Data Science for Wind Energy
Additive Multiplicative Kernel Regression
Power curve comparison
Percentage weighted difference between power curves
Covariate Matching
Energy decomposition for wind turbine performance comparison
Function comparison using Gaussian Process and Hypothesis testing
Power imputation
KNN : Fit
KNN : Predict
KNN : Update
predict from temporal Gaussian process
Smoothing spline Anova method
SVM based power curve modelling
Data synchronization
temporal Gaussian process
Updating data in a model
Update the data in a tempGP object
xgboost based power curve modelling
Data science methods used in wind energy applications. Current functionalities include creating a multi-dimensional power curve model, performing power curve function comparison, covariate matching, and energy decomposition. Relevant works for the developed functions are: funGP() - Prakash et al. (2022) <doi:10.1080/00401706.2021.1905073>, AMK() - Lee et al. (2015) <doi:10.1080/01621459.2014.977385>, tempGP() - Prakash et al. (2022) <doi:10.1080/00401706.2022.2069158>, ComparePCurve() - Ding et al. (2021) <doi:10.1016/j.renene.2021.02.136>, deltaEnergy() - Latiffianti et al. (2022) <doi:10.1002/we.2722>, syncSize() - Latiffianti et al. (2022) <doi:10.1002/we.2722>, imptPower() - Latiffianti et al. (2022) <doi:10.1002/we.2722>, All other functions - Ding (2019, ISBN:9780429956508).
Useful links