Pervasive Web Content Delivery with Efficient Data Reuse

1
Pervasive Web Content Delivery with Efficient
Data Reuse

• Chi-Hung Chi and Cao Yang
• School of Computing
• National University of Singapore
• Email chich_at_comp.nus.edu.sg

2
Outline

• Introduction
• Scenarios
• Observation
• Potentials and Challenges
• System Model and Architecture
• Requirements and Design Consideration
• Scalable Data Model
• System Architecture and Proxy
• Example
• Related Work
• Conclusion

3

• Part 1
• Introduction

4
Scenarios

• Digital Images on the Internet
• accounts for 40 of the data bytes accessed
  across the WWW
• Internet Client Variation
• in terms of hardware capabilities, user
  tolerance level, personal preference, etc.
• Network Variation
• in terms of network bandwidth, timeout latency,
  etc.

5
Problem

• Web-based digital image libraries
• Single copy approach
• Problem not able to accommodate the wide
  spectrum of Internet clients
• Multiple copy approach
• Problem hard to maintain
• What versions to keep?
• Users requirements keep changing.

6
Observation

• HTTP/1.1 protocol Allows a client to request
  portions of an object via Range requests.
• Example
• Range Request

Get http//www.nus.edu.sg Range bytes2500-4000
Servers reply
HTTP/1.1 206 Partial Content Date Thu, 03 May
2001 092212 GMT Last-Modified Thu, 03 May 2001
071227 GMT Content-Range bytes
2500-4000/7614 Content-Length 1501
7
Potentials Single-client scenario
Effective network speed 1KB/s Timeout latency
100s
Request 1 - 100K byte
Reply 1 100K byte
Client
Server
Image X 400KB
1 100KB
8
Potentials Single-client scenario
Effective network speed 1KB/s Timeout latency
100s
Request 100K - 200K byte
Reply 100K 200K byte
Client
Server
1 200KB
1 100KB
Image X 400KB
9
Potentials Multiple-clients scenario
1 100KB
Request X
Request X
10
Potentials Multiple-clients scenario
1 100KB
Request X
Request X
100KB 200KB
1 200KB
1 100KB
11
Big Idea!

• The potential benefits of JPEG 2000 and HTTP/1.1
  protocol can be maximized by storing and reusing
  partial objects.
• Over slow network link, as more clients requests
  for the target image, the visual effect improves
  until the original quality is obtained.

12
Our Solution

• Exploits the potentials of JPEG 2000 and HTTP/1.1
  protocol.
• A proxy-based transcoding system that stores and
  reuses partial objects.
• Allows scalable image web delivery.
• Minimizes network bandwidth consumption and
  client latency.

13

• Part 2
• System Model and Architecture

14
System Requirements

• Content adaptation
• Minimal bandwidth consumption
• Real-time delivery

15
Design Considerations

• Proxy-based
• On-demand transcoding
• Streamed transcoding
• Small transcoding overhead
• Bandwidth optimization (Along entire path)
• Data reuse

16
Scalable Data Model

• Basic Terminology
• B Set of all data bits BLK Set of all blocks
• O Set of all data objects P Set of all
  presentations
• Definition 1 Bit Stream
• On Union(b1b2b3 bm-1bm) where On?O, and
  bi?B with i?0,m.
• Definition 2 Block
• blk(i, j) Union( bibi1 bj-1bj )
• where blk(i,j)?BLK and bn?B with 0j.
• Definition 3 Presentation
• Bit expression
• Pi f (b1b2b3 bi1bi )
• where bi ? B, i? size of original object, and f
  represents the encoding function.
• Block Expression
• Pi f (blk(1,I1) blk(I11, I2) blk(I21, I3)
  blk(Ik1, i))
• where 0the encoding function.

17
Scalable Data Model

• Basic Properties
• Property 1 Inclusive Property
• Pj F (Pi , blk(i1, j))
• where i
• and F denotes the encoding function that generate
  Pi by using Pi and blk(i1, j)
• Property 2 Union Function F
• The encoding function F should be union function.

