Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning - IMT - Institut Mines-Télécom Accéder directement au contenu
Chapitre D'ouvrage Année : 2016

Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning

Résumé

In this paper, we propose a learning approach to adaptive performance tuning of database applications. The objective is to validate the opportunity to devise a tuning strategy that does not need prior knowledge of a cost model. Instead, the cost model is learned through reinforcement learning. We instantiate our approach to the use case of index tuning. We model the execution of queries and updates as a Markov decision process whose states are database configurations, actions are configuration changes, and rewards are functions of the cost of configuration change and query and update evaluation. During the reinforcement learning process, we face two important challenges: the unavailability of a cost model and the size of the state space. To address the former, we iteratively learn the cost model, in a principled manner, using regularization to avoid overfitting. To address the latter, we devise strategies to prune the state space, both in the general case and for the use case of index tuning. We empirically and comparatively evaluate our approach on a standard OLTP dataset. We show that our approach is competitive with state-of-the-art adaptive index tuning, which is dependent on a cost model.
Fichier principal
Vignette du fichier
article.pdf (1.81 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02115175 , version 1 (30-04-2019)

Identifiants

Citer

Debabrota Basu, Qian Lin, Weidong Chen, Hoang Tam Vo, Zihong Yuan, et al.. Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning. Abdelkader Hameurlain; Josef Küng; Roland Wagner; Qimin Chen. Transactions on Large-Scale Data- and Knowledge-Centered Systems XXVIII, 9940, Springer Verlag, pp.96-132, 2016, Lecture Notes in Computer Science, ⟨10.1007/978-3-662-53455-7_5⟩. ⟨hal-02115175⟩
91 Consultations
188 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More