基于最优输入径向基网络的风电功率预测方法

A wind power prediction method based on RBF neural network with optimal input

随着风电的大规模接入电网,对风电功率未来出力的把握显得尤为重要,而风电功率预测技术则是掌握出力特性的有力工具。基于实测历史数据,研究系统不同输入量对预测结果误差的影响,选取最佳输入量值;并在此基础上,构建基于RBF(径向基)神经网络的风电功率预测模型,对风电功率进行有效预测;预测结果表明,基于径向基神经网络的预测方法预测精度较高,可以为电网提供更加准确的风电预测出力信息,有助于为调度制定更加合理有效的计划。

With large-scale integration of wind power in power grids,it is of great importance to grasp the characteristics of future wind power output.Wind power forecasting is a useful tool to investigate the characteristics.Based on the historical data,this paper investigated the influence of different system input on the predicting error in order to get the best input values,and then constructed a wind power prediction model based on RBF （radial basis function）neural network. The prediction results showed that the wind power forecasting method based on the RBF neural network hadhigh precision.The results can provide more accurate information of wind power future output for the power system.The proposed power prediction method can be used to make more reasonable dispatching plans.