Enhanced Recurrent Neural Network for Short-term Wind Farm Power Output Prediction.

  • Ethelbert Chinedu Eze University of Sussex
  • Chris R. Chatwin, Professor.
Keywords: Wind Power Output Prediction, Recurrent Neural Network, Deep learning, oLSTM, ARIMA, MSE

Abstract

Scientists, investors and policy makers have become aware of the importance of providing near accurate spatial estimates of renewable energies. This is why current studies show improvements in methodologies to provide more precise energy predictions. Wind energy is tied to weather patterns, which are irregular, especially in climates with erratic weather patterns.  This can lead to errors in the predicted potentials. Therefore, recurrent neural networks (RNN) are exploited for enhanced wind-farm power output prediction. A model involving a combination of RNN regularization methods using dropout and long short-term memory (LSTM) is presented. In this model, the regularization scheme modifies and adapts to the stochastic nature of wind and is optimised for the wind farm power output (WFPO) prediction. This algorithm implements a dropout method to suit non-deterministic wind speed by applying LSTM to prevent RNN from overfitting. A demonstration for accuracy using the proposed method is performed on a 14-turbines wind farm. The model out performs the ARIMA model with up to 80% accuracy.

Downloads

Download data is not yet available.

Author Biography

Ethelbert Chinedu Eze, University of Sussex

I'm a PhD Candidate in Informatics at the University of Sussex, U.K.

