Distributed execution of workflow

Abstract

Grid computing is a fundamental technology for large scale distributed resource sharing. Workflow management is becoming one of the most important Grid services. A lot of research work has been done on different issues involved in workflow management systems. The focus of this project is on three areas: workflow partitioning, enactment and data movement. The main reasons which led us to this selection are: (i) there is few existing work on partitioning workflow, specially as a means of accelerating workflow execution; (ii) several systems have been developed using three main enactment models (i.e., centralized, hierarchical, and distributed models), but most of them focus on centralized execution control while the existing hierarchical and distributed models still have problems such as high overhead in communication amongst the distributed parties; and (iii) data movement mechanisms are divided into: centralized, mediated, and peer-to-peer models. A good combination of the three mentioned categories (partitioning, enactment, and data movement) with the purpose of reducing workflow make-span (MS) became a motivation to propose our system.