Methodology: Automatic Database Index Tuning Using Machine Learning

Methodology: Automatic Database Index Tuning Using Machine Learning

Index plays a crucial role in determining the query response time and enables fast data access. The Automatic index-tuning model using Machine Learning (ML) increases the index's adaptability to variable workloads by including the column's future usage, column properties, and query operati...

Full description

Saved in:
Bibliographic Details
Published in:2021 IEEE International Conference on Intelligent Systems, Smart and Green Technologies (ICISSGT) pp. 109 - 113
Main Authors: Valavala, Mounicasri, Alhamdani, Wasim
Format: Conference Proceeding
Language:English
Published: IEEE 01-11-2021
Subjects:
Adaptation models
Analytical models
Data collection
execution history
index tuning
Indexes
Machine learning
Time factors
workload forecast
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Index plays a crucial role in determining the query response time and enables fast data access. The Automatic index-tuning model using Machine Learning (ML) increases the index's adaptability to variable workloads by including the column's future usage, column properties, and query operations. The paper presents the methodology to create an automated model for index selection and is part of the Automatic Database Index Tuning series. Selecting the index using ML is the first of its kind. As a result, there is no available dataset. Hence, the research finalizes the features influencing index selection by interviewing the database professionals and data collection by analyzing the existing indexes. The paper will cover the data collection methods, data analysis, and implementation details of the model.
DOI:10.1109/ICISSGT52025.2021.00033