ArchiveSpace Name Record
Publication Search Results
Now showing 1 - 5 of 5
ItemGeoCast: An Efficient Overlay System for Multicast Applications(Georgia Institute of Technology, 2009) Liu, Ling ; Pu, Calton ; Wang, Yuehua ; Zhang, GongIn this paper, we present GeoCast, a geographical location aware overlay network framework designed for providing efficient group communication services. GeoCast can be seen as an extension to the CAN network in the term of topology management and routing protocol. Geocast design has three important properties that attractive to group communication applications. First, it uses geographical mapping of nodes to regions to take advantage of the similarity between physical and network proximity. Second, a shortcut enabled geo-distance routing protocol is employed in GeoCast, which is more resilient than Chord-like or Pastry-like overlay networks due to the availability of multiple independent routing paths. Third and most importantly, a novel routing table management scheme is designed to allow the applications based on that have ability to manage their maintenance overhead in terms of network resource constrains.
ItemITR/SI: Guarding the next internet frontier: countering denial of information(Georgia Institute of Technology, 2008-12-19) Ahamad, Mustaque ; Omiecinski, Edward ; Pu, Calton ; Mark, Leo ; Liu, Ling
ItemReliable End System Multicasting with a Heterogeneous Overlay Network(Georgia Institute of Technology, 2004-05-03) Zhang, Jianjun ; Liu, Ling ; Pu, Calton ; Ammar, Mostafa H.This paper presents PeerCast, a reliable and self-configurable peer to peer system for End System Multicast (ESM). Our approach has three unique features compared with existing approaches to application-level multicast systems. First, we propose a capacity-aware overlay construction technique to balance the multicast load among peers with heterogeneous capabilities. Second, we utilize the landmark signature technique to cluster peer nodes of the ESM overlay network, aiming at exploiting the network proximity of end system nodes for efficient multicast group subscription and fast dissemination of information across wide area networks. Third and most importantly, we develop a dynamic passive replication scheme to provide reliable subscription and multicast dissemination of information in an environment of inherently unreliable peers. We also present an analytical model to discuss its fault tolerance properties, and report a set of initial experiments, showing the feasibility and the effectiveness of the proposed approach.
ItemDistributed Workflow Restructuring: An Experimental Study(Georgia Institute of Technology, 2002) Ruiz, Duncan Dubugras ; Liu, Ling ; Pu, CaltonWorkflow systems have been one of the enabling technologies for automation of business processes in corporate enterprises. Many modern production workflows need to incorporate deadline control throughout the workflow management system. However, the increasing volume and diversity of digital information available online and the unpredictable amount of network delays or server failures have led to a growing problem that conventional workflow management systems do not have, namely how to reorganize existing workflow activities in order to meet deadlines in the presence of unexpected delays. We refer to this problem as the workflow-restructuring problem. This paper describes the notation and issues of workflow restructuring, and discusses a set of workflow activity restructuring operators. We illustrate the inherent semantics of these restructuring operators using the Transactional Activity Model (TAM). The paper contains two main contributions. First, we study the environmental instabilities (e.g., resource shortages and network delays) that cause workflows to perform sub-optimally and how workflow restructuring can address this problem. Second, we evaluate the effectiveness of workflow-restructuring operators through simulation. Our initial experiments demonstrate that run-time workflow restructuring can improve response time significantly for unstable environments.
ItemOmini: A Fully Automated Object Extraction System for the World Wide Web(Georgia Institute of Technology, 2000) Buttler, David John ; Liu, Ling ; Pu, CaltonThis paper presents a fully automated object extraction system - Omini.A distinct feature of Omini is the suite of algorithms and the automatically learned information extraction rules for discovering and extracting objects from dynamic Web pages or static Web pages that contain multiple object instances. We evaluated the system using more than 2,000 Web pages over 40 sites. It achieves 100% precision (returns only correct objects) and excellent recall (between 93% and 98%, with very few significant objects left out). The object boundary identification algorithms are fast, about 0.1 second per page with a simple optimization.