Publications (5)2.21 Total impact
- [Show abstract] [Hide abstract]
ABSTRACT: Publish/subscribe systems offer a loosely coupled communication paradigm in distributed information systems. However, supporting expression of semantic events, expression of logical and temporal patterns of composite events, and how to manage and route composite events and subscriptions still need further research. In this paper, we present the design and implementation of JTang composite and semantic publish/subscribe system over structured P2P networks, and highlight its novel features, including semantic broker network, composite event and subscription language and distributed composite subscription management. The experiments based on the Peersim simulator over the Pastry overlays show that the ontology routing table helps decrease the average number of hops and the use of composite subscriptions significantly reduces the load on the network.
Conference Paper: Parallel Matching Algorithms of Publish/Subscribe System.[Show abstract] [Hide abstract]
ABSTRACT: Publish/subscribe systems form an important communication paradigms in distributed systems. However, how to leverage current chip multi-processors to increase throughput and reduce the matching time still need further research. In this paper, we present and implement two types of parallel matching algorithms. Experiments show that relatively independent matching algorithm produces similar throughput as complete independent matching algorithm and the average matching time of collaborative matching algorithm is reduced by approximately 77% as the number of threads increases from one to six.
- [Show abstract] [Hide abstract]
ABSTRACT: Publish/subscribe systems have been adopted by many distributed applications to deliver data from publishers to subscribers in an anonymous fashion. However, existing content-based publish/subscribe systems suffer from limitations in scalability. This paper introduces a novel architecture for implementing a content-based publish/subscribe system, called JTangPS, on top of structured P2P networks. JTangPS achieves scalability by mapping subscriptions and events to rendezvous nodes in terms of the combination of domain schema identifier, number of attributes and the first attribute name in the subscription or event. JTangPS enhances routing efficiency by exploiting the embedded multicast tree on P2P networks and by aggregating event delivery messages. Experimental results using a variety of synthesis datasets demonstrate the scalability of system with large numbers of users.
Conference Paper: Exploring a Semantic Publish/Subscribe Middleware for Event-Based SOA[Show abstract] [Hide abstract]
ABSTRACT: Service Oriented Architecture is currently regarded as the next step for software architectures and achieve great usage in web services. However, the traditional SOA uses request/response pattern and is not suit for loose coupling, asynchronous scene while Even-Driven Architecture works well. To support the effective execution of possibly distributed and completely decoupled and heterogeneous services, synchronously or asynchronously executed in an efficient manner, there is an urgent need to integrate EDA and SOA into the next generation of SOA. We propose a semantic publish/subscribe system called JTangPS to serve as the event platform for event based SOA to satisfy the new challenges.
Conference Paper: An RDF-Based Publish/Subscribe System[Show abstract] [Hide abstract]
ABSTRACT: Publish/subscribe is a promising paradigm with a growing appeal in building large-scale distributed applications. Existing publish/subscribe systems have limited support for semantic information. In this paper, we propose JTangPS (JTang Publish/subscribe System), an RDF (Resource Description Framework) based publish/subscribe system which uses RDF graphs to describe events and RDF graph patterns to represent subscriptions. A fast graph-based matching algorithm is presented to reconcile the conflict of expressiveness and scalability. Experimental results using synthetic workload demonstrate the scalability of system with large numbers of subscriptions.
Hang-hsien, Zhejiang Sheng, China
- College of Computer Science and Technology