基于主成分分析的PSO-BP模型在城市需水预测中的应用

Application of PSO-BP Model Based on Principal Component Analysis in Prediction of Urban Water Demand

针对城市需水预测模型中需水量影响因子多、影响因子之间普遍存在多重共线问题以及BP神经网络收敛速度慢、易陷入局部最优等缺点,提出一种由主成分分析、粒子群算法及BP神经网络三者相结合的改进预测模型。以泰州市为实例,建立以主成分分析筛选需水量主要影响因子,粒子群优化BP网络连接权值和阈值的需水预测模型,将预测结果与BP神经网络预测模型预测结果作对比。结果表明:改进预测模型预测值与实际泰州市需水量吻合良好且训练速度更快、预测精度更高,可作为需水预测的一种有效方法。

Aiming at the shortcomings of multiple water demand factors in urban water demand forecasting model,the multicollinearity between impact factors,and the shortcomings of BP neural network such as slow convergence speed and easy to fall into local optimum,this paper proposes an improved prediction model combining principal component analysis,particle swarm optimization and BP neural network.Taking Taizhou City as an example,a water demand forecasting model was constructed by using principal component analysis to select the main influencing factors of water demand,particle swarm optimization BP network connection weights and threshold,and the prediction results were compared with the prediction results of BP neural network prediction model.The results show that the predicted value of the improved prediction model is in good agreement with the actual water demand of Taizhou City,and the training speed is faster and the prediction accuracy is higher.It can be used as an effective method for water demand forecasting.