Wind Turbine Operation Curves Modelling Techniques

Abstract

Wind turbines are machines operating in non-stationary conditions and the power of a wind turbine depends non-trivially on environmental conditions and working parameters. For these reasons, wind turbine power monitoring is a complex task which is typically addressed through data-driven methods for constructing a normal behavior model. On these grounds, this study is devoted the analysis of meaningful operation curves, which are rotor speed-power, generator speed-power and blade pitch-power. A key point is that these curves are analyzed in the appropriate operation region of the wind turbines: the rotor and generator curves are considered for moderate wind speed, when the blade pitch is fixed and the rotational speed varies (Region 2); the blade pitch curve is considered for higher wind speed, when the rotational speed is rated (Region 2 12). The selected curves are studied through a multivariate Support Vector Regression with Gaussian Kernel on the Supervisory Control And Data Acquisition (SCADA) data of two wind farms sited in Italy, featuring in total 15 2 MW wind turbines. An innovative aspect of the selected models is that minimum, maximum and standard deviation of the independent variables of interest are fed as input to the models, in addition to the typically employed average values: using the additional covariates proposed in this work, the error metrics decrease of order of one third, with respect to what would be obtained by employing as regressors only the average values of the independent variables. In general it results that, for all the considered curves, the prediction of the power is characterized by error metrics which are competitive with the state of the art in the literature for multivariate wind turbine power curve analysis: in particular, for one test case, a mean absolute percentage error of order of 2.5% is achieved. Furthermore, the approach presented in this study provides a superior capability of interpreting wind turbine performance in terms of the behavior of the main sub-components and eliminates as much as possible the dependence on nacelle anemometer data, whose use is critical because of issues related to the sites complexity.

Third-Order Sliding Mode Applied to the Direct Field-Oriented Control of the Asynchronous Generator for Variable-Speed Contra-Rotating Wind Turbine Generation Systems

“…The use of wind energy is now common in the world in the field of electric energy generation. The most widely used generation system for wind power conversion is the single-turbine, which is capable of converting 59% of the total wind power into useful electrical power [41]. This is still a very small percentage and needs to be increased.…”

Perspectives on SCADA Data Analysis Methods for Multivariate Wind Turbine Power Curve Modeling

“…In [14], two fundamental operation curves are analyzed through Gaussian process methods, which are the wind speed-blade pitch and the wind speed-rotor speed (Figure 4) curves. Other important operation curves, which have been addressed, for example, in [15,16], are the rotor speed-power (Figure 5), the generator speed-power (Figure 6) and the blade pitchpower curves (Figure 7): examples are reported using the same data set as for Figure 1 (courtesy of ENGIE Italia). Wind Speed (m/s) From Figures 3 and 4, it arises that, as the wind intensity increases from cut-in, at first the rotational speed increases and the blade pitch is held practically fixed: in this regime, the wind turbine operates by regulating the rotor speed on the grounds of the torque exerted on the rotor, in order to attain the maximum possible aerodynamic efficiency.…”

“…For higher wind speed (but below rated power), the logic of the control changes because the rotor speed saturates and the wind turbine operates in partial aerodynamic load, which is regulated by varying the blade pitch. Despite that it is typical that the region from cut-in to rated power is overall indicated as Region 2 of the power curve, it should be noticed that in general these two different control regions can be individuated and it makes sense to distinguish the variable rotor speed with respect to the variable blade pitch control region: for this reason, in [15,16], the nomenclature Region 2 and Region 2 1 /2 is adopted. Rotor Speed (rpm) On the grounds of Equation (3) and Figures 3-7, it therefore arises intuitively that knowing, for example, the blade pitch and the rotor speed in addition to the wind speed could be helpful for predicting how much power the wind turbine should extract.…”

“…All the studies cited in Section 2 except [17] use only the average values as covariates, but the use of minimum, maximum and standard deviation could be helpful for improving the regression. This issue has been addressed recently in [16] for the rotor speed, generator speed and blade pitch curves and it arises that the error metrics diminish of approximately one third if one employs as input for the regression also minimum, maximum and standard deviation of the independent variables. This perspective should be investigated in depth as well for multivariate wind turbine power curve modeling.…”

Valuation of Wind Energy Turbines Using Volatility of Wind and Price

“…The main purpose of this paper is to study the effect of energy value fluctuations on the assessment of the profitability of wind turbine facilities using the real option analysis method. The economic output of a wind turbine installation is a function of its electric energy output [23][24][25] and the value of market energy. The electric energy output is a function of the turbine used and wind speed statistics.…”