Power curve model classification to estimate wind turbine power output

2018 ◽  
Vol 43 (3) ◽  
pp. 213-224 ◽  
Author(s):  
Bharti Dongre ◽  
Rajesh K Pateriya
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
Spline Interpolation ◽  
Specific Power ◽  
Power Curve ◽  
Model Classification ◽  
Curve Model ◽  
Modelling Methodology ◽  
Power Curves ◽  
Modelling Data

This article presents a comparative study of empirical power curve models to estimate the output power of the turbine as a function of the wind speed. In these models, modelling strategy relies on the objective of modelling, data being used for the modelling and targeted accuracy. It has been observed that models based on presumed shape of power curve lack desired accuracy since these are developed using the power ratings of wind turbine which are not sufficient to exactly replicate the turbine’s actual behaviour. The performance of various models which comes under manufacturer power curve modelling methodology has been compared with reference to commercially available wind turbines. It has been found that power curves obtained through method of least squares and cubic spline interpolation methods exactly match with manufacturer power curve, whereas 5PL method gives sufficiently accurate results. Modelling based on actual data of wind farm has been found to be a powerful technique for developing site-specific power curves.

Statistical power curve modeling to estimate wind turbine power output

2019 ◽  
pp. 0309524X1989167
Author(s):  
Bharti Dongre ◽  
Rajesh Kumar Pateriya
Keyword(s):  
Wind Turbine ◽  
Statistical Power ◽  
Polynomial Regression ◽  
Smoothing Splines ◽  
Optimal Number ◽  
Specific Power ◽  
Power Curve ◽  
Curve Modeling ◽  
A Site ◽  
Power Curves

In the wind industry, the power curve serves as a performance index of the wind turbine. The machine-specific power curves are not sufficient to measure the performance of wind turbines in different environmental and geographical conditions. The aim is to develop a site-specific power curve of the wind turbine to estimate its output power. In this article, statistical methods based on empirical power curves are implemented using various techniques such as polynomial regression, splines regression, and smoothing splines regression. In the case of splines regression, instead of randomly selecting knots, the optimal number of knots and their positions are identified using three approaches: particle swarm optimization, half-split, and clustering. The National Renewable Energy Laboratory datasets have been used to develop the models. Imperial investigations show that knot-selection strategies improve the performance of splines regression. However, the smoothing splines-based power curve model estimates more accurately compared with all others.

Statistical calculation of thrust curve of a wind turbine based on available power curve and general specifications data

2021 ◽  
Author(s):  
Evgeny Atlaskin ◽  
Irene Suomi ◽  
Anders Lindfors
Keyword(s):  
Wind Speed ◽  
Wind Turbine ◽  
Wind Farm ◽  
Wind Farms ◽  
Power Curve ◽  
Wake Effect ◽  
Thrust Coefficient ◽  
Simple Method ◽  
Wind Speeds ◽  
Power Curves

<p>Power curves for a substantial number of wind turbine generators (WTG) became available in a number of public sources during the recent years. They can be used to estimate the power production of a wind farm fleet with uncertainty determined by the accuracy and consistency of the power curve data. However, in order to estimate power losses inside a wind farm due to wind speed reduction caused by the wake effect, information on the thrust force, or widely used thrust coefficient (Ct), is required. Unlike power curves, Ct curves for the whole range of operating wind speeds of a WTG are still scarcely available in open sources. Typically, power and Ct curves are requested from a WTG manufacturer or wind farm owner under a non-disclosure agreement. However, in a research study or in calculations over a multitude of wind farms with a variety of wind turbine models, collecting this information from owners may be hardly possible. This study represents a simple method to define Ct curve statistically using power curve and general specifications of WTGs available in open sources. Preliminary results demonstrate reasonable correspondence between simulated and given data. The estimations are done in the context of aggregated wind power calculations based on reanalysis or forecast data, so that the uncertainty of wake wind speed caused by the uncertainty of predicted Ct is comparable, or do not exceed, the uncertainty of given wind speed. Although the method may not provide accurate fits at low wind speeds, it represents an essential alternative to using physical Computational Fluid Dynamics (CFD) models that are both more demanding to computer resources and require detailed information on the geometry of the rotor blades and physical properties of the rotor, which are even more unavailable in open sources than power curves.</p>

