基于v-SVR的短期电力负荷预测

Power system load forecastingbased on v-support vector regression

提出了一种改进支持向量机(v-SVR)的电力系统短期负荷预测方法;将RBF和多项式函数作为核函数,进行了预测研究。研究结果表明,方法要比BP和模糊聚类方法具有很高的预测精度,方法是可行和有效的。

A new short-term load forecasting method for power system based on Support Vector Machine is presented. Using the polynomial function and radial base function as kernel function, the research of applying the SVM method to power system load forecasting,The forecasted results are compared with those BP artificial neural network method and Fuzzy Cluster method, and it is shown that the presented forecasting method is more accurate. Applying the presented method to actual load forecasting, the comparison among the forecasted results and the true shows that presented method is feasible and effective.