18
Scalable Data Model

• Property 3 Single Pass Property
• According to inclusive property, we have
• Pi F (Pi-1 , blk(i, i) ) or
• Pi F (Pi-1 , bi )
• Similarly,
• Pi-1 F (Pi-2 , bi-1 )
• Pi-2 F (Pi-3 , bi-2 )
• P2 F (P1 , b2 )
• P1 F (b1 )

19
Scalable Data Model

• Transcoding Operations
• Suppose we want to transform between a lower
  quality presentation Pi
• and a higher presentation Pj. Based on our data
  model, the following
• equation holds Pj Union (Pi , blk(i1, j))
• Conversion from higher quality to lower quality
• To transform Pj into Pi, simply discard the data
  bits ranging from bit (i1)
• to bit j.
• Conversion from lower quality to higher quality
• To transform Pi into Pj, we only need to retrieve
  the data bits ranging from
• i1 to j, and then append them to presentation Pi.

20
Scalable Data Model

• Impact on Image Transcoding
• Allows reuse of partial objects
• Allows streamed transcoding
• Incurs minimal transcoding overhead
• Transcoding Computation Instead Block Synthesis

21
System Architecture
Clients Request
ProxyCache
Servers Reply
22
Proxy Cache

• Caching partial objects
• Introducing the notion of partial hit
• Cache hit
• Cache miss
• Partial hit
• Enforcing single range
• Multiple ranges are not allowed.
• The cached content must start with the first data
  bit.

23
Example Cache Miss
Client 1
Req 1-100KB
Client 2
1-50KB
Proxy
Req 1-100KB
Client 3
Image X 400KB
1-200KB
Client 4
24
Example Partial Hit 1
Client 1
1-100KB
Req 50KB-150KB
Client 2
1-150KB
1-50KB
Proxy
Client 3
1-100KB
1-150KB
Image X 400KB
1-200KB
Client 4
25
Example Partial Hit 2
Client 1
1-100KB
Client 2
1-150KB
Proxy
Req 1-100KB
Client 3
1-150KB
Image X 400KB
1-200KB
Client 4
26
Example Partial Hit 3
Client 1
1-100KB
Client 2
Req 150KB-300KB
1-150KB
Proxy
Req 200KB-300KB
1-100KB
Client 3
Image X 400KB
Client 4
27
Streaming and Pipelining
28
Example

• JPEG 2000 Scalability in image quality

2KB
4KB
8KB
32KB (original)
16KB
24KB
29
Model Analysis

• Proxy-based
• On-demand transcoding
• Streamed transcoding
• Small transcoding overhead
• Bandwidth optimization (both client server)
• Data reuse

30

• Part 3
• Related Work

31
Related Work

• Progressive Data Formats
• Interlaced GIF
• Progressive JPEG
• JPEG 2000
• MPEG-4

32
Related Work

• Transcoding Systems
• Mowser
• GloMop
• InfoPyramid
• Hybrid Transcoding System

33
Current Transcoding Systems

• Assumption
• The transcoding process cannot commence until
  the object has been downloaded in its entirety.
• Limitations
• Does not support scalable image web delivery.
• Can not cache or reuse partial objects.
• Store-and-forward transcoding break the
  pipeline of data bytes transferred across the
  network

34

• Part 6
• Conclusion

35
Contributions

• Scalable data model
• Proposed a general data model that allows reuse
  of partial objects.
• Identified inclusive property that enables
  scalable web delivery.
• The data model enables streamed transcoding and
  minimizes transcoding overhead.
• The data model applies to any multimedia type
  such as image, audio and video.

36
Contributions

• System Model
• Exploited the potential benefits of scalable data
  format and HTTP/1.1 protocol.
• Supports scalable web delivery with cumulative
  effect.
• Proposed the idea of caching and reusing partial
  objects.
• Introduced the concept of partial hit.
• Benefits content adaptation, minimal network
  bandwidth consumption and real-time delivery.

37

• Q A