Forecasting wind power - Modeling periodic and non-linear effects under conditional heteroscedasticity

TL;DR

This paper introduces a novel joint modeling approach for wind speed and power forecasting that combines advanced time series models with regularization techniques, enabling accurate short- to medium-term predictions efficiently.

Contribution

It presents a combined TVARMA and power-TGARCH model with a high-dimensional lasso approach for fast, accurate wind power forecasting considering periodic and non-linear effects.

Findings

Accurate wind power forecasts up to 48 hours ahead.

Efficient modeling with high-dimensional shrinkage techniques.

Incorporation of periodicity and non-linear impacts improves forecast quality.

Abstract

In this article we present an approach that enables joint wind speed and wind power forecasts for a wind park. We combine a multivariate seasonal time varying threshold autoregressive moving average (TVARMA) model with a power threshold generalized autoregressive conditional heteroscedastic (power-TGARCH) model. The modeling framework incorporates diurnal and annual periodicity modeling by periodic B-splines, conditional heteroscedasticity and a complex autoregressive structure with non-linear impacts. In contrast to usually time-consuming estimation approaches as likelihood estimation, we apply a high-dimensional shrinkage technique. We utilize an iteratively re-weighted least absolute shrinkage and selection operator (lasso) technique. It allows for conditional heteroscedasticity, provides fast computing times and guarantees a parsimonious and regularized specification, even though the parameter space may be vast. We are able to show that our approach provides accurate forecasts of wind power at a turbine-specific level for forecasting horizons of up to 48 h (short- to medium-term forecasts).