Document Type
Thesis - Open Access
Award Date
2017
Degree Name
Master of Science (MS)
Department / School
Electrical Engineering and Computer Science
First Advisor
Yi Liu
Abstract
The continuous growth of data volume in various fields such as, healthcare, sciences, economics, and business has caused an overwhelming flow of data in the last decade. The overwhelming flow of data has raised challenges in processing, analyzing, and storing data, which lead many systems to face an issue in performance. Poor performance of systems creates negative impact such as delays, unprocessed data, and increasing response time. Processing huge amounts of data demands a powerful computational infrastructure to ensure that data processing and analysis success [7]. However, the architectures of these systems are not suitable to process that quantity of data. This calls for necessity to develop a methodology to improve the performance of systems handle massive amount of data. This thesis presents a novel dynamic scaling methodology to improve the performance of big data systems. The dynamic scaling methodology is developed to scale up the system based on the several aspects from the big data perspective. Moreover, these aspects are used by the helper project algorithm which is designed to divide a task into small chunks to be processed by the system. These small chunks run on several virtual machines to work in parallel to enhance the system’s runtime performance. In addition, the dynamic scaling methodology does not require many modifications on the applied, which makes it easy to use. The dynamic scaling methodology improves the performance of the big data system significantly. As a result, it provides a solution for performance failures in systems that process huge amount of data. This is study would be beneficial to IT researches that focus on performance of big data systems.
Library of Congress Subject Headings
Big data.
Information storage and retrieval systems -- Scalability.
Description
Includes bibliographical references (pages 52-53)
Format
application/pdf
Number of Pages
65
Publisher
South Dakota State University
Recommended Citation
Alhamdawi, Nashmiah, "A Dynamic Scaling Methodology for Improving Performance of Big Data Systems" (2017). Electronic Theses and Dissertations. 2261.
https://openprairie.sdstate.edu/etd/2261
Included in
Data Storage Systems Commons, Digital Communications and Networking Commons, Electrical and Computer Engineering Commons
Rights Statement
