The hybrid predictive model of elevator system for energy consumption

A hybrid predictive method is proposed, in this paper, based on the ARMA model prediction and the RBF neural network prediction to deal with the problem of prediction control of elevator group system for energy consumption. The new prediction method takes the advantages of both ARMA and RBF. The application of the elevator energy consumption prediction is studied in detail. The method can well meet the need of prediction for elevator energy consumption. The practical data are employed for simulation study, the results show that proposed method is feasible for the elevator energy consumption multi-step prediction, it has good predictive performance. Compared with the traditional methods, its prediction speed is faster and the precision is higher. It provides foundation for dispatch decision of elevator group control system which finishes the optimal dispatch of elevator to realize the objective of energy saving.