Development of multiple big data analysis platforms for business intelligence
Autor: | Chang, Bao Rong, Wang, Yo-Ai, Lee, Yun-Da, Huang, Chien-Feng |
---|---|
Rok vydání: | 2017 |
Předmět: |
Job scheduler
Computer science business.industry Distributed computing Big data 020206 networking & telecommunications Cloud computing 02 engineering and technology computer.software_genre Execution time Scheduling (computing) Data retrieval 020204 information systems Business intelligence 0202 electrical engineering electronic engineering information engineering Algorithm design Data mining business computer |
DOI: | 10.1109/icasi.2017.7988329 |
Popis: | This paper introduced the new approaches to big data platform, RHadoop and SparkR, and integrated them to form a high-performance big data analysis with multiple platforms as part of business intelligence (BI) to carry out rapid data retrieval and analysis with R programming. This paper aims to develop the optimization for job scheduling using MSHEFT algorithm and implement the optimized platform selection based on computing features for improving the system throughput significantly. As a result, although the optimized platform selection can reduce the execution time for the data retrieval and analysis significantly, furthermore scheduling optimization definitely increases the system efficiency a lot. |
Databáze: | OpenAIRE |
Externí odkaz: |