| EPSRC Reference: |
EP/F000936/1 |
| Title: |
Optimizing Peer-to-Peer Aggregation Performance Through Overlay Adaptation |
| Principal Investigator: |
Jarvis, Professor S |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
University of Warwick |
| Scheme: |
Standard Research |
| Starts: |
01 October 2007 |
Ends: |
30 September 2008 |
Value (£): |
73,951
|
| EPSRC Research Topic Classifications: |
| Networks & Distributed Systems |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Peer-to-peer networks are characterised by the computing power and bandwidth of their many participants, and contrast with alternative computing models based on a comparatively small number of servers. Peer-to-peer networks are formed by connections between participating nodes, collectively known as the 'peer-to-peer overlay'; often termed the 'virtual overlay' to differentiate it from the actual physical connections present in the underlying supporting networking infrastructure.This proposal is concerned with identifying and analysing general methods for automatically rearranging peer-to-peer overlay networks. Adaptation in peer-to-peer overlay networks is usually based on some external criteria, such as maintaining a directory structure according to a pre-defined name space. The most effective network structure for such systems, however, can to a large extent depend on what tasks are currently being executed. This project will examine if, and how, peer-to-peer networks can be adapted to maintain optimal performance as the tasks performed by the peers change. More specifically, this project aims to identify promising peer-to-peer overlay topologies to which a system can adapt in order to optimize the performance of pivotal information aggregation tasks, and to design and test one or more algorithms that demonstrate how such adaptation can be achieved. The project benefits from two distinguished research partners - the Commonwealth Scientific and Industrial Research Organization (CSIRO) ICT Center in Australia and the Vrije Universiteit Amsterdam. These partners will provide supporting application environments (for distributed energy resource management, peer-to-peer photo-sharing and grid resource management) in which this research can be validated, refined and, ultimately, applied. Industry analysts report that peer-to-peer continues to be the single largest consumer of data on ISP networks, and that peer-to-peer outstrips every other content distribution protocol on the Internet in terms of data traffic. Peer-to-peer networks also represent some of the fastest growing application areas in the industry. Fundamental research in this area, coupled with partners with whom this research can be directly applied, has the potential to offer significant benefits to the community at large.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.warwick.ac.uk |