Abstract
The wind power industry has seen an unprecedented growth in last few years. The surge in orders for wind turbines has resulted in a producers 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 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) and a PROLOG program designed to calculate the monthly mean wind speed.
Highlights
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
In this paper proposes a data-mining-based methodology for long term wind forecasting (ANN), which is suitable to deal with large real databases
Wind power density was determined by using the Weibull and Rayleigh probability density functions
Summary
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. The wind characteristics are needed for site selection, performance forecasting and planning of wind turbines Of these characteristics, the forecasting of mean monthly and daily wind speed is very important. Intermittency, and controllability characteristics, wind power integration presents unique challenges They can be grouped in the following: challenges in wind speed forecasting and forecasting wind power. Statistical analysis is useful in numerical data analysis, it does not solve data mining problems, such as discovering meaningful patterns in large quantities of data which are very much essential with the wind power systems. A model is developed to estimate monthly mean wind speed for a given period using PROLOG [3] ( AI Tool) Weibull probability distribution of wind speed and forecast the wind speed using artificial neural network. Using an artificial neural network (ANN) [7] in order to forecast the wind speed taking into account different input attributes, namely the number of previous hours used to predict the wind speed at a given site
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
