Multi-objective Optimization of Multi-Agent Elevator Group Control System Based on Real-time Particle Swarm Optimization Algorithm
- 1 School of Electronics & Information Engineering, Tongji University, Shanghai, China
Abstract
In order to get a globally optimized solution for the Elevator Group Control System (EGCS) scheduling problem, an algorithm with an overall optimization function is needed. In this study, Real-time Particle Swarm Optimization (RPSO) is proposed to find an optimal solution to the EGCS scheduling problem. Different traffic patterns and controller mechanisms for EGCS are analyzed. This study focuses on up-peak traffic because of its critical importance to modern office buildings. Simulation results show that EGCS based on Multi-Agent Systems (MAS) using RPSO gives good results for up-peak EGCS scheduling problem. Besides, the elevator real-time scheduling and reallocation functions are realized based on RPSO in case new information is available or the elevator becomes busy because it is unavailable or full. This study contributes a new scheduling algorithm for EGCS, and expands the application of PSO.
- P. Robertson, R. Smith and A. Rae, “Lift Traffic Patterns in a Multi-Storey Residential Block,” Applied Ergonomics, Vol. 7, No. 2, 1976, pp. 85-88. doi:10.1016/0003-6870(76)90154-X
- R. H. Crites and A. G. Barto, “Elevator Group Control Using Multiple Reinforcement Learning Agents,” Machine Learning, Vol. 33, No. 3, 1998, pp. 235-262. doi:10.1023/A:1007518724497
- B. Seckinger and J. Koehler, “Online-Synthese von Aufzugssteuerungen als Planungsproblem (In German),” Workshop Planen und Konfigurieren Interner Bericht des Instituts fur Informatik der Universitat Wu rzburg, 1999, pp. 127-134.
- C. Kim, K. Seong, H. Lee-Kwang and J. Kim, “Design and Implementation of a Fuzzy Elevator Group Control System,” IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, Vol. 28, No. 3, 1998, pp. 277-287. doi:10.1109/3468.668960
- D. Zhu, L. Jiang, Y. Zhou, G. Shan and K. He, “Modern Elevator Group Supervisory Control Systems and Neural Networks Technique,” IEEE International Conference on Intelligent Processing Systems, Vol. 1, 1997, pp. 528-532.
- N. Imasaki, S. Kubo, S. Nakai, T. Yoshitsugu, J. I. Kiji and T. Endo, “Elevator Group Control System Tuned by a Fuzzy Neural Network Applied Method,” International Joint Conference of the 4th IEEE International Conference on Fuzzy Systems, Vol. 4, 1995, pp. 1735-1740.
- F. Luo, Y. G. Xu and J. Z. Cao, “Elevator Traffic Flow Prediction with Least Squares Support Vector Machines,” International Conference on Machine Learning and Cybernetics, Vol. 7, 2005, pp. 4266-4270.
- CIBSE Guide D, “Transportation Systems in Buildings,” The Chartered Institution of Building Services Engineers, London, 2010
- M. L. Siikonen, “On Traffic Planning Methodology,” Elevator Technology, Vol. 27, No. 3, 2000, pp. 267-274.
- H. Hakonen and M. L. Siikonen, “Elevator Traffic Simulation Procedure,” Elevator World, Vol. 57, No. 9, 2008, pp. 180-190.
- T. Susi, J. Sorsa and M. L. Siikonen, “Passenger Behaviour in Elevator Simulation,” Elevatori, Vol. 34, No. 5, 2005, pp. 28-37.
- J. Koehler and D. Ottiger, “An AI-Based Approach to Destination Control in Elevators,” AI Magazine, 2002, p. 23.
- X. Qin, H. Jiang, Y. Zhu and D. R. Swanson, “Dynamic Load Balancing for I/O- and Memory-Intensive Workload in Clusters Using a Feedback Control Mechanism,” Proceedings of the 9th International Euro-Par Conference on Parallel Processing, 2003, pp. 224-229.