基于RBF-BP组合神经网络的短期风电功率预测研究  

Short-term wind power forecasting based on RBF-BP neural network

作　　者：张靠社[1] 罗钊[1] 

机构地区：[1]西安理工大学水利水电学院,陕西西安710048

出　　处：《可再生能源》2014年第9期1346-1351,共6页Renewable Energy Resources

基　　金：国家电网公司科技资助项目(5227221302A2;5227221303A0)

摘　　要：为提高风电输出功率预测精度,提出一种基于RBF-BP组合神经网络模型的短期风电功率预测方法。在考虑尾流等因素影响的基础上,对风速进行预处理。根据相关历史数据,建立RBF-BP组合神经网络短期风电功率预测模型,对风电输出功率进行预测。仿真分析结果表明,该预测方法能有效提高风电输出功率预测精度。In order to improve precision of wind farm output power forecasting, a short-term power forecasting method based on RBF-BP combined neural network model is proposed. By considering wake and terrain factors, wind speed is pretreated. According to historical data, a short-term power forecasting model is established to predict the output power based on RBF-BP combined neural network. The simulation results show that this method can effectively improve prediction accuracy of the output Dower.

关 键 词：尾流 地势 RBF—BP组合神经网络 短期风电功率预测 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程]