Sergey A. Petunin (petunin@vniia.ru),Denis V. Verbov (vedenis@yandex.ru), Roman V. Lavrinchuk (lavrinchuk.roman@gmail.com)

Dukhov Automatics Research Institute

The paper considers the application of machine learning methods in the analysis of database workload monitoring data. An approach is proposed for clustering queries performed in the database based on the input coefficient, which reflects the relation of the work done to the returned result. An example of analysis of load history using heat maps is given and the ratio of complexity parameters of actual queries to the introduced coefficient is considered.

database, optimization of SQL query, classification, machine learning, statistics, information systems.