Multi-Modal Wind Speed Modeling Using Mixture Probability Density Functions

For stochastic planning and operation of modern wind power farms, probability distribution functions (PDFs) are developed to estimate wind speed probabilities in a more predictable fashion. The parameters of the proposed model are obtained using the expectation-maximization (EM) algorithm to determine the model maximum log log-likelihood estimation (MLE). Additionally, the Bayesian information criterion (BIC), and Bootstrap Likelihood ratio test techniques are employed to analyze the appropriate number of PDFs and to determine the goodness of fit, respectively. The results demonstrate the accuracy of the proposed multi-modal PDFs compared to that of the well-known single PDFs utilized in the literature.