Skip to main navigation Skip to search Skip to main content

Reinforcement Learning for Time-Series Query Optimization

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Time-series databases (TSDBs) are essential for managing large-scale time-series data in fields like finance, IoT, and agriculture. However, traditional query optimization methods, such as dynamic programming, struggle with high computational complexity and inaccurate cost estimates. This paper proposes a novel query optimization module for TSDBs using reinforcement learning (RL), specifically Deep Q-Networks (DQN) and Double Deep Q-Networks (DDQN). These algorithms dynamically learn optimal join orders based on query workloads and connection costs. Experiments show that RL-based methods achieve better optimization performance and stability compared to traditional heuristics, especially under complex cost models. This work highlights the potential of RL in improving query optimization for TSDBs.

Original languageEnglish
Title of host publicationData Science - 11th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2025, Proceedings
EditorsYi Yu, Haiwei Pan, Qilong Han, Hongzhi Wang, Chen Yu, Haiyi Liu, Xianhua Song, Zeguang Lu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages271-281
Number of pages11
ISBN (Print)9789819525652
DOIs
StatePublished - 2026
Event11th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2025 - Hiroshima, Japan
Duration: 19 Sep 202521 Sep 2025

Publication series

NameCommunications in Computer and Information Science
Volume2673 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference11th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2025
Country/TerritoryJapan
CityHiroshima
Period19/09/2521/09/25

Keywords

  • Distributed Indexing
  • LSM-Tree
  • Non-Primary Key Query

Fingerprint

Dive into the research topics of 'Reinforcement Learning for Time-Series Query Optimization'. Together they form a unique fingerprint.

Cite this