Construction of a parametric model of competitive access in relational databases by using a random forest method

Authors

  • Dmitry Gromey Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015, Russian Federation https://orcid.org/0000-0003-1066-556X
  • Eugene Lebedenko Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015, Russian Federation https://orcid.org/0000-0001-6135-0352
  • Dmitry Nikolaev Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015, Russian Federation https://orcid.org/0000-0001-9334-6948
  • Tatyana Rozhkova Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015, Russian Federation https://orcid.org/0000-0002-7079-4366

DOI:

https://doi.org/10.15587/1729-4061.2019.170071

Keywords:

autonomous systems of database management, self-identifiable databases, random forest, competitive access, parallel computing in relational database management systems.

Abstract

We have considered the task on modeling a request execution time in autonomous relational databases with competitive queries. The shortcomings of existing approaches have been specified, which ignore the cost of the share of successive operations in the cooperative access to data in a memory hierarchy. We have examined the issue of the application of relative cost for the implementation of components in the operations of a plan of the query, instead of calculating the predicted time of computation.

A technique has been proposed for the formal construction of precedents for a training sample, as well as the approach to building a regression model. The developed modification of the machine learning method random forest is used for calculating the request execution time based on their texts and temporary marks of the start, duration of execution.

The constructed parametrical model of competitive access to data is required for obtaining accurate estimates of request execution time when using parallel computations. Models with such characteristics are needed to solve the problems on automated management of a physical data scheme, for building self-identifiable DBMS. The key differences from existing approaches are the application of a request execution time as the target value, accounting the values of predicates and mutual influence of requests that are executed in parallel.

To confirm the results obtained, a simulation model has been used based on the widely known test TPC-C. The used function of loss, taking into consideration the regression nature of the model, was the ratio of the sum of modules of difference between the actual and obtained time to the actual time. The check itself was carried out based on a reference sample, generated for the increasing length of training at postponed data. In the course of this study we have proved a possibility to apply the machine learning method random forest for processing statistical data on the execution of SQL queries. The result obtained is promising for such an approach and makes it possible to derive the parametric models of competitive request processing.

Author Biographies

Dmitry Gromey, Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015

Department of Informatics and Computer Science

Eugene Lebedenko, Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015

PhD, Associate Professor

Department of Informatics and Computer Science

Dmitry Nikolaev, Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015

Department of Informatics and Computer Science

Tatyana Rozhkova, Federal State Government Educational Institution of Higher Education "The Academy of Federal Security Guard Service of the Russian Federation" Priborostroitel'naya str., 35, Orel, Russia, 302015

