Autonomic management of workflows on hybrid grid-cloud infrastructure

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