@inproceedings{585d47beb04f4a279f9029628903136e,
title = "PeNeLoop: Parallelizing Federated SPARQL Queries in Presence of Replicated Fragments",
abstract = "Replicating data fragments in Linked Data improves data availability and performances of federated query engines. Existing replication aware federated query engines mainly focus on source selection and query decomposition in order to prune redundant sources and reduce intermediate results thanks to data locality. In this paper, we extend replication-aware federated query engines with a replication-aware parallel join operator: PeNeLoop. PeNeLoop exploits redundant sources to parallelize the join operator and reduce execution time. We implemented PeNeLoop in the federated query engine FedX with the replicated-aware source selection Fedra and we empirically evaluated the performance of FedX + Fedra + PeNeLoop. Experimental results suggest that FedX + Fedra + PeNeLoop outperforms FedX + Fedra in terms of execution time while preserving answer completeness.",
keywords = "Federated SPARQL Query Processing, Fragment Replication, Linked Data, Parallel Query Processing",
author = "Thomas Minier and Gabriela Montoya and Hala Skaf-Molli and Pascal Molli",
year = "2017",
language = "English",
volume = "1870",
series = "CEUR Workshop Proceedings",
publisher = "CEUR Workshop Proceedings",
pages = "37--50",
booktitle = "Joint Proceedings of the 2nd RDF Stream Processing (RSP 2017) and the Querying the Web of Data (QuWeDa 2017) Workshops co-located with 14th ESWC 2017 (ESWC 2017), Portoroz, Slovenia, May 28th - to - 29th, 2017",
note = "14th Extended Semantic Web Conference, ESWC 2017 ; Conference date: 28-05-2017 Through 01-06-2017",
}