Comprehensible Models for Reconfiguring Enterprise Relational Databases to Avoid Incidents

Giurgiu, Ioana; Botezatu, Mirela; Wiesmann, D.

doi:10.1145/2806416.2806448

Cited by 7 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first category of work focused on the ML based approach techniques and have been developed to see how artificial intelligence (AI) can benefit the most challenging issues in database systems, including automate physical design phase (e.g., index and view recommendation), query performance prediction, 26 query plan optimization, 27 and self-tuning and admission control. 28 The main focus of each issue is to address one or more of the following cost-driven research questions: (i) How to use machine learning to provide comprehensible models for reconfiguring DBMS to avoid high risk incidents; 29 (ii) How to select the optimal query plan by applying DL for better query plan enumeration (e.g., References 30-33), (iii) predicting the database or workload performance under hypothetical resource or parameter changes, [2][3][4] (iv) Using supervised predictive models to recommend indexes for databases where a query execution cost increases after changing the indexes (e.g., References 34 and 35), and (v) self-tuning of several configuration parameters (e.g., buffer cache size) that can significantly affect the performance of a DBMS (e.g., References 10,36,37).…”

Section: Machine Learning-based Approachmentioning

confidence: 99%

DeepCM: Deep neural networks to improve accuracy prediction of database cost models

Ouared

Chadli

Daoud³

2021

Concurrency and Computation

View full text Add to dashboard Cite

A major challenge for many database management tasks including admission control, query scheduling, progress monitoring and self-driving data storage systems is to enhance queries performances which are based on computational models known as database cost models. One of the most challenging aspects of developing accurate database cost models is identifying their parameters and capturing their relationships, consequently we can derive the query execution cost on the basis of a specific database hosted on a given platform. Furthermore, the highly dynamic workload (i.e., a set of queries) and the query execution variation lead to performance degradation risk, therefore cost models need to be improved by considering newer software configuration and future workload characteristics. In this article, we propose a framework called DeepCM that is based on a min-max optimization for building robust database cost model against uncertainty parameters. Furthermore, our framework is based on Robust Deep Neural Networks to build database cost models that guarantee a high accuracy regardless of variations from software configuration and workload characteristics.Several experiments have been done to evaluate the robustness of produced cost models and findings show that DeepCM provides a high cost model prediction accuracy and stable performance.

show abstract