Hybrid Transformer Network for Different Horizons-based Enriched Wind Speed Forecasting

—Highly accurate di ff erent horizon-based wind speed fore- casting facilitates a better modern power system. This paper proposed a novel astute hybrid wind speed forecasting model and applied it to di ff erent horizons. The proposed hybrid forecasting model decomposes the original wind speed data into IMFs (Intrinsic Mode Function) using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN). We fed the obtained subseries from ICEEMDAN to the transformer network. Each transformer network computes the forecast subseries and then passes to the fusion phase. Get the primary wind speed forecasting from the fusion of individual transformer network forecast subseries. Estimate the residual error values and predict errors using a multilayer perceptron neural network. The forecast error is added to the primary forecast wind speed to leverage the high accuracy of wind speed forecasting. Comparative analysis with real-time Kethanur, India wind farm dataset results reveals the pro- posed ICEEMDAN-TNF-MLPN-RECS hybrid model’s superior performance with MAE = 1.7096 × 10 − 07 , MAPE = 2.8416 × 10 − 06 , MRE = 2.8416 × 10 − 08 , MSE = 5.0206 × 10 − 14 , and RMSE = 2.2407 × 10 − 07 for case study 1 and MAE = 6.1565 × 10 − 07 , MAPE = 9.5005 × 10 − 06 , MRE = 9.5005 × 10 − 08 , MSE = 8.9289 × 10 − 13 , and RMSE = 9.4493 × 10 − 07 for case study 2 enriched wind speed forecasting than state-of-the-art methods and reduces the burden on the power system engineer. proposed ICEEMDAN-TNF-MLPN-RECS hybrid model fore- casting capability is validated on the two hub-based retrieved carried out a comparative performance investigation to demonstrate the proposed fore- casting model. According the comparative investigation and that the proposed with forecasting and both case studies. Moreover, we highlighted issues of and addition, we performed the validity of the proposed hybrid horizons Thus, proposed support ectively and The proposed intelligent hybrid forecasting model is and application scenarios. Future research plans to extend the work to various scales, with speed forecasting and practical implementation of the wind farm.

[1]  Zijun Zhang,et al.  Generative Probabilistic Wind Speed Forecasting: A Variational Recurrent Autoencoder Based Method , 2022, IEEE Transactions on Power Systems.

[2]  Bolong Chen,et al.  Short-term wind speed forecasting using recurrent neural networks with error correction , 2021 .

[3]  Lin Wang,et al.  Wind speed forecasting based on variational mode decomposition and improved echo state network , 2021 .

[4]  Mohammad Rastegar,et al.  Advanced Deep Learning Approach for Probabilistic Wind Speed Forecasting , 2021, IEEE Transactions on Industrial Informatics.

[5]  M. Madhiarasan.  Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network , 2020 .

[6]  Behnam Mohammadi-Ivatloo,et al.  Long-Term Wind Power Forecasting Using Tree-Based Learning Algorithms , 2020, IEEE Access.

[7]  Q. Wu,et al.  Ultra-short term wind speed prediction using mathematical morphology decomposition and long short-term memory , 2020 .

[8]  Li-Cheng Wu,et al.  Ultra-Short-Term Wind Speed Forecasting for Wind Power Based on Gated Recurrent Unit , 2020, 2020 8th International Electrical Engineering Congress (iEECON).

[9]  Xue Ben,et al.  Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case , 2020, ArXiv.

[10]  Héctor Allende,et al.  LSTM-Based Multi-scale Model for Wind Speed Forecasting , 2018, CIARP.

[11]  S. N. Deepa,et al.  Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting , 2017, Artificial Intelligence Review.

[12]  Christiaan M. van der Walt,et al.  Forecasting wind speed using support vector regression and feature selection , 2017, 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech).

[13]  Okyay Kaynak,et al.  Rough Deep Neural Architecture for Short-Term Wind Speed Forecasting , 2017, IEEE Transactions on Industrial Informatics.

[14]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[15]  S. N. Deepa,et al.  A novel criterion to select hidden neuron numbers in improved back propagation networks for wind speed forecasting , 2016, Applied Intelligence.

[16]  S. N. Deepa,et al.  Performance Investigation of Six Artificial Neural Networks for Different Time Scale Wind Speed Forecasting in Three Wind Farms of Coimbatore Region , 2016 .

[17]  C. L. Philip Chen,et al.  Predictive Deep Boltzmann Machine for Multiperiod Wind Speed Forecasting , 2015, IEEE Transactions on Sustainable Energy.

[18]  María Eugenia Torres,et al.  Improved complete ensemble EMD: A suitable tool for biomedical signal processing , 2014, Biomed. Signal Process. Control..

[19]  Qian Jian,et al.  Wind speed and power forecasting based on RBF neural network , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[20]  J.C. Palomares-Salas,et al.  ARIMA vs. Neural networks for wind speed forecasting , 2009, 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[21]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[22]  J.B. Theocharis,et al.  Long-term wind speed and power forecasting using local recurrent neural network models , 2006, IEEE Transactions on Energy Conversion.

[23]  Lars Landberg,et al.  Short-term prediction of local wind conditions , 1994 .

[24]  Yuhong Li,et al.  A Hybrid Deep Interval Prediction Model for Wind Speed Forecasting , 2021, IEEE Access.

[25]  Zexian Sun,et al.  Short-Term Wind Power Forecasting Based on VMD Decomposition, ConvLSTM Networks and Error Analysis , 2020, IEEE Access.

[26]  M Madhiarasan,et al.  Certain algebraic criteria for design of hybrid neural network models with applications in renewable energy forecasting , 2018 .

[27]  P. N. Suganthan,et al.  A Comparative Study of Empirical Mode Decomposition-Based Short-Term Wind Speed Forecasting Methods , 2015, IEEE Transactions on Sustainable Energy.

[28]  Yongqian Liu,et al.  Hybrid Forecasting Model for Very-Short Term Wind Power Forecasting Based on Grey Relational Analysis and Wind Speed Distribution Features , 2014, IEEE Transactions on Smart Grid.