Automating Workflow for Data Processing in Grid Architecture.
Zhichun Xiao, Craig W. Thompson, Wing Li · IKE · 2006
Workflows are at the heart of data processing solutions. Because of the poor performance and the license cost, traditional relational database management systems are no longer good choices for processing huge amount of data. Nowadays many data processing companies turn to the workflow grid to process huge amount of data. Currently, the generation of workflow is made by human being, which is very tedious, labor intensive, and error prone, and hence becomes the bottleneck of the performance of data processing in the grid architecture. This paper proposes a workflow automation strategy that can replace the human being by a workflow generator that can automatically generate a workflow from given input. A prototype has been implemented and a simulation has been designed.