Assessment of Wind Turbine’s Power Curve Based on Performance Reliability Theory

2014 ◽  
Vol 538 ◽  
pp. 270-273
Author(s):  
Mu Yong Zhang ◽  
Xiao Ming Rui ◽  
Juan Huo ◽  
Yan Feng Zhao
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
North China ◽  
Reliability Theory ◽  
Power Curve ◽  
Important Indicator ◽  
Assessment Measure ◽  
Generation Capacity ◽  
Power Curves ◽  
Unit Performance

Power curve of wind turbine is an important indicator in assessing unit performance and evaluating unit generation capacity. However, due to the ambiguity of assessment measure and lack of assessment methods, it is difficult to assess the power curve. For solving the problem, a method based on performance reliability is proposed in this article. Using the operating data recorded in SCADA, the measured power curve was tested, and according to the manufacturer promised power curve, based on performance reliability theory, a method of assessing power curve was proposed. Using the method provided herein, the power curves of 5 wind turbines, which were erected in a wind farm in north China, were assessed. Results show that the method is accurate, simple and practical. And it provides an important theoretical basis for power curve assessment of wind turbine in site.

Quantile based probabilistic wind turbine power curve model

2021 ◽  
Vol 296 ◽  
pp. 116913
Author(s):  
Keyi Xu ◽  
Jie Yan ◽  
Hao Zhang ◽  
Haoran Zhang ◽  
Shuang Han ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Power Curve ◽  
Curve Model

Technical and Economical Investigation of Wind Power Potential in Kuwait

2015 ◽  
Author(s):  
Yousef A. Gharbia ◽  
Haytham Ayoub
Keyword(s):  
Large Scale ◽  
Wind Farm ◽  
Wind Farms ◽  
Wind Data ◽  
Electricity Production ◽  
Specific Power ◽  
Wind Rose ◽  
Average Wind Speed ◽  
Prevailing Wind Direction ◽  
Power Curves

The State of Kuwait is considering diversifying its energy sector and not entirely depend on oil. This desire is motivated by Kuwait commitment to reducing its share of pollution, as a result of burning fossil fuel, and to extend the life of its oil and gas reserves. The potential for solar energy in Kuwait is quite obvious; however, it is not the case when it comes to wind energy. The aim of this work was to analyze wind data from several sites in Kuwait and assess their suitability for building large-scale wind farms. The analysis of hourly averaged wind data showed that some sites can have an average wind speed as high as 5.3 m/s at 10 m height. The power density using Weibull distribution function was calculated for the most promising sites. The prevailing wind direction for these sites was also determined using wind-rose charts. The power curves of several Gamesa turbines were used in order to identify the best turbine model in terms of specific power production cost. The results showed that the area of Abraq Al-Habari has the highest potential for building a large-scale wind farm. The payback period of investments was found to be around 7 years and the cost of electricity production was around US Cent 4/kWh.

Equivalent power curve model of a wind farm based on field measurement data

2011 ◽  
Author(s):  
B. P. Hayes ◽  
I. Ilie ◽  
A. Porpodas ◽  
S. Z. Djokic ◽  
G. Chicco
Keyword(s):  
Field Measurement ◽  
Wind Farm ◽  
Measurement Data ◽  
Power Curve ◽  
Curve Model

scholarly journals Evaluation of the Energy Performance of the Amougdoul Wind Farm, Morocco

2017 ◽  
Vol 7 (2) ◽  
pp. 692
Author(s):  
Asma Ezzaidi ◽  
Mustapha Elyaqouti ◽  
Lahoussine Bouhouch ◽  
Ahmed Ihlal
Keyword(s):  
Wind Turbine ◽  
Calculation Method ◽  
Wind Farm ◽  
Shape Parameter ◽  
Scale Parameter ◽  
Energy Performance ◽  
Energy Output ◽  
Power Calculation ◽  
Power Curve ◽  
Useful Power

