Author(s): Dulin S.K., Ryabtsev A.B.

Rubric: Information technology

DOI: 10.21777/2500-2112-2023-3-73-80

Release: 2023-3 (44)

Pages: 73-80

Keywords: database management system, analytical SQL queries, SQL query execution plan, cost estimation, machine learning

Annotation: The article describes the problem of optimizing the execution plans of analytical SQL queries using machine learning. Currently, none of the popular database management systems (DBMS) uses an optimizer based on machine learning. At the same time, it is machine learning that can solve the known problems of standard optimizers used in most modern DBMS. In this work, the disadvantages of existing approaches to planning analytical SQL queries are considered in detail. There is a lack of research on the use of well-known machine learning-based approaches to optimizing SQL queries in analytical databases. The relevance of solving the problem of optimizing SQL query execution plans for massively parallel column-based DBMS is shown. The paper provides a justification for the choice of specific methods based on machine learning. The modifications made are described, in particular, an approach to the selection of execution plans for analytical SQL queries based on the collection of a training sample and the selection of target values is proposed. The problem of implementing a machine learning-based approach is considered. Possible problems with the training of the model and its operation in fundamentally new situations arising during training are highlighted. The ways of their solution are proposed. Original experiments have been carried out with various methods of optimizing SQL queries in relation to a massively parallel column DBMS. It is shown that the proposed modifications of existing solutions significantly improve the speed of query execution.

Bibliography: Dulin S.K., Ryabtsev A.B. ANALYSIS OF APPROACHES TO QUERY OPTIMIZATION IN ANALYTICAL DBMS // Education Resources and Technologies. – 2023. – № 3 (44). – С. 73-80. doi: 10.21777/2500-2112-2023-3-73-80

Text article and list references