Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights

Accurate wind power prediction can improve the safety and reliability of grid operation. To further enhance the accuracy of short-term wind power prediction, this paper proposes a CNN-LSTM&GRU multi-model combined prediction method considering the difficulty in obtaining optimal prediction resul...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui JIA, Guohua YANG, Haofeng ZHENG, Honghao ZHANG, Xuan LIU, Hang YU
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2022-05-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202104023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053044550500352
author Rui JIA
Guohua YANG
Haofeng ZHENG
Honghao ZHANG
Xuan LIU
Hang YU
author_facet Rui JIA
Guohua YANG
Haofeng ZHENG
Honghao ZHANG
Xuan LIU
Hang YU
author_sort Rui JIA
collection DOAJ
description Accurate wind power prediction can improve the safety and reliability of grid operation. To further enhance the accuracy of short-term wind power prediction, this paper proposes a CNN-LSTM&GRU multi-model combined prediction method considering the difficulty in obtaining optimal prediction results with a single model. Firstly, a convolutional neural network (CNN) is used to extract local features of data and combined with a long short-term memory (LSTM) network to construct a CNN-LSTM network structure that incorporates local feature pre-extraction modules. Then, the CNN-LSTM network is paralleled with a gated recurrent unit (GRU) network. An adaptive weight learning module is employed to select the best weights for the outputs of the CNN-LSTM module and the GRU module. In this way, the paper constructs a combined short-term prediction model based on CNN-LSTM&GRU. Finally, the model is applied to the power prediction of a wind farm in northwestern China. The experimental results show that the proposed model has a smaller mean absolute error (MAE), a smaller root mean square error (RMSE), and higher prediction accuracy than single models and other combined models.
format Article
id doaj-art-ce571131c49f4a1380e61ca6acf93627
institution DOAJ
issn 1004-9649
language zho
publishDate 2022-05-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-ce571131c49f4a1380e61ca6acf936272025-08-20T02:52:38ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492022-05-01555475610.11930/j.issn.1004-9649.202104023zgdl-55-10-jiaruiCombined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive WeightsRui JIA0Guohua YANG1Haofeng ZHENG2Honghao ZHANG3Xuan LIU4Hang YU5School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaSchool of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaSchool of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaSchool of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaSchool of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaSchool of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, ChinaAccurate wind power prediction can improve the safety and reliability of grid operation. To further enhance the accuracy of short-term wind power prediction, this paper proposes a CNN-LSTM&GRU multi-model combined prediction method considering the difficulty in obtaining optimal prediction results with a single model. Firstly, a convolutional neural network (CNN) is used to extract local features of data and combined with a long short-term memory (LSTM) network to construct a CNN-LSTM network structure that incorporates local feature pre-extraction modules. Then, the CNN-LSTM network is paralleled with a gated recurrent unit (GRU) network. An adaptive weight learning module is employed to select the best weights for the outputs of the CNN-LSTM module and the GRU module. In this way, the paper constructs a combined short-term prediction model based on CNN-LSTM&GRU. Finally, the model is applied to the power prediction of a wind farm in northwestern China. The experimental results show that the proposed model has a smaller mean absolute error (MAE), a smaller root mean square error (RMSE), and higher prediction accuracy than single models and other combined models.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202104023short-term wind power predictioncnn-lstmgrucombined predictionadaptive weight learning
spellingShingle Rui JIA
Guohua YANG
Haofeng ZHENG
Honghao ZHANG
Xuan LIU
Hang YU
Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
Zhongguo dianli
short-term wind power prediction
cnn-lstm
gru
combined prediction
adaptive weight learning
title Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
title_full Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
title_fullStr Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
title_full_unstemmed Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
title_short Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights
title_sort combined wind power prediction method based on cnn lstm gru with adaptive weights
topic short-term wind power prediction
cnn-lstm
gru
combined prediction
adaptive weight learning
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202104023
work_keys_str_mv AT ruijia combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights
AT guohuayang combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights
AT haofengzheng combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights
AT honghaozhang combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights
AT xuanliu combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights
AT hangyu combinedwindpowerpredictionmethodbasedoncnnlstmgruwithadaptiveweights