DocumentCode :
685033
Title :
Research of elevator group scheduling system based on reinforcement learning algorithm
Author :
Liu Zheng ; Shu Guang ; Dong Hui
Author_Institution :
Dept. of Comput. Sci. & Technol., Harbin Univ. of Sci. & Technol., Harbin, China
Volume :
01
fYear :
2013
fDate :
16-18 Aug. 2013
Firstpage :
606
Lastpage :
610
Abstract :
Elevator group control system (EGCS) is a complex decision-making system, which has characteristics of multi-objective, randomness and nonlinear. It is difficult to adopt precise mathematical models describing. This paper introduces a new elevator dynamic scheduling system based on reinforcement learning algorithm. We trade reinforcement learning algorithm as the way to learn the optimal strategy in the course of interacting with the environment. Average waiting time and average riding time are optimized indicators. Combine with the value iteration algorithm called Q-learning to construct the whole algorithm for elevator group scheduling. The simulation result shows great superior and feasibility for elevator dynamic scheduling system based on reinforcement learning algorithm.
Keywords :
decision making; iterative methods; learning (artificial intelligence); lifts; scheduling; EGCS; Q-learning; average riding time; average waiting time; complex decision-making system; elevator dynamic scheduling system; elevator group control system; elevator group scheduling system; multiobjective characteristics; nonlinear characteristics; randomness characteristics; reinforcement learning algorithm; value iteration algorithm; Acceleration; Dynamic scheduling; Elevators; Heuristic algorithms; Silicon; TV; Q-learning; elevator group control system; reinforcement learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Measurement, Information and Control (ICMIC), 2013 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4799-1390-9
Type :
conf
DOI :
10.1109/MIC.2013.6758037
Filename :
6758037
Link To Document :
بازگشت