Workflow technology undoubtedly has been one of the most important domains of interest over the past decades, from both research and practice perspectives. However, problems such as potential poor performance, lack of reliability, limited scalability, insufficient user support, and unsatisfactory system openness are largely ignored. This research reveals that these problems are mainly caused by the mismatch between application nature, i.e., distributed, and system design, i.e., centralized management. Therefore, conventional approaches based on the client-server architecture have not addressed them properly so far. The authors abandon the dominating client-server architecture in supporting workflow because of its inherent limitations. Instead, the peer-to-peer infrastructure is used to provide genuinely decentralized workflow support, which removes the centralized data repository and control engine from the system. Consequently, both data and control are distributed so that workflow functions are fulfilled through the direct communication and coordination among the relevant peers. With the support of this approach, performance bottlenecks are likely to be eliminated while increased resilience to failure, enhanced scalability, and better user support are likely to be achieved. Moreover, this approach also provides a more open framework for service-oriented workflow over the Internet. This paper presents the authors' innovative decentralized workflow system design. The paper also covers the corresponding mechanisms for system functions and the Swinburne Decentralized Workflow prototype, which implements and demonstrates this design and functions.
Available at: http://works.bepress.com/jyan/34/