Applied Intelligence and Computing
Analysis of Machine Learning Techniques for Database Optimization
Authors: Darshit Amit Pandya
Publishing Date: 08-11-2024
ISBN: 978-81-955020-9-7
Abstract
This study discusses the available database optimization techniques to overcome the limitations of the traditional (empirical) database optimization techniques by analyzing and leveraging the machine learning techniques to meet the high performance demands and diverse workloads of today’s world, by exploring and analyzing several categories of possible improvements, including query optimization, optimizing indexing strategies, reducing resource utilization, optimizing entity matching, and enhancing cardinality estimation. Through this technical overview, the survey aims to provide a more comprehensive understanding of the advancements and complexities in leveraging machine learning for enhancing database performance and efficiency. This study also explores the limitations and uncovered areas of the existing SOTA, and further explores the recent advancements and novel approaches proposed in the domain of intelligent database optimization, and how they overcome the limitations of SOTA techniques. Finally, certain problem statements are deduced and listed to guide future research in the domain of intelligent database optimization.
Keywords
Machine Learning, Deep Learning, Databases, Optimization, SQL
Cite as
Darshit Amit Pandya, "Analysis of Machine Learning Techniques for Database Optimization", In: Mukesh Saraswat and Rajani Kumari (eds), Applied Intelligence and Computing, SCRS, India, 2024, pp. 73-80. https://doi.org/10.56155/978-81-955020-9-7-9