Intelligent Scheduling System for Elevators Based on Particle Swarm Optimization Algorithm

A elevator scheduling method based on the particle swarm optimization algorithm is proposed to address the dynamics and complexity of the elevator environment and the mutual constraints between multiple objectives. To address the policy optimization challenges arising from dimensional disasters in the elevator state space, a proximal policy optimization algorithm is used to reduce the complexity of training. Simulation results show that the proposed algorithm can achieve optimal control of elevators with very low complexity and resolve the conflict between efficient operation of elevators and fairness of user waiting time.