Optimal Index Selection Using Optimized Deep Q-Learning Algorithm for NoSQL Database

The resource requirements for managing the data for sophisticated applications have increased as big data technology has advanced. NoSQL (MongoDB) databases are being used increasingly frequently as a result of the desire for high-performance reading and writing. However, the performance of the data...

Full description

Saved in:
Bibliographic Details
Published in:SN computer science Vol. 5; no. 5; p. 504
Main Authors: Sumalatha, V., Pabboju, Suresh
Format: Journal Article
Language:English
Published: Singapore Springer Nature Singapore 01.06.2024
Springer Nature B.V
Subjects:
Adaptive algorithms
Algorithms
Big Data
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Deep learning
Indexing services
Information Systems and Communication Service
Linear programming
Machine learning
Original Research
Pattern Recognition and Graphics
Queries
Software Engineering/Programming and Operating Systems
Vision
Workloads
DQN
QPHH
MongoDB
ACOA
NoSQL
ISSN:2661-8907, 2662-995X, 2661-8907
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The resource requirements for managing the data for sophisticated applications have increased as big data technology has advanced. NoSQL (MongoDB) databases are being used increasingly frequently as a result of the desire for high-performance reading and writing. However, the performance of the database is degraded due to the number of queries in a certain time period. Thus to enhance the database performance, an automatic index selection scheme is presented in this paper. Namely, an optimized deep Q-learning network (DQN) is presented for optimal index selection. To enhance the decision making performance of DQN, an adaptive crocodile optimization algorithm (ACOA) is used. Using this algorithm, best action sequences of DQN are obtained. In terms of YCSB mongoDB, the suggested model's performance is assessed. The article's findings show that the suggested model achieves better average cost time (ACT), average time of query execution (ATQ) and query per hour (QPHH) and throughput.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-024-02863-9