From probabilistic forecasts to statistical scenarios of short-term wind power production

By Pierre Pinson, Henrik Madsen, Henrik Aa. Nielsen, George Papaefthymiou, B. Klockl. 2009

545 citations recorded by the source corpus.

Short-term (up to 2-3 days ahead) probabilistic forecasts of wind power provide forecast users with a highly valuable information on the uncertainty of expected wind generation. Whatever the type of these probabilistic forecasts, they are produced on a per horizon basis, and hence do not inform on the development of the forecast uncertainty through forecast series. However, this additional information may be paramount for a large class of time-dependent and multi-stage decision-making problems e.g. optimal operation of combined wind-storage systems or multiple-market trading with different gate closures. This issue is addressed here by describing a method that permits the generation of statistical scenarios of short-term wind generation that accounts for both the interdependence structure of prediction errors and the predictive distributions of wind power production. The method is based on the conversion of series of prediction errors to a multivariate Gaussian random variable, the interdependence structure of which can then be summarized by a unique covariance matrix. Such matrix is recursively estimated in order to accommodate long-term variations in the prediction error characteristics. The quality and interest of the methodology are demonstrated with an application to the test case of a multi-MW wind farm over a period of more than two years.

Subfields: Economics and Econometrics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/3a69765c25c90c613ee5cdf1d9665c4e7df9600d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Electrical and Electronic Engineering

Citations in the corpus

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks (2017, unknown): “For example, in [13], [14], [15], [4], [16],”
Generation and evaluation of space–time trajectories of photovoltaic power (2016, unknown): “In [20], an approach is proposed to capture and model the time dependent structure of wind power generation for successive hours using marginal densities.”
Energy Forecasting: A Review and Outlook (2020, unknown): “The main approach that was proposed builds on the use of copulas for coupling predictive marginal densities [60].”
Setting the Operating Reserve Using Probabilistic Wind Power Forecasts (2011, background): “[14] of the forecasts, and scenarios incorporating temporal [30] or spatial [31] interdependence structure of prediction errors.”
Energy Storage Arbitrage Under Day-Ahead and Real-Time Price Uncertainty (2018, unknown): “We use the scenario generation approach described in [21] to generate forecast scenarios from the estimated pdfs.”
Scenario Generation of Wind Power Based on Statistical Uncertainty and Variability (2013, methodology): “The difference between the proposed method and that of [18] and [32] is that an approach for the identification of covariance structure is proposed based on the probability distribution of wind power variations, which will be discussed in Section IV.”
Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine (2014, background): “With nonparametric probability forecasts of wind power, the statistical scenarios of short-term wind power can be generated [11].”
Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets (2019, methodology): “In [15]–[17], the scenarios are constructed by computing the complex covariance matrix based on a multivariate Gaussian distribution assumption.”
Forecasting: theory and practice (2020, methodology): “Since for a specific lead-time the forecast interval only encompasses information from a marginal distribution, it can also be named marginal forecast interval (MFI).”
Wind power forecasting : state-of-the-art 2009. (2009, methodology): “Scenarios of generation [270]: Scenarios contain information about the forecasted density/cumulative probability functions for the time horizon, and provide information about the development of the prediction errors through the set of look-ahead times and the spatial distribution.”
Stochastic Energy Scheduling in Microgrids With Intermittent Renewable Energy Resources (2014, methodology): “In order to capture the uncertainty of the wind power predictions, Monte Carlo simulations [30] were performed to generate a pool of wind power scenarios each day.”
Chance-Constrained Two-Stage Unit Commitment Under Uncertain Load and Wind Power Output Using Bilinear Benders Decomposition (2016, unknown): “Then, N scenarios including wind power output and load demand are generated from probabilistic forecasting [46].”