Cooperative Overlay Networking for Streaming Media Content

1
Cooperative Overlay Networking for Streaming
Media Content

• Feng Wang1, Jiangchuan Liu1, Kui Wu2
• 1School of Computing Science, Simon Fraser
  University
• fwa1, jcliu_at_cs.sfu.ca
• 2Department of Computer Science, University of
  Victoria
• wkui_at_cs.uvic.ca

Chapter 6 Cooperative Networking (Wiley)
Editors M. S. Obaidat and S. Misra
2
Outline

• Background and Motivation
• A Cooperative Overlay Design mTreebone
• Treebone Construction and Optimization
• Collaborative Push/Pull Data Delivery
• Performance Evaluation
• Conclusion and Future Work

3
Background

• Architectural Choices for Media Streaming
• IP Multicast
• Implement multicast at the IP (network) layer
• Multicast routing is the most efficient
• Limited in reach and scope due to concerns
  regarding scalability, deployment, and support
  for higher level functionality
• Proxy Caching
• Exploits the temporal locality of client requests
  for streaming media content

4
Background (contd)

• Deploy a group of proxies to cooperatively
  utilize caching space, balance loads and improve
  the overall performance
• Peer-to-Peer
• Functionality is pushed to users actually
  participating in the multicast group
• Administration, maintenance, responsibility for
  operations of a system are distributed among
  users
• Research focuses on simultaneous media broadcast
  using the application end-point architecture

5
Motivation

• Previous proposals for Peer-to-Peer Media
  Streaming can be broadly classified into two
  categories
• Tree-based approaches
• Peers are organized into structures (typically
  trees) for delivering data
• Each data packet is pushed using the same
  structure
• Nodes on the structure have well-defined
  relationships, e.g., parent-child relationships
  in trees

6
Motivation (contd)

• Mesh-based approaches
• Do not construct or maintain an explicit
  structure for delivering data
• Use the availability of data to guide the data
  flow
• Based on data availability information
  periodically exchanged among partner nodes, a
  node may then retrieve unavailable data from
  other partners, or supply available data to other
  partners

7
Motivation (contd)

• Different category of approaches have different
  advantages
• Mesh-based approaches have good robustness, but
  suffer from the efficiency-latency tradeoff
• Tree-based approaches use efficient push
  delivery, but have to face data outage during
  internal node dynamics.

Can we combine their advantages together to offer
high efficiency and resilience with moderate
maintenance cost?
8
Our Idea - mTreebone

• Hybrid Cooperative Tree/Mesh Overlay
• Organize stable nodes as a tree backbone
  (Treebone) to efficiently deliver data
• Mesh overlay assists
• Treebone and handles
• dynamics

9
Questions

• How to identify stable nodes?
• How to better organize these nodes?
• How to reconcile Treebone and mesh overlay?

10
Questions

• How to identify stable nodes?
• How to better organize these nodes?
• How to reconcile Treebone and mesh overlay?

11
Stable Node Identification

• Previous studies nodes with higher ages tend to
  stay longer
• Select an Age Threshold T and consider nodes
  staying longer than T as stable
• Objective maximize the Expected Service Time of
  a Treebone node
• For Pareto Dist. (with k as shape parameter)

12
Treebone Evolution

• Each new node attaches to a node with available
  bandwidth
• Non-Treebone nodes check periodically until
  promoted into Treebone

0
5
0
5
6
7
12
10
6
17
8
17
11
13
Questions

• How to identify stable nodes?
• How to better organize these nodes?
• How to reconcile Treebone and mesh overlay?

14
Treebone Optimization

• Reduce average depth of Treebone node
• High-Degree-Preemption
• Low-Delay-Jump
• Theorem The average depth of Treebone is
  minimized when high-degree-preemption and
  low-delay-jump terminate at all Treebone nodes.

15
Questions

• How to identify stable nodes?
• How to better organize these nodes?
• How to reconcile Treebone and mesh overlay?

16
Seamless Push/Pull Switching

• Tree-push pointer
• receives data pushed
• from Treebone
• Mesh-pull window
• detects loss and pull data
• from mesh neighbors
• To avoid duplicate data, mesh-pull window always
  keeps behind Tree-push pointer

Playback Direction
Tree-push Pointer
Playback Pointer
Mesh-pull Window
17
Outline

• Introduction
• mTreebone Design
• Treebone Construction and Optimization
• Collaborative Push/Pull Data Delivery
• Performance Evaluation
• Conclusion and Future Work

18
Performance Evaluation

• Scenario
• Arrival Poisson dist.
• Duration Pareto dist.
• Simulations
• 5000 nodes
• Prototype Experiments on PlanetLab
• 200 nodes

19
Simulation Results
Data Loss Rate
Startup Latency
Playback Delay
20
Experiment Results
Data Loss Rate
Startup Latency
Playback Delay
21
Experiment Results (contd)
Control Overhead
Different Age Threshold
Different Churn Rate
22
Outline

• Introduction
• mTreebone Design
• Treebone Construction and Optimization
• Collaborative Push/Pull Data Delivery
• Performance Evaluation
• Conclusion and Future Work

23
Conclusion

• mTreebone a hybrid cooperative overlay taking
  advantages of both tree and mesh
• Treebone by stable nodes to offer high
  efficiency
• mesh structure to improve the robustness
• Threshold based Treebone nodes selection
• Treebone construction and optimization
• Seamless push/pull switching buffer

24
Future Work

• Other tree organization and optimization methods
  to further improve Treebones efficiency and
  interactions with mesh
• Multi-tree-based backbone, which may lead to more
  balanced load and finer-grained bandwidth control
• Conduct large scale experiments as well as real
  deployment over global Internet