LS-SVM在澜沧江水库群运行调度中的应用研究

Application of LS-SVM in the Operation and Scheduling of Reservoirs in Lancang River

利用最小二乘支持向量机(LS-SVM)的径流预测方法建立澜沧江月径流预测模型,对月径流进行预测,与季节性水平模型预测结果进行对比,并将预测结果运用于澜沧江水库群调度。结果表明,基于最小二乘支持向量机的模拟预测训练期和预测应用期的模型效率系数分别高达80%和88%,年均最大和最小径流相对误差仅为10%,精度较季节性水平模型更高,说明将最小二乘支持向量机用于澜沧江月径流预测是可行的,可满足澜沧江水库群调度的需要。

A monthly runoff prediction model for Lancang River is established by using least squares support vector machine （ LS-SVM）. The monthly runoff is predicted and compared with the results of seasonal level model, and the forecast results are applied to the scheduling of reservoirs in Lancang River. The results show that the efficiency coefficients of LS-SVM model are 80% and 88% respectively, and the relative errors of maximum and minimum runoff are all only 10% which is more accurate than seasonal level model. The application of LS-SVA model in monthly runoff prediction of Laneang River is feasible, and the model can meet the needs of the operation and scheduling of reservoirs in Lancang River.