%0 Journal Article
%T Comparison and Optimization of Neural Networks and Network Ensembles for Gap Filling of Wind Energy Data
%A Andres Schmidt
%A Maya Suchaneck
%J Journal of Renewable Energy
%D 2014
%I Hindawi Publishing Corporation
%R 10.1155/2014/986830
%X Wind turbines play an important role in providing electrical energy for an ever-growing demand. Due to climate change driven by anthropogenic emissions of greenhouse gases, the exploration and use of sustainable energy sources is essential with wind energy covering a significant portion. Data of existing wind turbines is needed to reduce the uncertainty of model predictions of future energy yields for planned wind farms. Due to maintenance routines and technical issues, data gaps of reference wind parks are unavoidable. Here, we present real-world case studies using multilayer perceptron networks and radial basis function networks to reproduce electrical energy outputs of wind turbines at 3 different locations in Germany covering a range of landscapes with varying topographic complexity. The results show that the energy output values of the turbines could be modeled with high correlations ranging from 0.90 to 0.99. In complex terrain, the RBF networks outperformed the MLP networks. In addition, rare extreme values were better captured by the RBF networks in most cases. By using wind meteorological variables and operating data recorded by the wind turbines in addition to the daily energy output values, the error could be further reduced to more than 20%. 1. Introduction The Combination of climate change and the dependence on fossil fuels slowly cause changes in energy policy and trigger an increasing demand for sustainable energy sources. Global carbon dioxide emissions are ever increasing and the associated consequences for the climate are widely scientifically recognized [1¨C3]. Over the last decade and in particular since the release of the report of the Intergovernmental Panel on Climate Change (IPCC) in 2007, public and political awareness of renewable energy technologies has increased considerably. This is not at least due to the large and fast growing economies and the associated increase of numbers of cars and energy consumption, and therefore of CO2 emissions [4]. Wind energy has the potential to be a vital contributor to renewable energy technologies that will substitute more and more for gas and coal [5]. In order to decrease the uncertainty of wind energy yield predictions during the planning of a single turbine or wind farm, data of nearby existing wind turbines are often used as reference for model evaluation. In Germany, the legislation that grants priority to renewable energy sources (Renewable Energy Resources Act, EEG) states that only wind turbines in areas with sufficient wind energy potential are qualified to receive compensation for
%U http://www.hindawi.com/journals/jre/2014/986830/