Cloud computing plays a significant role to store and analyze the exponentially growing volume of generated data. However, cloud computing is inherently a frequent environment for failures and its services undergo long downtime periods. These failures threaten the user experience especially when we take into consideration that not only the currently generated data have a tremendous volume but also it presents new types and different generation velocities. Therefore, the aim of this paper is to propose a broker architecture, which ensures that behavioral requirements in terms of dependability properties are met by the provided cloud service at the infrastructure, platform and service levels. This architecture takes the decision to continue the service delivery with the same cloud provider or to migrate toward a new provider based on the evaluation of the fault severity impact. DBA takes into consideration the interdependence between the cloud service models and formalizes all dependability attributes with a single state-based stochastic model. Results demonstrate the introduced amelioration in terms of dependability properties compared to classic cloud service delivery. The main contribution concerns safety improvement by avoiding catastrophic failures.