Tackling Missing Values in Probabilistic Wind Power Forecasting: A Generative Approach
This addresses a practical problem for wind power forecasting practitioners by improving accuracy in handling sensor failures, though it is incremental as it builds on existing probabilistic forecasting techniques.
The paper tackles missing values in probabilistic wind power forecasting by proposing a generative model that jointly predicts missing values and forecasting targets, avoiding preprocessing errors and achieving better performance in continuous ranked probability score compared to traditional impute-then-predict methods.
Machine learning techniques have been successfully used in probabilistic wind power forecasting. However, the issue of missing values within datasets due to sensor failure, for instance, has been overlooked for a long time. Although it is natural to consider addressing this issue by imputing missing values before model estimation and forecasting, we suggest treating missing values and forecasting targets indifferently and predicting all unknown values simultaneously based on observations. In this paper, we offer an efficient probabilistic forecasting approach by estimating the joint distribution of features and targets based on a generative model. It is free of preprocessing, and thus avoids introducing potential errors. Compared with the traditional "impute, then predict" pipeline, the proposed approach achieves better performance in terms of continuous ranked probability score.