RESEARCH ON WIND SPEED INTERVAL PREDICTION BASED ON HYBRID DEEP LEARNING MODEL

Ma Caizheng; Wang Cong; Wang Xiaorong; Zhang Hongli

doi:10.19912/j.0254-0096.tynxb.2021-1241

PDF(1978 KB)

Acta Energiae Solaris Sinica ›› 2023, Vol. 44 ›› Issue (3) : 139-146. DOI: 10.19912/j.0254-0096.tynxb.2021-1241

RESEARCH ON WIND SPEED INTERVAL PREDICTION BASED ON HYBRID DEEP LEARNING MODEL

Ma Caizheng¹, Wang Cong¹, Wang Xiaorong², Zhang Hongli¹

Author information +

History +

Abstract

The uncertainty of wind speed makes it more difficult to predict wind speed, and wind energy is difficult to be used effectively. In order to solve the above problems, a hybrid depth learning model for wind speed interval prediction is proposed based on Convolutional Neural Network (CNN), Shared Weight Long Short-Term Memory Network (SWLSTM), Attention Mechanism (AM) and Gaussian Process Regression (GPR). Firstly, the network combined CNN and SWLSTM is used to extract the features of wind speed series. Secondly,AM module is added to make use of the feature vector. Finally, the interval prediction is carried out through GPR. The model is applied to two wind speed data sets to test, and compared with other wind speed prediction models from two aspects of point prediction accuracy and interval prediction results. The experimental results show that the prediction model can obtain high-precision prediction results and appropriate prediction interval.

Key words

wind power / wind speed prediction / Gaussian process regression / long short-term memorynetwork / attention mechanism

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Ma Caizheng, Wang Cong, Wang Xiaorong, Zhang Hongli. RESEARCH ON WIND SPEED INTERVAL PREDICTION BASED ON HYBRID DEEP LEARNING MODEL[J]. Acta Energiae Solaris Sinica. 2023, 44(3): 139-146 https://doi.org/10.19912/j.0254-0096.tynxb.2021-1241

References

[1] DONG Y C, ZHANG H L, WANG C, et al.A novel hybrid model based on bernstein polynomial with mixture of Gaussians for wind power forecasting[J]. Applied energy, 2021, 286: 116545.
[2] WANG C, ZHANG H L, MA P.Wind power forecasting based on singular spectrum analysis and a new hybrid Laguerre neural network[J]. Applied energy, 2020, 259: 114139.
[3] 梁超, 刘永前, 周家慷, 等. 基于卷积循环神经网络的风电场内多点位风速预测方法[J]. 电网技术, 2021, 45(2): 534-542.
LIANG C, LIU Y Q, ZHOU J K,et al.Wind speed prediction at multi-locations based on combination of recurrent and convolutional neural networks[J]. Power system technology, 2021, 45(2): 534-542.
[4] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term windpower forecasting based on LSTM[J]. Power system technology, 2017, 41(12): 3792-3802.
[5] 魏昱洲, 许西宁. 基于LSTM长短期记忆网络的超短期风速预测[J]. 电子测量与仪器学报, 2019, 33(2): 64-71.
WEI Y Z, XU X N.Ultra-short term wind speedprediction based on LSTM long and short term memorynetwork[J].Journal of electronic measurement and instrumentation,2019, 33(2): 64-71.
[6] 李昭昱, 艾芊, 张宇帆, 等. 基于attention机制的LSTM神经网络超短期负荷预测方法[J]. 供用电, 2019, 36(1): 17-22.
LI Z Y,AI Q, ZHANG Y F, et al.A LSTM neuralnetwork method based on attention mechanism for ultra short-term load forecasting[J]. Distribution & utilization, 2019, 36(1): 17-22.
[7] 刘擘龙, 张宏立, 王聪, 等. 基于序列到序列和注意力机制的超短期风速预测[J]. 太阳能学报, 2021, 42(9):286-294.
LIU B L, ZHANG H L, WANG C, et al.Ultra-short-term wind speed predition based on sequence-to-sequence and attention mechanism[J]. Acta energiae solaris sinica, 2021, 42(9): 286-294.
[8] ZHANG Z D,YE L, QIN H, et al.Wind speed prediction method using shared weight long short-term memory network and gaussian process regression[J]. Applied energy, 2019, 247: 270-284.
[9] LI X Y,YI X H, LIU ZH, et al.Application of novel hybrid deep leaning model for cleaner production in a paper industrial wastewater treatment system[J]. Journal of cleaner production, 2021, 294: 126343.
[10] HE K J, JI L, WU C WD, et al.Using SARIMA-CNN-LSTM approach to forecast daily tourism demand[J].Journal of hospitality and tourism management, 2021, 49:25-33.
[11] LIU L, CHEN J, ZHAO G Y, et al.From BoW to CNN: two decades of texture representation for texture classification[J]. International journal of computer vision,2019, 127(1): 74-109.
[12] ANGRICK M, HERFF C, JOHNSON G, et al.Interpretation of convolutional neural networks for speech spectrogram regression from intracranial recordings[J].Neurocomputing, 2019, 342: 145-151.
[13] YAO Q H, WANG R X, FAN X M, et al.Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network[J]. Information fusion, 2020, 53: 174-182.
[14] CHAI T, DRAXLERR R.Root mean square error or mean absolute error?-arguments against avoiding RMSE in the literature[J]. Geoscientific model development, 2014, 7(3): 1247-1250.
[15] ROBERTO C Q, EDNA A R, LUPERCIO F B.Using the coefficient of determination R² to test the significance of multiple linear regression[J]. Teaching statistics, 2013, 35(2): 84-88.
[16] LI R R, JIN Y A.Wind speed interval prediction system based on multi-objective optimization for machine learning method[J]. Applied energy, 2018, 228: 2207-2220.
[17] LIU Y Q, YE L, QIN H, et al.Monthly streamflow forecasting based onhidden markov model and gaussian mixture regression[J]. Journal of hydrology, 2018, 561: 146-159.