基于卷积神经网络特征提取的风电功率爬坡预测

为提高风电功率爬坡预测的准确性,提出了一种基于卷积神经网络、长短期记忆网络和注意力机制的风电功率爬坡预测方法。首先,针对风电功率爬坡发生次数少、特征复杂、预测模型难以对小样本爬坡事件有效学习的问题,使用卷积神经网络对风电功率序列进行特征提取。然后,使用长短期记忆网络建立预测模型,解决风电功率的长时依赖问题,并在模型中加入注意力机制对长短期记忆网络单元的输出进行加权,从而加强风电特征的学习,提高爬坡预测准确度。仿真验证表明,模型对风电功率爬坡预测有较高的准确性。

Wind Power Ramp Forecast Based on Feature Extraction Using Convolutional Neural Network

To improve the accuracy of wind power ramp forecast, a method based on long short-term memory (LSTM) network, convolutional neural network (CNN) and attention mechanism (AM) is proposed. Wind power ramp event rarely occurs and has complex characteristics, and it is difficult for forecast model to effectively learn from small number of ramp event samples. So CNN is used to extract features in wind power time series. And the LSTM network is used to build forecasting model to solve the long-term dependence of wind power. Then AM is added to the model to weight outputs of LSTM network units to strengthen the learning of wind power features, thus improving the accuracy of ramp forecast. The simulation results show that the forecasting model has high accuracy on wind power ramp forecast.