Service area-based elevator group supervisory control system using GNP with RL

Jin Zhou, Lu Yu, Shingo Mabu, Kotaro Hirasawa, Takayuki Furuzuki, Sandor Markon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Genetic Network Programming (GNP) was proposed several years ago as a new evolutionary computation method. Its unique features, such as highly compact structure, potential memory function, etc, are verified by many studies mainly on virtual world problems. Recently, GNP is also applied to some complicated real world problems like Elevator Group Supervisory Control Systems (EGSCS) and stock price prediction systems. As we know, EGSCS is a very large scale stochastic dynamic optimization problem. Due to its vast state space, significant uncertainty and numerous resource constraints such as finite car capacities and registered hall/car calls, it is hard to manage EGSCS using conventional control methods. In this paper, we propose an enhanced algorithm of EGSCS using GNP with Reinforcement Learning (RL) where an importance weight tuning method and a car assignment policy based on service area are introduced.

Original languageEnglish
Title of host publication2006 SICE-ICASE International Joint Conference
Pages5967-5972
Number of pages6
DOIs
Publication statusPublished - 2006
Event2006 SICE-ICASE International Joint Conference - Busan
Duration: 2006 Oct 182006 Oct 21

Other

Other2006 SICE-ICASE International Joint Conference
CityBusan
Period06/10/1806/10/21

Fingerprint

Elevators
Reinforcement learning
Control systems
Railroad cars
Evolutionary algorithms
Tuning
Data storage equipment

Keywords

  • Elevator group supervisory control system
  • Genetic network programming
  • Importance weight
  • Reinforcement learning
  • Service area

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Zhou, J., Yu, L., Mabu, S., Hirasawa, K., Furuzuki, T., & Markon, S. (2006). Service area-based elevator group supervisory control system using GNP with RL. In 2006 SICE-ICASE International Joint Conference (pp. 5967-5972). [4108647] https://doi.org/10.1109/SICE.2006.315839

Service area-based elevator group supervisory control system using GNP with RL. / Zhou, Jin; Yu, Lu; Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki; Markon, Sandor.

2006 SICE-ICASE International Joint Conference. 2006. p. 5967-5972 4108647.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhou, J, Yu, L, Mabu, S, Hirasawa, K, Furuzuki, T & Markon, S 2006, Service area-based elevator group supervisory control system using GNP with RL. in 2006 SICE-ICASE International Joint Conference., 4108647, pp. 5967-5972, 2006 SICE-ICASE International Joint Conference, Busan, 06/10/18. https://doi.org/10.1109/SICE.2006.315839
Zhou J, Yu L, Mabu S, Hirasawa K, Furuzuki T, Markon S. Service area-based elevator group supervisory control system using GNP with RL. In 2006 SICE-ICASE International Joint Conference. 2006. p. 5967-5972. 4108647 https://doi.org/10.1109/SICE.2006.315839
Zhou, Jin ; Yu, Lu ; Mabu, Shingo ; Hirasawa, Kotaro ; Furuzuki, Takayuki ; Markon, Sandor. / Service area-based elevator group supervisory control system using GNP with RL. 2006 SICE-ICASE International Joint Conference. 2006. pp. 5967-5972
@inproceedings{a299a9a50e3a4fedb3b84211f4c436d9,
title = "Service area-based elevator group supervisory control system using GNP with RL",
abstract = "Genetic Network Programming (GNP) was proposed several years ago as a new evolutionary computation method. Its unique features, such as highly compact structure, potential memory function, etc, are verified by many studies mainly on virtual world problems. Recently, GNP is also applied to some complicated real world problems like Elevator Group Supervisory Control Systems (EGSCS) and stock price prediction systems. As we know, EGSCS is a very large scale stochastic dynamic optimization problem. Due to its vast state space, significant uncertainty and numerous resource constraints such as finite car capacities and registered hall/car calls, it is hard to manage EGSCS using conventional control methods. In this paper, we propose an enhanced algorithm of EGSCS using GNP with Reinforcement Learning (RL) where an importance weight tuning method and a car assignment policy based on service area are introduced.",
keywords = "Elevator group supervisory control system, Genetic network programming, Importance weight, Reinforcement learning, Service area",
author = "Jin Zhou and Lu Yu and Shingo Mabu and Kotaro Hirasawa and Takayuki Furuzuki and Sandor Markon",
year = "2006",
doi = "10.1109/SICE.2006.315839",
language = "English",
isbn = "8995003855",
pages = "5967--5972",
booktitle = "2006 SICE-ICASE International Joint Conference",

}

TY - GEN

T1 - Service area-based elevator group supervisory control system using GNP with RL

AU - Zhou, Jin

AU - Yu, Lu

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Markon, Sandor

PY - 2006

Y1 - 2006

N2 - Genetic Network Programming (GNP) was proposed several years ago as a new evolutionary computation method. Its unique features, such as highly compact structure, potential memory function, etc, are verified by many studies mainly on virtual world problems. Recently, GNP is also applied to some complicated real world problems like Elevator Group Supervisory Control Systems (EGSCS) and stock price prediction systems. As we know, EGSCS is a very large scale stochastic dynamic optimization problem. Due to its vast state space, significant uncertainty and numerous resource constraints such as finite car capacities and registered hall/car calls, it is hard to manage EGSCS using conventional control methods. In this paper, we propose an enhanced algorithm of EGSCS using GNP with Reinforcement Learning (RL) where an importance weight tuning method and a car assignment policy based on service area are introduced.

AB - Genetic Network Programming (GNP) was proposed several years ago as a new evolutionary computation method. Its unique features, such as highly compact structure, potential memory function, etc, are verified by many studies mainly on virtual world problems. Recently, GNP is also applied to some complicated real world problems like Elevator Group Supervisory Control Systems (EGSCS) and stock price prediction systems. As we know, EGSCS is a very large scale stochastic dynamic optimization problem. Due to its vast state space, significant uncertainty and numerous resource constraints such as finite car capacities and registered hall/car calls, it is hard to manage EGSCS using conventional control methods. In this paper, we propose an enhanced algorithm of EGSCS using GNP with Reinforcement Learning (RL) where an importance weight tuning method and a car assignment policy based on service area are introduced.

KW - Elevator group supervisory control system

KW - Genetic network programming

KW - Importance weight

KW - Reinforcement learning

KW - Service area

UR - http://www.scopus.com/inward/record.url?scp=34250739426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250739426&partnerID=8YFLogxK

U2 - 10.1109/SICE.2006.315839

DO - 10.1109/SICE.2006.315839

M3 - Conference contribution

AN - SCOPUS:34250739426

SN - 8995003855

SN - 9788995003855

SP - 5967

EP - 5972

BT - 2006 SICE-ICASE International Joint Conference

ER -