Description
In this project, we mainly focus on two parts:
To discover in-band streaming services in P2P overlays. We describe and evaluate a new service indexing mechanism for in-band streaming services such as application relays, mixers, and media transcoders. For this type of service, the location of the service in the network and service admission status are key attributes. We describe and analyze a service indexing mechanism which uses network position-based advertisement. We show that this mechanism gives good service selection, provides a close to uniform advertisement distribution in the overlay, reduces message overhead, and exhibits acceptable stability and setup delay.
To investigate the location-aware relay discovery and selection problem for large-scale P2P streaming networks. In these large-scale and dynamic overlays, it incurs significant communication and computation cost to discover a sufficiently large relay candidate set and further to select one relay with good performance. The network location can be measured directly or indirectly with the tradeoffs between timeliness, overhead and accuracy. We demonstrate that indirect measurements can only achieve a coarse estimation of peers' network location, and the methods based on pure indirect measurement cannot lead to a good relay selection. Howerver, a simple two-phase approach can achieve efficient relay discovery and accurate relay selection.
Experiment
We mainly perform following experiment:
Measuring round trip time (RTT) between pairs of end hosts
Evaluating service indexing mechanism
Comparing different relay selection techniques
Main tools
RTT measurement: RttOmeter, King, Internet Coordinate System (ICS) such as Vivaldi, Meridian, etc.
Data collection and process: Apache Tomcat, MySQL, PlatnetLab
Programming language: Java, C/C++, SQL
Publications
John Buford, Angela Wang, Xiaojun Hei, Yong Liu and Keith W. Ross, "Discovery of In-Band Streaming Services in Peer-to-Peer Overlays", GLOBECOM07, Washington, D.C., USA, Nov. 2007
Related links