Data Distribution for Processing Spatial Multijoins Using the Gain-Loss Method
Abstract: This study analyzes the efficiency of the Gain-Loss (GL) method for spatial data distribution in distributed systems, utilizing the DGEO system. The problem lies in the complexity and high processing costs associated with multiway spatial join queries over large volumes of spatial data, highlighting the need for computer clusters. In this context, the objective was to investigate the efficiency of GL compared to the Round-Robin (RR) method, considering execution time and network consumption in a distributed system with real datasets. The methodology involved executing seven spatial queries on a cluster with four virtual machines, using real datasets and three different scheduling methods. The results showed that GL outperformed RR in query execution time but exhibited inferior performance in terms of network traffic, still facing challenges in query optimization.
Keywords: Multiway Spatial Join; Distributed systems; Data Distribuition; Gain-Loss.
Complete monograph. Copyright © 2024. All rights reserved.
Disclaimer: Although the student carefully wrote the original abstract, and it was revised and improved, English is not him or the advisor' mother language. The original work is written in Portuguese.
Citation: Ahmed Subhi Sousa. Distribuição de dados para processamento de multijunções espaciais usando o método Gain-Loss. Monografia. Bacharelado em Ciência da Computação. Universidade Federal de Jataí. Jataí, GO, Brasil. 2024. 42p.
Copy citation in bibtex format.