基于超参数优化和双重注意力机制的超短期风电功率预测  

An Ultra-Short-Term Wind Power Forecasting Method Based on Hyperparameter Optimization and Dual-Stage Attention Mechanism

作　　者：康田雨 覃智君[1] KANG Tianyu;QIN Zhijun(School of Electrical Engineering,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学电气工程学院,南宁530004

出　　处：《南方电网技术》2022年第5期44-53,共10页Southern Power System Technology

基　　金：国家自然科学基金资助项目(51767001)。

摘　　要：高精度的风电功率预测在电力系统的安全稳定运行和能源系统的优化配置中至关重要。为了从多维风电历史数据中提取隐藏信息,准确选择与预测目标高度相关的高维特征,克服时间序列的短时记忆问题,提出了一种以卷积神经网络-双向长短时记忆网络(convolutional neural network and bidirectional long short term memory network,CNN-BiLSTM)为基础模型,结合双重注意力机制和贝叶斯优化算法的风电功率超短期预测模型。首先,为了自主挖掘输入特征与风电功率之间的数据关联,进一步突出重要特征影响,在常规的CNN架构上增加注意力机制,构建特征注意力模块;然后在BiLSTM网络输出端引入注意力机制形成时间注意力模块,增强BiLSTM网络的长时记忆能力,加强重要历史信息的影响;最后,采用贝叶斯优化算法优化所提模型的超参数,选取最优超参数,发挥模型最佳性能。以中国西北某风电场实际数据进行验证,模型的单步预测精度达到95.58%。多步预测结合数值天气预报信息实现4 h前超短期预测,其精度达到90.44%。实验结果表明所提基于超参数优化和双重注意力机制的预测模型相比其他模型具有更高的预测精度。High precision wind power prediction plays an important role in the safe and stable operation of power system and the optimal allocation of energy system.In this paper,in order to extract the hidden information from the multi-dimensional wind power historical data,accurately select the features highly related to the prediction target,and overcome the short-term memory problem of time series,an ultra-short-term wind power forecasting model is proposed which is based on convolutional neural network and bidirectional long short term memory network(CNN-BiLSTM),combined with dual-stage attention mechanism and Bayesian optimization algorithm.Firstly,in order to autonomously mine the data association between input features and wind power data,and further highlight the impact of important high-dimensional features,the attention mechanism is added to the common CNN to build a feature attention module.Secondly,the attention mechanism is introduced into the output of the BiLSTM network to form a temporal attention module,which enhances the long-term memory ability and strengthens the influence of important historical information.Finally,the Bayesian optimization algorithm is used to optimize the hyperparameters of the proposed model,and the optimal hyperparameters can be selected to show the best performance of the model.The verification experiment is conducted with actual data from a wind farm in Northwest China,accuracy of single-step prediction model is 95.58%,and accuracy of 4 hours ahead ultra-short-term multi-step prediction model combined with NWP information is 90.44%.The experimental results show that the proposed model is more accurate than others.

关 键 词：风电功率预测 深度学习 注意力机制 长短时记忆网络 卷积神经网络 超参数优化 

分 类 号：TM614[电气工程—电力系统及自动化]