Next-generation query optimization: AI-powered query engines

Saha, Sayantan (2025) Next-generation query optimization: AI-powered query engines. World Journal of Advanced Engineering Technology and Sciences, 15 (1). pp. 472-485. ISSN 2582-8266

AI-powered query optimization represents an emerging paradigm that addresses fundamental limitations in traditional database management systems. By leveraging machine learning techniques, these next-generation query engines can dynamically adapt to evolving data patterns, workload characteristics, and user behaviors. Unlike conventional optimizers that rely on static models and simplified assumptions, AI-driven approaches continuously learn from query execution feedback to improve performance. From workload-aware optimization and adaptive execution to intelligent data management and natural language interfaces, these systems demonstrate significant potential across various aspects of query processing. While implementation challenges exist around training data requirements, explainability, and system integration, ongoing research in end-to-end learned optimizers, federated query intelligence, hardware-aware optimization, and personalized query processing points to a future where database systems become increasingly self-optimizing and context-aware.