Abstract
Multi-Car Elevator (MCE) that has several elevator cars in a single shaft attracts attention for improvement of transportation in high-rise buildings. However, because of lack of experience of such novel systems, design of controller for MCE is very difficult engineering problem. One of the promising approaches is application of evolutionary optimization to from-scratch optimization of the controller through discrete event simulation of the MCE system. In the present paper, the authors propose application of evolutionary multi-objective optimization to design of traffic-sensitive MCE controller. The controller for MCE is optimized for different traffic conditions in multi-objective way. By combining the multi-objective optimization with the exemplar-based policy (EBP) representation that has adequate flexibility and generalization ability as a controller, we can successfully design a controller that performs well both in the different traffic conditions and works adequately by generalization in the conditions not used in the optimization process.
Keywords
- Feature Vector
- Generalization Ability
- Policy Representation
- General Floor
- Elevator Shaft
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Beielstein, T., Ewald, C.P., Markon, S.: Optimal elevator group control by evolution strategies. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2724, pp. 1963–1974. Springer, Heidelberg (2003)
Deb, K., Arawal, S., Pratap, A., Meyarivan, T.: Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimization: NSGA-II. In: Deb, K., Rudolph, G., Lutton, E., Merelo, J.J., Schoenauer, M., Schwefel, H.-P., Yao, X. (eds.) Parallel Problem Solving from Nature-PPSN VI. LNCS, vol. 1917, pp. 849–858. Springer, Heidelberg (2000)
Ikeda, K.: Exemplar-Based Direct Policy Search with Evolutionary Optimization. In: Congress on Evolutionary Computation, pp. 2357–2364 (2005)
Ikeda, K., Kobayashi, S.: Deterministic Multi-Step Crossover Fusion: A Handy Crossover Composition for GAs. In: Parallel Problem Solving from Nature, pp. 162–171 (2002)
Ikeda, K., Suzuki, H., Markon, S., Kita, H.: Evolutionary Optimization of a Controller for Multi-Car Elevators. In: International Conference on Industrial Technology (accepted, 2006)
Kim, C.B., Seong, K.A., Lee-Kwang, H., Kim, J.O.: Design and implementation of a fuzzy elevator group control system. IEEE Transactions on Systems, Man, and Cybernetics, Part A 28(3), 277–287 (1998)
Kita, H., Markon, S., Sudo, T., Suzuki, H.: A Study on Control of Multi-Car Elevators (in Japanese). In: SICE Symposium on Autonomous and Decentralized System, pp. 63–66 (2002)
Mimaki, K., Markon, S., Kita, H., Komoriya, Y., Nishikawa, Y.: Modeling and Analysis of Complex Traffic in Buildings. In: Proc. IEEE SMC’99, pp. 589–594. IEEE Computer Society Press, Los Alamitos (1999)
Obayashi, S., Sasaki, D.: Multi-Objective Optimization for Aerodynamic Designs by Using ARMOGAs. In: 7th Intr. Conf. on High Performance Computing and Grid in Asia Pacific Region (2004)
Ono, I.: A Real-coded Genetic Algorithm for Function Optimization Using Unimodal Normal Distribution Crossover. In: Proc. of 7th Intr. Conf. on Genetic Algorithms, pp. 246–253 (1997)
Sudo, T., Suzuki, H., Markon, S., Kita, H.: Effectiveness and control strategies of multi-car elevators for high-rise buildings (in Japanese). In: TRANSLOG02 (2002)
Takahashi, S., Kita, H., Suzuki, H., Sudo, T., Markon, S.: Simulation-based Optimization of a Controller for Multi-Car Elevators Using a Genetic Algorithm for Noisy Fitness Function. In: Congress on Evolutionary Computation, pp. 1582–1587 (2003)
Zhou, J., Eguchi, T., Hirasawa, K., Hu, J., Markon, S.: Elevator group supervisory control system using genetic network programming with reinforcement learning. In: IEEE Congress on Evolutionary Computation, vol. 1, pp. 336–342. IEEE, Los Alamitos (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Ikeda, K., Suzuki, H., Markon, S., Kita, H. (2007). Designing Traffic-Sensitive Controllers for Multi-Car Elevators Through Evolutionary Multi-objective Optimization. In: Obayashi, S., Deb, K., Poloni, C., Hiroyasu, T., Murata, T. (eds) Evolutionary Multi-Criterion Optimization. EMO 2007. Lecture Notes in Computer Science, vol 4403. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70928-2_51
Download citation
DOI: https://doi.org/10.1007/978-3-540-70928-2_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70927-5
Online ISBN: 978-3-540-70928-2
eBook Packages: Computer ScienceComputer Science (R0)