Next generation large-scale distributed systems – such as smart cities – are dynamic, heterogeneous and multi-domain in nature. The same is true for applications hosted on these systems. Application heterogeneity stems from their Unit of Composition (UoC); some applications might be coarse-grained and composed from processes or actors, whereas others might be fine-grained and composed from software components. Software components can further amplify heterogeneity since there exists different component models for different domains. Lifecycle management of such distributed, heterogeneous applications is a considerable challenge.

In this paper, we solve this problem by reasoning about these systems as a Software Product Line (SPL) where individual dimensions of heterogeneity can be considered as product variants. To enable such reasoning, first, we present UMRELA (Universal feature-Model for distRibutEd appLicAtions), a conceptual feature model that identifies commonalities and variability points for capturing and representing distributed applications and their target system. This results in a product line of a family of distributed applications. UMRELA facilitates representation of initial configuration point, and the configuration space of the system. The latter represents all possible states the system can reach and is used as an implicit encoding to calculate new configuration points at runtime. Second, we present a prototype Application Management Framework (AMF) as a proof of concept configuration management tool that uses UMRELA to manage heterogeneous distributed applications.