Short and long-term wind turbine power output prediction

Abstract

In the wind energy industry, it is of great importance to develop models that accurately forecast the power output of a wind turbine, as such predictions are used for wind farm location assessment or power pricing and bidding, monitoring, and preventive maintenance. As a first step, and following the guidelines of the existing literature, we use the supervisory control and data acquisition (SCADA) data to model the wind turbine power curve (WTPC). We explore various parametric and non-parametric approaches for the modeling of the WTPC, such as parametric logistic functions, and non-parametric piecewise linear, polynomial, or cubic spline interpolation functions. We demonstrate that all aforementioned classes of models are rich enough (with respect to their relative complexity) to accurately model the WTPC, as their mean squared error (MSE) is close to the MSE lower bound calculated from the historical data. We further enhance the accuracy of our proposed model, by incorporating additional environmental factors that affect the power output, such as the ambient temperature, and the wind direction. However, all aforementioned models, when it comes to forecasting, seem to have an intrinsic limitation, due to their inability to capture the inherent auto-correlation of the data. To avoid this conundrum, we show that adding a properly scaled ARMA modeling layer increases short-term prediction performance, while keeping the long-term prediction capability of the model.

Emergent Failures and Cascades in Power Grids: A Statistical Physics Perspective

“…The Gaussian assumption is debatable, both for solar and wind. While consistent with atmospheric physics [25] and recent wind park statistics [26,27], different models are preferred for different timescales [28][29][30][31]. An extension of our framework to the dynamic model in [31] looks promising (using Freidlin-Wentzell theory as in [32]).…”

Non-stationarity in correlation matrices for wind turbine SCADA-data and implications for failure detection

“…[18]. An easily understood example is modelling the power curve [19,20] and then testing for deviations [21]. For a neural network, it might mean to predict one (or more) variables based on other measurements and then compare with the actual measurement.…”

Correlated power time series of individual wind turbines: A data driven model approach

“…Most models aim at finding a precise point forecast of time series for a certain time scale and horizon [30]. In contrast to that, other effort is put into modelling different properties related to power output such as the power curve [31,32], wind power ramps [33] or power density estimates [34]. Models also vary in terms of the time scale [35] that ranges from ultra-short-term (ms-s) [36] to long-term forecasts (months) [37].…”