基于免疫支持向量机方法的电力系统短期负荷预测

A SHORT-TERM LOAD FORECASTING APPROACH BASED ON IMMUNE SUPPORT VECTOR MACHINES

在对支持向量机(Support Vector Machines,SVM)方法的参数性能进行分析的基础上,提出了一种免疫支持向量机方法来预测电力系统短期负荷,其中利用免疫算法来优化支持向量机方法的参数。免疫算法是根据人类或其它高等动物免疫系统的机理而设计的,通过仿真抗原和抗体之间的相互作用过程,有效地克服了未成熟收敛现象,提高了群体的多样性。电力系统短期负荷预测的实际算例表明,与支持向量机方法相比,本文所提免疫支持向量机方法具有更高的预测精度。

On the basis of analyzing the parameter performance of support vector machine (SVM), an immune support vector machines method for short-term load forecasting is presented in which the parameters in SVM method are optimized by immune algorithm. Through the simulation of interaction between antigens and antibodies the immune algorithm, which is designed according to mechanism of the immune systems of human and other mammals, can effectively surmount the premature convergence and promote the diversity of colony. The calculation results from short-term load forecasting example of actual power network show that the presented immune SVM method can offer more accurate forecasting result than SVM method.