基于改进OLS-RBF神经网络模型的短期风电场出力预测  

Short-term forecasting of wind power output based on improved OLS-RBF ANN model

作　　者：洪翠[1] 温步瀛[1] 林维明[1] 

机构地区：[1]福州大学电气工程与自动化学院,福建福州350108

出　　处：《电力自动化设备》2012年第9期40-43,59,共5页Electric Power Automation Equipment

基　　金：福建省青年科技人才创新项目(2011J05124);福建省教育厅A类项目(JA08024)~~

摘　　要：介绍了基于正交最小二乘(OLS)方法构造径向基函数(RBF)神经网络模型的基本思想,分析了传统OLS-RBF模型对基函数宽度初值的敏感性。采用梯度下降法调整和确定基函数宽度初值,有效降低其对网络的影响。以风电场的风速和环境温度作为预测输入,分别采用改进模型与传统模型对福建某沿海风电场的短期出力进行了预测,研究结果表明,改进的OLS-RBF模型预测结果更加准确,精度较高。The basic concept of RBF（Radial Basis Function） ANN model based on OLS（Orthogonal Least Squares） method is presented and the sensitivity of the traditional OLS-RBF model to the initial width of basic function is analyzed.The gradient descent method is applied to adjust and decide the initial width of basic function,which effectively reduces its impact on network.With the wind speed and environment temperature as inputs,the power output of a coastal wind farm in Fujian is forecasted by the improved model and traditional model respectively,which shows that,the improved model has better precision and accuracy.

关 键 词：短期风电出力预测 改进OLS-RBF神经网络 梯度下降法 风电 预测 神经网络 模型 

分 类 号：TM614[电气工程—电力系统及自动化]