References

[1] CNBC, "China and US lead way with wind power installations, says global energy report.," 05 May, 2017 13 Feb 2017
[2] C. Liang, P. Wang, X. Han, W. Qin, Y. Jia, and T. Yuan, "Battery Energy Storage Selection Based on a Novel Intermittent Wind Speed Model for Improving Power System Dynamic Reliability," IEEE Transactions on Smart Grid, 2017.
[3] Z. Guo, W. Zhao, H. Lu, and J. Wang, Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model. 2012, pp. 241–249.
[4] Z. Guo, W. Zhao, H. Lu, and J. Wang, "Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model," Renewable Energy, vol. 37, no. 1, pp. 241-249, 2012/01/01/ 2012.
[5] S. Balluff, J. Bendfeld, and S. Krauter, "Short term wind and energy prediction for offshore wind farms using neural networks," in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 379-382.
[6] T. Wardah, A. A. Kamil, A. B. S. Hamid, and W. W. I. Maisarah, "Statistical verification of numerical weather prediction models for quantitative precipitation forecast," in 2011 IEEE Colloquium on Humanities, Science and Engineering, 2011, pp. 88-92.
[7] N. Chen, Z. Qian, I. T. Nabney, and X. Meng, "Wind Power Forecasts Using Gaussian Processes and Numerical Weather Prediction," IEEE Transactions on Power Systems, vol. 29, no. 2, pp. 656-665, 2014.
[8] M. Yesilbudak, S. Sagiroglu, and I. Colak, "A new approach to very short term wind speed prediction using k-nearest neighbor classification," Energy Conversion and Management, vol. 69, pp. 77-86, 2013/05/01/ 2013.
[10] H. Liu, H.-q. Tian, and Y.-f. Li, "Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction," Applied Energy, vol. 98, pp. 415-424, 2012/10/01/ 2012.
[11] S. Baran, "Probabilistic wind speed forecasting using Bayesian model averaging with truncated normal components," Computational Statistics & Data Analysis, vol. 75, pp. 227-238, 2014/07/01/ 2014.
[12] D. Lee and R. Baldick, "Short-Term Wind Power Ensemble Prediction Based on Gaussian Processes and Neural Networks," IEEE Trans. Smart Grid, vol. 5, no. 1, pp. 501-510, 2014.
[13] H.-z. Li, S. Guo, C.-j. Li, and J.-q. Sun, "A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm," Knowledge-Based Systems, vol. 37, pp. 378-387, 2013/01/01/ 2013.
[14] W. Zhang, J. Wang, J. Wang, Z. Zhao, and M. Tian, "Short-term wind speed forecasting based on a hybrid model," Applied Soft Computing, vol. 13, no. 7, pp. 3225-3233, 2013/07/01/ 2013.
[15] J. Shi, Z. Ding, W.-J. Lee, Y. Yang, Y. Liu, and M. Zhang, "Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features," IEEE Transactions on Smart Grid, vol. 5, no. 1, pp. 521-526, 2014.
[16] S. Haykin, Kalman filtering and neural networks. John Wiley & Sons, 2004.
[17] S. Salcedo-Sanz, E. G. Ortiz-Garcı´a, Á. M. Pérez-Bellido, A. Portilla-Figueras, and L. Prieto, "Short term wind speed prediction based on evolutionary support vector regression algorithms," Expert Systems with Applications, vol. 38, no. 4, pp. 4052-4057, 2011/04/01/ 2011.
[18] J. Liu and E. Zio, "SVM hyperparameters tuning for recursive multi-step-ahead prediction," (in English), Neural Computing & Applications, Article vol. 28, no. 12, pp. 3749-3763, Dec 2017.
[19] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical evaluation of gated recurrent neural networks on sequence modeling," arXiv preprint arXiv:1412.3555, 2014.
[20] O. Wallscheid, W. Kirchgässner, and J. Böcker, "Investigation of long short-term memory networks to temperature prediction for permanent magnet synchronous motors," in 2017 International Joint Conference on Neural Networks (IJCNN), 2017, pp. 1940-1947.
[21] W. Yao, P. Huang, and Z. Jia, "Multidimensional LSTM Networks to Predict Wind Speed," in 2018 37th Chinese Control Conference (CCC), 2018, pp. 7493-7497.
[22] B. Kanna and S. N. Singh, "Long term wind power forecast using adaptive wavelet neural network," in 2016 IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering (UPCON), 2016, pp. 671-676.
[23] D. T. Mirikitani and N. Nikolaev, "Recursive Bayesian Recurrent Neural Networks for Time-Series Modeling," IEEE Transactions on Neural Networks, vol. 21, no. 2, pp. 262-274, 2010.
[24] J. Brownlee, "How to Use Weight Regularization with LSTM Networks for Time Series Forecasting," p. 1, May 5, 2017 2017.
[25] M. Coto-Jimenez and J. Goddard-Close, "LSTM Deep Neural Networks Postfiltering for Enhancing Synthetic Voices," (in English), International Journal of Pattern Recognition and Artificial Intelligence, Article; Proceedings Paper vol. 32, no. 1, p. 24, Jan 2018, Art. no. 1860008.
[26] D. Q. Wang, Y. L. Gao, J. X. Liu, C. H. Zheng, and X. Z. Kong, "Identifying drug-pathway association pairs based on L1L2,1-integrative penalized matrix decomposition," (in English), Oncotarget, Article vol. 8, no. 29, pp. 48075-48085, Jul 2017.
[27] V. Pham, C. Kermorvant, and J. Louradour, Dropout Improves Recurrent Neural Networks for Handwriting Recognition. 2013.
[28] T. Moon, H. Choi, H. Lee, and I. Song, RnnDrop: a novel dropout for RNNs in ASR. 2015, pp. 65-70.
[29] T. Bluche, C. Kermorvant, and J. Louradour, "Where to apply dropout in recurrent neural networks for handwriting recognition?," in 2015 13th International Conference on Document Analysis and Recognition (ICDAR), 2015, pp. 681-685.
[30] M. Fei and D. Y. Yeung, "Temporal Models for Predicting Student Dropout in Massive Open Online Courses," in 2015 IEEE International Conference on Data Mining Workshop (ICDMW), 2015, pp. 256-263.
[31] Q. Hu, R. Zhang, and Y. Zhou, "Transfer learning for short-term wind speed prediction with deep neural networks," Renewable Energy, vol. 85, pp. 83-95, 2016.
[32] P. Society, "phm11 data challenge - condition monitoring of anemometers," https://www.phmsociety.org/competition/pmh/11/problems. , Case study 10/11/2014 2011.
[33] L. Sun, C. Chen, and Q. Cheng, "Feature extraction and pattern identification for anemometer condition diagnosis," Int. J. Progn. Heal. Manag, vol. 3, pp. 8-18, 2012.
[34] D. Kececioglu, Reliability engineering handbook. DEStech Publications, Inc, 2002.
[35] R. Maalej and M. Kherallah, "Improving MDLSTM for Offline Arabic Handwriting Recognition Using Dropout at Different Positions," in Artificial Neural Networks and Machine Learning – ICANN 2016: 25th International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II, A. E. P. Villa, P. Masulli, and A. J. Pons Rivero, Eds. Cham: Springer International Publishing, 2016, pp. 431-438.
[36] Y. Fei, J. Hu, K. Gao, J. Tu, W.-q. Li, and W. Wang, "Predicting risk for portal vein thrombosis in acute pancreatitis patients: A comparison of radical basis function artificial neural network and logistic regression models," Journal of critical care, vol. 39, pp. 115-123, 2017.
[37] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[38] G. Vaca-Castano, S. Das, J. P. Sousa, N. D. Lobo, and M. Shah, "Improved scene identification and object detection on egocentric vision of daily activities," Computer Vision and Image Understanding, vol. 156, pp. 92-103, 3// 2017.
[39] S. V. Ravuri and A. Stolcke, "Recurrent neural network and LSTM models for lexical utterance classification," in INTERSPEECH, 2015, pp. 135-139.
[40] T. N. Sainath et al., "Deep convolutional neural networks for large-scale speech tasks," Neural Networks, vol. 64, pp. 39-48, 2015.
[41] E. Phaisangittisagul, "An Analysis of the Regularization between L2 and Dropout in Single Hidden Layer Neural Network," IEEE Computer society, Conference Paper vol. DOI 10.1109/ISMS.2016.14, no. 2166-0670/16, p. 6, 2016 2016.
Published
2019-02-11