Jason Bryant

Towards Mobile Data Streaming in Service Oriented Architecture

Service Oriented Architecture (SOA) is an architectural pattern providing agility to align technical solutions to modular business services that are decoupled from service consumers. Service capabilities such as interface options, quality of service (QoS), throughput, security and other constraints are described in the Service Level Agreement (SLA) that would typically be published in the service registry (UDDI) for use by consumers and/or mediation mechanisms. For mobile data streaming applications, problems arise when a service provider’s SLA attributes cannot be mapped one-to-one to the service consumers (i.e. 150MB/sec video stream service provider to 5MB/sec data consumer). In this paper we present a generic framework prototype for managing and disseminating streaming data within a SOA environment as an alternative to custom service implementations based upon specific consumers or data types. Based on this framework, we implemented a set of services: Stream Discovery Service, Stream Multiplexor / Demultiplexor(routing) Service, Stream Brokering Service, Stream Repository Service and Stream Filtering Service to demonstrate the flexibility of such a streaming data framework within SOA environment.

PAPaS : peer assisted publish and subscribe

The scalability of a content-based publish subscribe system typically depends on efficient subscription matching (brokering) and dissemination. As the number of subscribers increases, the matching and dissemination processes can increase bandwidth usage and overwhelm the server. Peer Assisted Publish and Subscribe (PAPaS) is a hybrid broker/P2P content-based publish and subscribe (pub/sub) system with varying event sizes. Publishers and subscribers share the burden through self-brokering and dissemination in P2P fashion. The practical implications inherent in combining pub/sub and P2P protocols are explored. Scalability analysis of the overall broker workloads and event distribution are demonstrated to show the benefits of PAPaS. Experimental results show that our approach is simple and highly effective at minimizing the brokering and event forwarding overhead as well as supporting the dynamicity of mobile clients in pub/sub middleware systems.

Enabling semantic technologies in publish and subscribe middleware

The Publish and Subscribe (pub/sub) dissemination paradigm has emerged as a popular means of disseminating time-sensitive or filtered information, usually in the form of middleware within the enterprise systems of Service-Oriented Architectures (SOA). Through the use of an event service, or broker, published information is disseminated only to the subscribers interested in that information. However, brokering semantically rich information, especially with resource constrained (e.g. limited memory, bandwidth, etc.) subscribers, has not yet been sufficiently explored. We present a service-oriented approach for enabling semantic technologies in pub/sub systems. We map the explicit client subscriptions to the semantic context of the published data, allowing implicit data to be disseminated to the subscriber while enforcing security policies across semantically related data. To illustrate, we show that semantic technologies not only enable semantically rich content sharing but contribute data reduction suitable for resource constrained clients and security policy enforcement capabilities.

A hybrid publish subscribe protocol

Content-based publish/subscribe system performance depends upon the efficient subscription matching and event dissemination to interested subscribers. We propose a hybrid content-based publish/subscribe protocol for large size events wherein a centralized brokering system is coupled with a decentralized BitTorrent-like peer-to-peer (P2P) protocol for scalable event distribution among publishers and subscribers. Events are mapped to a torrent that grows as new events are published. Subscribers self-broker on event metadata and request content only if interested. Subscriber interests determine event popularity that the broker estimates with sampling. Popular events are disseminated P2P; unpopular events, directly from the broker; and somewhat popular ones, with P2P and broker-directed pre-seeding. The challenge is the dissemination of popular events without overwhelming centralized resources while efficiently disseminating unpopular events that lack sufficient interest to sustain gossip-based dissemination. The key advances include new means of handling variable event popularity inherent in content-based pub/sub and an adaptive anti-entropy mechanism for undelivered events.

Semantic modeling of analytic-based relationships with Direct Qualification

Successfully modeling state and analytics-based semantic relationships of documents enhances thoroughness of representation, contextualization of importance and relevancy, posterity of provenance, and a delineation of priority for a document. These attributes are the core elements that form the machine-based knowledge representation for documents. However, modeling document relationships that can change over time can be inelegant, limited, complex or overly burdensome for semantic technologies. In this paper, we present Direct Qualification (DQ), an approach for modeling any semantically referenced document, concept, or named graph with results from associated applied analytics. The proposed approach supplements the traditional subject-object relationships by providing a third leg to the relationship; the qualification of how and why the relationship exists. To illustrate, we show a prototype of an event-based system with a realistic use case for applying DQ to relevancy analytics of PageRank and Hyperlink-Induced Topic Search (HITS).

PAPaS: peer-assisted publish and subscribe

The scalability of a content-based Publish and Subscribe (pub/sub) system typically depends on efficient subscription matching (brokering) and dissemination. As the number of subscribers increases, the matching and dissemination processes can increase bandwidth usage and overwhelm the server. Peer-Assisted Publish and Subscribe (PAPaS) is a hybrid broker/P2P content-based pub/sub system with varying event sizes. Publishers and subscribers share the burden through self-brokering and dissemination in a P2P fashion. The practical implications inherent in combining pub/sub and P2P protocols are explored. Scalability analysis of the overall broker workloads and event distribution are demonstrated to show the benefits of PAPaS. Experimental results show that our approach is simple and highly effective at minimising the brokering and event forwarding overhead as well as supporting the dynamicity of mobile clients in pub/sub middleware systems.