[7-8]On Distributed Resource Sharing
Date:2008-07-03
Title: On Distributed Resource Sharing
Speaker: Yong Meng TEO
（Department of Computer Science National University of Singapore）
e-mail: teoym@comp.nus.edu.sg; http:// www.comp.nus.edu.sg/~teoym
Time: 10：00-11：30 am, July 8
Venue: Room337, Building #5
Abstract:
In recent years, we have seen an increasing number of Internet-scale applications that focuses on resource sharing. The infrastructure and technologies that these applications leverage are peer-to-peer, grid, web services, among others. Major research challenges arise due to the increased complexity of large decentralized organisation, dynamism of the operating environments and its scale. This talk covers an overview of ongoing research in selected aspects of resource sharing. On computational cycle sharing, we discuss ALiCE (Adaptive and scalable internet-based Computing Engine), a lightweight Java-based grid middleware. On infrastructure for resource sharing, we discuss a new read-only DHT (Distributed Hash Tables) technique for resource discovery, and DiRAM, a market-based approach to resource pricing and allocation. On software components sharing, we discuss CODES (Composable Discrete-Event Simulation), a framework for composable modelling and simulation. Lastly, on network bandwidth sharing, we discuss TFTTP (Tit-for-Tag Transfer Protocol), a technique for high-bandwidth peer-to-peer data transfers with the right incentives.
Biography
TEO Yong Meng is an Associate Professor with the Department of Computer Science at the National University of Singapore, and an Associate Senior Scientist at Sun Microsystems Asia-Pacific Science and Technology Centre. He was a Fellow of the Singapore-Massachusetts Institute of Technology Alliance from 2002-2006. He received his Master and PhD in Computer Science from the University of Manchester, UK, in 1987 and 1989. He currently heads the Computer Systems Research Laboratory and the Information Technology Unit. His main research interest is in parallel and distributed computing, parallel simulation and performance analysis. Current projects include selfstabilization in large distributed systems, fault-tolerant consensus in distributed systems and performance analysis of petascale systems.