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. This study analyes different traffic patterns and control mechanisms,and proposes a real-time particle swarm optimization(RPSO ) as an optimal solution to the EGOS scheduling problem. Simulation results show that distributed EGOS using RPSO can be scheduled well. Besides, the elevalor real-time scheduling and re-allocation functions are realized in case the elevator is unavailable or full. RPSO algorithm can reduce the waiting time of the passengers by almost 50 0 0 , and reduce passengers' riding time by almost one third.

Key words: Elevator group control system, Distributed, Real-time particle swarm optimization, Up-peak