城市生活用水量的支持向量回归预测

SVM-Based Prediction of City Municipal and Domestic Water Consumption

城市生活用水量预测在城市水资源利用和节约用水规划管理中起着非常重要的作用。建立了支持向量机(SUPPORT VESTORM ACH INE,SVM)理论的城市生活用水量预测模型,该模型以统计学习理论为基础,利用天津市历年来城市生活用水量数据进行实例验证,并与人工神经网络方法所取得的结果进行比较,证明支持向量机方法能取得更好的效果,为城市用水管理部门制定用水规划提供了有效和可信的理论支持。

The prediction of city municipal and domestic water consumption plays an important role in utilization of urban water resources. This paper first sets up a prediction model of city municipal and domestic water consumption based on support vector machine （SVM）, and then applies the method to water consumption of Tianjin. In comparison with artificial neural network, the method of SVM is proved to be much better. The study will provide an effective and creditable theoretical support for water consumption programming.