Using the lasso method for space-time short-term wind speed predictions

TL;DR

This paper introduces a flexible multivariate model for high-resolution short-term wind speed forecasting that leverages spatial data and employs advanced shrinkage methods like lasso, significantly improving forecast accuracy.

Contribution

It proposes a novel high-resolution spatial-temporal wind speed prediction model using a periodic vector autoregressive approach combined with re-weighted lasso and elastic net for efficient variable selection.

Findings

Spatial data integration greatly improves forecast accuracy.

Re-weighted lasso and elastic net effectively handle large explanatory variable sets.

Model outperforms existing benchmarks in out-of-sample tests.

Abstract

Accurate wind power forecasts depend on reliable wind speed forecasts. Numerical Weather Predictions (NWPs) utilize huge amounts of computing time, but still have rather low spatial and temporal resolution. However, stochastic wind speed forecasts perform well in rather high temporal resolution settings. They consume comparably little computing resources and return reliable forecasts, if forecasting horizons are not too long. In the recent literature, spatial interdependence is increasingly taken into consideration. In this paper we propose a new and quite flexible multivariate model that accounts for neighbouring weather stations' information and as such, exploits spatial data at a high resolution. The model is applied to forecasting horizons of up to one day and is capable of handling a high resolution temporal structure. We use a periodic vector autoregressive model with seasonal lags to account for the interaction of the explanatory variables. Periodicity is considered and is modelled by cubic B-splines. Due to the model's flexibility, the number of explanatory variables becomes huge. Therefore, we utilize time-saving shrinkage methods like lasso and elastic net for estimation. Particularly, a relatively newly developed iteratively re-weighted lasso and elastic net is applied that also incorporates heteroscedasticity. We compare our model to several benchmarks. The out-of-sample forecasting results show that the exploitation of spatial information increases the forecasting accuracy tremendously, in comparison to models in use so far.