@inproceedings{766de20a6baa40c197e0cdc429b79934,
title = "Scalable Query Optimization for Efficient Data Processing Using MapReduce",
abstract = "MapReduce is widely acknowledged by both industry and academia as an effective programming model for query processing on big data. It is crucial to design an optimizer which finds the most efficient way to execute an SQL query using MapReduce. However, existing work in parallel query processing either falls short of optimizing an SQL query using MapReduce or the time complexity of the optimizer it uses is exponential. Also, industry solutions such as HIVE, and YSmart do not optimize the join sequence of an SQL query and cannot guarantee an optimal execution plan. In this paper, we propose a scalable optimizer for SQL queries using MapReduce, named SOSQL. Experiments performed on Google Cloud Platform confirmed the scalability and efficiency of SOSQL over existing work.",
keywords = "Big data, Google, Industries, Optimization, Partitioning algorithms, Query processing, Time complexity",
author = "Yi Shan and Yi Chen",
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.2015.100",
language = "English (US)",
series = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "649--652",
editor = "Latifur Khan and Carminati Barbara",
booktitle = "Proceedings - 2015 IEEE International Congress on Big Data, BigData Congress 2015",
address = "United States",
}