Data replication and deployment of local SPARQL endpoints improve scalability and availability of public SPARQL endpoints, making the consumption of Linked Data a reality. This solution requires synchronization and specific query processing strategies to take advantage of replication. However, existing replication aware techniques in federations of SPARQL endpoints do not consider data dynamicity. We propose FEDRA, an approach for querying federations of endpoints that benefits from replication. Participants in FEDRA federations can copy fragments of data from several datasets, and describe them using provenance and views. These descriptions enable FEDRA to reduce the number of selected endpoints while satisfying user divergence requirements. Experiments on real-world datasets suggest savings of up to three orders of magnitude.
