Complex applications composed of many interconnected but functionally independent services or components are widely adopted and deployed on the cloud to exploit its elasticity. This allows the application to react to load changes by varying the amount of computational resources used. Deciding the proper scaling settings for a complex architecture is, however, a daunting task: many possible settings exists with big repercussions in terms of performance and cost. In this paper, we present a methodology that, by relying on modeling and automatic parameter configurators, allows to understand the best way to configure the scalability of the application to be deployed on the cloud. We exemplify the approach by using an existing service-oriented framework to dispatch car software updates.