An Empirical Analysis of Constrained Support Vector Quantile Regression for Nonparametric Probabilistic Forecasting of Wind Power
This work addresses uncertainty analysis for wind power forecasting in smart grids, offering incremental improvements over existing methods by preventing overlapping quantile estimates.
The paper tackled the problem of probabilistic forecasting for wind power by proposing a constrained support vector quantile regression method, which achieved significantly better performance than three benchmark models in terms of pinball loss and reliability measures for prediction intervals.
Uncertainty analysis in the form of probabilistic forecasting can provide significant improvements in decision-making processes in the smart power grid for better integrating renewable energies such as wind. Whereas point forecasting provides a single expected value, probabilistic forecasts provide more information in the form of quantiles, prediction intervals, or full predictive densities. This paper analyzes the effectiveness of an approach for nonparametric probabilistic forecasting of wind power that combines support vector machines and nonlinear quantile regression with non-crossing constraints. A numerical case study is conducted using publicly available wind data from the Global Energy Forecasting Competition 2014. Multiple quantiles are estimated to form 20%, 40%, 60% and 80% prediction intervals which are evaluated using the pinball loss function and reliability measures. Three benchmark models are used for comparison where results demonstrate the proposed approach leads to significantly better performance while preventing the problem of overlapping quantile estimates.