Standardizing the Performance Evaluation of Short-Term Wind Power Prediction Models

By Henrik Madsen, Pierre Pinson, G. Kariniotakis, Henrik Aa. Nielsen, Torben Skov Nielsen. 2005

382 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/8b6f36609187002ea3bbab178b780bcfb8978881

How researchers see this paper

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

In Aerospace Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Trading Wind Generation From Short-Term Probabilistic Forecasts of Wind Power (2007, background): “Their improvement with respect to Persistence (which corresponds to a relative error reduction) reaches high levels (up to 40%‐60%) for horizons further than 6‐10 h ahead [ 29 ].”
AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network (2012, methodology): “To capture the benefits of persistence for first look-ahead hours and also to have reasonable performance over longer look-ahead hours, a new-reference (NR) model has been suggested in [31], and it is defined as”
Online short-term solar power forecasting (2009, methodology): “Instead, quantile regression is used, inspired by Møller et al. (2008) where it is applied to wind power forecasts.”
Short-term spatio-temporal prediction of wind speed and direction (2014, methodology): “For forecasts horizons of 6 to 72 hours numerical weather prediction (NWP) models are employed and are a significant improvement on persistence, the standard against which this type of forecast is measured [5,6].”
Powering Up With Space-Time Wind Forecasting (2010, background): “A better loss function should relate predicted wind speeds to the wind power since predicting power is the ultimate goal ( Madsen et al. 2005 ).”
Very‐short‐term probabilistic forecasting of wind power with generalized logit–normal distributions (2012, methodology): “…related to the median and expectation of predictive densities, since the corresponding normalized mean average error and normalized root-mean-square error scores appear to be the most employed in the wind power forecasting literature (Giebel et al., 2011; Costa et al., 2008; Madsen et al., 2005).”
An Advanced Statistical Method for Wind Power Forecasting (2007, background): “In [ 20 ] and [21], the performance of eight state-of-the-art statistical wind power prediction models applied on the same wind farm is compared.”
A review on the young history of the wind power short-term prediction (2008, background): “Also, they mentioned that the most appropriate performance measure depends on the intended application [79].”
Spatio‐temporal analysis and modeling of short‐term wind power forecast errors (2011, background): “For more details on evaluation of statistical model fitting, we refer to [20, 27], and also to [15] for the specific case of the wind power application.”
An analog ensemble for short-term probabilistic solar power forecast (2015, methodology): “A common verification framework, as suggested for WPF by [53], should be used to evaluate a deterministic forecast.”
Wind power forecasting : state-of-the-art 2009. (2009, positive): “Adapted from [85] and [86], it consists of an evaluation protocol to measure and grade their accuracy [85].”