Wind energy forecasting with missing values within a fully conditional specification framework
Authors:
Preprint
Abstract
Wind power forecasting is essential to power system operation and electricity markets. As abundant data became available thanks to the deployment of measurement infrastructures and the democratization of meteorological modelling, extensive data-driven approaches have been developed within both point and probabilistic forecasting frameworks. These models usually assume that the dataset at hand is complete and overlook missing value issues that often occur in practice. In contrast to that common approach, we rigorously consider here the wind power forecasting problem in the presence of missing values, by jointly accommodating imputation and forecasting tasks. Our approach allows inferring the joint distribution of input features and target variables at the model estimation stage based on incomplete observations only. We place emphasis on a fully conditional specification method owing to its desirable properties, e.g., being assumption-free when it comes to these joint distributions. Then, at the operational forecasting stage, with available features at hand, one can issue forecasts by implicitly imputing all missing entries. The approach is applicable to both point and probabilistic forecasting, while yielding competitive forecast quality within both simulation and real-world case studies. It confirms that by using a powerful universal imputation method like fully conditional specification, the proposed approach is superior to the common approach, especially in the context of probabilistic forecasting.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Missing data in wind farm time series: Properties and effect on forecastsElectric Power Systems Research, 2020
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- Online adaptive lasso estimation in vector autoregressive models for high dimensional wind power forecastingInternational Journal of Forecasting, 2019
- Wind power prediction with missing data using Gaussian process regression and multiple imputationApplied Soft Computing, 2018
- Elements of Nonlinear Time Series Analysis and Forecasting2017
- LASSO vector autoregression structures for very short‐term wind power forecastingWind Energy, 2016
- Probabilistic gradient boosting machines for GEFCom2014 wind forecastingInternational Journal of Forecasting, 2016
- Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyondInternational Journal of Forecasting, 2016
- The Wind Integration National Dataset (WIND) ToolkitApplied Energy, 2015
- Reliability diagrams for non‐parametric density forecasts of continuous variables: Accounting for serial correlationQuarterly Journal of the Royal Meteorological Society, 2010