Short-Term Nacelle Orientation Forecasting Using Bilinear Transformation and ICEEMDAN Framework

Huajin Li,Qian Cheng,Jiahao Deng,Chuanhao Pu,Dimuthu D. K. Arachchige,Peng Feng

doi:10.3389/fenrg.2021.780928

Abstract

To maximize energy extraction, the nacelle of a wind turbine follows the wind direction. Accurate prediction of wind direction is vital for yaw control. A tandem hybrid approach to improve the prediction accuracy of the wind direction data is developed. The proposed approach in this paper includes the bilinear transformation, effective data decomposition techniques, long-short-term-memory recurrent neural networks (LSTM-RNNs), and error decomposition correction methods. In the proposed approach, the angular wind direction data is firstly transformed into time-series to accommodate the full range of yaw motion. Then, the continuous transformed series are decomposed into a group of subseries using a novel decomposition technique. Next, for each subseries, the wind directions are predicted using LSTM-RNNs. In the final step, it decomposed the errors for each predicted subseries to correct the predicted wind direction and then perform inverse bilinear transformation to obtain the final wind direction forecasting. The robustness and effectiveness of the proposed approach are verified using data collected from a wind farm located in Huitengxile, Inner Mongolia, China. Computational results indicate that the proposed hybrid approach outperforms the other single approaches tested to predict the nacelle direction over short-time horizons. The proposed approach can be useful for practical wind farm operations.

Highlights

Wind energy generation is expanding with about 12% of world’s electricity to be supplied by 2020 (Kodama and Burls 2019)
Based on the above considerations, in this research, we propose a new hybrid approach combining ICEEMDAN and error correction methods for short-term wind direction forecasting
The major contribution of this research can be summarized as follows: First, the wind direction forecasting system based on ICEEMDAN decomposition, LSTM-RNN and error correction has been proposed; Second, the comparative analysis is performed against other benchmarking deep-learning algorithm; Third, the experiments were performed in different seasons to explore seasonal patterns of wind directions

Summary

INTRODUCTION

Wind energy generation is expanding with about 12% of world’s electricity to be supplied by 2020 (Kodama and Burls 2019). The major contribution of this research can be summarized as follows: First, the wind direction forecasting system based on ICEEMDAN decomposition, LSTM-RNN and error correction has been proposed; Second, the comparative analysis is performed against other benchmarking deep-learning algorithm; Third, the experiments were performed in different seasons to explore seasonal patterns of wind directions. To integrate the wind direction series with the ICEEMDAN modules, the implementations are introduced as follows (Duan et al, 2021): Step 1: Compute the local means of realizations using the EMD algorithm described in Eq 7: xi x + β0E1 wi (7). After the forecasting outcome produced by each LSTM-RNN, the error series E(t) of the training dataset can be computed by comparing the original transformed wind direction series.

EXPERIMENTAL RESULTS

CONCLUSION

DATA AVAILABILITY STATEMENT