基于最小二乘支持向量机的短期负荷预测  

Short-term Load Forecasting Based on Least Squares Support Vector Machine

作　　者：杨卓[1] 

机构地区：[1]广西电力工业勘察设计研究院,广西南宁530023

出　　处：《企业科技与发展（下半月）》2010年第5期25-27,30,共4页

摘　　要：支持向量机是一种基于统计学理论的新颖的机器学习方法,该方法被广泛用于解决分类和回归问题。文章将最小二乘支持向量机(LS-SVM)算法应用于电力系统短期负荷预测中,并将其预测结果和BP神经网络的预测结果进行比较分析。仿真实验表明,该方法在短期负荷预测中具有很好的预测速度和精度。Support vector machine（SVM ） is a kind of novel machine learning methods based on statistical learning theory. It is widely used for questions of classification and regression. This article applies LS-SVM to short-term load forecasting of power system and compares the forecasting result with that of the BP nerve network. Simulation experiments show that this method enjoys good forecasting speed and accuracy in short-term load forecasting.

关 键 词：最小二乘支持向量机 回归 电力系统 短期负荷预测 

分 类 号：TM714[电气工程—电力系统及自动化]