Bayesian Hierarchy Non-stationary Neural Network on Short Term Prediction Wind Power Model for Measuring Work Capacity of Wind Turbine

  • Authors

    • A. Prasetyowati
    • D. Sudiana
    • H. Sudibyo
    https://doi.org/10.14419/ijet.v8i1.10.28398
  • Wind Power, POT, GDP, BHM, NN, WDNN

  • Abstract

    Wind energy is environmentally friendly energy, intermittent problems often occur in the generation of this energy in tropical wind lands. Due to this problem the working capacity of wind turbines does not have an average work size. So that it is difficult for operators to calculate the capacity produced by the wind turbines which are located on the observation land. In this study wind speed identification using Peaks Over Threshold (POT) method with extreme data distribution pattern of wind speed generated by pareto distribution (GPD). Estimation of GPD parameters is carried out using the Bayesian Hierarchy Model (BHM) to overcome the problem of data limitations and uncertainty of parameters in determining the capacity of the wind turbine. Regression model to get a prediction of wind turbine working capacity using Neural Network (NN). The Bayes Neural Network model provides the smallest error in wind power prediction compared to the Neural Network (NN) prediction model and the Wavelet Decomposition Neural Network (WDNN) model.

     

     

  • References

    1. [1] S. Zergane, A. Smaili, and C. Masson, “Optimization of wind turbine placement in a wind farm using a new pseudo-random number generation method,†Renew. Energy, vol. 125, pp. 166–171, 2018.

      [2] Z. Ghahramani, “Bayesian Modelling,†2012.

      [3] J. Sari and I. Hanugraheni, “Pemodelan Bayesian Hirarki Data Curah Hujan Ekstrem di Jakarta,†vol. 5, no. 1, 2016.

      [4] Loukatou, S. Howell, P. Johnson, and P. Duck, “Stochastic wind speed modelling for estimation of expected wind power output,â€Appl. Energy, vol. 228, no. June, pp. 1328– 1340, 2018.

      [5] P. Parameter and P. Pembeza, “Parameter Estimation of Stochastic Differential Equation,†vol. 41, no. 12, pp. 1635–1642, 2012.

      [6] W. Wu and M. Peng, “A Data Mining Approach Combining K-Means Clustering with Bagging Neural Network for Short-term Wind Power Forecasting,†pp. 1–8.

      [7] J. K. Kruschke and W. Vanpaemel, “Bayesian Estimation in Hierarchical Models,†pp. 279– 299, 2015.

      [8] T. Liu, H. Wei, and K. Zhang, “Wind power prediction with missing data using Gaussian process regression and multiple imputation,†Appl. Soft Comput. J., vol. 71, pp. 905–916, 2018.

      [9] D. Y. Hong, T. Y. Ji, M. S. Li, and Q. H. Wu, “Electrical Power and Energy Systems Ultra- short-term forecast of wind speed and wind power based on morphological high frequency fi lter and double similarity search algorithm ☆,†vol. 104, no. April 2017, pp. 868–879, 2019.

      [10] P. L. Mcdermott and C. K. Wikle, “Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data,†pp. 1–47, 2018.

      [11] J. Naik, R. Bisoi, and P. K. Dash, “Prediction interval forecasting of wind speed and wind power using modes decomposition based low rank multi-kernel ridge regression,†Renew. Energy, vol. 129, pp. 357–383, 2018.

      [12] G. Sun, C. Jiang, P. Cheng, Y. Liu, X. Wang, and Y. Fu, “Short-term wind power forecasts by a synthetical similar time series data mining method,†Renew. Energy, vol. 115, pp. 575–584, 2018.

      [13] S. Tasnim, A. Rahman, A. Maung, T. Oo, and

      [14] E. Haque, “Knowle dge-Base d Systems Wind power prediction in new stations based on knowledge of existing Stations : A cluster based multi source domain adaptation approach,†Knowledge-Based Syst., vol. 145, pp. 15–24, 2018.

      [15] Shari, M. J. Ghadi, S. Ghavidel, L. Li, and

      [16] J. Zhang, “A new method based on Type-2 fuzzy neural network for accurate wind power forecasting under uncertain data,†vol. 120, pp. 220–230, 2018.

      [17] N. S. Pearre and L. G. Swan, “Statistical approach for improved wind speed forecasting for wind power production,†Sustain. Energy Technol. Assessments, vol. 27, no. January, pp. 180–191, 2018.

  • Downloads

  • How to Cite

    Prasetyowati, A., Sudiana, D., & Sudibyo, H. (2019). Bayesian Hierarchy Non-stationary Neural Network on Short Term Prediction Wind Power Model for Measuring Work Capacity of Wind Turbine. International Journal of Engineering & Technology, 8(1.10), 235-240. https://doi.org/10.14419/ijet.v8i1.10.28398

    Received date: 2019-03-15

    Accepted date: 2019-03-15