Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199829,
        author = {Kusuri Karthik and G.Abhishek and P.ShivaKrishna and Dr. Monoj Suthradhar},
        title = {RL-DBMS: Reinforcement Learning–Based Dynamic Database Optimization for Hybrid Cloud Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {14342-14353},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199829},
        abstract = {A key element of database management systems (DBMS) is query optimization, which establishes effective SQL query execution techniques. Conventional cost-based query optimizers choose execution strategies using heuristic criteria and statistical estimation. However, these approaches often produce suboptimal plans in dynamic workloads and distributed environments such as hybrid cloud systems. Recent research has explored machine learning and reinforcement learning techniques to improve database optimization tasks, including query planning, indexing, and workload management. In particular, reinforcement learning enables database systems to learn optimal optimization strategies through interaction with query workloads and system performance feedback. In this paper, we present RL-DBMS, a reinforcement learning–based framework for dynamic database optimization in hybrid cloud environments. RL-DBMS integrates workload analysis, adaptive query planning, and reinforcement learning policies to continuously improve database performance. The framework leverages reinforcement learning to optimize query execution strategies, resource allocation, and indexing decisions in distributed database systems. We analyze recent advances in learned query optimizers, including Neo, Bao, Balsa, and Lero, and examine reinforcement learning–based optimization approaches such as SkinnerDB and UDO. Our study demonstrates that reinforcement learning can significantly improve query performance and enable autonomous database systems capable of adapting to dynamic cloud workloads.},
        keywords = {Reinforcement Learning, Query Optimization, Autonomous Databases, Hybrid Cloud Databases, Machine Learning for Databases.},
        month = {April},
        }