PeNeLoop: Parallelizing Federated SPARQL Queries in Presence of Replicated Fragments

Thomas Minier, Gabriela Montoya, Hala Skaf-Molli, Pascal Molli

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

1 Citation (Scopus)
12 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationJoint 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
Number of pages14
Volume1870
PublisherCEUR Workshop Proceedings
Publication date2017
Pages37-50
Publication statusPublished - 2017
Event14th Extended Semantic Web Conference, ESWC 2017 - Portoroz, Slovenia
Duration: 28 May 20171 Jun 2017

Conference

Conference14th Extended Semantic Web Conference, ESWC 2017
Country/TerritorySlovenia
CityPortoroz
Period28/05/201701/06/2017
SponsorElsevier, IOS Press
SeriesCEUR Workshop Proceedings
Volume1870
ISSN1613-0073

Keywords

  • Federated SPARQL Query Processing
  • Fragment Replication
  • Linked Data
  • Parallel Query Processing

Fingerprint

Dive into the research topics of 'PeNeLoop: Parallelizing Federated SPARQL Queries in Presence of Replicated Fragments'. Together they form a unique fingerprint.

Cite this