Elevator group supervisory control system using genetic network programming with macro nodes and reinforcement learning

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

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Elevator Group Supervisory Control System (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. Recently, many solutions for EGSCS using Artificial Intelligence (AI) technologies have been reported. Genetic Network Programming (GNP), which is proposed as a new evolutionary computation method several years ago, is also proved to be efficient when applied to EGSCS problem. In this paper, we propose an extended algorithm for EGSCS by introducing Reinforcement Learning (RL) into GNP framework, and an improvement of the EGSCS' performances is expected since the efficiency of GNP with RL has been clarified in some other studies like tile-world problem. Simulation tests using traffic flows in a typical office building have been made, and the results show an actual improvement of the EGSCS' performances comparing to the algorithms using original GNP and conventional control methods. Furthermore, as a further study, an importance weight optimization algorithm is employed based on GNP with RL and its efficiency is also verified with the better performances.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume127
Issue number8
Publication statusPublished - 2007

Fingerprint

Elevators
Reinforcement learning
Computer programming
Macros
Control systems
Railroad cars
Office buildings
Tile
Evolutionary algorithms
Artificial intelligence

Keywords

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

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Elevator group supervisory control system using genetic network programming with macro nodes and reinforcement learning. / Zhou, Jin; Yu, Lu; Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki; Markon, Sandor.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 127, No. 8, 2007.

Research output: Contribution to journalArticle

@article{43473297b9a0474e9da141b8c7e3106b,
title = "Elevator group supervisory control system using genetic network programming with macro nodes and reinforcement learning",
abstract = "Elevator Group Supervisory Control System (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. Recently, many solutions for EGSCS using Artificial Intelligence (AI) technologies have been reported. Genetic Network Programming (GNP), which is proposed as a new evolutionary computation method several years ago, is also proved to be efficient when applied to EGSCS problem. In this paper, we propose an extended algorithm for EGSCS by introducing Reinforcement Learning (RL) into GNP framework, and an improvement of the EGSCS' performances is expected since the efficiency of GNP with RL has been clarified in some other studies like tile-world problem. Simulation tests using traffic flows in a typical office building have been made, and the results show an actual improvement of the EGSCS' performances comparing to the algorithms using original GNP and conventional control methods. Furthermore, as a further study, an importance weight optimization algorithm is employed based on GNP with RL and its efficiency is also verified with the better performances.",
keywords = "Elevator group supervisory control system, Genetic network programming, Importance weight, Reinforcement learning",
author = "Jin Zhou and Lu Yu and Shingo Mabu and Kotaro Hirasawa and Takayuki Furuzuki and Sandor Markon",
year = "2007",
language = "English",
volume = "127",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "8",

}

TY - JOUR

T1 - Elevator group supervisory control system using genetic network programming with macro nodes and reinforcement learning

AU - Zhou, Jin

AU - Yu, Lu

AU - Mabu, Shingo

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Markon, Sandor

PY - 2007

Y1 - 2007

N2 - Elevator Group Supervisory Control System (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. Recently, many solutions for EGSCS using Artificial Intelligence (AI) technologies have been reported. Genetic Network Programming (GNP), which is proposed as a new evolutionary computation method several years ago, is also proved to be efficient when applied to EGSCS problem. In this paper, we propose an extended algorithm for EGSCS by introducing Reinforcement Learning (RL) into GNP framework, and an improvement of the EGSCS' performances is expected since the efficiency of GNP with RL has been clarified in some other studies like tile-world problem. Simulation tests using traffic flows in a typical office building have been made, and the results show an actual improvement of the EGSCS' performances comparing to the algorithms using original GNP and conventional control methods. Furthermore, as a further study, an importance weight optimization algorithm is employed based on GNP with RL and its efficiency is also verified with the better performances.

AB - Elevator Group Supervisory Control System (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. Recently, many solutions for EGSCS using Artificial Intelligence (AI) technologies have been reported. Genetic Network Programming (GNP), which is proposed as a new evolutionary computation method several years ago, is also proved to be efficient when applied to EGSCS problem. In this paper, we propose an extended algorithm for EGSCS by introducing Reinforcement Learning (RL) into GNP framework, and an improvement of the EGSCS' performances is expected since the efficiency of GNP with RL has been clarified in some other studies like tile-world problem. Simulation tests using traffic flows in a typical office building have been made, and the results show an actual improvement of the EGSCS' performances comparing to the algorithms using original GNP and conventional control methods. Furthermore, as a further study, an importance weight optimization algorithm is employed based on GNP with RL and its efficiency is also verified with the better performances.

KW - Elevator group supervisory control system

KW - Genetic network programming

KW - Importance weight

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=34548235792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548235792&partnerID=8YFLogxK

M3 - Article

VL - 127

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 8

ER -