Enhancing Wind Turbine Power Forecast via Convolutional Neural Network

The rapid development in wind power comes with new technical challenges. Reliable and accurate wind power forecast is of considerable significance to the electricity system’s daily dispatching and production. Traditional forecast methods usually utilize wind speed and turbine parameters as the model inputs. However, they are not sufficient to account for complex weather variability and the various wind turbine features in the real world. Inspired by the excellent performance of convolutional neural networks (CNN) in computer vision, we propose a novel approach to predicting short-term wind power by converting time series into images and exploit a CNN to analyze them. In our approach, we first propose two transformation methods to map wind speed and precipitation data time series into image matrices. After integrating multi-dimensional information and extracting features, we design a novel CNN framework to forecast 24-h wind turbine power. Our method is implemented on the Keras deep learning platform and tested on 10 sets of 3-year wind turbine data from Hangzhou, China. The superior performance of the proposed method is demonstrated through comparisons using state-of-the-art techniques in wind turbine power forecasting.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Yan Shen,et al.  Validation and comparison of a new gauge‐based precipitation analysis over mainland China , 2016 .

[3]  Alessandro Corsini,et al.  Computational analysis of wind-turbine blade rain erosion , 2016 .

[4]  Mohan Kolhe,et al.  Generalized feed-forward based method for wind energy prediction , 2013 .

[5]  Kwok-Wing Chau,et al.  A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources , 2019, IEEE Access.

[6]  Chengshi Tian,et al.  A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting , 2019, Applied Energy.

[7]  H. D. Mathur,et al.  Forecasting of solar and wind power using LSTM RNN for load frequency control in isolated microgrid , 2020, International Journal of Modelling and Simulation.

[8]  Haiyan Lu,et al.  A Novel Framework of Reservoir Computing for Deterministic and Probabilistic Wind Power Forecasting , 2020, IEEE Transactions on Sustainable Energy.

[9]  Feng Qian,et al.  Multi-step wind speed forecasting based on a hybrid forecasting architecture and an improved bat algorithm , 2017 .

[10]  Jianzhou Wang,et al.  A novel hybrid model for short-term wind power forecasting , 2019, Appl. Soft Comput..

[11]  Zhenlong Wu,et al.  Effects of rain on vertical axis wind turbine performance , 2017 .

[12]  Diab W. Abueidda,et al.  Deep learning for plasticity and thermo-viscoplasticity , 2021 .

[13]  Mark Landry,et al.  Probabilistic gradient boosting machines for GEFCom2014 wind forecasting , 2016 .

[14]  Fernando Luiz Cyrino Oliveira,et al.  Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods , 2018 .

[15]  Tinghui Ouyang,et al.  Prediction of wind power ramp events based on residual correction , 2019, Renewable Energy.

[16]  Wei Chen,et al.  A deep learning framework for time series classification using Relative Position Matrix and Convolutional Neural Network , 2019, Neurocomputing.

[17]  Tim Oates,et al.  Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks , 2014 .

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Pengfei Chen,et al.  An Inter Type-2 FCR Algorithm Based T–S Fuzzy Model for Short-Term Wind Power Interval Prediction , 2019, IEEE Transactions on Industrial Informatics.

[20]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[21]  L. W. Oliveira,et al.  Reliability-constrained dynamic transmission expansion planning considering wind power generation , 2020 .

[22]  Nima Hatami,et al.  Classification of time-series images using deep convolutional neural networks , 2017, International Conference on Machine Vision.

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

[24]  Y. Ge,et al.  Aerodynamic performance and wind-induced effect of large-scale wind turbine system under yaw and wind-rain combination action , 2019, Renewable Energy.

[25]  Yanbin Yuan,et al.  Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine , 2017 .

[26]  Yongxin Zhu,et al.  Multiscale deep network based multistep prediction of high-dimensional time series from power transmission systems , 2020, Trans. Emerg. Telecommun. Technol..

[27]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[28]  Xiaoming Xue,et al.  Short-Term Wind Speed Interval Prediction Based on Ensemble GRU Model , 2020, IEEE Transactions on Sustainable Energy.

[29]  Pinar Karagoz,et al.  Data Mining-Based Upscaling Approach for Regional Wind Power Forecasting: Regional Statistical Hybrid Wind Power Forecast Technique (RegionalSHWIP) , 2019, IEEE Access.

[30]  Weisheng Wang,et al.  Forecasted Scenarios of Regional Wind Farms Based on Regular Vine Copulas , 2020, Journal of Modern Power Systems and Clean Energy.