遗传最小二乘支持向量机法预测时用水量

Genetic least squares support vector machine approach to hourly water consumption prediction

为解决传统最小二乘支持向量机采用交叉验证确定参数耗时较长的问题,提出基于遗传算法和最小二乘支持向量机的城市时用水量预测方法.根据城市时用水量序列具有较强相关性的特点,利用自相关系数法分析时用水量序列的变化规律,并引入二进制编码的自适应遗传算法优化最小二乘支持向量机的超参数,采用交叉验证法确定遗传算法个体的适应值,建立了时用水量预测模型.实例分析表明:与基于传统最小二乘支持向量机的时用水量预测方法相比,基于遗传算法和最小二乘支持向量机的时用水量预测方法计算速度更快,预测精度更高.

As traditional least squares support vector machine（LSSVM） parameter selection using cross-validation is time-consuming,a city hourly water consumption forecasting method based on genetic algorithm（GA） and LSSVM was proposed.An autocorrelation method was used to analyze the hourly water consumption series according to the strong serial correlation.A self-adaptive binary GA was introduced to optimize the hyper-parameters of LSSVM,and the individual fitness values in GA were determined by cross-validation.Then a hourly water consumption forecasting model was built.Case study shows that the proposed hourly water consumption forecasting method based on GA and LSSVM has higher computing speed and better estimating performance than the traditional LSSVM–based method.