^PAPER_TITLE^

^AUTHOR_NAME^

International Journal of Computer Techniques

ISSN 2394-2231

DOI Registered

Volume 13, Issue 1 | Published: January – February 2026

Table of Contents

Author

Mohamed Chetouani

Abstract

This paper presents a comparative and experimental review of AI-assisted query optimization techniques in relational databases. The study examines traditional optimization methods, explores AI-based approaches including machine learning and reinforcement learning, and evaluates their effectiveness through experimental results.

Keywords

Query Optimization, Relational Databases, Artificial Intelligence, Machine Learning, Reinforcement Learning, Genetic Algorithms

Conclusion

AI-assisted query optimizers have demonstrated clear advantages over traditional cost-based and rule-based systems. By leveraging machine learning and deep learning models, these optimizers can significantly reduce cardinality and cost estimation errors, resulting in improved query execution performance across diverse workloads, including unseen queries and complex predicate structures. Models such as Neo and End-to-End illustrate the ability to generalize beyond the training data, dynamically adapting to changes in data distributions and query patterns—a capability that remains a key limitation of conventional systems. Despite these advancements, several challenges persist. Deep learning models often function as black boxes, making interpretability and debugging difficult. The integration of adaptive and online learning mechanisms introduces runtime overhead, which may affect overall system efficiency. Furthermore, performance can vary depending on the underlying DBMS, hardware, and benchmark choice, raising concerns about reproducibility and general applicability. Future research should focus on explainable and hybrid optimization frameworks that combine the reliability of traditional methods with the adaptability of AI-assisted approaches. Emphasis on robust evaluation, realistic workloads, and production-ready deployment will be crucial for translating experimental gains into operational database systems, ensuring that AI-assisted optimization can be safely and effectively integrated into real-world environments.

