Autonomic management of workflows on hybrid Grid-Cloud infrastructure

Grids can be considered as dominant platforms for large-scale parallel/distributed computing in science and engineering. Clouds allow users to acquire and release resources on-demand. Next generation computing environments will benefit from the combination of Grid and Cloud paradigms providing frameworks that integrate traditional Grid services with on-demand Cloud services. Nowadays, workflows are the preferred means for the combination of services into added value service chains representing functional business processes or complex scientific experiments. A promising way to manage effectively services composition in a dynamic and heterogenous environment is to make the workflow management framework able to self-adapt at runtime to changes in its environment and provide an uniform resource access mechanism over Grid and Cloud infrastructures. Autonomic workflow management systems can support the runtime modification of workflows with the aim of improving their performance and recover from faults determining and provisioning the appropriate mix of Grid/Cloud services with requested QoS. This paper describes Sunflower an innovative P2P agent-based framework for configuring, enacting, managing and adapting workflows on hybrid Grid-Cloud infrastructures. To orchestrate Grid and Cloud services, Sunflower uses a bio-inspired autonomic choreography model and integrates the scheduling algorithm with a provisioning component that can dynamically launch virtual machines in a Cloud infrastructure to provide on-demand services in peak-load situations.