Organizations are nowadays more and more adopting Cloud computing to execute their multi-tenant business processes in order to quickly adapt to changes of requirements at lower costs. In such environment, using configurable process models allows for various tenants to share a reference process which can be customized depending on their needs. However, there is a lack of support for cloud-specific resource configuration with considering quality of service requirements. In this paper, we cope with this gap by proposing a genetic-based approach that enables to optimally extract cloud resource configuration allocation w.r.t Cloud resource features (i.e., elasticity and shareability), and process non functional properties (i.e. QoS properties)