A Novel Domain Oriented Approach for Scientific Grid Workflow Composition

Abstract—Existing knowledge based Grid workflow languages and composition tools require sophisticated expertise of domain scientists in order to automate the process of managing work-flows and its components (activities). So far semantic workflow specification and management has not been addressed from a general and integrated perspective. This paper presents a novel domain oriented approach which features separations of concerns between data meaning and data representation and between activity function (semantic description of workflow activities) and activity type (syntactic description of workflow activities). These separations are implemented as part of Abstract Grid Workflow Language (AGWL) which supports the development of Grid workflows at a high level (semantic) of abstraction. The corresponding workflow composition tool simplifies Grid workflow composition by (i) enabling users to compose Grid workflows at the level of data meaning and activity function that shields the complexity of the Grid, any specific implementation technology (e.g. Web or Grid service) and any specific data representation, (ii) semi-automatic data flow composition, and (iii) automatic data conversions. We have implemented our approach as part of the ASKALON Grid application development and computing environment. We demonstrate the effectiveness of our approach by applying it to a real world meteorology workflow application and report some preliminary results. Our approach can also be adapted to other scientific domains by developing the corresponding ontologies for those domains. I