Traffic Prediction for Efficient Elevator Dispatching

摘要

Group elevator dispatching has received more and more attentions as its importance for the transportation efficiency of a high-rise building. The major obstacle that prevents the optimization of the elevator dispatching is the uncertain traffic flow of passengers. In this paper, we propose a machine-learning based algorithm to analyze the historical traffic data and then derive a statistical traffic model to represent the generic distribution of traffic flow. Based on the statistical traffic model, all possible dispatching schemes of an elevator group are enumerated. To simulate the cooperation among elevators, a platform with continuous lift movement and coming passengers is built up. The dispatching scheme that can minimize the passengers time cost as well as the total energy consumption of lifts will be selected. The proposed technology would improve the lift efficiency and provide better user experience.