Abstract: Data distribution is a challenge in the distributed execution of multiway spatial join queries. An efficient execution requires both a balanced data distribution as well as a distribution with spatial data colocalization. In this paper, we compare two methods of spatial data distribution and propose a new one called Gain-Loss, based in the R0-tree algorithms. Our evaluation shows that Gain-Loss has a reduced area overlay between servers in all tested scenarios and also a competitive object balancing. This result indicates a more efficient execution of queries, with a reduction in the use of computational resources, mainly network usage and processing time.

Keywords: Data Distribution; Multiway Spatial Join; R0-Tree; Gain-Loss.

Download paper

Citation: Guilherme Silva Tonon; Thiago Borges de Oliveira. Gain-Loss: Método de Distribuição de Dados para Processamento Distribuído de Multijunções Espaciais. In: Proceedings of XX Geoinfo, São José dos Campos, SP, Brasil, 2019, pp. 274--279.

Copy citation in bibtex format.