Department of Informatics and Computer Science

References

  1. Gromey, D. D., Lebedenko, E. V. (2015). Automation of data distribution for the DBMS with competitive requests. Modern informatization problems in simulation and social technologies Proceedings of the XX-th International Open Science Conference. Yelm, WA, USA, 167–173.
  2. Chaudhuri, S., Narasayya, V., Ramamurthy, R. (2009). Exact cardinality query optimization for optimizer testing. Proceedings of the VLDB Endowment, 2 (1), 994–1005. doi: https://doi.org/10.14778/1687627.1687739
  3. Borchuk, L. E. (2016). Stoimostnye optimizatory dlya SUBD: vchera i segodnya. Otkrytye sistemy. SUBD, 1, 36–39.
  4. Kim, K., Wang, T., Johnson, R., Pandis, I. (2016). ERMIA. Proceedings of the 2016 International Conference on Management of Data – SIGMOD '16. doi: https://doi.org/10.1145/2882903.2882905
  5. Neumann, T., Mühlbauer, T., Kemper, A. (2015). Fast Serializable Multi-Version Concurrency Control for Main-Memory Database Systems. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data – SIGMOD '15. doi: https://doi.org/10.1145/2723372.2749436
  6. Rheinländer, A., Leser, U., Graefe, G. (2017). Optimization of Complex Dataflows with User-Defined Functions. ACM Computing Surveys, 50 (3), 1–39. doi: https://doi.org/10.1145/3078752
  7. Basu, D., Lin, Q., Chen, W., Vo, H. T., Yuan, Z., Senellart, P., Bressan, S. (2015). Cost-Model Oblivious Database Tuning with Reinforcement Learning. Lecture Notes in Computer Science, 253–268. doi: https://doi.org/10.1007/978-3-319-22849-5_18
  8. Das, S., Li, F., Narasayya, V. R., König, A. C. (2016). Automated Demand-driven Resource Scaling in Relational Database-as-a-Service. Proceedings of the 2016 International Conference on Management of Data – SIGMOD '16. doi: https://doi.org/10.1145/2882903.2903733
  9. Mozafari, B., Niu, N. (2015). A Handbook for Building an Approximate Query Engine. IEEE Data Eng. Bull., 38 (3), 3–29.
  10. Yoon, D. Y., Niu, N., Mozafari, B. (2016). DBSherlock. Proceedings of the 2016 International Conference on Management of Data – SIGMOD '16. doi: https://doi.org/10.1145/2882903.2915218
  11. Radhika, G., Chhabra, P., Kumari, R. (2014). Consistency models in distributed shared memory systems. International Journal of Computer Science and Mobile Computing, 3 (9), 196–201.
  12. Arulraj, J., Pavlo, A., Dulloor, S. R. (2015). Let's Talk About Storage & Recovery Methods for Non-Volatile Memory Database Systems. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data – SIGMOD '15. doi: https://doi.org/10.1145/2723372.2749441
  13. Ma, L., Van Aken, D., Hefny, A., Mezerhane, G., Pavlo, A., Gordon, G. J. (2018). Query-based Workload Forecasting for Self-Driving Database Management Systems. Proceedings of the 2018 International Conference on Management of Data – SIGMOD '18. doi: https://doi.org/10.1145/3183713.3196908
  14. Arulraj, J., Pavlo, A., Menon, P. (2016). Bridging the Archipelago between Row-Stores and Column-Stores for Hybrid Workloads. Proceedings of the 2016 International Conference on Management of Data – SIGMOD '16. doi: https://doi.org/10.1145/2882903.2915231
  15. Nithya, B. (2016). An Analysis on Applications of Machine Learning Tools, Techniques and Practices in Health Care System. International Journal of Advanced Research in Computer Science and Software Engineering, 6 (6).
  16. Hogland, J., Anderson, N. (2017). Function Modeling Improves the Efficiency of Spatial Modeling Using Big Data from Remote Sensing. Big Data and Cognitive Computing, 1 (1), 3. doi: https://doi.org/10.3390/bdcc1010003
  17. Ross, K., Moh, M., Moh, T.-S., Yao, J. (2018). Multi-source data analysis and evaluation of machine learning techniques for SQL injection detection. Proceedings of the ACMSE 2018 Conference on – ACMSE '18. doi: https://doi.org/10.1145/3190645.3190670
  18. Janitza, S., Celik, E., Boulesteix, A.-L. (2018). A computationally fast variable importance test for random forests for high-dimensional data. Advances in Data Analysis and Classification, 12 (4), 885–915. doi: https://doi.org/10.1007/s11634-016-0276-4
  19. Cumin, J., Petit, J., Scuturici, V., Surdu, S. (2017). Data Exploration with SQL using Machine Learning Techniques. Open Proceedings, 96–107. doi: http://doi.org/10.5441/002/edbt.2017.10

Downloads

Published

2019-06-11

How to Cite

Gromey, D., Lebedenko, E., Nikolaev, D., & Rozhkova, T. (2019). Construction of a parametric model of competitive access in relational databases by using a random forest method. Eastern-European Journal of Enterprise Technologies, 3(2 (99), 15–24. https://doi.org/10.15587/1729-4061.2019.170071