Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
8120089 | Renewable and Sustainable Energy Reviews | 2014 | 16 Pages |
Abstract
The randomness and intermittence of wind resources is the biggest challenge in the integration of wind power into the power system. Accurate forecasting of wind power generation is an efficient tool to deal with such problem. Conventional wind power forecasting produces a value, or the conditional expectation of wind power output at a time point in the future. However, any prediction involves inherent uncertainty. In recent years, several probabilistic forecasting approaches have been reported in wind power forecasting studies. Compared to currently wide-used point forecasts, probabilistic forecasts could provide additional quantitative information on the uncertainty associated with wind power generation. For decision-makings in the uncertainty environment, probabilistic forecasts are optimal inputs. A review of state-of-the-art methods and new developments in wind power probabilistic forecasting is presented in this paper. Firstly, three different representations of wind power uncertainty are briefly introduced. Then, different forecasting methods are discussed. These methods are classified into three categories in terms of uncertainty representation, i.e. probabilistic forecasts (parametric and non-parametric), risk index forecasts and space-time scenario forecasts. Finally, requirements and the overall framework of the uncertainty forecasting evaluation are summarized. In addition, this article also describes current challenges and future developments associated with wind power probabilistic prediction.
Keywords
Continuous ranked probability scoreLQRCDFKDEQuantile regression forestwpfBMASQRNPRINWPCRPSForecasting evaluationMRIindependent system operatorISOKernel density estimationStochastic optimizationCumulative Distribution FunctionProbability density functionDecision-makingQuantile regressionBayesian model averagingUncertainty representationartificial intelligencePdfNumerical weather predictionProbabilistic forecastingWind power forecasting
Related Topics
Physical Sciences and Engineering
Energy
Renewable Energy, Sustainability and the Environment
Authors
Yao Zhang, Jianxue Wang, Xifan Wang,