• Version
• Download 2
• File Size 515.99 KB
• Download

AI-Augmented Database Indexing for High-Performance Query Optimization

 

 

Authors:

Ritesh Kumar
Independent Researcher
Pennsylvania, USA
ritesh2901@gmail.com

Abstract—Database indexing plays a crucial role in optimizing query performance, particularly in cloud-native and high-performance computing environments. Traditional indexing techniques often struggle to adapt dynamically to varying workloads, leading to suboptimal query execution times and increased computational overhead. This paper presents an AI-augmented approach to database indexing that leverages reinforcement learning-based adaptive indexing and machine learning-driven query optimization. By integrating AI models into indexing strategies, databases can dynamically adjust index structures, predict query access patterns, and optimize execution plans in real time. The proposed framework is evaluated using PostgreSQL, DocumentDB, and GraphDB, demonstrating significant improvements in query execution speed, resource utilization, and overall system efficiency. The paper also discusses the architectural considerations for deploying AI-augmented indexing in distributed database systems and explores its impact on read-heavy and write-intensive workloads. Experimental results highlight significant performance gains achieved through AI-driven indexing, paving the way for more intelligent and adaptive database systems.

Keywords— AI-driven indexing, database optimization, adaptive indexing, reinforcement learning, query performance, PostgreSQL, DocumentDB, GraphDB, machine learning, cloud databases, high-performance computing