Analysis of Wind Energy Time Series with Kernel Methods and Neural Networks

摘要：

Wind energy has an important part to play as renewable energy resource in a sustainable world. For a reliable integration of wind energy the volatile nature of wind has to be understood. This article shows how kernel methods and neural networks can serve as modeling, forecasting and monitoring techniques, and, how they contribute to a successful integration of wind into smart energy grids. First, we will employ kernel density estimation for modeling of wind data. Kernel density estimation allows a statistically sound modeling of time series data. The corresponding experiments are based on real data of wind energy time series from the NREL western wind resource dataset. Second, we will show how prediction of wind energy can be accomplished with the help of support vector regression. Last, we will use selforganizing feature maps to map high-dimensional wind time series to colored sequences that can be used for error detection.

作者: Oliver Kramer Fabian Gieseke

作者单位: Bauhaus-University Weimar Institute of Structural Mechanics 99423 Weimar, Germany

会议类型: 国际会议

会议名称: 2011 Seventh International Conference on Natural Computation(第七届自然计算国际会议 ICNC 2011)

会议地点: 上海

会议语种:英文

页码: 2427-2431

在线出版日期: 2011-07-26（万方平台首次上网日期，不代表论文的发表时间）