Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts

Nielsen, Henrik Aalborg; Madsen, Henrik; Nielsen, Thomas Alexander Sick

doi:10.1002/we.180

Cited by 223 publications

(160 citation statements)

References 7 publications

Supporting

Mentioning

154

Contrasting

Order By: Relevance

“…Forecasted quantiles of the generation probability distribution are estimated by using three methods: adaptive variance estimation, ensemble based quantiles [206], and quantile regression [207].…”

Section: The Wppt Systemmentioning

confidence: 99%

Wind power forecasting : state-of-the-art 2009.

Monteiro¹,

Bessa²,

Miranda³

et al. 2009

300

264

View full text Add to dashboard Cite

Section: The Wppt Systemmentioning

confidence: 99%

Wind power forecasting : state-of-the-art 2009.

Monteiro¹,

Bessa²,

Miranda³

et al. 2009

300

264

View full text Add to dashboard Cite

“…According to Nielsen et al [27], the quantiles may cross in quantile regression, because to compute each quantile it is necessary to solve an independent optimization problem. The pdf forecasts supply directly non-crossing quantiles.…”

Section: Motivation To Represent Wind Power Uncertainty By Probabilitmentioning

confidence: 99%

“…For the wind power forecast problem, we have the following: The results obtained with the Nadaraya-Watson estimator and the Quantile-copula estimator will be compared with the linear quantile regression model and the spline quantile regression [27]. The spline quantile regression is a model from the state-of-the-art in wind power forecasting, which consists of a linear quantile regression with the base functions formulated as cubic B-splines, in order to obtain the quantile with proportion α of the forecast errors.…”

Section: Time-adaptive Quantile-copula Estimatormentioning

confidence: 99%

Development and testing of improved statistical wind power forecasting methods.

Mendes¹,

Bessa²,

Keko³

et al. 2011

View full text Add to dashboard Cite

“…However, persistence forecasts are poor at predicting ramps; a ramp 60 identified in the previous 30 min to an hour can change magnitude or even sign (i.e., up-or down-ramp) in a short period and therefore lead to large forecast errors. In recent years, there has been a growing interest in information regarding the uncertainty of wind power forecasts to make energy decisions (Nielsen et al, 2006b). Typical single (i.e., point) forecasts cannot provide this necessary uncertainty information, but probabilistic forecasts can.…”

Section: Introductionmentioning

confidence: 99%

Generating wind power scenarios for probabilistic ramp event prediction using multivariate statistical post-processing

Worsnop

2018

Preprint

View full text Add to dashboard Cite

Wind power forecasting is gaining international significance as more regions promote policies to increase the use of renewable energy. Wind ramps, large variations in wind power production during a period of minutes to hours, challenge utilities and electrical balancing authorities. A sudden decrease in wind energy production must be balanced by other power 15 generators to meet energy demands, while a sharp increase in unexpected production results in excess power that may not be used in the power grid, leading to a loss of potential profits. In this study, we compare different methods to generate probabilistic ramp forecasts from the High Resolution Rapid Refresh (HRRR) numerical weather prediction model with up to twelve hours of lead time at two tall-tower locations in the United States. We validate model performance using 21 months of 80-m wind speed observations from towers in Boulder, Colorado and near the Columbia River Gorge in eastern 20Oregon.We employ four statistical post-processing methods, three of which are not currently used in the literature for wind forecasting. These procedures correct biases in the model and generate short-term wind speed scenarios which are then converted to power scenarios. This probabilistic enhancement of HRRR point forecasts provides valuable uncertainty information of ramp events and improves the skill of predicting ramp events over the raw forecasts. We compute Brier skill 25 scores for each method at predicting up-and down-ramps to determine which method provides the best prediction. We find that the Standard Schaake Shuffle method yields the highest skill at predicting ramp events for these datasets, especially for up-ramp events at the Oregon site. Increased skill for ramp prediction is limited at the Boulder, CO site using any of the multivariate methods, because of the poor initial forecasts in this area of complex terrain. These statistical methods can be implemented by wind farm operators to generate a range of possible wind speed and power scenarios to aid and optimize 30 decisions before ramp events occur.Wind Energ. Sci. Discuss., https://doi

show abstract

Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts

Cited by 223 publications

References 7 publications

Wind power forecasting : state-of-the-art 2009.

Wind power forecasting : state-of-the-art 2009.

Development and testing of improved statistical wind power forecasting methods.

Generating wind power scenarios for probabilistic ramp event prediction using multivariate statistical post-processing

Contact Info

Product

Resources

About