Parallel Spatial Join Aggregation with Two Combine Stages in Map-Reduce Framework

DOI

10.2991/jimec-16.2016.18How to use a DOI?

Keywords

Spatial join aggregation, Map-Combine-Reduce, Cloud computing

Abstract

Current analysis show that Map-Reduce cannot directly support spatial join operations with secondary reduction features efficiently. This paper proposes a Map-Reduce based parallel strategy-- -Map-Combine-Reduce (MCR)---to treat the join aggregation of large-scale spatial data. MCR takes advantage of combine stage in Map-Reduce model to integrate the partial aggregation results distributed at various maperp and reducers. Filter optimization was proposed to facilitate single-allocation issues of spatial objects in division of parallel tasks to further improve the efficiency of join aggregation querying. Experimental results have proven its efficiency, effectiveness, and simplification during processing spatial join aggregation query.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Chuang Yao
AU  - Luo Chen
AU  - JinXin Shen
PY  - 2016/10
DA  - 2016/10
TI  - Parallel Spatial Join Aggregation with Two Combine Stages in Map-Reduce Framework
BT  - Proceedings of the 2016 Joint International Information Technology, Mechanical and Electronic Engineering
PB  - Atlantis Press
SP  - 103
EP  - 109
SN  - 2352-5401
UR  - https://doi.org/10.2991/jimec-16.2016.18
DO  - 10.2991/jimec-16.2016.18
ID  - Yao2016/10
ER  -