基于时间序列和神经网络法的风电功率预测

为克服风速与风电功率之间的非线性关系对预测精度的影响,建立了基于时间序列法和神经网络法的改进预测模型。用时间序列法建立风速预测模型;利用神经网络法建立风速-风电功率模型,并以风速预测数据为输入量预测风电功率。以某风电场为例,比较分析了该改进模型与传统预测模型的平均绝对误差和相关系数,结果表明该改进预测模型可有效提高预测精度。

Wind power prediction based on time-series and BP-ANN

To solve the problem that non-linear relationship between wind speed and wind power could amplify prediction error, the improved model for wind speed and wind power forecasting in short term was proposed based on time series and back propagation artificial neural network (BP ANN). First, the time series model was built to forecast wind speed. Then the BP-ANN model of wind speed-to-power was set up and the predicted wind speed was input into the model to obtain wind power. Taking a wind power plant as an example, mean absolute error and correlation index of the improved model and the conventional model were compared, and the result showed that the improved model could improve wind power forecasting accuracy.