Short term wind speed estimation in Saudi Arabia

Abstract In this paper, three methods are used for the prediction of wind speed, 12 h ahead, based on 72 h previous wind speed values at three locations viz. Rawdat Bin Habbas (inland north), Juaymah (east coast), and Dhulom (inland western region) in Saudi Arabia. These methods are Particle Swarm Optimization (PSO), Abductory Induction Mechanism (AIM), and the Persistence (PER) model. The available data at each site was divided into three consecutive groups. The first 50% was used for training, the second 25% for validation, and the remaining 25% for testing. The validation data set was used to select the network architecture and other user defined parameters. The testing data was used only to assess the performance of the networks on future unseen data that has not been used for training or model selection. For each of the three methods, each of 12 networks was trained to produce the wind speed at one of the next 12 h. Relatively, Close agreements were found between the predicted and measured hourly mean wind speed for all three locations with coefficient of correlation R 2 values between 81.7% and 98.0% for PSO, between 79.8% and 98.5% for AIM and between 59.5% and 88.4% for persistence model. Both PSO and AIM methods underestimated WS values during most hours with an average value of 0.036 m/s and 0.02 m/s, respectively. However, persistence model overestimated the WS by an average value of 0.51 m/s. It is shown that the two developed models outperformed the persistence model on predicting wind speed 12 h ahead of time with slight advantage to the PSO method.

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

[2]  N. Vogiatzis,et al.  Analysis of wind potential and characteristics in North Aegean, Greece , 2004 .

[3]  Darrell W. Pepper,et al.  Application of an h-adaptive finite element model for wind energy assessment in Nevada , 2007 .

[4]  F. C. Kaminsky,et al.  A COMPARISON OF ALTERNATIVE APPROACHES FOR THE SYNTHETIC GENERATION OF A WIND-SPEED TIME-SERIES , 1991 .

[5]  A. Çavusoglu,et al.  A classification mechanism for determining average wind speed and power in several regions of Turkey using artificial neural networks , 2005 .

[6]  Keith C. Drake,et al.  Abductive reasoning networks , 1991, Neurocomputing.

[7]  Rodolfo Pallabazzer.  Previsional estimation of the energy output of windgenerators , 2004 .

[8]  Z. Şen,et al.  First-order Markov chain approach to wind speed modelling , 2001 .

[9]  M. Mohandes.  Modeling global solar radiation using Particle Swarm Optimization (PSO) , 2012 .

[10]  S. Rehman,et al.  Spatial estimation of wind speed , 2012 .

[11]  James Kennedy,et al.  Particle swarm optimization , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[12]  Lars Landberg,et al.  Short-term prediction of local wind conditions , 1994 .

[13]  Mehrdad Abedi,et al.  Short term wind speed forecasting for wind turbine applications using linear prediction method , 2008 .

[14]  Z. Janjic.  The Step-Mountain Eta Coordinate Model: Further Developments of the Convection, Viscous Sublayer, and Turbulence Closure Schemes , 1994 .

[15]  Athanasios Sfetsos,et al.  A comparison of various forecasting techniques applied to mean hourly wind speed time series , 2000 .

[16]  Nicolas Moussiopoulos,et al.  The microscale model MIMO: development and assessment , 2000 .

[17]  George Galanis,et al.  Wind power prediction based on numerical and statistical models , 2013 .

[18]  H. S. Bagiorgas,et al.  Weibull Parameters Estimation Using Four Different Methods and Most Energy-Carrying Wind Speed Analysis , 2011 .

[19]  C.C.Y. Ma,et al.  Statistical comparison of solar radiation correlations Monthly average global and diffuse radiation on horizontal surfaces , 1983 .

[20]  T. Kitagawa,et al.  A wavelet-based method to generate artificial wind fluctuation data , 2003 .

[21]  Eugene Fernandez,et al.  Analysis of wind power generation and prediction using ANN: A case study , 2008 .

[22]  T. O. Halawani,et al.  Weibull parameters for wind speed distribution in Saudi Arabia , 1994 .

[23]  John A. Davies,et al.  Estimating Solar Irradiation on Horizontal Surfaces , 1984 .

[24]  N. Erdem Unal,et al.  Stochastic generation of hourly mean wind speed data , 2004 .

[25]  Norberto Fueyo,et al.  High resolution modelling of the on‐shore technical wind energy potential in Spain , 2010 .

[26]  A. Tapia,et al.  Application of a control algorithm for wind speed prediction and active power generation , 2005 .

[27]  D.A. Bechrakis,et al.  Correlation of wind speed between neighboring measuring stations , 2004, IEEE Transactions on Energy Conversion.

[28]  J.B. Theocharis,et al.  A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation , 2004, IEEE Transactions on Energy Conversion.

[29]  Shuhui Li,et al.  Using neural networks to estimate wind turbine power generation , 2001 .

[30]  Abdeen Mustafa Omer,et al.  Diffuse solar radiation over Shambat, Khartoum North , 1994 .

[31]  R. E. Abdel-Aal,et al.  Hourly temperature forecasting using abductive networks , 2004, Eng. Appl. Artif. Intell..

[32]  C. F. Ratto,et al.  Stochastic modelling of wind velocities time series , 1998 .

[33]  R. Hanitsch,et al.  Evaluation of wind energy potential and electricity generation on the coast of Mediterranean Sea in Egypt , 2006 .

[34]  A. Hepbasli,et al.  A review on the development of wind energy in Turkey , 2004 .

[35]  J. Palutikof,et al.  Estimation of extreme wind speeds with very long return periods , 1995 .

[36]  K. Agbossou,et al.  Nonlinear model identification of wind turbine with a neural network , 2004, IEEE Transactions on Energy Conversion.

[37]  Shuhui Li,et al.  Comparative Analysis of Regression and Artificial Neural Network Models for Wind Turbine Power Curve Estimation , 2001 .