電梯群控系統(Elevator Group Control System，以下簡稱EGCS)所面對的問題是如何在連續、即時的動態環境中，作出聰明的電梯指派。相同的一組乘客搭乘順序與時間，會因為系統排程(Scheduling)、並行運行(Concurrency)等因素，而會有不一樣的結果(如等待時間、搭乘時間及擁擠度)。而且電梯控制系統更必須在即時與動態的環境中，不停地做出聰明的派車決定。另外派車決定的前後順序也會彼此互相影響。
由於在EGCS所考慮的變數及狀況相當複雜，本研究選擇使用基因演算法(Genetic Algorithms)－一種多點推測的搜尋方法，可找出逼近函數的最佳解，來做派車決定。我們利用JAVA語言多執行緒(Multi-threading)的功能，實作了的電梯模擬系統。然後用基因演算法來決定適當之派車。經由實驗，我們比較了使用最短路徑做為派車的EGCS，以及使用基因演算法派車的EGCS，後者展現了較佳的效能。

The problem of Elevator Group Control System (EGCS) is how to schedule elevators smartly and continuously in a dynamic and real-time environment. Because it is a concurrent system, slightly differences in system scheduling can produce different results. For example, same test cases may yield different results in average riding time, average waiting time, or crowdedness of passengers. Such phenomenon poses great challenge to EGCS.
Because there are too many factors must take into consideration by EGCS, we use Genetic algorithm to control the elevators of EGCS, which has been known as an effective approach to find near-optimal solutions. We implement an elevator simulation system using Java’s multi-threading constructs. On which, we experiment two methods: (1) using Genetic algorithm to schedule the elevators. (2) using shortest distance to schedule the elevators. We compare the results and conclude that the approach using Genetic algorithm yields better results.

[1] Atsuya Fujino, Toshimitsu Tobita, and Kazuhiro Segawa et al., “An Elevator Group Control System with Floor Attribute Control Method and system Optimization Using Genetic Algorithms,” Proceedings of the IEEE IECON 21st International Conference on Industrial Electronics, Control, and Instrumentation, vol. 2, pp.1502-1507, 1995.
[2] Atsuya Fujino, Toshimitsu Tobita, and Kazuhiro Segawa et al., “An Elevator Group Control System with Floor-Attribute Control Method and system Optimization Using Genetic Algorithms,” IEEE Transactions on Industrial Electronics, vol. 44, issue 4, pp.546-552, 1997.
[3] BARNEY, G.C., and DOS SANTOS, S.M., “Elevator Traffic, Analysis, Design and Control,” Peter Peregrinus, London, 1985.
[4] Chang Bum Kim, Kyoung A. Seong, Hyung Lee-Kwang, Jeong O. Kim, Yong Bae Lim, “A Fuzzy Approach to Elevator Group Control System,” IEEE Transactions on System, Man and Cybernetics, vol. 25, issue 6, pp.985-990, June 1995.
[5] Chang Bum Kim, Kyoung A. Seong, Hyung Lee-Kwang et al., “Design and Implementation of a Fuzzy Elevator Group Control System,” IEEE Transactions on System, Man, and Cybernetics Part A vol. 28, issue 3, pp.277-287, May 1998.
[6] ERMAN, L.D., LONDON, P.E., and FICKAS, S.F., “The Design and Example Use of Hearsay-III,” Proceedings IJCAI-81, 409-415, 1981.
[7] G. G. Clard, P. Mebta and R. Prowse, “Knowledge-based Elevator Controller,” International Conference on Control, vol. 1, pp. 42-47, 1994.
[8] Goldberg, D. E. “Genetic Algorithms in Search, Optimization, and Machine Learning,” Addison-Wesley Publishing Company, Inc. 1989.
[9] Grantham K.H. Pang, Biswajit nandy, “Intelligent Scheduling of Group of Elevators,” Proceedings. IEEE International Conference on Control, pp.144-149, 1989.
[10] HAYES-ROTH, B., “A Blackboard Architecture for Control,” Artificial Intelligence, 26, 251-321, 1985.
[11] IGARASHI. Kazuyuki, TAKE. Seiji and ISHIKAWA. TOMO, “Supervisory Control for Elevator Group with Fuzzy Expert System,” Proceedings of the IEEE International Conference on Industrial Technology, pp.133-137, 1994.
[12] John H. Holland. “Adaptation in Natural and Artificial Systems: 2nd edition.” MIT Press. 1992. Review: The original work on genetic algorithms, from their inventor, updated in a 2nd edition. (First edition published 1975)
[13] Ming Ho and Brent Robertson, “Elevator Group Supervisory Control Using Fuzzy Logic,” Proceedings. Canadian Conference on Electrical and Computer Engineering, vol. 2, pp.825-828, 1994.
[14] Naoki Imasaki, Susumu Kubot, Shoji Nakait, tatsuo Yoshitsugu, Jun-ichi Kiji and Tsunekazu Endo, “Elevator Group Control System Tuned by A Fuzzy Neural Network Applied Method,” IEEE 1995, 1735-1740.
[15] NII, H.P., “Blackboard System : The Blackboard Model of Problem Solving and the Evolution of Blackboard Architecture,” The AI magazine, Part I, Summer 1986, 38-53. Part II , August 1986, 82-106.
[16] Shintaro Tsuju and Masaaki Amono, “Application of the Expert System to Elevator Group-Supervisory Control,” Proceedings. Fifth Conference on Artificial Intelligence for Applications, pp.287-294, 1989.
[17] Toshimitsu Tobita, Atsuya Fujino, Kazuhiro Segawa et al., “A Parameter Turing Method using Genetic Algorithms for An Elevator Group System,” Proceedings of the IEEE IECON 22nd International Conference on Industrial Electronics, Control, and Instrumentation, vol. 2, pp.823-828, 1996.
[18] Toshimitsu Tobita, Atsuya Fujino, H.Inaba, K,Yoneda and T.Ueshima, “An Elevator Characterized Group Supervisory Control System,” IECON’91, IEEE 1991, 1972-1976.
[19] T. Yamaguchi, T.Endo and k. Haruki, “Fuzzy Predict and Control Method and Its Application,” proceedings. IEEE International Conference on Control, pp.287-292, 1988.
[20] Yaochu Jin, Jingping Jiang, Jing Zhu, “Neural Network based Fuzzy Identification and Its Application to Modeling and Control of Complex System,” IEEE 1995, 990-985.
[21] Yasuyuki Sogawa, Tomo Ishikawa, kazuyuki Igarashi, “Supervisory Control for Elevator Group by Using Fuzzy Expert System which address the Riding Time,” IEEE 1996, 419-424.
[22] Yuan-Wei Ho and Li-Chen Fu “Dynamic Scheduling Approach to Group Control of Elevator System with Learning Ability,” Proceedings. ICRA ‘00 IEEE International Conference on Robotics and Automation, vol. 3, pp.2410-2415, 2000.
[23] Zbigniew Michalewicz, “Genetic Algorithms + Data Structures = Evolution Program” Springer-Verlag 1992
[24] Zhu Deven and Wu Chengdong, “Fuzzy Control of Group Elevator,” Proceedings. TENCON ’93., IEEE Region 10 Conference on computer, Communication, Control and Power Engineering, vol.4, pp.304-307, 1993.