Mid-long Term Load Forecasting Based on Simulated Annealing and SVM Algorithm

Accurate mid-long term load forecasting can improve the economic and social benefits of power system.The model of support vector machine(SVM) was analyzed,and a new mid-long term load forecasting method based SVM method was proposed in order to overcome the shortcoming that some parameters have to be determined by experience.The simulated annealing algorithm was applied to optimize the parameters in the method.An example proved that the proposed method can efficiently select the parameters of the SVM method.It can reduce the support vector machine modeling training error and testing error.Compared to the method using the default parameters SVM method,the accuracy of load forecasting is effectively improved.