混沌遗传最小二乘支持向量机法预测日用水量

Application of Chaos Genetic Algorithm and Least Squares Support Vector Machine Method in Daily Water Consumption Prediction

利用混沌运动的初值敏感性、内在随机性和遍历性的特点,提出基于混沌遗传算法和最小二乘支持向量机的城市日用水量预测法。通过混沌映射搜索自适应遗传算法的较优初始种群,采用自适应遗传算法优化最小二乘支持向量机的超参数,利用交叉验证法确定遗传算法个体的适应值,建立基于最小二乘支持向量机的日用水量预测模型。实例分析结果表明,与基于遗传最小二乘支持向量机的日用水量预测法相比,提出的预测方法具有更高的预测精度。

Using the characteristics of sensitive dependence on initial conditions, intrinsic stochastic property and ergodicity ot cnaonc motion, a forecasting method for city daily water consumption based on chaos genetic algorithm and least squares support vector machine （LSSVM） is proposed in this paper. The chaotic map is used to search the optimal initial population of self-adaptive genetic al- gorithm （AGA）, the AGA is introduced to optimize the hyper-parameters of LSSVM, and the individual fitness values in AGA are determined by cross-validation. Then the LSSVM-based daily water consumption forecasting model is built. The case study shows that the proposed method based on chaos GA and LSSVM has better estimating performance than the genetic LSSVM-based method.