread
With IP
Payload
Encap.
Thread
With All
Headers
/Trailers
Ready
Queue
Trans.
Thread
Encap.
Thread
Encap.
Thread
9
Design Decisions (3/3)
[D3] Implement a centralized Configuration
Manager to allow save/restore settings
interface with Web GUI for management
[D4] Modularized design for future extensions
For example, MPE-FEC Burst is a subclass of
MPE Burst
10
Software Architecture
11
High-Level Design
12
Design of Burst Schedulers
13
Design of Burst Readers
14
Design of Bursts
15
Design of Encapsulators
16
Design of Transmitter
17
Design of PSI/SI Tables
PAT: program association
PMT: program map
NIT: network information
INT: IP/MAC notification
SDT: service description
TDT: time and date
18
Design of Configuration Manager
19
Testbed Setup
20
Future Work
Web GUI for configuration management [Cong]
MPE-FEC support [Hamed]
PSI/SI table implementation [Farid]
StreamReader classes [Som]
Flute server integration
ESG files implementation
21
Conclusions
Presented layout of general broadcast network
Outlined design goals of a broadcast base station
Described our design decisions and system
architecture
Presented the high-level system design and detailed
design for each component
Highlighted future work
22
Thank You, and Questions?
More details can be found online at http://nsl.cs.sfu.ca
23