双语论文讲解文稿.docx

Dynamic forecast of daily urban water consumption using variable-structure support vector regression model.基于变结构支持向量回归的城市日用水量预测When we see the title what kind of questions you will ask ? A reliable forecasting model for daily water consumption would provide the data basis for regulating urban water supply facilities. In this paper, a variable-structure support vector regression (VS-SVR) model is developed for dynamic forecast of the water consumption. The complexity of urban water supply systems has been increasing recently, leading to unprecedented challenges for the regulation of water resources.The optimal scheduling process typically consists of water consumption forecasting, working-process simulation and scheduling decision-making. Among them, the water consumption forecast is the core of the process and is often regarded as one of the most critical issues in water supply enterprises.最小二乘支持向量回归机（Least Squares Support Vector Regression-LSSVR）扩展卡尔曼滤波器（Extended Kalman Filter，EKF）After viewing these logic charts above, did they leave something in your mind ? To be honest ,when I see these things for the first time, I were already confused by the professional vocabulary and formulas. As for you and me , I think a detailed example would be a better choice to help us understand this model and may further understand how it operates.Application example :We are trying to do some analysis on a water supply company which located at Yongchuan District from January to June in 2012. From this period, we can do some forecasts to these 180 days’ water consumption , then these turn into 180 date, as the figure1.1 shows :图 1变结构支持向量回归日用水量预测模型结构Fig． 1Structure of daily water consumption forecasting model based on variable-structure LSSVMThe Procedure of how to create models and forecast :Step one : Grouping -daily urban water consumption of 180 days. Generally speaking, 70-90 % of whole date will be used into modeling, then the rest will be the test date and check the veracity of