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

Browell, J. and Gilbert, C. (2017) Cluster-based Regime-switching AR for the EEM 2017 Wind Power Forecasting Competition. In: 2017 14th International Conference on the European Energy Market (EEM), Dresden, Germany, 06-09 Jun 2017, ISBN 9781509054992 (doi: 10.1109/EEM.2017.7982034)

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.

• Item Type: Conference Proceedings
• Additional Information: Jethro Browell is supported by the University of Strathclyde's EPSRC Doctoral Prize, grant number EP/M508159/1, and Ciaran Gilbert by the University of Strathclyde's EPSRC Centre for Doctoral Training in Wind and Marine Energy Systems, grant number EP/L016680/1.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Browell, Dr Jethro
• Authors: Browell, J., and Gilbert, C.
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• ISSN: 2165-4093
• ISBN: 9781509054992
• Data DOI: 10. 15129/01f10e89-3a33-4437-8b2e-9b53c70dad4f