References

[1]Almeida, Fernando, Pedro Silva, and Fernando Araújo. 2019. “Performance Analysis and Optimization Techniques for Oracle Relational Databases.” Cybernetics and Information Technologies 19 (2): 117–32. https://doi.org/10.2478/cait-2019-0019. [2] Ammar, Ali Ben. 2016. “Query Optimization Techniques in Graph Databases.” International Journal of Database Management Systems 8 (4): 01–14. https://doi.org/10.5121/ijdms.2016.8401. [3]Azhir, Elham, Nima Jafari Navimipour, Mehdi Hosseinzadeh, Arash Sharifi, and Aso Darwesh. 2019. “Query Optimization Mechanisms in the Cloud Environments: A Systematic Study.” International Journal of Communication Systems 32 (8). https://doi.org/10.1002/dac.3940. [4]Chaudhuri, Surajit. 1998. “An Overview of Query Optimization in Relational Systems.” Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (Seattle Washington USA), May, 34–43. https://doi.org/10.1145/275487.275492. [5]A. Aljanaby, E. Abuelrub, and M. Odeh, “A Survey of Distributed Query Optimization.” [6]Dantuluri, Venkata Narasimha Raju. 2025. “AI-Powered Query Optimization in Multitenant Database Systems.” Journal of Computer Science and Technology Studies 7 (4): 802–13. https://doi.org/10.32996/jcsts.2025.7.4.93. [7]Ganguly, Sumit, Akshay Goel, and Avi Silberschatz. 1996. “Efficient and Accurate Cost Models for Parallel Query Optimization (Extended Abstract).” Proceedings of the Fifteenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (Montreal Quebec Canada), June, 172–81. https://doi.org/10.1145/237661.237707. [8]Heitz, Jonas, and Kurt Stockinger. 2019. Join Query Optimization with Deep Reinforcement Learning Algorithms. arXiv. https://doi.org/10.48550/arXiv.1911.11689. [9]Inersjö, Elizabeth. 2021. Comparing Database Optimisation Techniques in PostgreSQL : Indexes, Query Writing and the Query Optimiser. https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva- 306703. [10]Jarke, Matthias, and Jurgen Koch. 1984. “Query Optimization in Database Systems.” ACM Computing Surveys 16 (2): 111–52. https://doi.org/10.1145/356924.356928. [11]Krishnan, Sanjay, Zongheng Yang, Ken Goldberg, Joseph Hellerstein, and Ion Stoica. 2019. Learning to Optimize Join Queries With Deep Reinforcement Learning. arXiv. https://doi.org/10.48550/arXiv.1808.03196. [12]Lehmann, Claude, Pavel Sulimov, and Kurt Stockinger. 2024. Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective. arXiv. https://doi.org/10.48550/arXiv.2309.01551. [13]Li, Ziming, Youhuan Li, Yuyu Luo, Guoliang Li, and Chuxu Zhang. 2025. Graph Neural Networks for Databases: A Survey. arXiv. https://doi.org/10.48550/arXiv.2502.12908. [14]Marcus, Ryan, Parimarjan Negi, Hongzi Mao, et al. 2019. “Neo: A Learned Query Optimizer.” Proceedings of the VLDB Endowment 12 (11): 1705–18. https://doi.org/10.14778/3342263.3342644. [15]Marcus, Ryan, and Olga Papaemmanouil. 2018. Towards a Hands- Free Query Optimizer Through Deep Learning. arXiv. https://doi.org/10.48550/arXiv.1809.10212. [16]Mikhaylov, Artem, Nina S. Mazyavkina, Mikhail Salnikov, Ilya Trofimov, Fu Qiang, and Evgeny Burnaev. 2022. “Learned Query Optimizers: Evaluation and Improvement.” IEEE Access 10: 75205–18. https://doi.org/10.1109/ACCESS.2022.3190376. [17]Ortiz, Jennifer, Magdalena Balazinska, Johannes Gehrke, and S. Sathiya Keerthi. 2019. An Empirical Analysis of Deep Learning for Cardinality Estimation. arXiv. https://doi.org/10.48550/arXiv.1905.06425. [18]Padia, Shyam, Sushant Khulge, Akhilesh Gupta, and Parth Khadilikar. 2015. Query Optimization Strategies in Distributed Databases. 6. [19]P.Karthikeyan, M., K. Krishnaveni, and Dac-Nhuong Le. 2024. “Analysis of Multi-Join Query Optimization Using ACO and Q- Learning.” International Journal of Computing and Digital Systems 16 (1): 1523–33. https://doi.org/10.12785/ijcds/1601113. [20]Ramadan, Mohamed, Ayman El-Kilany, Hoda M. O. Mokhtar, and Ibrahim Sobh. 2022. “RL_QOptimizer: A Reinforcement Learning Based Query Optimizer.” IEEE Access 10: 70502–15. https://doi.org/10.1109/ACCESS.2022.3187102. [21] Schmidt, Michael, Olaf Görlitz, Peter Haase, Günter Ladwig, Andreas Schwarte, and Thanh Tran. 2011. “FedBench: A Benchmark Suite for Federated Semantic Data Query Processing.” In The Semantic Web – ISWC 2011, edited by Lora Aroyo, Chris Welty, Harith Alani, et al. Springer. https://doi.org/10.1007/978- 3-642-25073-6_37. [22]Sun, Ji, and Guoliang Li. 2019. An End-to-End Learning-Based Cost Estimator. arXiv. https://doi.org/10.48550/arXiv.1906.02560. [23]Zhou, Xuanhe, Chengliang Chai, Guoliang Li, and Ji Sun. n.d. Database Meets AI: A Survey. [24]D. J. Rigden, “Adaptive Query Optimization in Distributed SQL Databases,” International Journal of Technology Management, vol. 2, no. 3. [25]R. Marcus and O. Papaemmanouil, “Plan-Structured Deep Neural Network Models for Query Performance Prediction,” Proceedings of the VLDB Endowment, vol. 12, no. 11, pp. 1733–1746, Jul. 2019, arXiv:1902.00132 [cs]. [Online]. Available: http://arxiv.org/abs/1902. 00132

How to Cite This Paper

Mohamed Chetouani (2025). AI-Assisted Query Optimization in Relational Databases: A Comparative and Experimental Review . International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.

AI-Assisted Query Optimization in Relational Databases A Comparative and Experimental Review Download

ijct-publication-certificate-Mohamed Chetouani Download