Cloud computing paradigm has become the solution to provide good service quality and exploit economies of scale. However, the management of such elastic resources, with different Quality-of-Service (QoS) combined with on-demand self-service, is a complex issue. This paper proposes an approach driven by Service Level Agreement (SLA) for optimizing the capacity planning for Cloud applications. The main challenge for a service provider is to determine the best trade-off between profit and customer satisfaction. In order to address this issue, we follow a queueing network proposal and present an analytical performance model to predict Cloud service performance. Based on a utility function and a capacity planning method, our solution calculates the optimal configuration. We rely on autonomic computing to adjust continuously the configuration. Simulation experiments indicate that our model i) faithfully captures the performance of Cloud applications for a number of workloads and configurations and ii) successfully keeps the best trade-off.