Adaptive Video Streaming in Vertical Handoff: A Case Study

1
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Ling-Jyh Chen, Guang Yang, Tony Sun, M. Y.
  Sanadidi, Mario Gerla
• Computer Science Department, University of
  California at Los Angeles

2
Outline of the Talk
Adaptive Video Streaming in Vertical Handoff A
Case Study

• The problem the performance of video streaming
  may degrade due to wireless channel errors and
  vertical handoffs.
• Key idea
• Adaptive video delivery can improve the end
  users perceived quality.
• Seamless handoff can provide uninterrupted
  services even with the presence of mobility.
• The results we show that the combination of
  adaptive video streaming and seamless handoff can
  go a long way in providing better video streaming
  in mobile computing scenarios.

3
Adaptive Video Streaming in Vertical Handoff A
Case Study
Introduction

• Mobile Computing Scenarios

Mobility
4
Introduction (cont.)
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Three issues
• Seamless mobility across heterogeneous networks.
• Adaptation to network dynamics such as wireless
  channel errors and congestion.
• Application adaptation to maximize the end users
  perceived quality.

5
Background Seamless Handoff
Adaptive Video Streaming in Vertical Handoff A
Case Study
A seamless handoff is defined as a handoff scheme
that maintains the connectivity of all
applications on the mobile device when the
handoff occurs.
6
Background Seamless Handoff
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Two goals low latencies and few packet losses
• Related Work
• Network Layer Approaches
• MIPv4, IPv6
• Upper Layer Approaches
• End-to-End Approaches (e.g. Dynamic DNS)
• New Session Layer Protocols (e.g. MSOCKS)
• Transport Layer Protocols (e.g. TCP-MH and SCTP)
• Middleware Approach (e.g. USHA)
• Q Which seamless handoff solution are you using?

7
Proposed Approach USHA
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Universal Seamless Handoff Architecture

NAT server
NAT Server
All packets are encapsulated and transmitted
using UDP
Applications are bound to the tunnel and
transparent to the handoff.
8
Background Video Streaming
Adaptive Video Streaming in Vertical Handoff A
Case Study
SCP
Helix
RAP
Microsoft
TEAR
VTP
TFRC
9
Proposed Approach VTP
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Video Transport Protocol
• Bandwidth Estimation
• Achieved Rate Measurement
• Available Bandwidth Estimation
• Assume we use packet trains of length k to
  measure the achieved rate.
• Denote di as the number of bytes in packet i, ti
  as the time when packet i arrives at the client.

10
Proposed Approach VTP (cont.)
Adaptive Video Streaming in Vertical Handoff A
Case Study

1. Rate Adaptation Multiple streams of the same
   content are encoded at different rates.

DR Decreasing Rate State IR Increasing Rate
State Q0 Lowest Quality Video (56Kbps) Q1
Normal Quality Video (150Kbps) Q2 Highest
Quality Video (500Kbps)
11
Proposed Approach VTP (cont.)
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Variable Bit Rate (VBR) Video
• VTP divides a video clip into a number of
  segments.
• For each segment, VTP computes a target rate, at
  which neither buffer overrun or underrun should
  occur.
• Since video streams are pre-stored, instantaneous
  sending rates are available beforehand, and so
  are the target rates of the segments.
• VTP applies these target rates to the finite
  state machine for rate adaptation.

12
Experiments
Adaptive Video Streaming in Vertical Handoff A
Case Study

• VTP server/client are implemented on Linux.
• USHA system is set up on Linux, with custom
  configured NAT and IP tunneling.
• VTP client is connected to the Internet via
  802.11b and 1xRTT, which is provided by Verizon
  Wireless.
• Two vertical handoff scenarios are tested
• From 1xRTT to 802.11b
• From 802.11b to 1xRTT

13
Experiments 1xRTT to 802.11b
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Non-adaptive Video Streaming

Frame Rate received at the Mobile Host
Sending Rate at the Video Server
14
Experiments 1xRTT to 802.11b
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Adaptive Video Streaming

Sending Rate at the Video Server
15
Experiments 802.11b to 1xRTT
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Non-adaptive Video Streaming

Frame Rate received at the Mobile Host
Sending Rate at the Video Server
16
Experiments 802.11b to 1xRTT
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Adaptive Video Streaming

Sending Rate at the Video Server
17
Discussion
Adaptive Video Streaming in Vertical Handoff A
Case Study

• Drastic changes in the link capacity are often
  associated with vertical handoffs.
• Most traditional streaming algorithms incorporate
  the well-known slowly-responsive congestion
  control (SlowCC) and thus cannot take aggressive
  advantage of the rapid change of resources in
  emerging vertical handoff scenarios.

18
Discussion (cont.)
Adaptive Video Streaming in Vertical Handoff A
Case Study

• For a handoff from LOW to HIGH, VTP can properly
  and rapidly adapt its sending rate and video
  quality to available bandwidth, and hence is
  successful in handling vertical handoffs.
• For a handoff from HIGH to LOW, application
  performance would benefit if the server could
  predict the handoff and thus adapt its sending
  rate in advance.

19
Conclusion
Adaptive Video Streaming in Vertical Handoff A
Case Study

• We studied the need and evaluated the performance
  of adaptive video streaming in vertical handoff
  scenarios.
• Experiments with handoffs from 1xRTT to 802.11b
  and vice versa have been carried out to evaluate
  the performance of our proposed solution.
• Such a combination of adaptive video streaming
  and seamless vertical handoff will become
  desirable in the emerging ubiquitous mobile
  computing environment.

20
Adaptive Video Streaming in Vertical Handoff A
Case Study

• T h a n k s !