Wind power curve modeling in complex terrain using statistical models
Authors:
- 1 January 2015
- journal article
- conference paper
- Published by AIP Publishing in Journal of Renewable and Sustainable Energy
- Vol. 7 (1) , 013103
Abstract
The simplest power curves model wind power only as a function of the wind speed at the turbine hub height. While the latter is an essential predictor of power output, wind speed information in other parts of the vertical profile, as well as additional atmospheric variables, are also important determinants of power. The goal of this work was to determine the gain in predictive ability afforded by adding wind speed information at other heights, as well as other atmospheric variables, to the power prediction model. Using data from a wind farm with a moderately complex terrain in the Altamont Pass region in California, we trained three statistical models—a neural network, a random forest and a Gaussian process model—to predict power output from various sets of aforementioned predictors. The comparison of these predictions to the observed power data revealed that considerable improvements in prediction accuracy can be achieved both through the addition of predictors other than the hub-height wind speed and the use of statistical models. To our knowledge, the use of the Gaussian process model in this context is new, in contrast to neural networks and random forests. The advantage of this model over the other two models is that it provides a much more natural way to estimate the uncertainty associated with its predictions. In addition, this study presents one of the most comprehensive analyses to date of the relative importance of various wind power curve inputs.Keywords
Funding Information
- Lawrence Livermore National Laboratory, Office of Science (12-ER-069)
This publication has 45 references indexed in Scilit:
- Corrections for Wind-Speed Errors from Sodar and Lidar in Complex TerrainBoundary-Layer Meteorology, 2012
- Accounting for the speed shear in wind turbine power performance measurementWind Energy, 2011
- Wind Shear and Uncertainties in Power Curve Measurement and Wind ResourcesWind Engineering, 2009
- Conically scanning lidar error in complex terrainMeteorologische Zeitschrift, 2009
- Adaptive Design and Analysis of Supercomputer ExperimentsTechnometrics, 2009
- Bayesian Treed Gaussian Process Models With an Application to Computer ModelingJournal of the American Statistical Association, 2008
- Wind speed errors for LIDARs and SODARs in complex terrainIOP Conference Series: Earth and Environmental Science, 2008
- Wind turbine power and sound in relation to atmospheric stabilityWind Energy, 2007
- Wind speed and power forecasting based on spatial correlation modelsIEEE Transactions on Energy Conversion, 1999
- Design and Analysis of Computer ExperimentsStatistical Science, 1989