Prediction of Wind Farm Power Output Based on an Enhanced Recurrent Neural Network

  • Ethelbert Chinedu Eze University of Sussex
  • E.S. Ibrahim Department of Geography, Humboldt University, Berlin, Germany
  • C.K. Ihim Department of Engineering and Informatics, University of Sussex, Brighton, UK
  • C.R Chatwin Department of Engineering and Informatics, University of Sussex, Brighton, UK
  • T. C. Yang Department of Engineering and Informatics, University of Sussex, Brighton, UK.
Keywords: Wind-power Output Prediction, Recurrent Neural Network, LSTM, eLSTM, ARIMA, MSE


This paper studies wind-farm power output prediction based on recurrent neural network. First, a hybrid recurrent neural network (RNN) regularization method involving dropout and long short-term memory (LSTM) is presented. In this model, a regularization scheme is applied to modify and adapt the stochastic nature of the wind. Secondly, a new data structure is presented to the model. Thirdly, the method is developed for wind farm power output (WFPO) prediction. This algorithm is based on the dropout method, which has made WFPO capable of better prediction irrespective of the non-deterministic wind speed. The LSTM solves the RNN limitation of overfitting. The proposed method is demonstrated by investigating the WFPO on a fourteen wind-turbines, provides up to 80% accurate result over ARIMA model.


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.


