ABSTRACT
This study introduces the Instance-Aware Index Advisor (IA2), a novel deep reinforcement learning (DRL)-based approach for optimizing index selection in databases facing large action spaces of potential candidates. IA2 introduces the Twin Delayed Deep Deterministic Policy Gradient - Temporal Difference State-Wise Action Refinery (TD3-TD-SWAR) model, enabling efficient index selection by understanding workload-index dependencies and employing adaptive action masking. This method includes a comprehensive workload model, enhancing its ability to adapt to unseen workloads and ensuring robust performance across diverse database environments. Evaluation on benchmarks such as TPC-H reveals IA2's suggested indexes' performance in enhancing runtime, securing a 40% reduction in runtime for complex TPC-H workloads compared to scenarios without indexes, and delivering a 20% improvement over existing state-of-the-art DRL-based index advisors
- Surajit Chaudhuri and Vivek R Narasayya. 1997. An efficient, cost-driven index selection tool for Microsoft SQL server. In VLDB, Vol. 97. San Francisco, 146--155.Google Scholar
- Debabrata Dash, Neoklis Polyzotis, and Anastasia Ailamaki. 2011. Cophy: A scalable, portable, and interactive index advisor for large workloads. arXiv preprint arXiv:1104.3214 (2011).Google Scholar
- Scott Fujimoto, Herke Van Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. arXiv:1802.09477 (2018).Google Scholar
- Vijay R Konda and John N Tsitsiklis. 2000. Actor-critic algorithms. In NeurIPS.Google Scholar
- Jan Kossmann, Stefan Halfpap, Marcel Jankrift, and Rainer Schlosser. 2020. Magic mirror in my hand, which is the best in the land? an experimental evaluation of index selection algorithms. Proceedings of the VLDB Endowment 13, 12 (2020), 2382--2395.Google ScholarDigital Library
- Jan Kossmann, Alexander Kastius, and Rainer Schlosser. 2022. SWIRL: Selection of Workload-aware Indexes using Reinforcement Learning.. In EDBT. 2--155.Google Scholar
- Hai Lan, Zhifeng Bao, and Yuwei Peng. 2020. An index advisor using deep reinforcement learning. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2105--2108.Google ScholarDigital Library
- Vincent Y Lum and Huei Ling. 1971. An optimization problem on the selection of secondary keys. In Proceedings of the 1971 26th annual conference. 349--356.Google ScholarDigital Library
- Stratos Papadomanolakis and Anastassia Ailamaki. 2007. An integer linear programming approach to database design. In 2007 IEEE 23rd International Conference on Data Engineering Workshop. IEEE, 442--449.Google ScholarDigital Library
- Zahra Sadri, Le Gruenwald, and Eleazar Lead. 2020. DRLindex: deep reinforcement learning index advisor for a cluster database. In Proceedings of the 24th Symposium on International Database Engineering & Applications. 1--8.Google ScholarDigital Library
- Rainer Schlosser, Jan Kossmann, and Martin Boissier. 2019. Efficient scalable multi-attribute index selection using recursive strategies. In 2019 IEEE 35th International Conference on Data Engineering (ICDE). IEEE, 1238--1249.Google ScholarCross Ref
- Hao Sun and Taiyi Wang. 2022. Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference. arXiv preprint arXiv:2201.00354 (2022).Google Scholar
- Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press.Google ScholarDigital Library
- Gary Valentin, Michael Zuliani, Daniel C Zilio, Guy Lohman, and Alan Skelley. 2000. DB2 advisor: An optimizer smart enough to recommend its own indexes. In Proceedings of 16th International Conference on Data Engineering (Cat. No. 00CB37073). IEEE, 101--110.Google ScholarCross Ref
- Jinsung Yoon, James Jordon, and Mihaela van der Schaar. 2018. INVASE: Instance-wise variable selection using neural networks. In ICLR.Google Scholar
Index Terms
- IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse Workloads
Recommendations
An xml index advisor for DB2
SIGMOD '08: Proceedings of the 2008 ACM SIGMOD international conference on Management of dataXML database systems are expected to handle increasingly complex queries over increasingly large and highly structured XML databases. An important problem that needs to be solved for these systems is how to choose the best set of indexes for a given ...
Kaizen: a semi-automatic index advisor
SIGMOD '12: Proceedings of the 2012 ACM SIGMOD International Conference on Management of DataIndex tuning; i.e., selecting indexes that are appropriate for the workload to obtain good system performance, is a crucial task for database administrators. Administrators rely on automated index advisors for this task, but existing advisors work ...
Reward Shaping in Episodic Reinforcement Learning
AAMAS '17: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent SystemsRecent advancements in reinforcement learning confirm that reinforcement learning techniques can solve large scale problems leading to high quality autonomous decision making. It is a matter of time until we will see large scale applications of ...
Comments