A novel architecture for realizing grid workflow using tuple spaces

Grid workflow can be defined as the composition of grid application services which execute on heterogeneous and distributed resources in a well-defined order to accomplish a specific goal. Uncertainties within grid environments pose new challenges for grid workflow management systems such as lacking central control and undedicated resource sharing. In this paper, we provide a workflow enactment engine together with an XML-based workflow language (xWFL). The workflow engine supports a just in-time scheduling system, thus allowing the resource allocation decision to be made at the time of task execution and hence adapt to changing grid environments. We also show that an event-driven scheduling architecture using tuple spaces provides a highly flexible approach for executing large scale complex grid workflows.