Tunnel ventilation control using reinforcement learning methodology

Baeksuk Chu, Dongnam Kim, Daehie Hong, Jooyoung Park, Jin Taek Chung, Tae Hyung Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The main purpose of tunnel ventilation s stem is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve the objectives, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions without relying on exemplary supervision or complete models of the environment. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. In the process of constructing the reward of the tunnel ventilation system, two objectives listed above are included, that is, maintaining an adequate level of pollutants and minimizing power consumption. RL algorithm based on actor-critic architecture and gradient-following algorithm is adopted to the tunnel ventilation system. The simulations results performed with real data collected from existing tunnel ventilation system and real experimental verification are provided in this paper. It is confirmed that with the suggested controller, the pollutant level inside the tunnel was well maintained under allowable limit and the performance of energy consumption was improved compared to conventional control scheme.

Original languageEnglish
Pages (from-to)1003-1010
Number of pages8
JournalJSME International Journal, Series C: Mechanical Systems, Machine Elements and Manufacturing
Volume49
Issue number4
DOIs
Publication statusPublished - 2007 Jun 15

Fingerprint

Reinforcement learning
Ventilation
Tunnels
Electric power utilization
Visibility
Learning algorithms
Energy utilization
Feedback
Controllers

Keywords

  • Actor-critic architecture
  • Gradient-following algorithm
  • Reinforcement learning (RL)
  • Tunnel ventilation control

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Cite this

Tunnel ventilation control using reinforcement learning methodology. / Chu, Baeksuk; Kim, Dongnam; Hong, Daehie; Park, Jooyoung; Chung, Jin Taek; Kim, Tae Hyung.

In: JSME International Journal, Series C: Mechanical Systems, Machine Elements and Manufacturing, Vol. 49, No. 4, 15.06.2007, p. 1003-1010.

Research output: Contribution to journalArticle

@article{7ce89a36e31c45eb93008fd167d16948,
title = "Tunnel ventilation control using reinforcement learning methodology",
abstract = "The main purpose of tunnel ventilation s stem is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve the objectives, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions without relying on exemplary supervision or complete models of the environment. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. In the process of constructing the reward of the tunnel ventilation system, two objectives listed above are included, that is, maintaining an adequate level of pollutants and minimizing power consumption. RL algorithm based on actor-critic architecture and gradient-following algorithm is adopted to the tunnel ventilation system. The simulations results performed with real data collected from existing tunnel ventilation system and real experimental verification are provided in this paper. It is confirmed that with the suggested controller, the pollutant level inside the tunnel was well maintained under allowable limit and the performance of energy consumption was improved compared to conventional control scheme.",
keywords = "Actor-critic architecture, Gradient-following algorithm, Reinforcement learning (RL), Tunnel ventilation control",
author = "Baeksuk Chu and Dongnam Kim and Daehie Hong and Jooyoung Park and Chung, {Jin Taek} and Kim, {Tae Hyung}",
year = "2007",
month = "6",
day = "15",
doi = "10.1299/jsmec.49.1003",
language = "English",
volume = "49",
pages = "1003--1010",
journal = "JSME International Journal, Series C: Mechanical Systems, Machine Elements and Manufacturing",
issn = "1344-7653",
publisher = "Japan Society of Mechanical Engineers",
number = "4",

}

TY - JOUR

T1 - Tunnel ventilation control using reinforcement learning methodology

AU - Chu, Baeksuk

AU - Kim, Dongnam

AU - Hong, Daehie

AU - Park, Jooyoung

AU - Chung, Jin Taek

AU - Kim, Tae Hyung

PY - 2007/6/15

Y1 - 2007/6/15

N2 - The main purpose of tunnel ventilation s stem is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve the objectives, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions without relying on exemplary supervision or complete models of the environment. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. In the process of constructing the reward of the tunnel ventilation system, two objectives listed above are included, that is, maintaining an adequate level of pollutants and minimizing power consumption. RL algorithm based on actor-critic architecture and gradient-following algorithm is adopted to the tunnel ventilation system. The simulations results performed with real data collected from existing tunnel ventilation system and real experimental verification are provided in this paper. It is confirmed that with the suggested controller, the pollutant level inside the tunnel was well maintained under allowable limit and the performance of energy consumption was improved compared to conventional control scheme.

AB - The main purpose of tunnel ventilation s stem is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve the objectives, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions without relying on exemplary supervision or complete models of the environment. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. In the process of constructing the reward of the tunnel ventilation system, two objectives listed above are included, that is, maintaining an adequate level of pollutants and minimizing power consumption. RL algorithm based on actor-critic architecture and gradient-following algorithm is adopted to the tunnel ventilation system. The simulations results performed with real data collected from existing tunnel ventilation system and real experimental verification are provided in this paper. It is confirmed that with the suggested controller, the pollutant level inside the tunnel was well maintained under allowable limit and the performance of energy consumption was improved compared to conventional control scheme.

KW - Actor-critic architecture

KW - Gradient-following algorithm

KW - Reinforcement learning (RL)

KW - Tunnel ventilation control

UR - http://www.scopus.com/inward/record.url?scp=34548107704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548107704&partnerID=8YFLogxK

U2 - 10.1299/jsmec.49.1003

DO - 10.1299/jsmec.49.1003

M3 - Article

VL - 49

SP - 1003

EP - 1010

JO - JSME International Journal, Series C: Mechanical Systems, Machine Elements and Manufacturing

JF - JSME International Journal, Series C: Mechanical Systems, Machine Elements and Manufacturing

SN - 1344-7653

IS - 4

ER -