Combining reputation and QoS measures to improve cloud service composition

In order to provide a wide range of composite Cloud services, providers need to establish mutual agreements on large-scale distributed multi-cloud scenario. In such a way, providers can compose effective and efficient service workflows by taking resources of their own competitors and gain the capability to satisfy unexpected workload peaks. In this paper, we propose a reputation-based model capable to support the composition of complex Cloud services by taking into account both costs and measures of QoS which are collected by measuring both system measures and reputation feedbacks provided by the customers. The proposed model has been validated by a set of experimental results obtained by means of a number of simulations.