@inproceedings{9037d27e8f18494181d06c5051a2e1e5,
title = "Distributed SPARQL over Big RDF Data: A Comparative Analysis Using Presto and MapReduce",
abstract = "The processing of large volumes of RDF data require an efficient storage and query processing engine that can scale well with the volume of data. The initial attempts to address this issue focused on optimizing native RDF stores as well as conventional relational databases management systems. But as the volume of RDF data grew to exponential proportions, the limitations of these systems became apparent and researchers began to focus on using big data analysis tools, most notably Hadoop, to process RDF data. This paper presents a comparative analysis of performance of Presto (distributed SQL query engine) in processing big RDF data against Apache Hive. To evaluate the performance Presto for big RDF data processing, a map-reduce program and a compiler, based on Flex and Bison, were implemented. The map-reduce program loads RDF data into HDFS while the compiler translates SPARQL queries into a subset of SQL that Presto (and Hive) can understand.",
keywords = "Big Data processing, Database Performance, Evaluation, Querying, Semantic Web data",
author = "Mulugeta Mammo and Srividya Bansal",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 4th IEEE International Congress on Big Data, BigData Congress 2015 ; Conference date: 27-06-2015 Through 02-07-2015",
year = "2015",
month = aug,
day = "17",
doi = "10.1109/BigDataCongress.2015.15",
language = "English (US)",
series = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "33--40",
editor = "Latifur Khan and Carminati Barbara",
booktitle = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
}