Cluster-based regime-switching AR for the EEM 2017 Wind Power Forecasting Competition

Browell, Jethro and Gilbert, Ciaran P (2017) Cluster-based regime-switching AR for the EEM 2017 Wind Power Forecasting Competition. In: 2017 14th International Conference on the European Electricity Market Conference (EEM). IEEE, Piscataway. ISBN 9781509054992 (In Press)

[img]
Preview
Text (Browell-Gilbert-EEM-2017-Cluster-based-regime-switching-AR-for-the-EEM-2017-Wind-Power-Forecasting-Competition)
cluster_based_regime_4_.pdf
Accepted Author Manuscript

Download (587kB)| Preview

    Abstract

    This paper describes the regime-switching autoregressive models used to win the EEM 2017 Wind Power Forecasting Competition. The competition required participants to produce daily forecast wind power production for a portfolio of wind farms from 2 to 38 hours-ahead based on historic generation and numerical weather prediction analysis data only. The regimes used in the methodology presented are defined on the previous day’s weather conditions using the k-medians clustering algorithm. Cross-validation is used to identify models with the best predictive power from a pool of candidate models. The final methodology produced a final weighted mean absolute error 4.5% lower than the second place team during the two-week competition period.