This paper is concerned with the assessment of the the performance of the Amougdoul wind farm. We have determined the Weibull parameters; namely the scale parameter, <em>c</em> (m/s) and shape parameter, <em>k</em>. After that, we have estimated energy output by a wind turbine using two techniques: the useful power calculation method and the method based on the modeling of the power curve, which is respectively 134.5 kW and 194.19 KW corresponding to 27% and 39% of the available wind energy, which confirm that the conversion efficiency does not exceed 40%.

scholarly journals Multivariate Wind Turbine Power Curve Model Based on Data Clustering and Polynomial LASSO Regression

2021 ◽  
Vol 12 (1) ◽  
pp. 72
Author(s):  
Davide Astolfi ◽  
Ravi Pandit
Keyword(s):  
Wind Turbine ◽  
Data Clustering ◽  
Performance Monitoring ◽  
Power Curve ◽  
Lasso Regression ◽  
Data Set ◽  
Power Monitoring ◽  
Turbine Performance ◽  
Input Variables ◽  
Power Curves

Wind turbine performance monitoring is a complex task because of the non-stationary operation conditions and because the power has a multivariate dependence on the ambient conditions and working parameters. This motivates the research about the use of SCADA data for constructing reliable models applicable in wind turbine performance monitoring. The present work is devoted to multivariate wind turbine power curves, which can be conceived of as multiple input, single output models. The output is the power of the target wind turbine, and the input variables are the wind speed and additional covariates, which in this work are the blade pitch and rotor speed. The objective of this study is to contribute to the formulation of multivariate wind turbine power curve models, which conjugate precision and simplicity and are therefore appropriate for industrial applications. The non-linearity of the relation between the input variables and the output was taken into account through the simplification of a polynomial LASSO regression: the advantages of this are that the input variables selection is performed automatically. The k-means algorithm was employed for automatic multi-dimensional data clustering, and a separate sub-model was formulated for each cluster, whose total number was selected by analyzing the silhouette score. The proposed method was tested on the SCADA data of an industrial Vestas V52 wind turbine. It resulted that the most appropriate number of clusters was three, which fairly resembles the main features of the wind turbine control. As expected, the importance of the different input variables varied with the cluster. The achieved model validation error metrics are the following: the mean absolute percentage error was in the order of 7.2%, and the average difference of mean percentage errors on random subsets of the target data set was of the order of 0.001%. This indicates that the proposed model, despite its simplicity, can be reliably employed for wind turbine power monitoring and for evaluating accumulated performance changes due to aging and/or optimization.

scholarly journals Wind Turbine Power Curve Modeling with a Hybrid Machine Learning Technique

2019 ◽  
Vol 9 (22) ◽  
pp. 4930 ◽  
Author(s):  
Shenglei Pei ◽  
Yifen Li
Keyword(s):  
Wind Turbine ◽  
Wind Power ◽  
Power Output ◽  
Parametric Models ◽  
Wind Data ◽  
Support Vector ◽  
Power Curve ◽  
Hybrid Strategy ◽  
Curve Modeling ◽  
Power Curves

A power curve of a wind turbine describes the nonlinear relationship between wind speed and the corresponding power output. It shows the generation performance of a wind turbine. It plays vital roles in wind power forecasting, wind energy potential estimation, wind turbine selection, and wind turbine condition monitoring. In this paper, a hybrid power curve modeling technique is proposed. First, fuzzy c-means clustering is employed to detect and remove outliers from the original wind data. Then, different extreme learning machines are trained with the processed data. The corresponding wind power forecasts can also be obtained with the trained models. Finally, support vector regression is used to take advantage of different forecasts from different models. The results show that (1) five-parameter logistic function is superior to the others among the parametric models; (2) generally, nonparametric power curve models perform better than parametric models; (3) the proposed hybrid model can generate more accurate power output estimations than the other compared models, thus resulting in better wind turbine power curves. Overall, the proposed hybrid strategy can also be applied in power curve modeling, and is an effective tool to get better wind turbine power curves, even when the collected wind data is corrupted by outliers.

Sign in / Sign up

Export Citation Format

Share Document