Wind Turbine Power Curve Modeling Using Advanced Parametric and Nonparametric Methods

Abstract

Wind turbine power curve modeling is an important tool in turbine performance monitoring and power forecasting. There are several statistical techniques to fit the empirical power curve of a wind turbine, which can be classified into parametric and nonparametric methods. In this paper, we study four of these methods to estimate the wind turbine power curve. Polynomial regression is studied as the benchmark parametric model, and issues associated with this technique are discussed. We then introduce the locally weighted polynomial regression method, and show its advantages over the polynomial regression. Also, the spline regression method is examined to achieve more flexibility for fitting the power curve. Finally, we develop a penalized spline regression model to address the issues of choosing the number and location of knots in the spline regression. The performance of the presented methods is evaluated using two simulated data sets as well as an actual operational power data of a wind farm in North America.Index Terms-Nonparametric regression, penalized spline regression, polynomial regression, wind energy, wind turbine power curve.

An Improved Adaptive-Torque-Gain MPPT Control for Direct-Driven PMSG Wind Turbines Considering Wind Farm Turbulences

“…A variety of WECS configurations can be broadly classified into four types: Type 1 (fixed-speed WECS), Type 2 (limited-variable-speed WECS), Type 3 (variable-speed with partial power electronic conversion WECS), and Type 4 (variable-speed with full power electronic conversion WECS) [33][34][35][36][37]. In recent years, an increasing number of wind farms are using the Type 4 WECS, specifically the permanent magnetic synchronous generator (PMSG) based WECS, due to its high efficiency, gearless construction, light weight quality, and self-excitation features [21,[34][35][36].…”

“…A typical PMSG-based WECS is shown in Figure 1, in which wind power is transformed to mechanical power via a wind turbine, and further converted to electric power through a generator [37][38][39][40]. The wind power P wind and the mechanical power P m can be expressed as…”

A statistical algorithm for predicting the energy storage capacity for baseload wind power generation in the future electric grids

“…In this paper, we use the LWPR (locally weighted polynomial regression) and PSR (penalized spline regression) that are efficient methods for modelling wind turbine power curves proposed in Ref. [37]. The theoretical foundations of these two models are presented below.…”

A new Abnormal Identification Method of Wind Turbine Apply for Dealing with Big Data

“…By analyzing the data distribution of wind speed and power attributes, the power curve is accurately modeled by machine learning method, and the abnormal points are deviated from the normal range of power curve to achieve abnormal recognition [7][8]. A multi-dimensional clustering method called WPMCLU was proposed to identify the abnormal data of wind turbine [9].…”