Research and application of a combined neural network model for prediction of urban water use quantity
Back Propagation(BP)neural network model is influenced by multiple factors while predicting water use quantity,and tends to result in local optima.In order to solve these problems,this paper proposes a model to predict water use quantity based on the neural network,which combines Principal Component Analysis(PCA),Improved Particle Swarm Optimization(IPSO)and BP(or PCA-IPSO-BP in short).Firstly,a nonlinear asyn-chronous learning factor based on sinusoidal function is proposed to improve the Particle Swarm Optimization(PSO),so the Improved Particle Swarm Optimization(IPSO)algorithm is formed.Then the water use quantity factor is selected by PCA,and the BP neural network is optimized by IPSO algorithm.Finally,based on the water use quantity data of Urumqi from 2005 to 2020,the model is applied to simulate and predict water use quantity.The results show that the 14 factors related to economy,population,climate and water use efficiency can be re-placed by the principal components F1,F2 and F3 after dimensionality reduction.The PCA-IPSO-BP neural net-work model converges fastest and has the smallest fitness value.Its Root Mean Squared Error(RMSE),Mean Ab-solute Error(MAE),and Mean Absolute Percentage Error(MAPE)of the water use quantity simulation are 0.103×108 m3,0.093× 108 m3,and 0.89％,respectively.There is a trend of increasing water use quantity in the future,and the water use quantity is expected to increase to 12.58× 108 m3 in 2025,13.98×108 m3 in 2030 and 14.31×108 m3 in 2035.The model eliminates the redundant information between the factors and improves the prediction accuracy.The IPSO algorithm based on nonlinear asynchronous learning factors effectively avoids the local optima of the mod-el.The model can provide a new method for prediction of urban water use quantity.
water use quantity predictionPrincipal Component AnalysisBP neural network modelImproved Particle Swarm OptimizationUrumqi
万方数据
维普
