Machine Learning and Statistical Techniques for Daily Wind Energy Prediction

Authors : Lasini WİCKRAMASİNGHE, Piyal EKANAYAKE, Jeevani JAYASİNGHE

Pages : 1359-1370

Doi:10.35378/gujs.961338

View : 14 | Download : 7

Publication Date : 2022-12-01

Article Type : Research Paper

Abstract :This paper presents the development of wind energy prediction models for the Nala Danavi wind farm in Sri Lanka by using machine learning and statistical techniques. Wind speed and ambient temperature were used as the input variables in modeling while the daily wind energy production was the output variable. Correlation between the wind energy and each weather index was investigated using the Pearson’s and Spearman’s correlation coefficients and it was found that daily wind energy output is positively correlated with both daily averaged input variables. Statistical prediction models of Multiple Linear Regression insert ignore into journalissuearticles values(MLR); and Power Regression insert ignore into journalissuearticles values(PR); and the machine learning techniques of Support Vector Regression insert ignore into journalissuearticles values(SVR);, Gaussian Process Regression insert ignore into journalissuearticles values(GPR);, Feed Forward Backpropagation Neural Network insert ignore into journalissuearticles values(FFBPNN);, Cascade-Forward Backpropagation Neural Network insert ignore into journalissuearticles values(CFBPNN); and Recurrent Neural Network insert ignore into journalissuearticles values(RNN); were developed. The accuracy of the prediction models was measured in terms of the coefficient of determination, Bias, Percent Root mean square error insert ignore into journalissuearticles values(RMSE);Bias, and Nash-Sutcliffe Efficiency insert ignore into journalissuearticles values(NSE);. Results of the performance evaluation indicated that all the models are highly accurate while the FFBPNN-based model demonstrates outstanding performance with very low error. Such prediction models are highly important for a country like Sri Lanka whose power generation mainly depends on imported coal followed by hydropower and expanding the on-shore and off-shore wind farms gradually in many potential locations scattered over the country.
Keywords : Machine learning, Neural networks, Regression, Wind energy, Prediction models