Accounting for Environmental Conditions in Data-Driven Wind Turbine Power Models

Abstract

Continuous assessment of wind turbine performance is a key to maximising power generation at a very low cost. A wind turbine power curve is a non-linear function between power output and wind speed and is widely used to approach numerous problems linked to turbine operation. According to the current IEC standard, power curves are determined by a data reduction method, called binning, where hub height, wind speed and air density are considered as appropriate input parameters. However, as turbine rotors have grown in size over recent years, the impact of variations in wind speed, and thus of power output, can no longer be overlooked. Two environmental variables, namely wind shear and turbulence intensity, have the greatest impact on power output. Therefore, taking account of these factors may improve the accuracy as well as reduce the uncertainty of data-driven power curve models, which could be helpful in performance monitoring applications. This paper aims to quantify and analyse the impact of these two environmental factors on wind turbine power curves.Gaussian process (GP) is a data-driven, nonparametric based approach to power curve modelling that can incorporate these two additional environmental factors. The proposed technique's effectiveness is trained and validated using historical 10-minute average supervisory control and data acquisition (SCADA) datasets from variable speed, pitch control, and wind turbines rated at 2.5 MW. The results suggest that (i) the inclusion of the additional environmental parameters increases GP model accuracy and reduces uncertainty in estimating the power curve; (ii) a comparative study reveals that turbulence intensity has a relatively greater impact on GP model accuracy, together with uncertainty as compared to blade pitch angle. These conclusions are confirmed using performance error metrics and uncertainty calculations. The results have practical beneficial consequences for O&M related activities such as early failure detection.

Renewable Energy for Sustainable Development Goal of Clean and Affordable Energy

“…The methodology proposed by Gao et al, can be applied to quantify the cost of variability of wind power and address the intermittency for different geographical regions worldwide [51]. Systematic technological developments further improve the efficiency of the wind power plants [52][53][54]. Utilizing a combination of artificial intelligence and metaheuristic algorithms results in higher performance compared to using only classic methods.…”

Data-Driven wind turbine performance assessment and quantification using SCADA data and field measurements

“…AMK became the foundation enabling the Kernel PLUS comparison in Lee et al (2015b). Various more machine learning methods were attempted to build the power curve using a turbine's operational data, including trees (Barber and Nordborg, 2020;Lee et al, 2015a, CART or BART), support vector machine Astolfi et al, 2021, SVM), knearest neighborhood (Yesilbudak et al, 2013, kNN), gradient boost (Barber et al, 2022b), smoothing spline (Ding, 2019, SSANOVA), deep neural network (Karami et al, 2021, DNN), Gaussian process Pandit et al, 2022;Prakash et al, 2022b) and ensembles of multivariate polynomial regressions (Cascianelli et al, 2021). Chapter 5 of Ding (2019) provides an in-depth discussion of research challenges and data science solution techniques in modeling wind turbine power curves and Barber et al (2022b) provides a comparison among four machine learning methods (kNN, random forest, gradient boost, and ANN).…”

“…A common practice is the assumption of a normal distribution for the uncertainty. However, Gonzalez et al (2019) have shown that model errors are heteroskedastic and concluded that probabilistic models, such as Gaussian processes (Prakash et al, 2022a;Pandit et al, 2022) and AMK (Lee et al, 2015a), are more suitable in identifying the Ding (2019); the results of tempGP and SVM are obtained using the DSWE R package (Kumar et al, 2020); and DNN is obtained using the DSWE Python package (Kumar et al, 2022). normal bounds of turbine performance, allowing for uncertainty quantification for power curve comparisons.…”

Data‐driven models for predicting remaining useful life of high‐speed shaft bearings in wind turbines using vibration signal analysis and sparrow search algorithm

“…However, most of these turbines are located in remote mountainous areas or offshore, which poses significant challenges in transporting and hoisting the large components. The traditional method of waiting for system failure before replacing failed parts results in long downtime and puts enormous pressure on maintenance staff and standby parts inventory, increasing operating costs and ultimately affecting the Levelized Cost of Energy (LCoE) 2 . The cost of operation and maintenance (O&M) is a significant portion of the total annual wind turbine cost, with O&M accounting for 20%–25% of the LCoE 3,4 .…”