基于Elman神经网络的短期风电功率预测

为提高风电场输出功率预测精度，提出一种动态基于神经网络的功率预测方法。根据实际运行的风电场相关风速、相关风向和风电功率的历史数据，建立了基于Elman神经元网络的短期风电功率预测模型。运用多层Elman神经网络模型对西北某风电场实际1h和24h的风电输出功率预测，与BP神经网络模型对比，经仿真分析证明前者具有预测精度高的特点，三隐含层Elman神经网络模型预测效果最佳。这表明利用Elman回归神经网络建模对风电功率进行预测是可行的，能有效提高功率预测精度。

Short-Term Wind Power Forecasting Based on the Elman Neural Network

In order to improve the precision of wind farm power outputs forecasting, an artificial neural network （ANN） approach for power forecasting is proposed. Based on historical data from an operating wind farm such as wind speed, wind direction, wind power and so on, a short-term wind power forecasting model based on the well-developed Elman neural network is presented for forecasting. The multilayer Ehnan neural network model is used for a certain wind farm in the Northwest region for the actual 1 h and 24 h wind power prediction, and compared with the BP neural network model. The simulation and analysis prove that the former has a high forecasting precision while the three-hidden-layer Elman neural network has the best prediction effect. The simulation resuhs show that the method is feasible, and effective in improving the precision of power forecasting.