Agent-based QoS negotiation in data-centric clouds

Agent-level negotiations between an application and a cloud service provider (SP) need to consider two complexities: i) inaccuracy of computational models in capturing the behavior of a cloud-based system made up of diverse components and resources; and ii) disparity in the goals and priorities of an application and the SP in exercising a cloud-based system. The paper suggests the use of trial actions by an agent to learn about the system behavior and the opponent agent goals, as part of effective negotiation strategy. A larger goal of optimal QoS control can be achieved with trial actions that are aided by a computational model of the cloud-based system. A study of replicated data service on a cloud is also described.