Wind turbine power curve modelling using artificial neural network

Pelletier, Francis; Masson, Christian; Tahan, Antoine

doi:10.1016/j.renene.2015.11.065

Cited by 181 publications

(102 citation statements)

References 9 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…The model is labeled with ann in the following and is based on a Multilayer Perceptron Model [18], the input layer takes as input the forecasts of the wind speed at 10 m and 100 m above ground as well as the wind gust. The number and size of the hidden layers and activation function were selected through an optimization procedure, which resulted in a single hidden layer of 5 neurons and a sigmoid activation function.…”

Section: Benchmark Methodsmentioning

confidence: 99%

“…Among these, the following can be recalled: the copula power curve model [16], cubic spline interpolation [9], different types of artificial neural network [8,10,[17][18][19], multi-layer perceptron, random forest, k-nearest neighbors and support vector machines [8,15,20]. Among the non-parametric methods, there is the Method Of Bins on which the IEC 61400-12-1 standard is based [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Simple and Effective Approach for the Prediction of Turbine Power Production From Wind Speed Forecast

Marrocu

Massidda

2017

Energies

View full text Add to dashboard Cite

An accurate forecast of the power generated by a wind turbine is of paramount importance for its optimal exploitation. Several forecasting methods have been proposed either based on a physical modeling or using a statistical approach. All of them rely on the availability of high quality measures of local wind speed, corresponding generated power and on numerical weather forecasts. In this paper, a simple and effective wind power forecast technique, based on the probability distribution mapping of wind speed forecast and observed power data, is presented and it is applied to two turbines located on the island of Borkum (Germany) in the North Sea. The wind speed forecast of the ECMWF model at 100 m from the ground is used as the prognostic meteorological parameter. Training procedures are based entirely on relatively short time series of power measurements. Results show that our approach has skills that are similar or better than those obtained using more standard methods when measured with mean absolute error.

show abstract

Section: Benchmark Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Simple and Effective Approach for the Prediction of Turbine Power Production From Wind Speed Forecast

Marrocu

Massidda

2017

Energies

View full text Add to dashboard Cite

show abstract

“…They are also central to energy yield estimation. More recently, power curves have been seen to have the potential for WT condition monitoring; see for example Morshedizadeh et al and Pelletier et al Jia et al have proposed a performance assessment algorithm based on a similarity metric for the machine performance curve in which the health of the WT is validated by performing principal component analysis of the quasilinear region of the power curve. With the help of a power curve, performance deterioration associated with faults on an individual WT can be identified; see Wang et al and Kusiak and Verma …”

Section: Introductionmentioning

confidence: 99%

“…For example, Sohoni et al argued that a nonparametric model is suitable for dealing with large datasets and that it can incorporate the effects of different parameters other than wind speed on power curves more easily than parametric models. The work presented in Pelletier et al claims that power curve modeling using an artificial neural network (ANN) gives better accuracy than a parametric model, while Üstüntaş and Şahin conclude that cluster center fuzzy logic modeling can give an root mean square error (RMSE) value that is much lower than for a least squares fitted polynomial (ie, parametric) model. Despite this, Taslimi et al identify that a modified hyperbolic tangent (MHTan) model with backtracking search algorithm (BSA) gives an enhanced parametric model for power curve modeling that yields better accuracy than a fuzzy model.…”

Section: Introductionmentioning

confidence: 99%

Incorporating air density into a Gaussian process wind turbine power curve model for improving fitting accuracy

2018

View full text Add to dashboard Cite

A power curve conventionally represents the relationship between hub height wind speed and wind turbine power output. Power curves facilitate the prediction of power production at a site and are also useful in identifying the significant changes in turbine performance which can be vital for condition monitoring. However, their accuracy is significantly influenced by changes in air density, mainly when the turbine is operating below rated power. A Gaussian process (GP) is a nonparametric machine learning approach useful for power curve fitting. Critical analysis of temperature correction is essential for improving the accuracy of wind turbine power curves. The conventional approach is to correct the data for air density before it is binned to provide a power curve, as described in the IEC standard. In this paper, four different possible approaches of air density correction and its effect on GP power curve fitting model accuracy are explored to identify whether the traditional IEC approach used for air density correction is most effective when estimating power curves using a GP. Finding the most accurate air density compensation approach is necessary to minimize GP model uncertainty.

