A Statistical Analysis and Artificial Neural Network Behavior on Wind Speed Prediction: Case Study

The increased use of energy and the depletion of the fossil fuel reserves combined with the increase of the environmental pollution have encouraged the search for clean and pollution-free sources of energy. One of these is wind energy. The wind power industry has seen an unprecedented growth in last few years. The surge in orders for wind turbines has resulted in a producer’s market. This market imbalance, the relative immaturity of the wind industry, and rapid developments in data processing technology have created an opportunity to improve the performance of wind farms and change misconceptions surrounding their operations. This research offers a new paradigm for the wind power industry, data-driven modeling. Each wind Mast generates extensive data for many parameters, registered as frequently as every minute. As the predictive performance approach is novel to wind industry, it is essential to establish a viable research road map. This paper proposes a Statistical analysis and data-mining-based methodology for long term wind forecasting (ANN), which is suitable to deal with large real databases. The paper includes a case study based on a real database of five years of wind speed data for a site and discusses results of wind power density was determined by using the Weibull and Rayleigh probability density functions. Wind speed predicted using wind speed data with Datamining methodology using intelligent technology as Artificial Neural Networks (ANN). MATLAB R2008a Neural Network Toolbox used for the training the ANN back propagation algorithm and a PROLOG program is designed to calculate the monthly and Annual mean wind speed. The Statistical analysis of wind speed prediction shows that Weibull distribution is more suitable than Rayleigh distribution and by seeing the values of the k we can conclude that Higher values of k imply a sharper maximum in the frequency distribution curve and consequently a lower wind power density.