Conditional Variational Autoencoder Informed Probabilistic Wind Power Curve Modeling
- 7 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 14 (4) , 2445-2460
Abstract
In this paper, a conditional variational autoencoder based method is proposed for the probabilistic wind power curve modeling task. To advance the modeling performance, the latent random variable is introduced to characterize underlying weather and wind turbine conditions. The infinite Gaussian mixture model is adopted to better model the asymmetric and heterogeneous conditional distribution of the wind power given the wind speed. The conditional variational autoencoder is composed of an encoder and a decoder network. The encoder infers the state of the latent random variable given the wind speed and wind power, while the decoder learns the observational conditional distribution of the wind power given the wind speed and latent variable. With a well-trained conditional variational autoencoder, the conditional probability density function of the wind power could be estimated through the decoder network by sampling the latent random variable from its prior distribution. Wind turbine supervisory control and data acquisition datasets are used in experiments to validate advantages of the proposed method. Experimental results show that the proposed method outperforms other benchmarking deterministic and probabilistic wind power curve models with the lower continuous ranked probability score and more reliable and sharper prediction intervals. Experiments also reflect the better robustness of the conditional variational autoencoder to data pre-processed using univariate or multivariate inputs, as well as its superiority and potential for the wind power estimation considering multivariate inputs.Keywords
Funding Information
- Innovation and Technology Fund Midstream Research Programme
- Universities Project of Hong Kong Innovation and Technology Commission (ITS/034/22MS)
- National Natural Science Foundation of China (52007160)
- Guangdong Provincial Basic and Applied Basic Research - Offshore Wind Power Joint Fund (2022A1515240066)
- CityU HK Strategic Research (7005692)
This publication has 33 references indexed in Scilit:
- Review on probabilistic forecasting of wind power generationRenewable and Sustainable Energy Reviews, 2014
- Particle swarm optimization for construction of neural network-based prediction intervalsNeurocomputing, 2014
- A comprehensive review on wind turbine power curve modeling techniquesRenewable and Sustainable Energy Reviews, 2014
- Using Conditional Kernel Density Estimation for Wind Power Density ForecastingJournal of the American Statistical Association, 2012
- Accounting for the speed shear in wind turbine power performance measurementWind Energy, 2011
- Features and performance of some outlier detection methodsJournal of Applied Statistics, 2011
- On-line monitoring of power curvesRenewable Energy, 2009
- Local linear regression with adaptive orthogonal fitting for the wind power applicationStatistics and Computing, 2007
- Strictly Proper Scoring Rules, Prediction, and EstimationJournal of the American Statistical Association, 2007
- A tutorial on support vector regressionStatistics and Computing, 2004