show abstract

“…One might therefore possibly invoke other kinds of precision modeling of wind turbines power curve. It actually is a very fertile field in the scientific literature [14][15][16][17]: as regards these models, the main drawback for their application to the study of wind turbine upgrades is that they are too complex and not enough flexible to be applied to the range of different criticality that the study of wind turbine upgrades poses.The above shortcomings are both circumvented in the present study: this work actually is a collaboration between academia and industry. The industry is Renvico srl 1 , owning and managing 335 MW of full-scale wind turbines in Italy and France.…”

mentioning

confidence: 99%

Wind Turbine Power Curve Upgrades

Astolfi¹,

Castellani²,

Terzi³

2018

Preprint

View full text Add to dashboard Cite

Full-scale wind turbine technology has been widely developing in the recent years and condition monitoring techniques assist at the scope of making 100% technical availability a realistic perspective. In this context, several retrofitting techniques are being used for further improving the efficiency of wind kinetic energy conversion. This kind of interventions is costly and, furthermore, the estimation of the energy enhancement is commonly provided under the hypothesis of ideal conditions, as for example absence of wakes between nearby turbines. A precise quantification of the energy gained by retrofitting is therefore precious in real conditions, that can be very different from ideal ones. In this work, three kinds of retrofitting are studied through the operational data of test case wind farms: improved start-up through pitch angle adjustment near the cut-in, aerodynamic blade retrofitting by means of vortex generators and passive flow control devices, extension of the power curve by raising cut-out and high wind speed cut-in. SCADA data are employed and reliable methods are formulated for estimating the energy improvement from each of the above retrofitting. Further, an insight is provided about wind turbine functioning under very stressing regimes, as for example high wind speeds.retrofitting; further, for some reason as in one of the test cases of the present work, it might happen that the approach can't be employed at all. One might therefore possibly invoke other kinds of precision modeling of wind turbines power curve. It actually is a very fertile field in the scientific literature [14][15][16][17]: as regards these models, the main drawback for their application to the study of wind turbine upgrades is that they are too complex and not enough flexible to be applied to the range of different criticality that the study of wind turbine upgrades poses.The above shortcomings are both circumvented in the present study: this work actually is a collaboration between academia and industry. The industry is Renvico srl 1 , owning and managing 335 MW of full-scale wind turbines in Italy and France. Some wind turbines owned by Renvico have been retrofitted in several ways: this has been a pilot test and the decision of extending the retrofitting to the other wind turbines in the corresponding wind farms has been based on the assessment, coming from this study, of the real profit on the pilot test cases. The SCADA data from the retrofitted and non-retrofitted wind turbines from the wind farms of interest have therefore been shared with the University of Perugia. This academia-industry collaboration, as shall be shown in the next Sections, has produced methods for the study of power curve upgrades, standing at the frontier of the scientific debate and being as well integrable in the everyday industrial management of the wind turbines. This kind of studies on this subject, basing on operational data, has been very recently developing in the scientific literature: in [18], a kernel plus method is adopted for computing ...

show abstract

Wind turbine power curve modelling using artificial neural network

Cited by 181 publications

References 9 publications

A Simple and Effective Approach for the Prediction of Turbine Power Production From Wind Speed Forecast

A Simple and Effective Approach for the Prediction of Turbine Power Production From Wind Speed Forecast

Incorporating air density into a Gaussian process wind turbine power curve model for improving fitting accuracy

Wind Turbine Power Curve Upgrades

Contact Info

Product

Resources

About