RL_QOptimizer: A Reinforcement Learning Based Query Optimizer
With the current availability of massive datasets and scalability requirements, different systems are required to provide their users with the best performance possible in terms of speed. On the physical level, performance can be translated into queries’ execution time in database managem...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9810215/ |
| _version_ | 1811225448908062720 |
|---|---|
| author | Mohamed Ramadan Ayman El-Kilany Hoda M. O. Mokhtar Ibrahim Sobh |
| author_facet | Mohamed Ramadan Ayman El-Kilany Hoda M. O. Mokhtar Ibrahim Sobh |
| author_sort | Mohamed Ramadan |
| collection | DOAJ |
| description | With the current availability of massive datasets and scalability requirements, different systems are required to provide their users with the best performance possible in terms of speed. On the physical level, performance can be translated into queries’ execution time in database management systems. Queries have to execute efficiently (i.e. in minimum time) to meet users’ needs, which puts an excessive burden on the database management system (DBMS). In this paper, we mainly focus on enhancing the query optimizer, which is one of the main components in DBMS that is responsible for choosing the optimal query execution plan and consequently determines the query execution time. Inspired by recent research in reinforcement learning in different domains, this paper proposes A Deep Reinforcement Learning Based Query Optimizer (RL_QOptimizer), a new approach to find the best policy for join order in the query plan which depends solely on the reward system of reinforcement learning. The experimental results show that a notable advantage of the proposed approach against the existing query optimization model of PostgreSQL DBMS. |
| first_indexed | 2024-04-12T09:07:22Z |
| format | Article |
| id | doaj.art-962d974d93ef4f42a28dc4ebaa511d50 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T09:07:22Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-962d974d93ef4f42a28dc4ebaa511d502022-12-22T03:39:04ZengIEEEIEEE Access2169-35362022-01-0110705027051510.1109/ACCESS.2022.31871029810215RL_QOptimizer: A Reinforcement Learning Based Query OptimizerMohamed Ramadan0https://orcid.org/0000-0001-7107-4339Ayman El-Kilany1Hoda M. O. Mokhtar2https://orcid.org/0000-0002-7877-4108Ibrahim Sobh3https://orcid.org/0000-0002-9414-6267Information Systems Department, Faculty of Computers and Artificial Intelligence, Cairo University, Cairo, EgyptInformation Systems Department, Faculty of Computers and Artificial Intelligence, Cairo University, Cairo, EgyptInformation Systems Department, Faculty of Computers and Artificial Intelligence, Cairo University, Cairo, EgyptValeo, Cairo, EgyptWith the current availability of massive datasets and scalability requirements, different systems are required to provide their users with the best performance possible in terms of speed. On the physical level, performance can be translated into queries’ execution time in database management systems. Queries have to execute efficiently (i.e. in minimum time) to meet users’ needs, which puts an excessive burden on the database management system (DBMS). In this paper, we mainly focus on enhancing the query optimizer, which is one of the main components in DBMS that is responsible for choosing the optimal query execution plan and consequently determines the query execution time. Inspired by recent research in reinforcement learning in different domains, this paper proposes A Deep Reinforcement Learning Based Query Optimizer (RL_QOptimizer), a new approach to find the best policy for join order in the query plan which depends solely on the reward system of reinforcement learning. The experimental results show that a notable advantage of the proposed approach against the existing query optimization model of PostgreSQL DBMS.https://ieeexplore.ieee.org/document/9810215/Join ordering problemquery execution plan and query optimization |
| spellingShingle | Mohamed Ramadan Ayman El-Kilany Hoda M. O. Mokhtar Ibrahim Sobh RL_QOptimizer: A Reinforcement Learning Based Query Optimizer IEEE Access Join ordering problem query execution plan and query optimization |
| title | RL_QOptimizer: A Reinforcement Learning Based Query Optimizer |
| title_full | RL_QOptimizer: A Reinforcement Learning Based Query Optimizer |
| title_fullStr | RL_QOptimizer: A Reinforcement Learning Based Query Optimizer |
| title_full_unstemmed | RL_QOptimizer: A Reinforcement Learning Based Query Optimizer |
| title_short | RL_QOptimizer: A Reinforcement Learning Based Query Optimizer |
| title_sort | rl x005f qoptimizer a reinforcement learning based query optimizer |
| topic | Join ordering problem query execution plan and query optimization |
| url | https://ieeexplore.ieee.org/document/9810215/ |
| work_keys_str_mv | AT mohamedramadan rlx005fqoptimizerareinforcementlearningbasedqueryoptimizer AT aymanelkilany rlx005fqoptimizerareinforcementlearningbasedqueryoptimizer AT hodamomokhtar rlx005fqoptimizerareinforcementlearningbasedqueryoptimizer AT ibrahimsobh rlx005fqoptimizerareinforcementlearningbasedqueryoptimizer |