Integration of cloud-based services into distributed workflow systems: challenges and solutions

Abstract

The paper introduces the challenges in modern workflow management in distributed environments spanning multiple cluster, grid and cloud systems. Recent developments in cloud computing infrastructures are presented and are referring how clouds can be incorporated into distributed workflow management, aside from local and grid systems considered so far. Several challenges concerning workflow definition, optimisation and execution are considered. These range from configuration, integration of business and scientific services, data management, dynamic monitoring and tracking, reusable workflow patterns, semantic search and distributed execution of distributed services. Finally, the author recommends a solution to these challenges based on the BeesyCluster middleware for distributed management of services with static and dynamic rescheduling within a market of services.