Urban Water Consumption Forecast Based on QPSO-RBF Neural Network

Accurate forecast of urban water consumption is the basis of urban water supply network planning and design, and provides a scientific basis for water production and scheduling. Because the convergence speed of RBF neural network and accuracy of urban water consumption forecast based on RBF neural network are too low, we proposed a new forecast method based on QPSO-RBF neural network. In this method, the parameters of RBF neural network are optimized by QPSO, and then used the QPSO-RBF neural network to forecast urban water daily consumption. The experimental results show that both convergence speed and accuracy of the proposed method are better than the method based on RBP and PSO-RBF neural network.