RL4CEP: reinforcement learning for updating CEP rules

Abstract This paper presents RL4CEP, a reinforcement learning (RL) approach to dynamically update complex event processing (CEP) rules. RL4CEP uses Double Deep Q-Networks to update the threshold values used by CEP rules. It is implemented using Apache Flink as a CEP engine and Apache Kafka for messa...

Full description

Saved in:
Bibliographic Details
Main Authors: Afef Mdhaffar, Ghassen Baklouti, Yassine Rebai, Mohamed Jmaiel, Bernd Freisleben
Format: Article
Language:English
Published: Springer 2025-01-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01742-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1823861473175142400
author Afef Mdhaffar
Ghassen Baklouti
Yassine Rebai
Mohamed Jmaiel
Bernd Freisleben
author_facet Afef Mdhaffar
Ghassen Baklouti
Yassine Rebai
Mohamed Jmaiel
Bernd Freisleben
author_sort Afef Mdhaffar
collection DOAJ
description Abstract This paper presents RL4CEP, a reinforcement learning (RL) approach to dynamically update complex event processing (CEP) rules. RL4CEP uses Double Deep Q-Networks to update the threshold values used by CEP rules. It is implemented using Apache Flink as a CEP engine and Apache Kafka for message distribution. RL4CEP is a generic approach for scenarios in which CEP rules need to be updated dynamically. In this paper, we use RL4CEP in a financial trading use case. Our experimental results based on three financial trading rules and eight financial datasets demonstrate the merits of RL4CEP in improving the overall profit, when compared to baseline and state-of-the-art approaches, with a reasonable consumption of resources, i.e., RAM and CPU. Finally, our experiments indicate that RL4CEP is executed quite fast compared to traditional CEP engines processing static rules.
format Article
id doaj-art-69ef11e2b0da4a6394a6c40349bb8ee1
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-01-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-69ef11e2b0da4a6394a6c40349bb8ee12025-02-09T13:01:11ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111211510.1007/s40747-024-01742-3RL4CEP: reinforcement learning for updating CEP rulesAfef Mdhaffar0Ghassen Baklouti1Yassine Rebai2Mohamed Jmaiel3Bernd Freisleben4ReDCAD Laboratory, ENIS, University of SfaxReDCAD Laboratory, ENIS, University of SfaxDepartment of Computer Science, TELNET HoldingReDCAD Laboratory, ENIS, University of SfaxDepartment of Mathematics and Computer Science, University of MarburgAbstract This paper presents RL4CEP, a reinforcement learning (RL) approach to dynamically update complex event processing (CEP) rules. RL4CEP uses Double Deep Q-Networks to update the threshold values used by CEP rules. It is implemented using Apache Flink as a CEP engine and Apache Kafka for message distribution. RL4CEP is a generic approach for scenarios in which CEP rules need to be updated dynamically. In this paper, we use RL4CEP in a financial trading use case. Our experimental results based on three financial trading rules and eight financial datasets demonstrate the merits of RL4CEP in improving the overall profit, when compared to baseline and state-of-the-art approaches, with a reasonable consumption of resources, i.e., RAM and CPU. Finally, our experiments indicate that RL4CEP is executed quite fast compared to traditional CEP engines processing static rules.https://doi.org/10.1007/s40747-024-01742-3Deep Reinforcement LearningComplex Event ProcessingFinancial TradingCEP RulesRule Updates
spellingShingle Afef Mdhaffar
Ghassen Baklouti
Yassine Rebai
Mohamed Jmaiel
Bernd Freisleben
RL4CEP: reinforcement learning for updating CEP rules
Complex & Intelligent Systems
Deep Reinforcement Learning
Complex Event Processing
Financial Trading
CEP Rules
Rule Updates
title RL4CEP: reinforcement learning for updating CEP rules
title_full RL4CEP: reinforcement learning for updating CEP rules
title_fullStr RL4CEP: reinforcement learning for updating CEP rules
title_full_unstemmed RL4CEP: reinforcement learning for updating CEP rules
title_short RL4CEP: reinforcement learning for updating CEP rules
title_sort rl4cep reinforcement learning for updating cep rules
topic Deep Reinforcement Learning
Complex Event Processing
Financial Trading
CEP Rules
Rule Updates
url https://doi.org/10.1007/s40747-024-01742-3
work_keys_str_mv AT afefmdhaffar rl4cepreinforcementlearningforupdatingceprules
AT ghassenbaklouti rl4cepreinforcementlearningforupdatingceprules
AT yassinerebai rl4cepreinforcementlearningforupdatingceprules
AT mohamedjmaiel rl4cepreinforcementlearningforupdatingceprules
AT berndfreisleben rl4cepreinforcementlearningforupdatingceprules