基于粒子群支持向量机的短期电力负荷预测

A short-term load forecasting approach based on PSO support vector machine

在分析支持向量机SVM(Support VectorM ach ine)回归估计方法参数性能的基础上,提出粒子群算法PSO(Partic le Swarm Optim ization)优化参数的SVM短期电力负荷预测模型。PSO算法是一种新型的基于群体智能的随机优化算法,简单易于实现且具有更强的全局优化能力。用所建立的负荷预测模型编制的M atlab仿真程序,对某实际电网进行了短期负荷预测,结果表明预测精度更高。

On the basis of analyzing the parameter performance of support vector machine （ SVM ） for regression estimation, a shortterm load forecasting method based on SVM is presented in which the parameters in SVM are optimized by particle swarm optimization （PSO）. PSO algorithm is a novel random optimization method based on swarm intelligence which has more powerful ability of global optimization. The experimental results prove that the presented SVM method optimized by PSO can achieve greater accuracy than ordinary SVM method whose parameters are selected with across validation.