Data-augmented sequential deep learning for wind power forecasting

Accurate wind power forecasting plays a critical role in the operation of wind parks and the dispatch of wind energy into the power grid. With excellent automatic pattern recognition and nonlinear mapping ability for big data, deep learning is increasingly employed in wind power forecasting. However, salient realities are that in-situ measured wind data are relatively expensive and inaccessible and correlation between steps is omitted in most multistep wind power forecasts. This paper is the first time that data augmentation is applied to wind power forecasting by systematically summarizing and proposing both physics-oriented and data-oriented time-series wind data augmentation approaches to considerably enlarge primary datasets, and develops deep encoderdecoder long short-term memory networks that enable sequential input and sequential output for wind power forecasting. The proposed augmentation techniques and forecasting algorithm are deployed on five turbines with diverse topographies in an Arctic wind park, and the outcomes are evaluated against benchmark models and different augmentations. The main findings reveal that on one side, the average improvement in RMSE of the proposed forecasting model over the benchmarks is 33.89%, 10.60%, 7.12%, and 4.27% before data augmentations, and increases to 40.63%, 17.67%, 11.74%, and 7.06%, respectively, after augmentations. The other side unveils that the effect of data augmentations on prediction is intricately varying, but for the proposed model with and without augmentations, all augmentation approaches boost the model outperformance from 7.87% to 13.36% in RMSE, 5.24% to 8.97% in MAE, and similarly over 12% in QR90. Finally, data-oriented augmentations, in general, are slightly better than physics-driven ones.

[1]  Ceyhun Yildiz,et al.  An improved residual-based convolutional neural network for very short-term wind power forecasting , 2021 .

[2]  Mohamad Hanif Md Saad,et al.  Artificial Intelligence Based Hybrid Forecasting Approaches for Wind Power Generation: Progress, Challenges and Prospects , 2021, IEEE Access.

[3]  Wenxuan Sun,et al.  Short-Term Photovoltaic Power Prediction Modeling Based on AdaBoost Algorithm and Elman , 2020, 2020 10th International Conference on Power and Energy Systems (ICPES).

[4]  Toby P. Breckon,et al.  Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab , 2011 .

[5]  Serge J. Belongie,et al.  Residual Networks Behave Like Ensembles of Relatively Shallow Networks , 2016, NIPS.

[6]  Ping-Rui Tsai,et al.  Categorizing SHR and WKY rats by chi2 algorithm and decision tree , 2020, Scientific Reports.

[7]  Chen Sun,et al.  Revisiting Unreasonable Effectiveness of Data in Deep Learning Era , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Viviana Cocco Mariani,et al.  A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting , 2020 .

[9]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[10]  F. Bréon,et al.  Wind power potential and intermittency issues in the context of climate change , 2021, Energy Conversion and Management.

[11]  Kashem M. Muttaqi,et al.  On the management of wind power intermittency , 2013 .

[12]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[13]  Quoc V. Le,et al.  AutoAugment: Learning Augmentation Strategies From Data , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[15]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[16]  Yingtao Jiang,et al.  Wind Power Forecasting Methods Based on Deep Learning: A Survey , 2020, Computer Modeling in Engineering & Sciences.

[17]  Terri L. Moore,et al.  Regression Analysis by Example , 2001, Technometrics.

[18]  Qingli Dong,et al.  A novel forecasting model based on a hybrid processing strategy and an optimized local linear fuzzy neural network to make wind power forecasting: A case study of wind farms in China , 2017 .

[19]  Xiaolei Liu,et al.  Wind power forecasting – A data-driven method along with gated recurrent neural network , 2021 .

[20]  Yu Zhang,et al.  Short-term wind power forecasting approach based on Seq2Seq model using NWP data , 2020 .

[21]  K. Scheinberg,et al.  Feature Engineering and Forecasting via Derivative-free Optimization and Ensemble of Sequence-to-sequence Networks with Applications in Renewable Energy. , 2019 .

[22]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[23]  Graham W. Taylor,et al.  Dataset Augmentation in Feature Space , 2017, ICLR.

[24]  Muhammad Muneeb,et al.  A novel genetic LSTM model for wind power forecast , 2021 .

[25]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[26]  Jianchun Peng,et al.  A review of deep learning for renewable energy forecasting , 2019, Energy Conversion and Management.

[27]  Quoc V. Le,et al.  SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition , 2019, INTERSPEECH.

[28]  S. Anfinsen,et al.  Assessing probabilistic modelling for wind speed from numerical weather prediction model and observation in the Arctic , 2021, Scientific Reports.

[29]  Bo Chen,et al.  Review of wind power scenario generation methods for optimal operation of renewable energy systems , 2020 .

[30]  Wu Wang,et al.  Wind Power Prediction Using Ensemble Learning-Based Models , 2020, IEEE Access.

[31]  Li Yongle,et al.  Ultra-short term wind prediction with wavelet transform, deep belief network and ensemble learning , 2020 .

[32]  Zi Lin,et al.  A Critical Review of Wind Power Forecasting Methods—Past, Present and Future , 2020, Energies.

[33]  Hui Liu,et al.  Deterministic wind energy forecasting: A review of intelligent predictors and auxiliary methods , 2019, Energy Conversion and Management.

[34]  Farshid Keynia,et al.  A new short-term wind speed forecasting method based on fine-tuned LSTM neural network and optimal input sets , 2020, Energy Conversion and Management.

[35]  Lawrence V. Snyder,et al.  Feature Engineering and Forecasting via Integration of Derivative-free Optimization and Ensemble of Sequence-to-sequence Networks: Renewable Energy Case Studies , 2019, ArXiv.

[36]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[37]  Jean D. Gibbons,et al.  Nonparametric Statistical Inference : Revised and Expanded , 2014 .

[38]  Gregor Giebel,et al.  Wind power forecasting-a review of the state of the art , 2017 .

[39]  Ralf C. Staudemeyer,et al.  Understanding LSTM - a tutorial into Long Short-Term Memory Recurrent Neural Networks , 2019, ArXiv.

[40]  Yi Shi,et al.  Deep Supervised Hashing with Triplet Labels , 2016, ACCV.

[41]  Ponnuthurai Nagaratnam Suganthan,et al.  Ensemble methods for wind and solar power forecasting—A state-of-the-art review , 2015 .

[42]  Wu Jun,et al.  A novel model for wind power forecasting based on Markov residual correction , 2015, IREC2015 The Sixth International Renewable Energy Congress.

[43]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[44]  S. Anfinsen,et al.  Comparative study of data-driven short-term wind power forecasting approaches for the Norwegian Arctic region , 2021, Journal of Renewable and Sustainable Energy.