[1] CNBC, "China and US lead way with wind
power installations, says global energy report,"
Sustainable Energy, Online Report 13 February,
2017 2017.
[2] CNBC, "China and US lead way with wind
power installations, says global energy report.,"
05 May, 2017 13 Feb 2017
[3] 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.
[4] 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.
[5] 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.
[6] 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/
[7] 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.
[8] H. Liu, C. Chen, H.-q. Tian, and Y.-f. Li, "A
hybrid model for wind speed prediction using
empirical mode decomposition and artificial
neural networks," Renewable Energy, vol. 48,
pp. 545-556, 2012.
[9] 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.
[10] 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
[11] J. M. Hu, J. Z. Wang, and L. Q. Xiao, "A hybrid
approach based on the Gaussian process with tobservation model for short-term wind speed
forecasts," Renewable Energy, vol. 114, pp.
670-685, Dec 2017.
[12] 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.
[13] 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.
[14] C. F. Heuberger, I. Staffell, N. Shah, and N. Mac
Dowell, "A systems approach to quantifying the
value of power generation and energy storage
technologies in future electricity networks,"
Computers & Chemical Engineering, vol. 107,
pp. 247-256, Dec 2017.
[15] M. Padhee and R. Karki,
"Reliability/environmental impacts of wind
energy curtailment due to ramping constraints,"
(in English), International Journal of System
Assurance Engineering and Management,
Article vol. 8, no. 4, pp. 663-672, Dec 2017.
[16] K. Moustafa, "A clean environmental week: Let
the nature breathe," (in English), Science of the
Total Environment, Article vol. 598, pp. 639-
646, Nov 2017.
[17] I. Tanaka and H. Ohmori, "Method Evaluation
for Short-Term Wind Speed Prediction
Considering Multi Regions in Japan," (in
English), Journal of Robotics and
Mechatronics, Article vol. 28, no. 5, pp. 681-
686, Oct 2016.
[18] P. Chatziagorakis et al., "Enhancement of
hybrid renewable energy systems control with
neural networks applied to weather forecasting:
the case of Olvio," (in English), Neural
Computing & Applications, Article;
Proceedings Paper vol. 27, no. 5, pp. 1093-1118,
Jul 2016.
[19] 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.
[20] S. Hochreiter and J. Schmidhuber, "Long shortterm memory," (in eng), Neural Comput, vol. 9,
no. 8, pp. 1735-80, Nov 15 1997.
[21] D. T. Mirikitani and N. Nikolaev, "Recursive
Bayesian Recurrent Neural Networks for TimeSeries Modeling," IEEE Transactions on Neural
Networks, vol. 21, no. 2, pp. 262-274, 2010.
[22] V. Pham, C. Kermorvant, and J. Louradour,
Dropout Improves Recurrent Neural Networks
for Handwriting Recognition. 2013.
[23] 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.
[24] 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.
[25] S. Hochreiter, M. Heusel, and K. Obermayer,
"Fast model-based protein homology detection
without alignment," Bioinformatics, vol. 23, no.
14, pp. 1728-1736, 2007.
[26] R. Maalej, N. Tagougui, and M. Kherallah,
"Recognition of Handwritten Arabic Words
with Dropout Applied in MDLSTM," in Image
Analysis and Recognition: 13th International
Conference, ICIAR 2016, in Memory of
Mohamed Kamel, Póvoa de Varzim, Portugal,
July 13-15, 2016, Proceedings, A. Campilho
and F. Karray, Eds. Cham: Springer
International Publishing, 2016, pp. 746-752.
[27] T. Moon, H. Choi, H. Lee, and I. Song,
RnnDrop: a novel dropout for RNNs in ASR.
2015, pp. 65-70.
[28] P. Society, "phm11 data challenge - condition
monitoring of anemometers,"
1/problems. , Case study 10/11/2014 2011.
[29] 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.
[30] S. W. Vera Bulaevskaya, Andy Clifton, Wayne
Miller, "statistical analysis and modeling for
wind power forecasting," Article, Conference
Preceedings 10/06/2014 10/06/2014.
[31] M. Mazhar, S. Kara, and H. Kaebernick,
"Remaining life estimation of used components
in consumer products: Life cycle data analysis
by Weibull and artificial neural networks,"
Journal of operations management, vol. 25, no.
6, pp. 1184-1193, 2007.
[32] K. Attias and S. P. Ladany, "Optimal layout for
wind turbine farms," in World Renewable
Energy Congress-Sweden; 8-13 May; 2011;
Linköping; Sweden, 2011, no. 57, pp. 4153-
4160: Linköping University Electronic Press.
[33] X. Gao, H. Yang, and L. Lu, "Investigation into
the optimal wind turbine layout patterns for a
Hong Kong offshore wind farm," Energy, vol.
73, pp. 430-442, 2014/08/14/ 2014.
[34] 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,
[35] 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.
[36] 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//
[37] S. V. Ravuri and A. Stolcke, "Recurrent neural
network and LSTM models for lexical utterance
classification," in INTERSPEECH, 2015, pp.
[38] T. N. Sainath et al., "Deep convolutional neural
networks for large-scale speech tasks," Neural
Networks, vol. 64, pp. 39-48, 2015.
[39] 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.
[40] A. S. Walia, "Types of Optimization Algorithms
used in Neural Networks and Ways to Optimize
Gradient Descent," Blog 2017.
[41] S. Ryu, S. Kim, J. Choi, H. Yu, and G. G. Lee,
"Neural sentence embedding using only indomain sentences for out-of-domain sentence
detection in dialog systems," Pattern
Recognition Letters, vol. 88, pp. 26-32, 2017.
[42] U. Güçlü and M. A. J. van Gerven, "Modeling
the Dynamics of Human Brain Activity with
Recurrent Neural Networks," (in English),
Frontiers in Computational Neuroscience,
Original Research vol. 11, no. 7, 2017-
February-09 2017.
[43] L. Hui, T. Hong-qi, and L. Yan-fei,
"Comparison of two new ARIMA-ANN and
ARIMA-Kalman hybrid methods for wind
speed prediction.," Applied Energy, vol. 98, pp.
415-424, 2012.
[44] R. G. Kavasseri and K. Seetharaman, "Dayahead wind speed forecasting using f-ARIMA
models," Renewable Energy, vol. 34, no. 5, pp.
1388-1393, 5/5/2009 2009.
How to Cite
Eze, E. C., E.S. Ibrahim, C.K. Ihim, C.R Chatwin, & T. C. Yang. (2019). Prediction of Wind Farm Power Output Based on an Enhanced Recurrent Neural Network. IJRDO - Journal of Computer Science Engineering , 5(11), 10-16.