Efficient distributed query processing for autonomous RDF databases

The inherent flexibility of the RDF data model has led to its notable adoption in many domains, especially in the area of life-sciences. Some of these domains have an emerging need to access data integrated from various distributed sources of information. It is not always possible to implement this by simply loading all data into one central RDF store. For example, in the context of inter-institutional collaboration for drug development and clinical research participants often want to maintain control over their local databases. Alternatively, distributed query processing techniques can be utilized to evaluate queries by accessing the remote data sources only on demand and in conformance with local authorization models. In this paper we present an efficient approach to distributed query processing for large autonomous RDF databases. The groundwork is laid by a comprehensive RDF-specific schema- and instance-level synopsis. We present an optimizer that is able to utilize this synopsis to generate compact execution plans by precisely determining, at compile-time, those sources that are relevant to a query. Furthermore we present a tightly integrated query engine that is able to further reduce the volume of intermediate results at run-time. An extensive evaluation shows that our approach improves query execution times by up to two and transferred data volumes by up to three orders of magnitude compared to a naïve implementation.