Supervised learning of intra-daily recourse strategies for generation management under uncertainties

Author

Cornélusse, Bertrand ; Vignal, Gérald ; Defourny, Boris ; Wehenkel, Louis

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Univ. of Liege, Liege, Belgium

fYear

2009

Firstpage

1

Lastpage

8

Abstract

The aim of this work is to design intra-daily recourse strategies which may be used by operators to decide in real-time the modifications to bring to planned generation schedules of a set of units in order to respond to deviations from the forecasted operating scenario. Our aim is to design strategies that are interpretable by human operators, that comply with real-time constraints and that cover the major disturbances that may appear during the next day. To this end we propose a new framework using supervised learning to infer such recourse strategies from simulations of the system under a sample of conditions representing possible deviations from the forecast. This framework is validated on a realistic generation system of medium size.

Keywords

learning (artificial intelligence); load forecasting; power engineering computing; power generation planning; power generation scheduling; power system management; forecasted operating scenario; generation management; generation planning; intra-daily recourse strategies; machine learning; mixed integer linear programming; planned generation schedules; supervised learning; uncertainty management; Conference management; Economic forecasting; Energy management; Humans; Power generation; Predictive models; Processor scheduling; Scheduling algorithm; Supervised learning; Uncertainty; Mixed integer linear programming; generation planning; machine learning; uncertainty management;

fLanguage

English

Publisher

ieee

Conference_Titel

PowerTech, 2009 IEEE Bucharest

Conference_Location

Bucharest

Print_ISBN

978-1-4244-2234-0

Electronic_ISBN

978-1-4244-2235-7

Type

conf

DOI

10.1109/PTC.2009.5282226

Filename

5282226