A Comparative Study of Activation Functions of NAR and NARX Neural Network for Long-Term Wind Speed Forecasting in Malaysia

Since wind power is directly influenced by wind speed, long-term wind speed forecasting (WSF) plays an important role for wind farm installation. WSF is essential for controlling, energy management and scheduled wind power generation in wind farm. The proposed investigation in this paper provides 30-days-ahead WSF. Nonlinear Autoregressive (NAR) and Nonlinear Autoregressive Exogenous (NARX) Neural Network (NN) with different network settings have been used to facilitate the wind power generation. The essence of this study is that it compares the effect of activation functions (namely, tansig and logsig) in the performance of time series forecasting since activation function is the core element of any artificial neural network model. A set of wind speed data was collected from different meteorological stations in Malaysia, situated in Kuala Lumpur, Kuantan, and Melaka. The proposed activation functions tansig of NARNN and NARXNN resulted in promising outcomes in terms of very small error between actual and predicted wind speed as well as the comparison for the logsig transfer function results.

[1]  Teresa B. Ludermir,et al.  Comparison of new activation functions in neural network for forecasting financial time series , 2011, Neural Computing and Applications.

[2]  Razman Mat Tahar,et al.  Selection of renewable energy sources for sustainable development of electricity generation system using analytic hierarchy process: A case of Malaysia , 2014 .

[3]  A. V. Olgac,et al.  Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks , 2011 .

[4]  Zahari Taha,et al.  Psychological Variables in Ascertaining Potential Archers , 2018, Machine Learning in Sports.

[5]  W. S. Ho,et al.  Renewable energy policies and initiatives for a sustainable energy future in Malaysia , 2011 .

[6]  Carlos Gershenson,et al.  Wind speed forecasting for wind farms: A method based on support vector regression , 2016 .

[7]  Saad Mekhilef,et al.  Long-Term Wind Speed Forecasting and General Pattern Recognition Using Neural Networks , 2014, IEEE Transactions on Sustainable Energy.

[8]  Alfred Stein,et al.  Assessment of a conceptual hydrological model and artificial neural networks for daily outflows forecasting , 2013, International Journal of Environmental Science and Technology.

[9]  H. J. Lu,et al.  An improved neural network-based approach for short-term wind speed and power forecast , 2017 .

[10]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[11]  Dongxiao Niu,et al.  Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm , 2014 .

[12]  Chao Chen,et al.  A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks , 2012 .

[13]  Arash Andalib,et al.  Forecasting the Unknown Dynamics in NN3 Database Using a Nonlinear Autoregressive Recurrent Neural Network , 2007, 2007 International Joint Conference on Neural Networks.

[14]  Pierre Pinson,et al.  Standardizing the Performance Evaluation of Short-Term Wind Power Prediction Models , 2005 .

[15]  Haiyan Lu,et al.  A case study on a hybrid wind speed forecasting method using BP neural network , 2011, Knowl. Based Syst..

[16]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[17]  Omaima N. A. AL-Allaf,et al.  NONLINEAR AUTOREGRESSIVE NEURAL NETWORK FOR ESTIMATION SOIL TEMPERATURE: A COMPARISON OF DIFFERENT OPTIMIZATION NEURAL NETWORK ALGORITHMS , 2011 .

[18]  A. M. Razali,et al.  Evaluating the wind speed persistence for several wind stations in Peninsular Malaysia , 2012 .

[19]  Jing Shi,et al.  On comparing three artificial neural networks for wind speed forecasting , 2010 .

[20]  A. Immanuel Selvakumar,et al.  Linear and non-linear autoregressive models for short-term wind speed forecasting , 2016 .

[21]  Erasmo Cadenas,et al.  Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA–ANN model , 2010 .

[22]  David A. Cartes,et al.  Application of artificial intelligence to stator winding fault diagnosis in Permanent Magnet Synchronous Machines , 2013 .

[23]  Aoife Foley,et al.  Current methods and advances in forecasting of wind power generation , 2012 .

[24]  Othman A. Karim,et al.  The development of hybrid integrated renewable energy system (wind and solar) for sustainable living at Perhentian Island, Malaysia , 2009 .

[25]  Gianpaolo Vitale,et al.  Solar and wind forecasting by NARX neural networks , 2016 .

[26]  Anjar Wanto,et al.  Use of Binary Sigmoid Function And Linear Identity In Artificial Neural Networks For Forecasting Population Density , 2017 .

[27]  Maria del Carmen Pegalajar Jiménez,et al.  An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings , 2016 .

[28]  Benjamin K. Sovacool,et al.  Untapped potential: the difficulties of the Small Renewable Energy Power (SREP) program in Malaysia , 2011 .

[29]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[30]  Najdan Vukovic,et al.  A comprehensive experimental evaluation of orthogonal polynomial expanded random vector functional link neural networks for regression , 2017, Appl. Soft Comput..

[31]  Gm. Shafiullah,et al.  Hybrid renewable energy integration (HREI) system for subtropical climate in Central Queensland, Australia , 2016 .

[32]  Peter Wolfs,et al.  Potential challenges of integrating large-scale wind energy into the power grid–A review , 2013 .

[33]  Aliashim Albani,et al.  Wind Energy Potential and Power Law Indexes Assessment for Selected Near-Coastal Sites in Malaysia , 2017 .

[34]  E. Assareh,et al.  Solar radiation forecasting based on meteorological data using artificial neural networks , 2009, 2009 7th IEEE International Conference on Industrial Informatics.

[35]  Yongsheng Chen,et al.  Short-term wind speed and power forecasting using an ensemble of mixture density neural networks , 2016 .

[36]  A. M. Razali,et al.  Analyzing the East Coast Malaysia Wind Speed Data , 2009 .

[37]  W. Rivera,et al.  Short term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks , 2009 .

[38]  Jianzhou Wang,et al.  Short-term wind speed forecasting using a hybrid model , 2017 .

[39]  Davar Khalili,et al.  Daily Outflow Prediction by Multi Layer Perceptron with Logistic Sigmoid and Tangent Sigmoid Activation Functions , 2010 .

[40]  Yi-Ming Wei,et al.  One day ahead wind speed forecasting: A resampling-based approach , 2016 .

[41]  Alex Stojcevski,et al.  A time series ensemble method to predict wind power , 2014, 2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG).

[42]  C. Senabre,et al.  Application of SOM neural networks to short-term load forecasting: The Spanish electricity market case study , 2012 .

[43]  Zengwei Zheng,et al.  An Overview: the Development of Prediction Technology of Wind and Photovoltaic Power Generation , 2011 .

[44]  Gary Higgins,et al.  Real-time prediction model for indoor temperature in a commercial building , 2018, Applied Energy.

[45]  G. Lalchand,et al.  A review on sustainable power generation in Malaysia to 2030: Historical perspective, current assessment, and future strategies , 2014 .

[46]  Christopher Heard,et al.  Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model , 2016 .

[47]  Yann LeCun,et al.  Second Order Properties of Error Surfaces: Learning Time and Generalization , 1990, NIPS 1990.

[48]  Haiyan Lu,et al.  Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model , 2012 .

[49]  Qing Cao,et al.  Forecasting wind speed with recurrent neural networks , 2012, Eur. J. Oper. Res..